* [PATCH qemu v18 05/16] target/riscv: rvv: Add tail agnostic for vv instructions
2022-05-13 11:49 [PATCH qemu v18 00/16] Add tail agnostic behavior for rvv instructions ~eopxd
@ 2022-05-13 11:50 ` ~eopxd
2022-05-13 11:50 ` ~eopxd
` (15 subsequent siblings)
16 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-03-01 9:07 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
According to v-spec, tail agnostic behavior can be either kept as
undisturbed or set elements' bits to all 1s. To distinguish the
difference of tail policies, QEMU should be able to simulate the tail
agnostic behavior as "set tail elements' bits to all 1s".
There are multiple possibility for agnostic elements according to
v-spec. The main intent of this patch-set tries to add option that
can distinguish between tail policies. Setting agnostic elements to
all 1s allows QEMU to express this.
This is the first commit regarding the optional tail agnostic
behavior. Follow-up commits will add this optional behavior
for all rvv instructions.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/cpu.h | 2 +
target/riscv/cpu_helper.c | 2 +
target/riscv/insn_trans/trans_rvv.c.inc | 3 +-
target/riscv/internals.h | 5 +-
target/riscv/translate.c | 2 +
target/riscv/vector_helper.c | 295 +++++++++++++-----------
6 files changed, 177 insertions(+), 132 deletions(-)
diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h
index fe6c9a2c92..61552408b5 100644
--- a/target/riscv/cpu.h
+++ b/target/riscv/cpu.h
@@ -405,6 +405,7 @@ struct RISCVCPUConfig {
bool ext_zhinxmin;
bool ext_zve32f;
bool ext_zve64f;
+ bool rvv_ta_all_1s;
uint32_t mvendorid;
uint64_t marchid;
@@ -557,6 +558,7 @@ FIELD(TB_FLAGS, XL, 20, 2)
/* If PointerMasking should be applied */
FIELD(TB_FLAGS, PM_MASK_ENABLED, 22, 1)
FIELD(TB_FLAGS, PM_BASE_ENABLED, 23, 1)
+FIELD(TB_FLAGS, VTA, 24, 1)
#ifdef TARGET_RISCV32
#define riscv_cpu_mxl(env) ((void)(env), MXL_RV32)
diff --git a/target/riscv/cpu_helper.c b/target/riscv/cpu_helper.c
index e1aa4f2097..c0641b63cc 100644
--- a/target/riscv/cpu_helper.c
+++ b/target/riscv/cpu_helper.c
@@ -65,6 +65,8 @@ void cpu_get_tb_cpu_state(CPURISCVState *env, target_ulong *pc,
flags = FIELD_DP32(flags, TB_FLAGS, LMUL,
FIELD_EX64(env->vtype, VTYPE, VLMUL));
flags = FIELD_DP32(flags, TB_FLAGS, VL_EQ_VLMAX, vl_eq_vlmax);
+ flags = FIELD_DP32(flags, TB_FLAGS, VTA,
+ FIELD_EX64(env->vtype, VTYPE, VTA));
} else {
flags = FIELD_DP32(flags, TB_FLAGS, VILL, 1);
}
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index 4d5dfa794a..efdf5d6d81 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -1227,7 +1227,7 @@ do_opivv_gvec(DisasContext *s, arg_rmrr *a, GVecGen3Fn *gvec_fn,
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
- if (a->vm && s->vl_eq_vlmax) {
+ if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
gvec_fn(s->sew, vreg_ofs(s, a->rd),
vreg_ofs(s, a->rs2), vreg_ofs(s, a->rs1),
MAXSZ(s), MAXSZ(s));
@@ -1236,6 +1236,7 @@ do_opivv_gvec(DisasContext *s, arg_rmrr *a, GVecGen3Fn *gvec_fn,
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),
vreg_ofs(s, a->rs1), vreg_ofs(s, a->rs2),
cpu_env, s->cfg_ptr->vlen / 8,
diff --git a/target/riscv/internals.h b/target/riscv/internals.h
index dbb322bfa7..512c6c30cf 100644
--- a/target/riscv/internals.h
+++ b/target/riscv/internals.h
@@ -24,8 +24,9 @@
/* share data between vector helpers and decode code */
FIELD(VDATA, VM, 0, 1)
FIELD(VDATA, LMUL, 1, 3)
-FIELD(VDATA, NF, 4, 4)
-FIELD(VDATA, WD, 4, 1)
+FIELD(VDATA, VTA, 4, 1)
+FIELD(VDATA, NF, 5, 4)
+FIELD(VDATA, WD, 5, 1)
/* float point classify helpers */
target_ulong fclass_h(uint64_t frs1);
diff --git a/target/riscv/translate.c b/target/riscv/translate.c
index 0cd1d9ee94..832353be54 100644
--- a/target/riscv/translate.c
+++ b/target/riscv/translate.c
@@ -94,6 +94,7 @@ typedef struct DisasContext {
*/
int8_t lmul;
uint8_t sew;
+ uint8_t vta;
target_ulong vstart;
bool vl_eq_vlmax;
uint8_t ntemp;
@@ -1091,6 +1092,7 @@ static void riscv_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs)
ctx->vill = FIELD_EX32(tb_flags, TB_FLAGS, VILL);
ctx->sew = FIELD_EX32(tb_flags, TB_FLAGS, SEW);
ctx->lmul = sextract32(FIELD_EX32(tb_flags, TB_FLAGS, LMUL), 0, 3);
+ ctx->vta = FIELD_EX32(tb_flags, TB_FLAGS, VTA) && cpu->cfg.rvv_ta_all_1s;
ctx->vstart = env->vstart;
ctx->vl_eq_vlmax = FIELD_EX32(tb_flags, TB_FLAGS, VL_EQ_VLMAX);
ctx->misa_mxl_max = env->misa_mxl_max;
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 3b79b9cbc2..2248f0cbee 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -122,6 +122,11 @@ static inline int32_t vext_lmul(uint32_t desc)
return sextract32(FIELD_EX32(simd_data(desc), VDATA, LMUL), 0, 3);
}
+static inline uint32_t vext_vta(uint32_t desc)
+{
+ return FIELD_EX32(simd_data(desc), VDATA, VTA);
+}
+
/*
* Get the maximum number of elements can be operated.
*
@@ -140,6 +145,20 @@ static inline uint32_t vext_max_elems(uint32_t desc, uint32_t log2_esz)
return scale < 0 ? vlenb >> -scale : vlenb << scale;
}
+/*
+ * Get number of total elements, including prestart, body and tail elements.
+ * Note that when LMUL < 1, the tail includes the elements past VLMAX that
+ * are held in the same vector register.
+ */
+static inline uint32_t vext_get_total_elems(CPURISCVState *env, uint32_t desc, uint32_t esz)
+{
+ uint32_t vlenb = simd_maxsz(desc);
+ uint32_t sew = 1 << FIELD_EX64(env->vtype, VTYPE, VSEW);
+ int8_t emul = ctzl(esz) - ctzl(sew) + vext_lmul(desc) < 0 ? 0 :
+ ctzl(esz) - ctzl(sew) + vext_lmul(desc);
+ return (vlenb << emul) / esz;
+}
+
static inline target_ulong adjust_addr(CPURISCVState *env, target_ulong addr)
{
return (addr & env->cur_pmmask) | env->cur_pmbase;
@@ -172,6 +191,20 @@ static void probe_pages(CPURISCVState *env, target_ulong addr,
}
}
+/* set agnostic elements to 1s */
+static void vext_set_elems_1s(void *base, uint32_t is_agnostic, uint32_t cnt,
+ uint32_t tot)
+{
+ if (is_agnostic == 0) {
+ /* policy undisturbed */
+ return;
+ }
+ if (tot - cnt == 0) {
+ return ;
+ }
+ memset(base + cnt, -1, tot - cnt);
+}
+
static inline void vext_set_elem_mask(void *v0, int index,
uint8_t value)
{
@@ -707,10 +740,12 @@ RVVCALL(OPIVV2, vsub_vv_d, OP_SSS_D, H8, H8, H8, DO_SUB)
static void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2,
CPURISCVState *env, uint32_t desc,
- opivv2_fn *fn)
+ opivv2_fn *fn, uint32_t esz)
{
uint32_t vm = vext_vm(desc);
uint32_t vl = env->vl;
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+ uint32_t vta = vext_vta(desc);
uint32_t i;
for (i = env->vstart; i < vl; i++) {
@@ -720,26 +755,28 @@ static void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2,
fn(vd, vs1, vs2, i);
}
env->vstart = 0;
+ /* set tail elements to 1s */
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz);
}
/* generate the helpers for OPIVV */
-#define GEN_VEXT_VV(NAME) \
+#define GEN_VEXT_VV(NAME, ESZ) \
void HELPER(NAME)(void *vd, void *v0, void *vs1, \
void *vs2, CPURISCVState *env, \
uint32_t desc) \
{ \
do_vext_vv(vd, v0, vs1, vs2, env, desc, \
- do_##NAME); \
+ do_##NAME, ESZ); \
}
-GEN_VEXT_VV(vadd_vv_b)
-GEN_VEXT_VV(vadd_vv_h)
-GEN_VEXT_VV(vadd_vv_w)
-GEN_VEXT_VV(vadd_vv_d)
-GEN_VEXT_VV(vsub_vv_b)
-GEN_VEXT_VV(vsub_vv_h)
-GEN_VEXT_VV(vsub_vv_w)
-GEN_VEXT_VV(vsub_vv_d)
+GEN_VEXT_VV(vadd_vv_b, 1)
+GEN_VEXT_VV(vadd_vv_h, 2)
+GEN_VEXT_VV(vadd_vv_w, 4)
+GEN_VEXT_VV(vadd_vv_d, 8)
+GEN_VEXT_VV(vsub_vv_b, 1)
+GEN_VEXT_VV(vsub_vv_h, 2)
+GEN_VEXT_VV(vsub_vv_w, 4)
+GEN_VEXT_VV(vsub_vv_d, 8)
typedef void opivx2_fn(void *vd, target_long s1, void *vs2, int i);
@@ -884,30 +921,30 @@ RVVCALL(OPIVV2, vwadd_wv_w, WOP_WSSS_W, H8, H4, H4, DO_ADD)
RVVCALL(OPIVV2, vwsub_wv_b, WOP_WSSS_B, H2, H1, H1, DO_SUB)
RVVCALL(OPIVV2, vwsub_wv_h, WOP_WSSS_H, H4, H2, H2, DO_SUB)
RVVCALL(OPIVV2, vwsub_wv_w, WOP_WSSS_W, H8, H4, H4, DO_SUB)
-GEN_VEXT_VV(vwaddu_vv_b)
-GEN_VEXT_VV(vwaddu_vv_h)
-GEN_VEXT_VV(vwaddu_vv_w)
-GEN_VEXT_VV(vwsubu_vv_b)
-GEN_VEXT_VV(vwsubu_vv_h)
-GEN_VEXT_VV(vwsubu_vv_w)
-GEN_VEXT_VV(vwadd_vv_b)
-GEN_VEXT_VV(vwadd_vv_h)
-GEN_VEXT_VV(vwadd_vv_w)
-GEN_VEXT_VV(vwsub_vv_b)
-GEN_VEXT_VV(vwsub_vv_h)
-GEN_VEXT_VV(vwsub_vv_w)
-GEN_VEXT_VV(vwaddu_wv_b)
-GEN_VEXT_VV(vwaddu_wv_h)
-GEN_VEXT_VV(vwaddu_wv_w)
-GEN_VEXT_VV(vwsubu_wv_b)
-GEN_VEXT_VV(vwsubu_wv_h)
-GEN_VEXT_VV(vwsubu_wv_w)
-GEN_VEXT_VV(vwadd_wv_b)
-GEN_VEXT_VV(vwadd_wv_h)
-GEN_VEXT_VV(vwadd_wv_w)
-GEN_VEXT_VV(vwsub_wv_b)
-GEN_VEXT_VV(vwsub_wv_h)
-GEN_VEXT_VV(vwsub_wv_w)
+GEN_VEXT_VV(vwaddu_vv_b, 2)
+GEN_VEXT_VV(vwaddu_vv_h, 4)
+GEN_VEXT_VV(vwaddu_vv_w, 8)
+GEN_VEXT_VV(vwsubu_vv_b, 2)
+GEN_VEXT_VV(vwsubu_vv_h, 4)
+GEN_VEXT_VV(vwsubu_vv_w, 8)
+GEN_VEXT_VV(vwadd_vv_b, 2)
+GEN_VEXT_VV(vwadd_vv_h, 4)
+GEN_VEXT_VV(vwadd_vv_w, 8)
+GEN_VEXT_VV(vwsub_vv_b, 2)
+GEN_VEXT_VV(vwsub_vv_h, 4)
+GEN_VEXT_VV(vwsub_vv_w, 8)
+GEN_VEXT_VV(vwaddu_wv_b, 2)
+GEN_VEXT_VV(vwaddu_wv_h, 4)
+GEN_VEXT_VV(vwaddu_wv_w, 8)
+GEN_VEXT_VV(vwsubu_wv_b, 2)
+GEN_VEXT_VV(vwsubu_wv_h, 4)
+GEN_VEXT_VV(vwsubu_wv_w, 8)
+GEN_VEXT_VV(vwadd_wv_b, 2)
+GEN_VEXT_VV(vwadd_wv_h, 4)
+GEN_VEXT_VV(vwadd_wv_w, 8)
+GEN_VEXT_VV(vwsub_wv_b, 2)
+GEN_VEXT_VV(vwsub_wv_h, 4)
+GEN_VEXT_VV(vwsub_wv_w, 8)
RVVCALL(OPIVX2, vwaddu_vx_b, WOP_UUU_B, H2, H1, DO_ADD)
RVVCALL(OPIVX2, vwaddu_vx_h, WOP_UUU_H, H4, H2, DO_ADD)
@@ -1086,18 +1123,18 @@ RVVCALL(OPIVV2, vxor_vv_b, OP_SSS_B, H1, H1, H1, DO_XOR)
RVVCALL(OPIVV2, vxor_vv_h, OP_SSS_H, H2, H2, H2, DO_XOR)
RVVCALL(OPIVV2, vxor_vv_w, OP_SSS_W, H4, H4, H4, DO_XOR)
RVVCALL(OPIVV2, vxor_vv_d, OP_SSS_D, H8, H8, H8, DO_XOR)
-GEN_VEXT_VV(vand_vv_b)
-GEN_VEXT_VV(vand_vv_h)
-GEN_VEXT_VV(vand_vv_w)
-GEN_VEXT_VV(vand_vv_d)
-GEN_VEXT_VV(vor_vv_b)
-GEN_VEXT_VV(vor_vv_h)
-GEN_VEXT_VV(vor_vv_w)
-GEN_VEXT_VV(vor_vv_d)
-GEN_VEXT_VV(vxor_vv_b)
-GEN_VEXT_VV(vxor_vv_h)
-GEN_VEXT_VV(vxor_vv_w)
-GEN_VEXT_VV(vxor_vv_d)
+GEN_VEXT_VV(vand_vv_b, 1)
+GEN_VEXT_VV(vand_vv_h, 2)
+GEN_VEXT_VV(vand_vv_w, 4)
+GEN_VEXT_VV(vand_vv_d, 8)
+GEN_VEXT_VV(vor_vv_b, 1)
+GEN_VEXT_VV(vor_vv_h, 2)
+GEN_VEXT_VV(vor_vv_w, 4)
+GEN_VEXT_VV(vor_vv_d, 8)
+GEN_VEXT_VV(vxor_vv_b, 1)
+GEN_VEXT_VV(vxor_vv_h, 2)
+GEN_VEXT_VV(vxor_vv_w, 4)
+GEN_VEXT_VV(vxor_vv_d, 8)
RVVCALL(OPIVX2, vand_vx_b, OP_SSS_B, H1, H1, DO_AND)
RVVCALL(OPIVX2, vand_vx_h, OP_SSS_H, H2, H2, DO_AND)
@@ -1343,22 +1380,22 @@ RVVCALL(OPIVV2, vmax_vv_b, OP_SSS_B, H1, H1, H1, DO_MAX)
RVVCALL(OPIVV2, vmax_vv_h, OP_SSS_H, H2, H2, H2, DO_MAX)
RVVCALL(OPIVV2, vmax_vv_w, OP_SSS_W, H4, H4, H4, DO_MAX)
RVVCALL(OPIVV2, vmax_vv_d, OP_SSS_D, H8, H8, H8, DO_MAX)
-GEN_VEXT_VV(vminu_vv_b)
-GEN_VEXT_VV(vminu_vv_h)
-GEN_VEXT_VV(vminu_vv_w)
-GEN_VEXT_VV(vminu_vv_d)
-GEN_VEXT_VV(vmin_vv_b)
-GEN_VEXT_VV(vmin_vv_h)
-GEN_VEXT_VV(vmin_vv_w)
-GEN_VEXT_VV(vmin_vv_d)
-GEN_VEXT_VV(vmaxu_vv_b)
-GEN_VEXT_VV(vmaxu_vv_h)
-GEN_VEXT_VV(vmaxu_vv_w)
-GEN_VEXT_VV(vmaxu_vv_d)
-GEN_VEXT_VV(vmax_vv_b)
-GEN_VEXT_VV(vmax_vv_h)
-GEN_VEXT_VV(vmax_vv_w)
-GEN_VEXT_VV(vmax_vv_d)
+GEN_VEXT_VV(vminu_vv_b, 1)
+GEN_VEXT_VV(vminu_vv_h, 2)
+GEN_VEXT_VV(vminu_vv_w, 4)
+GEN_VEXT_VV(vminu_vv_d, 8)
+GEN_VEXT_VV(vmin_vv_b, 1)
+GEN_VEXT_VV(vmin_vv_h, 2)
+GEN_VEXT_VV(vmin_vv_w, 4)
+GEN_VEXT_VV(vmin_vv_d, 8)
+GEN_VEXT_VV(vmaxu_vv_b, 1)
+GEN_VEXT_VV(vmaxu_vv_h, 2)
+GEN_VEXT_VV(vmaxu_vv_w, 4)
+GEN_VEXT_VV(vmaxu_vv_d, 8)
+GEN_VEXT_VV(vmax_vv_b, 1)
+GEN_VEXT_VV(vmax_vv_h, 2)
+GEN_VEXT_VV(vmax_vv_w, 4)
+GEN_VEXT_VV(vmax_vv_d, 8)
RVVCALL(OPIVX2, vminu_vx_b, OP_UUU_B, H1, H1, DO_MIN)
RVVCALL(OPIVX2, vminu_vx_h, OP_UUU_H, H2, H2, DO_MIN)
@@ -1399,10 +1436,10 @@ RVVCALL(OPIVV2, vmul_vv_b, OP_SSS_B, H1, H1, H1, DO_MUL)
RVVCALL(OPIVV2, vmul_vv_h, OP_SSS_H, H2, H2, H2, DO_MUL)
RVVCALL(OPIVV2, vmul_vv_w, OP_SSS_W, H4, H4, H4, DO_MUL)
RVVCALL(OPIVV2, vmul_vv_d, OP_SSS_D, H8, H8, H8, DO_MUL)
-GEN_VEXT_VV(vmul_vv_b)
-GEN_VEXT_VV(vmul_vv_h)
-GEN_VEXT_VV(vmul_vv_w)
-GEN_VEXT_VV(vmul_vv_d)
+GEN_VEXT_VV(vmul_vv_b, 1)
+GEN_VEXT_VV(vmul_vv_h, 2)
+GEN_VEXT_VV(vmul_vv_w, 4)
+GEN_VEXT_VV(vmul_vv_d, 8)
static int8_t do_mulh_b(int8_t s2, int8_t s1)
{
@@ -1506,18 +1543,18 @@ RVVCALL(OPIVV2, vmulhsu_vv_b, OP_SUS_B, H1, H1, H1, do_mulhsu_b)
RVVCALL(OPIVV2, vmulhsu_vv_h, OP_SUS_H, H2, H2, H2, do_mulhsu_h)
RVVCALL(OPIVV2, vmulhsu_vv_w, OP_SUS_W, H4, H4, H4, do_mulhsu_w)
RVVCALL(OPIVV2, vmulhsu_vv_d, OP_SUS_D, H8, H8, H8, do_mulhsu_d)
-GEN_VEXT_VV(vmulh_vv_b)
-GEN_VEXT_VV(vmulh_vv_h)
-GEN_VEXT_VV(vmulh_vv_w)
-GEN_VEXT_VV(vmulh_vv_d)
-GEN_VEXT_VV(vmulhu_vv_b)
-GEN_VEXT_VV(vmulhu_vv_h)
-GEN_VEXT_VV(vmulhu_vv_w)
-GEN_VEXT_VV(vmulhu_vv_d)
-GEN_VEXT_VV(vmulhsu_vv_b)
-GEN_VEXT_VV(vmulhsu_vv_h)
-GEN_VEXT_VV(vmulhsu_vv_w)
-GEN_VEXT_VV(vmulhsu_vv_d)
+GEN_VEXT_VV(vmulh_vv_b, 1)
+GEN_VEXT_VV(vmulh_vv_h, 2)
+GEN_VEXT_VV(vmulh_vv_w, 4)
+GEN_VEXT_VV(vmulh_vv_d, 8)
+GEN_VEXT_VV(vmulhu_vv_b, 1)
+GEN_VEXT_VV(vmulhu_vv_h, 2)
+GEN_VEXT_VV(vmulhu_vv_w, 4)
+GEN_VEXT_VV(vmulhu_vv_d, 8)
+GEN_VEXT_VV(vmulhsu_vv_b, 1)
+GEN_VEXT_VV(vmulhsu_vv_h, 2)
+GEN_VEXT_VV(vmulhsu_vv_w, 4)
+GEN_VEXT_VV(vmulhsu_vv_d, 8)
RVVCALL(OPIVX2, vmul_vx_b, OP_SSS_B, H1, H1, DO_MUL)
RVVCALL(OPIVX2, vmul_vx_h, OP_SSS_H, H2, H2, DO_MUL)
@@ -1576,22 +1613,22 @@ RVVCALL(OPIVV2, vrem_vv_b, OP_SSS_B, H1, H1, H1, DO_REM)
RVVCALL(OPIVV2, vrem_vv_h, OP_SSS_H, H2, H2, H2, DO_REM)
RVVCALL(OPIVV2, vrem_vv_w, OP_SSS_W, H4, H4, H4, DO_REM)
RVVCALL(OPIVV2, vrem_vv_d, OP_SSS_D, H8, H8, H8, DO_REM)
-GEN_VEXT_VV(vdivu_vv_b)
-GEN_VEXT_VV(vdivu_vv_h)
-GEN_VEXT_VV(vdivu_vv_w)
-GEN_VEXT_VV(vdivu_vv_d)
-GEN_VEXT_VV(vdiv_vv_b)
-GEN_VEXT_VV(vdiv_vv_h)
-GEN_VEXT_VV(vdiv_vv_w)
-GEN_VEXT_VV(vdiv_vv_d)
-GEN_VEXT_VV(vremu_vv_b)
-GEN_VEXT_VV(vremu_vv_h)
-GEN_VEXT_VV(vremu_vv_w)
-GEN_VEXT_VV(vremu_vv_d)
-GEN_VEXT_VV(vrem_vv_b)
-GEN_VEXT_VV(vrem_vv_h)
-GEN_VEXT_VV(vrem_vv_w)
-GEN_VEXT_VV(vrem_vv_d)
+GEN_VEXT_VV(vdivu_vv_b, 1)
+GEN_VEXT_VV(vdivu_vv_h, 2)
+GEN_VEXT_VV(vdivu_vv_w, 4)
+GEN_VEXT_VV(vdivu_vv_d, 8)
+GEN_VEXT_VV(vdiv_vv_b, 1)
+GEN_VEXT_VV(vdiv_vv_h, 2)
+GEN_VEXT_VV(vdiv_vv_w, 4)
+GEN_VEXT_VV(vdiv_vv_d, 8)
+GEN_VEXT_VV(vremu_vv_b, 1)
+GEN_VEXT_VV(vremu_vv_h, 2)
+GEN_VEXT_VV(vremu_vv_w, 4)
+GEN_VEXT_VV(vremu_vv_d, 8)
+GEN_VEXT_VV(vrem_vv_b, 1)
+GEN_VEXT_VV(vrem_vv_h, 2)
+GEN_VEXT_VV(vrem_vv_w, 4)
+GEN_VEXT_VV(vrem_vv_d, 8)
RVVCALL(OPIVX2, vdivu_vx_b, OP_UUU_B, H1, H1, DO_DIVU)
RVVCALL(OPIVX2, vdivu_vx_h, OP_UUU_H, H2, H2, DO_DIVU)
@@ -1636,15 +1673,15 @@ RVVCALL(OPIVV2, vwmulu_vv_w, WOP_UUU_W, H8, H4, H4, DO_MUL)
RVVCALL(OPIVV2, vwmulsu_vv_b, WOP_SUS_B, H2, H1, H1, DO_MUL)
RVVCALL(OPIVV2, vwmulsu_vv_h, WOP_SUS_H, H4, H2, H2, DO_MUL)
RVVCALL(OPIVV2, vwmulsu_vv_w, WOP_SUS_W, H8, H4, H4, DO_MUL)
-GEN_VEXT_VV(vwmul_vv_b)
-GEN_VEXT_VV(vwmul_vv_h)
-GEN_VEXT_VV(vwmul_vv_w)
-GEN_VEXT_VV(vwmulu_vv_b)
-GEN_VEXT_VV(vwmulu_vv_h)
-GEN_VEXT_VV(vwmulu_vv_w)
-GEN_VEXT_VV(vwmulsu_vv_b)
-GEN_VEXT_VV(vwmulsu_vv_h)
-GEN_VEXT_VV(vwmulsu_vv_w)
+GEN_VEXT_VV(vwmul_vv_b, 2)
+GEN_VEXT_VV(vwmul_vv_h, 4)
+GEN_VEXT_VV(vwmul_vv_w, 8)
+GEN_VEXT_VV(vwmulu_vv_b, 2)
+GEN_VEXT_VV(vwmulu_vv_h, 4)
+GEN_VEXT_VV(vwmulu_vv_w, 8)
+GEN_VEXT_VV(vwmulsu_vv_b, 2)
+GEN_VEXT_VV(vwmulsu_vv_h, 4)
+GEN_VEXT_VV(vwmulsu_vv_w, 8)
RVVCALL(OPIVX2, vwmul_vx_b, WOP_SSS_B, H2, H1, DO_MUL)
RVVCALL(OPIVX2, vwmul_vx_h, WOP_SSS_H, H4, H2, DO_MUL)
@@ -1695,22 +1732,22 @@ RVVCALL(OPIVV3, vnmsub_vv_b, OP_SSS_B, H1, H1, H1, DO_NMSUB)
RVVCALL(OPIVV3, vnmsub_vv_h, OP_SSS_H, H2, H2, H2, DO_NMSUB)
RVVCALL(OPIVV3, vnmsub_vv_w, OP_SSS_W, H4, H4, H4, DO_NMSUB)
RVVCALL(OPIVV3, vnmsub_vv_d, OP_SSS_D, H8, H8, H8, DO_NMSUB)
-GEN_VEXT_VV(vmacc_vv_b)
-GEN_VEXT_VV(vmacc_vv_h)
-GEN_VEXT_VV(vmacc_vv_w)
-GEN_VEXT_VV(vmacc_vv_d)
-GEN_VEXT_VV(vnmsac_vv_b)
-GEN_VEXT_VV(vnmsac_vv_h)
-GEN_VEXT_VV(vnmsac_vv_w)
-GEN_VEXT_VV(vnmsac_vv_d)
-GEN_VEXT_VV(vmadd_vv_b)
-GEN_VEXT_VV(vmadd_vv_h)
-GEN_VEXT_VV(vmadd_vv_w)
-GEN_VEXT_VV(vmadd_vv_d)
-GEN_VEXT_VV(vnmsub_vv_b)
-GEN_VEXT_VV(vnmsub_vv_h)
-GEN_VEXT_VV(vnmsub_vv_w)
-GEN_VEXT_VV(vnmsub_vv_d)
+GEN_VEXT_VV(vmacc_vv_b, 1)
+GEN_VEXT_VV(vmacc_vv_h, 2)
+GEN_VEXT_VV(vmacc_vv_w, 4)
+GEN_VEXT_VV(vmacc_vv_d, 8)
+GEN_VEXT_VV(vnmsac_vv_b, 1)
+GEN_VEXT_VV(vnmsac_vv_h, 2)
+GEN_VEXT_VV(vnmsac_vv_w, 4)
+GEN_VEXT_VV(vnmsac_vv_d, 8)
+GEN_VEXT_VV(vmadd_vv_b, 1)
+GEN_VEXT_VV(vmadd_vv_h, 2)
+GEN_VEXT_VV(vmadd_vv_w, 4)
+GEN_VEXT_VV(vmadd_vv_d, 8)
+GEN_VEXT_VV(vnmsub_vv_b, 1)
+GEN_VEXT_VV(vnmsub_vv_h, 2)
+GEN_VEXT_VV(vnmsub_vv_w, 4)
+GEN_VEXT_VV(vnmsub_vv_d, 8)
#define OPIVX3(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \
static void do_##NAME(void *vd, target_long s1, void *vs2, int i) \
@@ -1763,15 +1800,15 @@ RVVCALL(OPIVV3, vwmacc_vv_w, WOP_SSS_W, H8, H4, H4, DO_MACC)
RVVCALL(OPIVV3, vwmaccsu_vv_b, WOP_SSU_B, H2, H1, H1, DO_MACC)
RVVCALL(OPIVV3, vwmaccsu_vv_h, WOP_SSU_H, H4, H2, H2, DO_MACC)
RVVCALL(OPIVV3, vwmaccsu_vv_w, WOP_SSU_W, H8, H4, H4, DO_MACC)
-GEN_VEXT_VV(vwmaccu_vv_b)
-GEN_VEXT_VV(vwmaccu_vv_h)
-GEN_VEXT_VV(vwmaccu_vv_w)
-GEN_VEXT_VV(vwmacc_vv_b)
-GEN_VEXT_VV(vwmacc_vv_h)
-GEN_VEXT_VV(vwmacc_vv_w)
-GEN_VEXT_VV(vwmaccsu_vv_b)
-GEN_VEXT_VV(vwmaccsu_vv_h)
-GEN_VEXT_VV(vwmaccsu_vv_w)
+GEN_VEXT_VV(vwmaccu_vv_b, 2)
+GEN_VEXT_VV(vwmaccu_vv_h, 4)
+GEN_VEXT_VV(vwmaccu_vv_w, 8)
+GEN_VEXT_VV(vwmacc_vv_b, 2)
+GEN_VEXT_VV(vwmacc_vv_h, 4)
+GEN_VEXT_VV(vwmacc_vv_w, 8)
+GEN_VEXT_VV(vwmaccsu_vv_b, 2)
+GEN_VEXT_VV(vwmaccsu_vv_h, 4)
+GEN_VEXT_VV(vwmaccsu_vv_w, 8)
RVVCALL(OPIVX3, vwmaccu_vx_b, WOP_UUU_B, H2, H1, DO_MACC)
RVVCALL(OPIVX3, vwmaccu_vx_h, WOP_UUU_H, H4, H2, DO_MACC)
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 06/16] target/riscv: rvv: Add tail agnostic for vector load / store instructions
2022-05-13 11:49 [PATCH qemu v18 00/16] Add tail agnostic behavior for rvv instructions ~eopxd
@ 2022-05-13 11:50 ` ~eopxd
2022-05-13 11:50 ` ~eopxd
` (15 subsequent siblings)
16 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-03-07 7:10 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
Destination register of unit-stride mask load and store instructions are
always written with a tail-agnostic policy.
A vector segment load / store instruction may contain fractional lmul
with nf * lmul > 1. The rest of the elements in the last register should
be treated as tail elements.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/insn_trans/trans_rvv.c.inc | 6 +++
target/riscv/translate.c | 2 +
target/riscv/vector_helper.c | 60 +++++++++++++++++++++++++
3 files changed, 68 insertions(+)
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index efdf5d6d81..4da06b859b 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -711,6 +711,7 @@ static bool ld_us_op(DisasContext *s, arg_r2nfvm *a, uint8_t eew)
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, emul);
data = FIELD_DP32(data, VDATA, NF, a->nf);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
return ldst_us_trans(a->rd, a->rs1, data, fn, s, false);
}
@@ -774,6 +775,8 @@ static bool ld_us_mask_op(DisasContext *s, arg_vlm_v *a, uint8_t eew)
/* EMUL = 1, NFIELDS = 1 */
data = FIELD_DP32(data, VDATA, LMUL, 0);
data = FIELD_DP32(data, VDATA, NF, 1);
+ /* Mask destination register are always tail-agnostic */
+ data = FIELD_DP32(data, VDATA, VTA, s->cfg_vta_all_1s);
return ldst_us_trans(a->rd, a->rs1, data, fn, s, false);
}
@@ -862,6 +865,7 @@ static bool ld_stride_op(DisasContext *s, arg_rnfvm *a, uint8_t eew)
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, emul);
data = FIELD_DP32(data, VDATA, NF, a->nf);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
return ldst_stride_trans(a->rd, a->rs1, a->rs2, data, fn, s, false);
}
@@ -991,6 +995,7 @@ static bool ld_index_op(DisasContext *s, arg_rnfvm *a, uint8_t eew)
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, emul);
data = FIELD_DP32(data, VDATA, NF, a->nf);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
return ldst_index_trans(a->rd, a->rs1, a->rs2, data, fn, s, false);
}
@@ -1108,6 +1113,7 @@ static bool ldff_op(DisasContext *s, arg_r2nfvm *a, uint8_t eew)
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, emul);
data = FIELD_DP32(data, VDATA, NF, a->nf);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
return ldff_trans(a->rd, a->rs1, data, fn, s);
}
diff --git a/target/riscv/translate.c b/target/riscv/translate.c
index 832353be54..384ffcc0fa 100644
--- a/target/riscv/translate.c
+++ b/target/riscv/translate.c
@@ -95,6 +95,7 @@ typedef struct DisasContext {
int8_t lmul;
uint8_t sew;
uint8_t vta;
+ bool cfg_vta_all_1s;
target_ulong vstart;
bool vl_eq_vlmax;
uint8_t ntemp;
@@ -1093,6 +1094,7 @@ static void riscv_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs)
ctx->sew = FIELD_EX32(tb_flags, TB_FLAGS, SEW);
ctx->lmul = sextract32(FIELD_EX32(tb_flags, TB_FLAGS, LMUL), 0, 3);
ctx->vta = FIELD_EX32(tb_flags, TB_FLAGS, VTA) && cpu->cfg.rvv_ta_all_1s;
+ ctx->cfg_vta_all_1s = cpu->cfg.rvv_ta_all_1s;
ctx->vstart = env->vstart;
ctx->vl_eq_vlmax = FIELD_EX32(tb_flags, TB_FLAGS, VL_EQ_VLMAX);
ctx->misa_mxl_max = env->misa_mxl_max;
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 2248f0cbee..cb14c321ea 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -269,6 +269,9 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base,
uint32_t i, k;
uint32_t nf = vext_nf(desc);
uint32_t max_elems = vext_max_elems(desc, log2_esz);
+ uint32_t esz = 1 << log2_esz;
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+ uint32_t vta = vext_vta(desc);
for (i = env->vstart; i < env->vl; i++, env->vstart++) {
if (!vm && !vext_elem_mask(v0, i)) {
@@ -283,6 +286,18 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base,
}
}
env->vstart = 0;
+ /* set tail elements to 1s */
+ for (k = 0; k < nf; ++k) {
+ vext_set_elems_1s(vd, vta, (k * max_elems + env->vl) * esz,
+ (k * max_elems + max_elems) * esz);
+ }
+ if (nf * max_elems % total_elems != 0) {
+ uint32_t vlenb = env_archcpu(env)->cfg.vlen >> 3;
+ uint32_t registers_used =
+ ((nf * max_elems) * esz + (vlenb - 1)) / vlenb;
+ vext_set_elems_1s(vd, vta, (nf * max_elems) * esz,
+ registers_used * vlenb);
+ }
}
#define GEN_VEXT_LD_STRIDE(NAME, ETYPE, LOAD_FN) \
@@ -328,6 +343,9 @@ vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
uint32_t i, k;
uint32_t nf = vext_nf(desc);
uint32_t max_elems = vext_max_elems(desc, log2_esz);
+ uint32_t esz = 1 << log2_esz;
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+ uint32_t vta = vext_vta(desc);
/* load bytes from guest memory */
for (i = env->vstart; i < evl; i++, env->vstart++) {
@@ -339,6 +357,18 @@ vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
}
}
env->vstart = 0;
+ /* set tail elements to 1s */
+ for (k = 0; k < nf; ++k) {
+ vext_set_elems_1s(vd, vta, (k * max_elems + evl) * esz,
+ (k * max_elems + max_elems) * esz);
+ }
+ if (nf * max_elems % total_elems != 0) {
+ uint32_t vlenb = env_archcpu(env)->cfg.vlen >> 3;
+ uint32_t registers_used =
+ ((nf * max_elems) * esz + (vlenb - 1)) / vlenb;
+ vext_set_elems_1s(vd, vta, (nf * max_elems) * esz,
+ registers_used * vlenb);
+ }
}
/*
@@ -438,6 +468,9 @@ vext_ldst_index(void *vd, void *v0, target_ulong base,
uint32_t nf = vext_nf(desc);
uint32_t vm = vext_vm(desc);
uint32_t max_elems = vext_max_elems(desc, log2_esz);
+ uint32_t esz = 1 << log2_esz;
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+ uint32_t vta = vext_vta(desc);
/* load bytes from guest memory */
for (i = env->vstart; i < env->vl; i++, env->vstart++) {
@@ -453,6 +486,18 @@ vext_ldst_index(void *vd, void *v0, target_ulong base,
}
}
env->vstart = 0;
+ /* set tail elements to 1s */
+ for (k = 0; k < nf; ++k) {
+ vext_set_elems_1s(vd, vta, (k * max_elems + env->vl) * esz,
+ (k * max_elems + max_elems) * esz);
+ }
+ if (nf * max_elems % total_elems != 0) {
+ uint32_t vlenb = env_archcpu(env)->cfg.vlen >> 3;
+ uint32_t registers_used =
+ ((nf * max_elems) * esz + (vlenb - 1)) / vlenb;
+ vext_set_elems_1s(vd, vta, (nf * max_elems) * esz,
+ registers_used * vlenb);
+ }
}
#define GEN_VEXT_LD_INDEX(NAME, ETYPE, INDEX_FN, LOAD_FN) \
@@ -520,6 +565,9 @@ vext_ldff(void *vd, void *v0, target_ulong base,
uint32_t nf = vext_nf(desc);
uint32_t vm = vext_vm(desc);
uint32_t max_elems = vext_max_elems(desc, log2_esz);
+ uint32_t esz = 1 << log2_esz;
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+ uint32_t vta = vext_vta(desc);
target_ulong addr, offset, remain;
/* probe every access*/
@@ -575,6 +623,18 @@ ProbeSuccess:
}
}
env->vstart = 0;
+ /* set tail elements to 1s */
+ for (k = 0; k < nf; ++k) {
+ vext_set_elems_1s(vd, vta, (k * max_elems + env->vl) * esz,
+ (k * max_elems + max_elems) * esz);
+ }
+ if (nf * max_elems % total_elems != 0) {
+ uint32_t vlenb = env_archcpu(env)->cfg.vlen >> 3;
+ uint32_t registers_used =
+ ((nf * max_elems) * esz + (vlenb - 1)) / vlenb;
+ vext_set_elems_1s(vd, vta, (nf * max_elems) * esz,
+ registers_used * vlenb);
+ }
}
#define GEN_VEXT_LDFF(NAME, ETYPE, LOAD_FN) \
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 07/16] target/riscv: rvv: Add tail agnostic for vx, vvm, vxm instructions
2022-05-13 11:49 [PATCH qemu v18 00/16] Add tail agnostic behavior for rvv instructions ~eopxd
@ 2022-05-13 11:50 ` ~eopxd
2022-05-13 11:50 ` ~eopxd
` (15 subsequent siblings)
16 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-03-07 7:32 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
`vmadc` and `vmsbc` produces a mask value, they always operate with
a tail agnostic policy.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/insn_trans/trans_rvv.c.inc | 13 +-
target/riscv/internals.h | 5 +-
target/riscv/vector_helper.c | 314 +++++++++++++-----------
3 files changed, 190 insertions(+), 142 deletions(-)
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index 4da06b859b..81f227f074 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -1289,6 +1289,8 @@ static bool opivx_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, uint32_t vm,
data = FIELD_DP32(data, VDATA, VM, vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
+ data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);
desc = tcg_constant_i32(simd_desc(s->cfg_ptr->vlen / 8,
s->cfg_ptr->vlen / 8, data));
@@ -1324,7 +1326,7 @@ do_opivx_gvec(DisasContext *s, arg_rmrr *a, GVecGen2sFn *gvec_fn,
return false;
}
- if (a->vm && s->vl_eq_vlmax) {
+ if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
TCGv_i64 src1 = tcg_temp_new_i64();
tcg_gen_ext_tl_i64(src1, get_gpr(s, a->rs1, EXT_SIGN));
@@ -1454,6 +1456,8 @@ static bool opivi_trans(uint32_t vd, uint32_t imm, uint32_t vs2, uint32_t vm,
data = FIELD_DP32(data, VDATA, VM, vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
+ data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);
desc = tcg_constant_i32(simd_desc(s->cfg_ptr->vlen / 8,
s->cfg_ptr->vlen / 8, data));
@@ -1482,7 +1486,7 @@ do_opivi_gvec(DisasContext *s, arg_rmrr *a, GVecGen2iFn *gvec_fn,
return false;
}
- if (a->vm && s->vl_eq_vlmax) {
+ if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
gvec_fn(s->sew, vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2),
extract_imm(s, a->rs1, imm_mode), MAXSZ(s), MAXSZ(s));
mark_vs_dirty(s);
@@ -1536,6 +1540,7 @@ static bool do_opivv_widen(DisasContext *s, arg_rmrr *a,
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),
vreg_ofs(s, a->rs1),
vreg_ofs(s, a->rs2),
@@ -1617,6 +1622,7 @@ static bool do_opiwv_widen(DisasContext *s, arg_rmrr *a,
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),
vreg_ofs(s, a->rs1),
vreg_ofs(s, a->rs2),
@@ -1695,6 +1701,9 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
+ data = \
+ FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);\
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs1), \
vreg_ofs(s, a->rs2), cpu_env, \
diff --git a/target/riscv/internals.h b/target/riscv/internals.h
index 512c6c30cf..193ce57a6d 100644
--- a/target/riscv/internals.h
+++ b/target/riscv/internals.h
@@ -25,8 +25,9 @@
FIELD(VDATA, VM, 0, 1)
FIELD(VDATA, LMUL, 1, 3)
FIELD(VDATA, VTA, 4, 1)
-FIELD(VDATA, NF, 5, 4)
-FIELD(VDATA, WD, 5, 1)
+FIELD(VDATA, VTA_ALL_1S, 5, 1)
+FIELD(VDATA, NF, 6, 4)
+FIELD(VDATA, WD, 6, 1)
/* float point classify helpers */
target_ulong fclass_h(uint64_t frs1);
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index cb14c321ea..3bcde37e28 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -127,6 +127,11 @@ static inline uint32_t vext_vta(uint32_t desc)
return FIELD_EX32(simd_data(desc), VDATA, VTA);
}
+static inline uint32_t vext_vta_all_1s(uint32_t desc)
+{
+ return FIELD_EX32(simd_data(desc), VDATA, VTA_ALL_1S);
+}
+
/*
* Get the maximum number of elements can be operated.
*
@@ -866,10 +871,12 @@ RVVCALL(OPIVX2, vrsub_vx_d, OP_SSS_D, H8, H8, DO_RSUB)
static void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2,
CPURISCVState *env, uint32_t desc,
- opivx2_fn fn)
+ opivx2_fn fn, uint32_t esz)
{
uint32_t vm = vext_vm(desc);
uint32_t vl = env->vl;
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+ uint32_t vta = vext_vta(desc);
uint32_t i;
for (i = env->vstart; i < vl; i++) {
@@ -879,30 +886,32 @@ static void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2,
fn(vd, s1, vs2, i);
}
env->vstart = 0;
+ /* set tail elements to 1s */
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz);
}
/* generate the helpers for OPIVX */
-#define GEN_VEXT_VX(NAME) \
+#define GEN_VEXT_VX(NAME, ESZ) \
void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
void *vs2, CPURISCVState *env, \
uint32_t desc) \
{ \
do_vext_vx(vd, v0, s1, vs2, env, desc, \
- do_##NAME); \
-}
-
-GEN_VEXT_VX(vadd_vx_b)
-GEN_VEXT_VX(vadd_vx_h)
-GEN_VEXT_VX(vadd_vx_w)
-GEN_VEXT_VX(vadd_vx_d)
-GEN_VEXT_VX(vsub_vx_b)
-GEN_VEXT_VX(vsub_vx_h)
-GEN_VEXT_VX(vsub_vx_w)
-GEN_VEXT_VX(vsub_vx_d)
-GEN_VEXT_VX(vrsub_vx_b)
-GEN_VEXT_VX(vrsub_vx_h)
-GEN_VEXT_VX(vrsub_vx_w)
-GEN_VEXT_VX(vrsub_vx_d)
+ do_##NAME, ESZ); \
+}
+
+GEN_VEXT_VX(vadd_vx_b, 1)
+GEN_VEXT_VX(vadd_vx_h, 2)
+GEN_VEXT_VX(vadd_vx_w, 4)
+GEN_VEXT_VX(vadd_vx_d, 8)
+GEN_VEXT_VX(vsub_vx_b, 1)
+GEN_VEXT_VX(vsub_vx_h, 2)
+GEN_VEXT_VX(vsub_vx_w, 4)
+GEN_VEXT_VX(vsub_vx_d, 8)
+GEN_VEXT_VX(vrsub_vx_b, 1)
+GEN_VEXT_VX(vrsub_vx_h, 2)
+GEN_VEXT_VX(vrsub_vx_w, 4)
+GEN_VEXT_VX(vrsub_vx_d, 8)
void HELPER(vec_rsubs8)(void *d, void *a, uint64_t b, uint32_t desc)
{
@@ -1030,30 +1039,30 @@ RVVCALL(OPIVX2, vwadd_wx_w, WOP_WSSS_W, H8, H4, DO_ADD)
RVVCALL(OPIVX2, vwsub_wx_b, WOP_WSSS_B, H2, H1, DO_SUB)
RVVCALL(OPIVX2, vwsub_wx_h, WOP_WSSS_H, H4, H2, DO_SUB)
RVVCALL(OPIVX2, vwsub_wx_w, WOP_WSSS_W, H8, H4, DO_SUB)
-GEN_VEXT_VX(vwaddu_vx_b)
-GEN_VEXT_VX(vwaddu_vx_h)
-GEN_VEXT_VX(vwaddu_vx_w)
-GEN_VEXT_VX(vwsubu_vx_b)
-GEN_VEXT_VX(vwsubu_vx_h)
-GEN_VEXT_VX(vwsubu_vx_w)
-GEN_VEXT_VX(vwadd_vx_b)
-GEN_VEXT_VX(vwadd_vx_h)
-GEN_VEXT_VX(vwadd_vx_w)
-GEN_VEXT_VX(vwsub_vx_b)
-GEN_VEXT_VX(vwsub_vx_h)
-GEN_VEXT_VX(vwsub_vx_w)
-GEN_VEXT_VX(vwaddu_wx_b)
-GEN_VEXT_VX(vwaddu_wx_h)
-GEN_VEXT_VX(vwaddu_wx_w)
-GEN_VEXT_VX(vwsubu_wx_b)
-GEN_VEXT_VX(vwsubu_wx_h)
-GEN_VEXT_VX(vwsubu_wx_w)
-GEN_VEXT_VX(vwadd_wx_b)
-GEN_VEXT_VX(vwadd_wx_h)
-GEN_VEXT_VX(vwadd_wx_w)
-GEN_VEXT_VX(vwsub_wx_b)
-GEN_VEXT_VX(vwsub_wx_h)
-GEN_VEXT_VX(vwsub_wx_w)
+GEN_VEXT_VX(vwaddu_vx_b, 2)
+GEN_VEXT_VX(vwaddu_vx_h, 4)
+GEN_VEXT_VX(vwaddu_vx_w, 8)
+GEN_VEXT_VX(vwsubu_vx_b, 2)
+GEN_VEXT_VX(vwsubu_vx_h, 4)
+GEN_VEXT_VX(vwsubu_vx_w, 8)
+GEN_VEXT_VX(vwadd_vx_b, 2)
+GEN_VEXT_VX(vwadd_vx_h, 4)
+GEN_VEXT_VX(vwadd_vx_w, 8)
+GEN_VEXT_VX(vwsub_vx_b, 2)
+GEN_VEXT_VX(vwsub_vx_h, 4)
+GEN_VEXT_VX(vwsub_vx_w, 8)
+GEN_VEXT_VX(vwaddu_wx_b, 2)
+GEN_VEXT_VX(vwaddu_wx_h, 4)
+GEN_VEXT_VX(vwaddu_wx_w, 8)
+GEN_VEXT_VX(vwsubu_wx_b, 2)
+GEN_VEXT_VX(vwsubu_wx_h, 4)
+GEN_VEXT_VX(vwsubu_wx_w, 8)
+GEN_VEXT_VX(vwadd_wx_b, 2)
+GEN_VEXT_VX(vwadd_wx_h, 4)
+GEN_VEXT_VX(vwadd_wx_w, 8)
+GEN_VEXT_VX(vwsub_wx_b, 2)
+GEN_VEXT_VX(vwsub_wx_h, 4)
+GEN_VEXT_VX(vwsub_wx_w, 8)
/* Vector Integer Add-with-Carry / Subtract-with-Borrow Instructions */
#define DO_VADC(N, M, C) (N + M + C)
@@ -1064,6 +1073,10 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = \
+ vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -1074,6 +1087,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
*((ETYPE *)vd + H(i)) = DO_OP(s2, s1, carry); \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VEXT_VADC_VVM(vadc_vvm_b, uint8_t, H1, DO_VADC)
@@ -1091,6 +1106,9 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -1100,6 +1118,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
*((ETYPE *)vd + H(i)) = DO_OP(s2, (ETYPE)(target_long)s1, carry);\
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VEXT_VADC_VXM(vadc_vxm_b, uint8_t, H1, DO_VADC)
@@ -1122,6 +1142,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
{ \
uint32_t vl = env->vl; \
uint32_t vm = vext_vm(desc); \
+ uint32_t total_elems = env_archcpu(env)->cfg.vlen; \
+ uint32_t vta_all_1s = vext_vta_all_1s(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -1131,6 +1153,13 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
vext_set_elem_mask(vd, i, DO_OP(s2, s1, carry)); \
} \
env->vstart = 0; \
+ /* mask destination register are always tail-agnostic */ \
+ /* set tail elements to 1s */ \
+ if (vta_all_1s) { \
+ for (; i < total_elems; i++) { \
+ vext_set_elem_mask(vd, i, 1); \
+ } \
+ } \
}
GEN_VEXT_VMADC_VVM(vmadc_vvm_b, uint8_t, H1, DO_MADC)
@@ -1149,6 +1178,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
{ \
uint32_t vl = env->vl; \
uint32_t vm = vext_vm(desc); \
+ uint32_t total_elems = env_archcpu(env)->cfg.vlen; \
+ uint32_t vta_all_1s = vext_vta_all_1s(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -1158,6 +1189,13 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
DO_OP(s2, (ETYPE)(target_long)s1, carry)); \
} \
env->vstart = 0; \
+ /* mask destination register are always tail-agnostic */ \
+ /* set tail elements to 1s */ \
+ if (vta_all_1s) { \
+ for (; i < total_elems; i++) { \
+ vext_set_elem_mask(vd, i, 1); \
+ } \
+ } \
}
GEN_VEXT_VMADC_VXM(vmadc_vxm_b, uint8_t, H1, DO_MADC)
@@ -1208,18 +1246,18 @@ RVVCALL(OPIVX2, vxor_vx_b, OP_SSS_B, H1, H1, DO_XOR)
RVVCALL(OPIVX2, vxor_vx_h, OP_SSS_H, H2, H2, DO_XOR)
RVVCALL(OPIVX2, vxor_vx_w, OP_SSS_W, H4, H4, DO_XOR)
RVVCALL(OPIVX2, vxor_vx_d, OP_SSS_D, H8, H8, DO_XOR)
-GEN_VEXT_VX(vand_vx_b)
-GEN_VEXT_VX(vand_vx_h)
-GEN_VEXT_VX(vand_vx_w)
-GEN_VEXT_VX(vand_vx_d)
-GEN_VEXT_VX(vor_vx_b)
-GEN_VEXT_VX(vor_vx_h)
-GEN_VEXT_VX(vor_vx_w)
-GEN_VEXT_VX(vor_vx_d)
-GEN_VEXT_VX(vxor_vx_b)
-GEN_VEXT_VX(vxor_vx_h)
-GEN_VEXT_VX(vxor_vx_w)
-GEN_VEXT_VX(vxor_vx_d)
+GEN_VEXT_VX(vand_vx_b, 1)
+GEN_VEXT_VX(vand_vx_h, 2)
+GEN_VEXT_VX(vand_vx_w, 4)
+GEN_VEXT_VX(vand_vx_d, 8)
+GEN_VEXT_VX(vor_vx_b, 1)
+GEN_VEXT_VX(vor_vx_h, 2)
+GEN_VEXT_VX(vor_vx_w, 4)
+GEN_VEXT_VX(vor_vx_d, 8)
+GEN_VEXT_VX(vxor_vx_b, 1)
+GEN_VEXT_VX(vxor_vx_h, 2)
+GEN_VEXT_VX(vxor_vx_w, 4)
+GEN_VEXT_VX(vxor_vx_d, 8)
/* Vector Single-Width Bit Shift Instructions */
#define DO_SLL(N, M) (N << (M))
@@ -1473,22 +1511,22 @@ RVVCALL(OPIVX2, vmax_vx_b, OP_SSS_B, H1, H1, DO_MAX)
RVVCALL(OPIVX2, vmax_vx_h, OP_SSS_H, H2, H2, DO_MAX)
RVVCALL(OPIVX2, vmax_vx_w, OP_SSS_W, H4, H4, DO_MAX)
RVVCALL(OPIVX2, vmax_vx_d, OP_SSS_D, H8, H8, DO_MAX)
-GEN_VEXT_VX(vminu_vx_b)
-GEN_VEXT_VX(vminu_vx_h)
-GEN_VEXT_VX(vminu_vx_w)
-GEN_VEXT_VX(vminu_vx_d)
-GEN_VEXT_VX(vmin_vx_b)
-GEN_VEXT_VX(vmin_vx_h)
-GEN_VEXT_VX(vmin_vx_w)
-GEN_VEXT_VX(vmin_vx_d)
-GEN_VEXT_VX(vmaxu_vx_b)
-GEN_VEXT_VX(vmaxu_vx_h)
-GEN_VEXT_VX(vmaxu_vx_w)
-GEN_VEXT_VX(vmaxu_vx_d)
-GEN_VEXT_VX(vmax_vx_b)
-GEN_VEXT_VX(vmax_vx_h)
-GEN_VEXT_VX(vmax_vx_w)
-GEN_VEXT_VX(vmax_vx_d)
+GEN_VEXT_VX(vminu_vx_b, 1)
+GEN_VEXT_VX(vminu_vx_h, 2)
+GEN_VEXT_VX(vminu_vx_w, 4)
+GEN_VEXT_VX(vminu_vx_d, 8)
+GEN_VEXT_VX(vmin_vx_b, 1)
+GEN_VEXT_VX(vmin_vx_h, 2)
+GEN_VEXT_VX(vmin_vx_w, 4)
+GEN_VEXT_VX(vmin_vx_d, 8)
+GEN_VEXT_VX(vmaxu_vx_b, 1)
+GEN_VEXT_VX(vmaxu_vx_h, 2)
+GEN_VEXT_VX(vmaxu_vx_w, 4)
+GEN_VEXT_VX(vmaxu_vx_d, 8)
+GEN_VEXT_VX(vmax_vx_b, 1)
+GEN_VEXT_VX(vmax_vx_h, 2)
+GEN_VEXT_VX(vmax_vx_w, 4)
+GEN_VEXT_VX(vmax_vx_d, 8)
/* Vector Single-Width Integer Multiply Instructions */
#define DO_MUL(N, M) (N * M)
@@ -1632,22 +1670,22 @@ RVVCALL(OPIVX2, vmulhsu_vx_b, OP_SUS_B, H1, H1, do_mulhsu_b)
RVVCALL(OPIVX2, vmulhsu_vx_h, OP_SUS_H, H2, H2, do_mulhsu_h)
RVVCALL(OPIVX2, vmulhsu_vx_w, OP_SUS_W, H4, H4, do_mulhsu_w)
RVVCALL(OPIVX2, vmulhsu_vx_d, OP_SUS_D, H8, H8, do_mulhsu_d)
-GEN_VEXT_VX(vmul_vx_b)
-GEN_VEXT_VX(vmul_vx_h)
-GEN_VEXT_VX(vmul_vx_w)
-GEN_VEXT_VX(vmul_vx_d)
-GEN_VEXT_VX(vmulh_vx_b)
-GEN_VEXT_VX(vmulh_vx_h)
-GEN_VEXT_VX(vmulh_vx_w)
-GEN_VEXT_VX(vmulh_vx_d)
-GEN_VEXT_VX(vmulhu_vx_b)
-GEN_VEXT_VX(vmulhu_vx_h)
-GEN_VEXT_VX(vmulhu_vx_w)
-GEN_VEXT_VX(vmulhu_vx_d)
-GEN_VEXT_VX(vmulhsu_vx_b)
-GEN_VEXT_VX(vmulhsu_vx_h)
-GEN_VEXT_VX(vmulhsu_vx_w)
-GEN_VEXT_VX(vmulhsu_vx_d)
+GEN_VEXT_VX(vmul_vx_b, 1)
+GEN_VEXT_VX(vmul_vx_h, 2)
+GEN_VEXT_VX(vmul_vx_w, 4)
+GEN_VEXT_VX(vmul_vx_d, 8)
+GEN_VEXT_VX(vmulh_vx_b, 1)
+GEN_VEXT_VX(vmulh_vx_h, 2)
+GEN_VEXT_VX(vmulh_vx_w, 4)
+GEN_VEXT_VX(vmulh_vx_d, 8)
+GEN_VEXT_VX(vmulhu_vx_b, 1)
+GEN_VEXT_VX(vmulhu_vx_h, 2)
+GEN_VEXT_VX(vmulhu_vx_w, 4)
+GEN_VEXT_VX(vmulhu_vx_d, 8)
+GEN_VEXT_VX(vmulhsu_vx_b, 1)
+GEN_VEXT_VX(vmulhsu_vx_h, 2)
+GEN_VEXT_VX(vmulhsu_vx_w, 4)
+GEN_VEXT_VX(vmulhsu_vx_d, 8)
/* Vector Integer Divide Instructions */
#define DO_DIVU(N, M) (unlikely(M == 0) ? (__typeof(N))(-1) : N / M)
@@ -1706,22 +1744,22 @@ RVVCALL(OPIVX2, vrem_vx_b, OP_SSS_B, H1, H1, DO_REM)
RVVCALL(OPIVX2, vrem_vx_h, OP_SSS_H, H2, H2, DO_REM)
RVVCALL(OPIVX2, vrem_vx_w, OP_SSS_W, H4, H4, DO_REM)
RVVCALL(OPIVX2, vrem_vx_d, OP_SSS_D, H8, H8, DO_REM)
-GEN_VEXT_VX(vdivu_vx_b)
-GEN_VEXT_VX(vdivu_vx_h)
-GEN_VEXT_VX(vdivu_vx_w)
-GEN_VEXT_VX(vdivu_vx_d)
-GEN_VEXT_VX(vdiv_vx_b)
-GEN_VEXT_VX(vdiv_vx_h)
-GEN_VEXT_VX(vdiv_vx_w)
-GEN_VEXT_VX(vdiv_vx_d)
-GEN_VEXT_VX(vremu_vx_b)
-GEN_VEXT_VX(vremu_vx_h)
-GEN_VEXT_VX(vremu_vx_w)
-GEN_VEXT_VX(vremu_vx_d)
-GEN_VEXT_VX(vrem_vx_b)
-GEN_VEXT_VX(vrem_vx_h)
-GEN_VEXT_VX(vrem_vx_w)
-GEN_VEXT_VX(vrem_vx_d)
+GEN_VEXT_VX(vdivu_vx_b, 1)
+GEN_VEXT_VX(vdivu_vx_h, 2)
+GEN_VEXT_VX(vdivu_vx_w, 4)
+GEN_VEXT_VX(vdivu_vx_d, 8)
+GEN_VEXT_VX(vdiv_vx_b, 1)
+GEN_VEXT_VX(vdiv_vx_h, 2)
+GEN_VEXT_VX(vdiv_vx_w, 4)
+GEN_VEXT_VX(vdiv_vx_d, 8)
+GEN_VEXT_VX(vremu_vx_b, 1)
+GEN_VEXT_VX(vremu_vx_h, 2)
+GEN_VEXT_VX(vremu_vx_w, 4)
+GEN_VEXT_VX(vremu_vx_d, 8)
+GEN_VEXT_VX(vrem_vx_b, 1)
+GEN_VEXT_VX(vrem_vx_h, 2)
+GEN_VEXT_VX(vrem_vx_w, 4)
+GEN_VEXT_VX(vrem_vx_d, 8)
/* Vector Widening Integer Multiply Instructions */
RVVCALL(OPIVV2, vwmul_vv_b, WOP_SSS_B, H2, H1, H1, DO_MUL)
@@ -1752,15 +1790,15 @@ RVVCALL(OPIVX2, vwmulu_vx_w, WOP_UUU_W, H8, H4, DO_MUL)
RVVCALL(OPIVX2, vwmulsu_vx_b, WOP_SUS_B, H2, H1, DO_MUL)
RVVCALL(OPIVX2, vwmulsu_vx_h, WOP_SUS_H, H4, H2, DO_MUL)
RVVCALL(OPIVX2, vwmulsu_vx_w, WOP_SUS_W, H8, H4, DO_MUL)
-GEN_VEXT_VX(vwmul_vx_b)
-GEN_VEXT_VX(vwmul_vx_h)
-GEN_VEXT_VX(vwmul_vx_w)
-GEN_VEXT_VX(vwmulu_vx_b)
-GEN_VEXT_VX(vwmulu_vx_h)
-GEN_VEXT_VX(vwmulu_vx_w)
-GEN_VEXT_VX(vwmulsu_vx_b)
-GEN_VEXT_VX(vwmulsu_vx_h)
-GEN_VEXT_VX(vwmulsu_vx_w)
+GEN_VEXT_VX(vwmul_vx_b, 2)
+GEN_VEXT_VX(vwmul_vx_h, 4)
+GEN_VEXT_VX(vwmul_vx_w, 8)
+GEN_VEXT_VX(vwmulu_vx_b, 2)
+GEN_VEXT_VX(vwmulu_vx_h, 4)
+GEN_VEXT_VX(vwmulu_vx_w, 8)
+GEN_VEXT_VX(vwmulsu_vx_b, 2)
+GEN_VEXT_VX(vwmulsu_vx_h, 4)
+GEN_VEXT_VX(vwmulsu_vx_w, 8)
/* Vector Single-Width Integer Multiply-Add Instructions */
#define OPIVV3(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP) \
@@ -1833,22 +1871,22 @@ RVVCALL(OPIVX3, vnmsub_vx_b, OP_SSS_B, H1, H1, DO_NMSUB)
RVVCALL(OPIVX3, vnmsub_vx_h, OP_SSS_H, H2, H2, DO_NMSUB)
RVVCALL(OPIVX3, vnmsub_vx_w, OP_SSS_W, H4, H4, DO_NMSUB)
RVVCALL(OPIVX3, vnmsub_vx_d, OP_SSS_D, H8, H8, DO_NMSUB)
-GEN_VEXT_VX(vmacc_vx_b)
-GEN_VEXT_VX(vmacc_vx_h)
-GEN_VEXT_VX(vmacc_vx_w)
-GEN_VEXT_VX(vmacc_vx_d)
-GEN_VEXT_VX(vnmsac_vx_b)
-GEN_VEXT_VX(vnmsac_vx_h)
-GEN_VEXT_VX(vnmsac_vx_w)
-GEN_VEXT_VX(vnmsac_vx_d)
-GEN_VEXT_VX(vmadd_vx_b)
-GEN_VEXT_VX(vmadd_vx_h)
-GEN_VEXT_VX(vmadd_vx_w)
-GEN_VEXT_VX(vmadd_vx_d)
-GEN_VEXT_VX(vnmsub_vx_b)
-GEN_VEXT_VX(vnmsub_vx_h)
-GEN_VEXT_VX(vnmsub_vx_w)
-GEN_VEXT_VX(vnmsub_vx_d)
+GEN_VEXT_VX(vmacc_vx_b, 1)
+GEN_VEXT_VX(vmacc_vx_h, 2)
+GEN_VEXT_VX(vmacc_vx_w, 4)
+GEN_VEXT_VX(vmacc_vx_d, 8)
+GEN_VEXT_VX(vnmsac_vx_b, 1)
+GEN_VEXT_VX(vnmsac_vx_h, 2)
+GEN_VEXT_VX(vnmsac_vx_w, 4)
+GEN_VEXT_VX(vnmsac_vx_d, 8)
+GEN_VEXT_VX(vmadd_vx_b, 1)
+GEN_VEXT_VX(vmadd_vx_h, 2)
+GEN_VEXT_VX(vmadd_vx_w, 4)
+GEN_VEXT_VX(vmadd_vx_d, 8)
+GEN_VEXT_VX(vnmsub_vx_b, 1)
+GEN_VEXT_VX(vnmsub_vx_h, 2)
+GEN_VEXT_VX(vnmsub_vx_w, 4)
+GEN_VEXT_VX(vnmsub_vx_d, 8)
/* Vector Widening Integer Multiply-Add Instructions */
RVVCALL(OPIVV3, vwmaccu_vv_b, WOP_UUU_B, H2, H1, H1, DO_MACC)
@@ -1882,18 +1920,18 @@ RVVCALL(OPIVX3, vwmaccsu_vx_w, WOP_SSU_W, H8, H4, DO_MACC)
RVVCALL(OPIVX3, vwmaccus_vx_b, WOP_SUS_B, H2, H1, DO_MACC)
RVVCALL(OPIVX3, vwmaccus_vx_h, WOP_SUS_H, H4, H2, DO_MACC)
RVVCALL(OPIVX3, vwmaccus_vx_w, WOP_SUS_W, H8, H4, DO_MACC)
-GEN_VEXT_VX(vwmaccu_vx_b)
-GEN_VEXT_VX(vwmaccu_vx_h)
-GEN_VEXT_VX(vwmaccu_vx_w)
-GEN_VEXT_VX(vwmacc_vx_b)
-GEN_VEXT_VX(vwmacc_vx_h)
-GEN_VEXT_VX(vwmacc_vx_w)
-GEN_VEXT_VX(vwmaccsu_vx_b)
-GEN_VEXT_VX(vwmaccsu_vx_h)
-GEN_VEXT_VX(vwmaccsu_vx_w)
-GEN_VEXT_VX(vwmaccus_vx_b)
-GEN_VEXT_VX(vwmaccus_vx_h)
-GEN_VEXT_VX(vwmaccus_vx_w)
+GEN_VEXT_VX(vwmaccu_vx_b, 2)
+GEN_VEXT_VX(vwmaccu_vx_h, 4)
+GEN_VEXT_VX(vwmaccu_vx_w, 8)
+GEN_VEXT_VX(vwmacc_vx_b, 2)
+GEN_VEXT_VX(vwmacc_vx_h, 4)
+GEN_VEXT_VX(vwmacc_vx_w, 8)
+GEN_VEXT_VX(vwmaccsu_vx_b, 2)
+GEN_VEXT_VX(vwmaccsu_vx_h, 4)
+GEN_VEXT_VX(vwmaccsu_vx_w, 8)
+GEN_VEXT_VX(vwmaccus_vx_b, 2)
+GEN_VEXT_VX(vwmaccus_vx_h, 4)
+GEN_VEXT_VX(vwmaccus_vx_w, 8)
/* Vector Integer Merge and Move Instructions */
#define GEN_VEXT_VMV_VV(NAME, ETYPE, H) \
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 08/16] target/riscv: rvv: Add tail agnostic for vector integer shift instructions
2022-05-13 11:49 [PATCH qemu v18 00/16] Add tail agnostic behavior for rvv instructions ~eopxd
@ 2022-05-13 11:50 ` ~eopxd
2022-05-13 11:50 ` ~eopxd
` (15 subsequent siblings)
16 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-03-07 9:38 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/insn_trans/trans_rvv.c.inc | 3 ++-
target/riscv/vector_helper.c | 11 +++++++++++
2 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index 81f227f074..b03d459d84 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -1827,7 +1827,7 @@ do_opivx_gvec_shift(DisasContext *s, arg_rmrr *a, GVecGen2sFn32 *gvec_fn,
return false;
}
- if (a->vm && s->vl_eq_vlmax) {
+ if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
TCGv_i32 src1 = tcg_temp_new_i32();
tcg_gen_trunc_tl_i32(src1, get_gpr(s, a->rs1, EXT_NONE));
@@ -1886,6 +1886,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs1), \
vreg_ofs(s, a->rs2), cpu_env, \
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 3bcde37e28..9738c50222 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -1270,6 +1270,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(TS1); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -1281,6 +1284,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
*((TS1 *)vd + HS1(i)) = OP(s2, s1 & MASK); \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VEXT_SHIFT_VV(vsll_vv_b, uint8_t, uint8_t, H1, H1, DO_SLL, 0x7)
@@ -1305,6 +1310,10 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(TD); \
+ uint32_t total_elems = \
+ vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -1315,6 +1324,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
*((TD *)vd + HD(i)) = OP(s2, s1 & MASK); \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz);\
}
GEN_VEXT_SHIFT_VX(vsll_vx_b, uint8_t, int8_t, H1, H1, DO_SLL, 0x7)
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 09/16] target/riscv: rvv: Add tail agnostic for vector integer comparison instructions
2022-05-13 11:49 [PATCH qemu v18 00/16] Add tail agnostic behavior for rvv instructions ~eopxd
@ 2022-05-13 11:50 ` ~eopxd
2022-05-13 11:50 ` ~eopxd
` (15 subsequent siblings)
16 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-03-07 9:43 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
Compares write mask registers, and so always operate under a tail-
agnostic policy.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/vector_helper.c | 18 ++++++++++++++++++
1 file changed, 18 insertions(+)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 9738c50222..b964b01a15 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -1370,6 +1370,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t total_elems = env_archcpu(env)->cfg.vlen; \
+ uint32_t vta_all_1s = vext_vta_all_1s(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -1381,6 +1383,13 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
vext_set_elem_mask(vd, i, DO_OP(s2, s1)); \
} \
env->vstart = 0; \
+ /* mask destination register are always tail-agnostic */ \
+ /* set tail elements to 1s */ \
+ if (vta_all_1s) { \
+ for (; i < total_elems; i++) { \
+ vext_set_elem_mask(vd, i, 1); \
+ } \
+ } \
}
GEN_VEXT_CMP_VV(vmseq_vv_b, uint8_t, H1, DO_MSEQ)
@@ -1419,6 +1428,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t total_elems = env_archcpu(env)->cfg.vlen; \
+ uint32_t vta_all_1s = vext_vta_all_1s(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -1430,6 +1441,13 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
DO_OP(s2, (ETYPE)(target_long)s1)); \
} \
env->vstart = 0; \
+ /* mask destination register are always tail-agnostic */ \
+ /* set tail elements to 1s */ \
+ if (vta_all_1s) { \
+ for (; i < total_elems; i++) { \
+ vext_set_elem_mask(vd, i, 1); \
+ } \
+ } \
}
GEN_VEXT_CMP_VX(vmseq_vx_b, uint8_t, H1, DO_MSEQ)
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 10/16] target/riscv: rvv: Add tail agnostic for vector integer merge and move instructions
2022-05-13 11:49 [PATCH qemu v18 00/16] Add tail agnostic behavior for rvv instructions ~eopxd
@ 2022-05-13 11:50 ` ~eopxd
2022-05-13 11:50 ` ~eopxd
` (15 subsequent siblings)
16 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-03-07 9:53 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/insn_trans/trans_rvv.c.inc | 12 ++++++++----
target/riscv/vector_helper.c | 20 ++++++++++++++++++++
2 files changed, 28 insertions(+), 4 deletions(-)
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index b03d459d84..50f874ceae 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -2082,12 +2082,13 @@ static bool trans_vmv_v_v(DisasContext *s, arg_vmv_v_v *a)
vext_check_isa_ill(s) &&
/* vmv.v.v has rs2 = 0 and vm = 1 */
vext_check_sss(s, a->rd, a->rs1, 0, 1)) {
- if (s->vl_eq_vlmax) {
+ if (s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
tcg_gen_gvec_mov(s->sew, vreg_ofs(s, a->rd),
vreg_ofs(s, a->rs1),
MAXSZ(s), MAXSZ(s));
} else {
uint32_t data = FIELD_DP32(0, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
static gen_helper_gvec_2_ptr * const fns[4] = {
gen_helper_vmv_v_v_b, gen_helper_vmv_v_v_h,
gen_helper_vmv_v_v_w, gen_helper_vmv_v_v_d,
@@ -2122,7 +2123,7 @@ static bool trans_vmv_v_x(DisasContext *s, arg_vmv_v_x *a)
s1 = get_gpr(s, a->rs1, EXT_SIGN);
- if (s->vl_eq_vlmax) {
+ if (s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
tcg_gen_gvec_dup_tl(s->sew, vreg_ofs(s, a->rd),
MAXSZ(s), MAXSZ(s), s1);
} else {
@@ -2130,6 +2131,7 @@ static bool trans_vmv_v_x(DisasContext *s, arg_vmv_v_x *a)
TCGv_i64 s1_i64 = tcg_temp_new_i64();
TCGv_ptr dest = tcg_temp_new_ptr();
uint32_t data = FIELD_DP32(0, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
static gen_helper_vmv_vx * const fns[4] = {
gen_helper_vmv_v_x_b, gen_helper_vmv_v_x_h,
gen_helper_vmv_v_x_w, gen_helper_vmv_v_x_d,
@@ -2159,7 +2161,7 @@ static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_i *a)
/* vmv.v.i has rs2 = 0 and vm = 1 */
vext_check_ss(s, a->rd, 0, 1)) {
int64_t simm = sextract64(a->rs1, 0, 5);
- if (s->vl_eq_vlmax) {
+ if (s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
tcg_gen_gvec_dup_imm(s->sew, vreg_ofs(s, a->rd),
MAXSZ(s), MAXSZ(s), simm);
mark_vs_dirty(s);
@@ -2168,6 +2170,7 @@ static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_i *a)
TCGv_i64 s1;
TCGv_ptr dest;
uint32_t data = FIELD_DP32(0, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
static gen_helper_vmv_vx * const fns[4] = {
gen_helper_vmv_v_x_b, gen_helper_vmv_v_x_h,
gen_helper_vmv_v_x_w, gen_helper_vmv_v_x_d,
@@ -2739,7 +2742,7 @@ static bool trans_vfmv_v_f(DisasContext *s, arg_vfmv_v_f *a)
TCGv_i64 t1;
- if (s->vl_eq_vlmax) {
+ if (s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
t1 = tcg_temp_new_i64();
/* NaN-box f[rs1] */
do_nanbox(s, t1, cpu_fpr[a->rs1]);
@@ -2751,6 +2754,7 @@ static bool trans_vfmv_v_f(DisasContext *s, arg_vfmv_v_f *a)
TCGv_ptr dest;
TCGv_i32 desc;
uint32_t data = FIELD_DP32(0, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
static gen_helper_vmv_vx * const fns[3] = {
gen_helper_vmv_v_x_h,
gen_helper_vmv_v_x_w,
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index b964b01a15..2bf670920a 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -1968,6 +1968,9 @@ void HELPER(NAME)(void *vd, void *vs1, CPURISCVState *env, \
uint32_t desc) \
{ \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -1975,6 +1978,8 @@ void HELPER(NAME)(void *vd, void *vs1, CPURISCVState *env, \
*((ETYPE *)vd + H(i)) = s1; \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VEXT_VMV_VV(vmv_v_v_b, int8_t, H1)
@@ -1987,12 +1992,17 @@ void HELPER(NAME)(void *vd, uint64_t s1, CPURISCVState *env, \
uint32_t desc) \
{ \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
*((ETYPE *)vd + H(i)) = (ETYPE)s1; \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VEXT_VMV_VX(vmv_v_x_b, int8_t, H1)
@@ -2005,6 +2015,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -2012,6 +2025,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
*((ETYPE *)vd + H(i)) = *(vt + H(i)); \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VEXT_VMERGE_VV(vmerge_vvm_b, int8_t, H1)
@@ -2024,6 +2039,9 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
void *vs2, CPURISCVState *env, uint32_t desc) \
{ \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -2033,6 +2051,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
*((ETYPE *)vd + H(i)) = d; \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VEXT_VMERGE_VX(vmerge_vxm_b, int8_t, H1)
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 11/16] target/riscv: rvv: Add tail agnostic for vector fix-point arithmetic instructions
2022-05-13 11:49 [PATCH qemu v18 00/16] Add tail agnostic behavior for rvv instructions ~eopxd
@ 2022-05-13 11:50 ` ~eopxd
2022-05-13 11:50 ` ~eopxd
` (15 subsequent siblings)
16 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-03-07 10:04 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/vector_helper.c | 220 ++++++++++++++++++-----------------
1 file changed, 114 insertions(+), 106 deletions(-)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 2bf670920a..db221797c6 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -2102,10 +2102,12 @@ static inline void
vext_vv_rm_2(void *vd, void *v0, void *vs1, void *vs2,
CPURISCVState *env,
uint32_t desc,
- opivv2_rm_fn *fn)
+ opivv2_rm_fn *fn, uint32_t esz)
{
uint32_t vm = vext_vm(desc);
uint32_t vl = env->vl;
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+ uint32_t vta = vext_vta(desc);
switch (env->vxrm) {
case 0: /* rnu */
@@ -2125,15 +2127,17 @@ vext_vv_rm_2(void *vd, void *v0, void *vs1, void *vs2,
env, vl, vm, 3, fn);
break;
}
+ /* set tail elements to 1s */
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz);
}
/* generate helpers for fixed point instructions with OPIVV format */
-#define GEN_VEXT_VV_RM(NAME) \
+#define GEN_VEXT_VV_RM(NAME, ESZ) \
void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
vext_vv_rm_2(vd, v0, vs1, vs2, env, desc, \
- do_##NAME); \
+ do_##NAME, ESZ); \
}
static inline uint8_t saddu8(CPURISCVState *env, int vxrm, uint8_t a, uint8_t b)
@@ -2183,10 +2187,10 @@ RVVCALL(OPIVV2_RM, vsaddu_vv_b, OP_UUU_B, H1, H1, H1, saddu8)
RVVCALL(OPIVV2_RM, vsaddu_vv_h, OP_UUU_H, H2, H2, H2, saddu16)
RVVCALL(OPIVV2_RM, vsaddu_vv_w, OP_UUU_W, H4, H4, H4, saddu32)
RVVCALL(OPIVV2_RM, vsaddu_vv_d, OP_UUU_D, H8, H8, H8, saddu64)
-GEN_VEXT_VV_RM(vsaddu_vv_b)
-GEN_VEXT_VV_RM(vsaddu_vv_h)
-GEN_VEXT_VV_RM(vsaddu_vv_w)
-GEN_VEXT_VV_RM(vsaddu_vv_d)
+GEN_VEXT_VV_RM(vsaddu_vv_b, 1)
+GEN_VEXT_VV_RM(vsaddu_vv_h, 2)
+GEN_VEXT_VV_RM(vsaddu_vv_w, 4)
+GEN_VEXT_VV_RM(vsaddu_vv_d, 8)
typedef void opivx2_rm_fn(void *vd, target_long s1, void *vs2, int i,
CPURISCVState *env, int vxrm);
@@ -2219,10 +2223,12 @@ static inline void
vext_vx_rm_2(void *vd, void *v0, target_long s1, void *vs2,
CPURISCVState *env,
uint32_t desc,
- opivx2_rm_fn *fn)
+ opivx2_rm_fn *fn, uint32_t esz)
{
uint32_t vm = vext_vm(desc);
uint32_t vl = env->vl;
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+ uint32_t vta = vext_vta(desc);
switch (env->vxrm) {
case 0: /* rnu */
@@ -2242,25 +2248,27 @@ vext_vx_rm_2(void *vd, void *v0, target_long s1, void *vs2,
env, vl, vm, 3, fn);
break;
}
+ /* set tail elements to 1s */
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz);
}
/* generate helpers for fixed point instructions with OPIVX format */
-#define GEN_VEXT_VX_RM(NAME) \
+#define GEN_VEXT_VX_RM(NAME, ESZ) \
void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
void *vs2, CPURISCVState *env, uint32_t desc) \
{ \
vext_vx_rm_2(vd, v0, s1, vs2, env, desc, \
- do_##NAME); \
+ do_##NAME, ESZ); \
}
RVVCALL(OPIVX2_RM, vsaddu_vx_b, OP_UUU_B, H1, H1, saddu8)
RVVCALL(OPIVX2_RM, vsaddu_vx_h, OP_UUU_H, H2, H2, saddu16)
RVVCALL(OPIVX2_RM, vsaddu_vx_w, OP_UUU_W, H4, H4, saddu32)
RVVCALL(OPIVX2_RM, vsaddu_vx_d, OP_UUU_D, H8, H8, saddu64)
-GEN_VEXT_VX_RM(vsaddu_vx_b)
-GEN_VEXT_VX_RM(vsaddu_vx_h)
-GEN_VEXT_VX_RM(vsaddu_vx_w)
-GEN_VEXT_VX_RM(vsaddu_vx_d)
+GEN_VEXT_VX_RM(vsaddu_vx_b, 1)
+GEN_VEXT_VX_RM(vsaddu_vx_h, 2)
+GEN_VEXT_VX_RM(vsaddu_vx_w, 4)
+GEN_VEXT_VX_RM(vsaddu_vx_d, 8)
static inline int8_t sadd8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
{
@@ -2306,19 +2314,19 @@ RVVCALL(OPIVV2_RM, vsadd_vv_b, OP_SSS_B, H1, H1, H1, sadd8)
RVVCALL(OPIVV2_RM, vsadd_vv_h, OP_SSS_H, H2, H2, H2, sadd16)
RVVCALL(OPIVV2_RM, vsadd_vv_w, OP_SSS_W, H4, H4, H4, sadd32)
RVVCALL(OPIVV2_RM, vsadd_vv_d, OP_SSS_D, H8, H8, H8, sadd64)
-GEN_VEXT_VV_RM(vsadd_vv_b)
-GEN_VEXT_VV_RM(vsadd_vv_h)
-GEN_VEXT_VV_RM(vsadd_vv_w)
-GEN_VEXT_VV_RM(vsadd_vv_d)
+GEN_VEXT_VV_RM(vsadd_vv_b, 1)
+GEN_VEXT_VV_RM(vsadd_vv_h, 2)
+GEN_VEXT_VV_RM(vsadd_vv_w, 4)
+GEN_VEXT_VV_RM(vsadd_vv_d, 8)
RVVCALL(OPIVX2_RM, vsadd_vx_b, OP_SSS_B, H1, H1, sadd8)
RVVCALL(OPIVX2_RM, vsadd_vx_h, OP_SSS_H, H2, H2, sadd16)
RVVCALL(OPIVX2_RM, vsadd_vx_w, OP_SSS_W, H4, H4, sadd32)
RVVCALL(OPIVX2_RM, vsadd_vx_d, OP_SSS_D, H8, H8, sadd64)
-GEN_VEXT_VX_RM(vsadd_vx_b)
-GEN_VEXT_VX_RM(vsadd_vx_h)
-GEN_VEXT_VX_RM(vsadd_vx_w)
-GEN_VEXT_VX_RM(vsadd_vx_d)
+GEN_VEXT_VX_RM(vsadd_vx_b, 1)
+GEN_VEXT_VX_RM(vsadd_vx_h, 2)
+GEN_VEXT_VX_RM(vsadd_vx_w, 4)
+GEN_VEXT_VX_RM(vsadd_vx_d, 8)
static inline uint8_t ssubu8(CPURISCVState *env, int vxrm, uint8_t a, uint8_t b)
{
@@ -2367,19 +2375,19 @@ RVVCALL(OPIVV2_RM, vssubu_vv_b, OP_UUU_B, H1, H1, H1, ssubu8)
RVVCALL(OPIVV2_RM, vssubu_vv_h, OP_UUU_H, H2, H2, H2, ssubu16)
RVVCALL(OPIVV2_RM, vssubu_vv_w, OP_UUU_W, H4, H4, H4, ssubu32)
RVVCALL(OPIVV2_RM, vssubu_vv_d, OP_UUU_D, H8, H8, H8, ssubu64)
-GEN_VEXT_VV_RM(vssubu_vv_b)
-GEN_VEXT_VV_RM(vssubu_vv_h)
-GEN_VEXT_VV_RM(vssubu_vv_w)
-GEN_VEXT_VV_RM(vssubu_vv_d)
+GEN_VEXT_VV_RM(vssubu_vv_b, 1)
+GEN_VEXT_VV_RM(vssubu_vv_h, 2)
+GEN_VEXT_VV_RM(vssubu_vv_w, 4)
+GEN_VEXT_VV_RM(vssubu_vv_d, 8)
RVVCALL(OPIVX2_RM, vssubu_vx_b, OP_UUU_B, H1, H1, ssubu8)
RVVCALL(OPIVX2_RM, vssubu_vx_h, OP_UUU_H, H2, H2, ssubu16)
RVVCALL(OPIVX2_RM, vssubu_vx_w, OP_UUU_W, H4, H4, ssubu32)
RVVCALL(OPIVX2_RM, vssubu_vx_d, OP_UUU_D, H8, H8, ssubu64)
-GEN_VEXT_VX_RM(vssubu_vx_b)
-GEN_VEXT_VX_RM(vssubu_vx_h)
-GEN_VEXT_VX_RM(vssubu_vx_w)
-GEN_VEXT_VX_RM(vssubu_vx_d)
+GEN_VEXT_VX_RM(vssubu_vx_b, 1)
+GEN_VEXT_VX_RM(vssubu_vx_h, 2)
+GEN_VEXT_VX_RM(vssubu_vx_w, 4)
+GEN_VEXT_VX_RM(vssubu_vx_d, 8)
static inline int8_t ssub8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
{
@@ -2425,19 +2433,19 @@ RVVCALL(OPIVV2_RM, vssub_vv_b, OP_SSS_B, H1, H1, H1, ssub8)
RVVCALL(OPIVV2_RM, vssub_vv_h, OP_SSS_H, H2, H2, H2, ssub16)
RVVCALL(OPIVV2_RM, vssub_vv_w, OP_SSS_W, H4, H4, H4, ssub32)
RVVCALL(OPIVV2_RM, vssub_vv_d, OP_SSS_D, H8, H8, H8, ssub64)
-GEN_VEXT_VV_RM(vssub_vv_b)
-GEN_VEXT_VV_RM(vssub_vv_h)
-GEN_VEXT_VV_RM(vssub_vv_w)
-GEN_VEXT_VV_RM(vssub_vv_d)
+GEN_VEXT_VV_RM(vssub_vv_b, 1)
+GEN_VEXT_VV_RM(vssub_vv_h, 2)
+GEN_VEXT_VV_RM(vssub_vv_w, 4)
+GEN_VEXT_VV_RM(vssub_vv_d, 8)
RVVCALL(OPIVX2_RM, vssub_vx_b, OP_SSS_B, H1, H1, ssub8)
RVVCALL(OPIVX2_RM, vssub_vx_h, OP_SSS_H, H2, H2, ssub16)
RVVCALL(OPIVX2_RM, vssub_vx_w, OP_SSS_W, H4, H4, ssub32)
RVVCALL(OPIVX2_RM, vssub_vx_d, OP_SSS_D, H8, H8, ssub64)
-GEN_VEXT_VX_RM(vssub_vx_b)
-GEN_VEXT_VX_RM(vssub_vx_h)
-GEN_VEXT_VX_RM(vssub_vx_w)
-GEN_VEXT_VX_RM(vssub_vx_d)
+GEN_VEXT_VX_RM(vssub_vx_b, 1)
+GEN_VEXT_VX_RM(vssub_vx_h, 2)
+GEN_VEXT_VX_RM(vssub_vx_w, 4)
+GEN_VEXT_VX_RM(vssub_vx_d, 8)
/* Vector Single-Width Averaging Add and Subtract */
static inline uint8_t get_round(int vxrm, uint64_t v, uint8_t shift)
@@ -2489,19 +2497,19 @@ RVVCALL(OPIVV2_RM, vaadd_vv_b, OP_SSS_B, H1, H1, H1, aadd32)
RVVCALL(OPIVV2_RM, vaadd_vv_h, OP_SSS_H, H2, H2, H2, aadd32)
RVVCALL(OPIVV2_RM, vaadd_vv_w, OP_SSS_W, H4, H4, H4, aadd32)
RVVCALL(OPIVV2_RM, vaadd_vv_d, OP_SSS_D, H8, H8, H8, aadd64)
-GEN_VEXT_VV_RM(vaadd_vv_b)
-GEN_VEXT_VV_RM(vaadd_vv_h)
-GEN_VEXT_VV_RM(vaadd_vv_w)
-GEN_VEXT_VV_RM(vaadd_vv_d)
+GEN_VEXT_VV_RM(vaadd_vv_b, 1)
+GEN_VEXT_VV_RM(vaadd_vv_h, 2)
+GEN_VEXT_VV_RM(vaadd_vv_w, 4)
+GEN_VEXT_VV_RM(vaadd_vv_d, 8)
RVVCALL(OPIVX2_RM, vaadd_vx_b, OP_SSS_B, H1, H1, aadd32)
RVVCALL(OPIVX2_RM, vaadd_vx_h, OP_SSS_H, H2, H2, aadd32)
RVVCALL(OPIVX2_RM, vaadd_vx_w, OP_SSS_W, H4, H4, aadd32)
RVVCALL(OPIVX2_RM, vaadd_vx_d, OP_SSS_D, H8, H8, aadd64)
-GEN_VEXT_VX_RM(vaadd_vx_b)
-GEN_VEXT_VX_RM(vaadd_vx_h)
-GEN_VEXT_VX_RM(vaadd_vx_w)
-GEN_VEXT_VX_RM(vaadd_vx_d)
+GEN_VEXT_VX_RM(vaadd_vx_b, 1)
+GEN_VEXT_VX_RM(vaadd_vx_h, 2)
+GEN_VEXT_VX_RM(vaadd_vx_w, 4)
+GEN_VEXT_VX_RM(vaadd_vx_d, 8)
static inline uint32_t aaddu32(CPURISCVState *env, int vxrm,
uint32_t a, uint32_t b)
@@ -2526,19 +2534,19 @@ RVVCALL(OPIVV2_RM, vaaddu_vv_b, OP_UUU_B, H1, H1, H1, aaddu32)
RVVCALL(OPIVV2_RM, vaaddu_vv_h, OP_UUU_H, H2, H2, H2, aaddu32)
RVVCALL(OPIVV2_RM, vaaddu_vv_w, OP_UUU_W, H4, H4, H4, aaddu32)
RVVCALL(OPIVV2_RM, vaaddu_vv_d, OP_UUU_D, H8, H8, H8, aaddu64)
-GEN_VEXT_VV_RM(vaaddu_vv_b)
-GEN_VEXT_VV_RM(vaaddu_vv_h)
-GEN_VEXT_VV_RM(vaaddu_vv_w)
-GEN_VEXT_VV_RM(vaaddu_vv_d)
+GEN_VEXT_VV_RM(vaaddu_vv_b, 1)
+GEN_VEXT_VV_RM(vaaddu_vv_h, 2)
+GEN_VEXT_VV_RM(vaaddu_vv_w, 4)
+GEN_VEXT_VV_RM(vaaddu_vv_d, 8)
RVVCALL(OPIVX2_RM, vaaddu_vx_b, OP_UUU_B, H1, H1, aaddu32)
RVVCALL(OPIVX2_RM, vaaddu_vx_h, OP_UUU_H, H2, H2, aaddu32)
RVVCALL(OPIVX2_RM, vaaddu_vx_w, OP_UUU_W, H4, H4, aaddu32)
RVVCALL(OPIVX2_RM, vaaddu_vx_d, OP_UUU_D, H8, H8, aaddu64)
-GEN_VEXT_VX_RM(vaaddu_vx_b)
-GEN_VEXT_VX_RM(vaaddu_vx_h)
-GEN_VEXT_VX_RM(vaaddu_vx_w)
-GEN_VEXT_VX_RM(vaaddu_vx_d)
+GEN_VEXT_VX_RM(vaaddu_vx_b, 1)
+GEN_VEXT_VX_RM(vaaddu_vx_h, 2)
+GEN_VEXT_VX_RM(vaaddu_vx_w, 4)
+GEN_VEXT_VX_RM(vaaddu_vx_d, 8)
static inline int32_t asub32(CPURISCVState *env, int vxrm, int32_t a, int32_t b)
{
@@ -2562,19 +2570,19 @@ RVVCALL(OPIVV2_RM, vasub_vv_b, OP_SSS_B, H1, H1, H1, asub32)
RVVCALL(OPIVV2_RM, vasub_vv_h, OP_SSS_H, H2, H2, H2, asub32)
RVVCALL(OPIVV2_RM, vasub_vv_w, OP_SSS_W, H4, H4, H4, asub32)
RVVCALL(OPIVV2_RM, vasub_vv_d, OP_SSS_D, H8, H8, H8, asub64)
-GEN_VEXT_VV_RM(vasub_vv_b)
-GEN_VEXT_VV_RM(vasub_vv_h)
-GEN_VEXT_VV_RM(vasub_vv_w)
-GEN_VEXT_VV_RM(vasub_vv_d)
+GEN_VEXT_VV_RM(vasub_vv_b, 1)
+GEN_VEXT_VV_RM(vasub_vv_h, 2)
+GEN_VEXT_VV_RM(vasub_vv_w, 4)
+GEN_VEXT_VV_RM(vasub_vv_d, 8)
RVVCALL(OPIVX2_RM, vasub_vx_b, OP_SSS_B, H1, H1, asub32)
RVVCALL(OPIVX2_RM, vasub_vx_h, OP_SSS_H, H2, H2, asub32)
RVVCALL(OPIVX2_RM, vasub_vx_w, OP_SSS_W, H4, H4, asub32)
RVVCALL(OPIVX2_RM, vasub_vx_d, OP_SSS_D, H8, H8, asub64)
-GEN_VEXT_VX_RM(vasub_vx_b)
-GEN_VEXT_VX_RM(vasub_vx_h)
-GEN_VEXT_VX_RM(vasub_vx_w)
-GEN_VEXT_VX_RM(vasub_vx_d)
+GEN_VEXT_VX_RM(vasub_vx_b, 1)
+GEN_VEXT_VX_RM(vasub_vx_h, 2)
+GEN_VEXT_VX_RM(vasub_vx_w, 4)
+GEN_VEXT_VX_RM(vasub_vx_d, 8)
static inline uint32_t asubu32(CPURISCVState *env, int vxrm,
uint32_t a, uint32_t b)
@@ -2599,19 +2607,19 @@ RVVCALL(OPIVV2_RM, vasubu_vv_b, OP_UUU_B, H1, H1, H1, asubu32)
RVVCALL(OPIVV2_RM, vasubu_vv_h, OP_UUU_H, H2, H2, H2, asubu32)
RVVCALL(OPIVV2_RM, vasubu_vv_w, OP_UUU_W, H4, H4, H4, asubu32)
RVVCALL(OPIVV2_RM, vasubu_vv_d, OP_UUU_D, H8, H8, H8, asubu64)
-GEN_VEXT_VV_RM(vasubu_vv_b)
-GEN_VEXT_VV_RM(vasubu_vv_h)
-GEN_VEXT_VV_RM(vasubu_vv_w)
-GEN_VEXT_VV_RM(vasubu_vv_d)
+GEN_VEXT_VV_RM(vasubu_vv_b, 1)
+GEN_VEXT_VV_RM(vasubu_vv_h, 2)
+GEN_VEXT_VV_RM(vasubu_vv_w, 4)
+GEN_VEXT_VV_RM(vasubu_vv_d, 8)
RVVCALL(OPIVX2_RM, vasubu_vx_b, OP_UUU_B, H1, H1, asubu32)
RVVCALL(OPIVX2_RM, vasubu_vx_h, OP_UUU_H, H2, H2, asubu32)
RVVCALL(OPIVX2_RM, vasubu_vx_w, OP_UUU_W, H4, H4, asubu32)
RVVCALL(OPIVX2_RM, vasubu_vx_d, OP_UUU_D, H8, H8, asubu64)
-GEN_VEXT_VX_RM(vasubu_vx_b)
-GEN_VEXT_VX_RM(vasubu_vx_h)
-GEN_VEXT_VX_RM(vasubu_vx_w)
-GEN_VEXT_VX_RM(vasubu_vx_d)
+GEN_VEXT_VX_RM(vasubu_vx_b, 1)
+GEN_VEXT_VX_RM(vasubu_vx_h, 2)
+GEN_VEXT_VX_RM(vasubu_vx_w, 4)
+GEN_VEXT_VX_RM(vasubu_vx_d, 8)
/* Vector Single-Width Fractional Multiply with Rounding and Saturation */
static inline int8_t vsmul8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
@@ -2706,19 +2714,19 @@ RVVCALL(OPIVV2_RM, vsmul_vv_b, OP_SSS_B, H1, H1, H1, vsmul8)
RVVCALL(OPIVV2_RM, vsmul_vv_h, OP_SSS_H, H2, H2, H2, vsmul16)
RVVCALL(OPIVV2_RM, vsmul_vv_w, OP_SSS_W, H4, H4, H4, vsmul32)
RVVCALL(OPIVV2_RM, vsmul_vv_d, OP_SSS_D, H8, H8, H8, vsmul64)
-GEN_VEXT_VV_RM(vsmul_vv_b)
-GEN_VEXT_VV_RM(vsmul_vv_h)
-GEN_VEXT_VV_RM(vsmul_vv_w)
-GEN_VEXT_VV_RM(vsmul_vv_d)
+GEN_VEXT_VV_RM(vsmul_vv_b, 1)
+GEN_VEXT_VV_RM(vsmul_vv_h, 2)
+GEN_VEXT_VV_RM(vsmul_vv_w, 4)
+GEN_VEXT_VV_RM(vsmul_vv_d, 8)
RVVCALL(OPIVX2_RM, vsmul_vx_b, OP_SSS_B, H1, H1, vsmul8)
RVVCALL(OPIVX2_RM, vsmul_vx_h, OP_SSS_H, H2, H2, vsmul16)
RVVCALL(OPIVX2_RM, vsmul_vx_w, OP_SSS_W, H4, H4, vsmul32)
RVVCALL(OPIVX2_RM, vsmul_vx_d, OP_SSS_D, H8, H8, vsmul64)
-GEN_VEXT_VX_RM(vsmul_vx_b)
-GEN_VEXT_VX_RM(vsmul_vx_h)
-GEN_VEXT_VX_RM(vsmul_vx_w)
-GEN_VEXT_VX_RM(vsmul_vx_d)
+GEN_VEXT_VX_RM(vsmul_vx_b, 1)
+GEN_VEXT_VX_RM(vsmul_vx_h, 2)
+GEN_VEXT_VX_RM(vsmul_vx_w, 4)
+GEN_VEXT_VX_RM(vsmul_vx_d, 8)
/* Vector Single-Width Scaling Shift Instructions */
static inline uint8_t
@@ -2765,19 +2773,19 @@ RVVCALL(OPIVV2_RM, vssrl_vv_b, OP_UUU_B, H1, H1, H1, vssrl8)
RVVCALL(OPIVV2_RM, vssrl_vv_h, OP_UUU_H, H2, H2, H2, vssrl16)
RVVCALL(OPIVV2_RM, vssrl_vv_w, OP_UUU_W, H4, H4, H4, vssrl32)
RVVCALL(OPIVV2_RM, vssrl_vv_d, OP_UUU_D, H8, H8, H8, vssrl64)
-GEN_VEXT_VV_RM(vssrl_vv_b)
-GEN_VEXT_VV_RM(vssrl_vv_h)
-GEN_VEXT_VV_RM(vssrl_vv_w)
-GEN_VEXT_VV_RM(vssrl_vv_d)
+GEN_VEXT_VV_RM(vssrl_vv_b, 1)
+GEN_VEXT_VV_RM(vssrl_vv_h, 2)
+GEN_VEXT_VV_RM(vssrl_vv_w, 4)
+GEN_VEXT_VV_RM(vssrl_vv_d, 8)
RVVCALL(OPIVX2_RM, vssrl_vx_b, OP_UUU_B, H1, H1, vssrl8)
RVVCALL(OPIVX2_RM, vssrl_vx_h, OP_UUU_H, H2, H2, vssrl16)
RVVCALL(OPIVX2_RM, vssrl_vx_w, OP_UUU_W, H4, H4, vssrl32)
RVVCALL(OPIVX2_RM, vssrl_vx_d, OP_UUU_D, H8, H8, vssrl64)
-GEN_VEXT_VX_RM(vssrl_vx_b)
-GEN_VEXT_VX_RM(vssrl_vx_h)
-GEN_VEXT_VX_RM(vssrl_vx_w)
-GEN_VEXT_VX_RM(vssrl_vx_d)
+GEN_VEXT_VX_RM(vssrl_vx_b, 1)
+GEN_VEXT_VX_RM(vssrl_vx_h, 2)
+GEN_VEXT_VX_RM(vssrl_vx_w, 4)
+GEN_VEXT_VX_RM(vssrl_vx_d, 8)
static inline int8_t
vssra8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
@@ -2824,19 +2832,19 @@ RVVCALL(OPIVV2_RM, vssra_vv_b, OP_SSS_B, H1, H1, H1, vssra8)
RVVCALL(OPIVV2_RM, vssra_vv_h, OP_SSS_H, H2, H2, H2, vssra16)
RVVCALL(OPIVV2_RM, vssra_vv_w, OP_SSS_W, H4, H4, H4, vssra32)
RVVCALL(OPIVV2_RM, vssra_vv_d, OP_SSS_D, H8, H8, H8, vssra64)
-GEN_VEXT_VV_RM(vssra_vv_b)
-GEN_VEXT_VV_RM(vssra_vv_h)
-GEN_VEXT_VV_RM(vssra_vv_w)
-GEN_VEXT_VV_RM(vssra_vv_d)
+GEN_VEXT_VV_RM(vssra_vv_b, 1)
+GEN_VEXT_VV_RM(vssra_vv_h, 2)
+GEN_VEXT_VV_RM(vssra_vv_w, 4)
+GEN_VEXT_VV_RM(vssra_vv_d, 8)
RVVCALL(OPIVX2_RM, vssra_vx_b, OP_SSS_B, H1, H1, vssra8)
RVVCALL(OPIVX2_RM, vssra_vx_h, OP_SSS_H, H2, H2, vssra16)
RVVCALL(OPIVX2_RM, vssra_vx_w, OP_SSS_W, H4, H4, vssra32)
RVVCALL(OPIVX2_RM, vssra_vx_d, OP_SSS_D, H8, H8, vssra64)
-GEN_VEXT_VX_RM(vssra_vx_b)
-GEN_VEXT_VX_RM(vssra_vx_h)
-GEN_VEXT_VX_RM(vssra_vx_w)
-GEN_VEXT_VX_RM(vssra_vx_d)
+GEN_VEXT_VX_RM(vssra_vx_b, 1)
+GEN_VEXT_VX_RM(vssra_vx_h, 2)
+GEN_VEXT_VX_RM(vssra_vx_w, 4)
+GEN_VEXT_VX_RM(vssra_vx_d, 8)
/* Vector Narrowing Fixed-Point Clip Instructions */
static inline int8_t
@@ -2899,16 +2907,16 @@ vnclip32(CPURISCVState *env, int vxrm, int64_t a, int32_t b)
RVVCALL(OPIVV2_RM, vnclip_wv_b, NOP_SSS_B, H1, H2, H1, vnclip8)
RVVCALL(OPIVV2_RM, vnclip_wv_h, NOP_SSS_H, H2, H4, H2, vnclip16)
RVVCALL(OPIVV2_RM, vnclip_wv_w, NOP_SSS_W, H4, H8, H4, vnclip32)
-GEN_VEXT_VV_RM(vnclip_wv_b)
-GEN_VEXT_VV_RM(vnclip_wv_h)
-GEN_VEXT_VV_RM(vnclip_wv_w)
+GEN_VEXT_VV_RM(vnclip_wv_b, 1)
+GEN_VEXT_VV_RM(vnclip_wv_h, 2)
+GEN_VEXT_VV_RM(vnclip_wv_w, 4)
RVVCALL(OPIVX2_RM, vnclip_wx_b, NOP_SSS_B, H1, H2, vnclip8)
RVVCALL(OPIVX2_RM, vnclip_wx_h, NOP_SSS_H, H2, H4, vnclip16)
RVVCALL(OPIVX2_RM, vnclip_wx_w, NOP_SSS_W, H4, H8, vnclip32)
-GEN_VEXT_VX_RM(vnclip_wx_b)
-GEN_VEXT_VX_RM(vnclip_wx_h)
-GEN_VEXT_VX_RM(vnclip_wx_w)
+GEN_VEXT_VX_RM(vnclip_wx_b, 1)
+GEN_VEXT_VX_RM(vnclip_wx_h, 2)
+GEN_VEXT_VX_RM(vnclip_wx_w, 4)
static inline uint8_t
vnclipu8(CPURISCVState *env, int vxrm, uint16_t a, uint8_t b)
@@ -2961,16 +2969,16 @@ vnclipu32(CPURISCVState *env, int vxrm, uint64_t a, uint32_t b)
RVVCALL(OPIVV2_RM, vnclipu_wv_b, NOP_UUU_B, H1, H2, H1, vnclipu8)
RVVCALL(OPIVV2_RM, vnclipu_wv_h, NOP_UUU_H, H2, H4, H2, vnclipu16)
RVVCALL(OPIVV2_RM, vnclipu_wv_w, NOP_UUU_W, H4, H8, H4, vnclipu32)
-GEN_VEXT_VV_RM(vnclipu_wv_b)
-GEN_VEXT_VV_RM(vnclipu_wv_h)
-GEN_VEXT_VV_RM(vnclipu_wv_w)
+GEN_VEXT_VV_RM(vnclipu_wv_b, 1)
+GEN_VEXT_VV_RM(vnclipu_wv_h, 2)
+GEN_VEXT_VV_RM(vnclipu_wv_w, 4)
RVVCALL(OPIVX2_RM, vnclipu_wx_b, NOP_UUU_B, H1, H2, vnclipu8)
RVVCALL(OPIVX2_RM, vnclipu_wx_h, NOP_UUU_H, H2, H4, vnclipu16)
RVVCALL(OPIVX2_RM, vnclipu_wx_w, NOP_UUU_W, H4, H8, vnclipu32)
-GEN_VEXT_VX_RM(vnclipu_wx_b)
-GEN_VEXT_VX_RM(vnclipu_wx_h)
-GEN_VEXT_VX_RM(vnclipu_wx_w)
+GEN_VEXT_VX_RM(vnclipu_wx_b, 1)
+GEN_VEXT_VX_RM(vnclipu_wx_h, 2)
+GEN_VEXT_VX_RM(vnclipu_wx_w, 4)
/*
*** Vector Float Point Arithmetic Instructions
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 12/16] target/riscv: rvv: Add tail agnostic for vector floating-point instructions
2022-05-13 11:49 [PATCH qemu v18 00/16] Add tail agnostic behavior for rvv instructions ~eopxd
@ 2022-05-13 11:50 ` ~eopxd
2022-05-13 11:50 ` ~eopxd
` (15 subsequent siblings)
16 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-03-07 10:05 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
Compares write mask registers, and so always operate under a tail-
agnostic policy.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/insn_trans/trans_rvv.c.inc | 17 +
target/riscv/vector_helper.c | 440 +++++++++++++-----------
2 files changed, 261 insertions(+), 196 deletions(-)
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index 50f874ceae..76dee1ba20 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -2334,6 +2334,9 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
+ data = \
+ FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);\
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs1), \
vreg_ofs(s, a->rs2), cpu_env, \
@@ -2416,6 +2419,9 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
gen_set_rm(s, RISCV_FRM_DYN); \
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
+ data = FIELD_DP32(data, VDATA, VTA_ALL_1S, \
+ s->cfg_vta_all_1s); \
return opfvf_trans(a->rd, a->rs1, a->rs2, data, \
fns[s->sew - 1], s); \
} \
@@ -2454,6 +2460,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs1), \
vreg_ofs(s, a->rs2), cpu_env, \
@@ -2493,6 +2500,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
gen_set_rm(s, RISCV_FRM_DYN); \
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
return opfvf_trans(a->rd, a->rs1, a->rs2, data, \
fns[s->sew - 1], s); \
} \
@@ -2529,6 +2537,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs1), \
vreg_ofs(s, a->rs2), cpu_env, \
@@ -2568,6 +2577,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
gen_set_rm(s, RISCV_FRM_DYN); \
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
return opfvf_trans(a->rd, a->rs1, a->rs2, data, \
fns[s->sew - 1], s); \
} \
@@ -2651,6 +2661,7 @@ static bool do_opfv(DisasContext *s, arg_rmr *a,
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),
vreg_ofs(s, a->rs2), cpu_env,
s->cfg_ptr->vlen / 8,
@@ -2855,6 +2866,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs2), cpu_env, \
s->cfg_ptr->vlen / 8, \
@@ -2906,6 +2918,8 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
+ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs2), cpu_env, \
s->cfg_ptr->vlen / 8, \
@@ -2973,6 +2987,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs2), cpu_env, \
s->cfg_ptr->vlen / 8, \
@@ -3026,6 +3041,8 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
+ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs2), cpu_env, \
s->cfg_ptr->vlen / 8, \
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index db221797c6..8ac7fabb05 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -2993,13 +2993,16 @@ static void do_##NAME(void *vd, void *vs1, void *vs2, int i, \
*((TD *)vd + HD(i)) = OP(s2, s1, &env->fp_status); \
}
-#define GEN_VEXT_VV_ENV(NAME) \
+#define GEN_VEXT_VV_ENV(NAME, ESZ) \
void HELPER(NAME)(void *vd, void *v0, void *vs1, \
void *vs2, CPURISCVState *env, \
uint32_t desc) \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t total_elems = \
+ vext_get_total_elems(env, desc, ESZ); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -3009,14 +3012,17 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
do_##NAME(vd, vs1, vs2, i, env); \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * ESZ, \
+ total_elems * ESZ); \
}
RVVCALL(OPFVV2, vfadd_vv_h, OP_UUU_H, H2, H2, H2, float16_add)
RVVCALL(OPFVV2, vfadd_vv_w, OP_UUU_W, H4, H4, H4, float32_add)
RVVCALL(OPFVV2, vfadd_vv_d, OP_UUU_D, H8, H8, H8, float64_add)
-GEN_VEXT_VV_ENV(vfadd_vv_h)
-GEN_VEXT_VV_ENV(vfadd_vv_w)
-GEN_VEXT_VV_ENV(vfadd_vv_d)
+GEN_VEXT_VV_ENV(vfadd_vv_h, 2)
+GEN_VEXT_VV_ENV(vfadd_vv_w, 4)
+GEN_VEXT_VV_ENV(vfadd_vv_d, 8)
#define OPFVF2(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \
static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \
@@ -3026,13 +3032,16 @@ static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \
*((TD *)vd + HD(i)) = OP(s2, (TX1)(T1)s1, &env->fp_status);\
}
-#define GEN_VEXT_VF(NAME) \
+#define GEN_VEXT_VF(NAME, ESZ) \
void HELPER(NAME)(void *vd, void *v0, uint64_t s1, \
void *vs2, CPURISCVState *env, \
uint32_t desc) \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t total_elems = \
+ vext_get_total_elems(env, desc, ESZ); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -3042,27 +3051,30 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, \
do_##NAME(vd, s1, vs2, i, env); \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * ESZ, \
+ total_elems * ESZ); \
}
RVVCALL(OPFVF2, vfadd_vf_h, OP_UUU_H, H2, H2, float16_add)
RVVCALL(OPFVF2, vfadd_vf_w, OP_UUU_W, H4, H4, float32_add)
RVVCALL(OPFVF2, vfadd_vf_d, OP_UUU_D, H8, H8, float64_add)
-GEN_VEXT_VF(vfadd_vf_h)
-GEN_VEXT_VF(vfadd_vf_w)
-GEN_VEXT_VF(vfadd_vf_d)
+GEN_VEXT_VF(vfadd_vf_h, 2)
+GEN_VEXT_VF(vfadd_vf_w, 4)
+GEN_VEXT_VF(vfadd_vf_d, 8)
RVVCALL(OPFVV2, vfsub_vv_h, OP_UUU_H, H2, H2, H2, float16_sub)
RVVCALL(OPFVV2, vfsub_vv_w, OP_UUU_W, H4, H4, H4, float32_sub)
RVVCALL(OPFVV2, vfsub_vv_d, OP_UUU_D, H8, H8, H8, float64_sub)
-GEN_VEXT_VV_ENV(vfsub_vv_h)
-GEN_VEXT_VV_ENV(vfsub_vv_w)
-GEN_VEXT_VV_ENV(vfsub_vv_d)
+GEN_VEXT_VV_ENV(vfsub_vv_h, 2)
+GEN_VEXT_VV_ENV(vfsub_vv_w, 4)
+GEN_VEXT_VV_ENV(vfsub_vv_d, 8)
RVVCALL(OPFVF2, vfsub_vf_h, OP_UUU_H, H2, H2, float16_sub)
RVVCALL(OPFVF2, vfsub_vf_w, OP_UUU_W, H4, H4, float32_sub)
RVVCALL(OPFVF2, vfsub_vf_d, OP_UUU_D, H8, H8, float64_sub)
-GEN_VEXT_VF(vfsub_vf_h)
-GEN_VEXT_VF(vfsub_vf_w)
-GEN_VEXT_VF(vfsub_vf_d)
+GEN_VEXT_VF(vfsub_vf_h, 2)
+GEN_VEXT_VF(vfsub_vf_w, 4)
+GEN_VEXT_VF(vfsub_vf_d, 8)
static uint16_t float16_rsub(uint16_t a, uint16_t b, float_status *s)
{
@@ -3082,9 +3094,9 @@ static uint64_t float64_rsub(uint64_t a, uint64_t b, float_status *s)
RVVCALL(OPFVF2, vfrsub_vf_h, OP_UUU_H, H2, H2, float16_rsub)
RVVCALL(OPFVF2, vfrsub_vf_w, OP_UUU_W, H4, H4, float32_rsub)
RVVCALL(OPFVF2, vfrsub_vf_d, OP_UUU_D, H8, H8, float64_rsub)
-GEN_VEXT_VF(vfrsub_vf_h)
-GEN_VEXT_VF(vfrsub_vf_w)
-GEN_VEXT_VF(vfrsub_vf_d)
+GEN_VEXT_VF(vfrsub_vf_h, 2)
+GEN_VEXT_VF(vfrsub_vf_w, 4)
+GEN_VEXT_VF(vfrsub_vf_d, 8)
/* Vector Widening Floating-Point Add/Subtract Instructions */
static uint32_t vfwadd16(uint16_t a, uint16_t b, float_status *s)
@@ -3102,12 +3114,12 @@ static uint64_t vfwadd32(uint32_t a, uint32_t b, float_status *s)
RVVCALL(OPFVV2, vfwadd_vv_h, WOP_UUU_H, H4, H2, H2, vfwadd16)
RVVCALL(OPFVV2, vfwadd_vv_w, WOP_UUU_W, H8, H4, H4, vfwadd32)
-GEN_VEXT_VV_ENV(vfwadd_vv_h)
-GEN_VEXT_VV_ENV(vfwadd_vv_w)
+GEN_VEXT_VV_ENV(vfwadd_vv_h, 4)
+GEN_VEXT_VV_ENV(vfwadd_vv_w, 8)
RVVCALL(OPFVF2, vfwadd_vf_h, WOP_UUU_H, H4, H2, vfwadd16)
RVVCALL(OPFVF2, vfwadd_vf_w, WOP_UUU_W, H8, H4, vfwadd32)
-GEN_VEXT_VF(vfwadd_vf_h)
-GEN_VEXT_VF(vfwadd_vf_w)
+GEN_VEXT_VF(vfwadd_vf_h, 4)
+GEN_VEXT_VF(vfwadd_vf_w, 8)
static uint32_t vfwsub16(uint16_t a, uint16_t b, float_status *s)
{
@@ -3124,12 +3136,12 @@ static uint64_t vfwsub32(uint32_t a, uint32_t b, float_status *s)
RVVCALL(OPFVV2, vfwsub_vv_h, WOP_UUU_H, H4, H2, H2, vfwsub16)
RVVCALL(OPFVV2, vfwsub_vv_w, WOP_UUU_W, H8, H4, H4, vfwsub32)
-GEN_VEXT_VV_ENV(vfwsub_vv_h)
-GEN_VEXT_VV_ENV(vfwsub_vv_w)
+GEN_VEXT_VV_ENV(vfwsub_vv_h, 4)
+GEN_VEXT_VV_ENV(vfwsub_vv_w, 8)
RVVCALL(OPFVF2, vfwsub_vf_h, WOP_UUU_H, H4, H2, vfwsub16)
RVVCALL(OPFVF2, vfwsub_vf_w, WOP_UUU_W, H8, H4, vfwsub32)
-GEN_VEXT_VF(vfwsub_vf_h)
-GEN_VEXT_VF(vfwsub_vf_w)
+GEN_VEXT_VF(vfwsub_vf_h, 4)
+GEN_VEXT_VF(vfwsub_vf_w, 8)
static uint32_t vfwaddw16(uint32_t a, uint16_t b, float_status *s)
{
@@ -3143,12 +3155,12 @@ static uint64_t vfwaddw32(uint64_t a, uint32_t b, float_status *s)
RVVCALL(OPFVV2, vfwadd_wv_h, WOP_WUUU_H, H4, H2, H2, vfwaddw16)
RVVCALL(OPFVV2, vfwadd_wv_w, WOP_WUUU_W, H8, H4, H4, vfwaddw32)
-GEN_VEXT_VV_ENV(vfwadd_wv_h)
-GEN_VEXT_VV_ENV(vfwadd_wv_w)
+GEN_VEXT_VV_ENV(vfwadd_wv_h, 4)
+GEN_VEXT_VV_ENV(vfwadd_wv_w, 8)
RVVCALL(OPFVF2, vfwadd_wf_h, WOP_WUUU_H, H4, H2, vfwaddw16)
RVVCALL(OPFVF2, vfwadd_wf_w, WOP_WUUU_W, H8, H4, vfwaddw32)
-GEN_VEXT_VF(vfwadd_wf_h)
-GEN_VEXT_VF(vfwadd_wf_w)
+GEN_VEXT_VF(vfwadd_wf_h, 4)
+GEN_VEXT_VF(vfwadd_wf_w, 8)
static uint32_t vfwsubw16(uint32_t a, uint16_t b, float_status *s)
{
@@ -3162,39 +3174,39 @@ static uint64_t vfwsubw32(uint64_t a, uint32_t b, float_status *s)
RVVCALL(OPFVV2, vfwsub_wv_h, WOP_WUUU_H, H4, H2, H2, vfwsubw16)
RVVCALL(OPFVV2, vfwsub_wv_w, WOP_WUUU_W, H8, H4, H4, vfwsubw32)
-GEN_VEXT_VV_ENV(vfwsub_wv_h)
-GEN_VEXT_VV_ENV(vfwsub_wv_w)
+GEN_VEXT_VV_ENV(vfwsub_wv_h, 4)
+GEN_VEXT_VV_ENV(vfwsub_wv_w, 8)
RVVCALL(OPFVF2, vfwsub_wf_h, WOP_WUUU_H, H4, H2, vfwsubw16)
RVVCALL(OPFVF2, vfwsub_wf_w, WOP_WUUU_W, H8, H4, vfwsubw32)
-GEN_VEXT_VF(vfwsub_wf_h)
-GEN_VEXT_VF(vfwsub_wf_w)
+GEN_VEXT_VF(vfwsub_wf_h, 4)
+GEN_VEXT_VF(vfwsub_wf_w, 8)
/* Vector Single-Width Floating-Point Multiply/Divide Instructions */
RVVCALL(OPFVV2, vfmul_vv_h, OP_UUU_H, H2, H2, H2, float16_mul)
RVVCALL(OPFVV2, vfmul_vv_w, OP_UUU_W, H4, H4, H4, float32_mul)
RVVCALL(OPFVV2, vfmul_vv_d, OP_UUU_D, H8, H8, H8, float64_mul)
-GEN_VEXT_VV_ENV(vfmul_vv_h)
-GEN_VEXT_VV_ENV(vfmul_vv_w)
-GEN_VEXT_VV_ENV(vfmul_vv_d)
+GEN_VEXT_VV_ENV(vfmul_vv_h, 2)
+GEN_VEXT_VV_ENV(vfmul_vv_w, 4)
+GEN_VEXT_VV_ENV(vfmul_vv_d, 8)
RVVCALL(OPFVF2, vfmul_vf_h, OP_UUU_H, H2, H2, float16_mul)
RVVCALL(OPFVF2, vfmul_vf_w, OP_UUU_W, H4, H4, float32_mul)
RVVCALL(OPFVF2, vfmul_vf_d, OP_UUU_D, H8, H8, float64_mul)
-GEN_VEXT_VF(vfmul_vf_h)
-GEN_VEXT_VF(vfmul_vf_w)
-GEN_VEXT_VF(vfmul_vf_d)
+GEN_VEXT_VF(vfmul_vf_h, 2)
+GEN_VEXT_VF(vfmul_vf_w, 4)
+GEN_VEXT_VF(vfmul_vf_d, 8)
RVVCALL(OPFVV2, vfdiv_vv_h, OP_UUU_H, H2, H2, H2, float16_div)
RVVCALL(OPFVV2, vfdiv_vv_w, OP_UUU_W, H4, H4, H4, float32_div)
RVVCALL(OPFVV2, vfdiv_vv_d, OP_UUU_D, H8, H8, H8, float64_div)
-GEN_VEXT_VV_ENV(vfdiv_vv_h)
-GEN_VEXT_VV_ENV(vfdiv_vv_w)
-GEN_VEXT_VV_ENV(vfdiv_vv_d)
+GEN_VEXT_VV_ENV(vfdiv_vv_h, 2)
+GEN_VEXT_VV_ENV(vfdiv_vv_w, 4)
+GEN_VEXT_VV_ENV(vfdiv_vv_d, 8)
RVVCALL(OPFVF2, vfdiv_vf_h, OP_UUU_H, H2, H2, float16_div)
RVVCALL(OPFVF2, vfdiv_vf_w, OP_UUU_W, H4, H4, float32_div)
RVVCALL(OPFVF2, vfdiv_vf_d, OP_UUU_D, H8, H8, float64_div)
-GEN_VEXT_VF(vfdiv_vf_h)
-GEN_VEXT_VF(vfdiv_vf_w)
-GEN_VEXT_VF(vfdiv_vf_d)
+GEN_VEXT_VF(vfdiv_vf_h, 2)
+GEN_VEXT_VF(vfdiv_vf_w, 4)
+GEN_VEXT_VF(vfdiv_vf_d, 8)
static uint16_t float16_rdiv(uint16_t a, uint16_t b, float_status *s)
{
@@ -3214,9 +3226,9 @@ static uint64_t float64_rdiv(uint64_t a, uint64_t b, float_status *s)
RVVCALL(OPFVF2, vfrdiv_vf_h, OP_UUU_H, H2, H2, float16_rdiv)
RVVCALL(OPFVF2, vfrdiv_vf_w, OP_UUU_W, H4, H4, float32_rdiv)
RVVCALL(OPFVF2, vfrdiv_vf_d, OP_UUU_D, H8, H8, float64_rdiv)
-GEN_VEXT_VF(vfrdiv_vf_h)
-GEN_VEXT_VF(vfrdiv_vf_w)
-GEN_VEXT_VF(vfrdiv_vf_d)
+GEN_VEXT_VF(vfrdiv_vf_h, 2)
+GEN_VEXT_VF(vfrdiv_vf_w, 4)
+GEN_VEXT_VF(vfrdiv_vf_d, 8)
/* Vector Widening Floating-Point Multiply */
static uint32_t vfwmul16(uint16_t a, uint16_t b, float_status *s)
@@ -3233,12 +3245,12 @@ static uint64_t vfwmul32(uint32_t a, uint32_t b, float_status *s)
}
RVVCALL(OPFVV2, vfwmul_vv_h, WOP_UUU_H, H4, H2, H2, vfwmul16)
RVVCALL(OPFVV2, vfwmul_vv_w, WOP_UUU_W, H8, H4, H4, vfwmul32)
-GEN_VEXT_VV_ENV(vfwmul_vv_h)
-GEN_VEXT_VV_ENV(vfwmul_vv_w)
+GEN_VEXT_VV_ENV(vfwmul_vv_h, 4)
+GEN_VEXT_VV_ENV(vfwmul_vv_w, 8)
RVVCALL(OPFVF2, vfwmul_vf_h, WOP_UUU_H, H4, H2, vfwmul16)
RVVCALL(OPFVF2, vfwmul_vf_w, WOP_UUU_W, H8, H4, vfwmul32)
-GEN_VEXT_VF(vfwmul_vf_h)
-GEN_VEXT_VF(vfwmul_vf_w)
+GEN_VEXT_VF(vfwmul_vf_h, 4)
+GEN_VEXT_VF(vfwmul_vf_w, 8)
/* Vector Single-Width Floating-Point Fused Multiply-Add Instructions */
#define OPFVV3(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP) \
@@ -3269,9 +3281,9 @@ static uint64_t fmacc64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfmacc_vv_h, OP_UUU_H, H2, H2, H2, fmacc16)
RVVCALL(OPFVV3, vfmacc_vv_w, OP_UUU_W, H4, H4, H4, fmacc32)
RVVCALL(OPFVV3, vfmacc_vv_d, OP_UUU_D, H8, H8, H8, fmacc64)
-GEN_VEXT_VV_ENV(vfmacc_vv_h)
-GEN_VEXT_VV_ENV(vfmacc_vv_w)
-GEN_VEXT_VV_ENV(vfmacc_vv_d)
+GEN_VEXT_VV_ENV(vfmacc_vv_h, 2)
+GEN_VEXT_VV_ENV(vfmacc_vv_w, 4)
+GEN_VEXT_VV_ENV(vfmacc_vv_d, 8)
#define OPFVF3(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \
static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \
@@ -3285,9 +3297,9 @@ static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \
RVVCALL(OPFVF3, vfmacc_vf_h, OP_UUU_H, H2, H2, fmacc16)
RVVCALL(OPFVF3, vfmacc_vf_w, OP_UUU_W, H4, H4, fmacc32)
RVVCALL(OPFVF3, vfmacc_vf_d, OP_UUU_D, H8, H8, fmacc64)
-GEN_VEXT_VF(vfmacc_vf_h)
-GEN_VEXT_VF(vfmacc_vf_w)
-GEN_VEXT_VF(vfmacc_vf_d)
+GEN_VEXT_VF(vfmacc_vf_h, 2)
+GEN_VEXT_VF(vfmacc_vf_w, 4)
+GEN_VEXT_VF(vfmacc_vf_d, 8)
static uint16_t fnmacc16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3310,15 +3322,15 @@ static uint64_t fnmacc64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfnmacc_vv_h, OP_UUU_H, H2, H2, H2, fnmacc16)
RVVCALL(OPFVV3, vfnmacc_vv_w, OP_UUU_W, H4, H4, H4, fnmacc32)
RVVCALL(OPFVV3, vfnmacc_vv_d, OP_UUU_D, H8, H8, H8, fnmacc64)
-GEN_VEXT_VV_ENV(vfnmacc_vv_h)
-GEN_VEXT_VV_ENV(vfnmacc_vv_w)
-GEN_VEXT_VV_ENV(vfnmacc_vv_d)
+GEN_VEXT_VV_ENV(vfnmacc_vv_h, 2)
+GEN_VEXT_VV_ENV(vfnmacc_vv_w, 4)
+GEN_VEXT_VV_ENV(vfnmacc_vv_d, 8)
RVVCALL(OPFVF3, vfnmacc_vf_h, OP_UUU_H, H2, H2, fnmacc16)
RVVCALL(OPFVF3, vfnmacc_vf_w, OP_UUU_W, H4, H4, fnmacc32)
RVVCALL(OPFVF3, vfnmacc_vf_d, OP_UUU_D, H8, H8, fnmacc64)
-GEN_VEXT_VF(vfnmacc_vf_h)
-GEN_VEXT_VF(vfnmacc_vf_w)
-GEN_VEXT_VF(vfnmacc_vf_d)
+GEN_VEXT_VF(vfnmacc_vf_h, 2)
+GEN_VEXT_VF(vfnmacc_vf_w, 4)
+GEN_VEXT_VF(vfnmacc_vf_d, 8)
static uint16_t fmsac16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3338,15 +3350,15 @@ static uint64_t fmsac64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfmsac_vv_h, OP_UUU_H, H2, H2, H2, fmsac16)
RVVCALL(OPFVV3, vfmsac_vv_w, OP_UUU_W, H4, H4, H4, fmsac32)
RVVCALL(OPFVV3, vfmsac_vv_d, OP_UUU_D, H8, H8, H8, fmsac64)
-GEN_VEXT_VV_ENV(vfmsac_vv_h)
-GEN_VEXT_VV_ENV(vfmsac_vv_w)
-GEN_VEXT_VV_ENV(vfmsac_vv_d)
+GEN_VEXT_VV_ENV(vfmsac_vv_h, 2)
+GEN_VEXT_VV_ENV(vfmsac_vv_w, 4)
+GEN_VEXT_VV_ENV(vfmsac_vv_d, 8)
RVVCALL(OPFVF3, vfmsac_vf_h, OP_UUU_H, H2, H2, fmsac16)
RVVCALL(OPFVF3, vfmsac_vf_w, OP_UUU_W, H4, H4, fmsac32)
RVVCALL(OPFVF3, vfmsac_vf_d, OP_UUU_D, H8, H8, fmsac64)
-GEN_VEXT_VF(vfmsac_vf_h)
-GEN_VEXT_VF(vfmsac_vf_w)
-GEN_VEXT_VF(vfmsac_vf_d)
+GEN_VEXT_VF(vfmsac_vf_h, 2)
+GEN_VEXT_VF(vfmsac_vf_w, 4)
+GEN_VEXT_VF(vfmsac_vf_d, 8)
static uint16_t fnmsac16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3366,15 +3378,15 @@ static uint64_t fnmsac64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfnmsac_vv_h, OP_UUU_H, H2, H2, H2, fnmsac16)
RVVCALL(OPFVV3, vfnmsac_vv_w, OP_UUU_W, H4, H4, H4, fnmsac32)
RVVCALL(OPFVV3, vfnmsac_vv_d, OP_UUU_D, H8, H8, H8, fnmsac64)
-GEN_VEXT_VV_ENV(vfnmsac_vv_h)
-GEN_VEXT_VV_ENV(vfnmsac_vv_w)
-GEN_VEXT_VV_ENV(vfnmsac_vv_d)
+GEN_VEXT_VV_ENV(vfnmsac_vv_h, 2)
+GEN_VEXT_VV_ENV(vfnmsac_vv_w, 4)
+GEN_VEXT_VV_ENV(vfnmsac_vv_d, 8)
RVVCALL(OPFVF3, vfnmsac_vf_h, OP_UUU_H, H2, H2, fnmsac16)
RVVCALL(OPFVF3, vfnmsac_vf_w, OP_UUU_W, H4, H4, fnmsac32)
RVVCALL(OPFVF3, vfnmsac_vf_d, OP_UUU_D, H8, H8, fnmsac64)
-GEN_VEXT_VF(vfnmsac_vf_h)
-GEN_VEXT_VF(vfnmsac_vf_w)
-GEN_VEXT_VF(vfnmsac_vf_d)
+GEN_VEXT_VF(vfnmsac_vf_h, 2)
+GEN_VEXT_VF(vfnmsac_vf_w, 4)
+GEN_VEXT_VF(vfnmsac_vf_d, 8)
static uint16_t fmadd16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3394,15 +3406,15 @@ static uint64_t fmadd64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfmadd_vv_h, OP_UUU_H, H2, H2, H2, fmadd16)
RVVCALL(OPFVV3, vfmadd_vv_w, OP_UUU_W, H4, H4, H4, fmadd32)
RVVCALL(OPFVV3, vfmadd_vv_d, OP_UUU_D, H8, H8, H8, fmadd64)
-GEN_VEXT_VV_ENV(vfmadd_vv_h)
-GEN_VEXT_VV_ENV(vfmadd_vv_w)
-GEN_VEXT_VV_ENV(vfmadd_vv_d)
+GEN_VEXT_VV_ENV(vfmadd_vv_h, 2)
+GEN_VEXT_VV_ENV(vfmadd_vv_w, 4)
+GEN_VEXT_VV_ENV(vfmadd_vv_d, 8)
RVVCALL(OPFVF3, vfmadd_vf_h, OP_UUU_H, H2, H2, fmadd16)
RVVCALL(OPFVF3, vfmadd_vf_w, OP_UUU_W, H4, H4, fmadd32)
RVVCALL(OPFVF3, vfmadd_vf_d, OP_UUU_D, H8, H8, fmadd64)
-GEN_VEXT_VF(vfmadd_vf_h)
-GEN_VEXT_VF(vfmadd_vf_w)
-GEN_VEXT_VF(vfmadd_vf_d)
+GEN_VEXT_VF(vfmadd_vf_h, 2)
+GEN_VEXT_VF(vfmadd_vf_w, 4)
+GEN_VEXT_VF(vfmadd_vf_d, 8)
static uint16_t fnmadd16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3425,15 +3437,15 @@ static uint64_t fnmadd64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfnmadd_vv_h, OP_UUU_H, H2, H2, H2, fnmadd16)
RVVCALL(OPFVV3, vfnmadd_vv_w, OP_UUU_W, H4, H4, H4, fnmadd32)
RVVCALL(OPFVV3, vfnmadd_vv_d, OP_UUU_D, H8, H8, H8, fnmadd64)
-GEN_VEXT_VV_ENV(vfnmadd_vv_h)
-GEN_VEXT_VV_ENV(vfnmadd_vv_w)
-GEN_VEXT_VV_ENV(vfnmadd_vv_d)
+GEN_VEXT_VV_ENV(vfnmadd_vv_h, 2)
+GEN_VEXT_VV_ENV(vfnmadd_vv_w, 4)
+GEN_VEXT_VV_ENV(vfnmadd_vv_d, 8)
RVVCALL(OPFVF3, vfnmadd_vf_h, OP_UUU_H, H2, H2, fnmadd16)
RVVCALL(OPFVF3, vfnmadd_vf_w, OP_UUU_W, H4, H4, fnmadd32)
RVVCALL(OPFVF3, vfnmadd_vf_d, OP_UUU_D, H8, H8, fnmadd64)
-GEN_VEXT_VF(vfnmadd_vf_h)
-GEN_VEXT_VF(vfnmadd_vf_w)
-GEN_VEXT_VF(vfnmadd_vf_d)
+GEN_VEXT_VF(vfnmadd_vf_h, 2)
+GEN_VEXT_VF(vfnmadd_vf_w, 4)
+GEN_VEXT_VF(vfnmadd_vf_d, 8)
static uint16_t fmsub16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3453,15 +3465,15 @@ static uint64_t fmsub64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfmsub_vv_h, OP_UUU_H, H2, H2, H2, fmsub16)
RVVCALL(OPFVV3, vfmsub_vv_w, OP_UUU_W, H4, H4, H4, fmsub32)
RVVCALL(OPFVV3, vfmsub_vv_d, OP_UUU_D, H8, H8, H8, fmsub64)
-GEN_VEXT_VV_ENV(vfmsub_vv_h)
-GEN_VEXT_VV_ENV(vfmsub_vv_w)
-GEN_VEXT_VV_ENV(vfmsub_vv_d)
+GEN_VEXT_VV_ENV(vfmsub_vv_h, 2)
+GEN_VEXT_VV_ENV(vfmsub_vv_w, 4)
+GEN_VEXT_VV_ENV(vfmsub_vv_d, 8)
RVVCALL(OPFVF3, vfmsub_vf_h, OP_UUU_H, H2, H2, fmsub16)
RVVCALL(OPFVF3, vfmsub_vf_w, OP_UUU_W, H4, H4, fmsub32)
RVVCALL(OPFVF3, vfmsub_vf_d, OP_UUU_D, H8, H8, fmsub64)
-GEN_VEXT_VF(vfmsub_vf_h)
-GEN_VEXT_VF(vfmsub_vf_w)
-GEN_VEXT_VF(vfmsub_vf_d)
+GEN_VEXT_VF(vfmsub_vf_h, 2)
+GEN_VEXT_VF(vfmsub_vf_w, 4)
+GEN_VEXT_VF(vfmsub_vf_d, 8)
static uint16_t fnmsub16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3481,15 +3493,15 @@ static uint64_t fnmsub64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfnmsub_vv_h, OP_UUU_H, H2, H2, H2, fnmsub16)
RVVCALL(OPFVV3, vfnmsub_vv_w, OP_UUU_W, H4, H4, H4, fnmsub32)
RVVCALL(OPFVV3, vfnmsub_vv_d, OP_UUU_D, H8, H8, H8, fnmsub64)
-GEN_VEXT_VV_ENV(vfnmsub_vv_h)
-GEN_VEXT_VV_ENV(vfnmsub_vv_w)
-GEN_VEXT_VV_ENV(vfnmsub_vv_d)
+GEN_VEXT_VV_ENV(vfnmsub_vv_h, 2)
+GEN_VEXT_VV_ENV(vfnmsub_vv_w, 4)
+GEN_VEXT_VV_ENV(vfnmsub_vv_d, 8)
RVVCALL(OPFVF3, vfnmsub_vf_h, OP_UUU_H, H2, H2, fnmsub16)
RVVCALL(OPFVF3, vfnmsub_vf_w, OP_UUU_W, H4, H4, fnmsub32)
RVVCALL(OPFVF3, vfnmsub_vf_d, OP_UUU_D, H8, H8, fnmsub64)
-GEN_VEXT_VF(vfnmsub_vf_h)
-GEN_VEXT_VF(vfnmsub_vf_w)
-GEN_VEXT_VF(vfnmsub_vf_d)
+GEN_VEXT_VF(vfnmsub_vf_h, 2)
+GEN_VEXT_VF(vfnmsub_vf_w, 4)
+GEN_VEXT_VF(vfnmsub_vf_d, 8)
/* Vector Widening Floating-Point Fused Multiply-Add Instructions */
static uint32_t fwmacc16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
@@ -3506,12 +3518,12 @@ static uint64_t fwmacc32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfwmacc_vv_h, WOP_UUU_H, H4, H2, H2, fwmacc16)
RVVCALL(OPFVV3, vfwmacc_vv_w, WOP_UUU_W, H8, H4, H4, fwmacc32)
-GEN_VEXT_VV_ENV(vfwmacc_vv_h)
-GEN_VEXT_VV_ENV(vfwmacc_vv_w)
+GEN_VEXT_VV_ENV(vfwmacc_vv_h, 4)
+GEN_VEXT_VV_ENV(vfwmacc_vv_w, 8)
RVVCALL(OPFVF3, vfwmacc_vf_h, WOP_UUU_H, H4, H2, fwmacc16)
RVVCALL(OPFVF3, vfwmacc_vf_w, WOP_UUU_W, H8, H4, fwmacc32)
-GEN_VEXT_VF(vfwmacc_vf_h)
-GEN_VEXT_VF(vfwmacc_vf_w)
+GEN_VEXT_VF(vfwmacc_vf_h, 4)
+GEN_VEXT_VF(vfwmacc_vf_w, 8)
static uint32_t fwnmacc16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
{
@@ -3529,12 +3541,12 @@ static uint64_t fwnmacc32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfwnmacc_vv_h, WOP_UUU_H, H4, H2, H2, fwnmacc16)
RVVCALL(OPFVV3, vfwnmacc_vv_w, WOP_UUU_W, H8, H4, H4, fwnmacc32)
-GEN_VEXT_VV_ENV(vfwnmacc_vv_h)
-GEN_VEXT_VV_ENV(vfwnmacc_vv_w)
+GEN_VEXT_VV_ENV(vfwnmacc_vv_h, 4)
+GEN_VEXT_VV_ENV(vfwnmacc_vv_w, 8)
RVVCALL(OPFVF3, vfwnmacc_vf_h, WOP_UUU_H, H4, H2, fwnmacc16)
RVVCALL(OPFVF3, vfwnmacc_vf_w, WOP_UUU_W, H8, H4, fwnmacc32)
-GEN_VEXT_VF(vfwnmacc_vf_h)
-GEN_VEXT_VF(vfwnmacc_vf_w)
+GEN_VEXT_VF(vfwnmacc_vf_h, 4)
+GEN_VEXT_VF(vfwnmacc_vf_w, 8)
static uint32_t fwmsac16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
{
@@ -3552,12 +3564,12 @@ static uint64_t fwmsac32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfwmsac_vv_h, WOP_UUU_H, H4, H2, H2, fwmsac16)
RVVCALL(OPFVV3, vfwmsac_vv_w, WOP_UUU_W, H8, H4, H4, fwmsac32)
-GEN_VEXT_VV_ENV(vfwmsac_vv_h)
-GEN_VEXT_VV_ENV(vfwmsac_vv_w)
+GEN_VEXT_VV_ENV(vfwmsac_vv_h, 4)
+GEN_VEXT_VV_ENV(vfwmsac_vv_w, 8)
RVVCALL(OPFVF3, vfwmsac_vf_h, WOP_UUU_H, H4, H2, fwmsac16)
RVVCALL(OPFVF3, vfwmsac_vf_w, WOP_UUU_W, H8, H4, fwmsac32)
-GEN_VEXT_VF(vfwmsac_vf_h)
-GEN_VEXT_VF(vfwmsac_vf_w)
+GEN_VEXT_VF(vfwmsac_vf_h, 4)
+GEN_VEXT_VF(vfwmsac_vf_w, 8)
static uint32_t fwnmsac16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
{
@@ -3575,12 +3587,12 @@ static uint64_t fwnmsac32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfwnmsac_vv_h, WOP_UUU_H, H4, H2, H2, fwnmsac16)
RVVCALL(OPFVV3, vfwnmsac_vv_w, WOP_UUU_W, H8, H4, H4, fwnmsac32)
-GEN_VEXT_VV_ENV(vfwnmsac_vv_h)
-GEN_VEXT_VV_ENV(vfwnmsac_vv_w)
+GEN_VEXT_VV_ENV(vfwnmsac_vv_h, 4)
+GEN_VEXT_VV_ENV(vfwnmsac_vv_w, 8)
RVVCALL(OPFVF3, vfwnmsac_vf_h, WOP_UUU_H, H4, H2, fwnmsac16)
RVVCALL(OPFVF3, vfwnmsac_vf_w, WOP_UUU_W, H8, H4, fwnmsac32)
-GEN_VEXT_VF(vfwnmsac_vf_h)
-GEN_VEXT_VF(vfwnmsac_vf_w)
+GEN_VEXT_VF(vfwnmsac_vf_h, 4)
+GEN_VEXT_VF(vfwnmsac_vf_w, 8)
/* Vector Floating-Point Square-Root Instruction */
/* (TD, T2, TX2) */
@@ -3596,12 +3608,15 @@ static void do_##NAME(void *vd, void *vs2, int i, \
*((TD *)vd + HD(i)) = OP(s2, &env->fp_status); \
}
-#define GEN_VEXT_V_ENV(NAME) \
+#define GEN_VEXT_V_ENV(NAME, ESZ) \
void HELPER(NAME)(void *vd, void *v0, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t total_elems = \
+ vext_get_total_elems(env, desc, ESZ); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
if (vl == 0) { \
@@ -3614,14 +3629,16 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \
do_##NAME(vd, vs2, i, env); \
} \
env->vstart = 0; \
+ vext_set_elems_1s(vd, vta, vl * ESZ, \
+ total_elems * ESZ); \
}
RVVCALL(OPFVV1, vfsqrt_v_h, OP_UU_H, H2, H2, float16_sqrt)
RVVCALL(OPFVV1, vfsqrt_v_w, OP_UU_W, H4, H4, float32_sqrt)
RVVCALL(OPFVV1, vfsqrt_v_d, OP_UU_D, H8, H8, float64_sqrt)
-GEN_VEXT_V_ENV(vfsqrt_v_h)
-GEN_VEXT_V_ENV(vfsqrt_v_w)
-GEN_VEXT_V_ENV(vfsqrt_v_d)
+GEN_VEXT_V_ENV(vfsqrt_v_h, 2)
+GEN_VEXT_V_ENV(vfsqrt_v_w, 4)
+GEN_VEXT_V_ENV(vfsqrt_v_d, 8)
/*
* Vector Floating-Point Reciprocal Square-Root Estimate Instruction
@@ -3801,9 +3818,9 @@ static float64 frsqrt7_d(float64 f, float_status *s)
RVVCALL(OPFVV1, vfrsqrt7_v_h, OP_UU_H, H2, H2, frsqrt7_h)
RVVCALL(OPFVV1, vfrsqrt7_v_w, OP_UU_W, H4, H4, frsqrt7_s)
RVVCALL(OPFVV1, vfrsqrt7_v_d, OP_UU_D, H8, H8, frsqrt7_d)
-GEN_VEXT_V_ENV(vfrsqrt7_v_h)
-GEN_VEXT_V_ENV(vfrsqrt7_v_w)
-GEN_VEXT_V_ENV(vfrsqrt7_v_d)
+GEN_VEXT_V_ENV(vfrsqrt7_v_h, 2)
+GEN_VEXT_V_ENV(vfrsqrt7_v_w, 4)
+GEN_VEXT_V_ENV(vfrsqrt7_v_d, 8)
/*
* Vector Floating-Point Reciprocal Estimate Instruction
@@ -3992,36 +4009,36 @@ static float64 frec7_d(float64 f, float_status *s)
RVVCALL(OPFVV1, vfrec7_v_h, OP_UU_H, H2, H2, frec7_h)
RVVCALL(OPFVV1, vfrec7_v_w, OP_UU_W, H4, H4, frec7_s)
RVVCALL(OPFVV1, vfrec7_v_d, OP_UU_D, H8, H8, frec7_d)
-GEN_VEXT_V_ENV(vfrec7_v_h)
-GEN_VEXT_V_ENV(vfrec7_v_w)
-GEN_VEXT_V_ENV(vfrec7_v_d)
+GEN_VEXT_V_ENV(vfrec7_v_h, 2)
+GEN_VEXT_V_ENV(vfrec7_v_w, 4)
+GEN_VEXT_V_ENV(vfrec7_v_d, 8)
/* Vector Floating-Point MIN/MAX Instructions */
RVVCALL(OPFVV2, vfmin_vv_h, OP_UUU_H, H2, H2, H2, float16_minimum_number)
RVVCALL(OPFVV2, vfmin_vv_w, OP_UUU_W, H4, H4, H4, float32_minimum_number)
RVVCALL(OPFVV2, vfmin_vv_d, OP_UUU_D, H8, H8, H8, float64_minimum_number)
-GEN_VEXT_VV_ENV(vfmin_vv_h)
-GEN_VEXT_VV_ENV(vfmin_vv_w)
-GEN_VEXT_VV_ENV(vfmin_vv_d)
+GEN_VEXT_VV_ENV(vfmin_vv_h, 2)
+GEN_VEXT_VV_ENV(vfmin_vv_w, 4)
+GEN_VEXT_VV_ENV(vfmin_vv_d, 8)
RVVCALL(OPFVF2, vfmin_vf_h, OP_UUU_H, H2, H2, float16_minimum_number)
RVVCALL(OPFVF2, vfmin_vf_w, OP_UUU_W, H4, H4, float32_minimum_number)
RVVCALL(OPFVF2, vfmin_vf_d, OP_UUU_D, H8, H8, float64_minimum_number)
-GEN_VEXT_VF(vfmin_vf_h)
-GEN_VEXT_VF(vfmin_vf_w)
-GEN_VEXT_VF(vfmin_vf_d)
+GEN_VEXT_VF(vfmin_vf_h, 2)
+GEN_VEXT_VF(vfmin_vf_w, 4)
+GEN_VEXT_VF(vfmin_vf_d, 8)
RVVCALL(OPFVV2, vfmax_vv_h, OP_UUU_H, H2, H2, H2, float16_maximum_number)
RVVCALL(OPFVV2, vfmax_vv_w, OP_UUU_W, H4, H4, H4, float32_maximum_number)
RVVCALL(OPFVV2, vfmax_vv_d, OP_UUU_D, H8, H8, H8, float64_maximum_number)
-GEN_VEXT_VV_ENV(vfmax_vv_h)
-GEN_VEXT_VV_ENV(vfmax_vv_w)
-GEN_VEXT_VV_ENV(vfmax_vv_d)
+GEN_VEXT_VV_ENV(vfmax_vv_h, 2)
+GEN_VEXT_VV_ENV(vfmax_vv_w, 4)
+GEN_VEXT_VV_ENV(vfmax_vv_d, 8)
RVVCALL(OPFVF2, vfmax_vf_h, OP_UUU_H, H2, H2, float16_maximum_number)
RVVCALL(OPFVF2, vfmax_vf_w, OP_UUU_W, H4, H4, float32_maximum_number)
RVVCALL(OPFVF2, vfmax_vf_d, OP_UUU_D, H8, H8, float64_maximum_number)
-GEN_VEXT_VF(vfmax_vf_h)
-GEN_VEXT_VF(vfmax_vf_w)
-GEN_VEXT_VF(vfmax_vf_d)
+GEN_VEXT_VF(vfmax_vf_h, 2)
+GEN_VEXT_VF(vfmax_vf_w, 4)
+GEN_VEXT_VF(vfmax_vf_d, 8)
/* Vector Floating-Point Sign-Injection Instructions */
static uint16_t fsgnj16(uint16_t a, uint16_t b, float_status *s)
@@ -4042,15 +4059,15 @@ static uint64_t fsgnj64(uint64_t a, uint64_t b, float_status *s)
RVVCALL(OPFVV2, vfsgnj_vv_h, OP_UUU_H, H2, H2, H2, fsgnj16)
RVVCALL(OPFVV2, vfsgnj_vv_w, OP_UUU_W, H4, H4, H4, fsgnj32)
RVVCALL(OPFVV2, vfsgnj_vv_d, OP_UUU_D, H8, H8, H8, fsgnj64)
-GEN_VEXT_VV_ENV(vfsgnj_vv_h)
-GEN_VEXT_VV_ENV(vfsgnj_vv_w)
-GEN_VEXT_VV_ENV(vfsgnj_vv_d)
+GEN_VEXT_VV_ENV(vfsgnj_vv_h, 2)
+GEN_VEXT_VV_ENV(vfsgnj_vv_w, 4)
+GEN_VEXT_VV_ENV(vfsgnj_vv_d, 8)
RVVCALL(OPFVF2, vfsgnj_vf_h, OP_UUU_H, H2, H2, fsgnj16)
RVVCALL(OPFVF2, vfsgnj_vf_w, OP_UUU_W, H4, H4, fsgnj32)
RVVCALL(OPFVF2, vfsgnj_vf_d, OP_UUU_D, H8, H8, fsgnj64)
-GEN_VEXT_VF(vfsgnj_vf_h)
-GEN_VEXT_VF(vfsgnj_vf_w)
-GEN_VEXT_VF(vfsgnj_vf_d)
+GEN_VEXT_VF(vfsgnj_vf_h, 2)
+GEN_VEXT_VF(vfsgnj_vf_w, 4)
+GEN_VEXT_VF(vfsgnj_vf_d, 8)
static uint16_t fsgnjn16(uint16_t a, uint16_t b, float_status *s)
{
@@ -4070,15 +4087,15 @@ static uint64_t fsgnjn64(uint64_t a, uint64_t b, float_status *s)
RVVCALL(OPFVV2, vfsgnjn_vv_h, OP_UUU_H, H2, H2, H2, fsgnjn16)
RVVCALL(OPFVV2, vfsgnjn_vv_w, OP_UUU_W, H4, H4, H4, fsgnjn32)
RVVCALL(OPFVV2, vfsgnjn_vv_d, OP_UUU_D, H8, H8, H8, fsgnjn64)
-GEN_VEXT_VV_ENV(vfsgnjn_vv_h)
-GEN_VEXT_VV_ENV(vfsgnjn_vv_w)
-GEN_VEXT_VV_ENV(vfsgnjn_vv_d)
+GEN_VEXT_VV_ENV(vfsgnjn_vv_h, 2)
+GEN_VEXT_VV_ENV(vfsgnjn_vv_w, 4)
+GEN_VEXT_VV_ENV(vfsgnjn_vv_d, 8)
RVVCALL(OPFVF2, vfsgnjn_vf_h, OP_UUU_H, H2, H2, fsgnjn16)
RVVCALL(OPFVF2, vfsgnjn_vf_w, OP_UUU_W, H4, H4, fsgnjn32)
RVVCALL(OPFVF2, vfsgnjn_vf_d, OP_UUU_D, H8, H8, fsgnjn64)
-GEN_VEXT_VF(vfsgnjn_vf_h)
-GEN_VEXT_VF(vfsgnjn_vf_w)
-GEN_VEXT_VF(vfsgnjn_vf_d)
+GEN_VEXT_VF(vfsgnjn_vf_h, 2)
+GEN_VEXT_VF(vfsgnjn_vf_w, 4)
+GEN_VEXT_VF(vfsgnjn_vf_d, 8)
static uint16_t fsgnjx16(uint16_t a, uint16_t b, float_status *s)
{
@@ -4098,15 +4115,15 @@ static uint64_t fsgnjx64(uint64_t a, uint64_t b, float_status *s)
RVVCALL(OPFVV2, vfsgnjx_vv_h, OP_UUU_H, H2, H2, H2, fsgnjx16)
RVVCALL(OPFVV2, vfsgnjx_vv_w, OP_UUU_W, H4, H4, H4, fsgnjx32)
RVVCALL(OPFVV2, vfsgnjx_vv_d, OP_UUU_D, H8, H8, H8, fsgnjx64)
-GEN_VEXT_VV_ENV(vfsgnjx_vv_h)
-GEN_VEXT_VV_ENV(vfsgnjx_vv_w)
-GEN_VEXT_VV_ENV(vfsgnjx_vv_d)
+GEN_VEXT_VV_ENV(vfsgnjx_vv_h, 2)
+GEN_VEXT_VV_ENV(vfsgnjx_vv_w, 4)
+GEN_VEXT_VV_ENV(vfsgnjx_vv_d, 8)
RVVCALL(OPFVF2, vfsgnjx_vf_h, OP_UUU_H, H2, H2, fsgnjx16)
RVVCALL(OPFVF2, vfsgnjx_vf_w, OP_UUU_W, H4, H4, fsgnjx32)
RVVCALL(OPFVF2, vfsgnjx_vf_d, OP_UUU_D, H8, H8, fsgnjx64)
-GEN_VEXT_VF(vfsgnjx_vf_h)
-GEN_VEXT_VF(vfsgnjx_vf_w)
-GEN_VEXT_VF(vfsgnjx_vf_d)
+GEN_VEXT_VF(vfsgnjx_vf_h, 2)
+GEN_VEXT_VF(vfsgnjx_vf_w, 4)
+GEN_VEXT_VF(vfsgnjx_vf_d, 8)
/* Vector Floating-Point Compare Instructions */
#define GEN_VEXT_CMP_VV_ENV(NAME, ETYPE, H, DO_OP) \
@@ -4115,6 +4132,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t total_elems = env_archcpu(env)->cfg.vlen; \
+ uint32_t vta_all_1s = vext_vta_all_1s(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -4127,6 +4146,13 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
DO_OP(s2, s1, &env->fp_status)); \
} \
env->vstart = 0; \
+ /* mask destination register are always tail-agnostic */ \
+ /* set tail elements to 1s */ \
+ if (vta_all_1s) { \
+ for (; i < total_elems; i++) { \
+ vext_set_elem_mask(vd, i, 1); \
+ } \
+ } \
}
GEN_VEXT_CMP_VV_ENV(vmfeq_vv_h, uint16_t, H2, float16_eq_quiet)
@@ -4139,6 +4165,8 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t total_elems = env_archcpu(env)->cfg.vlen; \
+ uint32_t vta_all_1s = vext_vta_all_1s(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -4150,6 +4178,13 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \
DO_OP(s2, (ETYPE)s1, &env->fp_status)); \
} \
env->vstart = 0; \
+ /* mask destination register are always tail-agnostic */ \
+ /* set tail elements to 1s */ \
+ if (vta_all_1s) { \
+ for (; i < total_elems; i++) { \
+ vext_set_elem_mask(vd, i, 1); \
+ } \
+ } \
}
GEN_VEXT_CMP_VF(vmfeq_vf_h, uint16_t, H2, float16_eq_quiet)
@@ -4250,12 +4285,15 @@ static void do_##NAME(void *vd, void *vs2, int i) \
*((TD *)vd + HD(i)) = OP(s2); \
}
-#define GEN_VEXT_V(NAME) \
+#define GEN_VEXT_V(NAME, ESZ) \
void HELPER(NAME)(void *vd, void *v0, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t total_elems = \
+ vext_get_total_elems(env, desc, ESZ); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -4265,6 +4303,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \
do_##NAME(vd, vs2, i); \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * ESZ, \
+ total_elems * ESZ); \
}
target_ulong fclass_h(uint64_t frs1)
@@ -4327,17 +4368,22 @@ target_ulong fclass_d(uint64_t frs1)
RVVCALL(OPIVV1, vfclass_v_h, OP_UU_H, H2, H2, fclass_h)
RVVCALL(OPIVV1, vfclass_v_w, OP_UU_W, H4, H4, fclass_s)
RVVCALL(OPIVV1, vfclass_v_d, OP_UU_D, H8, H8, fclass_d)
-GEN_VEXT_V(vfclass_v_h)
-GEN_VEXT_V(vfclass_v_w)
-GEN_VEXT_V(vfclass_v_d)
+GEN_VEXT_V(vfclass_v_h, 2)
+GEN_VEXT_V(vfclass_v_w, 4)
+GEN_VEXT_V(vfclass_v_d, 8)
/* Vector Floating-Point Merge Instruction */
+
#define GEN_VFMERGE_VF(NAME, ETYPE, H) \
void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = \
+ vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -4346,6 +4392,8 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \
= (!vm && !vext_elem_mask(v0, i) ? s2 : s1); \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VFMERGE_VF(vfmerge_vfm_h, int16_t, H2)
@@ -4357,33 +4405,33 @@ GEN_VFMERGE_VF(vfmerge_vfm_d, int64_t, H8)
RVVCALL(OPFVV1, vfcvt_xu_f_v_h, OP_UU_H, H2, H2, float16_to_uint16)
RVVCALL(OPFVV1, vfcvt_xu_f_v_w, OP_UU_W, H4, H4, float32_to_uint32)
RVVCALL(OPFVV1, vfcvt_xu_f_v_d, OP_UU_D, H8, H8, float64_to_uint64)
-GEN_VEXT_V_ENV(vfcvt_xu_f_v_h)
-GEN_VEXT_V_ENV(vfcvt_xu_f_v_w)
-GEN_VEXT_V_ENV(vfcvt_xu_f_v_d)
+GEN_VEXT_V_ENV(vfcvt_xu_f_v_h, 2)
+GEN_VEXT_V_ENV(vfcvt_xu_f_v_w, 4)
+GEN_VEXT_V_ENV(vfcvt_xu_f_v_d, 8)
/* vfcvt.x.f.v vd, vs2, vm # Convert float to signed integer. */
RVVCALL(OPFVV1, vfcvt_x_f_v_h, OP_UU_H, H2, H2, float16_to_int16)
RVVCALL(OPFVV1, vfcvt_x_f_v_w, OP_UU_W, H4, H4, float32_to_int32)
RVVCALL(OPFVV1, vfcvt_x_f_v_d, OP_UU_D, H8, H8, float64_to_int64)
-GEN_VEXT_V_ENV(vfcvt_x_f_v_h)
-GEN_VEXT_V_ENV(vfcvt_x_f_v_w)
-GEN_VEXT_V_ENV(vfcvt_x_f_v_d)
+GEN_VEXT_V_ENV(vfcvt_x_f_v_h, 2)
+GEN_VEXT_V_ENV(vfcvt_x_f_v_w, 4)
+GEN_VEXT_V_ENV(vfcvt_x_f_v_d, 8)
/* vfcvt.f.xu.v vd, vs2, vm # Convert unsigned integer to float. */
RVVCALL(OPFVV1, vfcvt_f_xu_v_h, OP_UU_H, H2, H2, uint16_to_float16)
RVVCALL(OPFVV1, vfcvt_f_xu_v_w, OP_UU_W, H4, H4, uint32_to_float32)
RVVCALL(OPFVV1, vfcvt_f_xu_v_d, OP_UU_D, H8, H8, uint64_to_float64)
-GEN_VEXT_V_ENV(vfcvt_f_xu_v_h)
-GEN_VEXT_V_ENV(vfcvt_f_xu_v_w)
-GEN_VEXT_V_ENV(vfcvt_f_xu_v_d)
+GEN_VEXT_V_ENV(vfcvt_f_xu_v_h, 2)
+GEN_VEXT_V_ENV(vfcvt_f_xu_v_w, 4)
+GEN_VEXT_V_ENV(vfcvt_f_xu_v_d, 8)
/* vfcvt.f.x.v vd, vs2, vm # Convert integer to float. */
RVVCALL(OPFVV1, vfcvt_f_x_v_h, OP_UU_H, H2, H2, int16_to_float16)
RVVCALL(OPFVV1, vfcvt_f_x_v_w, OP_UU_W, H4, H4, int32_to_float32)
RVVCALL(OPFVV1, vfcvt_f_x_v_d, OP_UU_D, H8, H8, int64_to_float64)
-GEN_VEXT_V_ENV(vfcvt_f_x_v_h)
-GEN_VEXT_V_ENV(vfcvt_f_x_v_w)
-GEN_VEXT_V_ENV(vfcvt_f_x_v_d)
+GEN_VEXT_V_ENV(vfcvt_f_x_v_h, 2)
+GEN_VEXT_V_ENV(vfcvt_f_x_v_w, 4)
+GEN_VEXT_V_ENV(vfcvt_f_x_v_d, 8)
/* Widening Floating-Point/Integer Type-Convert Instructions */
/* (TD, T2, TX2) */
@@ -4393,30 +4441,30 @@ GEN_VEXT_V_ENV(vfcvt_f_x_v_d)
/* vfwcvt.xu.f.v vd, vs2, vm # Convert float to double-width unsigned integer.*/
RVVCALL(OPFVV1, vfwcvt_xu_f_v_h, WOP_UU_H, H4, H2, float16_to_uint32)
RVVCALL(OPFVV1, vfwcvt_xu_f_v_w, WOP_UU_W, H8, H4, float32_to_uint64)
-GEN_VEXT_V_ENV(vfwcvt_xu_f_v_h)
-GEN_VEXT_V_ENV(vfwcvt_xu_f_v_w)
+GEN_VEXT_V_ENV(vfwcvt_xu_f_v_h, 4)
+GEN_VEXT_V_ENV(vfwcvt_xu_f_v_w, 8)
/* vfwcvt.x.f.v vd, vs2, vm # Convert float to double-width signed integer. */
RVVCALL(OPFVV1, vfwcvt_x_f_v_h, WOP_UU_H, H4, H2, float16_to_int32)
RVVCALL(OPFVV1, vfwcvt_x_f_v_w, WOP_UU_W, H8, H4, float32_to_int64)
-GEN_VEXT_V_ENV(vfwcvt_x_f_v_h)
-GEN_VEXT_V_ENV(vfwcvt_x_f_v_w)
+GEN_VEXT_V_ENV(vfwcvt_x_f_v_h, 4)
+GEN_VEXT_V_ENV(vfwcvt_x_f_v_w, 8)
/* vfwcvt.f.xu.v vd, vs2, vm # Convert unsigned integer to double-width float */
RVVCALL(OPFVV1, vfwcvt_f_xu_v_b, WOP_UU_B, H2, H1, uint8_to_float16)
RVVCALL(OPFVV1, vfwcvt_f_xu_v_h, WOP_UU_H, H4, H2, uint16_to_float32)
RVVCALL(OPFVV1, vfwcvt_f_xu_v_w, WOP_UU_W, H8, H4, uint32_to_float64)
-GEN_VEXT_V_ENV(vfwcvt_f_xu_v_b)
-GEN_VEXT_V_ENV(vfwcvt_f_xu_v_h)
-GEN_VEXT_V_ENV(vfwcvt_f_xu_v_w)
+GEN_VEXT_V_ENV(vfwcvt_f_xu_v_b, 2)
+GEN_VEXT_V_ENV(vfwcvt_f_xu_v_h, 4)
+GEN_VEXT_V_ENV(vfwcvt_f_xu_v_w, 8)
/* vfwcvt.f.x.v vd, vs2, vm # Convert integer to double-width float. */
RVVCALL(OPFVV1, vfwcvt_f_x_v_b, WOP_UU_B, H2, H1, int8_to_float16)
RVVCALL(OPFVV1, vfwcvt_f_x_v_h, WOP_UU_H, H4, H2, int16_to_float32)
RVVCALL(OPFVV1, vfwcvt_f_x_v_w, WOP_UU_W, H8, H4, int32_to_float64)
-GEN_VEXT_V_ENV(vfwcvt_f_x_v_b)
-GEN_VEXT_V_ENV(vfwcvt_f_x_v_h)
-GEN_VEXT_V_ENV(vfwcvt_f_x_v_w)
+GEN_VEXT_V_ENV(vfwcvt_f_x_v_b, 2)
+GEN_VEXT_V_ENV(vfwcvt_f_x_v_h, 4)
+GEN_VEXT_V_ENV(vfwcvt_f_x_v_w, 8)
/*
* vfwcvt.f.f.v vd, vs2, vm
@@ -4429,8 +4477,8 @@ static uint32_t vfwcvtffv16(uint16_t a, float_status *s)
RVVCALL(OPFVV1, vfwcvt_f_f_v_h, WOP_UU_H, H4, H2, vfwcvtffv16)
RVVCALL(OPFVV1, vfwcvt_f_f_v_w, WOP_UU_W, H8, H4, float32_to_float64)
-GEN_VEXT_V_ENV(vfwcvt_f_f_v_h)
-GEN_VEXT_V_ENV(vfwcvt_f_f_v_w)
+GEN_VEXT_V_ENV(vfwcvt_f_f_v_h, 4)
+GEN_VEXT_V_ENV(vfwcvt_f_f_v_w, 8)
/* Narrowing Floating-Point/Integer Type-Convert Instructions */
/* (TD, T2, TX2) */
@@ -4441,29 +4489,29 @@ GEN_VEXT_V_ENV(vfwcvt_f_f_v_w)
RVVCALL(OPFVV1, vfncvt_xu_f_w_b, NOP_UU_B, H1, H2, float16_to_uint8)
RVVCALL(OPFVV1, vfncvt_xu_f_w_h, NOP_UU_H, H2, H4, float32_to_uint16)
RVVCALL(OPFVV1, vfncvt_xu_f_w_w, NOP_UU_W, H4, H8, float64_to_uint32)
-GEN_VEXT_V_ENV(vfncvt_xu_f_w_b)
-GEN_VEXT_V_ENV(vfncvt_xu_f_w_h)
-GEN_VEXT_V_ENV(vfncvt_xu_f_w_w)
+GEN_VEXT_V_ENV(vfncvt_xu_f_w_b, 1)
+GEN_VEXT_V_ENV(vfncvt_xu_f_w_h, 2)
+GEN_VEXT_V_ENV(vfncvt_xu_f_w_w, 4)
/* vfncvt.x.f.v vd, vs2, vm # Convert double-width float to signed integer. */
RVVCALL(OPFVV1, vfncvt_x_f_w_b, NOP_UU_B, H1, H2, float16_to_int8)
RVVCALL(OPFVV1, vfncvt_x_f_w_h, NOP_UU_H, H2, H4, float32_to_int16)
RVVCALL(OPFVV1, vfncvt_x_f_w_w, NOP_UU_W, H4, H8, float64_to_int32)
-GEN_VEXT_V_ENV(vfncvt_x_f_w_b)
-GEN_VEXT_V_ENV(vfncvt_x_f_w_h)
-GEN_VEXT_V_ENV(vfncvt_x_f_w_w)
+GEN_VEXT_V_ENV(vfncvt_x_f_w_b, 1)
+GEN_VEXT_V_ENV(vfncvt_x_f_w_h, 2)
+GEN_VEXT_V_ENV(vfncvt_x_f_w_w, 4)
/* vfncvt.f.xu.v vd, vs2, vm # Convert double-width unsigned integer to float */
RVVCALL(OPFVV1, vfncvt_f_xu_w_h, NOP_UU_H, H2, H4, uint32_to_float16)
RVVCALL(OPFVV1, vfncvt_f_xu_w_w, NOP_UU_W, H4, H8, uint64_to_float32)
-GEN_VEXT_V_ENV(vfncvt_f_xu_w_h)
-GEN_VEXT_V_ENV(vfncvt_f_xu_w_w)
+GEN_VEXT_V_ENV(vfncvt_f_xu_w_h, 2)
+GEN_VEXT_V_ENV(vfncvt_f_xu_w_w, 4)
/* vfncvt.f.x.v vd, vs2, vm # Convert double-width integer to float. */
RVVCALL(OPFVV1, vfncvt_f_x_w_h, NOP_UU_H, H2, H4, int32_to_float16)
RVVCALL(OPFVV1, vfncvt_f_x_w_w, NOP_UU_W, H4, H8, int64_to_float32)
-GEN_VEXT_V_ENV(vfncvt_f_x_w_h)
-GEN_VEXT_V_ENV(vfncvt_f_x_w_w)
+GEN_VEXT_V_ENV(vfncvt_f_x_w_h, 2)
+GEN_VEXT_V_ENV(vfncvt_f_x_w_w, 4)
/* vfncvt.f.f.v vd, vs2, vm # Convert double float to single-width float. */
static uint16_t vfncvtffv16(uint32_t a, float_status *s)
@@ -4473,8 +4521,8 @@ static uint16_t vfncvtffv16(uint32_t a, float_status *s)
RVVCALL(OPFVV1, vfncvt_f_f_w_h, NOP_UU_H, H2, H4, vfncvtffv16)
RVVCALL(OPFVV1, vfncvt_f_f_w_w, NOP_UU_W, H4, H8, float64_to_float32)
-GEN_VEXT_V_ENV(vfncvt_f_f_w_h)
-GEN_VEXT_V_ENV(vfncvt_f_f_w_w)
+GEN_VEXT_V_ENV(vfncvt_f_f_w_h, 2)
+GEN_VEXT_V_ENV(vfncvt_f_f_w_w, 4)
/*
*** Vector Reduction Operations
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 13/16] target/riscv: rvv: Add tail agnostic for vector reduction instructions
2022-05-13 11:49 [PATCH qemu v18 00/16] Add tail agnostic behavior for rvv instructions ~eopxd
@ 2022-05-13 11:50 ` ~eopxd
2022-05-13 11:50 ` ~eopxd
` (15 subsequent siblings)
16 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-03-07 12:21 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/vector_helper.c | 20 ++++++++++++++++++++
1 file changed, 20 insertions(+)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 8ac7fabb05..2ab4308ef0 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4534,6 +4534,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(TD); \
+ uint32_t vlenb = simd_maxsz(desc); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
TD s1 = *((TD *)vs1 + HD(0)); \
\
@@ -4546,6 +4549,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
} \
*((TD *)vd + HD(0)) = s1; \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, esz, vlenb); \
}
/* vd[0] = sum(vs1[0], vs2[*]) */
@@ -4615,6 +4620,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(TD); \
+ uint32_t vlenb = simd_maxsz(desc); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
TD s1 = *((TD *)vs1 + HD(0)); \
\
@@ -4627,6 +4635,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
} \
*((TD *)vd + HD(0)) = s1; \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, esz, vlenb); \
}
/* Unordered sum */
@@ -4651,6 +4661,9 @@ void HELPER(vfwredsum_vs_h)(void *vd, void *v0, void *vs1,
{
uint32_t vm = vext_vm(desc);
uint32_t vl = env->vl;
+ uint32_t esz = sizeof(uint32_t);
+ uint32_t vlenb = simd_maxsz(desc);
+ uint32_t vta = vext_vta(desc);
uint32_t i;
uint32_t s1 = *((uint32_t *)vs1 + H4(0));
@@ -4664,6 +4677,8 @@ void HELPER(vfwredsum_vs_h)(void *vd, void *v0, void *vs1,
}
*((uint32_t *)vd + H4(0)) = s1;
env->vstart = 0;
+ /* set tail elements to 1s */
+ vext_set_elems_1s(vd, vta, esz, vlenb);
}
void HELPER(vfwredsum_vs_w)(void *vd, void *v0, void *vs1,
@@ -4671,6 +4686,9 @@ void HELPER(vfwredsum_vs_w)(void *vd, void *v0, void *vs1,
{
uint32_t vm = vext_vm(desc);
uint32_t vl = env->vl;
+ uint32_t esz = sizeof(uint64_t);
+ uint32_t vlenb = simd_maxsz(desc);
+ uint32_t vta = vext_vta(desc);
uint32_t i;
uint64_t s1 = *((uint64_t *)vs1);
@@ -4684,6 +4702,8 @@ void HELPER(vfwredsum_vs_w)(void *vd, void *v0, void *vs1,
}
*((uint64_t *)vd) = s1;
env->vstart = 0;
+ /* set tail elements to 1s */
+ vext_set_elems_1s(vd, vta, esz, vlenb);
}
/*
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 14/16] target/riscv: rvv: Add tail agnostic for vector mask instructions
2022-05-13 11:49 [PATCH qemu v18 00/16] Add tail agnostic behavior for rvv instructions ~eopxd
@ 2022-05-13 11:50 ` ~eopxd
2022-05-13 11:50 ` ~eopxd
` (15 subsequent siblings)
16 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-03-07 15:26 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
The tail elements in the destination mask register are updated under
a tail-agnostic policy.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/insn_trans/trans_rvv.c.inc | 6 +++++
target/riscv/vector_helper.c | 30 +++++++++++++++++++++++++
2 files changed, 36 insertions(+)
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index 76dee1ba20..430d4e4460 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -3131,6 +3131,8 @@ static bool trans_##NAME(DisasContext *s, arg_r *a) \
tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = \
+ FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);\
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs1), \
vreg_ofs(s, a->rs2), cpu_env, \
@@ -3235,6 +3237,8 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = \
+ FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);\
tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), \
vreg_ofs(s, 0), vreg_ofs(s, a->rs2), \
cpu_env, s->cfg_ptr->vlen / 8, \
@@ -3272,6 +3276,7 @@ static bool trans_viota_m(DisasContext *s, arg_viota_m *a)
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
static gen_helper_gvec_3_ptr * const fns[4] = {
gen_helper_viota_m_b, gen_helper_viota_m_h,
gen_helper_viota_m_w, gen_helper_viota_m_d,
@@ -3301,6 +3306,7 @@ static bool trans_vid_v(DisasContext *s, arg_vid_v *a)
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
static gen_helper_gvec_2_ptr * const fns[4] = {
gen_helper_vid_v_b, gen_helper_vid_v_h,
gen_helper_vid_v_w, gen_helper_vid_v_d,
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 2ab4308ef0..5c2d1c02f4 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4716,6 +4716,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
uint32_t desc) \
{ \
uint32_t vl = env->vl; \
+ uint32_t total_elems = env_archcpu(env)->cfg.vlen; \
+ uint32_t vta_all_1s = vext_vta_all_1s(desc); \
uint32_t i; \
int a, b; \
\
@@ -4725,6 +4727,15 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
vext_set_elem_mask(vd, i, OP(b, a)); \
} \
env->vstart = 0; \
+ /* mask destination register are always tail- \
+ * agnostic \
+ */ \
+ /* set tail elements to 1s */ \
+ if (vta_all_1s) { \
+ for (; i < total_elems; i++) { \
+ vext_set_elem_mask(vd, i, 1); \
+ } \
+ } \
}
#define DO_NAND(N, M) (!(N & M))
@@ -4792,6 +4803,8 @@ static void vmsetm(void *vd, void *v0, void *vs2, CPURISCVState *env,
{
uint32_t vm = vext_vm(desc);
uint32_t vl = env->vl;
+ uint32_t total_elems = env_archcpu(env)->cfg.vlen;
+ uint32_t vta_all_1s = vext_vta_all_1s(desc);
int i;
bool first_mask_bit = false;
@@ -4820,6 +4833,13 @@ static void vmsetm(void *vd, void *v0, void *vs2, CPURISCVState *env,
}
}
env->vstart = 0;
+ /* mask destination register are always tail-agnostic */
+ /* set tail elements to 1s */
+ if (vta_all_1s) {
+ for (; i < total_elems; i++) {
+ vext_set_elem_mask(vd, i, 1);
+ }
+ }
}
void HELPER(vmsbf_m)(void *vd, void *v0, void *vs2, CPURISCVState *env,
@@ -4847,6 +4867,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, CPURISCVState *env, \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t sum = 0; \
int i; \
\
@@ -4860,6 +4883,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, CPURISCVState *env, \
} \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VEXT_VIOTA_M(viota_m_b, uint8_t, H1)
@@ -4873,6 +4898,9 @@ void HELPER(NAME)(void *vd, void *v0, CPURISCVState *env, uint32_t desc) \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
int i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -4882,6 +4910,8 @@ void HELPER(NAME)(void *vd, void *v0, CPURISCVState *env, uint32_t desc) \
*((ETYPE *)vd + H(i)) = i; \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VEXT_VID_V(vid_v_b, uint8_t, H1)
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 15/16] target/riscv: rvv: Add tail agnostic for vector permutation instructions
2022-05-13 11:49 [PATCH qemu v18 00/16] Add tail agnostic behavior for rvv instructions ~eopxd
@ 2022-05-13 11:50 ` ~eopxd
2022-05-13 11:50 ` ~eopxd
` (15 subsequent siblings)
16 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-03-07 15:59 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/insn_trans/trans_rvv.c.inc | 7 +++--
target/riscv/vector_helper.c | 40 +++++++++++++++++++++++++
2 files changed, 45 insertions(+), 2 deletions(-)
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index 430d4e4460..6e8ed7694c 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -3665,7 +3665,7 @@ static bool trans_vrgather_vx(DisasContext *s, arg_rmrr *a)
return false;
}
- if (a->vm && s->vl_eq_vlmax) {
+ if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
int scale = s->lmul - (s->sew + 3);
int vlmax = s->cfg_ptr->vlen >> -scale;
TCGv_i64 dest = tcg_temp_new_i64();
@@ -3697,7 +3697,7 @@ static bool trans_vrgather_vi(DisasContext *s, arg_rmrr *a)
return false;
}
- if (a->vm && s->vl_eq_vlmax) {
+ if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
int scale = s->lmul - (s->sew + 3);
int vlmax = s->cfg_ptr->vlen >> -scale;
if (a->rs1 >= vlmax) {
@@ -3749,6 +3749,7 @@ static bool trans_vcompress_vm(DisasContext *s, arg_r *a)
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),
vreg_ofs(s, a->rs1), vreg_ofs(s, a->rs2),
cpu_env, s->cfg_ptr->vlen / 8,
@@ -3849,6 +3850,8 @@ static bool int_ext_op(DisasContext *s, arg_rmr *a, uint8_t seq)
}
data = FIELD_DP32(data, VDATA, VM, a->vm);
+ data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),
vreg_ofs(s, a->rs2), cpu_env,
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 5c2d1c02f4..2afbac6e37 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4930,6 +4930,9 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
target_ulong offset = s1, i_min, i; \
\
i_min = MAX(env->vstart, offset); \
@@ -4939,6 +4942,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
} \
*((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(i - offset)); \
} \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
/* vslideup.vx vd, vs2, rs1, vm # vd[i+rs1] = vs2[i] */
@@ -4954,6 +4959,9 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
uint32_t vlmax = vext_max_elems(desc, ctzl(sizeof(ETYPE))); \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
target_ulong i_max, i; \
\
i_max = MAX(MIN(s1 < vlmax ? vlmax - s1 : 0, vl), env->vstart); \
@@ -4970,6 +4978,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
} \
\
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
/* vslidedown.vx vd, vs2, rs1, vm # vd[i] = vs2[i+rs1] */
@@ -4985,6 +4995,9 @@ static void vslide1up_##BITWIDTH(void *vd, void *v0, target_ulong s1, \
typedef uint##BITWIDTH##_t ETYPE; \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -4998,6 +5011,8 @@ static void vslide1up_##BITWIDTH(void *vd, void *v0, target_ulong s1, \
} \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VEXT_VSLIE1UP(8, H1)
@@ -5025,6 +5040,9 @@ static void vslide1down_##BITWIDTH(void *vd, void *v0, target_ulong s1, \
typedef uint##BITWIDTH##_t ETYPE; \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -5038,6 +5056,8 @@ static void vslide1down_##BITWIDTH(void *vd, void *v0, target_ulong s1, \
} \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VEXT_VSLIDE1DOWN(8, H1)
@@ -5091,6 +5111,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
uint32_t vlmax = vext_max_elems(desc, ctzl(sizeof(TS2))); \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(TS2); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint64_t index; \
uint32_t i; \
\
@@ -5106,6 +5129,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
} \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
/* vd[i] = (vs1[i] >= VLMAX) ? 0 : vs2[vs1[i]]; */
@@ -5126,6 +5151,9 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
uint32_t vlmax = vext_max_elems(desc, ctzl(sizeof(ETYPE))); \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint64_t index = s1; \
uint32_t i; \
\
@@ -5140,6 +5168,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
} \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
/* vd[i] = (x[rs1] >= VLMAX) ? 0 : vs2[rs1] */
@@ -5154,6 +5184,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t num = 0, i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -5164,6 +5197,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
num++; \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
/* Compress into vd elements of vs2 where vs1 is enabled */
@@ -5195,6 +5230,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \
{ \
uint32_t vl = env->vl; \
uint32_t vm = vext_vm(desc); \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -5204,6 +5242,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \
*((ETYPE *)vd + HD(i)) = *((DTYPE *)vs2 + HS1(i)); \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VEXT_INT_EXT(vzext_vf2_h, uint16_t, uint8_t, H2, H1)
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 03/16] target/riscv: rvv: Rename ambiguous esz
2022-05-13 11:49 [PATCH qemu v18 00/16] Add tail agnostic behavior for rvv instructions ~eopxd
@ 2022-05-13 11:50 ` ~eopxd
2022-05-13 11:50 ` ~eopxd
` (15 subsequent siblings)
16 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-03-09 8:34 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
No functional change intended in this commit.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/vector_helper.c | 76 ++++++++++++++++++------------------
1 file changed, 38 insertions(+), 38 deletions(-)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 60840325c4..3b79b9cbc2 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -125,9 +125,9 @@ static inline int32_t vext_lmul(uint32_t desc)
/*
* Get the maximum number of elements can be operated.
*
- * esz: log2 of element size in bytes.
+ * log2_esz: log2 of element size in bytes.
*/
-static inline uint32_t vext_max_elems(uint32_t desc, uint32_t esz)
+static inline uint32_t vext_max_elems(uint32_t desc, uint32_t log2_esz)
{
/*
* As simd_desc support at most 2048 bytes, the max vlen is 1024 bits.
@@ -136,7 +136,7 @@ static inline uint32_t vext_max_elems(uint32_t desc, uint32_t esz)
uint32_t vlenb = simd_maxsz(desc);
/* Return VLMAX */
- int scale = vext_lmul(desc) - esz;
+ int scale = vext_lmul(desc) - log2_esz;
return scale < 0 ? vlenb >> -scale : vlenb << scale;
}
@@ -231,11 +231,11 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base,
target_ulong stride, CPURISCVState *env,
uint32_t desc, uint32_t vm,
vext_ldst_elem_fn *ldst_elem,
- uint32_t esz, uintptr_t ra)
+ uint32_t log2_esz, uintptr_t ra)
{
uint32_t i, k;
uint32_t nf = vext_nf(desc);
- uint32_t max_elems = vext_max_elems(desc, esz);
+ uint32_t max_elems = vext_max_elems(desc, log2_esz);
for (i = env->vstart; i < env->vl; i++, env->vstart++) {
if (!vm && !vext_elem_mask(v0, i)) {
@@ -244,7 +244,7 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base,
k = 0;
while (k < nf) {
- target_ulong addr = base + stride * i + (k << esz);
+ target_ulong addr = base + stride * i + (k << log2_esz);
ldst_elem(env, adjust_addr(env, addr), i + k * max_elems, vd, ra);
k++;
}
@@ -289,18 +289,18 @@ GEN_VEXT_ST_STRIDE(vsse64_v, int64_t, ste_d)
/* unmasked unit-stride load and store operation*/
static void
vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
- vext_ldst_elem_fn *ldst_elem, uint32_t esz, uint32_t evl,
+ vext_ldst_elem_fn *ldst_elem, uint32_t log2_esz, uint32_t evl,
uintptr_t ra)
{
uint32_t i, k;
uint32_t nf = vext_nf(desc);
- uint32_t max_elems = vext_max_elems(desc, esz);
+ uint32_t max_elems = vext_max_elems(desc, log2_esz);
/* load bytes from guest memory */
for (i = env->vstart; i < evl; i++, env->vstart++) {
k = 0;
while (k < nf) {
- target_ulong addr = base + ((i * nf + k) << esz);
+ target_ulong addr = base + ((i * nf + k) << log2_esz);
ldst_elem(env, adjust_addr(env, addr), i + k * max_elems, vd, ra);
k++;
}
@@ -399,12 +399,12 @@ vext_ldst_index(void *vd, void *v0, target_ulong base,
void *vs2, CPURISCVState *env, uint32_t desc,
vext_get_index_addr get_index_addr,
vext_ldst_elem_fn *ldst_elem,
- uint32_t esz, uintptr_t ra)
+ uint32_t log2_esz, uintptr_t ra)
{
uint32_t i, k;
uint32_t nf = vext_nf(desc);
uint32_t vm = vext_vm(desc);
- uint32_t max_elems = vext_max_elems(desc, esz);
+ uint32_t max_elems = vext_max_elems(desc, log2_esz);
/* load bytes from guest memory */
for (i = env->vstart; i < env->vl; i++, env->vstart++) {
@@ -414,7 +414,7 @@ vext_ldst_index(void *vd, void *v0, target_ulong base,
k = 0;
while (k < nf) {
- abi_ptr addr = get_index_addr(base, i, vs2) + (k << esz);
+ abi_ptr addr = get_index_addr(base, i, vs2) + (k << log2_esz);
ldst_elem(env, adjust_addr(env, addr), i + k * max_elems, vd, ra);
k++;
}
@@ -480,13 +480,13 @@ static inline void
vext_ldff(void *vd, void *v0, target_ulong base,
CPURISCVState *env, uint32_t desc,
vext_ldst_elem_fn *ldst_elem,
- uint32_t esz, uintptr_t ra)
+ uint32_t log2_esz, uintptr_t ra)
{
void *host;
uint32_t i, k, vl = 0;
uint32_t nf = vext_nf(desc);
uint32_t vm = vext_vm(desc);
- uint32_t max_elems = vext_max_elems(desc, esz);
+ uint32_t max_elems = vext_max_elems(desc, log2_esz);
target_ulong addr, offset, remain;
/* probe every access*/
@@ -494,12 +494,12 @@ vext_ldff(void *vd, void *v0, target_ulong base,
if (!vm && !vext_elem_mask(v0, i)) {
continue;
}
- addr = adjust_addr(env, base + i * (nf << esz));
+ addr = adjust_addr(env, base + i * (nf << log2_esz));
if (i == 0) {
- probe_pages(env, addr, nf << esz, ra, MMU_DATA_LOAD);
+ probe_pages(env, addr, nf << log2_esz, ra, MMU_DATA_LOAD);
} else {
/* if it triggers an exception, no need to check watchpoint */
- remain = nf << esz;
+ remain = nf << log2_esz;
while (remain > 0) {
offset = -(addr | TARGET_PAGE_MASK);
host = tlb_vaddr_to_host(env, addr, MMU_DATA_LOAD,
@@ -536,7 +536,7 @@ ProbeSuccess:
continue;
}
while (k < nf) {
- target_ulong addr = base + ((i * nf + k) << esz);
+ target_ulong addr = base + ((i * nf + k) << log2_esz);
ldst_elem(env, adjust_addr(env, addr), i + k * max_elems, vd, ra);
k++;
}
@@ -576,12 +576,12 @@ GEN_VEXT_LDFF(vle64ff_v, int64_t, lde_d)
*/
static void
vext_ldst_whole(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
- vext_ldst_elem_fn *ldst_elem, uint32_t esz, uintptr_t ra)
+ vext_ldst_elem_fn *ldst_elem, uint32_t log2_esz, uintptr_t ra)
{
uint32_t i, k, off, pos;
uint32_t nf = vext_nf(desc);
uint32_t vlenb = env_archcpu(env)->cfg.vlen >> 3;
- uint32_t max_elems = vlenb >> esz;
+ uint32_t max_elems = vlenb >> log2_esz;
k = env->vstart / max_elems;
off = env->vstart % max_elems;
@@ -589,7 +589,7 @@ vext_ldst_whole(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
if (off) {
/* load/store rest of elements of current segment pointed by vstart */
for (pos = off; pos < max_elems; pos++, env->vstart++) {
- target_ulong addr = base + ((pos + k * max_elems) << esz);
+ target_ulong addr = base + ((pos + k * max_elems) << log2_esz);
ldst_elem(env, adjust_addr(env, addr), pos + k * max_elems, vd, ra);
}
k++;
@@ -598,7 +598,7 @@ vext_ldst_whole(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
/* load/store elements for rest of segments */
for (; k < nf; k++) {
for (i = 0; i < max_elems; i++, env->vstart++) {
- target_ulong addr = base + ((i + k * max_elems) << esz);
+ target_ulong addr = base + ((i + k * max_elems) << log2_esz);
ldst_elem(env, adjust_addr(env, addr), i + k * max_elems, vd, ra);
}
}
@@ -4688,11 +4688,11 @@ GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_h, uint16_t, H2)
GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_w, uint32_t, H4)
GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_d, uint64_t, H8)
-#define GEN_VEXT_VSLIE1UP(ESZ, H) \
-static void vslide1up_##ESZ(void *vd, void *v0, target_ulong s1, void *vs2, \
- CPURISCVState *env, uint32_t desc) \
+#define GEN_VEXT_VSLIE1UP(BITWIDTH, H) \
+static void vslide1up_##BITWIDTH(void *vd, void *v0, target_ulong s1, \
+ void *vs2, CPURISCVState *env, uint32_t desc) \
{ \
- typedef uint##ESZ##_t ETYPE; \
+ typedef uint##BITWIDTH##_t ETYPE; \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
uint32_t i; \
@@ -4715,11 +4715,11 @@ GEN_VEXT_VSLIE1UP(16, H2)
GEN_VEXT_VSLIE1UP(32, H4)
GEN_VEXT_VSLIE1UP(64, H8)
-#define GEN_VEXT_VSLIDE1UP_VX(NAME, ESZ) \
+#define GEN_VEXT_VSLIDE1UP_VX(NAME, BITWIDTH) \
void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
- vslide1up_##ESZ(vd, v0, s1, vs2, env, desc); \
+ vslide1up_##BITWIDTH(vd, v0, s1, vs2, env, desc); \
}
/* vslide1up.vx vd, vs2, rs1, vm # vd[0]=x[rs1], vd[i+1] = vs2[i] */
@@ -4728,11 +4728,11 @@ GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_h, 16)
GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_w, 32)
GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_d, 64)
-#define GEN_VEXT_VSLIDE1DOWN(ESZ, H) \
-static void vslide1down_##ESZ(void *vd, void *v0, target_ulong s1, void *vs2, \
- CPURISCVState *env, uint32_t desc) \
+#define GEN_VEXT_VSLIDE1DOWN(BITWIDTH, H) \
+static void vslide1down_##BITWIDTH(void *vd, void *v0, target_ulong s1, \
+ void *vs2, CPURISCVState *env, uint32_t desc) \
{ \
- typedef uint##ESZ##_t ETYPE; \
+ typedef uint##BITWIDTH##_t ETYPE; \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
uint32_t i; \
@@ -4755,11 +4755,11 @@ GEN_VEXT_VSLIDE1DOWN(16, H2)
GEN_VEXT_VSLIDE1DOWN(32, H4)
GEN_VEXT_VSLIDE1DOWN(64, H8)
-#define GEN_VEXT_VSLIDE1DOWN_VX(NAME, ESZ) \
+#define GEN_VEXT_VSLIDE1DOWN_VX(NAME, BITWIDTH) \
void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
- vslide1down_##ESZ(vd, v0, s1, vs2, env, desc); \
+ vslide1down_##BITWIDTH(vd, v0, s1, vs2, env, desc); \
}
/* vslide1down.vx vd, vs2, rs1, vm # vd[i] = vs2[i+1], vd[vl-1]=x[rs1] */
@@ -4769,11 +4769,11 @@ GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_w, 32)
GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_d, 64)
/* Vector Floating-Point Slide Instructions */
-#define GEN_VEXT_VFSLIDE1UP_VF(NAME, ESZ) \
+#define GEN_VEXT_VFSLIDE1UP_VF(NAME, BITWIDTH) \
void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
- vslide1up_##ESZ(vd, v0, s1, vs2, env, desc); \
+ vslide1up_##BITWIDTH(vd, v0, s1, vs2, env, desc); \
}
/* vfslide1up.vf vd, vs2, rs1, vm # vd[0]=f[rs1], vd[i+1] = vs2[i] */
@@ -4781,11 +4781,11 @@ GEN_VEXT_VFSLIDE1UP_VF(vfslide1up_vf_h, 16)
GEN_VEXT_VFSLIDE1UP_VF(vfslide1up_vf_w, 32)
GEN_VEXT_VFSLIDE1UP_VF(vfslide1up_vf_d, 64)
-#define GEN_VEXT_VFSLIDE1DOWN_VF(NAME, ESZ) \
+#define GEN_VEXT_VFSLIDE1DOWN_VF(NAME, BITWIDTH) \
void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
- vslide1down_##ESZ(vd, v0, s1, vs2, env, desc); \
+ vslide1down_##BITWIDTH(vd, v0, s1, vs2, env, desc); \
}
/* vfslide1down.vf vd, vs2, rs1, vm # vd[i] = vs2[i+1], vd[vl-1]=f[rs1] */
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 04/16] target/riscv: rvv: Early exit when vstart >= vl
2022-05-13 11:49 [PATCH qemu v18 00/16] Add tail agnostic behavior for rvv instructions ~eopxd
@ 2022-05-13 11:50 ` ~eopxd
2022-05-13 11:50 ` ~eopxd
` (15 subsequent siblings)
16 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-03-12 6:28 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
According to v-spec (section 5.4):
When vstart ≥ vl, there are no body elements, and no elements are
updated in any destination vector register group, including that
no tail elements are updated with agnostic values.
vmsbf.m, vmsif.m, vmsof.m, viota.m, vcompress instructions themselves
require vstart to be zero. So they don't need the early exit.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/insn_trans/trans_rvv.c.inc | 27 +++++++++++++++++++++++++
1 file changed, 27 insertions(+)
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index 90327509f7..4d5dfa794a 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -652,6 +652,7 @@ static bool ldst_us_trans(uint32_t vd, uint32_t rs1, uint32_t data,
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
dest = tcg_temp_new_ptr();
mask = tcg_temp_new_ptr();
@@ -818,6 +819,7 @@ static bool ldst_stride_trans(uint32_t vd, uint32_t rs1, uint32_t rs2,
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
dest = tcg_temp_new_ptr();
mask = tcg_temp_new_ptr();
@@ -925,6 +927,7 @@ static bool ldst_index_trans(uint32_t vd, uint32_t rs1, uint32_t vs2,
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
dest = tcg_temp_new_ptr();
mask = tcg_temp_new_ptr();
@@ -1067,6 +1070,7 @@ static bool ldff_trans(uint32_t vd, uint32_t rs1, uint32_t data,
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
dest = tcg_temp_new_ptr();
mask = tcg_temp_new_ptr();
@@ -1221,6 +1225,7 @@ do_opivv_gvec(DisasContext *s, arg_rmrr *a, GVecGen3Fn *gvec_fn,
}
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
if (a->vm && s->vl_eq_vlmax) {
gvec_fn(s->sew, vreg_ofs(s, a->rd),
@@ -1268,6 +1273,7 @@ static bool opivx_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, uint32_t vm,
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
dest = tcg_temp_new_ptr();
mask = tcg_temp_new_ptr();
@@ -1432,6 +1438,7 @@ static bool opivi_trans(uint32_t vd, uint32_t imm, uint32_t vs2, uint32_t vm,
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
dest = tcg_temp_new_ptr();
mask = tcg_temp_new_ptr();
@@ -1518,6 +1525,7 @@ static bool do_opivv_widen(DisasContext *s, arg_rmrr *a,
uint32_t data = 0;
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
@@ -1598,6 +1606,7 @@ static bool do_opiwv_widen(DisasContext *s, arg_rmrr *a,
uint32_t data = 0;
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
@@ -1675,6 +1684,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
}; \
TCGLabel *over = gen_new_label(); \
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
@@ -1856,6 +1866,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
}; \
TCGLabel *over = gen_new_label(); \
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
@@ -2066,6 +2077,7 @@ static bool trans_vmv_v_v(DisasContext *s, arg_vmv_v_v *a)
};
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
tcg_gen_gvec_2_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs1),
cpu_env, s->cfg_ptr->vlen / 8,
@@ -2089,6 +2101,7 @@ static bool trans_vmv_v_x(DisasContext *s, arg_vmv_v_x *a)
TCGv s1;
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
s1 = get_gpr(s, a->rs1, EXT_SIGN);
@@ -2144,6 +2157,7 @@ static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_i *a)
};
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
s1 = tcg_constant_i64(simm);
dest = tcg_temp_new_ptr();
@@ -2296,6 +2310,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
TCGLabel *over = gen_new_label(); \
gen_set_rm(s, RISCV_FRM_DYN); \
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
@@ -2326,6 +2341,7 @@ static bool opfvf_trans(uint32_t vd, uint32_t rs1, uint32_t vs2,
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
dest = tcg_temp_new_ptr();
mask = tcg_temp_new_ptr();
@@ -2414,6 +2430,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
TCGLabel *over = gen_new_label(); \
gen_set_rm(s, RISCV_FRM_DYN); \
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);\
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
@@ -2488,6 +2505,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
TCGLabel *over = gen_new_label(); \
gen_set_rm(s, RISCV_FRM_DYN); \
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
@@ -2609,6 +2627,7 @@ static bool do_opfv(DisasContext *s, arg_rmr *a,
TCGLabel *over = gen_new_label();
gen_set_rm(s, rm);
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
@@ -2722,6 +2741,7 @@ static bool trans_vfmv_v_f(DisasContext *s, arg_vfmv_v_f *a)
};
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
t1 = tcg_temp_new_i64();
/* NaN-box f[rs1] */
@@ -2810,6 +2830,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
TCGLabel *over = gen_new_label(); \
gen_set_rm(s, FRM); \
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
@@ -2861,6 +2882,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
TCGLabel *over = gen_new_label(); \
gen_set_rm(s, RISCV_FRM_DYN); \
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
@@ -2926,6 +2948,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
TCGLabel *over = gen_new_label(); \
gen_set_rm(s, FRM); \
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
@@ -2979,6 +3002,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
TCGLabel *over = gen_new_label(); \
gen_set_rm(s, FRM); \
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
@@ -3066,6 +3090,7 @@ static bool trans_##NAME(DisasContext *s, arg_r *a) \
gen_helper_gvec_4_ptr *fn = gen_helper_##NAME; \
TCGLabel *over = gen_new_label(); \
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
@@ -3234,6 +3259,7 @@ static bool trans_vid_v(DisasContext *s, arg_vid_v *a)
uint32_t data = 0;
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
@@ -3744,6 +3770,7 @@ static bool int_ext_op(DisasContext *s, arg_rmr *a, uint8_t seq)
gen_helper_gvec_3_ptr *fn;
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
static gen_helper_gvec_3_ptr * const fns[6][4] = {
{
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 01/16] target/riscv: rvv: Prune redundant ESZ, DSZ parameter passed
2022-05-13 11:49 [PATCH qemu v18 00/16] Add tail agnostic behavior for rvv instructions ~eopxd
@ 2022-05-13 11:50 ` ~eopxd
2022-05-13 11:50 ` ~eopxd
` (15 subsequent siblings)
16 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-03-14 7:38 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
No functional change intended in this commit.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/vector_helper.c | 1132 +++++++++++++++++-----------------
1 file changed, 565 insertions(+), 567 deletions(-)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 576b14e5a3..85dd611cd9 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -710,7 +710,6 @@ RVVCALL(OPIVV2, vsub_vv_d, OP_SSS_D, H8, H8, H8, DO_SUB)
static void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2,
CPURISCVState *env, uint32_t desc,
- uint32_t esz, uint32_t dsz,
opivv2_fn *fn)
{
uint32_t vm = vext_vm(desc);
@@ -727,23 +726,23 @@ static void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2,
}
/* generate the helpers for OPIVV */
-#define GEN_VEXT_VV(NAME, ESZ, DSZ) \
+#define GEN_VEXT_VV(NAME) \
void HELPER(NAME)(void *vd, void *v0, void *vs1, \
void *vs2, CPURISCVState *env, \
uint32_t desc) \
{ \
- do_vext_vv(vd, v0, vs1, vs2, env, desc, ESZ, DSZ, \
+ do_vext_vv(vd, v0, vs1, vs2, env, desc, \
do_##NAME); \
}
-GEN_VEXT_VV(vadd_vv_b, 1, 1)
-GEN_VEXT_VV(vadd_vv_h, 2, 2)
-GEN_VEXT_VV(vadd_vv_w, 4, 4)
-GEN_VEXT_VV(vadd_vv_d, 8, 8)
-GEN_VEXT_VV(vsub_vv_b, 1, 1)
-GEN_VEXT_VV(vsub_vv_h, 2, 2)
-GEN_VEXT_VV(vsub_vv_w, 4, 4)
-GEN_VEXT_VV(vsub_vv_d, 8, 8)
+GEN_VEXT_VV(vadd_vv_b)
+GEN_VEXT_VV(vadd_vv_h)
+GEN_VEXT_VV(vadd_vv_w)
+GEN_VEXT_VV(vadd_vv_d)
+GEN_VEXT_VV(vsub_vv_b)
+GEN_VEXT_VV(vsub_vv_h)
+GEN_VEXT_VV(vsub_vv_w)
+GEN_VEXT_VV(vsub_vv_d)
typedef void opivx2_fn(void *vd, target_long s1, void *vs2, int i);
@@ -773,7 +772,6 @@ RVVCALL(OPIVX2, vrsub_vx_d, OP_SSS_D, H8, H8, DO_RSUB)
static void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2,
CPURISCVState *env, uint32_t desc,
- uint32_t esz, uint32_t dsz,
opivx2_fn fn)
{
uint32_t vm = vext_vm(desc);
@@ -790,27 +788,27 @@ static void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2,
}
/* generate the helpers for OPIVX */
-#define GEN_VEXT_VX(NAME, ESZ, DSZ) \
+#define GEN_VEXT_VX(NAME) \
void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
void *vs2, CPURISCVState *env, \
uint32_t desc) \
{ \
- do_vext_vx(vd, v0, s1, vs2, env, desc, ESZ, DSZ, \
+ do_vext_vx(vd, v0, s1, vs2, env, desc, \
do_##NAME); \
}
-GEN_VEXT_VX(vadd_vx_b, 1, 1)
-GEN_VEXT_VX(vadd_vx_h, 2, 2)
-GEN_VEXT_VX(vadd_vx_w, 4, 4)
-GEN_VEXT_VX(vadd_vx_d, 8, 8)
-GEN_VEXT_VX(vsub_vx_b, 1, 1)
-GEN_VEXT_VX(vsub_vx_h, 2, 2)
-GEN_VEXT_VX(vsub_vx_w, 4, 4)
-GEN_VEXT_VX(vsub_vx_d, 8, 8)
-GEN_VEXT_VX(vrsub_vx_b, 1, 1)
-GEN_VEXT_VX(vrsub_vx_h, 2, 2)
-GEN_VEXT_VX(vrsub_vx_w, 4, 4)
-GEN_VEXT_VX(vrsub_vx_d, 8, 8)
+GEN_VEXT_VX(vadd_vx_b)
+GEN_VEXT_VX(vadd_vx_h)
+GEN_VEXT_VX(vadd_vx_w)
+GEN_VEXT_VX(vadd_vx_d)
+GEN_VEXT_VX(vsub_vx_b)
+GEN_VEXT_VX(vsub_vx_h)
+GEN_VEXT_VX(vsub_vx_w)
+GEN_VEXT_VX(vsub_vx_d)
+GEN_VEXT_VX(vrsub_vx_b)
+GEN_VEXT_VX(vrsub_vx_h)
+GEN_VEXT_VX(vrsub_vx_w)
+GEN_VEXT_VX(vrsub_vx_d)
void HELPER(vec_rsubs8)(void *d, void *a, uint64_t b, uint32_t desc)
{
@@ -889,30 +887,30 @@ RVVCALL(OPIVV2, vwadd_wv_w, WOP_WSSS_W, H8, H4, H4, DO_ADD)
RVVCALL(OPIVV2, vwsub_wv_b, WOP_WSSS_B, H2, H1, H1, DO_SUB)
RVVCALL(OPIVV2, vwsub_wv_h, WOP_WSSS_H, H4, H2, H2, DO_SUB)
RVVCALL(OPIVV2, vwsub_wv_w, WOP_WSSS_W, H8, H4, H4, DO_SUB)
-GEN_VEXT_VV(vwaddu_vv_b, 1, 2)
-GEN_VEXT_VV(vwaddu_vv_h, 2, 4)
-GEN_VEXT_VV(vwaddu_vv_w, 4, 8)
-GEN_VEXT_VV(vwsubu_vv_b, 1, 2)
-GEN_VEXT_VV(vwsubu_vv_h, 2, 4)
-GEN_VEXT_VV(vwsubu_vv_w, 4, 8)
-GEN_VEXT_VV(vwadd_vv_b, 1, 2)
-GEN_VEXT_VV(vwadd_vv_h, 2, 4)
-GEN_VEXT_VV(vwadd_vv_w, 4, 8)
-GEN_VEXT_VV(vwsub_vv_b, 1, 2)
-GEN_VEXT_VV(vwsub_vv_h, 2, 4)
-GEN_VEXT_VV(vwsub_vv_w, 4, 8)
-GEN_VEXT_VV(vwaddu_wv_b, 1, 2)
-GEN_VEXT_VV(vwaddu_wv_h, 2, 4)
-GEN_VEXT_VV(vwaddu_wv_w, 4, 8)
-GEN_VEXT_VV(vwsubu_wv_b, 1, 2)
-GEN_VEXT_VV(vwsubu_wv_h, 2, 4)
-GEN_VEXT_VV(vwsubu_wv_w, 4, 8)
-GEN_VEXT_VV(vwadd_wv_b, 1, 2)
-GEN_VEXT_VV(vwadd_wv_h, 2, 4)
-GEN_VEXT_VV(vwadd_wv_w, 4, 8)
-GEN_VEXT_VV(vwsub_wv_b, 1, 2)
-GEN_VEXT_VV(vwsub_wv_h, 2, 4)
-GEN_VEXT_VV(vwsub_wv_w, 4, 8)
+GEN_VEXT_VV(vwaddu_vv_b)
+GEN_VEXT_VV(vwaddu_vv_h)
+GEN_VEXT_VV(vwaddu_vv_w)
+GEN_VEXT_VV(vwsubu_vv_b)
+GEN_VEXT_VV(vwsubu_vv_h)
+GEN_VEXT_VV(vwsubu_vv_w)
+GEN_VEXT_VV(vwadd_vv_b)
+GEN_VEXT_VV(vwadd_vv_h)
+GEN_VEXT_VV(vwadd_vv_w)
+GEN_VEXT_VV(vwsub_vv_b)
+GEN_VEXT_VV(vwsub_vv_h)
+GEN_VEXT_VV(vwsub_vv_w)
+GEN_VEXT_VV(vwaddu_wv_b)
+GEN_VEXT_VV(vwaddu_wv_h)
+GEN_VEXT_VV(vwaddu_wv_w)
+GEN_VEXT_VV(vwsubu_wv_b)
+GEN_VEXT_VV(vwsubu_wv_h)
+GEN_VEXT_VV(vwsubu_wv_w)
+GEN_VEXT_VV(vwadd_wv_b)
+GEN_VEXT_VV(vwadd_wv_h)
+GEN_VEXT_VV(vwadd_wv_w)
+GEN_VEXT_VV(vwsub_wv_b)
+GEN_VEXT_VV(vwsub_wv_h)
+GEN_VEXT_VV(vwsub_wv_w)
RVVCALL(OPIVX2, vwaddu_vx_b, WOP_UUU_B, H2, H1, DO_ADD)
RVVCALL(OPIVX2, vwaddu_vx_h, WOP_UUU_H, H4, H2, DO_ADD)
@@ -938,30 +936,30 @@ RVVCALL(OPIVX2, vwadd_wx_w, WOP_WSSS_W, H8, H4, DO_ADD)
RVVCALL(OPIVX2, vwsub_wx_b, WOP_WSSS_B, H2, H1, DO_SUB)
RVVCALL(OPIVX2, vwsub_wx_h, WOP_WSSS_H, H4, H2, DO_SUB)
RVVCALL(OPIVX2, vwsub_wx_w, WOP_WSSS_W, H8, H4, DO_SUB)
-GEN_VEXT_VX(vwaddu_vx_b, 1, 2)
-GEN_VEXT_VX(vwaddu_vx_h, 2, 4)
-GEN_VEXT_VX(vwaddu_vx_w, 4, 8)
-GEN_VEXT_VX(vwsubu_vx_b, 1, 2)
-GEN_VEXT_VX(vwsubu_vx_h, 2, 4)
-GEN_VEXT_VX(vwsubu_vx_w, 4, 8)
-GEN_VEXT_VX(vwadd_vx_b, 1, 2)
-GEN_VEXT_VX(vwadd_vx_h, 2, 4)
-GEN_VEXT_VX(vwadd_vx_w, 4, 8)
-GEN_VEXT_VX(vwsub_vx_b, 1, 2)
-GEN_VEXT_VX(vwsub_vx_h, 2, 4)
-GEN_VEXT_VX(vwsub_vx_w, 4, 8)
-GEN_VEXT_VX(vwaddu_wx_b, 1, 2)
-GEN_VEXT_VX(vwaddu_wx_h, 2, 4)
-GEN_VEXT_VX(vwaddu_wx_w, 4, 8)
-GEN_VEXT_VX(vwsubu_wx_b, 1, 2)
-GEN_VEXT_VX(vwsubu_wx_h, 2, 4)
-GEN_VEXT_VX(vwsubu_wx_w, 4, 8)
-GEN_VEXT_VX(vwadd_wx_b, 1, 2)
-GEN_VEXT_VX(vwadd_wx_h, 2, 4)
-GEN_VEXT_VX(vwadd_wx_w, 4, 8)
-GEN_VEXT_VX(vwsub_wx_b, 1, 2)
-GEN_VEXT_VX(vwsub_wx_h, 2, 4)
-GEN_VEXT_VX(vwsub_wx_w, 4, 8)
+GEN_VEXT_VX(vwaddu_vx_b)
+GEN_VEXT_VX(vwaddu_vx_h)
+GEN_VEXT_VX(vwaddu_vx_w)
+GEN_VEXT_VX(vwsubu_vx_b)
+GEN_VEXT_VX(vwsubu_vx_h)
+GEN_VEXT_VX(vwsubu_vx_w)
+GEN_VEXT_VX(vwadd_vx_b)
+GEN_VEXT_VX(vwadd_vx_h)
+GEN_VEXT_VX(vwadd_vx_w)
+GEN_VEXT_VX(vwsub_vx_b)
+GEN_VEXT_VX(vwsub_vx_h)
+GEN_VEXT_VX(vwsub_vx_w)
+GEN_VEXT_VX(vwaddu_wx_b)
+GEN_VEXT_VX(vwaddu_wx_h)
+GEN_VEXT_VX(vwaddu_wx_w)
+GEN_VEXT_VX(vwsubu_wx_b)
+GEN_VEXT_VX(vwsubu_wx_h)
+GEN_VEXT_VX(vwsubu_wx_w)
+GEN_VEXT_VX(vwadd_wx_b)
+GEN_VEXT_VX(vwadd_wx_h)
+GEN_VEXT_VX(vwadd_wx_w)
+GEN_VEXT_VX(vwsub_wx_b)
+GEN_VEXT_VX(vwsub_wx_h)
+GEN_VEXT_VX(vwsub_wx_w)
/* Vector Integer Add-with-Carry / Subtract-with-Borrow Instructions */
#define DO_VADC(N, M, C) (N + M + C)
@@ -1091,18 +1089,18 @@ RVVCALL(OPIVV2, vxor_vv_b, OP_SSS_B, H1, H1, H1, DO_XOR)
RVVCALL(OPIVV2, vxor_vv_h, OP_SSS_H, H2, H2, H2, DO_XOR)
RVVCALL(OPIVV2, vxor_vv_w, OP_SSS_W, H4, H4, H4, DO_XOR)
RVVCALL(OPIVV2, vxor_vv_d, OP_SSS_D, H8, H8, H8, DO_XOR)
-GEN_VEXT_VV(vand_vv_b, 1, 1)
-GEN_VEXT_VV(vand_vv_h, 2, 2)
-GEN_VEXT_VV(vand_vv_w, 4, 4)
-GEN_VEXT_VV(vand_vv_d, 8, 8)
-GEN_VEXT_VV(vor_vv_b, 1, 1)
-GEN_VEXT_VV(vor_vv_h, 2, 2)
-GEN_VEXT_VV(vor_vv_w, 4, 4)
-GEN_VEXT_VV(vor_vv_d, 8, 8)
-GEN_VEXT_VV(vxor_vv_b, 1, 1)
-GEN_VEXT_VV(vxor_vv_h, 2, 2)
-GEN_VEXT_VV(vxor_vv_w, 4, 4)
-GEN_VEXT_VV(vxor_vv_d, 8, 8)
+GEN_VEXT_VV(vand_vv_b)
+GEN_VEXT_VV(vand_vv_h)
+GEN_VEXT_VV(vand_vv_w)
+GEN_VEXT_VV(vand_vv_d)
+GEN_VEXT_VV(vor_vv_b)
+GEN_VEXT_VV(vor_vv_h)
+GEN_VEXT_VV(vor_vv_w)
+GEN_VEXT_VV(vor_vv_d)
+GEN_VEXT_VV(vxor_vv_b)
+GEN_VEXT_VV(vxor_vv_h)
+GEN_VEXT_VV(vxor_vv_w)
+GEN_VEXT_VV(vxor_vv_d)
RVVCALL(OPIVX2, vand_vx_b, OP_SSS_B, H1, H1, DO_AND)
RVVCALL(OPIVX2, vand_vx_h, OP_SSS_H, H2, H2, DO_AND)
@@ -1116,18 +1114,18 @@ RVVCALL(OPIVX2, vxor_vx_b, OP_SSS_B, H1, H1, DO_XOR)
RVVCALL(OPIVX2, vxor_vx_h, OP_SSS_H, H2, H2, DO_XOR)
RVVCALL(OPIVX2, vxor_vx_w, OP_SSS_W, H4, H4, DO_XOR)
RVVCALL(OPIVX2, vxor_vx_d, OP_SSS_D, H8, H8, DO_XOR)
-GEN_VEXT_VX(vand_vx_b, 1, 1)
-GEN_VEXT_VX(vand_vx_h, 2, 2)
-GEN_VEXT_VX(vand_vx_w, 4, 4)
-GEN_VEXT_VX(vand_vx_d, 8, 8)
-GEN_VEXT_VX(vor_vx_b, 1, 1)
-GEN_VEXT_VX(vor_vx_h, 2, 2)
-GEN_VEXT_VX(vor_vx_w, 4, 4)
-GEN_VEXT_VX(vor_vx_d, 8, 8)
-GEN_VEXT_VX(vxor_vx_b, 1, 1)
-GEN_VEXT_VX(vxor_vx_h, 2, 2)
-GEN_VEXT_VX(vxor_vx_w, 4, 4)
-GEN_VEXT_VX(vxor_vx_d, 8, 8)
+GEN_VEXT_VX(vand_vx_b)
+GEN_VEXT_VX(vand_vx_h)
+GEN_VEXT_VX(vand_vx_w)
+GEN_VEXT_VX(vand_vx_d)
+GEN_VEXT_VX(vor_vx_b)
+GEN_VEXT_VX(vor_vx_h)
+GEN_VEXT_VX(vor_vx_w)
+GEN_VEXT_VX(vor_vx_d)
+GEN_VEXT_VX(vxor_vx_b)
+GEN_VEXT_VX(vxor_vx_h)
+GEN_VEXT_VX(vxor_vx_w)
+GEN_VEXT_VX(vxor_vx_d)
/* Vector Single-Width Bit Shift Instructions */
#define DO_SLL(N, M) (N << (M))
@@ -1348,22 +1346,22 @@ RVVCALL(OPIVV2, vmax_vv_b, OP_SSS_B, H1, H1, H1, DO_MAX)
RVVCALL(OPIVV2, vmax_vv_h, OP_SSS_H, H2, H2, H2, DO_MAX)
RVVCALL(OPIVV2, vmax_vv_w, OP_SSS_W, H4, H4, H4, DO_MAX)
RVVCALL(OPIVV2, vmax_vv_d, OP_SSS_D, H8, H8, H8, DO_MAX)
-GEN_VEXT_VV(vminu_vv_b, 1, 1)
-GEN_VEXT_VV(vminu_vv_h, 2, 2)
-GEN_VEXT_VV(vminu_vv_w, 4, 4)
-GEN_VEXT_VV(vminu_vv_d, 8, 8)
-GEN_VEXT_VV(vmin_vv_b, 1, 1)
-GEN_VEXT_VV(vmin_vv_h, 2, 2)
-GEN_VEXT_VV(vmin_vv_w, 4, 4)
-GEN_VEXT_VV(vmin_vv_d, 8, 8)
-GEN_VEXT_VV(vmaxu_vv_b, 1, 1)
-GEN_VEXT_VV(vmaxu_vv_h, 2, 2)
-GEN_VEXT_VV(vmaxu_vv_w, 4, 4)
-GEN_VEXT_VV(vmaxu_vv_d, 8, 8)
-GEN_VEXT_VV(vmax_vv_b, 1, 1)
-GEN_VEXT_VV(vmax_vv_h, 2, 2)
-GEN_VEXT_VV(vmax_vv_w, 4, 4)
-GEN_VEXT_VV(vmax_vv_d, 8, 8)
+GEN_VEXT_VV(vminu_vv_b)
+GEN_VEXT_VV(vminu_vv_h)
+GEN_VEXT_VV(vminu_vv_w)
+GEN_VEXT_VV(vminu_vv_d)
+GEN_VEXT_VV(vmin_vv_b)
+GEN_VEXT_VV(vmin_vv_h)
+GEN_VEXT_VV(vmin_vv_w)
+GEN_VEXT_VV(vmin_vv_d)
+GEN_VEXT_VV(vmaxu_vv_b)
+GEN_VEXT_VV(vmaxu_vv_h)
+GEN_VEXT_VV(vmaxu_vv_w)
+GEN_VEXT_VV(vmaxu_vv_d)
+GEN_VEXT_VV(vmax_vv_b)
+GEN_VEXT_VV(vmax_vv_h)
+GEN_VEXT_VV(vmax_vv_w)
+GEN_VEXT_VV(vmax_vv_d)
RVVCALL(OPIVX2, vminu_vx_b, OP_UUU_B, H1, H1, DO_MIN)
RVVCALL(OPIVX2, vminu_vx_h, OP_UUU_H, H2, H2, DO_MIN)
@@ -1381,22 +1379,22 @@ RVVCALL(OPIVX2, vmax_vx_b, OP_SSS_B, H1, H1, DO_MAX)
RVVCALL(OPIVX2, vmax_vx_h, OP_SSS_H, H2, H2, DO_MAX)
RVVCALL(OPIVX2, vmax_vx_w, OP_SSS_W, H4, H4, DO_MAX)
RVVCALL(OPIVX2, vmax_vx_d, OP_SSS_D, H8, H8, DO_MAX)
-GEN_VEXT_VX(vminu_vx_b, 1, 1)
-GEN_VEXT_VX(vminu_vx_h, 2, 2)
-GEN_VEXT_VX(vminu_vx_w, 4, 4)
-GEN_VEXT_VX(vminu_vx_d, 8, 8)
-GEN_VEXT_VX(vmin_vx_b, 1, 1)
-GEN_VEXT_VX(vmin_vx_h, 2, 2)
-GEN_VEXT_VX(vmin_vx_w, 4, 4)
-GEN_VEXT_VX(vmin_vx_d, 8, 8)
-GEN_VEXT_VX(vmaxu_vx_b, 1, 1)
-GEN_VEXT_VX(vmaxu_vx_h, 2, 2)
-GEN_VEXT_VX(vmaxu_vx_w, 4, 4)
-GEN_VEXT_VX(vmaxu_vx_d, 8, 8)
-GEN_VEXT_VX(vmax_vx_b, 1, 1)
-GEN_VEXT_VX(vmax_vx_h, 2, 2)
-GEN_VEXT_VX(vmax_vx_w, 4, 4)
-GEN_VEXT_VX(vmax_vx_d, 8, 8)
+GEN_VEXT_VX(vminu_vx_b)
+GEN_VEXT_VX(vminu_vx_h)
+GEN_VEXT_VX(vminu_vx_w)
+GEN_VEXT_VX(vminu_vx_d)
+GEN_VEXT_VX(vmin_vx_b)
+GEN_VEXT_VX(vmin_vx_h)
+GEN_VEXT_VX(vmin_vx_w)
+GEN_VEXT_VX(vmin_vx_d)
+GEN_VEXT_VX(vmaxu_vx_b)
+GEN_VEXT_VX(vmaxu_vx_h)
+GEN_VEXT_VX(vmaxu_vx_w)
+GEN_VEXT_VX(vmaxu_vx_d)
+GEN_VEXT_VX(vmax_vx_b)
+GEN_VEXT_VX(vmax_vx_h)
+GEN_VEXT_VX(vmax_vx_w)
+GEN_VEXT_VX(vmax_vx_d)
/* Vector Single-Width Integer Multiply Instructions */
#define DO_MUL(N, M) (N * M)
@@ -1404,10 +1402,10 @@ RVVCALL(OPIVV2, vmul_vv_b, OP_SSS_B, H1, H1, H1, DO_MUL)
RVVCALL(OPIVV2, vmul_vv_h, OP_SSS_H, H2, H2, H2, DO_MUL)
RVVCALL(OPIVV2, vmul_vv_w, OP_SSS_W, H4, H4, H4, DO_MUL)
RVVCALL(OPIVV2, vmul_vv_d, OP_SSS_D, H8, H8, H8, DO_MUL)
-GEN_VEXT_VV(vmul_vv_b, 1, 1)
-GEN_VEXT_VV(vmul_vv_h, 2, 2)
-GEN_VEXT_VV(vmul_vv_w, 4, 4)
-GEN_VEXT_VV(vmul_vv_d, 8, 8)
+GEN_VEXT_VV(vmul_vv_b)
+GEN_VEXT_VV(vmul_vv_h)
+GEN_VEXT_VV(vmul_vv_w)
+GEN_VEXT_VV(vmul_vv_d)
static int8_t do_mulh_b(int8_t s2, int8_t s1)
{
@@ -1511,18 +1509,18 @@ RVVCALL(OPIVV2, vmulhsu_vv_b, OP_SUS_B, H1, H1, H1, do_mulhsu_b)
RVVCALL(OPIVV2, vmulhsu_vv_h, OP_SUS_H, H2, H2, H2, do_mulhsu_h)
RVVCALL(OPIVV2, vmulhsu_vv_w, OP_SUS_W, H4, H4, H4, do_mulhsu_w)
RVVCALL(OPIVV2, vmulhsu_vv_d, OP_SUS_D, H8, H8, H8, do_mulhsu_d)
-GEN_VEXT_VV(vmulh_vv_b, 1, 1)
-GEN_VEXT_VV(vmulh_vv_h, 2, 2)
-GEN_VEXT_VV(vmulh_vv_w, 4, 4)
-GEN_VEXT_VV(vmulh_vv_d, 8, 8)
-GEN_VEXT_VV(vmulhu_vv_b, 1, 1)
-GEN_VEXT_VV(vmulhu_vv_h, 2, 2)
-GEN_VEXT_VV(vmulhu_vv_w, 4, 4)
-GEN_VEXT_VV(vmulhu_vv_d, 8, 8)
-GEN_VEXT_VV(vmulhsu_vv_b, 1, 1)
-GEN_VEXT_VV(vmulhsu_vv_h, 2, 2)
-GEN_VEXT_VV(vmulhsu_vv_w, 4, 4)
-GEN_VEXT_VV(vmulhsu_vv_d, 8, 8)
+GEN_VEXT_VV(vmulh_vv_b)
+GEN_VEXT_VV(vmulh_vv_h)
+GEN_VEXT_VV(vmulh_vv_w)
+GEN_VEXT_VV(vmulh_vv_d)
+GEN_VEXT_VV(vmulhu_vv_b)
+GEN_VEXT_VV(vmulhu_vv_h)
+GEN_VEXT_VV(vmulhu_vv_w)
+GEN_VEXT_VV(vmulhu_vv_d)
+GEN_VEXT_VV(vmulhsu_vv_b)
+GEN_VEXT_VV(vmulhsu_vv_h)
+GEN_VEXT_VV(vmulhsu_vv_w)
+GEN_VEXT_VV(vmulhsu_vv_d)
RVVCALL(OPIVX2, vmul_vx_b, OP_SSS_B, H1, H1, DO_MUL)
RVVCALL(OPIVX2, vmul_vx_h, OP_SSS_H, H2, H2, DO_MUL)
@@ -1540,22 +1538,22 @@ RVVCALL(OPIVX2, vmulhsu_vx_b, OP_SUS_B, H1, H1, do_mulhsu_b)
RVVCALL(OPIVX2, vmulhsu_vx_h, OP_SUS_H, H2, H2, do_mulhsu_h)
RVVCALL(OPIVX2, vmulhsu_vx_w, OP_SUS_W, H4, H4, do_mulhsu_w)
RVVCALL(OPIVX2, vmulhsu_vx_d, OP_SUS_D, H8, H8, do_mulhsu_d)
-GEN_VEXT_VX(vmul_vx_b, 1, 1)
-GEN_VEXT_VX(vmul_vx_h, 2, 2)
-GEN_VEXT_VX(vmul_vx_w, 4, 4)
-GEN_VEXT_VX(vmul_vx_d, 8, 8)
-GEN_VEXT_VX(vmulh_vx_b, 1, 1)
-GEN_VEXT_VX(vmulh_vx_h, 2, 2)
-GEN_VEXT_VX(vmulh_vx_w, 4, 4)
-GEN_VEXT_VX(vmulh_vx_d, 8, 8)
-GEN_VEXT_VX(vmulhu_vx_b, 1, 1)
-GEN_VEXT_VX(vmulhu_vx_h, 2, 2)
-GEN_VEXT_VX(vmulhu_vx_w, 4, 4)
-GEN_VEXT_VX(vmulhu_vx_d, 8, 8)
-GEN_VEXT_VX(vmulhsu_vx_b, 1, 1)
-GEN_VEXT_VX(vmulhsu_vx_h, 2, 2)
-GEN_VEXT_VX(vmulhsu_vx_w, 4, 4)
-GEN_VEXT_VX(vmulhsu_vx_d, 8, 8)
+GEN_VEXT_VX(vmul_vx_b)
+GEN_VEXT_VX(vmul_vx_h)
+GEN_VEXT_VX(vmul_vx_w)
+GEN_VEXT_VX(vmul_vx_d)
+GEN_VEXT_VX(vmulh_vx_b)
+GEN_VEXT_VX(vmulh_vx_h)
+GEN_VEXT_VX(vmulh_vx_w)
+GEN_VEXT_VX(vmulh_vx_d)
+GEN_VEXT_VX(vmulhu_vx_b)
+GEN_VEXT_VX(vmulhu_vx_h)
+GEN_VEXT_VX(vmulhu_vx_w)
+GEN_VEXT_VX(vmulhu_vx_d)
+GEN_VEXT_VX(vmulhsu_vx_b)
+GEN_VEXT_VX(vmulhsu_vx_h)
+GEN_VEXT_VX(vmulhsu_vx_w)
+GEN_VEXT_VX(vmulhsu_vx_d)
/* Vector Integer Divide Instructions */
#define DO_DIVU(N, M) (unlikely(M == 0) ? (__typeof(N))(-1) : N / M)
@@ -1581,22 +1579,22 @@ RVVCALL(OPIVV2, vrem_vv_b, OP_SSS_B, H1, H1, H1, DO_REM)
RVVCALL(OPIVV2, vrem_vv_h, OP_SSS_H, H2, H2, H2, DO_REM)
RVVCALL(OPIVV2, vrem_vv_w, OP_SSS_W, H4, H4, H4, DO_REM)
RVVCALL(OPIVV2, vrem_vv_d, OP_SSS_D, H8, H8, H8, DO_REM)
-GEN_VEXT_VV(vdivu_vv_b, 1, 1)
-GEN_VEXT_VV(vdivu_vv_h, 2, 2)
-GEN_VEXT_VV(vdivu_vv_w, 4, 4)
-GEN_VEXT_VV(vdivu_vv_d, 8, 8)
-GEN_VEXT_VV(vdiv_vv_b, 1, 1)
-GEN_VEXT_VV(vdiv_vv_h, 2, 2)
-GEN_VEXT_VV(vdiv_vv_w, 4, 4)
-GEN_VEXT_VV(vdiv_vv_d, 8, 8)
-GEN_VEXT_VV(vremu_vv_b, 1, 1)
-GEN_VEXT_VV(vremu_vv_h, 2, 2)
-GEN_VEXT_VV(vremu_vv_w, 4, 4)
-GEN_VEXT_VV(vremu_vv_d, 8, 8)
-GEN_VEXT_VV(vrem_vv_b, 1, 1)
-GEN_VEXT_VV(vrem_vv_h, 2, 2)
-GEN_VEXT_VV(vrem_vv_w, 4, 4)
-GEN_VEXT_VV(vrem_vv_d, 8, 8)
+GEN_VEXT_VV(vdivu_vv_b)
+GEN_VEXT_VV(vdivu_vv_h)
+GEN_VEXT_VV(vdivu_vv_w)
+GEN_VEXT_VV(vdivu_vv_d)
+GEN_VEXT_VV(vdiv_vv_b)
+GEN_VEXT_VV(vdiv_vv_h)
+GEN_VEXT_VV(vdiv_vv_w)
+GEN_VEXT_VV(vdiv_vv_d)
+GEN_VEXT_VV(vremu_vv_b)
+GEN_VEXT_VV(vremu_vv_h)
+GEN_VEXT_VV(vremu_vv_w)
+GEN_VEXT_VV(vremu_vv_d)
+GEN_VEXT_VV(vrem_vv_b)
+GEN_VEXT_VV(vrem_vv_h)
+GEN_VEXT_VV(vrem_vv_w)
+GEN_VEXT_VV(vrem_vv_d)
RVVCALL(OPIVX2, vdivu_vx_b, OP_UUU_B, H1, H1, DO_DIVU)
RVVCALL(OPIVX2, vdivu_vx_h, OP_UUU_H, H2, H2, DO_DIVU)
@@ -1614,22 +1612,22 @@ RVVCALL(OPIVX2, vrem_vx_b, OP_SSS_B, H1, H1, DO_REM)
RVVCALL(OPIVX2, vrem_vx_h, OP_SSS_H, H2, H2, DO_REM)
RVVCALL(OPIVX2, vrem_vx_w, OP_SSS_W, H4, H4, DO_REM)
RVVCALL(OPIVX2, vrem_vx_d, OP_SSS_D, H8, H8, DO_REM)
-GEN_VEXT_VX(vdivu_vx_b, 1, 1)
-GEN_VEXT_VX(vdivu_vx_h, 2, 2)
-GEN_VEXT_VX(vdivu_vx_w, 4, 4)
-GEN_VEXT_VX(vdivu_vx_d, 8, 8)
-GEN_VEXT_VX(vdiv_vx_b, 1, 1)
-GEN_VEXT_VX(vdiv_vx_h, 2, 2)
-GEN_VEXT_VX(vdiv_vx_w, 4, 4)
-GEN_VEXT_VX(vdiv_vx_d, 8, 8)
-GEN_VEXT_VX(vremu_vx_b, 1, 1)
-GEN_VEXT_VX(vremu_vx_h, 2, 2)
-GEN_VEXT_VX(vremu_vx_w, 4, 4)
-GEN_VEXT_VX(vremu_vx_d, 8, 8)
-GEN_VEXT_VX(vrem_vx_b, 1, 1)
-GEN_VEXT_VX(vrem_vx_h, 2, 2)
-GEN_VEXT_VX(vrem_vx_w, 4, 4)
-GEN_VEXT_VX(vrem_vx_d, 8, 8)
+GEN_VEXT_VX(vdivu_vx_b)
+GEN_VEXT_VX(vdivu_vx_h)
+GEN_VEXT_VX(vdivu_vx_w)
+GEN_VEXT_VX(vdivu_vx_d)
+GEN_VEXT_VX(vdiv_vx_b)
+GEN_VEXT_VX(vdiv_vx_h)
+GEN_VEXT_VX(vdiv_vx_w)
+GEN_VEXT_VX(vdiv_vx_d)
+GEN_VEXT_VX(vremu_vx_b)
+GEN_VEXT_VX(vremu_vx_h)
+GEN_VEXT_VX(vremu_vx_w)
+GEN_VEXT_VX(vremu_vx_d)
+GEN_VEXT_VX(vrem_vx_b)
+GEN_VEXT_VX(vrem_vx_h)
+GEN_VEXT_VX(vrem_vx_w)
+GEN_VEXT_VX(vrem_vx_d)
/* Vector Widening Integer Multiply Instructions */
RVVCALL(OPIVV2, vwmul_vv_b, WOP_SSS_B, H2, H1, H1, DO_MUL)
@@ -1641,15 +1639,15 @@ RVVCALL(OPIVV2, vwmulu_vv_w, WOP_UUU_W, H8, H4, H4, DO_MUL)
RVVCALL(OPIVV2, vwmulsu_vv_b, WOP_SUS_B, H2, H1, H1, DO_MUL)
RVVCALL(OPIVV2, vwmulsu_vv_h, WOP_SUS_H, H4, H2, H2, DO_MUL)
RVVCALL(OPIVV2, vwmulsu_vv_w, WOP_SUS_W, H8, H4, H4, DO_MUL)
-GEN_VEXT_VV(vwmul_vv_b, 1, 2)
-GEN_VEXT_VV(vwmul_vv_h, 2, 4)
-GEN_VEXT_VV(vwmul_vv_w, 4, 8)
-GEN_VEXT_VV(vwmulu_vv_b, 1, 2)
-GEN_VEXT_VV(vwmulu_vv_h, 2, 4)
-GEN_VEXT_VV(vwmulu_vv_w, 4, 8)
-GEN_VEXT_VV(vwmulsu_vv_b, 1, 2)
-GEN_VEXT_VV(vwmulsu_vv_h, 2, 4)
-GEN_VEXT_VV(vwmulsu_vv_w, 4, 8)
+GEN_VEXT_VV(vwmul_vv_b)
+GEN_VEXT_VV(vwmul_vv_h)
+GEN_VEXT_VV(vwmul_vv_w)
+GEN_VEXT_VV(vwmulu_vv_b)
+GEN_VEXT_VV(vwmulu_vv_h)
+GEN_VEXT_VV(vwmulu_vv_w)
+GEN_VEXT_VV(vwmulsu_vv_b)
+GEN_VEXT_VV(vwmulsu_vv_h)
+GEN_VEXT_VV(vwmulsu_vv_w)
RVVCALL(OPIVX2, vwmul_vx_b, WOP_SSS_B, H2, H1, DO_MUL)
RVVCALL(OPIVX2, vwmul_vx_h, WOP_SSS_H, H4, H2, DO_MUL)
@@ -1660,15 +1658,15 @@ RVVCALL(OPIVX2, vwmulu_vx_w, WOP_UUU_W, H8, H4, DO_MUL)
RVVCALL(OPIVX2, vwmulsu_vx_b, WOP_SUS_B, H2, H1, DO_MUL)
RVVCALL(OPIVX2, vwmulsu_vx_h, WOP_SUS_H, H4, H2, DO_MUL)
RVVCALL(OPIVX2, vwmulsu_vx_w, WOP_SUS_W, H8, H4, DO_MUL)
-GEN_VEXT_VX(vwmul_vx_b, 1, 2)
-GEN_VEXT_VX(vwmul_vx_h, 2, 4)
-GEN_VEXT_VX(vwmul_vx_w, 4, 8)
-GEN_VEXT_VX(vwmulu_vx_b, 1, 2)
-GEN_VEXT_VX(vwmulu_vx_h, 2, 4)
-GEN_VEXT_VX(vwmulu_vx_w, 4, 8)
-GEN_VEXT_VX(vwmulsu_vx_b, 1, 2)
-GEN_VEXT_VX(vwmulsu_vx_h, 2, 4)
-GEN_VEXT_VX(vwmulsu_vx_w, 4, 8)
+GEN_VEXT_VX(vwmul_vx_b)
+GEN_VEXT_VX(vwmul_vx_h)
+GEN_VEXT_VX(vwmul_vx_w)
+GEN_VEXT_VX(vwmulu_vx_b)
+GEN_VEXT_VX(vwmulu_vx_h)
+GEN_VEXT_VX(vwmulu_vx_w)
+GEN_VEXT_VX(vwmulsu_vx_b)
+GEN_VEXT_VX(vwmulsu_vx_h)
+GEN_VEXT_VX(vwmulsu_vx_w)
/* Vector Single-Width Integer Multiply-Add Instructions */
#define OPIVV3(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP) \
@@ -1700,22 +1698,22 @@ RVVCALL(OPIVV3, vnmsub_vv_b, OP_SSS_B, H1, H1, H1, DO_NMSUB)
RVVCALL(OPIVV3, vnmsub_vv_h, OP_SSS_H, H2, H2, H2, DO_NMSUB)
RVVCALL(OPIVV3, vnmsub_vv_w, OP_SSS_W, H4, H4, H4, DO_NMSUB)
RVVCALL(OPIVV3, vnmsub_vv_d, OP_SSS_D, H8, H8, H8, DO_NMSUB)
-GEN_VEXT_VV(vmacc_vv_b, 1, 1)
-GEN_VEXT_VV(vmacc_vv_h, 2, 2)
-GEN_VEXT_VV(vmacc_vv_w, 4, 4)
-GEN_VEXT_VV(vmacc_vv_d, 8, 8)
-GEN_VEXT_VV(vnmsac_vv_b, 1, 1)
-GEN_VEXT_VV(vnmsac_vv_h, 2, 2)
-GEN_VEXT_VV(vnmsac_vv_w, 4, 4)
-GEN_VEXT_VV(vnmsac_vv_d, 8, 8)
-GEN_VEXT_VV(vmadd_vv_b, 1, 1)
-GEN_VEXT_VV(vmadd_vv_h, 2, 2)
-GEN_VEXT_VV(vmadd_vv_w, 4, 4)
-GEN_VEXT_VV(vmadd_vv_d, 8, 8)
-GEN_VEXT_VV(vnmsub_vv_b, 1, 1)
-GEN_VEXT_VV(vnmsub_vv_h, 2, 2)
-GEN_VEXT_VV(vnmsub_vv_w, 4, 4)
-GEN_VEXT_VV(vnmsub_vv_d, 8, 8)
+GEN_VEXT_VV(vmacc_vv_b)
+GEN_VEXT_VV(vmacc_vv_h)
+GEN_VEXT_VV(vmacc_vv_w)
+GEN_VEXT_VV(vmacc_vv_d)
+GEN_VEXT_VV(vnmsac_vv_b)
+GEN_VEXT_VV(vnmsac_vv_h)
+GEN_VEXT_VV(vnmsac_vv_w)
+GEN_VEXT_VV(vnmsac_vv_d)
+GEN_VEXT_VV(vmadd_vv_b)
+GEN_VEXT_VV(vmadd_vv_h)
+GEN_VEXT_VV(vmadd_vv_w)
+GEN_VEXT_VV(vmadd_vv_d)
+GEN_VEXT_VV(vnmsub_vv_b)
+GEN_VEXT_VV(vnmsub_vv_h)
+GEN_VEXT_VV(vnmsub_vv_w)
+GEN_VEXT_VV(vnmsub_vv_d)
#define OPIVX3(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \
static void do_##NAME(void *vd, target_long s1, void *vs2, int i) \
@@ -1741,22 +1739,22 @@ RVVCALL(OPIVX3, vnmsub_vx_b, OP_SSS_B, H1, H1, DO_NMSUB)
RVVCALL(OPIVX3, vnmsub_vx_h, OP_SSS_H, H2, H2, DO_NMSUB)
RVVCALL(OPIVX3, vnmsub_vx_w, OP_SSS_W, H4, H4, DO_NMSUB)
RVVCALL(OPIVX3, vnmsub_vx_d, OP_SSS_D, H8, H8, DO_NMSUB)
-GEN_VEXT_VX(vmacc_vx_b, 1, 1)
-GEN_VEXT_VX(vmacc_vx_h, 2, 2)
-GEN_VEXT_VX(vmacc_vx_w, 4, 4)
-GEN_VEXT_VX(vmacc_vx_d, 8, 8)
-GEN_VEXT_VX(vnmsac_vx_b, 1, 1)
-GEN_VEXT_VX(vnmsac_vx_h, 2, 2)
-GEN_VEXT_VX(vnmsac_vx_w, 4, 4)
-GEN_VEXT_VX(vnmsac_vx_d, 8, 8)
-GEN_VEXT_VX(vmadd_vx_b, 1, 1)
-GEN_VEXT_VX(vmadd_vx_h, 2, 2)
-GEN_VEXT_VX(vmadd_vx_w, 4, 4)
-GEN_VEXT_VX(vmadd_vx_d, 8, 8)
-GEN_VEXT_VX(vnmsub_vx_b, 1, 1)
-GEN_VEXT_VX(vnmsub_vx_h, 2, 2)
-GEN_VEXT_VX(vnmsub_vx_w, 4, 4)
-GEN_VEXT_VX(vnmsub_vx_d, 8, 8)
+GEN_VEXT_VX(vmacc_vx_b)
+GEN_VEXT_VX(vmacc_vx_h)
+GEN_VEXT_VX(vmacc_vx_w)
+GEN_VEXT_VX(vmacc_vx_d)
+GEN_VEXT_VX(vnmsac_vx_b)
+GEN_VEXT_VX(vnmsac_vx_h)
+GEN_VEXT_VX(vnmsac_vx_w)
+GEN_VEXT_VX(vnmsac_vx_d)
+GEN_VEXT_VX(vmadd_vx_b)
+GEN_VEXT_VX(vmadd_vx_h)
+GEN_VEXT_VX(vmadd_vx_w)
+GEN_VEXT_VX(vmadd_vx_d)
+GEN_VEXT_VX(vnmsub_vx_b)
+GEN_VEXT_VX(vnmsub_vx_h)
+GEN_VEXT_VX(vnmsub_vx_w)
+GEN_VEXT_VX(vnmsub_vx_d)
/* Vector Widening Integer Multiply-Add Instructions */
RVVCALL(OPIVV3, vwmaccu_vv_b, WOP_UUU_B, H2, H1, H1, DO_MACC)
@@ -1768,15 +1766,15 @@ RVVCALL(OPIVV3, vwmacc_vv_w, WOP_SSS_W, H8, H4, H4, DO_MACC)
RVVCALL(OPIVV3, vwmaccsu_vv_b, WOP_SSU_B, H2, H1, H1, DO_MACC)
RVVCALL(OPIVV3, vwmaccsu_vv_h, WOP_SSU_H, H4, H2, H2, DO_MACC)
RVVCALL(OPIVV3, vwmaccsu_vv_w, WOP_SSU_W, H8, H4, H4, DO_MACC)
-GEN_VEXT_VV(vwmaccu_vv_b, 1, 2)
-GEN_VEXT_VV(vwmaccu_vv_h, 2, 4)
-GEN_VEXT_VV(vwmaccu_vv_w, 4, 8)
-GEN_VEXT_VV(vwmacc_vv_b, 1, 2)
-GEN_VEXT_VV(vwmacc_vv_h, 2, 4)
-GEN_VEXT_VV(vwmacc_vv_w, 4, 8)
-GEN_VEXT_VV(vwmaccsu_vv_b, 1, 2)
-GEN_VEXT_VV(vwmaccsu_vv_h, 2, 4)
-GEN_VEXT_VV(vwmaccsu_vv_w, 4, 8)
+GEN_VEXT_VV(vwmaccu_vv_b)
+GEN_VEXT_VV(vwmaccu_vv_h)
+GEN_VEXT_VV(vwmaccu_vv_w)
+GEN_VEXT_VV(vwmacc_vv_b)
+GEN_VEXT_VV(vwmacc_vv_h)
+GEN_VEXT_VV(vwmacc_vv_w)
+GEN_VEXT_VV(vwmaccsu_vv_b)
+GEN_VEXT_VV(vwmaccsu_vv_h)
+GEN_VEXT_VV(vwmaccsu_vv_w)
RVVCALL(OPIVX3, vwmaccu_vx_b, WOP_UUU_B, H2, H1, DO_MACC)
RVVCALL(OPIVX3, vwmaccu_vx_h, WOP_UUU_H, H4, H2, DO_MACC)
@@ -1790,18 +1788,18 @@ RVVCALL(OPIVX3, vwmaccsu_vx_w, WOP_SSU_W, H8, H4, DO_MACC)
RVVCALL(OPIVX3, vwmaccus_vx_b, WOP_SUS_B, H2, H1, DO_MACC)
RVVCALL(OPIVX3, vwmaccus_vx_h, WOP_SUS_H, H4, H2, DO_MACC)
RVVCALL(OPIVX3, vwmaccus_vx_w, WOP_SUS_W, H8, H4, DO_MACC)
-GEN_VEXT_VX(vwmaccu_vx_b, 1, 2)
-GEN_VEXT_VX(vwmaccu_vx_h, 2, 4)
-GEN_VEXT_VX(vwmaccu_vx_w, 4, 8)
-GEN_VEXT_VX(vwmacc_vx_b, 1, 2)
-GEN_VEXT_VX(vwmacc_vx_h, 2, 4)
-GEN_VEXT_VX(vwmacc_vx_w, 4, 8)
-GEN_VEXT_VX(vwmaccsu_vx_b, 1, 2)
-GEN_VEXT_VX(vwmaccsu_vx_h, 2, 4)
-GEN_VEXT_VX(vwmaccsu_vx_w, 4, 8)
-GEN_VEXT_VX(vwmaccus_vx_b, 1, 2)
-GEN_VEXT_VX(vwmaccus_vx_h, 2, 4)
-GEN_VEXT_VX(vwmaccus_vx_w, 4, 8)
+GEN_VEXT_VX(vwmaccu_vx_b)
+GEN_VEXT_VX(vwmaccu_vx_h)
+GEN_VEXT_VX(vwmaccu_vx_w)
+GEN_VEXT_VX(vwmacc_vx_b)
+GEN_VEXT_VX(vwmacc_vx_h)
+GEN_VEXT_VX(vwmacc_vx_w)
+GEN_VEXT_VX(vwmaccsu_vx_b)
+GEN_VEXT_VX(vwmaccsu_vx_h)
+GEN_VEXT_VX(vwmaccsu_vx_w)
+GEN_VEXT_VX(vwmaccus_vx_b)
+GEN_VEXT_VX(vwmaccus_vx_h)
+GEN_VEXT_VX(vwmaccus_vx_w)
/* Vector Integer Merge and Move Instructions */
#define GEN_VEXT_VMV_VV(NAME, ETYPE, H) \
@@ -1922,7 +1920,7 @@ vext_vv_rm_1(void *vd, void *v0, void *vs1, void *vs2,
static inline void
vext_vv_rm_2(void *vd, void *v0, void *vs1, void *vs2,
CPURISCVState *env,
- uint32_t desc, uint32_t esz, uint32_t dsz,
+ uint32_t desc,
opivv2_rm_fn *fn)
{
uint32_t vm = vext_vm(desc);
@@ -1949,11 +1947,11 @@ vext_vv_rm_2(void *vd, void *v0, void *vs1, void *vs2,
}
/* generate helpers for fixed point instructions with OPIVV format */
-#define GEN_VEXT_VV_RM(NAME, ESZ, DSZ) \
+#define GEN_VEXT_VV_RM(NAME) \
void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
- vext_vv_rm_2(vd, v0, vs1, vs2, env, desc, ESZ, DSZ, \
+ vext_vv_rm_2(vd, v0, vs1, vs2, env, desc, \
do_##NAME); \
}
@@ -2004,10 +2002,10 @@ RVVCALL(OPIVV2_RM, vsaddu_vv_b, OP_UUU_B, H1, H1, H1, saddu8)
RVVCALL(OPIVV2_RM, vsaddu_vv_h, OP_UUU_H, H2, H2, H2, saddu16)
RVVCALL(OPIVV2_RM, vsaddu_vv_w, OP_UUU_W, H4, H4, H4, saddu32)
RVVCALL(OPIVV2_RM, vsaddu_vv_d, OP_UUU_D, H8, H8, H8, saddu64)
-GEN_VEXT_VV_RM(vsaddu_vv_b, 1, 1)
-GEN_VEXT_VV_RM(vsaddu_vv_h, 2, 2)
-GEN_VEXT_VV_RM(vsaddu_vv_w, 4, 4)
-GEN_VEXT_VV_RM(vsaddu_vv_d, 8, 8)
+GEN_VEXT_VV_RM(vsaddu_vv_b)
+GEN_VEXT_VV_RM(vsaddu_vv_h)
+GEN_VEXT_VV_RM(vsaddu_vv_w)
+GEN_VEXT_VV_RM(vsaddu_vv_d)
typedef void opivx2_rm_fn(void *vd, target_long s1, void *vs2, int i,
CPURISCVState *env, int vxrm);
@@ -2039,7 +2037,7 @@ vext_vx_rm_1(void *vd, void *v0, target_long s1, void *vs2,
static inline void
vext_vx_rm_2(void *vd, void *v0, target_long s1, void *vs2,
CPURISCVState *env,
- uint32_t desc, uint32_t esz, uint32_t dsz,
+ uint32_t desc,
opivx2_rm_fn *fn)
{
uint32_t vm = vext_vm(desc);
@@ -2066,11 +2064,11 @@ vext_vx_rm_2(void *vd, void *v0, target_long s1, void *vs2,
}
/* generate helpers for fixed point instructions with OPIVX format */
-#define GEN_VEXT_VX_RM(NAME, ESZ, DSZ) \
+#define GEN_VEXT_VX_RM(NAME) \
void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
void *vs2, CPURISCVState *env, uint32_t desc) \
{ \
- vext_vx_rm_2(vd, v0, s1, vs2, env, desc, ESZ, DSZ, \
+ vext_vx_rm_2(vd, v0, s1, vs2, env, desc, \
do_##NAME); \
}
@@ -2078,10 +2076,10 @@ RVVCALL(OPIVX2_RM, vsaddu_vx_b, OP_UUU_B, H1, H1, saddu8)
RVVCALL(OPIVX2_RM, vsaddu_vx_h, OP_UUU_H, H2, H2, saddu16)
RVVCALL(OPIVX2_RM, vsaddu_vx_w, OP_UUU_W, H4, H4, saddu32)
RVVCALL(OPIVX2_RM, vsaddu_vx_d, OP_UUU_D, H8, H8, saddu64)
-GEN_VEXT_VX_RM(vsaddu_vx_b, 1, 1)
-GEN_VEXT_VX_RM(vsaddu_vx_h, 2, 2)
-GEN_VEXT_VX_RM(vsaddu_vx_w, 4, 4)
-GEN_VEXT_VX_RM(vsaddu_vx_d, 8, 8)
+GEN_VEXT_VX_RM(vsaddu_vx_b)
+GEN_VEXT_VX_RM(vsaddu_vx_h)
+GEN_VEXT_VX_RM(vsaddu_vx_w)
+GEN_VEXT_VX_RM(vsaddu_vx_d)
static inline int8_t sadd8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
{
@@ -2127,19 +2125,19 @@ RVVCALL(OPIVV2_RM, vsadd_vv_b, OP_SSS_B, H1, H1, H1, sadd8)
RVVCALL(OPIVV2_RM, vsadd_vv_h, OP_SSS_H, H2, H2, H2, sadd16)
RVVCALL(OPIVV2_RM, vsadd_vv_w, OP_SSS_W, H4, H4, H4, sadd32)
RVVCALL(OPIVV2_RM, vsadd_vv_d, OP_SSS_D, H8, H8, H8, sadd64)
-GEN_VEXT_VV_RM(vsadd_vv_b, 1, 1)
-GEN_VEXT_VV_RM(vsadd_vv_h, 2, 2)
-GEN_VEXT_VV_RM(vsadd_vv_w, 4, 4)
-GEN_VEXT_VV_RM(vsadd_vv_d, 8, 8)
+GEN_VEXT_VV_RM(vsadd_vv_b)
+GEN_VEXT_VV_RM(vsadd_vv_h)
+GEN_VEXT_VV_RM(vsadd_vv_w)
+GEN_VEXT_VV_RM(vsadd_vv_d)
RVVCALL(OPIVX2_RM, vsadd_vx_b, OP_SSS_B, H1, H1, sadd8)
RVVCALL(OPIVX2_RM, vsadd_vx_h, OP_SSS_H, H2, H2, sadd16)
RVVCALL(OPIVX2_RM, vsadd_vx_w, OP_SSS_W, H4, H4, sadd32)
RVVCALL(OPIVX2_RM, vsadd_vx_d, OP_SSS_D, H8, H8, sadd64)
-GEN_VEXT_VX_RM(vsadd_vx_b, 1, 1)
-GEN_VEXT_VX_RM(vsadd_vx_h, 2, 2)
-GEN_VEXT_VX_RM(vsadd_vx_w, 4, 4)
-GEN_VEXT_VX_RM(vsadd_vx_d, 8, 8)
+GEN_VEXT_VX_RM(vsadd_vx_b)
+GEN_VEXT_VX_RM(vsadd_vx_h)
+GEN_VEXT_VX_RM(vsadd_vx_w)
+GEN_VEXT_VX_RM(vsadd_vx_d)
static inline uint8_t ssubu8(CPURISCVState *env, int vxrm, uint8_t a, uint8_t b)
{
@@ -2188,19 +2186,19 @@ RVVCALL(OPIVV2_RM, vssubu_vv_b, OP_UUU_B, H1, H1, H1, ssubu8)
RVVCALL(OPIVV2_RM, vssubu_vv_h, OP_UUU_H, H2, H2, H2, ssubu16)
RVVCALL(OPIVV2_RM, vssubu_vv_w, OP_UUU_W, H4, H4, H4, ssubu32)
RVVCALL(OPIVV2_RM, vssubu_vv_d, OP_UUU_D, H8, H8, H8, ssubu64)
-GEN_VEXT_VV_RM(vssubu_vv_b, 1, 1)
-GEN_VEXT_VV_RM(vssubu_vv_h, 2, 2)
-GEN_VEXT_VV_RM(vssubu_vv_w, 4, 4)
-GEN_VEXT_VV_RM(vssubu_vv_d, 8, 8)
+GEN_VEXT_VV_RM(vssubu_vv_b)
+GEN_VEXT_VV_RM(vssubu_vv_h)
+GEN_VEXT_VV_RM(vssubu_vv_w)
+GEN_VEXT_VV_RM(vssubu_vv_d)
RVVCALL(OPIVX2_RM, vssubu_vx_b, OP_UUU_B, H1, H1, ssubu8)
RVVCALL(OPIVX2_RM, vssubu_vx_h, OP_UUU_H, H2, H2, ssubu16)
RVVCALL(OPIVX2_RM, vssubu_vx_w, OP_UUU_W, H4, H4, ssubu32)
RVVCALL(OPIVX2_RM, vssubu_vx_d, OP_UUU_D, H8, H8, ssubu64)
-GEN_VEXT_VX_RM(vssubu_vx_b, 1, 1)
-GEN_VEXT_VX_RM(vssubu_vx_h, 2, 2)
-GEN_VEXT_VX_RM(vssubu_vx_w, 4, 4)
-GEN_VEXT_VX_RM(vssubu_vx_d, 8, 8)
+GEN_VEXT_VX_RM(vssubu_vx_b)
+GEN_VEXT_VX_RM(vssubu_vx_h)
+GEN_VEXT_VX_RM(vssubu_vx_w)
+GEN_VEXT_VX_RM(vssubu_vx_d)
static inline int8_t ssub8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
{
@@ -2246,19 +2244,19 @@ RVVCALL(OPIVV2_RM, vssub_vv_b, OP_SSS_B, H1, H1, H1, ssub8)
RVVCALL(OPIVV2_RM, vssub_vv_h, OP_SSS_H, H2, H2, H2, ssub16)
RVVCALL(OPIVV2_RM, vssub_vv_w, OP_SSS_W, H4, H4, H4, ssub32)
RVVCALL(OPIVV2_RM, vssub_vv_d, OP_SSS_D, H8, H8, H8, ssub64)
-GEN_VEXT_VV_RM(vssub_vv_b, 1, 1)
-GEN_VEXT_VV_RM(vssub_vv_h, 2, 2)
-GEN_VEXT_VV_RM(vssub_vv_w, 4, 4)
-GEN_VEXT_VV_RM(vssub_vv_d, 8, 8)
+GEN_VEXT_VV_RM(vssub_vv_b)
+GEN_VEXT_VV_RM(vssub_vv_h)
+GEN_VEXT_VV_RM(vssub_vv_w)
+GEN_VEXT_VV_RM(vssub_vv_d)
RVVCALL(OPIVX2_RM, vssub_vx_b, OP_SSS_B, H1, H1, ssub8)
RVVCALL(OPIVX2_RM, vssub_vx_h, OP_SSS_H, H2, H2, ssub16)
RVVCALL(OPIVX2_RM, vssub_vx_w, OP_SSS_W, H4, H4, ssub32)
RVVCALL(OPIVX2_RM, vssub_vx_d, OP_SSS_D, H8, H8, ssub64)
-GEN_VEXT_VX_RM(vssub_vx_b, 1, 1)
-GEN_VEXT_VX_RM(vssub_vx_h, 2, 2)
-GEN_VEXT_VX_RM(vssub_vx_w, 4, 4)
-GEN_VEXT_VX_RM(vssub_vx_d, 8, 8)
+GEN_VEXT_VX_RM(vssub_vx_b)
+GEN_VEXT_VX_RM(vssub_vx_h)
+GEN_VEXT_VX_RM(vssub_vx_w)
+GEN_VEXT_VX_RM(vssub_vx_d)
/* Vector Single-Width Averaging Add and Subtract */
static inline uint8_t get_round(int vxrm, uint64_t v, uint8_t shift)
@@ -2310,19 +2308,19 @@ RVVCALL(OPIVV2_RM, vaadd_vv_b, OP_SSS_B, H1, H1, H1, aadd32)
RVVCALL(OPIVV2_RM, vaadd_vv_h, OP_SSS_H, H2, H2, H2, aadd32)
RVVCALL(OPIVV2_RM, vaadd_vv_w, OP_SSS_W, H4, H4, H4, aadd32)
RVVCALL(OPIVV2_RM, vaadd_vv_d, OP_SSS_D, H8, H8, H8, aadd64)
-GEN_VEXT_VV_RM(vaadd_vv_b, 1, 1)
-GEN_VEXT_VV_RM(vaadd_vv_h, 2, 2)
-GEN_VEXT_VV_RM(vaadd_vv_w, 4, 4)
-GEN_VEXT_VV_RM(vaadd_vv_d, 8, 8)
+GEN_VEXT_VV_RM(vaadd_vv_b)
+GEN_VEXT_VV_RM(vaadd_vv_h)
+GEN_VEXT_VV_RM(vaadd_vv_w)
+GEN_VEXT_VV_RM(vaadd_vv_d)
RVVCALL(OPIVX2_RM, vaadd_vx_b, OP_SSS_B, H1, H1, aadd32)
RVVCALL(OPIVX2_RM, vaadd_vx_h, OP_SSS_H, H2, H2, aadd32)
RVVCALL(OPIVX2_RM, vaadd_vx_w, OP_SSS_W, H4, H4, aadd32)
RVVCALL(OPIVX2_RM, vaadd_vx_d, OP_SSS_D, H8, H8, aadd64)
-GEN_VEXT_VX_RM(vaadd_vx_b, 1, 1)
-GEN_VEXT_VX_RM(vaadd_vx_h, 2, 2)
-GEN_VEXT_VX_RM(vaadd_vx_w, 4, 4)
-GEN_VEXT_VX_RM(vaadd_vx_d, 8, 8)
+GEN_VEXT_VX_RM(vaadd_vx_b)
+GEN_VEXT_VX_RM(vaadd_vx_h)
+GEN_VEXT_VX_RM(vaadd_vx_w)
+GEN_VEXT_VX_RM(vaadd_vx_d)
static inline uint32_t aaddu32(CPURISCVState *env, int vxrm,
uint32_t a, uint32_t b)
@@ -2347,19 +2345,19 @@ RVVCALL(OPIVV2_RM, vaaddu_vv_b, OP_UUU_B, H1, H1, H1, aaddu32)
RVVCALL(OPIVV2_RM, vaaddu_vv_h, OP_UUU_H, H2, H2, H2, aaddu32)
RVVCALL(OPIVV2_RM, vaaddu_vv_w, OP_UUU_W, H4, H4, H4, aaddu32)
RVVCALL(OPIVV2_RM, vaaddu_vv_d, OP_UUU_D, H8, H8, H8, aaddu64)
-GEN_VEXT_VV_RM(vaaddu_vv_b, 1, 1)
-GEN_VEXT_VV_RM(vaaddu_vv_h, 2, 2)
-GEN_VEXT_VV_RM(vaaddu_vv_w, 4, 4)
-GEN_VEXT_VV_RM(vaaddu_vv_d, 8, 8)
+GEN_VEXT_VV_RM(vaaddu_vv_b)
+GEN_VEXT_VV_RM(vaaddu_vv_h)
+GEN_VEXT_VV_RM(vaaddu_vv_w)
+GEN_VEXT_VV_RM(vaaddu_vv_d)
RVVCALL(OPIVX2_RM, vaaddu_vx_b, OP_UUU_B, H1, H1, aaddu32)
RVVCALL(OPIVX2_RM, vaaddu_vx_h, OP_UUU_H, H2, H2, aaddu32)
RVVCALL(OPIVX2_RM, vaaddu_vx_w, OP_UUU_W, H4, H4, aaddu32)
RVVCALL(OPIVX2_RM, vaaddu_vx_d, OP_UUU_D, H8, H8, aaddu64)
-GEN_VEXT_VX_RM(vaaddu_vx_b, 1, 1)
-GEN_VEXT_VX_RM(vaaddu_vx_h, 2, 2)
-GEN_VEXT_VX_RM(vaaddu_vx_w, 4, 4)
-GEN_VEXT_VX_RM(vaaddu_vx_d, 8, 8)
+GEN_VEXT_VX_RM(vaaddu_vx_b)
+GEN_VEXT_VX_RM(vaaddu_vx_h)
+GEN_VEXT_VX_RM(vaaddu_vx_w)
+GEN_VEXT_VX_RM(vaaddu_vx_d)
static inline int32_t asub32(CPURISCVState *env, int vxrm, int32_t a, int32_t b)
{
@@ -2383,19 +2381,19 @@ RVVCALL(OPIVV2_RM, vasub_vv_b, OP_SSS_B, H1, H1, H1, asub32)
RVVCALL(OPIVV2_RM, vasub_vv_h, OP_SSS_H, H2, H2, H2, asub32)
RVVCALL(OPIVV2_RM, vasub_vv_w, OP_SSS_W, H4, H4, H4, asub32)
RVVCALL(OPIVV2_RM, vasub_vv_d, OP_SSS_D, H8, H8, H8, asub64)
-GEN_VEXT_VV_RM(vasub_vv_b, 1, 1)
-GEN_VEXT_VV_RM(vasub_vv_h, 2, 2)
-GEN_VEXT_VV_RM(vasub_vv_w, 4, 4)
-GEN_VEXT_VV_RM(vasub_vv_d, 8, 8)
+GEN_VEXT_VV_RM(vasub_vv_b)
+GEN_VEXT_VV_RM(vasub_vv_h)
+GEN_VEXT_VV_RM(vasub_vv_w)
+GEN_VEXT_VV_RM(vasub_vv_d)
RVVCALL(OPIVX2_RM, vasub_vx_b, OP_SSS_B, H1, H1, asub32)
RVVCALL(OPIVX2_RM, vasub_vx_h, OP_SSS_H, H2, H2, asub32)
RVVCALL(OPIVX2_RM, vasub_vx_w, OP_SSS_W, H4, H4, asub32)
RVVCALL(OPIVX2_RM, vasub_vx_d, OP_SSS_D, H8, H8, asub64)
-GEN_VEXT_VX_RM(vasub_vx_b, 1, 1)
-GEN_VEXT_VX_RM(vasub_vx_h, 2, 2)
-GEN_VEXT_VX_RM(vasub_vx_w, 4, 4)
-GEN_VEXT_VX_RM(vasub_vx_d, 8, 8)
+GEN_VEXT_VX_RM(vasub_vx_b)
+GEN_VEXT_VX_RM(vasub_vx_h)
+GEN_VEXT_VX_RM(vasub_vx_w)
+GEN_VEXT_VX_RM(vasub_vx_d)
static inline uint32_t asubu32(CPURISCVState *env, int vxrm,
uint32_t a, uint32_t b)
@@ -2420,19 +2418,19 @@ RVVCALL(OPIVV2_RM, vasubu_vv_b, OP_UUU_B, H1, H1, H1, asubu32)
RVVCALL(OPIVV2_RM, vasubu_vv_h, OP_UUU_H, H2, H2, H2, asubu32)
RVVCALL(OPIVV2_RM, vasubu_vv_w, OP_UUU_W, H4, H4, H4, asubu32)
RVVCALL(OPIVV2_RM, vasubu_vv_d, OP_UUU_D, H8, H8, H8, asubu64)
-GEN_VEXT_VV_RM(vasubu_vv_b, 1, 1)
-GEN_VEXT_VV_RM(vasubu_vv_h, 2, 2)
-GEN_VEXT_VV_RM(vasubu_vv_w, 4, 4)
-GEN_VEXT_VV_RM(vasubu_vv_d, 8, 8)
+GEN_VEXT_VV_RM(vasubu_vv_b)
+GEN_VEXT_VV_RM(vasubu_vv_h)
+GEN_VEXT_VV_RM(vasubu_vv_w)
+GEN_VEXT_VV_RM(vasubu_vv_d)
RVVCALL(OPIVX2_RM, vasubu_vx_b, OP_UUU_B, H1, H1, asubu32)
RVVCALL(OPIVX2_RM, vasubu_vx_h, OP_UUU_H, H2, H2, asubu32)
RVVCALL(OPIVX2_RM, vasubu_vx_w, OP_UUU_W, H4, H4, asubu32)
RVVCALL(OPIVX2_RM, vasubu_vx_d, OP_UUU_D, H8, H8, asubu64)
-GEN_VEXT_VX_RM(vasubu_vx_b, 1, 1)
-GEN_VEXT_VX_RM(vasubu_vx_h, 2, 2)
-GEN_VEXT_VX_RM(vasubu_vx_w, 4, 4)
-GEN_VEXT_VX_RM(vasubu_vx_d, 8, 8)
+GEN_VEXT_VX_RM(vasubu_vx_b)
+GEN_VEXT_VX_RM(vasubu_vx_h)
+GEN_VEXT_VX_RM(vasubu_vx_w)
+GEN_VEXT_VX_RM(vasubu_vx_d)
/* Vector Single-Width Fractional Multiply with Rounding and Saturation */
static inline int8_t vsmul8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
@@ -2527,19 +2525,19 @@ RVVCALL(OPIVV2_RM, vsmul_vv_b, OP_SSS_B, H1, H1, H1, vsmul8)
RVVCALL(OPIVV2_RM, vsmul_vv_h, OP_SSS_H, H2, H2, H2, vsmul16)
RVVCALL(OPIVV2_RM, vsmul_vv_w, OP_SSS_W, H4, H4, H4, vsmul32)
RVVCALL(OPIVV2_RM, vsmul_vv_d, OP_SSS_D, H8, H8, H8, vsmul64)
-GEN_VEXT_VV_RM(vsmul_vv_b, 1, 1)
-GEN_VEXT_VV_RM(vsmul_vv_h, 2, 2)
-GEN_VEXT_VV_RM(vsmul_vv_w, 4, 4)
-GEN_VEXT_VV_RM(vsmul_vv_d, 8, 8)
+GEN_VEXT_VV_RM(vsmul_vv_b)
+GEN_VEXT_VV_RM(vsmul_vv_h)
+GEN_VEXT_VV_RM(vsmul_vv_w)
+GEN_VEXT_VV_RM(vsmul_vv_d)
RVVCALL(OPIVX2_RM, vsmul_vx_b, OP_SSS_B, H1, H1, vsmul8)
RVVCALL(OPIVX2_RM, vsmul_vx_h, OP_SSS_H, H2, H2, vsmul16)
RVVCALL(OPIVX2_RM, vsmul_vx_w, OP_SSS_W, H4, H4, vsmul32)
RVVCALL(OPIVX2_RM, vsmul_vx_d, OP_SSS_D, H8, H8, vsmul64)
-GEN_VEXT_VX_RM(vsmul_vx_b, 1, 1)
-GEN_VEXT_VX_RM(vsmul_vx_h, 2, 2)
-GEN_VEXT_VX_RM(vsmul_vx_w, 4, 4)
-GEN_VEXT_VX_RM(vsmul_vx_d, 8, 8)
+GEN_VEXT_VX_RM(vsmul_vx_b)
+GEN_VEXT_VX_RM(vsmul_vx_h)
+GEN_VEXT_VX_RM(vsmul_vx_w)
+GEN_VEXT_VX_RM(vsmul_vx_d)
/* Vector Single-Width Scaling Shift Instructions */
static inline uint8_t
@@ -2586,19 +2584,19 @@ RVVCALL(OPIVV2_RM, vssrl_vv_b, OP_UUU_B, H1, H1, H1, vssrl8)
RVVCALL(OPIVV2_RM, vssrl_vv_h, OP_UUU_H, H2, H2, H2, vssrl16)
RVVCALL(OPIVV2_RM, vssrl_vv_w, OP_UUU_W, H4, H4, H4, vssrl32)
RVVCALL(OPIVV2_RM, vssrl_vv_d, OP_UUU_D, H8, H8, H8, vssrl64)
-GEN_VEXT_VV_RM(vssrl_vv_b, 1, 1)
-GEN_VEXT_VV_RM(vssrl_vv_h, 2, 2)
-GEN_VEXT_VV_RM(vssrl_vv_w, 4, 4)
-GEN_VEXT_VV_RM(vssrl_vv_d, 8, 8)
+GEN_VEXT_VV_RM(vssrl_vv_b)
+GEN_VEXT_VV_RM(vssrl_vv_h)
+GEN_VEXT_VV_RM(vssrl_vv_w)
+GEN_VEXT_VV_RM(vssrl_vv_d)
RVVCALL(OPIVX2_RM, vssrl_vx_b, OP_UUU_B, H1, H1, vssrl8)
RVVCALL(OPIVX2_RM, vssrl_vx_h, OP_UUU_H, H2, H2, vssrl16)
RVVCALL(OPIVX2_RM, vssrl_vx_w, OP_UUU_W, H4, H4, vssrl32)
RVVCALL(OPIVX2_RM, vssrl_vx_d, OP_UUU_D, H8, H8, vssrl64)
-GEN_VEXT_VX_RM(vssrl_vx_b, 1, 1)
-GEN_VEXT_VX_RM(vssrl_vx_h, 2, 2)
-GEN_VEXT_VX_RM(vssrl_vx_w, 4, 4)
-GEN_VEXT_VX_RM(vssrl_vx_d, 8, 8)
+GEN_VEXT_VX_RM(vssrl_vx_b)
+GEN_VEXT_VX_RM(vssrl_vx_h)
+GEN_VEXT_VX_RM(vssrl_vx_w)
+GEN_VEXT_VX_RM(vssrl_vx_d)
static inline int8_t
vssra8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
@@ -2645,19 +2643,19 @@ RVVCALL(OPIVV2_RM, vssra_vv_b, OP_SSS_B, H1, H1, H1, vssra8)
RVVCALL(OPIVV2_RM, vssra_vv_h, OP_SSS_H, H2, H2, H2, vssra16)
RVVCALL(OPIVV2_RM, vssra_vv_w, OP_SSS_W, H4, H4, H4, vssra32)
RVVCALL(OPIVV2_RM, vssra_vv_d, OP_SSS_D, H8, H8, H8, vssra64)
-GEN_VEXT_VV_RM(vssra_vv_b, 1, 1)
-GEN_VEXT_VV_RM(vssra_vv_h, 2, 2)
-GEN_VEXT_VV_RM(vssra_vv_w, 4, 4)
-GEN_VEXT_VV_RM(vssra_vv_d, 8, 8)
+GEN_VEXT_VV_RM(vssra_vv_b)
+GEN_VEXT_VV_RM(vssra_vv_h)
+GEN_VEXT_VV_RM(vssra_vv_w)
+GEN_VEXT_VV_RM(vssra_vv_d)
RVVCALL(OPIVX2_RM, vssra_vx_b, OP_SSS_B, H1, H1, vssra8)
RVVCALL(OPIVX2_RM, vssra_vx_h, OP_SSS_H, H2, H2, vssra16)
RVVCALL(OPIVX2_RM, vssra_vx_w, OP_SSS_W, H4, H4, vssra32)
RVVCALL(OPIVX2_RM, vssra_vx_d, OP_SSS_D, H8, H8, vssra64)
-GEN_VEXT_VX_RM(vssra_vx_b, 1, 1)
-GEN_VEXT_VX_RM(vssra_vx_h, 2, 2)
-GEN_VEXT_VX_RM(vssra_vx_w, 4, 4)
-GEN_VEXT_VX_RM(vssra_vx_d, 8, 8)
+GEN_VEXT_VX_RM(vssra_vx_b)
+GEN_VEXT_VX_RM(vssra_vx_h)
+GEN_VEXT_VX_RM(vssra_vx_w)
+GEN_VEXT_VX_RM(vssra_vx_d)
/* Vector Narrowing Fixed-Point Clip Instructions */
static inline int8_t
@@ -2720,16 +2718,16 @@ vnclip32(CPURISCVState *env, int vxrm, int64_t a, int32_t b)
RVVCALL(OPIVV2_RM, vnclip_wv_b, NOP_SSS_B, H1, H2, H1, vnclip8)
RVVCALL(OPIVV2_RM, vnclip_wv_h, NOP_SSS_H, H2, H4, H2, vnclip16)
RVVCALL(OPIVV2_RM, vnclip_wv_w, NOP_SSS_W, H4, H8, H4, vnclip32)
-GEN_VEXT_VV_RM(vnclip_wv_b, 1, 1)
-GEN_VEXT_VV_RM(vnclip_wv_h, 2, 2)
-GEN_VEXT_VV_RM(vnclip_wv_w, 4, 4)
+GEN_VEXT_VV_RM(vnclip_wv_b)
+GEN_VEXT_VV_RM(vnclip_wv_h)
+GEN_VEXT_VV_RM(vnclip_wv_w)
RVVCALL(OPIVX2_RM, vnclip_wx_b, NOP_SSS_B, H1, H2, vnclip8)
RVVCALL(OPIVX2_RM, vnclip_wx_h, NOP_SSS_H, H2, H4, vnclip16)
RVVCALL(OPIVX2_RM, vnclip_wx_w, NOP_SSS_W, H4, H8, vnclip32)
-GEN_VEXT_VX_RM(vnclip_wx_b, 1, 1)
-GEN_VEXT_VX_RM(vnclip_wx_h, 2, 2)
-GEN_VEXT_VX_RM(vnclip_wx_w, 4, 4)
+GEN_VEXT_VX_RM(vnclip_wx_b)
+GEN_VEXT_VX_RM(vnclip_wx_h)
+GEN_VEXT_VX_RM(vnclip_wx_w)
static inline uint8_t
vnclipu8(CPURISCVState *env, int vxrm, uint16_t a, uint8_t b)
@@ -2782,16 +2780,16 @@ vnclipu32(CPURISCVState *env, int vxrm, uint64_t a, uint32_t b)
RVVCALL(OPIVV2_RM, vnclipu_wv_b, NOP_UUU_B, H1, H2, H1, vnclipu8)
RVVCALL(OPIVV2_RM, vnclipu_wv_h, NOP_UUU_H, H2, H4, H2, vnclipu16)
RVVCALL(OPIVV2_RM, vnclipu_wv_w, NOP_UUU_W, H4, H8, H4, vnclipu32)
-GEN_VEXT_VV_RM(vnclipu_wv_b, 1, 1)
-GEN_VEXT_VV_RM(vnclipu_wv_h, 2, 2)
-GEN_VEXT_VV_RM(vnclipu_wv_w, 4, 4)
+GEN_VEXT_VV_RM(vnclipu_wv_b)
+GEN_VEXT_VV_RM(vnclipu_wv_h)
+GEN_VEXT_VV_RM(vnclipu_wv_w)
RVVCALL(OPIVX2_RM, vnclipu_wx_b, NOP_UUU_B, H1, H2, vnclipu8)
RVVCALL(OPIVX2_RM, vnclipu_wx_h, NOP_UUU_H, H2, H4, vnclipu16)
RVVCALL(OPIVX2_RM, vnclipu_wx_w, NOP_UUU_W, H4, H8, vnclipu32)
-GEN_VEXT_VX_RM(vnclipu_wx_b, 1, 1)
-GEN_VEXT_VX_RM(vnclipu_wx_h, 2, 2)
-GEN_VEXT_VX_RM(vnclipu_wx_w, 4, 4)
+GEN_VEXT_VX_RM(vnclipu_wx_b)
+GEN_VEXT_VX_RM(vnclipu_wx_h)
+GEN_VEXT_VX_RM(vnclipu_wx_w)
/*
*** Vector Float Point Arithmetic Instructions
@@ -2806,7 +2804,7 @@ static void do_##NAME(void *vd, void *vs1, void *vs2, int i, \
*((TD *)vd + HD(i)) = OP(s2, s1, &env->fp_status); \
}
-#define GEN_VEXT_VV_ENV(NAME, ESZ, DSZ) \
+#define GEN_VEXT_VV_ENV(NAME) \
void HELPER(NAME)(void *vd, void *v0, void *vs1, \
void *vs2, CPURISCVState *env, \
uint32_t desc) \
@@ -2827,9 +2825,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
RVVCALL(OPFVV2, vfadd_vv_h, OP_UUU_H, H2, H2, H2, float16_add)
RVVCALL(OPFVV2, vfadd_vv_w, OP_UUU_W, H4, H4, H4, float32_add)
RVVCALL(OPFVV2, vfadd_vv_d, OP_UUU_D, H8, H8, H8, float64_add)
-GEN_VEXT_VV_ENV(vfadd_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfadd_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfadd_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfadd_vv_h)
+GEN_VEXT_VV_ENV(vfadd_vv_w)
+GEN_VEXT_VV_ENV(vfadd_vv_d)
#define OPFVF2(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \
static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \
@@ -2839,7 +2837,7 @@ static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \
*((TD *)vd + HD(i)) = OP(s2, (TX1)(T1)s1, &env->fp_status);\
}
-#define GEN_VEXT_VF(NAME, ESZ, DSZ) \
+#define GEN_VEXT_VF(NAME) \
void HELPER(NAME)(void *vd, void *v0, uint64_t s1, \
void *vs2, CPURISCVState *env, \
uint32_t desc) \
@@ -2860,22 +2858,22 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, \
RVVCALL(OPFVF2, vfadd_vf_h, OP_UUU_H, H2, H2, float16_add)
RVVCALL(OPFVF2, vfadd_vf_w, OP_UUU_W, H4, H4, float32_add)
RVVCALL(OPFVF2, vfadd_vf_d, OP_UUU_D, H8, H8, float64_add)
-GEN_VEXT_VF(vfadd_vf_h, 2, 2)
-GEN_VEXT_VF(vfadd_vf_w, 4, 4)
-GEN_VEXT_VF(vfadd_vf_d, 8, 8)
+GEN_VEXT_VF(vfadd_vf_h)
+GEN_VEXT_VF(vfadd_vf_w)
+GEN_VEXT_VF(vfadd_vf_d)
RVVCALL(OPFVV2, vfsub_vv_h, OP_UUU_H, H2, H2, H2, float16_sub)
RVVCALL(OPFVV2, vfsub_vv_w, OP_UUU_W, H4, H4, H4, float32_sub)
RVVCALL(OPFVV2, vfsub_vv_d, OP_UUU_D, H8, H8, H8, float64_sub)
-GEN_VEXT_VV_ENV(vfsub_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfsub_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfsub_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfsub_vv_h)
+GEN_VEXT_VV_ENV(vfsub_vv_w)
+GEN_VEXT_VV_ENV(vfsub_vv_d)
RVVCALL(OPFVF2, vfsub_vf_h, OP_UUU_H, H2, H2, float16_sub)
RVVCALL(OPFVF2, vfsub_vf_w, OP_UUU_W, H4, H4, float32_sub)
RVVCALL(OPFVF2, vfsub_vf_d, OP_UUU_D, H8, H8, float64_sub)
-GEN_VEXT_VF(vfsub_vf_h, 2, 2)
-GEN_VEXT_VF(vfsub_vf_w, 4, 4)
-GEN_VEXT_VF(vfsub_vf_d, 8, 8)
+GEN_VEXT_VF(vfsub_vf_h)
+GEN_VEXT_VF(vfsub_vf_w)
+GEN_VEXT_VF(vfsub_vf_d)
static uint16_t float16_rsub(uint16_t a, uint16_t b, float_status *s)
{
@@ -2895,9 +2893,9 @@ static uint64_t float64_rsub(uint64_t a, uint64_t b, float_status *s)
RVVCALL(OPFVF2, vfrsub_vf_h, OP_UUU_H, H2, H2, float16_rsub)
RVVCALL(OPFVF2, vfrsub_vf_w, OP_UUU_W, H4, H4, float32_rsub)
RVVCALL(OPFVF2, vfrsub_vf_d, OP_UUU_D, H8, H8, float64_rsub)
-GEN_VEXT_VF(vfrsub_vf_h, 2, 2)
-GEN_VEXT_VF(vfrsub_vf_w, 4, 4)
-GEN_VEXT_VF(vfrsub_vf_d, 8, 8)
+GEN_VEXT_VF(vfrsub_vf_h)
+GEN_VEXT_VF(vfrsub_vf_w)
+GEN_VEXT_VF(vfrsub_vf_d)
/* Vector Widening Floating-Point Add/Subtract Instructions */
static uint32_t vfwadd16(uint16_t a, uint16_t b, float_status *s)
@@ -2915,12 +2913,12 @@ static uint64_t vfwadd32(uint32_t a, uint32_t b, float_status *s)
RVVCALL(OPFVV2, vfwadd_vv_h, WOP_UUU_H, H4, H2, H2, vfwadd16)
RVVCALL(OPFVV2, vfwadd_vv_w, WOP_UUU_W, H8, H4, H4, vfwadd32)
-GEN_VEXT_VV_ENV(vfwadd_vv_h, 2, 4)
-GEN_VEXT_VV_ENV(vfwadd_vv_w, 4, 8)
+GEN_VEXT_VV_ENV(vfwadd_vv_h)
+GEN_VEXT_VV_ENV(vfwadd_vv_w)
RVVCALL(OPFVF2, vfwadd_vf_h, WOP_UUU_H, H4, H2, vfwadd16)
RVVCALL(OPFVF2, vfwadd_vf_w, WOP_UUU_W, H8, H4, vfwadd32)
-GEN_VEXT_VF(vfwadd_vf_h, 2, 4)
-GEN_VEXT_VF(vfwadd_vf_w, 4, 8)
+GEN_VEXT_VF(vfwadd_vf_h)
+GEN_VEXT_VF(vfwadd_vf_w)
static uint32_t vfwsub16(uint16_t a, uint16_t b, float_status *s)
{
@@ -2937,12 +2935,12 @@ static uint64_t vfwsub32(uint32_t a, uint32_t b, float_status *s)
RVVCALL(OPFVV2, vfwsub_vv_h, WOP_UUU_H, H4, H2, H2, vfwsub16)
RVVCALL(OPFVV2, vfwsub_vv_w, WOP_UUU_W, H8, H4, H4, vfwsub32)
-GEN_VEXT_VV_ENV(vfwsub_vv_h, 2, 4)
-GEN_VEXT_VV_ENV(vfwsub_vv_w, 4, 8)
+GEN_VEXT_VV_ENV(vfwsub_vv_h)
+GEN_VEXT_VV_ENV(vfwsub_vv_w)
RVVCALL(OPFVF2, vfwsub_vf_h, WOP_UUU_H, H4, H2, vfwsub16)
RVVCALL(OPFVF2, vfwsub_vf_w, WOP_UUU_W, H8, H4, vfwsub32)
-GEN_VEXT_VF(vfwsub_vf_h, 2, 4)
-GEN_VEXT_VF(vfwsub_vf_w, 4, 8)
+GEN_VEXT_VF(vfwsub_vf_h)
+GEN_VEXT_VF(vfwsub_vf_w)
static uint32_t vfwaddw16(uint32_t a, uint16_t b, float_status *s)
{
@@ -2956,12 +2954,12 @@ static uint64_t vfwaddw32(uint64_t a, uint32_t b, float_status *s)
RVVCALL(OPFVV2, vfwadd_wv_h, WOP_WUUU_H, H4, H2, H2, vfwaddw16)
RVVCALL(OPFVV2, vfwadd_wv_w, WOP_WUUU_W, H8, H4, H4, vfwaddw32)
-GEN_VEXT_VV_ENV(vfwadd_wv_h, 2, 4)
-GEN_VEXT_VV_ENV(vfwadd_wv_w, 4, 8)
+GEN_VEXT_VV_ENV(vfwadd_wv_h)
+GEN_VEXT_VV_ENV(vfwadd_wv_w)
RVVCALL(OPFVF2, vfwadd_wf_h, WOP_WUUU_H, H4, H2, vfwaddw16)
RVVCALL(OPFVF2, vfwadd_wf_w, WOP_WUUU_W, H8, H4, vfwaddw32)
-GEN_VEXT_VF(vfwadd_wf_h, 2, 4)
-GEN_VEXT_VF(vfwadd_wf_w, 4, 8)
+GEN_VEXT_VF(vfwadd_wf_h)
+GEN_VEXT_VF(vfwadd_wf_w)
static uint32_t vfwsubw16(uint32_t a, uint16_t b, float_status *s)
{
@@ -2975,39 +2973,39 @@ static uint64_t vfwsubw32(uint64_t a, uint32_t b, float_status *s)
RVVCALL(OPFVV2, vfwsub_wv_h, WOP_WUUU_H, H4, H2, H2, vfwsubw16)
RVVCALL(OPFVV2, vfwsub_wv_w, WOP_WUUU_W, H8, H4, H4, vfwsubw32)
-GEN_VEXT_VV_ENV(vfwsub_wv_h, 2, 4)
-GEN_VEXT_VV_ENV(vfwsub_wv_w, 4, 8)
+GEN_VEXT_VV_ENV(vfwsub_wv_h)
+GEN_VEXT_VV_ENV(vfwsub_wv_w)
RVVCALL(OPFVF2, vfwsub_wf_h, WOP_WUUU_H, H4, H2, vfwsubw16)
RVVCALL(OPFVF2, vfwsub_wf_w, WOP_WUUU_W, H8, H4, vfwsubw32)
-GEN_VEXT_VF(vfwsub_wf_h, 2, 4)
-GEN_VEXT_VF(vfwsub_wf_w, 4, 8)
+GEN_VEXT_VF(vfwsub_wf_h)
+GEN_VEXT_VF(vfwsub_wf_w)
/* Vector Single-Width Floating-Point Multiply/Divide Instructions */
RVVCALL(OPFVV2, vfmul_vv_h, OP_UUU_H, H2, H2, H2, float16_mul)
RVVCALL(OPFVV2, vfmul_vv_w, OP_UUU_W, H4, H4, H4, float32_mul)
RVVCALL(OPFVV2, vfmul_vv_d, OP_UUU_D, H8, H8, H8, float64_mul)
-GEN_VEXT_VV_ENV(vfmul_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfmul_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfmul_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfmul_vv_h)
+GEN_VEXT_VV_ENV(vfmul_vv_w)
+GEN_VEXT_VV_ENV(vfmul_vv_d)
RVVCALL(OPFVF2, vfmul_vf_h, OP_UUU_H, H2, H2, float16_mul)
RVVCALL(OPFVF2, vfmul_vf_w, OP_UUU_W, H4, H4, float32_mul)
RVVCALL(OPFVF2, vfmul_vf_d, OP_UUU_D, H8, H8, float64_mul)
-GEN_VEXT_VF(vfmul_vf_h, 2, 2)
-GEN_VEXT_VF(vfmul_vf_w, 4, 4)
-GEN_VEXT_VF(vfmul_vf_d, 8, 8)
+GEN_VEXT_VF(vfmul_vf_h)
+GEN_VEXT_VF(vfmul_vf_w)
+GEN_VEXT_VF(vfmul_vf_d)
RVVCALL(OPFVV2, vfdiv_vv_h, OP_UUU_H, H2, H2, H2, float16_div)
RVVCALL(OPFVV2, vfdiv_vv_w, OP_UUU_W, H4, H4, H4, float32_div)
RVVCALL(OPFVV2, vfdiv_vv_d, OP_UUU_D, H8, H8, H8, float64_div)
-GEN_VEXT_VV_ENV(vfdiv_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfdiv_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfdiv_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfdiv_vv_h)
+GEN_VEXT_VV_ENV(vfdiv_vv_w)
+GEN_VEXT_VV_ENV(vfdiv_vv_d)
RVVCALL(OPFVF2, vfdiv_vf_h, OP_UUU_H, H2, H2, float16_div)
RVVCALL(OPFVF2, vfdiv_vf_w, OP_UUU_W, H4, H4, float32_div)
RVVCALL(OPFVF2, vfdiv_vf_d, OP_UUU_D, H8, H8, float64_div)
-GEN_VEXT_VF(vfdiv_vf_h, 2, 2)
-GEN_VEXT_VF(vfdiv_vf_w, 4, 4)
-GEN_VEXT_VF(vfdiv_vf_d, 8, 8)
+GEN_VEXT_VF(vfdiv_vf_h)
+GEN_VEXT_VF(vfdiv_vf_w)
+GEN_VEXT_VF(vfdiv_vf_d)
static uint16_t float16_rdiv(uint16_t a, uint16_t b, float_status *s)
{
@@ -3027,9 +3025,9 @@ static uint64_t float64_rdiv(uint64_t a, uint64_t b, float_status *s)
RVVCALL(OPFVF2, vfrdiv_vf_h, OP_UUU_H, H2, H2, float16_rdiv)
RVVCALL(OPFVF2, vfrdiv_vf_w, OP_UUU_W, H4, H4, float32_rdiv)
RVVCALL(OPFVF2, vfrdiv_vf_d, OP_UUU_D, H8, H8, float64_rdiv)
-GEN_VEXT_VF(vfrdiv_vf_h, 2, 2)
-GEN_VEXT_VF(vfrdiv_vf_w, 4, 4)
-GEN_VEXT_VF(vfrdiv_vf_d, 8, 8)
+GEN_VEXT_VF(vfrdiv_vf_h)
+GEN_VEXT_VF(vfrdiv_vf_w)
+GEN_VEXT_VF(vfrdiv_vf_d)
/* Vector Widening Floating-Point Multiply */
static uint32_t vfwmul16(uint16_t a, uint16_t b, float_status *s)
@@ -3046,12 +3044,12 @@ static uint64_t vfwmul32(uint32_t a, uint32_t b, float_status *s)
}
RVVCALL(OPFVV2, vfwmul_vv_h, WOP_UUU_H, H4, H2, H2, vfwmul16)
RVVCALL(OPFVV2, vfwmul_vv_w, WOP_UUU_W, H8, H4, H4, vfwmul32)
-GEN_VEXT_VV_ENV(vfwmul_vv_h, 2, 4)
-GEN_VEXT_VV_ENV(vfwmul_vv_w, 4, 8)
+GEN_VEXT_VV_ENV(vfwmul_vv_h)
+GEN_VEXT_VV_ENV(vfwmul_vv_w)
RVVCALL(OPFVF2, vfwmul_vf_h, WOP_UUU_H, H4, H2, vfwmul16)
RVVCALL(OPFVF2, vfwmul_vf_w, WOP_UUU_W, H8, H4, vfwmul32)
-GEN_VEXT_VF(vfwmul_vf_h, 2, 4)
-GEN_VEXT_VF(vfwmul_vf_w, 4, 8)
+GEN_VEXT_VF(vfwmul_vf_h)
+GEN_VEXT_VF(vfwmul_vf_w)
/* Vector Single-Width Floating-Point Fused Multiply-Add Instructions */
#define OPFVV3(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP) \
@@ -3082,9 +3080,9 @@ static uint64_t fmacc64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfmacc_vv_h, OP_UUU_H, H2, H2, H2, fmacc16)
RVVCALL(OPFVV3, vfmacc_vv_w, OP_UUU_W, H4, H4, H4, fmacc32)
RVVCALL(OPFVV3, vfmacc_vv_d, OP_UUU_D, H8, H8, H8, fmacc64)
-GEN_VEXT_VV_ENV(vfmacc_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfmacc_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfmacc_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfmacc_vv_h)
+GEN_VEXT_VV_ENV(vfmacc_vv_w)
+GEN_VEXT_VV_ENV(vfmacc_vv_d)
#define OPFVF3(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \
static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \
@@ -3098,9 +3096,9 @@ static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \
RVVCALL(OPFVF3, vfmacc_vf_h, OP_UUU_H, H2, H2, fmacc16)
RVVCALL(OPFVF3, vfmacc_vf_w, OP_UUU_W, H4, H4, fmacc32)
RVVCALL(OPFVF3, vfmacc_vf_d, OP_UUU_D, H8, H8, fmacc64)
-GEN_VEXT_VF(vfmacc_vf_h, 2, 2)
-GEN_VEXT_VF(vfmacc_vf_w, 4, 4)
-GEN_VEXT_VF(vfmacc_vf_d, 8, 8)
+GEN_VEXT_VF(vfmacc_vf_h)
+GEN_VEXT_VF(vfmacc_vf_w)
+GEN_VEXT_VF(vfmacc_vf_d)
static uint16_t fnmacc16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3123,15 +3121,15 @@ static uint64_t fnmacc64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfnmacc_vv_h, OP_UUU_H, H2, H2, H2, fnmacc16)
RVVCALL(OPFVV3, vfnmacc_vv_w, OP_UUU_W, H4, H4, H4, fnmacc32)
RVVCALL(OPFVV3, vfnmacc_vv_d, OP_UUU_D, H8, H8, H8, fnmacc64)
-GEN_VEXT_VV_ENV(vfnmacc_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfnmacc_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfnmacc_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfnmacc_vv_h)
+GEN_VEXT_VV_ENV(vfnmacc_vv_w)
+GEN_VEXT_VV_ENV(vfnmacc_vv_d)
RVVCALL(OPFVF3, vfnmacc_vf_h, OP_UUU_H, H2, H2, fnmacc16)
RVVCALL(OPFVF3, vfnmacc_vf_w, OP_UUU_W, H4, H4, fnmacc32)
RVVCALL(OPFVF3, vfnmacc_vf_d, OP_UUU_D, H8, H8, fnmacc64)
-GEN_VEXT_VF(vfnmacc_vf_h, 2, 2)
-GEN_VEXT_VF(vfnmacc_vf_w, 4, 4)
-GEN_VEXT_VF(vfnmacc_vf_d, 8, 8)
+GEN_VEXT_VF(vfnmacc_vf_h)
+GEN_VEXT_VF(vfnmacc_vf_w)
+GEN_VEXT_VF(vfnmacc_vf_d)
static uint16_t fmsac16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3151,15 +3149,15 @@ static uint64_t fmsac64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfmsac_vv_h, OP_UUU_H, H2, H2, H2, fmsac16)
RVVCALL(OPFVV3, vfmsac_vv_w, OP_UUU_W, H4, H4, H4, fmsac32)
RVVCALL(OPFVV3, vfmsac_vv_d, OP_UUU_D, H8, H8, H8, fmsac64)
-GEN_VEXT_VV_ENV(vfmsac_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfmsac_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfmsac_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfmsac_vv_h)
+GEN_VEXT_VV_ENV(vfmsac_vv_w)
+GEN_VEXT_VV_ENV(vfmsac_vv_d)
RVVCALL(OPFVF3, vfmsac_vf_h, OP_UUU_H, H2, H2, fmsac16)
RVVCALL(OPFVF3, vfmsac_vf_w, OP_UUU_W, H4, H4, fmsac32)
RVVCALL(OPFVF3, vfmsac_vf_d, OP_UUU_D, H8, H8, fmsac64)
-GEN_VEXT_VF(vfmsac_vf_h, 2, 2)
-GEN_VEXT_VF(vfmsac_vf_w, 4, 4)
-GEN_VEXT_VF(vfmsac_vf_d, 8, 8)
+GEN_VEXT_VF(vfmsac_vf_h)
+GEN_VEXT_VF(vfmsac_vf_w)
+GEN_VEXT_VF(vfmsac_vf_d)
static uint16_t fnmsac16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3179,15 +3177,15 @@ static uint64_t fnmsac64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfnmsac_vv_h, OP_UUU_H, H2, H2, H2, fnmsac16)
RVVCALL(OPFVV3, vfnmsac_vv_w, OP_UUU_W, H4, H4, H4, fnmsac32)
RVVCALL(OPFVV3, vfnmsac_vv_d, OP_UUU_D, H8, H8, H8, fnmsac64)
-GEN_VEXT_VV_ENV(vfnmsac_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfnmsac_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfnmsac_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfnmsac_vv_h)
+GEN_VEXT_VV_ENV(vfnmsac_vv_w)
+GEN_VEXT_VV_ENV(vfnmsac_vv_d)
RVVCALL(OPFVF3, vfnmsac_vf_h, OP_UUU_H, H2, H2, fnmsac16)
RVVCALL(OPFVF3, vfnmsac_vf_w, OP_UUU_W, H4, H4, fnmsac32)
RVVCALL(OPFVF3, vfnmsac_vf_d, OP_UUU_D, H8, H8, fnmsac64)
-GEN_VEXT_VF(vfnmsac_vf_h, 2, 2)
-GEN_VEXT_VF(vfnmsac_vf_w, 4, 4)
-GEN_VEXT_VF(vfnmsac_vf_d, 8, 8)
+GEN_VEXT_VF(vfnmsac_vf_h)
+GEN_VEXT_VF(vfnmsac_vf_w)
+GEN_VEXT_VF(vfnmsac_vf_d)
static uint16_t fmadd16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3207,15 +3205,15 @@ static uint64_t fmadd64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfmadd_vv_h, OP_UUU_H, H2, H2, H2, fmadd16)
RVVCALL(OPFVV3, vfmadd_vv_w, OP_UUU_W, H4, H4, H4, fmadd32)
RVVCALL(OPFVV3, vfmadd_vv_d, OP_UUU_D, H8, H8, H8, fmadd64)
-GEN_VEXT_VV_ENV(vfmadd_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfmadd_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfmadd_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfmadd_vv_h)
+GEN_VEXT_VV_ENV(vfmadd_vv_w)
+GEN_VEXT_VV_ENV(vfmadd_vv_d)
RVVCALL(OPFVF3, vfmadd_vf_h, OP_UUU_H, H2, H2, fmadd16)
RVVCALL(OPFVF3, vfmadd_vf_w, OP_UUU_W, H4, H4, fmadd32)
RVVCALL(OPFVF3, vfmadd_vf_d, OP_UUU_D, H8, H8, fmadd64)
-GEN_VEXT_VF(vfmadd_vf_h, 2, 2)
-GEN_VEXT_VF(vfmadd_vf_w, 4, 4)
-GEN_VEXT_VF(vfmadd_vf_d, 8, 8)
+GEN_VEXT_VF(vfmadd_vf_h)
+GEN_VEXT_VF(vfmadd_vf_w)
+GEN_VEXT_VF(vfmadd_vf_d)
static uint16_t fnmadd16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3238,15 +3236,15 @@ static uint64_t fnmadd64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfnmadd_vv_h, OP_UUU_H, H2, H2, H2, fnmadd16)
RVVCALL(OPFVV3, vfnmadd_vv_w, OP_UUU_W, H4, H4, H4, fnmadd32)
RVVCALL(OPFVV3, vfnmadd_vv_d, OP_UUU_D, H8, H8, H8, fnmadd64)
-GEN_VEXT_VV_ENV(vfnmadd_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfnmadd_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfnmadd_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfnmadd_vv_h)
+GEN_VEXT_VV_ENV(vfnmadd_vv_w)
+GEN_VEXT_VV_ENV(vfnmadd_vv_d)
RVVCALL(OPFVF3, vfnmadd_vf_h, OP_UUU_H, H2, H2, fnmadd16)
RVVCALL(OPFVF3, vfnmadd_vf_w, OP_UUU_W, H4, H4, fnmadd32)
RVVCALL(OPFVF3, vfnmadd_vf_d, OP_UUU_D, H8, H8, fnmadd64)
-GEN_VEXT_VF(vfnmadd_vf_h, 2, 2)
-GEN_VEXT_VF(vfnmadd_vf_w, 4, 4)
-GEN_VEXT_VF(vfnmadd_vf_d, 8, 8)
+GEN_VEXT_VF(vfnmadd_vf_h)
+GEN_VEXT_VF(vfnmadd_vf_w)
+GEN_VEXT_VF(vfnmadd_vf_d)
static uint16_t fmsub16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3266,15 +3264,15 @@ static uint64_t fmsub64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfmsub_vv_h, OP_UUU_H, H2, H2, H2, fmsub16)
RVVCALL(OPFVV3, vfmsub_vv_w, OP_UUU_W, H4, H4, H4, fmsub32)
RVVCALL(OPFVV3, vfmsub_vv_d, OP_UUU_D, H8, H8, H8, fmsub64)
-GEN_VEXT_VV_ENV(vfmsub_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfmsub_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfmsub_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfmsub_vv_h)
+GEN_VEXT_VV_ENV(vfmsub_vv_w)
+GEN_VEXT_VV_ENV(vfmsub_vv_d)
RVVCALL(OPFVF3, vfmsub_vf_h, OP_UUU_H, H2, H2, fmsub16)
RVVCALL(OPFVF3, vfmsub_vf_w, OP_UUU_W, H4, H4, fmsub32)
RVVCALL(OPFVF3, vfmsub_vf_d, OP_UUU_D, H8, H8, fmsub64)
-GEN_VEXT_VF(vfmsub_vf_h, 2, 2)
-GEN_VEXT_VF(vfmsub_vf_w, 4, 4)
-GEN_VEXT_VF(vfmsub_vf_d, 8, 8)
+GEN_VEXT_VF(vfmsub_vf_h)
+GEN_VEXT_VF(vfmsub_vf_w)
+GEN_VEXT_VF(vfmsub_vf_d)
static uint16_t fnmsub16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3294,15 +3292,15 @@ static uint64_t fnmsub64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfnmsub_vv_h, OP_UUU_H, H2, H2, H2, fnmsub16)
RVVCALL(OPFVV3, vfnmsub_vv_w, OP_UUU_W, H4, H4, H4, fnmsub32)
RVVCALL(OPFVV3, vfnmsub_vv_d, OP_UUU_D, H8, H8, H8, fnmsub64)
-GEN_VEXT_VV_ENV(vfnmsub_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfnmsub_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfnmsub_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfnmsub_vv_h)
+GEN_VEXT_VV_ENV(vfnmsub_vv_w)
+GEN_VEXT_VV_ENV(vfnmsub_vv_d)
RVVCALL(OPFVF3, vfnmsub_vf_h, OP_UUU_H, H2, H2, fnmsub16)
RVVCALL(OPFVF3, vfnmsub_vf_w, OP_UUU_W, H4, H4, fnmsub32)
RVVCALL(OPFVF3, vfnmsub_vf_d, OP_UUU_D, H8, H8, fnmsub64)
-GEN_VEXT_VF(vfnmsub_vf_h, 2, 2)
-GEN_VEXT_VF(vfnmsub_vf_w, 4, 4)
-GEN_VEXT_VF(vfnmsub_vf_d, 8, 8)
+GEN_VEXT_VF(vfnmsub_vf_h)
+GEN_VEXT_VF(vfnmsub_vf_w)
+GEN_VEXT_VF(vfnmsub_vf_d)
/* Vector Widening Floating-Point Fused Multiply-Add Instructions */
static uint32_t fwmacc16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
@@ -3319,12 +3317,12 @@ static uint64_t fwmacc32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfwmacc_vv_h, WOP_UUU_H, H4, H2, H2, fwmacc16)
RVVCALL(OPFVV3, vfwmacc_vv_w, WOP_UUU_W, H8, H4, H4, fwmacc32)
-GEN_VEXT_VV_ENV(vfwmacc_vv_h, 2, 4)
-GEN_VEXT_VV_ENV(vfwmacc_vv_w, 4, 8)
+GEN_VEXT_VV_ENV(vfwmacc_vv_h)
+GEN_VEXT_VV_ENV(vfwmacc_vv_w)
RVVCALL(OPFVF3, vfwmacc_vf_h, WOP_UUU_H, H4, H2, fwmacc16)
RVVCALL(OPFVF3, vfwmacc_vf_w, WOP_UUU_W, H8, H4, fwmacc32)
-GEN_VEXT_VF(vfwmacc_vf_h, 2, 4)
-GEN_VEXT_VF(vfwmacc_vf_w, 4, 8)
+GEN_VEXT_VF(vfwmacc_vf_h)
+GEN_VEXT_VF(vfwmacc_vf_w)
static uint32_t fwnmacc16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
{
@@ -3342,12 +3340,12 @@ static uint64_t fwnmacc32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfwnmacc_vv_h, WOP_UUU_H, H4, H2, H2, fwnmacc16)
RVVCALL(OPFVV3, vfwnmacc_vv_w, WOP_UUU_W, H8, H4, H4, fwnmacc32)
-GEN_VEXT_VV_ENV(vfwnmacc_vv_h, 2, 4)
-GEN_VEXT_VV_ENV(vfwnmacc_vv_w, 4, 8)
+GEN_VEXT_VV_ENV(vfwnmacc_vv_h)
+GEN_VEXT_VV_ENV(vfwnmacc_vv_w)
RVVCALL(OPFVF3, vfwnmacc_vf_h, WOP_UUU_H, H4, H2, fwnmacc16)
RVVCALL(OPFVF3, vfwnmacc_vf_w, WOP_UUU_W, H8, H4, fwnmacc32)
-GEN_VEXT_VF(vfwnmacc_vf_h, 2, 4)
-GEN_VEXT_VF(vfwnmacc_vf_w, 4, 8)
+GEN_VEXT_VF(vfwnmacc_vf_h)
+GEN_VEXT_VF(vfwnmacc_vf_w)
static uint32_t fwmsac16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
{
@@ -3365,12 +3363,12 @@ static uint64_t fwmsac32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfwmsac_vv_h, WOP_UUU_H, H4, H2, H2, fwmsac16)
RVVCALL(OPFVV3, vfwmsac_vv_w, WOP_UUU_W, H8, H4, H4, fwmsac32)
-GEN_VEXT_VV_ENV(vfwmsac_vv_h, 2, 4)
-GEN_VEXT_VV_ENV(vfwmsac_vv_w, 4, 8)
+GEN_VEXT_VV_ENV(vfwmsac_vv_h)
+GEN_VEXT_VV_ENV(vfwmsac_vv_w)
RVVCALL(OPFVF3, vfwmsac_vf_h, WOP_UUU_H, H4, H2, fwmsac16)
RVVCALL(OPFVF3, vfwmsac_vf_w, WOP_UUU_W, H8, H4, fwmsac32)
-GEN_VEXT_VF(vfwmsac_vf_h, 2, 4)
-GEN_VEXT_VF(vfwmsac_vf_w, 4, 8)
+GEN_VEXT_VF(vfwmsac_vf_h)
+GEN_VEXT_VF(vfwmsac_vf_w)
static uint32_t fwnmsac16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
{
@@ -3388,12 +3386,12 @@ static uint64_t fwnmsac32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfwnmsac_vv_h, WOP_UUU_H, H4, H2, H2, fwnmsac16)
RVVCALL(OPFVV3, vfwnmsac_vv_w, WOP_UUU_W, H8, H4, H4, fwnmsac32)
-GEN_VEXT_VV_ENV(vfwnmsac_vv_h, 2, 4)
-GEN_VEXT_VV_ENV(vfwnmsac_vv_w, 4, 8)
+GEN_VEXT_VV_ENV(vfwnmsac_vv_h)
+GEN_VEXT_VV_ENV(vfwnmsac_vv_w)
RVVCALL(OPFVF3, vfwnmsac_vf_h, WOP_UUU_H, H4, H2, fwnmsac16)
RVVCALL(OPFVF3, vfwnmsac_vf_w, WOP_UUU_W, H8, H4, fwnmsac32)
-GEN_VEXT_VF(vfwnmsac_vf_h, 2, 4)
-GEN_VEXT_VF(vfwnmsac_vf_w, 4, 8)
+GEN_VEXT_VF(vfwnmsac_vf_h)
+GEN_VEXT_VF(vfwnmsac_vf_w)
/* Vector Floating-Point Square-Root Instruction */
/* (TD, T2, TX2) */
@@ -3409,7 +3407,7 @@ static void do_##NAME(void *vd, void *vs2, int i, \
*((TD *)vd + HD(i)) = OP(s2, &env->fp_status); \
}
-#define GEN_VEXT_V_ENV(NAME, ESZ, DSZ) \
+#define GEN_VEXT_V_ENV(NAME) \
void HELPER(NAME)(void *vd, void *v0, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
@@ -3432,9 +3430,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \
RVVCALL(OPFVV1, vfsqrt_v_h, OP_UU_H, H2, H2, float16_sqrt)
RVVCALL(OPFVV1, vfsqrt_v_w, OP_UU_W, H4, H4, float32_sqrt)
RVVCALL(OPFVV1, vfsqrt_v_d, OP_UU_D, H8, H8, float64_sqrt)
-GEN_VEXT_V_ENV(vfsqrt_v_h, 2, 2)
-GEN_VEXT_V_ENV(vfsqrt_v_w, 4, 4)
-GEN_VEXT_V_ENV(vfsqrt_v_d, 8, 8)
+GEN_VEXT_V_ENV(vfsqrt_v_h)
+GEN_VEXT_V_ENV(vfsqrt_v_w)
+GEN_VEXT_V_ENV(vfsqrt_v_d)
/*
* Vector Floating-Point Reciprocal Square-Root Estimate Instruction
@@ -3614,9 +3612,9 @@ static float64 frsqrt7_d(float64 f, float_status *s)
RVVCALL(OPFVV1, vfrsqrt7_v_h, OP_UU_H, H2, H2, frsqrt7_h)
RVVCALL(OPFVV1, vfrsqrt7_v_w, OP_UU_W, H4, H4, frsqrt7_s)
RVVCALL(OPFVV1, vfrsqrt7_v_d, OP_UU_D, H8, H8, frsqrt7_d)
-GEN_VEXT_V_ENV(vfrsqrt7_v_h, 2, 2)
-GEN_VEXT_V_ENV(vfrsqrt7_v_w, 4, 4)
-GEN_VEXT_V_ENV(vfrsqrt7_v_d, 8, 8)
+GEN_VEXT_V_ENV(vfrsqrt7_v_h)
+GEN_VEXT_V_ENV(vfrsqrt7_v_w)
+GEN_VEXT_V_ENV(vfrsqrt7_v_d)
/*
* Vector Floating-Point Reciprocal Estimate Instruction
@@ -3805,36 +3803,36 @@ static float64 frec7_d(float64 f, float_status *s)
RVVCALL(OPFVV1, vfrec7_v_h, OP_UU_H, H2, H2, frec7_h)
RVVCALL(OPFVV1, vfrec7_v_w, OP_UU_W, H4, H4, frec7_s)
RVVCALL(OPFVV1, vfrec7_v_d, OP_UU_D, H8, H8, frec7_d)
-GEN_VEXT_V_ENV(vfrec7_v_h, 2, 2)
-GEN_VEXT_V_ENV(vfrec7_v_w, 4, 4)
-GEN_VEXT_V_ENV(vfrec7_v_d, 8, 8)
+GEN_VEXT_V_ENV(vfrec7_v_h)
+GEN_VEXT_V_ENV(vfrec7_v_w)
+GEN_VEXT_V_ENV(vfrec7_v_d)
/* Vector Floating-Point MIN/MAX Instructions */
RVVCALL(OPFVV2, vfmin_vv_h, OP_UUU_H, H2, H2, H2, float16_minimum_number)
RVVCALL(OPFVV2, vfmin_vv_w, OP_UUU_W, H4, H4, H4, float32_minimum_number)
RVVCALL(OPFVV2, vfmin_vv_d, OP_UUU_D, H8, H8, H8, float64_minimum_number)
-GEN_VEXT_VV_ENV(vfmin_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfmin_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfmin_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfmin_vv_h)
+GEN_VEXT_VV_ENV(vfmin_vv_w)
+GEN_VEXT_VV_ENV(vfmin_vv_d)
RVVCALL(OPFVF2, vfmin_vf_h, OP_UUU_H, H2, H2, float16_minimum_number)
RVVCALL(OPFVF2, vfmin_vf_w, OP_UUU_W, H4, H4, float32_minimum_number)
RVVCALL(OPFVF2, vfmin_vf_d, OP_UUU_D, H8, H8, float64_minimum_number)
-GEN_VEXT_VF(vfmin_vf_h, 2, 2)
-GEN_VEXT_VF(vfmin_vf_w, 4, 4)
-GEN_VEXT_VF(vfmin_vf_d, 8, 8)
+GEN_VEXT_VF(vfmin_vf_h)
+GEN_VEXT_VF(vfmin_vf_w)
+GEN_VEXT_VF(vfmin_vf_d)
RVVCALL(OPFVV2, vfmax_vv_h, OP_UUU_H, H2, H2, H2, float16_maximum_number)
RVVCALL(OPFVV2, vfmax_vv_w, OP_UUU_W, H4, H4, H4, float32_maximum_number)
RVVCALL(OPFVV2, vfmax_vv_d, OP_UUU_D, H8, H8, H8, float64_maximum_number)
-GEN_VEXT_VV_ENV(vfmax_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfmax_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfmax_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfmax_vv_h)
+GEN_VEXT_VV_ENV(vfmax_vv_w)
+GEN_VEXT_VV_ENV(vfmax_vv_d)
RVVCALL(OPFVF2, vfmax_vf_h, OP_UUU_H, H2, H2, float16_maximum_number)
RVVCALL(OPFVF2, vfmax_vf_w, OP_UUU_W, H4, H4, float32_maximum_number)
RVVCALL(OPFVF2, vfmax_vf_d, OP_UUU_D, H8, H8, float64_maximum_number)
-GEN_VEXT_VF(vfmax_vf_h, 2, 2)
-GEN_VEXT_VF(vfmax_vf_w, 4, 4)
-GEN_VEXT_VF(vfmax_vf_d, 8, 8)
+GEN_VEXT_VF(vfmax_vf_h)
+GEN_VEXT_VF(vfmax_vf_w)
+GEN_VEXT_VF(vfmax_vf_d)
/* Vector Floating-Point Sign-Injection Instructions */
static uint16_t fsgnj16(uint16_t a, uint16_t b, float_status *s)
@@ -3855,15 +3853,15 @@ static uint64_t fsgnj64(uint64_t a, uint64_t b, float_status *s)
RVVCALL(OPFVV2, vfsgnj_vv_h, OP_UUU_H, H2, H2, H2, fsgnj16)
RVVCALL(OPFVV2, vfsgnj_vv_w, OP_UUU_W, H4, H4, H4, fsgnj32)
RVVCALL(OPFVV2, vfsgnj_vv_d, OP_UUU_D, H8, H8, H8, fsgnj64)
-GEN_VEXT_VV_ENV(vfsgnj_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfsgnj_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfsgnj_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfsgnj_vv_h)
+GEN_VEXT_VV_ENV(vfsgnj_vv_w)
+GEN_VEXT_VV_ENV(vfsgnj_vv_d)
RVVCALL(OPFVF2, vfsgnj_vf_h, OP_UUU_H, H2, H2, fsgnj16)
RVVCALL(OPFVF2, vfsgnj_vf_w, OP_UUU_W, H4, H4, fsgnj32)
RVVCALL(OPFVF2, vfsgnj_vf_d, OP_UUU_D, H8, H8, fsgnj64)
-GEN_VEXT_VF(vfsgnj_vf_h, 2, 2)
-GEN_VEXT_VF(vfsgnj_vf_w, 4, 4)
-GEN_VEXT_VF(vfsgnj_vf_d, 8, 8)
+GEN_VEXT_VF(vfsgnj_vf_h)
+GEN_VEXT_VF(vfsgnj_vf_w)
+GEN_VEXT_VF(vfsgnj_vf_d)
static uint16_t fsgnjn16(uint16_t a, uint16_t b, float_status *s)
{
@@ -3883,15 +3881,15 @@ static uint64_t fsgnjn64(uint64_t a, uint64_t b, float_status *s)
RVVCALL(OPFVV2, vfsgnjn_vv_h, OP_UUU_H, H2, H2, H2, fsgnjn16)
RVVCALL(OPFVV2, vfsgnjn_vv_w, OP_UUU_W, H4, H4, H4, fsgnjn32)
RVVCALL(OPFVV2, vfsgnjn_vv_d, OP_UUU_D, H8, H8, H8, fsgnjn64)
-GEN_VEXT_VV_ENV(vfsgnjn_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfsgnjn_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfsgnjn_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfsgnjn_vv_h)
+GEN_VEXT_VV_ENV(vfsgnjn_vv_w)
+GEN_VEXT_VV_ENV(vfsgnjn_vv_d)
RVVCALL(OPFVF2, vfsgnjn_vf_h, OP_UUU_H, H2, H2, fsgnjn16)
RVVCALL(OPFVF2, vfsgnjn_vf_w, OP_UUU_W, H4, H4, fsgnjn32)
RVVCALL(OPFVF2, vfsgnjn_vf_d, OP_UUU_D, H8, H8, fsgnjn64)
-GEN_VEXT_VF(vfsgnjn_vf_h, 2, 2)
-GEN_VEXT_VF(vfsgnjn_vf_w, 4, 4)
-GEN_VEXT_VF(vfsgnjn_vf_d, 8, 8)
+GEN_VEXT_VF(vfsgnjn_vf_h)
+GEN_VEXT_VF(vfsgnjn_vf_w)
+GEN_VEXT_VF(vfsgnjn_vf_d)
static uint16_t fsgnjx16(uint16_t a, uint16_t b, float_status *s)
{
@@ -3911,15 +3909,15 @@ static uint64_t fsgnjx64(uint64_t a, uint64_t b, float_status *s)
RVVCALL(OPFVV2, vfsgnjx_vv_h, OP_UUU_H, H2, H2, H2, fsgnjx16)
RVVCALL(OPFVV2, vfsgnjx_vv_w, OP_UUU_W, H4, H4, H4, fsgnjx32)
RVVCALL(OPFVV2, vfsgnjx_vv_d, OP_UUU_D, H8, H8, H8, fsgnjx64)
-GEN_VEXT_VV_ENV(vfsgnjx_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfsgnjx_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfsgnjx_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfsgnjx_vv_h)
+GEN_VEXT_VV_ENV(vfsgnjx_vv_w)
+GEN_VEXT_VV_ENV(vfsgnjx_vv_d)
RVVCALL(OPFVF2, vfsgnjx_vf_h, OP_UUU_H, H2, H2, fsgnjx16)
RVVCALL(OPFVF2, vfsgnjx_vf_w, OP_UUU_W, H4, H4, fsgnjx32)
RVVCALL(OPFVF2, vfsgnjx_vf_d, OP_UUU_D, H8, H8, fsgnjx64)
-GEN_VEXT_VF(vfsgnjx_vf_h, 2, 2)
-GEN_VEXT_VF(vfsgnjx_vf_w, 4, 4)
-GEN_VEXT_VF(vfsgnjx_vf_d, 8, 8)
+GEN_VEXT_VF(vfsgnjx_vf_h)
+GEN_VEXT_VF(vfsgnjx_vf_w)
+GEN_VEXT_VF(vfsgnjx_vf_d)
/* Vector Floating-Point Compare Instructions */
#define GEN_VEXT_CMP_VV_ENV(NAME, ETYPE, H, DO_OP) \
@@ -4063,7 +4061,7 @@ static void do_##NAME(void *vd, void *vs2, int i) \
*((TD *)vd + HD(i)) = OP(s2); \
}
-#define GEN_VEXT_V(NAME, ESZ, DSZ) \
+#define GEN_VEXT_V(NAME) \
void HELPER(NAME)(void *vd, void *v0, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
@@ -4140,9 +4138,9 @@ target_ulong fclass_d(uint64_t frs1)
RVVCALL(OPIVV1, vfclass_v_h, OP_UU_H, H2, H2, fclass_h)
RVVCALL(OPIVV1, vfclass_v_w, OP_UU_W, H4, H4, fclass_s)
RVVCALL(OPIVV1, vfclass_v_d, OP_UU_D, H8, H8, fclass_d)
-GEN_VEXT_V(vfclass_v_h, 2, 2)
-GEN_VEXT_V(vfclass_v_w, 4, 4)
-GEN_VEXT_V(vfclass_v_d, 8, 8)
+GEN_VEXT_V(vfclass_v_h)
+GEN_VEXT_V(vfclass_v_w)
+GEN_VEXT_V(vfclass_v_d)
/* Vector Floating-Point Merge Instruction */
#define GEN_VFMERGE_VF(NAME, ETYPE, H) \
@@ -4170,33 +4168,33 @@ GEN_VFMERGE_VF(vfmerge_vfm_d, int64_t, H8)
RVVCALL(OPFVV1, vfcvt_xu_f_v_h, OP_UU_H, H2, H2, float16_to_uint16)
RVVCALL(OPFVV1, vfcvt_xu_f_v_w, OP_UU_W, H4, H4, float32_to_uint32)
RVVCALL(OPFVV1, vfcvt_xu_f_v_d, OP_UU_D, H8, H8, float64_to_uint64)
-GEN_VEXT_V_ENV(vfcvt_xu_f_v_h, 2, 2)
-GEN_VEXT_V_ENV(vfcvt_xu_f_v_w, 4, 4)
-GEN_VEXT_V_ENV(vfcvt_xu_f_v_d, 8, 8)
+GEN_VEXT_V_ENV(vfcvt_xu_f_v_h)
+GEN_VEXT_V_ENV(vfcvt_xu_f_v_w)
+GEN_VEXT_V_ENV(vfcvt_xu_f_v_d)
/* vfcvt.x.f.v vd, vs2, vm # Convert float to signed integer. */
RVVCALL(OPFVV1, vfcvt_x_f_v_h, OP_UU_H, H2, H2, float16_to_int16)
RVVCALL(OPFVV1, vfcvt_x_f_v_w, OP_UU_W, H4, H4, float32_to_int32)
RVVCALL(OPFVV1, vfcvt_x_f_v_d, OP_UU_D, H8, H8, float64_to_int64)
-GEN_VEXT_V_ENV(vfcvt_x_f_v_h, 2, 2)
-GEN_VEXT_V_ENV(vfcvt_x_f_v_w, 4, 4)
-GEN_VEXT_V_ENV(vfcvt_x_f_v_d, 8, 8)
+GEN_VEXT_V_ENV(vfcvt_x_f_v_h)
+GEN_VEXT_V_ENV(vfcvt_x_f_v_w)
+GEN_VEXT_V_ENV(vfcvt_x_f_v_d)
/* vfcvt.f.xu.v vd, vs2, vm # Convert unsigned integer to float. */
RVVCALL(OPFVV1, vfcvt_f_xu_v_h, OP_UU_H, H2, H2, uint16_to_float16)
RVVCALL(OPFVV1, vfcvt_f_xu_v_w, OP_UU_W, H4, H4, uint32_to_float32)
RVVCALL(OPFVV1, vfcvt_f_xu_v_d, OP_UU_D, H8, H8, uint64_to_float64)
-GEN_VEXT_V_ENV(vfcvt_f_xu_v_h, 2, 2)
-GEN_VEXT_V_ENV(vfcvt_f_xu_v_w, 4, 4)
-GEN_VEXT_V_ENV(vfcvt_f_xu_v_d, 8, 8)
+GEN_VEXT_V_ENV(vfcvt_f_xu_v_h)
+GEN_VEXT_V_ENV(vfcvt_f_xu_v_w)
+GEN_VEXT_V_ENV(vfcvt_f_xu_v_d)
/* vfcvt.f.x.v vd, vs2, vm # Convert integer to float. */
RVVCALL(OPFVV1, vfcvt_f_x_v_h, OP_UU_H, H2, H2, int16_to_float16)
RVVCALL(OPFVV1, vfcvt_f_x_v_w, OP_UU_W, H4, H4, int32_to_float32)
RVVCALL(OPFVV1, vfcvt_f_x_v_d, OP_UU_D, H8, H8, int64_to_float64)
-GEN_VEXT_V_ENV(vfcvt_f_x_v_h, 2, 2)
-GEN_VEXT_V_ENV(vfcvt_f_x_v_w, 4, 4)
-GEN_VEXT_V_ENV(vfcvt_f_x_v_d, 8, 8)
+GEN_VEXT_V_ENV(vfcvt_f_x_v_h)
+GEN_VEXT_V_ENV(vfcvt_f_x_v_w)
+GEN_VEXT_V_ENV(vfcvt_f_x_v_d)
/* Widening Floating-Point/Integer Type-Convert Instructions */
/* (TD, T2, TX2) */
@@ -4206,30 +4204,30 @@ GEN_VEXT_V_ENV(vfcvt_f_x_v_d, 8, 8)
/* vfwcvt.xu.f.v vd, vs2, vm # Convert float to double-width unsigned integer.*/
RVVCALL(OPFVV1, vfwcvt_xu_f_v_h, WOP_UU_H, H4, H2, float16_to_uint32)
RVVCALL(OPFVV1, vfwcvt_xu_f_v_w, WOP_UU_W, H8, H4, float32_to_uint64)
-GEN_VEXT_V_ENV(vfwcvt_xu_f_v_h, 2, 4)
-GEN_VEXT_V_ENV(vfwcvt_xu_f_v_w, 4, 8)
+GEN_VEXT_V_ENV(vfwcvt_xu_f_v_h)
+GEN_VEXT_V_ENV(vfwcvt_xu_f_v_w)
/* vfwcvt.x.f.v vd, vs2, vm # Convert float to double-width signed integer. */
RVVCALL(OPFVV1, vfwcvt_x_f_v_h, WOP_UU_H, H4, H2, float16_to_int32)
RVVCALL(OPFVV1, vfwcvt_x_f_v_w, WOP_UU_W, H8, H4, float32_to_int64)
-GEN_VEXT_V_ENV(vfwcvt_x_f_v_h, 2, 4)
-GEN_VEXT_V_ENV(vfwcvt_x_f_v_w, 4, 8)
+GEN_VEXT_V_ENV(vfwcvt_x_f_v_h)
+GEN_VEXT_V_ENV(vfwcvt_x_f_v_w)
/* vfwcvt.f.xu.v vd, vs2, vm # Convert unsigned integer to double-width float */
RVVCALL(OPFVV1, vfwcvt_f_xu_v_b, WOP_UU_B, H2, H1, uint8_to_float16)
RVVCALL(OPFVV1, vfwcvt_f_xu_v_h, WOP_UU_H, H4, H2, uint16_to_float32)
RVVCALL(OPFVV1, vfwcvt_f_xu_v_w, WOP_UU_W, H8, H4, uint32_to_float64)
-GEN_VEXT_V_ENV(vfwcvt_f_xu_v_b, 1, 2)
-GEN_VEXT_V_ENV(vfwcvt_f_xu_v_h, 2, 4)
-GEN_VEXT_V_ENV(vfwcvt_f_xu_v_w, 4, 8)
+GEN_VEXT_V_ENV(vfwcvt_f_xu_v_b)
+GEN_VEXT_V_ENV(vfwcvt_f_xu_v_h)
+GEN_VEXT_V_ENV(vfwcvt_f_xu_v_w)
/* vfwcvt.f.x.v vd, vs2, vm # Convert integer to double-width float. */
RVVCALL(OPFVV1, vfwcvt_f_x_v_b, WOP_UU_B, H2, H1, int8_to_float16)
RVVCALL(OPFVV1, vfwcvt_f_x_v_h, WOP_UU_H, H4, H2, int16_to_float32)
RVVCALL(OPFVV1, vfwcvt_f_x_v_w, WOP_UU_W, H8, H4, int32_to_float64)
-GEN_VEXT_V_ENV(vfwcvt_f_x_v_b, 1, 2)
-GEN_VEXT_V_ENV(vfwcvt_f_x_v_h, 2, 4)
-GEN_VEXT_V_ENV(vfwcvt_f_x_v_w, 4, 8)
+GEN_VEXT_V_ENV(vfwcvt_f_x_v_b)
+GEN_VEXT_V_ENV(vfwcvt_f_x_v_h)
+GEN_VEXT_V_ENV(vfwcvt_f_x_v_w)
/*
* vfwcvt.f.f.v vd, vs2, vm
@@ -4242,8 +4240,8 @@ static uint32_t vfwcvtffv16(uint16_t a, float_status *s)
RVVCALL(OPFVV1, vfwcvt_f_f_v_h, WOP_UU_H, H4, H2, vfwcvtffv16)
RVVCALL(OPFVV1, vfwcvt_f_f_v_w, WOP_UU_W, H8, H4, float32_to_float64)
-GEN_VEXT_V_ENV(vfwcvt_f_f_v_h, 2, 4)
-GEN_VEXT_V_ENV(vfwcvt_f_f_v_w, 4, 8)
+GEN_VEXT_V_ENV(vfwcvt_f_f_v_h)
+GEN_VEXT_V_ENV(vfwcvt_f_f_v_w)
/* Narrowing Floating-Point/Integer Type-Convert Instructions */
/* (TD, T2, TX2) */
@@ -4254,29 +4252,29 @@ GEN_VEXT_V_ENV(vfwcvt_f_f_v_w, 4, 8)
RVVCALL(OPFVV1, vfncvt_xu_f_w_b, NOP_UU_B, H1, H2, float16_to_uint8)
RVVCALL(OPFVV1, vfncvt_xu_f_w_h, NOP_UU_H, H2, H4, float32_to_uint16)
RVVCALL(OPFVV1, vfncvt_xu_f_w_w, NOP_UU_W, H4, H8, float64_to_uint32)
-GEN_VEXT_V_ENV(vfncvt_xu_f_w_b, 1, 1)
-GEN_VEXT_V_ENV(vfncvt_xu_f_w_h, 2, 2)
-GEN_VEXT_V_ENV(vfncvt_xu_f_w_w, 4, 4)
+GEN_VEXT_V_ENV(vfncvt_xu_f_w_b)
+GEN_VEXT_V_ENV(vfncvt_xu_f_w_h)
+GEN_VEXT_V_ENV(vfncvt_xu_f_w_w)
/* vfncvt.x.f.v vd, vs2, vm # Convert double-width float to signed integer. */
RVVCALL(OPFVV1, vfncvt_x_f_w_b, NOP_UU_B, H1, H2, float16_to_int8)
RVVCALL(OPFVV1, vfncvt_x_f_w_h, NOP_UU_H, H2, H4, float32_to_int16)
RVVCALL(OPFVV1, vfncvt_x_f_w_w, NOP_UU_W, H4, H8, float64_to_int32)
-GEN_VEXT_V_ENV(vfncvt_x_f_w_b, 1, 1)
-GEN_VEXT_V_ENV(vfncvt_x_f_w_h, 2, 2)
-GEN_VEXT_V_ENV(vfncvt_x_f_w_w, 4, 4)
+GEN_VEXT_V_ENV(vfncvt_x_f_w_b)
+GEN_VEXT_V_ENV(vfncvt_x_f_w_h)
+GEN_VEXT_V_ENV(vfncvt_x_f_w_w)
/* vfncvt.f.xu.v vd, vs2, vm # Convert double-width unsigned integer to float */
RVVCALL(OPFVV1, vfncvt_f_xu_w_h, NOP_UU_H, H2, H4, uint32_to_float16)
RVVCALL(OPFVV1, vfncvt_f_xu_w_w, NOP_UU_W, H4, H8, uint64_to_float32)
-GEN_VEXT_V_ENV(vfncvt_f_xu_w_h, 2, 2)
-GEN_VEXT_V_ENV(vfncvt_f_xu_w_w, 4, 4)
+GEN_VEXT_V_ENV(vfncvt_f_xu_w_h)
+GEN_VEXT_V_ENV(vfncvt_f_xu_w_w)
/* vfncvt.f.x.v vd, vs2, vm # Convert double-width integer to float. */
RVVCALL(OPFVV1, vfncvt_f_x_w_h, NOP_UU_H, H2, H4, int32_to_float16)
RVVCALL(OPFVV1, vfncvt_f_x_w_w, NOP_UU_W, H4, H8, int64_to_float32)
-GEN_VEXT_V_ENV(vfncvt_f_x_w_h, 2, 2)
-GEN_VEXT_V_ENV(vfncvt_f_x_w_w, 4, 4)
+GEN_VEXT_V_ENV(vfncvt_f_x_w_h)
+GEN_VEXT_V_ENV(vfncvt_f_x_w_w)
/* vfncvt.f.f.v vd, vs2, vm # Convert double float to single-width float. */
static uint16_t vfncvtffv16(uint32_t a, float_status *s)
@@ -4286,8 +4284,8 @@ static uint16_t vfncvtffv16(uint32_t a, float_status *s)
RVVCALL(OPFVV1, vfncvt_f_f_w_h, NOP_UU_H, H2, H4, vfncvtffv16)
RVVCALL(OPFVV1, vfncvt_f_f_w_w, NOP_UU_W, H4, H8, float64_to_float32)
-GEN_VEXT_V_ENV(vfncvt_f_f_w_h, 2, 2)
-GEN_VEXT_V_ENV(vfncvt_f_f_w_w, 4, 4)
+GEN_VEXT_V_ENV(vfncvt_f_f_w_h)
+GEN_VEXT_V_ENV(vfncvt_f_f_w_w)
/*
*** Vector Reduction Operations
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 16/16] target/riscv: rvv: Add option 'rvv_ta_all_1s' to enable optional tail agnostic behavior
2022-05-13 11:49 [PATCH qemu v18 00/16] Add tail agnostic behavior for rvv instructions ~eopxd
@ 2022-05-13 11:50 ` ~eopxd
2022-05-13 11:50 ` ~eopxd
` (15 subsequent siblings)
16 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-04-28 3:26 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
According to v-spec, tail agnostic behavior can be either kept as
undisturbed or set elements' bits to all 1s. To distinguish the
difference of tail policies, QEMU should be able to simulate the tail
agnostic behavior as "set tail elements' bits to all 1s".
There are multiple possibility for agnostic elements according to
v-spec. The main intent of this patch-set tries to add option that
can distinguish between tail policies. Setting agnostic elements to
all 1s allows QEMU to express this.
This commit adds option 'rvv_ta_all_1s' is added to enable the
behavior, it is default as disabled.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/cpu.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
index ccacdee215..720c8b9e5c 100644
--- a/target/riscv/cpu.c
+++ b/target/riscv/cpu.c
@@ -879,6 +879,7 @@ static Property riscv_cpu_properties[] = {
DEFINE_PROP_BOOL("x-aia", RISCVCPU, cfg.aia, false),
DEFINE_PROP_UINT64("resetvec", RISCVCPU, cfg.resetvec, DEFAULT_RSTVEC),
+ DEFINE_PROP_BOOL("rvv_ta_all_1s", RISCVCPU, cfg.rvv_ta_all_1s, false),
DEFINE_PROP_END_OF_LIST(),
};
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 02/16] target/riscv: rvv: Prune redundant access_type parameter passed
2022-05-13 11:49 [PATCH qemu v18 00/16] Add tail agnostic behavior for rvv instructions ~eopxd
` (14 preceding siblings ...)
2022-05-13 11:50 ` ~eopxd
@ 2022-05-12 7:47 ` ~eopxd
2022-05-23 21:39 ` Alistair Francis
2022-06-06 1:37 ` [PATCH qemu v18 00/16] Add tail agnostic behavior for rvv instructions Alistair Francis
16 siblings, 1 reply; 35+ messages in thread
From: ~eopxd @ 2022-05-12 7:47 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
No functional change intended in this commit.
Signed-off-by: eop Chen <eop.chen@sifive.com>
---
target/riscv/vector_helper.c | 35 ++++++++++++++++-------------------
1 file changed, 16 insertions(+), 19 deletions(-)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 85dd611cd9..60840325c4 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -231,7 +231,7 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base,
target_ulong stride, CPURISCVState *env,
uint32_t desc, uint32_t vm,
vext_ldst_elem_fn *ldst_elem,
- uint32_t esz, uintptr_t ra, MMUAccessType access_type)
+ uint32_t esz, uintptr_t ra)
{
uint32_t i, k;
uint32_t nf = vext_nf(desc);
@@ -259,7 +259,7 @@ void HELPER(NAME)(void *vd, void * v0, target_ulong base, \
{ \
uint32_t vm = vext_vm(desc); \
vext_ldst_stride(vd, v0, base, stride, env, desc, vm, LOAD_FN, \
- ctzl(sizeof(ETYPE)), GETPC(), MMU_DATA_LOAD); \
+ ctzl(sizeof(ETYPE)), GETPC()); \
}
GEN_VEXT_LD_STRIDE(vlse8_v, int8_t, lde_b)
@@ -274,7 +274,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong base, \
{ \
uint32_t vm = vext_vm(desc); \
vext_ldst_stride(vd, v0, base, stride, env, desc, vm, STORE_FN, \
- ctzl(sizeof(ETYPE)), GETPC(), MMU_DATA_STORE); \
+ ctzl(sizeof(ETYPE)), GETPC()); \
}
GEN_VEXT_ST_STRIDE(vsse8_v, int8_t, ste_b)
@@ -290,7 +290,7 @@ GEN_VEXT_ST_STRIDE(vsse64_v, int64_t, ste_d)
static void
vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
vext_ldst_elem_fn *ldst_elem, uint32_t esz, uint32_t evl,
- uintptr_t ra, MMUAccessType access_type)
+ uintptr_t ra)
{
uint32_t i, k;
uint32_t nf = vext_nf(desc);
@@ -319,14 +319,14 @@ void HELPER(NAME##_mask)(void *vd, void *v0, target_ulong base, \
{ \
uint32_t stride = vext_nf(desc) << ctzl(sizeof(ETYPE)); \
vext_ldst_stride(vd, v0, base, stride, env, desc, false, LOAD_FN, \
- ctzl(sizeof(ETYPE)), GETPC(), MMU_DATA_LOAD); \
+ ctzl(sizeof(ETYPE)), GETPC()); \
} \
\
void HELPER(NAME)(void *vd, void *v0, target_ulong base, \
CPURISCVState *env, uint32_t desc) \
{ \
vext_ldst_us(vd, base, env, desc, LOAD_FN, \
- ctzl(sizeof(ETYPE)), env->vl, GETPC(), MMU_DATA_LOAD); \
+ ctzl(sizeof(ETYPE)), env->vl, GETPC()); \
}
GEN_VEXT_LD_US(vle8_v, int8_t, lde_b)
@@ -340,14 +340,14 @@ void HELPER(NAME##_mask)(void *vd, void *v0, target_ulong base, \
{ \
uint32_t stride = vext_nf(desc) << ctzl(sizeof(ETYPE)); \
vext_ldst_stride(vd, v0, base, stride, env, desc, false, STORE_FN, \
- ctzl(sizeof(ETYPE)), GETPC(), MMU_DATA_STORE); \
+ ctzl(sizeof(ETYPE)), GETPC()); \
} \
\
void HELPER(NAME)(void *vd, void *v0, target_ulong base, \
CPURISCVState *env, uint32_t desc) \
{ \
vext_ldst_us(vd, base, env, desc, STORE_FN, \
- ctzl(sizeof(ETYPE)), env->vl, GETPC(), MMU_DATA_STORE); \
+ ctzl(sizeof(ETYPE)), env->vl, GETPC()); \
}
GEN_VEXT_ST_US(vse8_v, int8_t, ste_b)
@@ -364,7 +364,7 @@ void HELPER(vlm_v)(void *vd, void *v0, target_ulong base,
/* evl = ceil(vl/8) */
uint8_t evl = (env->vl + 7) >> 3;
vext_ldst_us(vd, base, env, desc, lde_b,
- 0, evl, GETPC(), MMU_DATA_LOAD);
+ 0, evl, GETPC());
}
void HELPER(vsm_v)(void *vd, void *v0, target_ulong base,
@@ -373,7 +373,7 @@ void HELPER(vsm_v)(void *vd, void *v0, target_ulong base,
/* evl = ceil(vl/8) */
uint8_t evl = (env->vl + 7) >> 3;
vext_ldst_us(vd, base, env, desc, ste_b,
- 0, evl, GETPC(), MMU_DATA_STORE);
+ 0, evl, GETPC());
}
/*
@@ -399,7 +399,7 @@ vext_ldst_index(void *vd, void *v0, target_ulong base,
void *vs2, CPURISCVState *env, uint32_t desc,
vext_get_index_addr get_index_addr,
vext_ldst_elem_fn *ldst_elem,
- uint32_t esz, uintptr_t ra, MMUAccessType access_type)
+ uint32_t esz, uintptr_t ra)
{
uint32_t i, k;
uint32_t nf = vext_nf(desc);
@@ -427,7 +427,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong base, \
void *vs2, CPURISCVState *env, uint32_t desc) \
{ \
vext_ldst_index(vd, v0, base, vs2, env, desc, INDEX_FN, \
- LOAD_FN, ctzl(sizeof(ETYPE)), GETPC(), MMU_DATA_LOAD); \
+ LOAD_FN, ctzl(sizeof(ETYPE)), GETPC()); \
}
GEN_VEXT_LD_INDEX(vlxei8_8_v, int8_t, idx_b, lde_b)
@@ -453,7 +453,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong base, \
{ \
vext_ldst_index(vd, v0, base, vs2, env, desc, INDEX_FN, \
STORE_FN, ctzl(sizeof(ETYPE)), \
- GETPC(), MMU_DATA_STORE); \
+ GETPC()); \
}
GEN_VEXT_ST_INDEX(vsxei8_8_v, int8_t, idx_b, ste_b)
@@ -576,8 +576,7 @@ GEN_VEXT_LDFF(vle64ff_v, int64_t, lde_d)
*/
static void
vext_ldst_whole(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
- vext_ldst_elem_fn *ldst_elem, uint32_t esz, uintptr_t ra,
- MMUAccessType access_type)
+ vext_ldst_elem_fn *ldst_elem, uint32_t esz, uintptr_t ra)
{
uint32_t i, k, off, pos;
uint32_t nf = vext_nf(desc);
@@ -612,8 +611,7 @@ void HELPER(NAME)(void *vd, target_ulong base, \
CPURISCVState *env, uint32_t desc) \
{ \
vext_ldst_whole(vd, base, env, desc, LOAD_FN, \
- ctzl(sizeof(ETYPE)), GETPC(), \
- MMU_DATA_LOAD); \
+ ctzl(sizeof(ETYPE)), GETPC()); \
}
GEN_VEXT_LD_WHOLE(vl1re8_v, int8_t, lde_b)
@@ -638,8 +636,7 @@ void HELPER(NAME)(void *vd, target_ulong base, \
CPURISCVState *env, uint32_t desc) \
{ \
vext_ldst_whole(vd, base, env, desc, STORE_FN, \
- ctzl(sizeof(ETYPE)), GETPC(), \
- MMU_DATA_STORE); \
+ ctzl(sizeof(ETYPE)), GETPC()); \
}
GEN_VEXT_ST_WHOLE(vs1r_v, int8_t, ste_b)
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 00/16] Add tail agnostic behavior for rvv instructions
@ 2022-05-13 11:49 ~eopxd
2022-05-13 11:50 ` ~eopxd
` (16 more replies)
0 siblings, 17 replies; 35+ messages in thread
From: ~eopxd @ 2022-05-13 11:49 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
According to v-spec, tail agnostic behavior can be either kept as
undisturbed or set elements' bits to all 1s. To distinguish the
difference of tail policies, QEMU should be able to simulate the tail
agnostic behavior as "set tail elements' bits to all 1s". An option
'rvv_ta_all_1s' is added to enable the behavior, it is default as
disabled.
There are multiple possibility for agnostic elements according to
v-spec. The main intent of this patch-set tries to add option that
can distinguish between tail policies. Setting agnostic elements to
all 1s makes things simple and allow QEMU to express this.
We may explore other possibility of agnostic behavior by adding
other options in the future. Please understand that this patch-set
is limited.
v2 updates:
- Addressed comments from Weiwei Li
- Added commit tail agnostic on load / store instructions (which
I forgot to include into the patch-set)
v3 updates:
- Missed the very 1st commit, adding it back
v4 updates:
- Renamed vlmax to total_elems
- Deal with tail element when vl_eq_vlmax == true
v5 updates:
- Let `vext_get_total_elems` take `desc` and `esz`
- Utilize `simd_maxsz(desc)` to get `vlenb`
- Fix alignments to code
v6 updates:
- Fix `vext_get_total_elems`
v7 updates:
- Reuse `max_elems` for vector load / store helper functions. The
translation sets desc's `lmul` to `min(1, lmul)`, making
`vext_max_elems` equivalent to `vext_get_total_elems`.
v8 updates:
- Simplify `vext_set_elems_1s`, don't need `vext_set_elems_1s_fns`
- Fix `vext_get_total_elems`, it should derive upon EMUL instead
of LMUL
v9 updates:
- Let instructions that is tail agnostic regardless of vta respect the
option and not the vta.
v10 updates:
- Correct range to set element to 1s for load instructions
v11 updates:
- Separate addition of option 'rvv_ta_all_1s' as a new (last) commit
- Add description to show intent of the option in first commit for the
optional tail agnostic behavior
- Tag WeiWei as Reviewed-by for all commits
- Tag Alistair as Reviewed-by for commit 01, 02
- Tag Alistair as Acked-by for commit 03
v12 updates:
- Add missing space in WeiWei's "Reviewed-by" tag
v13 updates:
- Fix tail agnostic for vext_ldst_us. The function operates on input
parameter 'evl' rather than 'env->vl'.
- Fix tail elements for vector segment load / store instructions
A vector segment load / store instruction may contain fractional
lmul with nf * lmul > 1. The rest of the elements in the last
register should be treated as tail elements.
- Fix tail agnostic length for instructions with mask destination
register. Instructions with mask destination register should have
'vlen - vl' tail elements.
v14 updates:
- Pass lmul information to into vector helper function.
`vext_get_total_elems` needs it.
v15 updates:
- Rebase to latest `master`
- Tag Alistair as Acked by for commit 04 ~ 14
- Tag Alistair as Acked by for commit 15
v16 updates:
- Fix bug, when encountering situation when lmul < 0 and vl_eq_vlmax,
the original version will override on `vd` but the computation will
override again, meaning the tail elements will not be set correctly.
Now, we don't use TCG functions if we are trying to simulate all 1s
for agnostic and use vector helpers instead.
v17 updates:
- Add "Prune access_type parameter" commit to cleanup vector load/
store functions. Then add parameter `is_load` in vector helper
functions to enable vta behavior in the commit for adding vta on
vector load/store functions.
v18 updates:
- Don't use `is_load` parameter in vector helper. Don't let vta pass
through in `trans_rvv.inc`
eopXD (16):
target/riscv: rvv: Prune redundant ESZ, DSZ parameter passed
target/riscv: rvv: Prune redundant access_type parameter passed
target/riscv: rvv: Rename ambiguous esz
target/riscv: rvv: Early exit when vstart >= vl
target/riscv: rvv: Add tail agnostic for vv instructions
target/riscv: rvv: Add tail agnostic for vector load / store
instructions
target/riscv: rvv: Add tail agnostic for vx, vvm, vxm instructions
target/riscv: rvv: Add tail agnostic for vector integer shift
instructions
target/riscv: rvv: Add tail agnostic for vector integer comparison
instructions
target/riscv: rvv: Add tail agnostic for vector integer merge and move
instructions
target/riscv: rvv: Add tail agnostic for vector fix-point arithmetic
instructions
target/riscv: rvv: Add tail agnostic for vector floating-point
instructions
target/riscv: rvv: Add tail agnostic for vector reduction instructions
target/riscv: rvv: Add tail agnostic for vector mask instructions
target/riscv: rvv: Add tail agnostic for vector permutation
instructions
target/riscv: rvv: Add option 'rvv_ta_all_1s' to enable optional tail
agnostic behavior
target/riscv/cpu.c | 1 +
target/riscv/cpu.h | 2 +
target/riscv/cpu_helper.c | 2 +
target/riscv/insn_trans/trans_rvv.c.inc | 94 +-
target/riscv/internals.h | 6 +-
target/riscv/translate.c | 4 +
target/riscv/vector_helper.c | 1587 ++++++++++++++---------
7 files changed, 1053 insertions(+), 643 deletions(-)
--
2.34.2
^ permalink raw reply [flat|nested] 35+ messages in thread
* [PATCH qemu v18 04/16] target/riscv: rvv: Early exit when vstart >= vl
@ 2022-05-13 11:50 ` ~eopxd
0 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-05-13 11:50 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
According to v-spec (section 5.4):
When vstart ≥ vl, there are no body elements, and no elements are
updated in any destination vector register group, including that
no tail elements are updated with agnostic values.
vmsbf.m, vmsif.m, vmsof.m, viota.m, vcompress instructions themselves
require vstart to be zero. So they don't need the early exit.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/insn_trans/trans_rvv.c.inc | 27 +++++++++++++++++++++++++
1 file changed, 27 insertions(+)
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index 90327509f7..4d5dfa794a 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -652,6 +652,7 @@ static bool ldst_us_trans(uint32_t vd, uint32_t rs1, uint32_t data,
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
dest = tcg_temp_new_ptr();
mask = tcg_temp_new_ptr();
@@ -818,6 +819,7 @@ static bool ldst_stride_trans(uint32_t vd, uint32_t rs1, uint32_t rs2,
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
dest = tcg_temp_new_ptr();
mask = tcg_temp_new_ptr();
@@ -925,6 +927,7 @@ static bool ldst_index_trans(uint32_t vd, uint32_t rs1, uint32_t vs2,
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
dest = tcg_temp_new_ptr();
mask = tcg_temp_new_ptr();
@@ -1067,6 +1070,7 @@ static bool ldff_trans(uint32_t vd, uint32_t rs1, uint32_t data,
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
dest = tcg_temp_new_ptr();
mask = tcg_temp_new_ptr();
@@ -1221,6 +1225,7 @@ do_opivv_gvec(DisasContext *s, arg_rmrr *a, GVecGen3Fn *gvec_fn,
}
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
if (a->vm && s->vl_eq_vlmax) {
gvec_fn(s->sew, vreg_ofs(s, a->rd),
@@ -1268,6 +1273,7 @@ static bool opivx_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, uint32_t vm,
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
dest = tcg_temp_new_ptr();
mask = tcg_temp_new_ptr();
@@ -1432,6 +1438,7 @@ static bool opivi_trans(uint32_t vd, uint32_t imm, uint32_t vs2, uint32_t vm,
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
dest = tcg_temp_new_ptr();
mask = tcg_temp_new_ptr();
@@ -1518,6 +1525,7 @@ static bool do_opivv_widen(DisasContext *s, arg_rmrr *a,
uint32_t data = 0;
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
@@ -1598,6 +1606,7 @@ static bool do_opiwv_widen(DisasContext *s, arg_rmrr *a,
uint32_t data = 0;
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
@@ -1675,6 +1684,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
}; \
TCGLabel *over = gen_new_label(); \
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
@@ -1856,6 +1866,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
}; \
TCGLabel *over = gen_new_label(); \
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
@@ -2066,6 +2077,7 @@ static bool trans_vmv_v_v(DisasContext *s, arg_vmv_v_v *a)
};
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
tcg_gen_gvec_2_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs1),
cpu_env, s->cfg_ptr->vlen / 8,
@@ -2089,6 +2101,7 @@ static bool trans_vmv_v_x(DisasContext *s, arg_vmv_v_x *a)
TCGv s1;
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
s1 = get_gpr(s, a->rs1, EXT_SIGN);
@@ -2144,6 +2157,7 @@ static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_i *a)
};
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
s1 = tcg_constant_i64(simm);
dest = tcg_temp_new_ptr();
@@ -2296,6 +2310,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
TCGLabel *over = gen_new_label(); \
gen_set_rm(s, RISCV_FRM_DYN); \
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
@@ -2326,6 +2341,7 @@ static bool opfvf_trans(uint32_t vd, uint32_t rs1, uint32_t vs2,
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
dest = tcg_temp_new_ptr();
mask = tcg_temp_new_ptr();
@@ -2414,6 +2430,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
TCGLabel *over = gen_new_label(); \
gen_set_rm(s, RISCV_FRM_DYN); \
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);\
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
@@ -2488,6 +2505,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
TCGLabel *over = gen_new_label(); \
gen_set_rm(s, RISCV_FRM_DYN); \
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
@@ -2609,6 +2627,7 @@ static bool do_opfv(DisasContext *s, arg_rmr *a,
TCGLabel *over = gen_new_label();
gen_set_rm(s, rm);
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
@@ -2722,6 +2741,7 @@ static bool trans_vfmv_v_f(DisasContext *s, arg_vfmv_v_f *a)
};
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
t1 = tcg_temp_new_i64();
/* NaN-box f[rs1] */
@@ -2810,6 +2830,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
TCGLabel *over = gen_new_label(); \
gen_set_rm(s, FRM); \
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
@@ -2861,6 +2882,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
TCGLabel *over = gen_new_label(); \
gen_set_rm(s, RISCV_FRM_DYN); \
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
@@ -2926,6 +2948,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
TCGLabel *over = gen_new_label(); \
gen_set_rm(s, FRM); \
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
@@ -2979,6 +3002,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
TCGLabel *over = gen_new_label(); \
gen_set_rm(s, FRM); \
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
@@ -3066,6 +3090,7 @@ static bool trans_##NAME(DisasContext *s, arg_r *a) \
gen_helper_gvec_4_ptr *fn = gen_helper_##NAME; \
TCGLabel *over = gen_new_label(); \
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
@@ -3234,6 +3259,7 @@ static bool trans_vid_v(DisasContext *s, arg_vid_v *a)
uint32_t data = 0;
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
@@ -3744,6 +3770,7 @@ static bool int_ext_op(DisasContext *s, arg_rmr *a, uint8_t seq)
gen_helper_gvec_3_ptr *fn;
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
static gen_helper_gvec_3_ptr * const fns[6][4] = {
{
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 03/16] target/riscv: rvv: Rename ambiguous esz
@ 2022-05-13 11:50 ` ~eopxd
0 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-05-13 11:50 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
No functional change intended in this commit.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/vector_helper.c | 76 ++++++++++++++++++------------------
1 file changed, 38 insertions(+), 38 deletions(-)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 60840325c4..3b79b9cbc2 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -125,9 +125,9 @@ static inline int32_t vext_lmul(uint32_t desc)
/*
* Get the maximum number of elements can be operated.
*
- * esz: log2 of element size in bytes.
+ * log2_esz: log2 of element size in bytes.
*/
-static inline uint32_t vext_max_elems(uint32_t desc, uint32_t esz)
+static inline uint32_t vext_max_elems(uint32_t desc, uint32_t log2_esz)
{
/*
* As simd_desc support at most 2048 bytes, the max vlen is 1024 bits.
@@ -136,7 +136,7 @@ static inline uint32_t vext_max_elems(uint32_t desc, uint32_t esz)
uint32_t vlenb = simd_maxsz(desc);
/* Return VLMAX */
- int scale = vext_lmul(desc) - esz;
+ int scale = vext_lmul(desc) - log2_esz;
return scale < 0 ? vlenb >> -scale : vlenb << scale;
}
@@ -231,11 +231,11 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base,
target_ulong stride, CPURISCVState *env,
uint32_t desc, uint32_t vm,
vext_ldst_elem_fn *ldst_elem,
- uint32_t esz, uintptr_t ra)
+ uint32_t log2_esz, uintptr_t ra)
{
uint32_t i, k;
uint32_t nf = vext_nf(desc);
- uint32_t max_elems = vext_max_elems(desc, esz);
+ uint32_t max_elems = vext_max_elems(desc, log2_esz);
for (i = env->vstart; i < env->vl; i++, env->vstart++) {
if (!vm && !vext_elem_mask(v0, i)) {
@@ -244,7 +244,7 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base,
k = 0;
while (k < nf) {
- target_ulong addr = base + stride * i + (k << esz);
+ target_ulong addr = base + stride * i + (k << log2_esz);
ldst_elem(env, adjust_addr(env, addr), i + k * max_elems, vd, ra);
k++;
}
@@ -289,18 +289,18 @@ GEN_VEXT_ST_STRIDE(vsse64_v, int64_t, ste_d)
/* unmasked unit-stride load and store operation*/
static void
vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
- vext_ldst_elem_fn *ldst_elem, uint32_t esz, uint32_t evl,
+ vext_ldst_elem_fn *ldst_elem, uint32_t log2_esz, uint32_t evl,
uintptr_t ra)
{
uint32_t i, k;
uint32_t nf = vext_nf(desc);
- uint32_t max_elems = vext_max_elems(desc, esz);
+ uint32_t max_elems = vext_max_elems(desc, log2_esz);
/* load bytes from guest memory */
for (i = env->vstart; i < evl; i++, env->vstart++) {
k = 0;
while (k < nf) {
- target_ulong addr = base + ((i * nf + k) << esz);
+ target_ulong addr = base + ((i * nf + k) << log2_esz);
ldst_elem(env, adjust_addr(env, addr), i + k * max_elems, vd, ra);
k++;
}
@@ -399,12 +399,12 @@ vext_ldst_index(void *vd, void *v0, target_ulong base,
void *vs2, CPURISCVState *env, uint32_t desc,
vext_get_index_addr get_index_addr,
vext_ldst_elem_fn *ldst_elem,
- uint32_t esz, uintptr_t ra)
+ uint32_t log2_esz, uintptr_t ra)
{
uint32_t i, k;
uint32_t nf = vext_nf(desc);
uint32_t vm = vext_vm(desc);
- uint32_t max_elems = vext_max_elems(desc, esz);
+ uint32_t max_elems = vext_max_elems(desc, log2_esz);
/* load bytes from guest memory */
for (i = env->vstart; i < env->vl; i++, env->vstart++) {
@@ -414,7 +414,7 @@ vext_ldst_index(void *vd, void *v0, target_ulong base,
k = 0;
while (k < nf) {
- abi_ptr addr = get_index_addr(base, i, vs2) + (k << esz);
+ abi_ptr addr = get_index_addr(base, i, vs2) + (k << log2_esz);
ldst_elem(env, adjust_addr(env, addr), i + k * max_elems, vd, ra);
k++;
}
@@ -480,13 +480,13 @@ static inline void
vext_ldff(void *vd, void *v0, target_ulong base,
CPURISCVState *env, uint32_t desc,
vext_ldst_elem_fn *ldst_elem,
- uint32_t esz, uintptr_t ra)
+ uint32_t log2_esz, uintptr_t ra)
{
void *host;
uint32_t i, k, vl = 0;
uint32_t nf = vext_nf(desc);
uint32_t vm = vext_vm(desc);
- uint32_t max_elems = vext_max_elems(desc, esz);
+ uint32_t max_elems = vext_max_elems(desc, log2_esz);
target_ulong addr, offset, remain;
/* probe every access*/
@@ -494,12 +494,12 @@ vext_ldff(void *vd, void *v0, target_ulong base,
if (!vm && !vext_elem_mask(v0, i)) {
continue;
}
- addr = adjust_addr(env, base + i * (nf << esz));
+ addr = adjust_addr(env, base + i * (nf << log2_esz));
if (i == 0) {
- probe_pages(env, addr, nf << esz, ra, MMU_DATA_LOAD);
+ probe_pages(env, addr, nf << log2_esz, ra, MMU_DATA_LOAD);
} else {
/* if it triggers an exception, no need to check watchpoint */
- remain = nf << esz;
+ remain = nf << log2_esz;
while (remain > 0) {
offset = -(addr | TARGET_PAGE_MASK);
host = tlb_vaddr_to_host(env, addr, MMU_DATA_LOAD,
@@ -536,7 +536,7 @@ ProbeSuccess:
continue;
}
while (k < nf) {
- target_ulong addr = base + ((i * nf + k) << esz);
+ target_ulong addr = base + ((i * nf + k) << log2_esz);
ldst_elem(env, adjust_addr(env, addr), i + k * max_elems, vd, ra);
k++;
}
@@ -576,12 +576,12 @@ GEN_VEXT_LDFF(vle64ff_v, int64_t, lde_d)
*/
static void
vext_ldst_whole(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
- vext_ldst_elem_fn *ldst_elem, uint32_t esz, uintptr_t ra)
+ vext_ldst_elem_fn *ldst_elem, uint32_t log2_esz, uintptr_t ra)
{
uint32_t i, k, off, pos;
uint32_t nf = vext_nf(desc);
uint32_t vlenb = env_archcpu(env)->cfg.vlen >> 3;
- uint32_t max_elems = vlenb >> esz;
+ uint32_t max_elems = vlenb >> log2_esz;
k = env->vstart / max_elems;
off = env->vstart % max_elems;
@@ -589,7 +589,7 @@ vext_ldst_whole(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
if (off) {
/* load/store rest of elements of current segment pointed by vstart */
for (pos = off; pos < max_elems; pos++, env->vstart++) {
- target_ulong addr = base + ((pos + k * max_elems) << esz);
+ target_ulong addr = base + ((pos + k * max_elems) << log2_esz);
ldst_elem(env, adjust_addr(env, addr), pos + k * max_elems, vd, ra);
}
k++;
@@ -598,7 +598,7 @@ vext_ldst_whole(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
/* load/store elements for rest of segments */
for (; k < nf; k++) {
for (i = 0; i < max_elems; i++, env->vstart++) {
- target_ulong addr = base + ((i + k * max_elems) << esz);
+ target_ulong addr = base + ((i + k * max_elems) << log2_esz);
ldst_elem(env, adjust_addr(env, addr), i + k * max_elems, vd, ra);
}
}
@@ -4688,11 +4688,11 @@ GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_h, uint16_t, H2)
GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_w, uint32_t, H4)
GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_d, uint64_t, H8)
-#define GEN_VEXT_VSLIE1UP(ESZ, H) \
-static void vslide1up_##ESZ(void *vd, void *v0, target_ulong s1, void *vs2, \
- CPURISCVState *env, uint32_t desc) \
+#define GEN_VEXT_VSLIE1UP(BITWIDTH, H) \
+static void vslide1up_##BITWIDTH(void *vd, void *v0, target_ulong s1, \
+ void *vs2, CPURISCVState *env, uint32_t desc) \
{ \
- typedef uint##ESZ##_t ETYPE; \
+ typedef uint##BITWIDTH##_t ETYPE; \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
uint32_t i; \
@@ -4715,11 +4715,11 @@ GEN_VEXT_VSLIE1UP(16, H2)
GEN_VEXT_VSLIE1UP(32, H4)
GEN_VEXT_VSLIE1UP(64, H8)
-#define GEN_VEXT_VSLIDE1UP_VX(NAME, ESZ) \
+#define GEN_VEXT_VSLIDE1UP_VX(NAME, BITWIDTH) \
void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
- vslide1up_##ESZ(vd, v0, s1, vs2, env, desc); \
+ vslide1up_##BITWIDTH(vd, v0, s1, vs2, env, desc); \
}
/* vslide1up.vx vd, vs2, rs1, vm # vd[0]=x[rs1], vd[i+1] = vs2[i] */
@@ -4728,11 +4728,11 @@ GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_h, 16)
GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_w, 32)
GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_d, 64)
-#define GEN_VEXT_VSLIDE1DOWN(ESZ, H) \
-static void vslide1down_##ESZ(void *vd, void *v0, target_ulong s1, void *vs2, \
- CPURISCVState *env, uint32_t desc) \
+#define GEN_VEXT_VSLIDE1DOWN(BITWIDTH, H) \
+static void vslide1down_##BITWIDTH(void *vd, void *v0, target_ulong s1, \
+ void *vs2, CPURISCVState *env, uint32_t desc) \
{ \
- typedef uint##ESZ##_t ETYPE; \
+ typedef uint##BITWIDTH##_t ETYPE; \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
uint32_t i; \
@@ -4755,11 +4755,11 @@ GEN_VEXT_VSLIDE1DOWN(16, H2)
GEN_VEXT_VSLIDE1DOWN(32, H4)
GEN_VEXT_VSLIDE1DOWN(64, H8)
-#define GEN_VEXT_VSLIDE1DOWN_VX(NAME, ESZ) \
+#define GEN_VEXT_VSLIDE1DOWN_VX(NAME, BITWIDTH) \
void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
- vslide1down_##ESZ(vd, v0, s1, vs2, env, desc); \
+ vslide1down_##BITWIDTH(vd, v0, s1, vs2, env, desc); \
}
/* vslide1down.vx vd, vs2, rs1, vm # vd[i] = vs2[i+1], vd[vl-1]=x[rs1] */
@@ -4769,11 +4769,11 @@ GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_w, 32)
GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_d, 64)
/* Vector Floating-Point Slide Instructions */
-#define GEN_VEXT_VFSLIDE1UP_VF(NAME, ESZ) \
+#define GEN_VEXT_VFSLIDE1UP_VF(NAME, BITWIDTH) \
void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
- vslide1up_##ESZ(vd, v0, s1, vs2, env, desc); \
+ vslide1up_##BITWIDTH(vd, v0, s1, vs2, env, desc); \
}
/* vfslide1up.vf vd, vs2, rs1, vm # vd[0]=f[rs1], vd[i+1] = vs2[i] */
@@ -4781,11 +4781,11 @@ GEN_VEXT_VFSLIDE1UP_VF(vfslide1up_vf_h, 16)
GEN_VEXT_VFSLIDE1UP_VF(vfslide1up_vf_w, 32)
GEN_VEXT_VFSLIDE1UP_VF(vfslide1up_vf_d, 64)
-#define GEN_VEXT_VFSLIDE1DOWN_VF(NAME, ESZ) \
+#define GEN_VEXT_VFSLIDE1DOWN_VF(NAME, BITWIDTH) \
void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
- vslide1down_##ESZ(vd, v0, s1, vs2, env, desc); \
+ vslide1down_##BITWIDTH(vd, v0, s1, vs2, env, desc); \
}
/* vfslide1down.vf vd, vs2, rs1, vm # vd[i] = vs2[i+1], vd[vl-1]=f[rs1] */
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 06/16] target/riscv: rvv: Add tail agnostic for vector load / store instructions
@ 2022-05-13 11:50 ` ~eopxd
0 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-05-13 11:50 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
Destination register of unit-stride mask load and store instructions are
always written with a tail-agnostic policy.
A vector segment load / store instruction may contain fractional lmul
with nf * lmul > 1. The rest of the elements in the last register should
be treated as tail elements.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/insn_trans/trans_rvv.c.inc | 6 +++
target/riscv/translate.c | 2 +
target/riscv/vector_helper.c | 60 +++++++++++++++++++++++++
3 files changed, 68 insertions(+)
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index efdf5d6d81..4da06b859b 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -711,6 +711,7 @@ static bool ld_us_op(DisasContext *s, arg_r2nfvm *a, uint8_t eew)
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, emul);
data = FIELD_DP32(data, VDATA, NF, a->nf);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
return ldst_us_trans(a->rd, a->rs1, data, fn, s, false);
}
@@ -774,6 +775,8 @@ static bool ld_us_mask_op(DisasContext *s, arg_vlm_v *a, uint8_t eew)
/* EMUL = 1, NFIELDS = 1 */
data = FIELD_DP32(data, VDATA, LMUL, 0);
data = FIELD_DP32(data, VDATA, NF, 1);
+ /* Mask destination register are always tail-agnostic */
+ data = FIELD_DP32(data, VDATA, VTA, s->cfg_vta_all_1s);
return ldst_us_trans(a->rd, a->rs1, data, fn, s, false);
}
@@ -862,6 +865,7 @@ static bool ld_stride_op(DisasContext *s, arg_rnfvm *a, uint8_t eew)
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, emul);
data = FIELD_DP32(data, VDATA, NF, a->nf);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
return ldst_stride_trans(a->rd, a->rs1, a->rs2, data, fn, s, false);
}
@@ -991,6 +995,7 @@ static bool ld_index_op(DisasContext *s, arg_rnfvm *a, uint8_t eew)
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, emul);
data = FIELD_DP32(data, VDATA, NF, a->nf);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
return ldst_index_trans(a->rd, a->rs1, a->rs2, data, fn, s, false);
}
@@ -1108,6 +1113,7 @@ static bool ldff_op(DisasContext *s, arg_r2nfvm *a, uint8_t eew)
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, emul);
data = FIELD_DP32(data, VDATA, NF, a->nf);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
return ldff_trans(a->rd, a->rs1, data, fn, s);
}
diff --git a/target/riscv/translate.c b/target/riscv/translate.c
index 832353be54..384ffcc0fa 100644
--- a/target/riscv/translate.c
+++ b/target/riscv/translate.c
@@ -95,6 +95,7 @@ typedef struct DisasContext {
int8_t lmul;
uint8_t sew;
uint8_t vta;
+ bool cfg_vta_all_1s;
target_ulong vstart;
bool vl_eq_vlmax;
uint8_t ntemp;
@@ -1093,6 +1094,7 @@ static void riscv_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs)
ctx->sew = FIELD_EX32(tb_flags, TB_FLAGS, SEW);
ctx->lmul = sextract32(FIELD_EX32(tb_flags, TB_FLAGS, LMUL), 0, 3);
ctx->vta = FIELD_EX32(tb_flags, TB_FLAGS, VTA) && cpu->cfg.rvv_ta_all_1s;
+ ctx->cfg_vta_all_1s = cpu->cfg.rvv_ta_all_1s;
ctx->vstart = env->vstart;
ctx->vl_eq_vlmax = FIELD_EX32(tb_flags, TB_FLAGS, VL_EQ_VLMAX);
ctx->misa_mxl_max = env->misa_mxl_max;
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 2248f0cbee..cb14c321ea 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -269,6 +269,9 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base,
uint32_t i, k;
uint32_t nf = vext_nf(desc);
uint32_t max_elems = vext_max_elems(desc, log2_esz);
+ uint32_t esz = 1 << log2_esz;
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+ uint32_t vta = vext_vta(desc);
for (i = env->vstart; i < env->vl; i++, env->vstart++) {
if (!vm && !vext_elem_mask(v0, i)) {
@@ -283,6 +286,18 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base,
}
}
env->vstart = 0;
+ /* set tail elements to 1s */
+ for (k = 0; k < nf; ++k) {
+ vext_set_elems_1s(vd, vta, (k * max_elems + env->vl) * esz,
+ (k * max_elems + max_elems) * esz);
+ }
+ if (nf * max_elems % total_elems != 0) {
+ uint32_t vlenb = env_archcpu(env)->cfg.vlen >> 3;
+ uint32_t registers_used =
+ ((nf * max_elems) * esz + (vlenb - 1)) / vlenb;
+ vext_set_elems_1s(vd, vta, (nf * max_elems) * esz,
+ registers_used * vlenb);
+ }
}
#define GEN_VEXT_LD_STRIDE(NAME, ETYPE, LOAD_FN) \
@@ -328,6 +343,9 @@ vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
uint32_t i, k;
uint32_t nf = vext_nf(desc);
uint32_t max_elems = vext_max_elems(desc, log2_esz);
+ uint32_t esz = 1 << log2_esz;
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+ uint32_t vta = vext_vta(desc);
/* load bytes from guest memory */
for (i = env->vstart; i < evl; i++, env->vstart++) {
@@ -339,6 +357,18 @@ vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
}
}
env->vstart = 0;
+ /* set tail elements to 1s */
+ for (k = 0; k < nf; ++k) {
+ vext_set_elems_1s(vd, vta, (k * max_elems + evl) * esz,
+ (k * max_elems + max_elems) * esz);
+ }
+ if (nf * max_elems % total_elems != 0) {
+ uint32_t vlenb = env_archcpu(env)->cfg.vlen >> 3;
+ uint32_t registers_used =
+ ((nf * max_elems) * esz + (vlenb - 1)) / vlenb;
+ vext_set_elems_1s(vd, vta, (nf * max_elems) * esz,
+ registers_used * vlenb);
+ }
}
/*
@@ -438,6 +468,9 @@ vext_ldst_index(void *vd, void *v0, target_ulong base,
uint32_t nf = vext_nf(desc);
uint32_t vm = vext_vm(desc);
uint32_t max_elems = vext_max_elems(desc, log2_esz);
+ uint32_t esz = 1 << log2_esz;
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+ uint32_t vta = vext_vta(desc);
/* load bytes from guest memory */
for (i = env->vstart; i < env->vl; i++, env->vstart++) {
@@ -453,6 +486,18 @@ vext_ldst_index(void *vd, void *v0, target_ulong base,
}
}
env->vstart = 0;
+ /* set tail elements to 1s */
+ for (k = 0; k < nf; ++k) {
+ vext_set_elems_1s(vd, vta, (k * max_elems + env->vl) * esz,
+ (k * max_elems + max_elems) * esz);
+ }
+ if (nf * max_elems % total_elems != 0) {
+ uint32_t vlenb = env_archcpu(env)->cfg.vlen >> 3;
+ uint32_t registers_used =
+ ((nf * max_elems) * esz + (vlenb - 1)) / vlenb;
+ vext_set_elems_1s(vd, vta, (nf * max_elems) * esz,
+ registers_used * vlenb);
+ }
}
#define GEN_VEXT_LD_INDEX(NAME, ETYPE, INDEX_FN, LOAD_FN) \
@@ -520,6 +565,9 @@ vext_ldff(void *vd, void *v0, target_ulong base,
uint32_t nf = vext_nf(desc);
uint32_t vm = vext_vm(desc);
uint32_t max_elems = vext_max_elems(desc, log2_esz);
+ uint32_t esz = 1 << log2_esz;
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+ uint32_t vta = vext_vta(desc);
target_ulong addr, offset, remain;
/* probe every access*/
@@ -575,6 +623,18 @@ ProbeSuccess:
}
}
env->vstart = 0;
+ /* set tail elements to 1s */
+ for (k = 0; k < nf; ++k) {
+ vext_set_elems_1s(vd, vta, (k * max_elems + env->vl) * esz,
+ (k * max_elems + max_elems) * esz);
+ }
+ if (nf * max_elems % total_elems != 0) {
+ uint32_t vlenb = env_archcpu(env)->cfg.vlen >> 3;
+ uint32_t registers_used =
+ ((nf * max_elems) * esz + (vlenb - 1)) / vlenb;
+ vext_set_elems_1s(vd, vta, (nf * max_elems) * esz,
+ registers_used * vlenb);
+ }
}
#define GEN_VEXT_LDFF(NAME, ETYPE, LOAD_FN) \
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 08/16] target/riscv: rvv: Add tail agnostic for vector integer shift instructions
@ 2022-05-13 11:50 ` ~eopxd
0 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-05-13 11:50 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/insn_trans/trans_rvv.c.inc | 3 ++-
target/riscv/vector_helper.c | 11 +++++++++++
2 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index 81f227f074..b03d459d84 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -1827,7 +1827,7 @@ do_opivx_gvec_shift(DisasContext *s, arg_rmrr *a, GVecGen2sFn32 *gvec_fn,
return false;
}
- if (a->vm && s->vl_eq_vlmax) {
+ if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
TCGv_i32 src1 = tcg_temp_new_i32();
tcg_gen_trunc_tl_i32(src1, get_gpr(s, a->rs1, EXT_NONE));
@@ -1886,6 +1886,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs1), \
vreg_ofs(s, a->rs2), cpu_env, \
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 3bcde37e28..9738c50222 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -1270,6 +1270,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(TS1); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -1281,6 +1284,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
*((TS1 *)vd + HS1(i)) = OP(s2, s1 & MASK); \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VEXT_SHIFT_VV(vsll_vv_b, uint8_t, uint8_t, H1, H1, DO_SLL, 0x7)
@@ -1305,6 +1310,10 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(TD); \
+ uint32_t total_elems = \
+ vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -1315,6 +1324,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
*((TD *)vd + HD(i)) = OP(s2, s1 & MASK); \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz);\
}
GEN_VEXT_SHIFT_VX(vsll_vx_b, uint8_t, int8_t, H1, H1, DO_SLL, 0x7)
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 05/16] target/riscv: rvv: Add tail agnostic for vv instructions
@ 2022-05-13 11:50 ` ~eopxd
0 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-05-13 11:50 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
According to v-spec, tail agnostic behavior can be either kept as
undisturbed or set elements' bits to all 1s. To distinguish the
difference of tail policies, QEMU should be able to simulate the tail
agnostic behavior as "set tail elements' bits to all 1s".
There are multiple possibility for agnostic elements according to
v-spec. The main intent of this patch-set tries to add option that
can distinguish between tail policies. Setting agnostic elements to
all 1s allows QEMU to express this.
This is the first commit regarding the optional tail agnostic
behavior. Follow-up commits will add this optional behavior
for all rvv instructions.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/cpu.h | 2 +
target/riscv/cpu_helper.c | 2 +
target/riscv/insn_trans/trans_rvv.c.inc | 3 +-
target/riscv/internals.h | 5 +-
target/riscv/translate.c | 2 +
target/riscv/vector_helper.c | 295 +++++++++++++-----------
6 files changed, 177 insertions(+), 132 deletions(-)
diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h
index fe6c9a2c92..61552408b5 100644
--- a/target/riscv/cpu.h
+++ b/target/riscv/cpu.h
@@ -405,6 +405,7 @@ struct RISCVCPUConfig {
bool ext_zhinxmin;
bool ext_zve32f;
bool ext_zve64f;
+ bool rvv_ta_all_1s;
uint32_t mvendorid;
uint64_t marchid;
@@ -557,6 +558,7 @@ FIELD(TB_FLAGS, XL, 20, 2)
/* If PointerMasking should be applied */
FIELD(TB_FLAGS, PM_MASK_ENABLED, 22, 1)
FIELD(TB_FLAGS, PM_BASE_ENABLED, 23, 1)
+FIELD(TB_FLAGS, VTA, 24, 1)
#ifdef TARGET_RISCV32
#define riscv_cpu_mxl(env) ((void)(env), MXL_RV32)
diff --git a/target/riscv/cpu_helper.c b/target/riscv/cpu_helper.c
index e1aa4f2097..c0641b63cc 100644
--- a/target/riscv/cpu_helper.c
+++ b/target/riscv/cpu_helper.c
@@ -65,6 +65,8 @@ void cpu_get_tb_cpu_state(CPURISCVState *env, target_ulong *pc,
flags = FIELD_DP32(flags, TB_FLAGS, LMUL,
FIELD_EX64(env->vtype, VTYPE, VLMUL));
flags = FIELD_DP32(flags, TB_FLAGS, VL_EQ_VLMAX, vl_eq_vlmax);
+ flags = FIELD_DP32(flags, TB_FLAGS, VTA,
+ FIELD_EX64(env->vtype, VTYPE, VTA));
} else {
flags = FIELD_DP32(flags, TB_FLAGS, VILL, 1);
}
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index 4d5dfa794a..efdf5d6d81 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -1227,7 +1227,7 @@ do_opivv_gvec(DisasContext *s, arg_rmrr *a, GVecGen3Fn *gvec_fn,
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
- if (a->vm && s->vl_eq_vlmax) {
+ if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
gvec_fn(s->sew, vreg_ofs(s, a->rd),
vreg_ofs(s, a->rs2), vreg_ofs(s, a->rs1),
MAXSZ(s), MAXSZ(s));
@@ -1236,6 +1236,7 @@ do_opivv_gvec(DisasContext *s, arg_rmrr *a, GVecGen3Fn *gvec_fn,
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),
vreg_ofs(s, a->rs1), vreg_ofs(s, a->rs2),
cpu_env, s->cfg_ptr->vlen / 8,
diff --git a/target/riscv/internals.h b/target/riscv/internals.h
index dbb322bfa7..512c6c30cf 100644
--- a/target/riscv/internals.h
+++ b/target/riscv/internals.h
@@ -24,8 +24,9 @@
/* share data between vector helpers and decode code */
FIELD(VDATA, VM, 0, 1)
FIELD(VDATA, LMUL, 1, 3)
-FIELD(VDATA, NF, 4, 4)
-FIELD(VDATA, WD, 4, 1)
+FIELD(VDATA, VTA, 4, 1)
+FIELD(VDATA, NF, 5, 4)
+FIELD(VDATA, WD, 5, 1)
/* float point classify helpers */
target_ulong fclass_h(uint64_t frs1);
diff --git a/target/riscv/translate.c b/target/riscv/translate.c
index 0cd1d9ee94..832353be54 100644
--- a/target/riscv/translate.c
+++ b/target/riscv/translate.c
@@ -94,6 +94,7 @@ typedef struct DisasContext {
*/
int8_t lmul;
uint8_t sew;
+ uint8_t vta;
target_ulong vstart;
bool vl_eq_vlmax;
uint8_t ntemp;
@@ -1091,6 +1092,7 @@ static void riscv_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs)
ctx->vill = FIELD_EX32(tb_flags, TB_FLAGS, VILL);
ctx->sew = FIELD_EX32(tb_flags, TB_FLAGS, SEW);
ctx->lmul = sextract32(FIELD_EX32(tb_flags, TB_FLAGS, LMUL), 0, 3);
+ ctx->vta = FIELD_EX32(tb_flags, TB_FLAGS, VTA) && cpu->cfg.rvv_ta_all_1s;
ctx->vstart = env->vstart;
ctx->vl_eq_vlmax = FIELD_EX32(tb_flags, TB_FLAGS, VL_EQ_VLMAX);
ctx->misa_mxl_max = env->misa_mxl_max;
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 3b79b9cbc2..2248f0cbee 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -122,6 +122,11 @@ static inline int32_t vext_lmul(uint32_t desc)
return sextract32(FIELD_EX32(simd_data(desc), VDATA, LMUL), 0, 3);
}
+static inline uint32_t vext_vta(uint32_t desc)
+{
+ return FIELD_EX32(simd_data(desc), VDATA, VTA);
+}
+
/*
* Get the maximum number of elements can be operated.
*
@@ -140,6 +145,20 @@ static inline uint32_t vext_max_elems(uint32_t desc, uint32_t log2_esz)
return scale < 0 ? vlenb >> -scale : vlenb << scale;
}
+/*
+ * Get number of total elements, including prestart, body and tail elements.
+ * Note that when LMUL < 1, the tail includes the elements past VLMAX that
+ * are held in the same vector register.
+ */
+static inline uint32_t vext_get_total_elems(CPURISCVState *env, uint32_t desc, uint32_t esz)
+{
+ uint32_t vlenb = simd_maxsz(desc);
+ uint32_t sew = 1 << FIELD_EX64(env->vtype, VTYPE, VSEW);
+ int8_t emul = ctzl(esz) - ctzl(sew) + vext_lmul(desc) < 0 ? 0 :
+ ctzl(esz) - ctzl(sew) + vext_lmul(desc);
+ return (vlenb << emul) / esz;
+}
+
static inline target_ulong adjust_addr(CPURISCVState *env, target_ulong addr)
{
return (addr & env->cur_pmmask) | env->cur_pmbase;
@@ -172,6 +191,20 @@ static void probe_pages(CPURISCVState *env, target_ulong addr,
}
}
+/* set agnostic elements to 1s */
+static void vext_set_elems_1s(void *base, uint32_t is_agnostic, uint32_t cnt,
+ uint32_t tot)
+{
+ if (is_agnostic == 0) {
+ /* policy undisturbed */
+ return;
+ }
+ if (tot - cnt == 0) {
+ return ;
+ }
+ memset(base + cnt, -1, tot - cnt);
+}
+
static inline void vext_set_elem_mask(void *v0, int index,
uint8_t value)
{
@@ -707,10 +740,12 @@ RVVCALL(OPIVV2, vsub_vv_d, OP_SSS_D, H8, H8, H8, DO_SUB)
static void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2,
CPURISCVState *env, uint32_t desc,
- opivv2_fn *fn)
+ opivv2_fn *fn, uint32_t esz)
{
uint32_t vm = vext_vm(desc);
uint32_t vl = env->vl;
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+ uint32_t vta = vext_vta(desc);
uint32_t i;
for (i = env->vstart; i < vl; i++) {
@@ -720,26 +755,28 @@ static void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2,
fn(vd, vs1, vs2, i);
}
env->vstart = 0;
+ /* set tail elements to 1s */
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz);
}
/* generate the helpers for OPIVV */
-#define GEN_VEXT_VV(NAME) \
+#define GEN_VEXT_VV(NAME, ESZ) \
void HELPER(NAME)(void *vd, void *v0, void *vs1, \
void *vs2, CPURISCVState *env, \
uint32_t desc) \
{ \
do_vext_vv(vd, v0, vs1, vs2, env, desc, \
- do_##NAME); \
+ do_##NAME, ESZ); \
}
-GEN_VEXT_VV(vadd_vv_b)
-GEN_VEXT_VV(vadd_vv_h)
-GEN_VEXT_VV(vadd_vv_w)
-GEN_VEXT_VV(vadd_vv_d)
-GEN_VEXT_VV(vsub_vv_b)
-GEN_VEXT_VV(vsub_vv_h)
-GEN_VEXT_VV(vsub_vv_w)
-GEN_VEXT_VV(vsub_vv_d)
+GEN_VEXT_VV(vadd_vv_b, 1)
+GEN_VEXT_VV(vadd_vv_h, 2)
+GEN_VEXT_VV(vadd_vv_w, 4)
+GEN_VEXT_VV(vadd_vv_d, 8)
+GEN_VEXT_VV(vsub_vv_b, 1)
+GEN_VEXT_VV(vsub_vv_h, 2)
+GEN_VEXT_VV(vsub_vv_w, 4)
+GEN_VEXT_VV(vsub_vv_d, 8)
typedef void opivx2_fn(void *vd, target_long s1, void *vs2, int i);
@@ -884,30 +921,30 @@ RVVCALL(OPIVV2, vwadd_wv_w, WOP_WSSS_W, H8, H4, H4, DO_ADD)
RVVCALL(OPIVV2, vwsub_wv_b, WOP_WSSS_B, H2, H1, H1, DO_SUB)
RVVCALL(OPIVV2, vwsub_wv_h, WOP_WSSS_H, H4, H2, H2, DO_SUB)
RVVCALL(OPIVV2, vwsub_wv_w, WOP_WSSS_W, H8, H4, H4, DO_SUB)
-GEN_VEXT_VV(vwaddu_vv_b)
-GEN_VEXT_VV(vwaddu_vv_h)
-GEN_VEXT_VV(vwaddu_vv_w)
-GEN_VEXT_VV(vwsubu_vv_b)
-GEN_VEXT_VV(vwsubu_vv_h)
-GEN_VEXT_VV(vwsubu_vv_w)
-GEN_VEXT_VV(vwadd_vv_b)
-GEN_VEXT_VV(vwadd_vv_h)
-GEN_VEXT_VV(vwadd_vv_w)
-GEN_VEXT_VV(vwsub_vv_b)
-GEN_VEXT_VV(vwsub_vv_h)
-GEN_VEXT_VV(vwsub_vv_w)
-GEN_VEXT_VV(vwaddu_wv_b)
-GEN_VEXT_VV(vwaddu_wv_h)
-GEN_VEXT_VV(vwaddu_wv_w)
-GEN_VEXT_VV(vwsubu_wv_b)
-GEN_VEXT_VV(vwsubu_wv_h)
-GEN_VEXT_VV(vwsubu_wv_w)
-GEN_VEXT_VV(vwadd_wv_b)
-GEN_VEXT_VV(vwadd_wv_h)
-GEN_VEXT_VV(vwadd_wv_w)
-GEN_VEXT_VV(vwsub_wv_b)
-GEN_VEXT_VV(vwsub_wv_h)
-GEN_VEXT_VV(vwsub_wv_w)
+GEN_VEXT_VV(vwaddu_vv_b, 2)
+GEN_VEXT_VV(vwaddu_vv_h, 4)
+GEN_VEXT_VV(vwaddu_vv_w, 8)
+GEN_VEXT_VV(vwsubu_vv_b, 2)
+GEN_VEXT_VV(vwsubu_vv_h, 4)
+GEN_VEXT_VV(vwsubu_vv_w, 8)
+GEN_VEXT_VV(vwadd_vv_b, 2)
+GEN_VEXT_VV(vwadd_vv_h, 4)
+GEN_VEXT_VV(vwadd_vv_w, 8)
+GEN_VEXT_VV(vwsub_vv_b, 2)
+GEN_VEXT_VV(vwsub_vv_h, 4)
+GEN_VEXT_VV(vwsub_vv_w, 8)
+GEN_VEXT_VV(vwaddu_wv_b, 2)
+GEN_VEXT_VV(vwaddu_wv_h, 4)
+GEN_VEXT_VV(vwaddu_wv_w, 8)
+GEN_VEXT_VV(vwsubu_wv_b, 2)
+GEN_VEXT_VV(vwsubu_wv_h, 4)
+GEN_VEXT_VV(vwsubu_wv_w, 8)
+GEN_VEXT_VV(vwadd_wv_b, 2)
+GEN_VEXT_VV(vwadd_wv_h, 4)
+GEN_VEXT_VV(vwadd_wv_w, 8)
+GEN_VEXT_VV(vwsub_wv_b, 2)
+GEN_VEXT_VV(vwsub_wv_h, 4)
+GEN_VEXT_VV(vwsub_wv_w, 8)
RVVCALL(OPIVX2, vwaddu_vx_b, WOP_UUU_B, H2, H1, DO_ADD)
RVVCALL(OPIVX2, vwaddu_vx_h, WOP_UUU_H, H4, H2, DO_ADD)
@@ -1086,18 +1123,18 @@ RVVCALL(OPIVV2, vxor_vv_b, OP_SSS_B, H1, H1, H1, DO_XOR)
RVVCALL(OPIVV2, vxor_vv_h, OP_SSS_H, H2, H2, H2, DO_XOR)
RVVCALL(OPIVV2, vxor_vv_w, OP_SSS_W, H4, H4, H4, DO_XOR)
RVVCALL(OPIVV2, vxor_vv_d, OP_SSS_D, H8, H8, H8, DO_XOR)
-GEN_VEXT_VV(vand_vv_b)
-GEN_VEXT_VV(vand_vv_h)
-GEN_VEXT_VV(vand_vv_w)
-GEN_VEXT_VV(vand_vv_d)
-GEN_VEXT_VV(vor_vv_b)
-GEN_VEXT_VV(vor_vv_h)
-GEN_VEXT_VV(vor_vv_w)
-GEN_VEXT_VV(vor_vv_d)
-GEN_VEXT_VV(vxor_vv_b)
-GEN_VEXT_VV(vxor_vv_h)
-GEN_VEXT_VV(vxor_vv_w)
-GEN_VEXT_VV(vxor_vv_d)
+GEN_VEXT_VV(vand_vv_b, 1)
+GEN_VEXT_VV(vand_vv_h, 2)
+GEN_VEXT_VV(vand_vv_w, 4)
+GEN_VEXT_VV(vand_vv_d, 8)
+GEN_VEXT_VV(vor_vv_b, 1)
+GEN_VEXT_VV(vor_vv_h, 2)
+GEN_VEXT_VV(vor_vv_w, 4)
+GEN_VEXT_VV(vor_vv_d, 8)
+GEN_VEXT_VV(vxor_vv_b, 1)
+GEN_VEXT_VV(vxor_vv_h, 2)
+GEN_VEXT_VV(vxor_vv_w, 4)
+GEN_VEXT_VV(vxor_vv_d, 8)
RVVCALL(OPIVX2, vand_vx_b, OP_SSS_B, H1, H1, DO_AND)
RVVCALL(OPIVX2, vand_vx_h, OP_SSS_H, H2, H2, DO_AND)
@@ -1343,22 +1380,22 @@ RVVCALL(OPIVV2, vmax_vv_b, OP_SSS_B, H1, H1, H1, DO_MAX)
RVVCALL(OPIVV2, vmax_vv_h, OP_SSS_H, H2, H2, H2, DO_MAX)
RVVCALL(OPIVV2, vmax_vv_w, OP_SSS_W, H4, H4, H4, DO_MAX)
RVVCALL(OPIVV2, vmax_vv_d, OP_SSS_D, H8, H8, H8, DO_MAX)
-GEN_VEXT_VV(vminu_vv_b)
-GEN_VEXT_VV(vminu_vv_h)
-GEN_VEXT_VV(vminu_vv_w)
-GEN_VEXT_VV(vminu_vv_d)
-GEN_VEXT_VV(vmin_vv_b)
-GEN_VEXT_VV(vmin_vv_h)
-GEN_VEXT_VV(vmin_vv_w)
-GEN_VEXT_VV(vmin_vv_d)
-GEN_VEXT_VV(vmaxu_vv_b)
-GEN_VEXT_VV(vmaxu_vv_h)
-GEN_VEXT_VV(vmaxu_vv_w)
-GEN_VEXT_VV(vmaxu_vv_d)
-GEN_VEXT_VV(vmax_vv_b)
-GEN_VEXT_VV(vmax_vv_h)
-GEN_VEXT_VV(vmax_vv_w)
-GEN_VEXT_VV(vmax_vv_d)
+GEN_VEXT_VV(vminu_vv_b, 1)
+GEN_VEXT_VV(vminu_vv_h, 2)
+GEN_VEXT_VV(vminu_vv_w, 4)
+GEN_VEXT_VV(vminu_vv_d, 8)
+GEN_VEXT_VV(vmin_vv_b, 1)
+GEN_VEXT_VV(vmin_vv_h, 2)
+GEN_VEXT_VV(vmin_vv_w, 4)
+GEN_VEXT_VV(vmin_vv_d, 8)
+GEN_VEXT_VV(vmaxu_vv_b, 1)
+GEN_VEXT_VV(vmaxu_vv_h, 2)
+GEN_VEXT_VV(vmaxu_vv_w, 4)
+GEN_VEXT_VV(vmaxu_vv_d, 8)
+GEN_VEXT_VV(vmax_vv_b, 1)
+GEN_VEXT_VV(vmax_vv_h, 2)
+GEN_VEXT_VV(vmax_vv_w, 4)
+GEN_VEXT_VV(vmax_vv_d, 8)
RVVCALL(OPIVX2, vminu_vx_b, OP_UUU_B, H1, H1, DO_MIN)
RVVCALL(OPIVX2, vminu_vx_h, OP_UUU_H, H2, H2, DO_MIN)
@@ -1399,10 +1436,10 @@ RVVCALL(OPIVV2, vmul_vv_b, OP_SSS_B, H1, H1, H1, DO_MUL)
RVVCALL(OPIVV2, vmul_vv_h, OP_SSS_H, H2, H2, H2, DO_MUL)
RVVCALL(OPIVV2, vmul_vv_w, OP_SSS_W, H4, H4, H4, DO_MUL)
RVVCALL(OPIVV2, vmul_vv_d, OP_SSS_D, H8, H8, H8, DO_MUL)
-GEN_VEXT_VV(vmul_vv_b)
-GEN_VEXT_VV(vmul_vv_h)
-GEN_VEXT_VV(vmul_vv_w)
-GEN_VEXT_VV(vmul_vv_d)
+GEN_VEXT_VV(vmul_vv_b, 1)
+GEN_VEXT_VV(vmul_vv_h, 2)
+GEN_VEXT_VV(vmul_vv_w, 4)
+GEN_VEXT_VV(vmul_vv_d, 8)
static int8_t do_mulh_b(int8_t s2, int8_t s1)
{
@@ -1506,18 +1543,18 @@ RVVCALL(OPIVV2, vmulhsu_vv_b, OP_SUS_B, H1, H1, H1, do_mulhsu_b)
RVVCALL(OPIVV2, vmulhsu_vv_h, OP_SUS_H, H2, H2, H2, do_mulhsu_h)
RVVCALL(OPIVV2, vmulhsu_vv_w, OP_SUS_W, H4, H4, H4, do_mulhsu_w)
RVVCALL(OPIVV2, vmulhsu_vv_d, OP_SUS_D, H8, H8, H8, do_mulhsu_d)
-GEN_VEXT_VV(vmulh_vv_b)
-GEN_VEXT_VV(vmulh_vv_h)
-GEN_VEXT_VV(vmulh_vv_w)
-GEN_VEXT_VV(vmulh_vv_d)
-GEN_VEXT_VV(vmulhu_vv_b)
-GEN_VEXT_VV(vmulhu_vv_h)
-GEN_VEXT_VV(vmulhu_vv_w)
-GEN_VEXT_VV(vmulhu_vv_d)
-GEN_VEXT_VV(vmulhsu_vv_b)
-GEN_VEXT_VV(vmulhsu_vv_h)
-GEN_VEXT_VV(vmulhsu_vv_w)
-GEN_VEXT_VV(vmulhsu_vv_d)
+GEN_VEXT_VV(vmulh_vv_b, 1)
+GEN_VEXT_VV(vmulh_vv_h, 2)
+GEN_VEXT_VV(vmulh_vv_w, 4)
+GEN_VEXT_VV(vmulh_vv_d, 8)
+GEN_VEXT_VV(vmulhu_vv_b, 1)
+GEN_VEXT_VV(vmulhu_vv_h, 2)
+GEN_VEXT_VV(vmulhu_vv_w, 4)
+GEN_VEXT_VV(vmulhu_vv_d, 8)
+GEN_VEXT_VV(vmulhsu_vv_b, 1)
+GEN_VEXT_VV(vmulhsu_vv_h, 2)
+GEN_VEXT_VV(vmulhsu_vv_w, 4)
+GEN_VEXT_VV(vmulhsu_vv_d, 8)
RVVCALL(OPIVX2, vmul_vx_b, OP_SSS_B, H1, H1, DO_MUL)
RVVCALL(OPIVX2, vmul_vx_h, OP_SSS_H, H2, H2, DO_MUL)
@@ -1576,22 +1613,22 @@ RVVCALL(OPIVV2, vrem_vv_b, OP_SSS_B, H1, H1, H1, DO_REM)
RVVCALL(OPIVV2, vrem_vv_h, OP_SSS_H, H2, H2, H2, DO_REM)
RVVCALL(OPIVV2, vrem_vv_w, OP_SSS_W, H4, H4, H4, DO_REM)
RVVCALL(OPIVV2, vrem_vv_d, OP_SSS_D, H8, H8, H8, DO_REM)
-GEN_VEXT_VV(vdivu_vv_b)
-GEN_VEXT_VV(vdivu_vv_h)
-GEN_VEXT_VV(vdivu_vv_w)
-GEN_VEXT_VV(vdivu_vv_d)
-GEN_VEXT_VV(vdiv_vv_b)
-GEN_VEXT_VV(vdiv_vv_h)
-GEN_VEXT_VV(vdiv_vv_w)
-GEN_VEXT_VV(vdiv_vv_d)
-GEN_VEXT_VV(vremu_vv_b)
-GEN_VEXT_VV(vremu_vv_h)
-GEN_VEXT_VV(vremu_vv_w)
-GEN_VEXT_VV(vremu_vv_d)
-GEN_VEXT_VV(vrem_vv_b)
-GEN_VEXT_VV(vrem_vv_h)
-GEN_VEXT_VV(vrem_vv_w)
-GEN_VEXT_VV(vrem_vv_d)
+GEN_VEXT_VV(vdivu_vv_b, 1)
+GEN_VEXT_VV(vdivu_vv_h, 2)
+GEN_VEXT_VV(vdivu_vv_w, 4)
+GEN_VEXT_VV(vdivu_vv_d, 8)
+GEN_VEXT_VV(vdiv_vv_b, 1)
+GEN_VEXT_VV(vdiv_vv_h, 2)
+GEN_VEXT_VV(vdiv_vv_w, 4)
+GEN_VEXT_VV(vdiv_vv_d, 8)
+GEN_VEXT_VV(vremu_vv_b, 1)
+GEN_VEXT_VV(vremu_vv_h, 2)
+GEN_VEXT_VV(vremu_vv_w, 4)
+GEN_VEXT_VV(vremu_vv_d, 8)
+GEN_VEXT_VV(vrem_vv_b, 1)
+GEN_VEXT_VV(vrem_vv_h, 2)
+GEN_VEXT_VV(vrem_vv_w, 4)
+GEN_VEXT_VV(vrem_vv_d, 8)
RVVCALL(OPIVX2, vdivu_vx_b, OP_UUU_B, H1, H1, DO_DIVU)
RVVCALL(OPIVX2, vdivu_vx_h, OP_UUU_H, H2, H2, DO_DIVU)
@@ -1636,15 +1673,15 @@ RVVCALL(OPIVV2, vwmulu_vv_w, WOP_UUU_W, H8, H4, H4, DO_MUL)
RVVCALL(OPIVV2, vwmulsu_vv_b, WOP_SUS_B, H2, H1, H1, DO_MUL)
RVVCALL(OPIVV2, vwmulsu_vv_h, WOP_SUS_H, H4, H2, H2, DO_MUL)
RVVCALL(OPIVV2, vwmulsu_vv_w, WOP_SUS_W, H8, H4, H4, DO_MUL)
-GEN_VEXT_VV(vwmul_vv_b)
-GEN_VEXT_VV(vwmul_vv_h)
-GEN_VEXT_VV(vwmul_vv_w)
-GEN_VEXT_VV(vwmulu_vv_b)
-GEN_VEXT_VV(vwmulu_vv_h)
-GEN_VEXT_VV(vwmulu_vv_w)
-GEN_VEXT_VV(vwmulsu_vv_b)
-GEN_VEXT_VV(vwmulsu_vv_h)
-GEN_VEXT_VV(vwmulsu_vv_w)
+GEN_VEXT_VV(vwmul_vv_b, 2)
+GEN_VEXT_VV(vwmul_vv_h, 4)
+GEN_VEXT_VV(vwmul_vv_w, 8)
+GEN_VEXT_VV(vwmulu_vv_b, 2)
+GEN_VEXT_VV(vwmulu_vv_h, 4)
+GEN_VEXT_VV(vwmulu_vv_w, 8)
+GEN_VEXT_VV(vwmulsu_vv_b, 2)
+GEN_VEXT_VV(vwmulsu_vv_h, 4)
+GEN_VEXT_VV(vwmulsu_vv_w, 8)
RVVCALL(OPIVX2, vwmul_vx_b, WOP_SSS_B, H2, H1, DO_MUL)
RVVCALL(OPIVX2, vwmul_vx_h, WOP_SSS_H, H4, H2, DO_MUL)
@@ -1695,22 +1732,22 @@ RVVCALL(OPIVV3, vnmsub_vv_b, OP_SSS_B, H1, H1, H1, DO_NMSUB)
RVVCALL(OPIVV3, vnmsub_vv_h, OP_SSS_H, H2, H2, H2, DO_NMSUB)
RVVCALL(OPIVV3, vnmsub_vv_w, OP_SSS_W, H4, H4, H4, DO_NMSUB)
RVVCALL(OPIVV3, vnmsub_vv_d, OP_SSS_D, H8, H8, H8, DO_NMSUB)
-GEN_VEXT_VV(vmacc_vv_b)
-GEN_VEXT_VV(vmacc_vv_h)
-GEN_VEXT_VV(vmacc_vv_w)
-GEN_VEXT_VV(vmacc_vv_d)
-GEN_VEXT_VV(vnmsac_vv_b)
-GEN_VEXT_VV(vnmsac_vv_h)
-GEN_VEXT_VV(vnmsac_vv_w)
-GEN_VEXT_VV(vnmsac_vv_d)
-GEN_VEXT_VV(vmadd_vv_b)
-GEN_VEXT_VV(vmadd_vv_h)
-GEN_VEXT_VV(vmadd_vv_w)
-GEN_VEXT_VV(vmadd_vv_d)
-GEN_VEXT_VV(vnmsub_vv_b)
-GEN_VEXT_VV(vnmsub_vv_h)
-GEN_VEXT_VV(vnmsub_vv_w)
-GEN_VEXT_VV(vnmsub_vv_d)
+GEN_VEXT_VV(vmacc_vv_b, 1)
+GEN_VEXT_VV(vmacc_vv_h, 2)
+GEN_VEXT_VV(vmacc_vv_w, 4)
+GEN_VEXT_VV(vmacc_vv_d, 8)
+GEN_VEXT_VV(vnmsac_vv_b, 1)
+GEN_VEXT_VV(vnmsac_vv_h, 2)
+GEN_VEXT_VV(vnmsac_vv_w, 4)
+GEN_VEXT_VV(vnmsac_vv_d, 8)
+GEN_VEXT_VV(vmadd_vv_b, 1)
+GEN_VEXT_VV(vmadd_vv_h, 2)
+GEN_VEXT_VV(vmadd_vv_w, 4)
+GEN_VEXT_VV(vmadd_vv_d, 8)
+GEN_VEXT_VV(vnmsub_vv_b, 1)
+GEN_VEXT_VV(vnmsub_vv_h, 2)
+GEN_VEXT_VV(vnmsub_vv_w, 4)
+GEN_VEXT_VV(vnmsub_vv_d, 8)
#define OPIVX3(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \
static void do_##NAME(void *vd, target_long s1, void *vs2, int i) \
@@ -1763,15 +1800,15 @@ RVVCALL(OPIVV3, vwmacc_vv_w, WOP_SSS_W, H8, H4, H4, DO_MACC)
RVVCALL(OPIVV3, vwmaccsu_vv_b, WOP_SSU_B, H2, H1, H1, DO_MACC)
RVVCALL(OPIVV3, vwmaccsu_vv_h, WOP_SSU_H, H4, H2, H2, DO_MACC)
RVVCALL(OPIVV3, vwmaccsu_vv_w, WOP_SSU_W, H8, H4, H4, DO_MACC)
-GEN_VEXT_VV(vwmaccu_vv_b)
-GEN_VEXT_VV(vwmaccu_vv_h)
-GEN_VEXT_VV(vwmaccu_vv_w)
-GEN_VEXT_VV(vwmacc_vv_b)
-GEN_VEXT_VV(vwmacc_vv_h)
-GEN_VEXT_VV(vwmacc_vv_w)
-GEN_VEXT_VV(vwmaccsu_vv_b)
-GEN_VEXT_VV(vwmaccsu_vv_h)
-GEN_VEXT_VV(vwmaccsu_vv_w)
+GEN_VEXT_VV(vwmaccu_vv_b, 2)
+GEN_VEXT_VV(vwmaccu_vv_h, 4)
+GEN_VEXT_VV(vwmaccu_vv_w, 8)
+GEN_VEXT_VV(vwmacc_vv_b, 2)
+GEN_VEXT_VV(vwmacc_vv_h, 4)
+GEN_VEXT_VV(vwmacc_vv_w, 8)
+GEN_VEXT_VV(vwmaccsu_vv_b, 2)
+GEN_VEXT_VV(vwmaccsu_vv_h, 4)
+GEN_VEXT_VV(vwmaccsu_vv_w, 8)
RVVCALL(OPIVX3, vwmaccu_vx_b, WOP_UUU_B, H2, H1, DO_MACC)
RVVCALL(OPIVX3, vwmaccu_vx_h, WOP_UUU_H, H4, H2, DO_MACC)
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 07/16] target/riscv: rvv: Add tail agnostic for vx, vvm, vxm instructions
@ 2022-05-13 11:50 ` ~eopxd
0 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-05-13 11:50 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
`vmadc` and `vmsbc` produces a mask value, they always operate with
a tail agnostic policy.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/insn_trans/trans_rvv.c.inc | 13 +-
target/riscv/internals.h | 5 +-
target/riscv/vector_helper.c | 314 +++++++++++++-----------
3 files changed, 190 insertions(+), 142 deletions(-)
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index 4da06b859b..81f227f074 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -1289,6 +1289,8 @@ static bool opivx_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, uint32_t vm,
data = FIELD_DP32(data, VDATA, VM, vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
+ data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);
desc = tcg_constant_i32(simd_desc(s->cfg_ptr->vlen / 8,
s->cfg_ptr->vlen / 8, data));
@@ -1324,7 +1326,7 @@ do_opivx_gvec(DisasContext *s, arg_rmrr *a, GVecGen2sFn *gvec_fn,
return false;
}
- if (a->vm && s->vl_eq_vlmax) {
+ if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
TCGv_i64 src1 = tcg_temp_new_i64();
tcg_gen_ext_tl_i64(src1, get_gpr(s, a->rs1, EXT_SIGN));
@@ -1454,6 +1456,8 @@ static bool opivi_trans(uint32_t vd, uint32_t imm, uint32_t vs2, uint32_t vm,
data = FIELD_DP32(data, VDATA, VM, vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
+ data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);
desc = tcg_constant_i32(simd_desc(s->cfg_ptr->vlen / 8,
s->cfg_ptr->vlen / 8, data));
@@ -1482,7 +1486,7 @@ do_opivi_gvec(DisasContext *s, arg_rmrr *a, GVecGen2iFn *gvec_fn,
return false;
}
- if (a->vm && s->vl_eq_vlmax) {
+ if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
gvec_fn(s->sew, vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2),
extract_imm(s, a->rs1, imm_mode), MAXSZ(s), MAXSZ(s));
mark_vs_dirty(s);
@@ -1536,6 +1540,7 @@ static bool do_opivv_widen(DisasContext *s, arg_rmrr *a,
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),
vreg_ofs(s, a->rs1),
vreg_ofs(s, a->rs2),
@@ -1617,6 +1622,7 @@ static bool do_opiwv_widen(DisasContext *s, arg_rmrr *a,
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),
vreg_ofs(s, a->rs1),
vreg_ofs(s, a->rs2),
@@ -1695,6 +1701,9 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
+ data = \
+ FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);\
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs1), \
vreg_ofs(s, a->rs2), cpu_env, \
diff --git a/target/riscv/internals.h b/target/riscv/internals.h
index 512c6c30cf..193ce57a6d 100644
--- a/target/riscv/internals.h
+++ b/target/riscv/internals.h
@@ -25,8 +25,9 @@
FIELD(VDATA, VM, 0, 1)
FIELD(VDATA, LMUL, 1, 3)
FIELD(VDATA, VTA, 4, 1)
-FIELD(VDATA, NF, 5, 4)
-FIELD(VDATA, WD, 5, 1)
+FIELD(VDATA, VTA_ALL_1S, 5, 1)
+FIELD(VDATA, NF, 6, 4)
+FIELD(VDATA, WD, 6, 1)
/* float point classify helpers */
target_ulong fclass_h(uint64_t frs1);
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index cb14c321ea..3bcde37e28 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -127,6 +127,11 @@ static inline uint32_t vext_vta(uint32_t desc)
return FIELD_EX32(simd_data(desc), VDATA, VTA);
}
+static inline uint32_t vext_vta_all_1s(uint32_t desc)
+{
+ return FIELD_EX32(simd_data(desc), VDATA, VTA_ALL_1S);
+}
+
/*
* Get the maximum number of elements can be operated.
*
@@ -866,10 +871,12 @@ RVVCALL(OPIVX2, vrsub_vx_d, OP_SSS_D, H8, H8, DO_RSUB)
static void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2,
CPURISCVState *env, uint32_t desc,
- opivx2_fn fn)
+ opivx2_fn fn, uint32_t esz)
{
uint32_t vm = vext_vm(desc);
uint32_t vl = env->vl;
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+ uint32_t vta = vext_vta(desc);
uint32_t i;
for (i = env->vstart; i < vl; i++) {
@@ -879,30 +886,32 @@ static void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2,
fn(vd, s1, vs2, i);
}
env->vstart = 0;
+ /* set tail elements to 1s */
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz);
}
/* generate the helpers for OPIVX */
-#define GEN_VEXT_VX(NAME) \
+#define GEN_VEXT_VX(NAME, ESZ) \
void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
void *vs2, CPURISCVState *env, \
uint32_t desc) \
{ \
do_vext_vx(vd, v0, s1, vs2, env, desc, \
- do_##NAME); \
-}
-
-GEN_VEXT_VX(vadd_vx_b)
-GEN_VEXT_VX(vadd_vx_h)
-GEN_VEXT_VX(vadd_vx_w)
-GEN_VEXT_VX(vadd_vx_d)
-GEN_VEXT_VX(vsub_vx_b)
-GEN_VEXT_VX(vsub_vx_h)
-GEN_VEXT_VX(vsub_vx_w)
-GEN_VEXT_VX(vsub_vx_d)
-GEN_VEXT_VX(vrsub_vx_b)
-GEN_VEXT_VX(vrsub_vx_h)
-GEN_VEXT_VX(vrsub_vx_w)
-GEN_VEXT_VX(vrsub_vx_d)
+ do_##NAME, ESZ); \
+}
+
+GEN_VEXT_VX(vadd_vx_b, 1)
+GEN_VEXT_VX(vadd_vx_h, 2)
+GEN_VEXT_VX(vadd_vx_w, 4)
+GEN_VEXT_VX(vadd_vx_d, 8)
+GEN_VEXT_VX(vsub_vx_b, 1)
+GEN_VEXT_VX(vsub_vx_h, 2)
+GEN_VEXT_VX(vsub_vx_w, 4)
+GEN_VEXT_VX(vsub_vx_d, 8)
+GEN_VEXT_VX(vrsub_vx_b, 1)
+GEN_VEXT_VX(vrsub_vx_h, 2)
+GEN_VEXT_VX(vrsub_vx_w, 4)
+GEN_VEXT_VX(vrsub_vx_d, 8)
void HELPER(vec_rsubs8)(void *d, void *a, uint64_t b, uint32_t desc)
{
@@ -1030,30 +1039,30 @@ RVVCALL(OPIVX2, vwadd_wx_w, WOP_WSSS_W, H8, H4, DO_ADD)
RVVCALL(OPIVX2, vwsub_wx_b, WOP_WSSS_B, H2, H1, DO_SUB)
RVVCALL(OPIVX2, vwsub_wx_h, WOP_WSSS_H, H4, H2, DO_SUB)
RVVCALL(OPIVX2, vwsub_wx_w, WOP_WSSS_W, H8, H4, DO_SUB)
-GEN_VEXT_VX(vwaddu_vx_b)
-GEN_VEXT_VX(vwaddu_vx_h)
-GEN_VEXT_VX(vwaddu_vx_w)
-GEN_VEXT_VX(vwsubu_vx_b)
-GEN_VEXT_VX(vwsubu_vx_h)
-GEN_VEXT_VX(vwsubu_vx_w)
-GEN_VEXT_VX(vwadd_vx_b)
-GEN_VEXT_VX(vwadd_vx_h)
-GEN_VEXT_VX(vwadd_vx_w)
-GEN_VEXT_VX(vwsub_vx_b)
-GEN_VEXT_VX(vwsub_vx_h)
-GEN_VEXT_VX(vwsub_vx_w)
-GEN_VEXT_VX(vwaddu_wx_b)
-GEN_VEXT_VX(vwaddu_wx_h)
-GEN_VEXT_VX(vwaddu_wx_w)
-GEN_VEXT_VX(vwsubu_wx_b)
-GEN_VEXT_VX(vwsubu_wx_h)
-GEN_VEXT_VX(vwsubu_wx_w)
-GEN_VEXT_VX(vwadd_wx_b)
-GEN_VEXT_VX(vwadd_wx_h)
-GEN_VEXT_VX(vwadd_wx_w)
-GEN_VEXT_VX(vwsub_wx_b)
-GEN_VEXT_VX(vwsub_wx_h)
-GEN_VEXT_VX(vwsub_wx_w)
+GEN_VEXT_VX(vwaddu_vx_b, 2)
+GEN_VEXT_VX(vwaddu_vx_h, 4)
+GEN_VEXT_VX(vwaddu_vx_w, 8)
+GEN_VEXT_VX(vwsubu_vx_b, 2)
+GEN_VEXT_VX(vwsubu_vx_h, 4)
+GEN_VEXT_VX(vwsubu_vx_w, 8)
+GEN_VEXT_VX(vwadd_vx_b, 2)
+GEN_VEXT_VX(vwadd_vx_h, 4)
+GEN_VEXT_VX(vwadd_vx_w, 8)
+GEN_VEXT_VX(vwsub_vx_b, 2)
+GEN_VEXT_VX(vwsub_vx_h, 4)
+GEN_VEXT_VX(vwsub_vx_w, 8)
+GEN_VEXT_VX(vwaddu_wx_b, 2)
+GEN_VEXT_VX(vwaddu_wx_h, 4)
+GEN_VEXT_VX(vwaddu_wx_w, 8)
+GEN_VEXT_VX(vwsubu_wx_b, 2)
+GEN_VEXT_VX(vwsubu_wx_h, 4)
+GEN_VEXT_VX(vwsubu_wx_w, 8)
+GEN_VEXT_VX(vwadd_wx_b, 2)
+GEN_VEXT_VX(vwadd_wx_h, 4)
+GEN_VEXT_VX(vwadd_wx_w, 8)
+GEN_VEXT_VX(vwsub_wx_b, 2)
+GEN_VEXT_VX(vwsub_wx_h, 4)
+GEN_VEXT_VX(vwsub_wx_w, 8)
/* Vector Integer Add-with-Carry / Subtract-with-Borrow Instructions */
#define DO_VADC(N, M, C) (N + M + C)
@@ -1064,6 +1073,10 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = \
+ vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -1074,6 +1087,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
*((ETYPE *)vd + H(i)) = DO_OP(s2, s1, carry); \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VEXT_VADC_VVM(vadc_vvm_b, uint8_t, H1, DO_VADC)
@@ -1091,6 +1106,9 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -1100,6 +1118,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
*((ETYPE *)vd + H(i)) = DO_OP(s2, (ETYPE)(target_long)s1, carry);\
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VEXT_VADC_VXM(vadc_vxm_b, uint8_t, H1, DO_VADC)
@@ -1122,6 +1142,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
{ \
uint32_t vl = env->vl; \
uint32_t vm = vext_vm(desc); \
+ uint32_t total_elems = env_archcpu(env)->cfg.vlen; \
+ uint32_t vta_all_1s = vext_vta_all_1s(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -1131,6 +1153,13 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
vext_set_elem_mask(vd, i, DO_OP(s2, s1, carry)); \
} \
env->vstart = 0; \
+ /* mask destination register are always tail-agnostic */ \
+ /* set tail elements to 1s */ \
+ if (vta_all_1s) { \
+ for (; i < total_elems; i++) { \
+ vext_set_elem_mask(vd, i, 1); \
+ } \
+ } \
}
GEN_VEXT_VMADC_VVM(vmadc_vvm_b, uint8_t, H1, DO_MADC)
@@ -1149,6 +1178,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
{ \
uint32_t vl = env->vl; \
uint32_t vm = vext_vm(desc); \
+ uint32_t total_elems = env_archcpu(env)->cfg.vlen; \
+ uint32_t vta_all_1s = vext_vta_all_1s(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -1158,6 +1189,13 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
DO_OP(s2, (ETYPE)(target_long)s1, carry)); \
} \
env->vstart = 0; \
+ /* mask destination register are always tail-agnostic */ \
+ /* set tail elements to 1s */ \
+ if (vta_all_1s) { \
+ for (; i < total_elems; i++) { \
+ vext_set_elem_mask(vd, i, 1); \
+ } \
+ } \
}
GEN_VEXT_VMADC_VXM(vmadc_vxm_b, uint8_t, H1, DO_MADC)
@@ -1208,18 +1246,18 @@ RVVCALL(OPIVX2, vxor_vx_b, OP_SSS_B, H1, H1, DO_XOR)
RVVCALL(OPIVX2, vxor_vx_h, OP_SSS_H, H2, H2, DO_XOR)
RVVCALL(OPIVX2, vxor_vx_w, OP_SSS_W, H4, H4, DO_XOR)
RVVCALL(OPIVX2, vxor_vx_d, OP_SSS_D, H8, H8, DO_XOR)
-GEN_VEXT_VX(vand_vx_b)
-GEN_VEXT_VX(vand_vx_h)
-GEN_VEXT_VX(vand_vx_w)
-GEN_VEXT_VX(vand_vx_d)
-GEN_VEXT_VX(vor_vx_b)
-GEN_VEXT_VX(vor_vx_h)
-GEN_VEXT_VX(vor_vx_w)
-GEN_VEXT_VX(vor_vx_d)
-GEN_VEXT_VX(vxor_vx_b)
-GEN_VEXT_VX(vxor_vx_h)
-GEN_VEXT_VX(vxor_vx_w)
-GEN_VEXT_VX(vxor_vx_d)
+GEN_VEXT_VX(vand_vx_b, 1)
+GEN_VEXT_VX(vand_vx_h, 2)
+GEN_VEXT_VX(vand_vx_w, 4)
+GEN_VEXT_VX(vand_vx_d, 8)
+GEN_VEXT_VX(vor_vx_b, 1)
+GEN_VEXT_VX(vor_vx_h, 2)
+GEN_VEXT_VX(vor_vx_w, 4)
+GEN_VEXT_VX(vor_vx_d, 8)
+GEN_VEXT_VX(vxor_vx_b, 1)
+GEN_VEXT_VX(vxor_vx_h, 2)
+GEN_VEXT_VX(vxor_vx_w, 4)
+GEN_VEXT_VX(vxor_vx_d, 8)
/* Vector Single-Width Bit Shift Instructions */
#define DO_SLL(N, M) (N << (M))
@@ -1473,22 +1511,22 @@ RVVCALL(OPIVX2, vmax_vx_b, OP_SSS_B, H1, H1, DO_MAX)
RVVCALL(OPIVX2, vmax_vx_h, OP_SSS_H, H2, H2, DO_MAX)
RVVCALL(OPIVX2, vmax_vx_w, OP_SSS_W, H4, H4, DO_MAX)
RVVCALL(OPIVX2, vmax_vx_d, OP_SSS_D, H8, H8, DO_MAX)
-GEN_VEXT_VX(vminu_vx_b)
-GEN_VEXT_VX(vminu_vx_h)
-GEN_VEXT_VX(vminu_vx_w)
-GEN_VEXT_VX(vminu_vx_d)
-GEN_VEXT_VX(vmin_vx_b)
-GEN_VEXT_VX(vmin_vx_h)
-GEN_VEXT_VX(vmin_vx_w)
-GEN_VEXT_VX(vmin_vx_d)
-GEN_VEXT_VX(vmaxu_vx_b)
-GEN_VEXT_VX(vmaxu_vx_h)
-GEN_VEXT_VX(vmaxu_vx_w)
-GEN_VEXT_VX(vmaxu_vx_d)
-GEN_VEXT_VX(vmax_vx_b)
-GEN_VEXT_VX(vmax_vx_h)
-GEN_VEXT_VX(vmax_vx_w)
-GEN_VEXT_VX(vmax_vx_d)
+GEN_VEXT_VX(vminu_vx_b, 1)
+GEN_VEXT_VX(vminu_vx_h, 2)
+GEN_VEXT_VX(vminu_vx_w, 4)
+GEN_VEXT_VX(vminu_vx_d, 8)
+GEN_VEXT_VX(vmin_vx_b, 1)
+GEN_VEXT_VX(vmin_vx_h, 2)
+GEN_VEXT_VX(vmin_vx_w, 4)
+GEN_VEXT_VX(vmin_vx_d, 8)
+GEN_VEXT_VX(vmaxu_vx_b, 1)
+GEN_VEXT_VX(vmaxu_vx_h, 2)
+GEN_VEXT_VX(vmaxu_vx_w, 4)
+GEN_VEXT_VX(vmaxu_vx_d, 8)
+GEN_VEXT_VX(vmax_vx_b, 1)
+GEN_VEXT_VX(vmax_vx_h, 2)
+GEN_VEXT_VX(vmax_vx_w, 4)
+GEN_VEXT_VX(vmax_vx_d, 8)
/* Vector Single-Width Integer Multiply Instructions */
#define DO_MUL(N, M) (N * M)
@@ -1632,22 +1670,22 @@ RVVCALL(OPIVX2, vmulhsu_vx_b, OP_SUS_B, H1, H1, do_mulhsu_b)
RVVCALL(OPIVX2, vmulhsu_vx_h, OP_SUS_H, H2, H2, do_mulhsu_h)
RVVCALL(OPIVX2, vmulhsu_vx_w, OP_SUS_W, H4, H4, do_mulhsu_w)
RVVCALL(OPIVX2, vmulhsu_vx_d, OP_SUS_D, H8, H8, do_mulhsu_d)
-GEN_VEXT_VX(vmul_vx_b)
-GEN_VEXT_VX(vmul_vx_h)
-GEN_VEXT_VX(vmul_vx_w)
-GEN_VEXT_VX(vmul_vx_d)
-GEN_VEXT_VX(vmulh_vx_b)
-GEN_VEXT_VX(vmulh_vx_h)
-GEN_VEXT_VX(vmulh_vx_w)
-GEN_VEXT_VX(vmulh_vx_d)
-GEN_VEXT_VX(vmulhu_vx_b)
-GEN_VEXT_VX(vmulhu_vx_h)
-GEN_VEXT_VX(vmulhu_vx_w)
-GEN_VEXT_VX(vmulhu_vx_d)
-GEN_VEXT_VX(vmulhsu_vx_b)
-GEN_VEXT_VX(vmulhsu_vx_h)
-GEN_VEXT_VX(vmulhsu_vx_w)
-GEN_VEXT_VX(vmulhsu_vx_d)
+GEN_VEXT_VX(vmul_vx_b, 1)
+GEN_VEXT_VX(vmul_vx_h, 2)
+GEN_VEXT_VX(vmul_vx_w, 4)
+GEN_VEXT_VX(vmul_vx_d, 8)
+GEN_VEXT_VX(vmulh_vx_b, 1)
+GEN_VEXT_VX(vmulh_vx_h, 2)
+GEN_VEXT_VX(vmulh_vx_w, 4)
+GEN_VEXT_VX(vmulh_vx_d, 8)
+GEN_VEXT_VX(vmulhu_vx_b, 1)
+GEN_VEXT_VX(vmulhu_vx_h, 2)
+GEN_VEXT_VX(vmulhu_vx_w, 4)
+GEN_VEXT_VX(vmulhu_vx_d, 8)
+GEN_VEXT_VX(vmulhsu_vx_b, 1)
+GEN_VEXT_VX(vmulhsu_vx_h, 2)
+GEN_VEXT_VX(vmulhsu_vx_w, 4)
+GEN_VEXT_VX(vmulhsu_vx_d, 8)
/* Vector Integer Divide Instructions */
#define DO_DIVU(N, M) (unlikely(M == 0) ? (__typeof(N))(-1) : N / M)
@@ -1706,22 +1744,22 @@ RVVCALL(OPIVX2, vrem_vx_b, OP_SSS_B, H1, H1, DO_REM)
RVVCALL(OPIVX2, vrem_vx_h, OP_SSS_H, H2, H2, DO_REM)
RVVCALL(OPIVX2, vrem_vx_w, OP_SSS_W, H4, H4, DO_REM)
RVVCALL(OPIVX2, vrem_vx_d, OP_SSS_D, H8, H8, DO_REM)
-GEN_VEXT_VX(vdivu_vx_b)
-GEN_VEXT_VX(vdivu_vx_h)
-GEN_VEXT_VX(vdivu_vx_w)
-GEN_VEXT_VX(vdivu_vx_d)
-GEN_VEXT_VX(vdiv_vx_b)
-GEN_VEXT_VX(vdiv_vx_h)
-GEN_VEXT_VX(vdiv_vx_w)
-GEN_VEXT_VX(vdiv_vx_d)
-GEN_VEXT_VX(vremu_vx_b)
-GEN_VEXT_VX(vremu_vx_h)
-GEN_VEXT_VX(vremu_vx_w)
-GEN_VEXT_VX(vremu_vx_d)
-GEN_VEXT_VX(vrem_vx_b)
-GEN_VEXT_VX(vrem_vx_h)
-GEN_VEXT_VX(vrem_vx_w)
-GEN_VEXT_VX(vrem_vx_d)
+GEN_VEXT_VX(vdivu_vx_b, 1)
+GEN_VEXT_VX(vdivu_vx_h, 2)
+GEN_VEXT_VX(vdivu_vx_w, 4)
+GEN_VEXT_VX(vdivu_vx_d, 8)
+GEN_VEXT_VX(vdiv_vx_b, 1)
+GEN_VEXT_VX(vdiv_vx_h, 2)
+GEN_VEXT_VX(vdiv_vx_w, 4)
+GEN_VEXT_VX(vdiv_vx_d, 8)
+GEN_VEXT_VX(vremu_vx_b, 1)
+GEN_VEXT_VX(vremu_vx_h, 2)
+GEN_VEXT_VX(vremu_vx_w, 4)
+GEN_VEXT_VX(vremu_vx_d, 8)
+GEN_VEXT_VX(vrem_vx_b, 1)
+GEN_VEXT_VX(vrem_vx_h, 2)
+GEN_VEXT_VX(vrem_vx_w, 4)
+GEN_VEXT_VX(vrem_vx_d, 8)
/* Vector Widening Integer Multiply Instructions */
RVVCALL(OPIVV2, vwmul_vv_b, WOP_SSS_B, H2, H1, H1, DO_MUL)
@@ -1752,15 +1790,15 @@ RVVCALL(OPIVX2, vwmulu_vx_w, WOP_UUU_W, H8, H4, DO_MUL)
RVVCALL(OPIVX2, vwmulsu_vx_b, WOP_SUS_B, H2, H1, DO_MUL)
RVVCALL(OPIVX2, vwmulsu_vx_h, WOP_SUS_H, H4, H2, DO_MUL)
RVVCALL(OPIVX2, vwmulsu_vx_w, WOP_SUS_W, H8, H4, DO_MUL)
-GEN_VEXT_VX(vwmul_vx_b)
-GEN_VEXT_VX(vwmul_vx_h)
-GEN_VEXT_VX(vwmul_vx_w)
-GEN_VEXT_VX(vwmulu_vx_b)
-GEN_VEXT_VX(vwmulu_vx_h)
-GEN_VEXT_VX(vwmulu_vx_w)
-GEN_VEXT_VX(vwmulsu_vx_b)
-GEN_VEXT_VX(vwmulsu_vx_h)
-GEN_VEXT_VX(vwmulsu_vx_w)
+GEN_VEXT_VX(vwmul_vx_b, 2)
+GEN_VEXT_VX(vwmul_vx_h, 4)
+GEN_VEXT_VX(vwmul_vx_w, 8)
+GEN_VEXT_VX(vwmulu_vx_b, 2)
+GEN_VEXT_VX(vwmulu_vx_h, 4)
+GEN_VEXT_VX(vwmulu_vx_w, 8)
+GEN_VEXT_VX(vwmulsu_vx_b, 2)
+GEN_VEXT_VX(vwmulsu_vx_h, 4)
+GEN_VEXT_VX(vwmulsu_vx_w, 8)
/* Vector Single-Width Integer Multiply-Add Instructions */
#define OPIVV3(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP) \
@@ -1833,22 +1871,22 @@ RVVCALL(OPIVX3, vnmsub_vx_b, OP_SSS_B, H1, H1, DO_NMSUB)
RVVCALL(OPIVX3, vnmsub_vx_h, OP_SSS_H, H2, H2, DO_NMSUB)
RVVCALL(OPIVX3, vnmsub_vx_w, OP_SSS_W, H4, H4, DO_NMSUB)
RVVCALL(OPIVX3, vnmsub_vx_d, OP_SSS_D, H8, H8, DO_NMSUB)
-GEN_VEXT_VX(vmacc_vx_b)
-GEN_VEXT_VX(vmacc_vx_h)
-GEN_VEXT_VX(vmacc_vx_w)
-GEN_VEXT_VX(vmacc_vx_d)
-GEN_VEXT_VX(vnmsac_vx_b)
-GEN_VEXT_VX(vnmsac_vx_h)
-GEN_VEXT_VX(vnmsac_vx_w)
-GEN_VEXT_VX(vnmsac_vx_d)
-GEN_VEXT_VX(vmadd_vx_b)
-GEN_VEXT_VX(vmadd_vx_h)
-GEN_VEXT_VX(vmadd_vx_w)
-GEN_VEXT_VX(vmadd_vx_d)
-GEN_VEXT_VX(vnmsub_vx_b)
-GEN_VEXT_VX(vnmsub_vx_h)
-GEN_VEXT_VX(vnmsub_vx_w)
-GEN_VEXT_VX(vnmsub_vx_d)
+GEN_VEXT_VX(vmacc_vx_b, 1)
+GEN_VEXT_VX(vmacc_vx_h, 2)
+GEN_VEXT_VX(vmacc_vx_w, 4)
+GEN_VEXT_VX(vmacc_vx_d, 8)
+GEN_VEXT_VX(vnmsac_vx_b, 1)
+GEN_VEXT_VX(vnmsac_vx_h, 2)
+GEN_VEXT_VX(vnmsac_vx_w, 4)
+GEN_VEXT_VX(vnmsac_vx_d, 8)
+GEN_VEXT_VX(vmadd_vx_b, 1)
+GEN_VEXT_VX(vmadd_vx_h, 2)
+GEN_VEXT_VX(vmadd_vx_w, 4)
+GEN_VEXT_VX(vmadd_vx_d, 8)
+GEN_VEXT_VX(vnmsub_vx_b, 1)
+GEN_VEXT_VX(vnmsub_vx_h, 2)
+GEN_VEXT_VX(vnmsub_vx_w, 4)
+GEN_VEXT_VX(vnmsub_vx_d, 8)
/* Vector Widening Integer Multiply-Add Instructions */
RVVCALL(OPIVV3, vwmaccu_vv_b, WOP_UUU_B, H2, H1, H1, DO_MACC)
@@ -1882,18 +1920,18 @@ RVVCALL(OPIVX3, vwmaccsu_vx_w, WOP_SSU_W, H8, H4, DO_MACC)
RVVCALL(OPIVX3, vwmaccus_vx_b, WOP_SUS_B, H2, H1, DO_MACC)
RVVCALL(OPIVX3, vwmaccus_vx_h, WOP_SUS_H, H4, H2, DO_MACC)
RVVCALL(OPIVX3, vwmaccus_vx_w, WOP_SUS_W, H8, H4, DO_MACC)
-GEN_VEXT_VX(vwmaccu_vx_b)
-GEN_VEXT_VX(vwmaccu_vx_h)
-GEN_VEXT_VX(vwmaccu_vx_w)
-GEN_VEXT_VX(vwmacc_vx_b)
-GEN_VEXT_VX(vwmacc_vx_h)
-GEN_VEXT_VX(vwmacc_vx_w)
-GEN_VEXT_VX(vwmaccsu_vx_b)
-GEN_VEXT_VX(vwmaccsu_vx_h)
-GEN_VEXT_VX(vwmaccsu_vx_w)
-GEN_VEXT_VX(vwmaccus_vx_b)
-GEN_VEXT_VX(vwmaccus_vx_h)
-GEN_VEXT_VX(vwmaccus_vx_w)
+GEN_VEXT_VX(vwmaccu_vx_b, 2)
+GEN_VEXT_VX(vwmaccu_vx_h, 4)
+GEN_VEXT_VX(vwmaccu_vx_w, 8)
+GEN_VEXT_VX(vwmacc_vx_b, 2)
+GEN_VEXT_VX(vwmacc_vx_h, 4)
+GEN_VEXT_VX(vwmacc_vx_w, 8)
+GEN_VEXT_VX(vwmaccsu_vx_b, 2)
+GEN_VEXT_VX(vwmaccsu_vx_h, 4)
+GEN_VEXT_VX(vwmaccsu_vx_w, 8)
+GEN_VEXT_VX(vwmaccus_vx_b, 2)
+GEN_VEXT_VX(vwmaccus_vx_h, 4)
+GEN_VEXT_VX(vwmaccus_vx_w, 8)
/* Vector Integer Merge and Move Instructions */
#define GEN_VEXT_VMV_VV(NAME, ETYPE, H) \
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 01/16] target/riscv: rvv: Prune redundant ESZ, DSZ parameter passed
@ 2022-05-13 11:50 ` ~eopxd
0 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-05-13 11:50 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
No functional change intended in this commit.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/vector_helper.c | 1132 +++++++++++++++++-----------------
1 file changed, 565 insertions(+), 567 deletions(-)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 576b14e5a3..85dd611cd9 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -710,7 +710,6 @@ RVVCALL(OPIVV2, vsub_vv_d, OP_SSS_D, H8, H8, H8, DO_SUB)
static void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2,
CPURISCVState *env, uint32_t desc,
- uint32_t esz, uint32_t dsz,
opivv2_fn *fn)
{
uint32_t vm = vext_vm(desc);
@@ -727,23 +726,23 @@ static void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2,
}
/* generate the helpers for OPIVV */
-#define GEN_VEXT_VV(NAME, ESZ, DSZ) \
+#define GEN_VEXT_VV(NAME) \
void HELPER(NAME)(void *vd, void *v0, void *vs1, \
void *vs2, CPURISCVState *env, \
uint32_t desc) \
{ \
- do_vext_vv(vd, v0, vs1, vs2, env, desc, ESZ, DSZ, \
+ do_vext_vv(vd, v0, vs1, vs2, env, desc, \
do_##NAME); \
}
-GEN_VEXT_VV(vadd_vv_b, 1, 1)
-GEN_VEXT_VV(vadd_vv_h, 2, 2)
-GEN_VEXT_VV(vadd_vv_w, 4, 4)
-GEN_VEXT_VV(vadd_vv_d, 8, 8)
-GEN_VEXT_VV(vsub_vv_b, 1, 1)
-GEN_VEXT_VV(vsub_vv_h, 2, 2)
-GEN_VEXT_VV(vsub_vv_w, 4, 4)
-GEN_VEXT_VV(vsub_vv_d, 8, 8)
+GEN_VEXT_VV(vadd_vv_b)
+GEN_VEXT_VV(vadd_vv_h)
+GEN_VEXT_VV(vadd_vv_w)
+GEN_VEXT_VV(vadd_vv_d)
+GEN_VEXT_VV(vsub_vv_b)
+GEN_VEXT_VV(vsub_vv_h)
+GEN_VEXT_VV(vsub_vv_w)
+GEN_VEXT_VV(vsub_vv_d)
typedef void opivx2_fn(void *vd, target_long s1, void *vs2, int i);
@@ -773,7 +772,6 @@ RVVCALL(OPIVX2, vrsub_vx_d, OP_SSS_D, H8, H8, DO_RSUB)
static void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2,
CPURISCVState *env, uint32_t desc,
- uint32_t esz, uint32_t dsz,
opivx2_fn fn)
{
uint32_t vm = vext_vm(desc);
@@ -790,27 +788,27 @@ static void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2,
}
/* generate the helpers for OPIVX */
-#define GEN_VEXT_VX(NAME, ESZ, DSZ) \
+#define GEN_VEXT_VX(NAME) \
void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
void *vs2, CPURISCVState *env, \
uint32_t desc) \
{ \
- do_vext_vx(vd, v0, s1, vs2, env, desc, ESZ, DSZ, \
+ do_vext_vx(vd, v0, s1, vs2, env, desc, \
do_##NAME); \
}
-GEN_VEXT_VX(vadd_vx_b, 1, 1)
-GEN_VEXT_VX(vadd_vx_h, 2, 2)
-GEN_VEXT_VX(vadd_vx_w, 4, 4)
-GEN_VEXT_VX(vadd_vx_d, 8, 8)
-GEN_VEXT_VX(vsub_vx_b, 1, 1)
-GEN_VEXT_VX(vsub_vx_h, 2, 2)
-GEN_VEXT_VX(vsub_vx_w, 4, 4)
-GEN_VEXT_VX(vsub_vx_d, 8, 8)
-GEN_VEXT_VX(vrsub_vx_b, 1, 1)
-GEN_VEXT_VX(vrsub_vx_h, 2, 2)
-GEN_VEXT_VX(vrsub_vx_w, 4, 4)
-GEN_VEXT_VX(vrsub_vx_d, 8, 8)
+GEN_VEXT_VX(vadd_vx_b)
+GEN_VEXT_VX(vadd_vx_h)
+GEN_VEXT_VX(vadd_vx_w)
+GEN_VEXT_VX(vadd_vx_d)
+GEN_VEXT_VX(vsub_vx_b)
+GEN_VEXT_VX(vsub_vx_h)
+GEN_VEXT_VX(vsub_vx_w)
+GEN_VEXT_VX(vsub_vx_d)
+GEN_VEXT_VX(vrsub_vx_b)
+GEN_VEXT_VX(vrsub_vx_h)
+GEN_VEXT_VX(vrsub_vx_w)
+GEN_VEXT_VX(vrsub_vx_d)
void HELPER(vec_rsubs8)(void *d, void *a, uint64_t b, uint32_t desc)
{
@@ -889,30 +887,30 @@ RVVCALL(OPIVV2, vwadd_wv_w, WOP_WSSS_W, H8, H4, H4, DO_ADD)
RVVCALL(OPIVV2, vwsub_wv_b, WOP_WSSS_B, H2, H1, H1, DO_SUB)
RVVCALL(OPIVV2, vwsub_wv_h, WOP_WSSS_H, H4, H2, H2, DO_SUB)
RVVCALL(OPIVV2, vwsub_wv_w, WOP_WSSS_W, H8, H4, H4, DO_SUB)
-GEN_VEXT_VV(vwaddu_vv_b, 1, 2)
-GEN_VEXT_VV(vwaddu_vv_h, 2, 4)
-GEN_VEXT_VV(vwaddu_vv_w, 4, 8)
-GEN_VEXT_VV(vwsubu_vv_b, 1, 2)
-GEN_VEXT_VV(vwsubu_vv_h, 2, 4)
-GEN_VEXT_VV(vwsubu_vv_w, 4, 8)
-GEN_VEXT_VV(vwadd_vv_b, 1, 2)
-GEN_VEXT_VV(vwadd_vv_h, 2, 4)
-GEN_VEXT_VV(vwadd_vv_w, 4, 8)
-GEN_VEXT_VV(vwsub_vv_b, 1, 2)
-GEN_VEXT_VV(vwsub_vv_h, 2, 4)
-GEN_VEXT_VV(vwsub_vv_w, 4, 8)
-GEN_VEXT_VV(vwaddu_wv_b, 1, 2)
-GEN_VEXT_VV(vwaddu_wv_h, 2, 4)
-GEN_VEXT_VV(vwaddu_wv_w, 4, 8)
-GEN_VEXT_VV(vwsubu_wv_b, 1, 2)
-GEN_VEXT_VV(vwsubu_wv_h, 2, 4)
-GEN_VEXT_VV(vwsubu_wv_w, 4, 8)
-GEN_VEXT_VV(vwadd_wv_b, 1, 2)
-GEN_VEXT_VV(vwadd_wv_h, 2, 4)
-GEN_VEXT_VV(vwadd_wv_w, 4, 8)
-GEN_VEXT_VV(vwsub_wv_b, 1, 2)
-GEN_VEXT_VV(vwsub_wv_h, 2, 4)
-GEN_VEXT_VV(vwsub_wv_w, 4, 8)
+GEN_VEXT_VV(vwaddu_vv_b)
+GEN_VEXT_VV(vwaddu_vv_h)
+GEN_VEXT_VV(vwaddu_vv_w)
+GEN_VEXT_VV(vwsubu_vv_b)
+GEN_VEXT_VV(vwsubu_vv_h)
+GEN_VEXT_VV(vwsubu_vv_w)
+GEN_VEXT_VV(vwadd_vv_b)
+GEN_VEXT_VV(vwadd_vv_h)
+GEN_VEXT_VV(vwadd_vv_w)
+GEN_VEXT_VV(vwsub_vv_b)
+GEN_VEXT_VV(vwsub_vv_h)
+GEN_VEXT_VV(vwsub_vv_w)
+GEN_VEXT_VV(vwaddu_wv_b)
+GEN_VEXT_VV(vwaddu_wv_h)
+GEN_VEXT_VV(vwaddu_wv_w)
+GEN_VEXT_VV(vwsubu_wv_b)
+GEN_VEXT_VV(vwsubu_wv_h)
+GEN_VEXT_VV(vwsubu_wv_w)
+GEN_VEXT_VV(vwadd_wv_b)
+GEN_VEXT_VV(vwadd_wv_h)
+GEN_VEXT_VV(vwadd_wv_w)
+GEN_VEXT_VV(vwsub_wv_b)
+GEN_VEXT_VV(vwsub_wv_h)
+GEN_VEXT_VV(vwsub_wv_w)
RVVCALL(OPIVX2, vwaddu_vx_b, WOP_UUU_B, H2, H1, DO_ADD)
RVVCALL(OPIVX2, vwaddu_vx_h, WOP_UUU_H, H4, H2, DO_ADD)
@@ -938,30 +936,30 @@ RVVCALL(OPIVX2, vwadd_wx_w, WOP_WSSS_W, H8, H4, DO_ADD)
RVVCALL(OPIVX2, vwsub_wx_b, WOP_WSSS_B, H2, H1, DO_SUB)
RVVCALL(OPIVX2, vwsub_wx_h, WOP_WSSS_H, H4, H2, DO_SUB)
RVVCALL(OPIVX2, vwsub_wx_w, WOP_WSSS_W, H8, H4, DO_SUB)
-GEN_VEXT_VX(vwaddu_vx_b, 1, 2)
-GEN_VEXT_VX(vwaddu_vx_h, 2, 4)
-GEN_VEXT_VX(vwaddu_vx_w, 4, 8)
-GEN_VEXT_VX(vwsubu_vx_b, 1, 2)
-GEN_VEXT_VX(vwsubu_vx_h, 2, 4)
-GEN_VEXT_VX(vwsubu_vx_w, 4, 8)
-GEN_VEXT_VX(vwadd_vx_b, 1, 2)
-GEN_VEXT_VX(vwadd_vx_h, 2, 4)
-GEN_VEXT_VX(vwadd_vx_w, 4, 8)
-GEN_VEXT_VX(vwsub_vx_b, 1, 2)
-GEN_VEXT_VX(vwsub_vx_h, 2, 4)
-GEN_VEXT_VX(vwsub_vx_w, 4, 8)
-GEN_VEXT_VX(vwaddu_wx_b, 1, 2)
-GEN_VEXT_VX(vwaddu_wx_h, 2, 4)
-GEN_VEXT_VX(vwaddu_wx_w, 4, 8)
-GEN_VEXT_VX(vwsubu_wx_b, 1, 2)
-GEN_VEXT_VX(vwsubu_wx_h, 2, 4)
-GEN_VEXT_VX(vwsubu_wx_w, 4, 8)
-GEN_VEXT_VX(vwadd_wx_b, 1, 2)
-GEN_VEXT_VX(vwadd_wx_h, 2, 4)
-GEN_VEXT_VX(vwadd_wx_w, 4, 8)
-GEN_VEXT_VX(vwsub_wx_b, 1, 2)
-GEN_VEXT_VX(vwsub_wx_h, 2, 4)
-GEN_VEXT_VX(vwsub_wx_w, 4, 8)
+GEN_VEXT_VX(vwaddu_vx_b)
+GEN_VEXT_VX(vwaddu_vx_h)
+GEN_VEXT_VX(vwaddu_vx_w)
+GEN_VEXT_VX(vwsubu_vx_b)
+GEN_VEXT_VX(vwsubu_vx_h)
+GEN_VEXT_VX(vwsubu_vx_w)
+GEN_VEXT_VX(vwadd_vx_b)
+GEN_VEXT_VX(vwadd_vx_h)
+GEN_VEXT_VX(vwadd_vx_w)
+GEN_VEXT_VX(vwsub_vx_b)
+GEN_VEXT_VX(vwsub_vx_h)
+GEN_VEXT_VX(vwsub_vx_w)
+GEN_VEXT_VX(vwaddu_wx_b)
+GEN_VEXT_VX(vwaddu_wx_h)
+GEN_VEXT_VX(vwaddu_wx_w)
+GEN_VEXT_VX(vwsubu_wx_b)
+GEN_VEXT_VX(vwsubu_wx_h)
+GEN_VEXT_VX(vwsubu_wx_w)
+GEN_VEXT_VX(vwadd_wx_b)
+GEN_VEXT_VX(vwadd_wx_h)
+GEN_VEXT_VX(vwadd_wx_w)
+GEN_VEXT_VX(vwsub_wx_b)
+GEN_VEXT_VX(vwsub_wx_h)
+GEN_VEXT_VX(vwsub_wx_w)
/* Vector Integer Add-with-Carry / Subtract-with-Borrow Instructions */
#define DO_VADC(N, M, C) (N + M + C)
@@ -1091,18 +1089,18 @@ RVVCALL(OPIVV2, vxor_vv_b, OP_SSS_B, H1, H1, H1, DO_XOR)
RVVCALL(OPIVV2, vxor_vv_h, OP_SSS_H, H2, H2, H2, DO_XOR)
RVVCALL(OPIVV2, vxor_vv_w, OP_SSS_W, H4, H4, H4, DO_XOR)
RVVCALL(OPIVV2, vxor_vv_d, OP_SSS_D, H8, H8, H8, DO_XOR)
-GEN_VEXT_VV(vand_vv_b, 1, 1)
-GEN_VEXT_VV(vand_vv_h, 2, 2)
-GEN_VEXT_VV(vand_vv_w, 4, 4)
-GEN_VEXT_VV(vand_vv_d, 8, 8)
-GEN_VEXT_VV(vor_vv_b, 1, 1)
-GEN_VEXT_VV(vor_vv_h, 2, 2)
-GEN_VEXT_VV(vor_vv_w, 4, 4)
-GEN_VEXT_VV(vor_vv_d, 8, 8)
-GEN_VEXT_VV(vxor_vv_b, 1, 1)
-GEN_VEXT_VV(vxor_vv_h, 2, 2)
-GEN_VEXT_VV(vxor_vv_w, 4, 4)
-GEN_VEXT_VV(vxor_vv_d, 8, 8)
+GEN_VEXT_VV(vand_vv_b)
+GEN_VEXT_VV(vand_vv_h)
+GEN_VEXT_VV(vand_vv_w)
+GEN_VEXT_VV(vand_vv_d)
+GEN_VEXT_VV(vor_vv_b)
+GEN_VEXT_VV(vor_vv_h)
+GEN_VEXT_VV(vor_vv_w)
+GEN_VEXT_VV(vor_vv_d)
+GEN_VEXT_VV(vxor_vv_b)
+GEN_VEXT_VV(vxor_vv_h)
+GEN_VEXT_VV(vxor_vv_w)
+GEN_VEXT_VV(vxor_vv_d)
RVVCALL(OPIVX2, vand_vx_b, OP_SSS_B, H1, H1, DO_AND)
RVVCALL(OPIVX2, vand_vx_h, OP_SSS_H, H2, H2, DO_AND)
@@ -1116,18 +1114,18 @@ RVVCALL(OPIVX2, vxor_vx_b, OP_SSS_B, H1, H1, DO_XOR)
RVVCALL(OPIVX2, vxor_vx_h, OP_SSS_H, H2, H2, DO_XOR)
RVVCALL(OPIVX2, vxor_vx_w, OP_SSS_W, H4, H4, DO_XOR)
RVVCALL(OPIVX2, vxor_vx_d, OP_SSS_D, H8, H8, DO_XOR)
-GEN_VEXT_VX(vand_vx_b, 1, 1)
-GEN_VEXT_VX(vand_vx_h, 2, 2)
-GEN_VEXT_VX(vand_vx_w, 4, 4)
-GEN_VEXT_VX(vand_vx_d, 8, 8)
-GEN_VEXT_VX(vor_vx_b, 1, 1)
-GEN_VEXT_VX(vor_vx_h, 2, 2)
-GEN_VEXT_VX(vor_vx_w, 4, 4)
-GEN_VEXT_VX(vor_vx_d, 8, 8)
-GEN_VEXT_VX(vxor_vx_b, 1, 1)
-GEN_VEXT_VX(vxor_vx_h, 2, 2)
-GEN_VEXT_VX(vxor_vx_w, 4, 4)
-GEN_VEXT_VX(vxor_vx_d, 8, 8)
+GEN_VEXT_VX(vand_vx_b)
+GEN_VEXT_VX(vand_vx_h)
+GEN_VEXT_VX(vand_vx_w)
+GEN_VEXT_VX(vand_vx_d)
+GEN_VEXT_VX(vor_vx_b)
+GEN_VEXT_VX(vor_vx_h)
+GEN_VEXT_VX(vor_vx_w)
+GEN_VEXT_VX(vor_vx_d)
+GEN_VEXT_VX(vxor_vx_b)
+GEN_VEXT_VX(vxor_vx_h)
+GEN_VEXT_VX(vxor_vx_w)
+GEN_VEXT_VX(vxor_vx_d)
/* Vector Single-Width Bit Shift Instructions */
#define DO_SLL(N, M) (N << (M))
@@ -1348,22 +1346,22 @@ RVVCALL(OPIVV2, vmax_vv_b, OP_SSS_B, H1, H1, H1, DO_MAX)
RVVCALL(OPIVV2, vmax_vv_h, OP_SSS_H, H2, H2, H2, DO_MAX)
RVVCALL(OPIVV2, vmax_vv_w, OP_SSS_W, H4, H4, H4, DO_MAX)
RVVCALL(OPIVV2, vmax_vv_d, OP_SSS_D, H8, H8, H8, DO_MAX)
-GEN_VEXT_VV(vminu_vv_b, 1, 1)
-GEN_VEXT_VV(vminu_vv_h, 2, 2)
-GEN_VEXT_VV(vminu_vv_w, 4, 4)
-GEN_VEXT_VV(vminu_vv_d, 8, 8)
-GEN_VEXT_VV(vmin_vv_b, 1, 1)
-GEN_VEXT_VV(vmin_vv_h, 2, 2)
-GEN_VEXT_VV(vmin_vv_w, 4, 4)
-GEN_VEXT_VV(vmin_vv_d, 8, 8)
-GEN_VEXT_VV(vmaxu_vv_b, 1, 1)
-GEN_VEXT_VV(vmaxu_vv_h, 2, 2)
-GEN_VEXT_VV(vmaxu_vv_w, 4, 4)
-GEN_VEXT_VV(vmaxu_vv_d, 8, 8)
-GEN_VEXT_VV(vmax_vv_b, 1, 1)
-GEN_VEXT_VV(vmax_vv_h, 2, 2)
-GEN_VEXT_VV(vmax_vv_w, 4, 4)
-GEN_VEXT_VV(vmax_vv_d, 8, 8)
+GEN_VEXT_VV(vminu_vv_b)
+GEN_VEXT_VV(vminu_vv_h)
+GEN_VEXT_VV(vminu_vv_w)
+GEN_VEXT_VV(vminu_vv_d)
+GEN_VEXT_VV(vmin_vv_b)
+GEN_VEXT_VV(vmin_vv_h)
+GEN_VEXT_VV(vmin_vv_w)
+GEN_VEXT_VV(vmin_vv_d)
+GEN_VEXT_VV(vmaxu_vv_b)
+GEN_VEXT_VV(vmaxu_vv_h)
+GEN_VEXT_VV(vmaxu_vv_w)
+GEN_VEXT_VV(vmaxu_vv_d)
+GEN_VEXT_VV(vmax_vv_b)
+GEN_VEXT_VV(vmax_vv_h)
+GEN_VEXT_VV(vmax_vv_w)
+GEN_VEXT_VV(vmax_vv_d)
RVVCALL(OPIVX2, vminu_vx_b, OP_UUU_B, H1, H1, DO_MIN)
RVVCALL(OPIVX2, vminu_vx_h, OP_UUU_H, H2, H2, DO_MIN)
@@ -1381,22 +1379,22 @@ RVVCALL(OPIVX2, vmax_vx_b, OP_SSS_B, H1, H1, DO_MAX)
RVVCALL(OPIVX2, vmax_vx_h, OP_SSS_H, H2, H2, DO_MAX)
RVVCALL(OPIVX2, vmax_vx_w, OP_SSS_W, H4, H4, DO_MAX)
RVVCALL(OPIVX2, vmax_vx_d, OP_SSS_D, H8, H8, DO_MAX)
-GEN_VEXT_VX(vminu_vx_b, 1, 1)
-GEN_VEXT_VX(vminu_vx_h, 2, 2)
-GEN_VEXT_VX(vminu_vx_w, 4, 4)
-GEN_VEXT_VX(vminu_vx_d, 8, 8)
-GEN_VEXT_VX(vmin_vx_b, 1, 1)
-GEN_VEXT_VX(vmin_vx_h, 2, 2)
-GEN_VEXT_VX(vmin_vx_w, 4, 4)
-GEN_VEXT_VX(vmin_vx_d, 8, 8)
-GEN_VEXT_VX(vmaxu_vx_b, 1, 1)
-GEN_VEXT_VX(vmaxu_vx_h, 2, 2)
-GEN_VEXT_VX(vmaxu_vx_w, 4, 4)
-GEN_VEXT_VX(vmaxu_vx_d, 8, 8)
-GEN_VEXT_VX(vmax_vx_b, 1, 1)
-GEN_VEXT_VX(vmax_vx_h, 2, 2)
-GEN_VEXT_VX(vmax_vx_w, 4, 4)
-GEN_VEXT_VX(vmax_vx_d, 8, 8)
+GEN_VEXT_VX(vminu_vx_b)
+GEN_VEXT_VX(vminu_vx_h)
+GEN_VEXT_VX(vminu_vx_w)
+GEN_VEXT_VX(vminu_vx_d)
+GEN_VEXT_VX(vmin_vx_b)
+GEN_VEXT_VX(vmin_vx_h)
+GEN_VEXT_VX(vmin_vx_w)
+GEN_VEXT_VX(vmin_vx_d)
+GEN_VEXT_VX(vmaxu_vx_b)
+GEN_VEXT_VX(vmaxu_vx_h)
+GEN_VEXT_VX(vmaxu_vx_w)
+GEN_VEXT_VX(vmaxu_vx_d)
+GEN_VEXT_VX(vmax_vx_b)
+GEN_VEXT_VX(vmax_vx_h)
+GEN_VEXT_VX(vmax_vx_w)
+GEN_VEXT_VX(vmax_vx_d)
/* Vector Single-Width Integer Multiply Instructions */
#define DO_MUL(N, M) (N * M)
@@ -1404,10 +1402,10 @@ RVVCALL(OPIVV2, vmul_vv_b, OP_SSS_B, H1, H1, H1, DO_MUL)
RVVCALL(OPIVV2, vmul_vv_h, OP_SSS_H, H2, H2, H2, DO_MUL)
RVVCALL(OPIVV2, vmul_vv_w, OP_SSS_W, H4, H4, H4, DO_MUL)
RVVCALL(OPIVV2, vmul_vv_d, OP_SSS_D, H8, H8, H8, DO_MUL)
-GEN_VEXT_VV(vmul_vv_b, 1, 1)
-GEN_VEXT_VV(vmul_vv_h, 2, 2)
-GEN_VEXT_VV(vmul_vv_w, 4, 4)
-GEN_VEXT_VV(vmul_vv_d, 8, 8)
+GEN_VEXT_VV(vmul_vv_b)
+GEN_VEXT_VV(vmul_vv_h)
+GEN_VEXT_VV(vmul_vv_w)
+GEN_VEXT_VV(vmul_vv_d)
static int8_t do_mulh_b(int8_t s2, int8_t s1)
{
@@ -1511,18 +1509,18 @@ RVVCALL(OPIVV2, vmulhsu_vv_b, OP_SUS_B, H1, H1, H1, do_mulhsu_b)
RVVCALL(OPIVV2, vmulhsu_vv_h, OP_SUS_H, H2, H2, H2, do_mulhsu_h)
RVVCALL(OPIVV2, vmulhsu_vv_w, OP_SUS_W, H4, H4, H4, do_mulhsu_w)
RVVCALL(OPIVV2, vmulhsu_vv_d, OP_SUS_D, H8, H8, H8, do_mulhsu_d)
-GEN_VEXT_VV(vmulh_vv_b, 1, 1)
-GEN_VEXT_VV(vmulh_vv_h, 2, 2)
-GEN_VEXT_VV(vmulh_vv_w, 4, 4)
-GEN_VEXT_VV(vmulh_vv_d, 8, 8)
-GEN_VEXT_VV(vmulhu_vv_b, 1, 1)
-GEN_VEXT_VV(vmulhu_vv_h, 2, 2)
-GEN_VEXT_VV(vmulhu_vv_w, 4, 4)
-GEN_VEXT_VV(vmulhu_vv_d, 8, 8)
-GEN_VEXT_VV(vmulhsu_vv_b, 1, 1)
-GEN_VEXT_VV(vmulhsu_vv_h, 2, 2)
-GEN_VEXT_VV(vmulhsu_vv_w, 4, 4)
-GEN_VEXT_VV(vmulhsu_vv_d, 8, 8)
+GEN_VEXT_VV(vmulh_vv_b)
+GEN_VEXT_VV(vmulh_vv_h)
+GEN_VEXT_VV(vmulh_vv_w)
+GEN_VEXT_VV(vmulh_vv_d)
+GEN_VEXT_VV(vmulhu_vv_b)
+GEN_VEXT_VV(vmulhu_vv_h)
+GEN_VEXT_VV(vmulhu_vv_w)
+GEN_VEXT_VV(vmulhu_vv_d)
+GEN_VEXT_VV(vmulhsu_vv_b)
+GEN_VEXT_VV(vmulhsu_vv_h)
+GEN_VEXT_VV(vmulhsu_vv_w)
+GEN_VEXT_VV(vmulhsu_vv_d)
RVVCALL(OPIVX2, vmul_vx_b, OP_SSS_B, H1, H1, DO_MUL)
RVVCALL(OPIVX2, vmul_vx_h, OP_SSS_H, H2, H2, DO_MUL)
@@ -1540,22 +1538,22 @@ RVVCALL(OPIVX2, vmulhsu_vx_b, OP_SUS_B, H1, H1, do_mulhsu_b)
RVVCALL(OPIVX2, vmulhsu_vx_h, OP_SUS_H, H2, H2, do_mulhsu_h)
RVVCALL(OPIVX2, vmulhsu_vx_w, OP_SUS_W, H4, H4, do_mulhsu_w)
RVVCALL(OPIVX2, vmulhsu_vx_d, OP_SUS_D, H8, H8, do_mulhsu_d)
-GEN_VEXT_VX(vmul_vx_b, 1, 1)
-GEN_VEXT_VX(vmul_vx_h, 2, 2)
-GEN_VEXT_VX(vmul_vx_w, 4, 4)
-GEN_VEXT_VX(vmul_vx_d, 8, 8)
-GEN_VEXT_VX(vmulh_vx_b, 1, 1)
-GEN_VEXT_VX(vmulh_vx_h, 2, 2)
-GEN_VEXT_VX(vmulh_vx_w, 4, 4)
-GEN_VEXT_VX(vmulh_vx_d, 8, 8)
-GEN_VEXT_VX(vmulhu_vx_b, 1, 1)
-GEN_VEXT_VX(vmulhu_vx_h, 2, 2)
-GEN_VEXT_VX(vmulhu_vx_w, 4, 4)
-GEN_VEXT_VX(vmulhu_vx_d, 8, 8)
-GEN_VEXT_VX(vmulhsu_vx_b, 1, 1)
-GEN_VEXT_VX(vmulhsu_vx_h, 2, 2)
-GEN_VEXT_VX(vmulhsu_vx_w, 4, 4)
-GEN_VEXT_VX(vmulhsu_vx_d, 8, 8)
+GEN_VEXT_VX(vmul_vx_b)
+GEN_VEXT_VX(vmul_vx_h)
+GEN_VEXT_VX(vmul_vx_w)
+GEN_VEXT_VX(vmul_vx_d)
+GEN_VEXT_VX(vmulh_vx_b)
+GEN_VEXT_VX(vmulh_vx_h)
+GEN_VEXT_VX(vmulh_vx_w)
+GEN_VEXT_VX(vmulh_vx_d)
+GEN_VEXT_VX(vmulhu_vx_b)
+GEN_VEXT_VX(vmulhu_vx_h)
+GEN_VEXT_VX(vmulhu_vx_w)
+GEN_VEXT_VX(vmulhu_vx_d)
+GEN_VEXT_VX(vmulhsu_vx_b)
+GEN_VEXT_VX(vmulhsu_vx_h)
+GEN_VEXT_VX(vmulhsu_vx_w)
+GEN_VEXT_VX(vmulhsu_vx_d)
/* Vector Integer Divide Instructions */
#define DO_DIVU(N, M) (unlikely(M == 0) ? (__typeof(N))(-1) : N / M)
@@ -1581,22 +1579,22 @@ RVVCALL(OPIVV2, vrem_vv_b, OP_SSS_B, H1, H1, H1, DO_REM)
RVVCALL(OPIVV2, vrem_vv_h, OP_SSS_H, H2, H2, H2, DO_REM)
RVVCALL(OPIVV2, vrem_vv_w, OP_SSS_W, H4, H4, H4, DO_REM)
RVVCALL(OPIVV2, vrem_vv_d, OP_SSS_D, H8, H8, H8, DO_REM)
-GEN_VEXT_VV(vdivu_vv_b, 1, 1)
-GEN_VEXT_VV(vdivu_vv_h, 2, 2)
-GEN_VEXT_VV(vdivu_vv_w, 4, 4)
-GEN_VEXT_VV(vdivu_vv_d, 8, 8)
-GEN_VEXT_VV(vdiv_vv_b, 1, 1)
-GEN_VEXT_VV(vdiv_vv_h, 2, 2)
-GEN_VEXT_VV(vdiv_vv_w, 4, 4)
-GEN_VEXT_VV(vdiv_vv_d, 8, 8)
-GEN_VEXT_VV(vremu_vv_b, 1, 1)
-GEN_VEXT_VV(vremu_vv_h, 2, 2)
-GEN_VEXT_VV(vremu_vv_w, 4, 4)
-GEN_VEXT_VV(vremu_vv_d, 8, 8)
-GEN_VEXT_VV(vrem_vv_b, 1, 1)
-GEN_VEXT_VV(vrem_vv_h, 2, 2)
-GEN_VEXT_VV(vrem_vv_w, 4, 4)
-GEN_VEXT_VV(vrem_vv_d, 8, 8)
+GEN_VEXT_VV(vdivu_vv_b)
+GEN_VEXT_VV(vdivu_vv_h)
+GEN_VEXT_VV(vdivu_vv_w)
+GEN_VEXT_VV(vdivu_vv_d)
+GEN_VEXT_VV(vdiv_vv_b)
+GEN_VEXT_VV(vdiv_vv_h)
+GEN_VEXT_VV(vdiv_vv_w)
+GEN_VEXT_VV(vdiv_vv_d)
+GEN_VEXT_VV(vremu_vv_b)
+GEN_VEXT_VV(vremu_vv_h)
+GEN_VEXT_VV(vremu_vv_w)
+GEN_VEXT_VV(vremu_vv_d)
+GEN_VEXT_VV(vrem_vv_b)
+GEN_VEXT_VV(vrem_vv_h)
+GEN_VEXT_VV(vrem_vv_w)
+GEN_VEXT_VV(vrem_vv_d)
RVVCALL(OPIVX2, vdivu_vx_b, OP_UUU_B, H1, H1, DO_DIVU)
RVVCALL(OPIVX2, vdivu_vx_h, OP_UUU_H, H2, H2, DO_DIVU)
@@ -1614,22 +1612,22 @@ RVVCALL(OPIVX2, vrem_vx_b, OP_SSS_B, H1, H1, DO_REM)
RVVCALL(OPIVX2, vrem_vx_h, OP_SSS_H, H2, H2, DO_REM)
RVVCALL(OPIVX2, vrem_vx_w, OP_SSS_W, H4, H4, DO_REM)
RVVCALL(OPIVX2, vrem_vx_d, OP_SSS_D, H8, H8, DO_REM)
-GEN_VEXT_VX(vdivu_vx_b, 1, 1)
-GEN_VEXT_VX(vdivu_vx_h, 2, 2)
-GEN_VEXT_VX(vdivu_vx_w, 4, 4)
-GEN_VEXT_VX(vdivu_vx_d, 8, 8)
-GEN_VEXT_VX(vdiv_vx_b, 1, 1)
-GEN_VEXT_VX(vdiv_vx_h, 2, 2)
-GEN_VEXT_VX(vdiv_vx_w, 4, 4)
-GEN_VEXT_VX(vdiv_vx_d, 8, 8)
-GEN_VEXT_VX(vremu_vx_b, 1, 1)
-GEN_VEXT_VX(vremu_vx_h, 2, 2)
-GEN_VEXT_VX(vremu_vx_w, 4, 4)
-GEN_VEXT_VX(vremu_vx_d, 8, 8)
-GEN_VEXT_VX(vrem_vx_b, 1, 1)
-GEN_VEXT_VX(vrem_vx_h, 2, 2)
-GEN_VEXT_VX(vrem_vx_w, 4, 4)
-GEN_VEXT_VX(vrem_vx_d, 8, 8)
+GEN_VEXT_VX(vdivu_vx_b)
+GEN_VEXT_VX(vdivu_vx_h)
+GEN_VEXT_VX(vdivu_vx_w)
+GEN_VEXT_VX(vdivu_vx_d)
+GEN_VEXT_VX(vdiv_vx_b)
+GEN_VEXT_VX(vdiv_vx_h)
+GEN_VEXT_VX(vdiv_vx_w)
+GEN_VEXT_VX(vdiv_vx_d)
+GEN_VEXT_VX(vremu_vx_b)
+GEN_VEXT_VX(vremu_vx_h)
+GEN_VEXT_VX(vremu_vx_w)
+GEN_VEXT_VX(vremu_vx_d)
+GEN_VEXT_VX(vrem_vx_b)
+GEN_VEXT_VX(vrem_vx_h)
+GEN_VEXT_VX(vrem_vx_w)
+GEN_VEXT_VX(vrem_vx_d)
/* Vector Widening Integer Multiply Instructions */
RVVCALL(OPIVV2, vwmul_vv_b, WOP_SSS_B, H2, H1, H1, DO_MUL)
@@ -1641,15 +1639,15 @@ RVVCALL(OPIVV2, vwmulu_vv_w, WOP_UUU_W, H8, H4, H4, DO_MUL)
RVVCALL(OPIVV2, vwmulsu_vv_b, WOP_SUS_B, H2, H1, H1, DO_MUL)
RVVCALL(OPIVV2, vwmulsu_vv_h, WOP_SUS_H, H4, H2, H2, DO_MUL)
RVVCALL(OPIVV2, vwmulsu_vv_w, WOP_SUS_W, H8, H4, H4, DO_MUL)
-GEN_VEXT_VV(vwmul_vv_b, 1, 2)
-GEN_VEXT_VV(vwmul_vv_h, 2, 4)
-GEN_VEXT_VV(vwmul_vv_w, 4, 8)
-GEN_VEXT_VV(vwmulu_vv_b, 1, 2)
-GEN_VEXT_VV(vwmulu_vv_h, 2, 4)
-GEN_VEXT_VV(vwmulu_vv_w, 4, 8)
-GEN_VEXT_VV(vwmulsu_vv_b, 1, 2)
-GEN_VEXT_VV(vwmulsu_vv_h, 2, 4)
-GEN_VEXT_VV(vwmulsu_vv_w, 4, 8)
+GEN_VEXT_VV(vwmul_vv_b)
+GEN_VEXT_VV(vwmul_vv_h)
+GEN_VEXT_VV(vwmul_vv_w)
+GEN_VEXT_VV(vwmulu_vv_b)
+GEN_VEXT_VV(vwmulu_vv_h)
+GEN_VEXT_VV(vwmulu_vv_w)
+GEN_VEXT_VV(vwmulsu_vv_b)
+GEN_VEXT_VV(vwmulsu_vv_h)
+GEN_VEXT_VV(vwmulsu_vv_w)
RVVCALL(OPIVX2, vwmul_vx_b, WOP_SSS_B, H2, H1, DO_MUL)
RVVCALL(OPIVX2, vwmul_vx_h, WOP_SSS_H, H4, H2, DO_MUL)
@@ -1660,15 +1658,15 @@ RVVCALL(OPIVX2, vwmulu_vx_w, WOP_UUU_W, H8, H4, DO_MUL)
RVVCALL(OPIVX2, vwmulsu_vx_b, WOP_SUS_B, H2, H1, DO_MUL)
RVVCALL(OPIVX2, vwmulsu_vx_h, WOP_SUS_H, H4, H2, DO_MUL)
RVVCALL(OPIVX2, vwmulsu_vx_w, WOP_SUS_W, H8, H4, DO_MUL)
-GEN_VEXT_VX(vwmul_vx_b, 1, 2)
-GEN_VEXT_VX(vwmul_vx_h, 2, 4)
-GEN_VEXT_VX(vwmul_vx_w, 4, 8)
-GEN_VEXT_VX(vwmulu_vx_b, 1, 2)
-GEN_VEXT_VX(vwmulu_vx_h, 2, 4)
-GEN_VEXT_VX(vwmulu_vx_w, 4, 8)
-GEN_VEXT_VX(vwmulsu_vx_b, 1, 2)
-GEN_VEXT_VX(vwmulsu_vx_h, 2, 4)
-GEN_VEXT_VX(vwmulsu_vx_w, 4, 8)
+GEN_VEXT_VX(vwmul_vx_b)
+GEN_VEXT_VX(vwmul_vx_h)
+GEN_VEXT_VX(vwmul_vx_w)
+GEN_VEXT_VX(vwmulu_vx_b)
+GEN_VEXT_VX(vwmulu_vx_h)
+GEN_VEXT_VX(vwmulu_vx_w)
+GEN_VEXT_VX(vwmulsu_vx_b)
+GEN_VEXT_VX(vwmulsu_vx_h)
+GEN_VEXT_VX(vwmulsu_vx_w)
/* Vector Single-Width Integer Multiply-Add Instructions */
#define OPIVV3(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP) \
@@ -1700,22 +1698,22 @@ RVVCALL(OPIVV3, vnmsub_vv_b, OP_SSS_B, H1, H1, H1, DO_NMSUB)
RVVCALL(OPIVV3, vnmsub_vv_h, OP_SSS_H, H2, H2, H2, DO_NMSUB)
RVVCALL(OPIVV3, vnmsub_vv_w, OP_SSS_W, H4, H4, H4, DO_NMSUB)
RVVCALL(OPIVV3, vnmsub_vv_d, OP_SSS_D, H8, H8, H8, DO_NMSUB)
-GEN_VEXT_VV(vmacc_vv_b, 1, 1)
-GEN_VEXT_VV(vmacc_vv_h, 2, 2)
-GEN_VEXT_VV(vmacc_vv_w, 4, 4)
-GEN_VEXT_VV(vmacc_vv_d, 8, 8)
-GEN_VEXT_VV(vnmsac_vv_b, 1, 1)
-GEN_VEXT_VV(vnmsac_vv_h, 2, 2)
-GEN_VEXT_VV(vnmsac_vv_w, 4, 4)
-GEN_VEXT_VV(vnmsac_vv_d, 8, 8)
-GEN_VEXT_VV(vmadd_vv_b, 1, 1)
-GEN_VEXT_VV(vmadd_vv_h, 2, 2)
-GEN_VEXT_VV(vmadd_vv_w, 4, 4)
-GEN_VEXT_VV(vmadd_vv_d, 8, 8)
-GEN_VEXT_VV(vnmsub_vv_b, 1, 1)
-GEN_VEXT_VV(vnmsub_vv_h, 2, 2)
-GEN_VEXT_VV(vnmsub_vv_w, 4, 4)
-GEN_VEXT_VV(vnmsub_vv_d, 8, 8)
+GEN_VEXT_VV(vmacc_vv_b)
+GEN_VEXT_VV(vmacc_vv_h)
+GEN_VEXT_VV(vmacc_vv_w)
+GEN_VEXT_VV(vmacc_vv_d)
+GEN_VEXT_VV(vnmsac_vv_b)
+GEN_VEXT_VV(vnmsac_vv_h)
+GEN_VEXT_VV(vnmsac_vv_w)
+GEN_VEXT_VV(vnmsac_vv_d)
+GEN_VEXT_VV(vmadd_vv_b)
+GEN_VEXT_VV(vmadd_vv_h)
+GEN_VEXT_VV(vmadd_vv_w)
+GEN_VEXT_VV(vmadd_vv_d)
+GEN_VEXT_VV(vnmsub_vv_b)
+GEN_VEXT_VV(vnmsub_vv_h)
+GEN_VEXT_VV(vnmsub_vv_w)
+GEN_VEXT_VV(vnmsub_vv_d)
#define OPIVX3(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \
static void do_##NAME(void *vd, target_long s1, void *vs2, int i) \
@@ -1741,22 +1739,22 @@ RVVCALL(OPIVX3, vnmsub_vx_b, OP_SSS_B, H1, H1, DO_NMSUB)
RVVCALL(OPIVX3, vnmsub_vx_h, OP_SSS_H, H2, H2, DO_NMSUB)
RVVCALL(OPIVX3, vnmsub_vx_w, OP_SSS_W, H4, H4, DO_NMSUB)
RVVCALL(OPIVX3, vnmsub_vx_d, OP_SSS_D, H8, H8, DO_NMSUB)
-GEN_VEXT_VX(vmacc_vx_b, 1, 1)
-GEN_VEXT_VX(vmacc_vx_h, 2, 2)
-GEN_VEXT_VX(vmacc_vx_w, 4, 4)
-GEN_VEXT_VX(vmacc_vx_d, 8, 8)
-GEN_VEXT_VX(vnmsac_vx_b, 1, 1)
-GEN_VEXT_VX(vnmsac_vx_h, 2, 2)
-GEN_VEXT_VX(vnmsac_vx_w, 4, 4)
-GEN_VEXT_VX(vnmsac_vx_d, 8, 8)
-GEN_VEXT_VX(vmadd_vx_b, 1, 1)
-GEN_VEXT_VX(vmadd_vx_h, 2, 2)
-GEN_VEXT_VX(vmadd_vx_w, 4, 4)
-GEN_VEXT_VX(vmadd_vx_d, 8, 8)
-GEN_VEXT_VX(vnmsub_vx_b, 1, 1)
-GEN_VEXT_VX(vnmsub_vx_h, 2, 2)
-GEN_VEXT_VX(vnmsub_vx_w, 4, 4)
-GEN_VEXT_VX(vnmsub_vx_d, 8, 8)
+GEN_VEXT_VX(vmacc_vx_b)
+GEN_VEXT_VX(vmacc_vx_h)
+GEN_VEXT_VX(vmacc_vx_w)
+GEN_VEXT_VX(vmacc_vx_d)
+GEN_VEXT_VX(vnmsac_vx_b)
+GEN_VEXT_VX(vnmsac_vx_h)
+GEN_VEXT_VX(vnmsac_vx_w)
+GEN_VEXT_VX(vnmsac_vx_d)
+GEN_VEXT_VX(vmadd_vx_b)
+GEN_VEXT_VX(vmadd_vx_h)
+GEN_VEXT_VX(vmadd_vx_w)
+GEN_VEXT_VX(vmadd_vx_d)
+GEN_VEXT_VX(vnmsub_vx_b)
+GEN_VEXT_VX(vnmsub_vx_h)
+GEN_VEXT_VX(vnmsub_vx_w)
+GEN_VEXT_VX(vnmsub_vx_d)
/* Vector Widening Integer Multiply-Add Instructions */
RVVCALL(OPIVV3, vwmaccu_vv_b, WOP_UUU_B, H2, H1, H1, DO_MACC)
@@ -1768,15 +1766,15 @@ RVVCALL(OPIVV3, vwmacc_vv_w, WOP_SSS_W, H8, H4, H4, DO_MACC)
RVVCALL(OPIVV3, vwmaccsu_vv_b, WOP_SSU_B, H2, H1, H1, DO_MACC)
RVVCALL(OPIVV3, vwmaccsu_vv_h, WOP_SSU_H, H4, H2, H2, DO_MACC)
RVVCALL(OPIVV3, vwmaccsu_vv_w, WOP_SSU_W, H8, H4, H4, DO_MACC)
-GEN_VEXT_VV(vwmaccu_vv_b, 1, 2)
-GEN_VEXT_VV(vwmaccu_vv_h, 2, 4)
-GEN_VEXT_VV(vwmaccu_vv_w, 4, 8)
-GEN_VEXT_VV(vwmacc_vv_b, 1, 2)
-GEN_VEXT_VV(vwmacc_vv_h, 2, 4)
-GEN_VEXT_VV(vwmacc_vv_w, 4, 8)
-GEN_VEXT_VV(vwmaccsu_vv_b, 1, 2)
-GEN_VEXT_VV(vwmaccsu_vv_h, 2, 4)
-GEN_VEXT_VV(vwmaccsu_vv_w, 4, 8)
+GEN_VEXT_VV(vwmaccu_vv_b)
+GEN_VEXT_VV(vwmaccu_vv_h)
+GEN_VEXT_VV(vwmaccu_vv_w)
+GEN_VEXT_VV(vwmacc_vv_b)
+GEN_VEXT_VV(vwmacc_vv_h)
+GEN_VEXT_VV(vwmacc_vv_w)
+GEN_VEXT_VV(vwmaccsu_vv_b)
+GEN_VEXT_VV(vwmaccsu_vv_h)
+GEN_VEXT_VV(vwmaccsu_vv_w)
RVVCALL(OPIVX3, vwmaccu_vx_b, WOP_UUU_B, H2, H1, DO_MACC)
RVVCALL(OPIVX3, vwmaccu_vx_h, WOP_UUU_H, H4, H2, DO_MACC)
@@ -1790,18 +1788,18 @@ RVVCALL(OPIVX3, vwmaccsu_vx_w, WOP_SSU_W, H8, H4, DO_MACC)
RVVCALL(OPIVX3, vwmaccus_vx_b, WOP_SUS_B, H2, H1, DO_MACC)
RVVCALL(OPIVX3, vwmaccus_vx_h, WOP_SUS_H, H4, H2, DO_MACC)
RVVCALL(OPIVX3, vwmaccus_vx_w, WOP_SUS_W, H8, H4, DO_MACC)
-GEN_VEXT_VX(vwmaccu_vx_b, 1, 2)
-GEN_VEXT_VX(vwmaccu_vx_h, 2, 4)
-GEN_VEXT_VX(vwmaccu_vx_w, 4, 8)
-GEN_VEXT_VX(vwmacc_vx_b, 1, 2)
-GEN_VEXT_VX(vwmacc_vx_h, 2, 4)
-GEN_VEXT_VX(vwmacc_vx_w, 4, 8)
-GEN_VEXT_VX(vwmaccsu_vx_b, 1, 2)
-GEN_VEXT_VX(vwmaccsu_vx_h, 2, 4)
-GEN_VEXT_VX(vwmaccsu_vx_w, 4, 8)
-GEN_VEXT_VX(vwmaccus_vx_b, 1, 2)
-GEN_VEXT_VX(vwmaccus_vx_h, 2, 4)
-GEN_VEXT_VX(vwmaccus_vx_w, 4, 8)
+GEN_VEXT_VX(vwmaccu_vx_b)
+GEN_VEXT_VX(vwmaccu_vx_h)
+GEN_VEXT_VX(vwmaccu_vx_w)
+GEN_VEXT_VX(vwmacc_vx_b)
+GEN_VEXT_VX(vwmacc_vx_h)
+GEN_VEXT_VX(vwmacc_vx_w)
+GEN_VEXT_VX(vwmaccsu_vx_b)
+GEN_VEXT_VX(vwmaccsu_vx_h)
+GEN_VEXT_VX(vwmaccsu_vx_w)
+GEN_VEXT_VX(vwmaccus_vx_b)
+GEN_VEXT_VX(vwmaccus_vx_h)
+GEN_VEXT_VX(vwmaccus_vx_w)
/* Vector Integer Merge and Move Instructions */
#define GEN_VEXT_VMV_VV(NAME, ETYPE, H) \
@@ -1922,7 +1920,7 @@ vext_vv_rm_1(void *vd, void *v0, void *vs1, void *vs2,
static inline void
vext_vv_rm_2(void *vd, void *v0, void *vs1, void *vs2,
CPURISCVState *env,
- uint32_t desc, uint32_t esz, uint32_t dsz,
+ uint32_t desc,
opivv2_rm_fn *fn)
{
uint32_t vm = vext_vm(desc);
@@ -1949,11 +1947,11 @@ vext_vv_rm_2(void *vd, void *v0, void *vs1, void *vs2,
}
/* generate helpers for fixed point instructions with OPIVV format */
-#define GEN_VEXT_VV_RM(NAME, ESZ, DSZ) \
+#define GEN_VEXT_VV_RM(NAME) \
void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
- vext_vv_rm_2(vd, v0, vs1, vs2, env, desc, ESZ, DSZ, \
+ vext_vv_rm_2(vd, v0, vs1, vs2, env, desc, \
do_##NAME); \
}
@@ -2004,10 +2002,10 @@ RVVCALL(OPIVV2_RM, vsaddu_vv_b, OP_UUU_B, H1, H1, H1, saddu8)
RVVCALL(OPIVV2_RM, vsaddu_vv_h, OP_UUU_H, H2, H2, H2, saddu16)
RVVCALL(OPIVV2_RM, vsaddu_vv_w, OP_UUU_W, H4, H4, H4, saddu32)
RVVCALL(OPIVV2_RM, vsaddu_vv_d, OP_UUU_D, H8, H8, H8, saddu64)
-GEN_VEXT_VV_RM(vsaddu_vv_b, 1, 1)
-GEN_VEXT_VV_RM(vsaddu_vv_h, 2, 2)
-GEN_VEXT_VV_RM(vsaddu_vv_w, 4, 4)
-GEN_VEXT_VV_RM(vsaddu_vv_d, 8, 8)
+GEN_VEXT_VV_RM(vsaddu_vv_b)
+GEN_VEXT_VV_RM(vsaddu_vv_h)
+GEN_VEXT_VV_RM(vsaddu_vv_w)
+GEN_VEXT_VV_RM(vsaddu_vv_d)
typedef void opivx2_rm_fn(void *vd, target_long s1, void *vs2, int i,
CPURISCVState *env, int vxrm);
@@ -2039,7 +2037,7 @@ vext_vx_rm_1(void *vd, void *v0, target_long s1, void *vs2,
static inline void
vext_vx_rm_2(void *vd, void *v0, target_long s1, void *vs2,
CPURISCVState *env,
- uint32_t desc, uint32_t esz, uint32_t dsz,
+ uint32_t desc,
opivx2_rm_fn *fn)
{
uint32_t vm = vext_vm(desc);
@@ -2066,11 +2064,11 @@ vext_vx_rm_2(void *vd, void *v0, target_long s1, void *vs2,
}
/* generate helpers for fixed point instructions with OPIVX format */
-#define GEN_VEXT_VX_RM(NAME, ESZ, DSZ) \
+#define GEN_VEXT_VX_RM(NAME) \
void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
void *vs2, CPURISCVState *env, uint32_t desc) \
{ \
- vext_vx_rm_2(vd, v0, s1, vs2, env, desc, ESZ, DSZ, \
+ vext_vx_rm_2(vd, v0, s1, vs2, env, desc, \
do_##NAME); \
}
@@ -2078,10 +2076,10 @@ RVVCALL(OPIVX2_RM, vsaddu_vx_b, OP_UUU_B, H1, H1, saddu8)
RVVCALL(OPIVX2_RM, vsaddu_vx_h, OP_UUU_H, H2, H2, saddu16)
RVVCALL(OPIVX2_RM, vsaddu_vx_w, OP_UUU_W, H4, H4, saddu32)
RVVCALL(OPIVX2_RM, vsaddu_vx_d, OP_UUU_D, H8, H8, saddu64)
-GEN_VEXT_VX_RM(vsaddu_vx_b, 1, 1)
-GEN_VEXT_VX_RM(vsaddu_vx_h, 2, 2)
-GEN_VEXT_VX_RM(vsaddu_vx_w, 4, 4)
-GEN_VEXT_VX_RM(vsaddu_vx_d, 8, 8)
+GEN_VEXT_VX_RM(vsaddu_vx_b)
+GEN_VEXT_VX_RM(vsaddu_vx_h)
+GEN_VEXT_VX_RM(vsaddu_vx_w)
+GEN_VEXT_VX_RM(vsaddu_vx_d)
static inline int8_t sadd8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
{
@@ -2127,19 +2125,19 @@ RVVCALL(OPIVV2_RM, vsadd_vv_b, OP_SSS_B, H1, H1, H1, sadd8)
RVVCALL(OPIVV2_RM, vsadd_vv_h, OP_SSS_H, H2, H2, H2, sadd16)
RVVCALL(OPIVV2_RM, vsadd_vv_w, OP_SSS_W, H4, H4, H4, sadd32)
RVVCALL(OPIVV2_RM, vsadd_vv_d, OP_SSS_D, H8, H8, H8, sadd64)
-GEN_VEXT_VV_RM(vsadd_vv_b, 1, 1)
-GEN_VEXT_VV_RM(vsadd_vv_h, 2, 2)
-GEN_VEXT_VV_RM(vsadd_vv_w, 4, 4)
-GEN_VEXT_VV_RM(vsadd_vv_d, 8, 8)
+GEN_VEXT_VV_RM(vsadd_vv_b)
+GEN_VEXT_VV_RM(vsadd_vv_h)
+GEN_VEXT_VV_RM(vsadd_vv_w)
+GEN_VEXT_VV_RM(vsadd_vv_d)
RVVCALL(OPIVX2_RM, vsadd_vx_b, OP_SSS_B, H1, H1, sadd8)
RVVCALL(OPIVX2_RM, vsadd_vx_h, OP_SSS_H, H2, H2, sadd16)
RVVCALL(OPIVX2_RM, vsadd_vx_w, OP_SSS_W, H4, H4, sadd32)
RVVCALL(OPIVX2_RM, vsadd_vx_d, OP_SSS_D, H8, H8, sadd64)
-GEN_VEXT_VX_RM(vsadd_vx_b, 1, 1)
-GEN_VEXT_VX_RM(vsadd_vx_h, 2, 2)
-GEN_VEXT_VX_RM(vsadd_vx_w, 4, 4)
-GEN_VEXT_VX_RM(vsadd_vx_d, 8, 8)
+GEN_VEXT_VX_RM(vsadd_vx_b)
+GEN_VEXT_VX_RM(vsadd_vx_h)
+GEN_VEXT_VX_RM(vsadd_vx_w)
+GEN_VEXT_VX_RM(vsadd_vx_d)
static inline uint8_t ssubu8(CPURISCVState *env, int vxrm, uint8_t a, uint8_t b)
{
@@ -2188,19 +2186,19 @@ RVVCALL(OPIVV2_RM, vssubu_vv_b, OP_UUU_B, H1, H1, H1, ssubu8)
RVVCALL(OPIVV2_RM, vssubu_vv_h, OP_UUU_H, H2, H2, H2, ssubu16)
RVVCALL(OPIVV2_RM, vssubu_vv_w, OP_UUU_W, H4, H4, H4, ssubu32)
RVVCALL(OPIVV2_RM, vssubu_vv_d, OP_UUU_D, H8, H8, H8, ssubu64)
-GEN_VEXT_VV_RM(vssubu_vv_b, 1, 1)
-GEN_VEXT_VV_RM(vssubu_vv_h, 2, 2)
-GEN_VEXT_VV_RM(vssubu_vv_w, 4, 4)
-GEN_VEXT_VV_RM(vssubu_vv_d, 8, 8)
+GEN_VEXT_VV_RM(vssubu_vv_b)
+GEN_VEXT_VV_RM(vssubu_vv_h)
+GEN_VEXT_VV_RM(vssubu_vv_w)
+GEN_VEXT_VV_RM(vssubu_vv_d)
RVVCALL(OPIVX2_RM, vssubu_vx_b, OP_UUU_B, H1, H1, ssubu8)
RVVCALL(OPIVX2_RM, vssubu_vx_h, OP_UUU_H, H2, H2, ssubu16)
RVVCALL(OPIVX2_RM, vssubu_vx_w, OP_UUU_W, H4, H4, ssubu32)
RVVCALL(OPIVX2_RM, vssubu_vx_d, OP_UUU_D, H8, H8, ssubu64)
-GEN_VEXT_VX_RM(vssubu_vx_b, 1, 1)
-GEN_VEXT_VX_RM(vssubu_vx_h, 2, 2)
-GEN_VEXT_VX_RM(vssubu_vx_w, 4, 4)
-GEN_VEXT_VX_RM(vssubu_vx_d, 8, 8)
+GEN_VEXT_VX_RM(vssubu_vx_b)
+GEN_VEXT_VX_RM(vssubu_vx_h)
+GEN_VEXT_VX_RM(vssubu_vx_w)
+GEN_VEXT_VX_RM(vssubu_vx_d)
static inline int8_t ssub8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
{
@@ -2246,19 +2244,19 @@ RVVCALL(OPIVV2_RM, vssub_vv_b, OP_SSS_B, H1, H1, H1, ssub8)
RVVCALL(OPIVV2_RM, vssub_vv_h, OP_SSS_H, H2, H2, H2, ssub16)
RVVCALL(OPIVV2_RM, vssub_vv_w, OP_SSS_W, H4, H4, H4, ssub32)
RVVCALL(OPIVV2_RM, vssub_vv_d, OP_SSS_D, H8, H8, H8, ssub64)
-GEN_VEXT_VV_RM(vssub_vv_b, 1, 1)
-GEN_VEXT_VV_RM(vssub_vv_h, 2, 2)
-GEN_VEXT_VV_RM(vssub_vv_w, 4, 4)
-GEN_VEXT_VV_RM(vssub_vv_d, 8, 8)
+GEN_VEXT_VV_RM(vssub_vv_b)
+GEN_VEXT_VV_RM(vssub_vv_h)
+GEN_VEXT_VV_RM(vssub_vv_w)
+GEN_VEXT_VV_RM(vssub_vv_d)
RVVCALL(OPIVX2_RM, vssub_vx_b, OP_SSS_B, H1, H1, ssub8)
RVVCALL(OPIVX2_RM, vssub_vx_h, OP_SSS_H, H2, H2, ssub16)
RVVCALL(OPIVX2_RM, vssub_vx_w, OP_SSS_W, H4, H4, ssub32)
RVVCALL(OPIVX2_RM, vssub_vx_d, OP_SSS_D, H8, H8, ssub64)
-GEN_VEXT_VX_RM(vssub_vx_b, 1, 1)
-GEN_VEXT_VX_RM(vssub_vx_h, 2, 2)
-GEN_VEXT_VX_RM(vssub_vx_w, 4, 4)
-GEN_VEXT_VX_RM(vssub_vx_d, 8, 8)
+GEN_VEXT_VX_RM(vssub_vx_b)
+GEN_VEXT_VX_RM(vssub_vx_h)
+GEN_VEXT_VX_RM(vssub_vx_w)
+GEN_VEXT_VX_RM(vssub_vx_d)
/* Vector Single-Width Averaging Add and Subtract */
static inline uint8_t get_round(int vxrm, uint64_t v, uint8_t shift)
@@ -2310,19 +2308,19 @@ RVVCALL(OPIVV2_RM, vaadd_vv_b, OP_SSS_B, H1, H1, H1, aadd32)
RVVCALL(OPIVV2_RM, vaadd_vv_h, OP_SSS_H, H2, H2, H2, aadd32)
RVVCALL(OPIVV2_RM, vaadd_vv_w, OP_SSS_W, H4, H4, H4, aadd32)
RVVCALL(OPIVV2_RM, vaadd_vv_d, OP_SSS_D, H8, H8, H8, aadd64)
-GEN_VEXT_VV_RM(vaadd_vv_b, 1, 1)
-GEN_VEXT_VV_RM(vaadd_vv_h, 2, 2)
-GEN_VEXT_VV_RM(vaadd_vv_w, 4, 4)
-GEN_VEXT_VV_RM(vaadd_vv_d, 8, 8)
+GEN_VEXT_VV_RM(vaadd_vv_b)
+GEN_VEXT_VV_RM(vaadd_vv_h)
+GEN_VEXT_VV_RM(vaadd_vv_w)
+GEN_VEXT_VV_RM(vaadd_vv_d)
RVVCALL(OPIVX2_RM, vaadd_vx_b, OP_SSS_B, H1, H1, aadd32)
RVVCALL(OPIVX2_RM, vaadd_vx_h, OP_SSS_H, H2, H2, aadd32)
RVVCALL(OPIVX2_RM, vaadd_vx_w, OP_SSS_W, H4, H4, aadd32)
RVVCALL(OPIVX2_RM, vaadd_vx_d, OP_SSS_D, H8, H8, aadd64)
-GEN_VEXT_VX_RM(vaadd_vx_b, 1, 1)
-GEN_VEXT_VX_RM(vaadd_vx_h, 2, 2)
-GEN_VEXT_VX_RM(vaadd_vx_w, 4, 4)
-GEN_VEXT_VX_RM(vaadd_vx_d, 8, 8)
+GEN_VEXT_VX_RM(vaadd_vx_b)
+GEN_VEXT_VX_RM(vaadd_vx_h)
+GEN_VEXT_VX_RM(vaadd_vx_w)
+GEN_VEXT_VX_RM(vaadd_vx_d)
static inline uint32_t aaddu32(CPURISCVState *env, int vxrm,
uint32_t a, uint32_t b)
@@ -2347,19 +2345,19 @@ RVVCALL(OPIVV2_RM, vaaddu_vv_b, OP_UUU_B, H1, H1, H1, aaddu32)
RVVCALL(OPIVV2_RM, vaaddu_vv_h, OP_UUU_H, H2, H2, H2, aaddu32)
RVVCALL(OPIVV2_RM, vaaddu_vv_w, OP_UUU_W, H4, H4, H4, aaddu32)
RVVCALL(OPIVV2_RM, vaaddu_vv_d, OP_UUU_D, H8, H8, H8, aaddu64)
-GEN_VEXT_VV_RM(vaaddu_vv_b, 1, 1)
-GEN_VEXT_VV_RM(vaaddu_vv_h, 2, 2)
-GEN_VEXT_VV_RM(vaaddu_vv_w, 4, 4)
-GEN_VEXT_VV_RM(vaaddu_vv_d, 8, 8)
+GEN_VEXT_VV_RM(vaaddu_vv_b)
+GEN_VEXT_VV_RM(vaaddu_vv_h)
+GEN_VEXT_VV_RM(vaaddu_vv_w)
+GEN_VEXT_VV_RM(vaaddu_vv_d)
RVVCALL(OPIVX2_RM, vaaddu_vx_b, OP_UUU_B, H1, H1, aaddu32)
RVVCALL(OPIVX2_RM, vaaddu_vx_h, OP_UUU_H, H2, H2, aaddu32)
RVVCALL(OPIVX2_RM, vaaddu_vx_w, OP_UUU_W, H4, H4, aaddu32)
RVVCALL(OPIVX2_RM, vaaddu_vx_d, OP_UUU_D, H8, H8, aaddu64)
-GEN_VEXT_VX_RM(vaaddu_vx_b, 1, 1)
-GEN_VEXT_VX_RM(vaaddu_vx_h, 2, 2)
-GEN_VEXT_VX_RM(vaaddu_vx_w, 4, 4)
-GEN_VEXT_VX_RM(vaaddu_vx_d, 8, 8)
+GEN_VEXT_VX_RM(vaaddu_vx_b)
+GEN_VEXT_VX_RM(vaaddu_vx_h)
+GEN_VEXT_VX_RM(vaaddu_vx_w)
+GEN_VEXT_VX_RM(vaaddu_vx_d)
static inline int32_t asub32(CPURISCVState *env, int vxrm, int32_t a, int32_t b)
{
@@ -2383,19 +2381,19 @@ RVVCALL(OPIVV2_RM, vasub_vv_b, OP_SSS_B, H1, H1, H1, asub32)
RVVCALL(OPIVV2_RM, vasub_vv_h, OP_SSS_H, H2, H2, H2, asub32)
RVVCALL(OPIVV2_RM, vasub_vv_w, OP_SSS_W, H4, H4, H4, asub32)
RVVCALL(OPIVV2_RM, vasub_vv_d, OP_SSS_D, H8, H8, H8, asub64)
-GEN_VEXT_VV_RM(vasub_vv_b, 1, 1)
-GEN_VEXT_VV_RM(vasub_vv_h, 2, 2)
-GEN_VEXT_VV_RM(vasub_vv_w, 4, 4)
-GEN_VEXT_VV_RM(vasub_vv_d, 8, 8)
+GEN_VEXT_VV_RM(vasub_vv_b)
+GEN_VEXT_VV_RM(vasub_vv_h)
+GEN_VEXT_VV_RM(vasub_vv_w)
+GEN_VEXT_VV_RM(vasub_vv_d)
RVVCALL(OPIVX2_RM, vasub_vx_b, OP_SSS_B, H1, H1, asub32)
RVVCALL(OPIVX2_RM, vasub_vx_h, OP_SSS_H, H2, H2, asub32)
RVVCALL(OPIVX2_RM, vasub_vx_w, OP_SSS_W, H4, H4, asub32)
RVVCALL(OPIVX2_RM, vasub_vx_d, OP_SSS_D, H8, H8, asub64)
-GEN_VEXT_VX_RM(vasub_vx_b, 1, 1)
-GEN_VEXT_VX_RM(vasub_vx_h, 2, 2)
-GEN_VEXT_VX_RM(vasub_vx_w, 4, 4)
-GEN_VEXT_VX_RM(vasub_vx_d, 8, 8)
+GEN_VEXT_VX_RM(vasub_vx_b)
+GEN_VEXT_VX_RM(vasub_vx_h)
+GEN_VEXT_VX_RM(vasub_vx_w)
+GEN_VEXT_VX_RM(vasub_vx_d)
static inline uint32_t asubu32(CPURISCVState *env, int vxrm,
uint32_t a, uint32_t b)
@@ -2420,19 +2418,19 @@ RVVCALL(OPIVV2_RM, vasubu_vv_b, OP_UUU_B, H1, H1, H1, asubu32)
RVVCALL(OPIVV2_RM, vasubu_vv_h, OP_UUU_H, H2, H2, H2, asubu32)
RVVCALL(OPIVV2_RM, vasubu_vv_w, OP_UUU_W, H4, H4, H4, asubu32)
RVVCALL(OPIVV2_RM, vasubu_vv_d, OP_UUU_D, H8, H8, H8, asubu64)
-GEN_VEXT_VV_RM(vasubu_vv_b, 1, 1)
-GEN_VEXT_VV_RM(vasubu_vv_h, 2, 2)
-GEN_VEXT_VV_RM(vasubu_vv_w, 4, 4)
-GEN_VEXT_VV_RM(vasubu_vv_d, 8, 8)
+GEN_VEXT_VV_RM(vasubu_vv_b)
+GEN_VEXT_VV_RM(vasubu_vv_h)
+GEN_VEXT_VV_RM(vasubu_vv_w)
+GEN_VEXT_VV_RM(vasubu_vv_d)
RVVCALL(OPIVX2_RM, vasubu_vx_b, OP_UUU_B, H1, H1, asubu32)
RVVCALL(OPIVX2_RM, vasubu_vx_h, OP_UUU_H, H2, H2, asubu32)
RVVCALL(OPIVX2_RM, vasubu_vx_w, OP_UUU_W, H4, H4, asubu32)
RVVCALL(OPIVX2_RM, vasubu_vx_d, OP_UUU_D, H8, H8, asubu64)
-GEN_VEXT_VX_RM(vasubu_vx_b, 1, 1)
-GEN_VEXT_VX_RM(vasubu_vx_h, 2, 2)
-GEN_VEXT_VX_RM(vasubu_vx_w, 4, 4)
-GEN_VEXT_VX_RM(vasubu_vx_d, 8, 8)
+GEN_VEXT_VX_RM(vasubu_vx_b)
+GEN_VEXT_VX_RM(vasubu_vx_h)
+GEN_VEXT_VX_RM(vasubu_vx_w)
+GEN_VEXT_VX_RM(vasubu_vx_d)
/* Vector Single-Width Fractional Multiply with Rounding and Saturation */
static inline int8_t vsmul8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
@@ -2527,19 +2525,19 @@ RVVCALL(OPIVV2_RM, vsmul_vv_b, OP_SSS_B, H1, H1, H1, vsmul8)
RVVCALL(OPIVV2_RM, vsmul_vv_h, OP_SSS_H, H2, H2, H2, vsmul16)
RVVCALL(OPIVV2_RM, vsmul_vv_w, OP_SSS_W, H4, H4, H4, vsmul32)
RVVCALL(OPIVV2_RM, vsmul_vv_d, OP_SSS_D, H8, H8, H8, vsmul64)
-GEN_VEXT_VV_RM(vsmul_vv_b, 1, 1)
-GEN_VEXT_VV_RM(vsmul_vv_h, 2, 2)
-GEN_VEXT_VV_RM(vsmul_vv_w, 4, 4)
-GEN_VEXT_VV_RM(vsmul_vv_d, 8, 8)
+GEN_VEXT_VV_RM(vsmul_vv_b)
+GEN_VEXT_VV_RM(vsmul_vv_h)
+GEN_VEXT_VV_RM(vsmul_vv_w)
+GEN_VEXT_VV_RM(vsmul_vv_d)
RVVCALL(OPIVX2_RM, vsmul_vx_b, OP_SSS_B, H1, H1, vsmul8)
RVVCALL(OPIVX2_RM, vsmul_vx_h, OP_SSS_H, H2, H2, vsmul16)
RVVCALL(OPIVX2_RM, vsmul_vx_w, OP_SSS_W, H4, H4, vsmul32)
RVVCALL(OPIVX2_RM, vsmul_vx_d, OP_SSS_D, H8, H8, vsmul64)
-GEN_VEXT_VX_RM(vsmul_vx_b, 1, 1)
-GEN_VEXT_VX_RM(vsmul_vx_h, 2, 2)
-GEN_VEXT_VX_RM(vsmul_vx_w, 4, 4)
-GEN_VEXT_VX_RM(vsmul_vx_d, 8, 8)
+GEN_VEXT_VX_RM(vsmul_vx_b)
+GEN_VEXT_VX_RM(vsmul_vx_h)
+GEN_VEXT_VX_RM(vsmul_vx_w)
+GEN_VEXT_VX_RM(vsmul_vx_d)
/* Vector Single-Width Scaling Shift Instructions */
static inline uint8_t
@@ -2586,19 +2584,19 @@ RVVCALL(OPIVV2_RM, vssrl_vv_b, OP_UUU_B, H1, H1, H1, vssrl8)
RVVCALL(OPIVV2_RM, vssrl_vv_h, OP_UUU_H, H2, H2, H2, vssrl16)
RVVCALL(OPIVV2_RM, vssrl_vv_w, OP_UUU_W, H4, H4, H4, vssrl32)
RVVCALL(OPIVV2_RM, vssrl_vv_d, OP_UUU_D, H8, H8, H8, vssrl64)
-GEN_VEXT_VV_RM(vssrl_vv_b, 1, 1)
-GEN_VEXT_VV_RM(vssrl_vv_h, 2, 2)
-GEN_VEXT_VV_RM(vssrl_vv_w, 4, 4)
-GEN_VEXT_VV_RM(vssrl_vv_d, 8, 8)
+GEN_VEXT_VV_RM(vssrl_vv_b)
+GEN_VEXT_VV_RM(vssrl_vv_h)
+GEN_VEXT_VV_RM(vssrl_vv_w)
+GEN_VEXT_VV_RM(vssrl_vv_d)
RVVCALL(OPIVX2_RM, vssrl_vx_b, OP_UUU_B, H1, H1, vssrl8)
RVVCALL(OPIVX2_RM, vssrl_vx_h, OP_UUU_H, H2, H2, vssrl16)
RVVCALL(OPIVX2_RM, vssrl_vx_w, OP_UUU_W, H4, H4, vssrl32)
RVVCALL(OPIVX2_RM, vssrl_vx_d, OP_UUU_D, H8, H8, vssrl64)
-GEN_VEXT_VX_RM(vssrl_vx_b, 1, 1)
-GEN_VEXT_VX_RM(vssrl_vx_h, 2, 2)
-GEN_VEXT_VX_RM(vssrl_vx_w, 4, 4)
-GEN_VEXT_VX_RM(vssrl_vx_d, 8, 8)
+GEN_VEXT_VX_RM(vssrl_vx_b)
+GEN_VEXT_VX_RM(vssrl_vx_h)
+GEN_VEXT_VX_RM(vssrl_vx_w)
+GEN_VEXT_VX_RM(vssrl_vx_d)
static inline int8_t
vssra8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
@@ -2645,19 +2643,19 @@ RVVCALL(OPIVV2_RM, vssra_vv_b, OP_SSS_B, H1, H1, H1, vssra8)
RVVCALL(OPIVV2_RM, vssra_vv_h, OP_SSS_H, H2, H2, H2, vssra16)
RVVCALL(OPIVV2_RM, vssra_vv_w, OP_SSS_W, H4, H4, H4, vssra32)
RVVCALL(OPIVV2_RM, vssra_vv_d, OP_SSS_D, H8, H8, H8, vssra64)
-GEN_VEXT_VV_RM(vssra_vv_b, 1, 1)
-GEN_VEXT_VV_RM(vssra_vv_h, 2, 2)
-GEN_VEXT_VV_RM(vssra_vv_w, 4, 4)
-GEN_VEXT_VV_RM(vssra_vv_d, 8, 8)
+GEN_VEXT_VV_RM(vssra_vv_b)
+GEN_VEXT_VV_RM(vssra_vv_h)
+GEN_VEXT_VV_RM(vssra_vv_w)
+GEN_VEXT_VV_RM(vssra_vv_d)
RVVCALL(OPIVX2_RM, vssra_vx_b, OP_SSS_B, H1, H1, vssra8)
RVVCALL(OPIVX2_RM, vssra_vx_h, OP_SSS_H, H2, H2, vssra16)
RVVCALL(OPIVX2_RM, vssra_vx_w, OP_SSS_W, H4, H4, vssra32)
RVVCALL(OPIVX2_RM, vssra_vx_d, OP_SSS_D, H8, H8, vssra64)
-GEN_VEXT_VX_RM(vssra_vx_b, 1, 1)
-GEN_VEXT_VX_RM(vssra_vx_h, 2, 2)
-GEN_VEXT_VX_RM(vssra_vx_w, 4, 4)
-GEN_VEXT_VX_RM(vssra_vx_d, 8, 8)
+GEN_VEXT_VX_RM(vssra_vx_b)
+GEN_VEXT_VX_RM(vssra_vx_h)
+GEN_VEXT_VX_RM(vssra_vx_w)
+GEN_VEXT_VX_RM(vssra_vx_d)
/* Vector Narrowing Fixed-Point Clip Instructions */
static inline int8_t
@@ -2720,16 +2718,16 @@ vnclip32(CPURISCVState *env, int vxrm, int64_t a, int32_t b)
RVVCALL(OPIVV2_RM, vnclip_wv_b, NOP_SSS_B, H1, H2, H1, vnclip8)
RVVCALL(OPIVV2_RM, vnclip_wv_h, NOP_SSS_H, H2, H4, H2, vnclip16)
RVVCALL(OPIVV2_RM, vnclip_wv_w, NOP_SSS_W, H4, H8, H4, vnclip32)
-GEN_VEXT_VV_RM(vnclip_wv_b, 1, 1)
-GEN_VEXT_VV_RM(vnclip_wv_h, 2, 2)
-GEN_VEXT_VV_RM(vnclip_wv_w, 4, 4)
+GEN_VEXT_VV_RM(vnclip_wv_b)
+GEN_VEXT_VV_RM(vnclip_wv_h)
+GEN_VEXT_VV_RM(vnclip_wv_w)
RVVCALL(OPIVX2_RM, vnclip_wx_b, NOP_SSS_B, H1, H2, vnclip8)
RVVCALL(OPIVX2_RM, vnclip_wx_h, NOP_SSS_H, H2, H4, vnclip16)
RVVCALL(OPIVX2_RM, vnclip_wx_w, NOP_SSS_W, H4, H8, vnclip32)
-GEN_VEXT_VX_RM(vnclip_wx_b, 1, 1)
-GEN_VEXT_VX_RM(vnclip_wx_h, 2, 2)
-GEN_VEXT_VX_RM(vnclip_wx_w, 4, 4)
+GEN_VEXT_VX_RM(vnclip_wx_b)
+GEN_VEXT_VX_RM(vnclip_wx_h)
+GEN_VEXT_VX_RM(vnclip_wx_w)
static inline uint8_t
vnclipu8(CPURISCVState *env, int vxrm, uint16_t a, uint8_t b)
@@ -2782,16 +2780,16 @@ vnclipu32(CPURISCVState *env, int vxrm, uint64_t a, uint32_t b)
RVVCALL(OPIVV2_RM, vnclipu_wv_b, NOP_UUU_B, H1, H2, H1, vnclipu8)
RVVCALL(OPIVV2_RM, vnclipu_wv_h, NOP_UUU_H, H2, H4, H2, vnclipu16)
RVVCALL(OPIVV2_RM, vnclipu_wv_w, NOP_UUU_W, H4, H8, H4, vnclipu32)
-GEN_VEXT_VV_RM(vnclipu_wv_b, 1, 1)
-GEN_VEXT_VV_RM(vnclipu_wv_h, 2, 2)
-GEN_VEXT_VV_RM(vnclipu_wv_w, 4, 4)
+GEN_VEXT_VV_RM(vnclipu_wv_b)
+GEN_VEXT_VV_RM(vnclipu_wv_h)
+GEN_VEXT_VV_RM(vnclipu_wv_w)
RVVCALL(OPIVX2_RM, vnclipu_wx_b, NOP_UUU_B, H1, H2, vnclipu8)
RVVCALL(OPIVX2_RM, vnclipu_wx_h, NOP_UUU_H, H2, H4, vnclipu16)
RVVCALL(OPIVX2_RM, vnclipu_wx_w, NOP_UUU_W, H4, H8, vnclipu32)
-GEN_VEXT_VX_RM(vnclipu_wx_b, 1, 1)
-GEN_VEXT_VX_RM(vnclipu_wx_h, 2, 2)
-GEN_VEXT_VX_RM(vnclipu_wx_w, 4, 4)
+GEN_VEXT_VX_RM(vnclipu_wx_b)
+GEN_VEXT_VX_RM(vnclipu_wx_h)
+GEN_VEXT_VX_RM(vnclipu_wx_w)
/*
*** Vector Float Point Arithmetic Instructions
@@ -2806,7 +2804,7 @@ static void do_##NAME(void *vd, void *vs1, void *vs2, int i, \
*((TD *)vd + HD(i)) = OP(s2, s1, &env->fp_status); \
}
-#define GEN_VEXT_VV_ENV(NAME, ESZ, DSZ) \
+#define GEN_VEXT_VV_ENV(NAME) \
void HELPER(NAME)(void *vd, void *v0, void *vs1, \
void *vs2, CPURISCVState *env, \
uint32_t desc) \
@@ -2827,9 +2825,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
RVVCALL(OPFVV2, vfadd_vv_h, OP_UUU_H, H2, H2, H2, float16_add)
RVVCALL(OPFVV2, vfadd_vv_w, OP_UUU_W, H4, H4, H4, float32_add)
RVVCALL(OPFVV2, vfadd_vv_d, OP_UUU_D, H8, H8, H8, float64_add)
-GEN_VEXT_VV_ENV(vfadd_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfadd_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfadd_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfadd_vv_h)
+GEN_VEXT_VV_ENV(vfadd_vv_w)
+GEN_VEXT_VV_ENV(vfadd_vv_d)
#define OPFVF2(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \
static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \
@@ -2839,7 +2837,7 @@ static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \
*((TD *)vd + HD(i)) = OP(s2, (TX1)(T1)s1, &env->fp_status);\
}
-#define GEN_VEXT_VF(NAME, ESZ, DSZ) \
+#define GEN_VEXT_VF(NAME) \
void HELPER(NAME)(void *vd, void *v0, uint64_t s1, \
void *vs2, CPURISCVState *env, \
uint32_t desc) \
@@ -2860,22 +2858,22 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, \
RVVCALL(OPFVF2, vfadd_vf_h, OP_UUU_H, H2, H2, float16_add)
RVVCALL(OPFVF2, vfadd_vf_w, OP_UUU_W, H4, H4, float32_add)
RVVCALL(OPFVF2, vfadd_vf_d, OP_UUU_D, H8, H8, float64_add)
-GEN_VEXT_VF(vfadd_vf_h, 2, 2)
-GEN_VEXT_VF(vfadd_vf_w, 4, 4)
-GEN_VEXT_VF(vfadd_vf_d, 8, 8)
+GEN_VEXT_VF(vfadd_vf_h)
+GEN_VEXT_VF(vfadd_vf_w)
+GEN_VEXT_VF(vfadd_vf_d)
RVVCALL(OPFVV2, vfsub_vv_h, OP_UUU_H, H2, H2, H2, float16_sub)
RVVCALL(OPFVV2, vfsub_vv_w, OP_UUU_W, H4, H4, H4, float32_sub)
RVVCALL(OPFVV2, vfsub_vv_d, OP_UUU_D, H8, H8, H8, float64_sub)
-GEN_VEXT_VV_ENV(vfsub_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfsub_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfsub_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfsub_vv_h)
+GEN_VEXT_VV_ENV(vfsub_vv_w)
+GEN_VEXT_VV_ENV(vfsub_vv_d)
RVVCALL(OPFVF2, vfsub_vf_h, OP_UUU_H, H2, H2, float16_sub)
RVVCALL(OPFVF2, vfsub_vf_w, OP_UUU_W, H4, H4, float32_sub)
RVVCALL(OPFVF2, vfsub_vf_d, OP_UUU_D, H8, H8, float64_sub)
-GEN_VEXT_VF(vfsub_vf_h, 2, 2)
-GEN_VEXT_VF(vfsub_vf_w, 4, 4)
-GEN_VEXT_VF(vfsub_vf_d, 8, 8)
+GEN_VEXT_VF(vfsub_vf_h)
+GEN_VEXT_VF(vfsub_vf_w)
+GEN_VEXT_VF(vfsub_vf_d)
static uint16_t float16_rsub(uint16_t a, uint16_t b, float_status *s)
{
@@ -2895,9 +2893,9 @@ static uint64_t float64_rsub(uint64_t a, uint64_t b, float_status *s)
RVVCALL(OPFVF2, vfrsub_vf_h, OP_UUU_H, H2, H2, float16_rsub)
RVVCALL(OPFVF2, vfrsub_vf_w, OP_UUU_W, H4, H4, float32_rsub)
RVVCALL(OPFVF2, vfrsub_vf_d, OP_UUU_D, H8, H8, float64_rsub)
-GEN_VEXT_VF(vfrsub_vf_h, 2, 2)
-GEN_VEXT_VF(vfrsub_vf_w, 4, 4)
-GEN_VEXT_VF(vfrsub_vf_d, 8, 8)
+GEN_VEXT_VF(vfrsub_vf_h)
+GEN_VEXT_VF(vfrsub_vf_w)
+GEN_VEXT_VF(vfrsub_vf_d)
/* Vector Widening Floating-Point Add/Subtract Instructions */
static uint32_t vfwadd16(uint16_t a, uint16_t b, float_status *s)
@@ -2915,12 +2913,12 @@ static uint64_t vfwadd32(uint32_t a, uint32_t b, float_status *s)
RVVCALL(OPFVV2, vfwadd_vv_h, WOP_UUU_H, H4, H2, H2, vfwadd16)
RVVCALL(OPFVV2, vfwadd_vv_w, WOP_UUU_W, H8, H4, H4, vfwadd32)
-GEN_VEXT_VV_ENV(vfwadd_vv_h, 2, 4)
-GEN_VEXT_VV_ENV(vfwadd_vv_w, 4, 8)
+GEN_VEXT_VV_ENV(vfwadd_vv_h)
+GEN_VEXT_VV_ENV(vfwadd_vv_w)
RVVCALL(OPFVF2, vfwadd_vf_h, WOP_UUU_H, H4, H2, vfwadd16)
RVVCALL(OPFVF2, vfwadd_vf_w, WOP_UUU_W, H8, H4, vfwadd32)
-GEN_VEXT_VF(vfwadd_vf_h, 2, 4)
-GEN_VEXT_VF(vfwadd_vf_w, 4, 8)
+GEN_VEXT_VF(vfwadd_vf_h)
+GEN_VEXT_VF(vfwadd_vf_w)
static uint32_t vfwsub16(uint16_t a, uint16_t b, float_status *s)
{
@@ -2937,12 +2935,12 @@ static uint64_t vfwsub32(uint32_t a, uint32_t b, float_status *s)
RVVCALL(OPFVV2, vfwsub_vv_h, WOP_UUU_H, H4, H2, H2, vfwsub16)
RVVCALL(OPFVV2, vfwsub_vv_w, WOP_UUU_W, H8, H4, H4, vfwsub32)
-GEN_VEXT_VV_ENV(vfwsub_vv_h, 2, 4)
-GEN_VEXT_VV_ENV(vfwsub_vv_w, 4, 8)
+GEN_VEXT_VV_ENV(vfwsub_vv_h)
+GEN_VEXT_VV_ENV(vfwsub_vv_w)
RVVCALL(OPFVF2, vfwsub_vf_h, WOP_UUU_H, H4, H2, vfwsub16)
RVVCALL(OPFVF2, vfwsub_vf_w, WOP_UUU_W, H8, H4, vfwsub32)
-GEN_VEXT_VF(vfwsub_vf_h, 2, 4)
-GEN_VEXT_VF(vfwsub_vf_w, 4, 8)
+GEN_VEXT_VF(vfwsub_vf_h)
+GEN_VEXT_VF(vfwsub_vf_w)
static uint32_t vfwaddw16(uint32_t a, uint16_t b, float_status *s)
{
@@ -2956,12 +2954,12 @@ static uint64_t vfwaddw32(uint64_t a, uint32_t b, float_status *s)
RVVCALL(OPFVV2, vfwadd_wv_h, WOP_WUUU_H, H4, H2, H2, vfwaddw16)
RVVCALL(OPFVV2, vfwadd_wv_w, WOP_WUUU_W, H8, H4, H4, vfwaddw32)
-GEN_VEXT_VV_ENV(vfwadd_wv_h, 2, 4)
-GEN_VEXT_VV_ENV(vfwadd_wv_w, 4, 8)
+GEN_VEXT_VV_ENV(vfwadd_wv_h)
+GEN_VEXT_VV_ENV(vfwadd_wv_w)
RVVCALL(OPFVF2, vfwadd_wf_h, WOP_WUUU_H, H4, H2, vfwaddw16)
RVVCALL(OPFVF2, vfwadd_wf_w, WOP_WUUU_W, H8, H4, vfwaddw32)
-GEN_VEXT_VF(vfwadd_wf_h, 2, 4)
-GEN_VEXT_VF(vfwadd_wf_w, 4, 8)
+GEN_VEXT_VF(vfwadd_wf_h)
+GEN_VEXT_VF(vfwadd_wf_w)
static uint32_t vfwsubw16(uint32_t a, uint16_t b, float_status *s)
{
@@ -2975,39 +2973,39 @@ static uint64_t vfwsubw32(uint64_t a, uint32_t b, float_status *s)
RVVCALL(OPFVV2, vfwsub_wv_h, WOP_WUUU_H, H4, H2, H2, vfwsubw16)
RVVCALL(OPFVV2, vfwsub_wv_w, WOP_WUUU_W, H8, H4, H4, vfwsubw32)
-GEN_VEXT_VV_ENV(vfwsub_wv_h, 2, 4)
-GEN_VEXT_VV_ENV(vfwsub_wv_w, 4, 8)
+GEN_VEXT_VV_ENV(vfwsub_wv_h)
+GEN_VEXT_VV_ENV(vfwsub_wv_w)
RVVCALL(OPFVF2, vfwsub_wf_h, WOP_WUUU_H, H4, H2, vfwsubw16)
RVVCALL(OPFVF2, vfwsub_wf_w, WOP_WUUU_W, H8, H4, vfwsubw32)
-GEN_VEXT_VF(vfwsub_wf_h, 2, 4)
-GEN_VEXT_VF(vfwsub_wf_w, 4, 8)
+GEN_VEXT_VF(vfwsub_wf_h)
+GEN_VEXT_VF(vfwsub_wf_w)
/* Vector Single-Width Floating-Point Multiply/Divide Instructions */
RVVCALL(OPFVV2, vfmul_vv_h, OP_UUU_H, H2, H2, H2, float16_mul)
RVVCALL(OPFVV2, vfmul_vv_w, OP_UUU_W, H4, H4, H4, float32_mul)
RVVCALL(OPFVV2, vfmul_vv_d, OP_UUU_D, H8, H8, H8, float64_mul)
-GEN_VEXT_VV_ENV(vfmul_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfmul_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfmul_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfmul_vv_h)
+GEN_VEXT_VV_ENV(vfmul_vv_w)
+GEN_VEXT_VV_ENV(vfmul_vv_d)
RVVCALL(OPFVF2, vfmul_vf_h, OP_UUU_H, H2, H2, float16_mul)
RVVCALL(OPFVF2, vfmul_vf_w, OP_UUU_W, H4, H4, float32_mul)
RVVCALL(OPFVF2, vfmul_vf_d, OP_UUU_D, H8, H8, float64_mul)
-GEN_VEXT_VF(vfmul_vf_h, 2, 2)
-GEN_VEXT_VF(vfmul_vf_w, 4, 4)
-GEN_VEXT_VF(vfmul_vf_d, 8, 8)
+GEN_VEXT_VF(vfmul_vf_h)
+GEN_VEXT_VF(vfmul_vf_w)
+GEN_VEXT_VF(vfmul_vf_d)
RVVCALL(OPFVV2, vfdiv_vv_h, OP_UUU_H, H2, H2, H2, float16_div)
RVVCALL(OPFVV2, vfdiv_vv_w, OP_UUU_W, H4, H4, H4, float32_div)
RVVCALL(OPFVV2, vfdiv_vv_d, OP_UUU_D, H8, H8, H8, float64_div)
-GEN_VEXT_VV_ENV(vfdiv_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfdiv_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfdiv_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfdiv_vv_h)
+GEN_VEXT_VV_ENV(vfdiv_vv_w)
+GEN_VEXT_VV_ENV(vfdiv_vv_d)
RVVCALL(OPFVF2, vfdiv_vf_h, OP_UUU_H, H2, H2, float16_div)
RVVCALL(OPFVF2, vfdiv_vf_w, OP_UUU_W, H4, H4, float32_div)
RVVCALL(OPFVF2, vfdiv_vf_d, OP_UUU_D, H8, H8, float64_div)
-GEN_VEXT_VF(vfdiv_vf_h, 2, 2)
-GEN_VEXT_VF(vfdiv_vf_w, 4, 4)
-GEN_VEXT_VF(vfdiv_vf_d, 8, 8)
+GEN_VEXT_VF(vfdiv_vf_h)
+GEN_VEXT_VF(vfdiv_vf_w)
+GEN_VEXT_VF(vfdiv_vf_d)
static uint16_t float16_rdiv(uint16_t a, uint16_t b, float_status *s)
{
@@ -3027,9 +3025,9 @@ static uint64_t float64_rdiv(uint64_t a, uint64_t b, float_status *s)
RVVCALL(OPFVF2, vfrdiv_vf_h, OP_UUU_H, H2, H2, float16_rdiv)
RVVCALL(OPFVF2, vfrdiv_vf_w, OP_UUU_W, H4, H4, float32_rdiv)
RVVCALL(OPFVF2, vfrdiv_vf_d, OP_UUU_D, H8, H8, float64_rdiv)
-GEN_VEXT_VF(vfrdiv_vf_h, 2, 2)
-GEN_VEXT_VF(vfrdiv_vf_w, 4, 4)
-GEN_VEXT_VF(vfrdiv_vf_d, 8, 8)
+GEN_VEXT_VF(vfrdiv_vf_h)
+GEN_VEXT_VF(vfrdiv_vf_w)
+GEN_VEXT_VF(vfrdiv_vf_d)
/* Vector Widening Floating-Point Multiply */
static uint32_t vfwmul16(uint16_t a, uint16_t b, float_status *s)
@@ -3046,12 +3044,12 @@ static uint64_t vfwmul32(uint32_t a, uint32_t b, float_status *s)
}
RVVCALL(OPFVV2, vfwmul_vv_h, WOP_UUU_H, H4, H2, H2, vfwmul16)
RVVCALL(OPFVV2, vfwmul_vv_w, WOP_UUU_W, H8, H4, H4, vfwmul32)
-GEN_VEXT_VV_ENV(vfwmul_vv_h, 2, 4)
-GEN_VEXT_VV_ENV(vfwmul_vv_w, 4, 8)
+GEN_VEXT_VV_ENV(vfwmul_vv_h)
+GEN_VEXT_VV_ENV(vfwmul_vv_w)
RVVCALL(OPFVF2, vfwmul_vf_h, WOP_UUU_H, H4, H2, vfwmul16)
RVVCALL(OPFVF2, vfwmul_vf_w, WOP_UUU_W, H8, H4, vfwmul32)
-GEN_VEXT_VF(vfwmul_vf_h, 2, 4)
-GEN_VEXT_VF(vfwmul_vf_w, 4, 8)
+GEN_VEXT_VF(vfwmul_vf_h)
+GEN_VEXT_VF(vfwmul_vf_w)
/* Vector Single-Width Floating-Point Fused Multiply-Add Instructions */
#define OPFVV3(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP) \
@@ -3082,9 +3080,9 @@ static uint64_t fmacc64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfmacc_vv_h, OP_UUU_H, H2, H2, H2, fmacc16)
RVVCALL(OPFVV3, vfmacc_vv_w, OP_UUU_W, H4, H4, H4, fmacc32)
RVVCALL(OPFVV3, vfmacc_vv_d, OP_UUU_D, H8, H8, H8, fmacc64)
-GEN_VEXT_VV_ENV(vfmacc_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfmacc_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfmacc_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfmacc_vv_h)
+GEN_VEXT_VV_ENV(vfmacc_vv_w)
+GEN_VEXT_VV_ENV(vfmacc_vv_d)
#define OPFVF3(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \
static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \
@@ -3098,9 +3096,9 @@ static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \
RVVCALL(OPFVF3, vfmacc_vf_h, OP_UUU_H, H2, H2, fmacc16)
RVVCALL(OPFVF3, vfmacc_vf_w, OP_UUU_W, H4, H4, fmacc32)
RVVCALL(OPFVF3, vfmacc_vf_d, OP_UUU_D, H8, H8, fmacc64)
-GEN_VEXT_VF(vfmacc_vf_h, 2, 2)
-GEN_VEXT_VF(vfmacc_vf_w, 4, 4)
-GEN_VEXT_VF(vfmacc_vf_d, 8, 8)
+GEN_VEXT_VF(vfmacc_vf_h)
+GEN_VEXT_VF(vfmacc_vf_w)
+GEN_VEXT_VF(vfmacc_vf_d)
static uint16_t fnmacc16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3123,15 +3121,15 @@ static uint64_t fnmacc64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfnmacc_vv_h, OP_UUU_H, H2, H2, H2, fnmacc16)
RVVCALL(OPFVV3, vfnmacc_vv_w, OP_UUU_W, H4, H4, H4, fnmacc32)
RVVCALL(OPFVV3, vfnmacc_vv_d, OP_UUU_D, H8, H8, H8, fnmacc64)
-GEN_VEXT_VV_ENV(vfnmacc_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfnmacc_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfnmacc_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfnmacc_vv_h)
+GEN_VEXT_VV_ENV(vfnmacc_vv_w)
+GEN_VEXT_VV_ENV(vfnmacc_vv_d)
RVVCALL(OPFVF3, vfnmacc_vf_h, OP_UUU_H, H2, H2, fnmacc16)
RVVCALL(OPFVF3, vfnmacc_vf_w, OP_UUU_W, H4, H4, fnmacc32)
RVVCALL(OPFVF3, vfnmacc_vf_d, OP_UUU_D, H8, H8, fnmacc64)
-GEN_VEXT_VF(vfnmacc_vf_h, 2, 2)
-GEN_VEXT_VF(vfnmacc_vf_w, 4, 4)
-GEN_VEXT_VF(vfnmacc_vf_d, 8, 8)
+GEN_VEXT_VF(vfnmacc_vf_h)
+GEN_VEXT_VF(vfnmacc_vf_w)
+GEN_VEXT_VF(vfnmacc_vf_d)
static uint16_t fmsac16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3151,15 +3149,15 @@ static uint64_t fmsac64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfmsac_vv_h, OP_UUU_H, H2, H2, H2, fmsac16)
RVVCALL(OPFVV3, vfmsac_vv_w, OP_UUU_W, H4, H4, H4, fmsac32)
RVVCALL(OPFVV3, vfmsac_vv_d, OP_UUU_D, H8, H8, H8, fmsac64)
-GEN_VEXT_VV_ENV(vfmsac_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfmsac_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfmsac_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfmsac_vv_h)
+GEN_VEXT_VV_ENV(vfmsac_vv_w)
+GEN_VEXT_VV_ENV(vfmsac_vv_d)
RVVCALL(OPFVF3, vfmsac_vf_h, OP_UUU_H, H2, H2, fmsac16)
RVVCALL(OPFVF3, vfmsac_vf_w, OP_UUU_W, H4, H4, fmsac32)
RVVCALL(OPFVF3, vfmsac_vf_d, OP_UUU_D, H8, H8, fmsac64)
-GEN_VEXT_VF(vfmsac_vf_h, 2, 2)
-GEN_VEXT_VF(vfmsac_vf_w, 4, 4)
-GEN_VEXT_VF(vfmsac_vf_d, 8, 8)
+GEN_VEXT_VF(vfmsac_vf_h)
+GEN_VEXT_VF(vfmsac_vf_w)
+GEN_VEXT_VF(vfmsac_vf_d)
static uint16_t fnmsac16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3179,15 +3177,15 @@ static uint64_t fnmsac64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfnmsac_vv_h, OP_UUU_H, H2, H2, H2, fnmsac16)
RVVCALL(OPFVV3, vfnmsac_vv_w, OP_UUU_W, H4, H4, H4, fnmsac32)
RVVCALL(OPFVV3, vfnmsac_vv_d, OP_UUU_D, H8, H8, H8, fnmsac64)
-GEN_VEXT_VV_ENV(vfnmsac_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfnmsac_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfnmsac_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfnmsac_vv_h)
+GEN_VEXT_VV_ENV(vfnmsac_vv_w)
+GEN_VEXT_VV_ENV(vfnmsac_vv_d)
RVVCALL(OPFVF3, vfnmsac_vf_h, OP_UUU_H, H2, H2, fnmsac16)
RVVCALL(OPFVF3, vfnmsac_vf_w, OP_UUU_W, H4, H4, fnmsac32)
RVVCALL(OPFVF3, vfnmsac_vf_d, OP_UUU_D, H8, H8, fnmsac64)
-GEN_VEXT_VF(vfnmsac_vf_h, 2, 2)
-GEN_VEXT_VF(vfnmsac_vf_w, 4, 4)
-GEN_VEXT_VF(vfnmsac_vf_d, 8, 8)
+GEN_VEXT_VF(vfnmsac_vf_h)
+GEN_VEXT_VF(vfnmsac_vf_w)
+GEN_VEXT_VF(vfnmsac_vf_d)
static uint16_t fmadd16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3207,15 +3205,15 @@ static uint64_t fmadd64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfmadd_vv_h, OP_UUU_H, H2, H2, H2, fmadd16)
RVVCALL(OPFVV3, vfmadd_vv_w, OP_UUU_W, H4, H4, H4, fmadd32)
RVVCALL(OPFVV3, vfmadd_vv_d, OP_UUU_D, H8, H8, H8, fmadd64)
-GEN_VEXT_VV_ENV(vfmadd_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfmadd_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfmadd_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfmadd_vv_h)
+GEN_VEXT_VV_ENV(vfmadd_vv_w)
+GEN_VEXT_VV_ENV(vfmadd_vv_d)
RVVCALL(OPFVF3, vfmadd_vf_h, OP_UUU_H, H2, H2, fmadd16)
RVVCALL(OPFVF3, vfmadd_vf_w, OP_UUU_W, H4, H4, fmadd32)
RVVCALL(OPFVF3, vfmadd_vf_d, OP_UUU_D, H8, H8, fmadd64)
-GEN_VEXT_VF(vfmadd_vf_h, 2, 2)
-GEN_VEXT_VF(vfmadd_vf_w, 4, 4)
-GEN_VEXT_VF(vfmadd_vf_d, 8, 8)
+GEN_VEXT_VF(vfmadd_vf_h)
+GEN_VEXT_VF(vfmadd_vf_w)
+GEN_VEXT_VF(vfmadd_vf_d)
static uint16_t fnmadd16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3238,15 +3236,15 @@ static uint64_t fnmadd64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfnmadd_vv_h, OP_UUU_H, H2, H2, H2, fnmadd16)
RVVCALL(OPFVV3, vfnmadd_vv_w, OP_UUU_W, H4, H4, H4, fnmadd32)
RVVCALL(OPFVV3, vfnmadd_vv_d, OP_UUU_D, H8, H8, H8, fnmadd64)
-GEN_VEXT_VV_ENV(vfnmadd_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfnmadd_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfnmadd_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfnmadd_vv_h)
+GEN_VEXT_VV_ENV(vfnmadd_vv_w)
+GEN_VEXT_VV_ENV(vfnmadd_vv_d)
RVVCALL(OPFVF3, vfnmadd_vf_h, OP_UUU_H, H2, H2, fnmadd16)
RVVCALL(OPFVF3, vfnmadd_vf_w, OP_UUU_W, H4, H4, fnmadd32)
RVVCALL(OPFVF3, vfnmadd_vf_d, OP_UUU_D, H8, H8, fnmadd64)
-GEN_VEXT_VF(vfnmadd_vf_h, 2, 2)
-GEN_VEXT_VF(vfnmadd_vf_w, 4, 4)
-GEN_VEXT_VF(vfnmadd_vf_d, 8, 8)
+GEN_VEXT_VF(vfnmadd_vf_h)
+GEN_VEXT_VF(vfnmadd_vf_w)
+GEN_VEXT_VF(vfnmadd_vf_d)
static uint16_t fmsub16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3266,15 +3264,15 @@ static uint64_t fmsub64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfmsub_vv_h, OP_UUU_H, H2, H2, H2, fmsub16)
RVVCALL(OPFVV3, vfmsub_vv_w, OP_UUU_W, H4, H4, H4, fmsub32)
RVVCALL(OPFVV3, vfmsub_vv_d, OP_UUU_D, H8, H8, H8, fmsub64)
-GEN_VEXT_VV_ENV(vfmsub_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfmsub_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfmsub_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfmsub_vv_h)
+GEN_VEXT_VV_ENV(vfmsub_vv_w)
+GEN_VEXT_VV_ENV(vfmsub_vv_d)
RVVCALL(OPFVF3, vfmsub_vf_h, OP_UUU_H, H2, H2, fmsub16)
RVVCALL(OPFVF3, vfmsub_vf_w, OP_UUU_W, H4, H4, fmsub32)
RVVCALL(OPFVF3, vfmsub_vf_d, OP_UUU_D, H8, H8, fmsub64)
-GEN_VEXT_VF(vfmsub_vf_h, 2, 2)
-GEN_VEXT_VF(vfmsub_vf_w, 4, 4)
-GEN_VEXT_VF(vfmsub_vf_d, 8, 8)
+GEN_VEXT_VF(vfmsub_vf_h)
+GEN_VEXT_VF(vfmsub_vf_w)
+GEN_VEXT_VF(vfmsub_vf_d)
static uint16_t fnmsub16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3294,15 +3292,15 @@ static uint64_t fnmsub64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfnmsub_vv_h, OP_UUU_H, H2, H2, H2, fnmsub16)
RVVCALL(OPFVV3, vfnmsub_vv_w, OP_UUU_W, H4, H4, H4, fnmsub32)
RVVCALL(OPFVV3, vfnmsub_vv_d, OP_UUU_D, H8, H8, H8, fnmsub64)
-GEN_VEXT_VV_ENV(vfnmsub_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfnmsub_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfnmsub_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfnmsub_vv_h)
+GEN_VEXT_VV_ENV(vfnmsub_vv_w)
+GEN_VEXT_VV_ENV(vfnmsub_vv_d)
RVVCALL(OPFVF3, vfnmsub_vf_h, OP_UUU_H, H2, H2, fnmsub16)
RVVCALL(OPFVF3, vfnmsub_vf_w, OP_UUU_W, H4, H4, fnmsub32)
RVVCALL(OPFVF3, vfnmsub_vf_d, OP_UUU_D, H8, H8, fnmsub64)
-GEN_VEXT_VF(vfnmsub_vf_h, 2, 2)
-GEN_VEXT_VF(vfnmsub_vf_w, 4, 4)
-GEN_VEXT_VF(vfnmsub_vf_d, 8, 8)
+GEN_VEXT_VF(vfnmsub_vf_h)
+GEN_VEXT_VF(vfnmsub_vf_w)
+GEN_VEXT_VF(vfnmsub_vf_d)
/* Vector Widening Floating-Point Fused Multiply-Add Instructions */
static uint32_t fwmacc16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
@@ -3319,12 +3317,12 @@ static uint64_t fwmacc32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfwmacc_vv_h, WOP_UUU_H, H4, H2, H2, fwmacc16)
RVVCALL(OPFVV3, vfwmacc_vv_w, WOP_UUU_W, H8, H4, H4, fwmacc32)
-GEN_VEXT_VV_ENV(vfwmacc_vv_h, 2, 4)
-GEN_VEXT_VV_ENV(vfwmacc_vv_w, 4, 8)
+GEN_VEXT_VV_ENV(vfwmacc_vv_h)
+GEN_VEXT_VV_ENV(vfwmacc_vv_w)
RVVCALL(OPFVF3, vfwmacc_vf_h, WOP_UUU_H, H4, H2, fwmacc16)
RVVCALL(OPFVF3, vfwmacc_vf_w, WOP_UUU_W, H8, H4, fwmacc32)
-GEN_VEXT_VF(vfwmacc_vf_h, 2, 4)
-GEN_VEXT_VF(vfwmacc_vf_w, 4, 8)
+GEN_VEXT_VF(vfwmacc_vf_h)
+GEN_VEXT_VF(vfwmacc_vf_w)
static uint32_t fwnmacc16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
{
@@ -3342,12 +3340,12 @@ static uint64_t fwnmacc32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfwnmacc_vv_h, WOP_UUU_H, H4, H2, H2, fwnmacc16)
RVVCALL(OPFVV3, vfwnmacc_vv_w, WOP_UUU_W, H8, H4, H4, fwnmacc32)
-GEN_VEXT_VV_ENV(vfwnmacc_vv_h, 2, 4)
-GEN_VEXT_VV_ENV(vfwnmacc_vv_w, 4, 8)
+GEN_VEXT_VV_ENV(vfwnmacc_vv_h)
+GEN_VEXT_VV_ENV(vfwnmacc_vv_w)
RVVCALL(OPFVF3, vfwnmacc_vf_h, WOP_UUU_H, H4, H2, fwnmacc16)
RVVCALL(OPFVF3, vfwnmacc_vf_w, WOP_UUU_W, H8, H4, fwnmacc32)
-GEN_VEXT_VF(vfwnmacc_vf_h, 2, 4)
-GEN_VEXT_VF(vfwnmacc_vf_w, 4, 8)
+GEN_VEXT_VF(vfwnmacc_vf_h)
+GEN_VEXT_VF(vfwnmacc_vf_w)
static uint32_t fwmsac16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
{
@@ -3365,12 +3363,12 @@ static uint64_t fwmsac32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfwmsac_vv_h, WOP_UUU_H, H4, H2, H2, fwmsac16)
RVVCALL(OPFVV3, vfwmsac_vv_w, WOP_UUU_W, H8, H4, H4, fwmsac32)
-GEN_VEXT_VV_ENV(vfwmsac_vv_h, 2, 4)
-GEN_VEXT_VV_ENV(vfwmsac_vv_w, 4, 8)
+GEN_VEXT_VV_ENV(vfwmsac_vv_h)
+GEN_VEXT_VV_ENV(vfwmsac_vv_w)
RVVCALL(OPFVF3, vfwmsac_vf_h, WOP_UUU_H, H4, H2, fwmsac16)
RVVCALL(OPFVF3, vfwmsac_vf_w, WOP_UUU_W, H8, H4, fwmsac32)
-GEN_VEXT_VF(vfwmsac_vf_h, 2, 4)
-GEN_VEXT_VF(vfwmsac_vf_w, 4, 8)
+GEN_VEXT_VF(vfwmsac_vf_h)
+GEN_VEXT_VF(vfwmsac_vf_w)
static uint32_t fwnmsac16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
{
@@ -3388,12 +3386,12 @@ static uint64_t fwnmsac32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfwnmsac_vv_h, WOP_UUU_H, H4, H2, H2, fwnmsac16)
RVVCALL(OPFVV3, vfwnmsac_vv_w, WOP_UUU_W, H8, H4, H4, fwnmsac32)
-GEN_VEXT_VV_ENV(vfwnmsac_vv_h, 2, 4)
-GEN_VEXT_VV_ENV(vfwnmsac_vv_w, 4, 8)
+GEN_VEXT_VV_ENV(vfwnmsac_vv_h)
+GEN_VEXT_VV_ENV(vfwnmsac_vv_w)
RVVCALL(OPFVF3, vfwnmsac_vf_h, WOP_UUU_H, H4, H2, fwnmsac16)
RVVCALL(OPFVF3, vfwnmsac_vf_w, WOP_UUU_W, H8, H4, fwnmsac32)
-GEN_VEXT_VF(vfwnmsac_vf_h, 2, 4)
-GEN_VEXT_VF(vfwnmsac_vf_w, 4, 8)
+GEN_VEXT_VF(vfwnmsac_vf_h)
+GEN_VEXT_VF(vfwnmsac_vf_w)
/* Vector Floating-Point Square-Root Instruction */
/* (TD, T2, TX2) */
@@ -3409,7 +3407,7 @@ static void do_##NAME(void *vd, void *vs2, int i, \
*((TD *)vd + HD(i)) = OP(s2, &env->fp_status); \
}
-#define GEN_VEXT_V_ENV(NAME, ESZ, DSZ) \
+#define GEN_VEXT_V_ENV(NAME) \
void HELPER(NAME)(void *vd, void *v0, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
@@ -3432,9 +3430,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \
RVVCALL(OPFVV1, vfsqrt_v_h, OP_UU_H, H2, H2, float16_sqrt)
RVVCALL(OPFVV1, vfsqrt_v_w, OP_UU_W, H4, H4, float32_sqrt)
RVVCALL(OPFVV1, vfsqrt_v_d, OP_UU_D, H8, H8, float64_sqrt)
-GEN_VEXT_V_ENV(vfsqrt_v_h, 2, 2)
-GEN_VEXT_V_ENV(vfsqrt_v_w, 4, 4)
-GEN_VEXT_V_ENV(vfsqrt_v_d, 8, 8)
+GEN_VEXT_V_ENV(vfsqrt_v_h)
+GEN_VEXT_V_ENV(vfsqrt_v_w)
+GEN_VEXT_V_ENV(vfsqrt_v_d)
/*
* Vector Floating-Point Reciprocal Square-Root Estimate Instruction
@@ -3614,9 +3612,9 @@ static float64 frsqrt7_d(float64 f, float_status *s)
RVVCALL(OPFVV1, vfrsqrt7_v_h, OP_UU_H, H2, H2, frsqrt7_h)
RVVCALL(OPFVV1, vfrsqrt7_v_w, OP_UU_W, H4, H4, frsqrt7_s)
RVVCALL(OPFVV1, vfrsqrt7_v_d, OP_UU_D, H8, H8, frsqrt7_d)
-GEN_VEXT_V_ENV(vfrsqrt7_v_h, 2, 2)
-GEN_VEXT_V_ENV(vfrsqrt7_v_w, 4, 4)
-GEN_VEXT_V_ENV(vfrsqrt7_v_d, 8, 8)
+GEN_VEXT_V_ENV(vfrsqrt7_v_h)
+GEN_VEXT_V_ENV(vfrsqrt7_v_w)
+GEN_VEXT_V_ENV(vfrsqrt7_v_d)
/*
* Vector Floating-Point Reciprocal Estimate Instruction
@@ -3805,36 +3803,36 @@ static float64 frec7_d(float64 f, float_status *s)
RVVCALL(OPFVV1, vfrec7_v_h, OP_UU_H, H2, H2, frec7_h)
RVVCALL(OPFVV1, vfrec7_v_w, OP_UU_W, H4, H4, frec7_s)
RVVCALL(OPFVV1, vfrec7_v_d, OP_UU_D, H8, H8, frec7_d)
-GEN_VEXT_V_ENV(vfrec7_v_h, 2, 2)
-GEN_VEXT_V_ENV(vfrec7_v_w, 4, 4)
-GEN_VEXT_V_ENV(vfrec7_v_d, 8, 8)
+GEN_VEXT_V_ENV(vfrec7_v_h)
+GEN_VEXT_V_ENV(vfrec7_v_w)
+GEN_VEXT_V_ENV(vfrec7_v_d)
/* Vector Floating-Point MIN/MAX Instructions */
RVVCALL(OPFVV2, vfmin_vv_h, OP_UUU_H, H2, H2, H2, float16_minimum_number)
RVVCALL(OPFVV2, vfmin_vv_w, OP_UUU_W, H4, H4, H4, float32_minimum_number)
RVVCALL(OPFVV2, vfmin_vv_d, OP_UUU_D, H8, H8, H8, float64_minimum_number)
-GEN_VEXT_VV_ENV(vfmin_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfmin_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfmin_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfmin_vv_h)
+GEN_VEXT_VV_ENV(vfmin_vv_w)
+GEN_VEXT_VV_ENV(vfmin_vv_d)
RVVCALL(OPFVF2, vfmin_vf_h, OP_UUU_H, H2, H2, float16_minimum_number)
RVVCALL(OPFVF2, vfmin_vf_w, OP_UUU_W, H4, H4, float32_minimum_number)
RVVCALL(OPFVF2, vfmin_vf_d, OP_UUU_D, H8, H8, float64_minimum_number)
-GEN_VEXT_VF(vfmin_vf_h, 2, 2)
-GEN_VEXT_VF(vfmin_vf_w, 4, 4)
-GEN_VEXT_VF(vfmin_vf_d, 8, 8)
+GEN_VEXT_VF(vfmin_vf_h)
+GEN_VEXT_VF(vfmin_vf_w)
+GEN_VEXT_VF(vfmin_vf_d)
RVVCALL(OPFVV2, vfmax_vv_h, OP_UUU_H, H2, H2, H2, float16_maximum_number)
RVVCALL(OPFVV2, vfmax_vv_w, OP_UUU_W, H4, H4, H4, float32_maximum_number)
RVVCALL(OPFVV2, vfmax_vv_d, OP_UUU_D, H8, H8, H8, float64_maximum_number)
-GEN_VEXT_VV_ENV(vfmax_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfmax_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfmax_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfmax_vv_h)
+GEN_VEXT_VV_ENV(vfmax_vv_w)
+GEN_VEXT_VV_ENV(vfmax_vv_d)
RVVCALL(OPFVF2, vfmax_vf_h, OP_UUU_H, H2, H2, float16_maximum_number)
RVVCALL(OPFVF2, vfmax_vf_w, OP_UUU_W, H4, H4, float32_maximum_number)
RVVCALL(OPFVF2, vfmax_vf_d, OP_UUU_D, H8, H8, float64_maximum_number)
-GEN_VEXT_VF(vfmax_vf_h, 2, 2)
-GEN_VEXT_VF(vfmax_vf_w, 4, 4)
-GEN_VEXT_VF(vfmax_vf_d, 8, 8)
+GEN_VEXT_VF(vfmax_vf_h)
+GEN_VEXT_VF(vfmax_vf_w)
+GEN_VEXT_VF(vfmax_vf_d)
/* Vector Floating-Point Sign-Injection Instructions */
static uint16_t fsgnj16(uint16_t a, uint16_t b, float_status *s)
@@ -3855,15 +3853,15 @@ static uint64_t fsgnj64(uint64_t a, uint64_t b, float_status *s)
RVVCALL(OPFVV2, vfsgnj_vv_h, OP_UUU_H, H2, H2, H2, fsgnj16)
RVVCALL(OPFVV2, vfsgnj_vv_w, OP_UUU_W, H4, H4, H4, fsgnj32)
RVVCALL(OPFVV2, vfsgnj_vv_d, OP_UUU_D, H8, H8, H8, fsgnj64)
-GEN_VEXT_VV_ENV(vfsgnj_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfsgnj_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfsgnj_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfsgnj_vv_h)
+GEN_VEXT_VV_ENV(vfsgnj_vv_w)
+GEN_VEXT_VV_ENV(vfsgnj_vv_d)
RVVCALL(OPFVF2, vfsgnj_vf_h, OP_UUU_H, H2, H2, fsgnj16)
RVVCALL(OPFVF2, vfsgnj_vf_w, OP_UUU_W, H4, H4, fsgnj32)
RVVCALL(OPFVF2, vfsgnj_vf_d, OP_UUU_D, H8, H8, fsgnj64)
-GEN_VEXT_VF(vfsgnj_vf_h, 2, 2)
-GEN_VEXT_VF(vfsgnj_vf_w, 4, 4)
-GEN_VEXT_VF(vfsgnj_vf_d, 8, 8)
+GEN_VEXT_VF(vfsgnj_vf_h)
+GEN_VEXT_VF(vfsgnj_vf_w)
+GEN_VEXT_VF(vfsgnj_vf_d)
static uint16_t fsgnjn16(uint16_t a, uint16_t b, float_status *s)
{
@@ -3883,15 +3881,15 @@ static uint64_t fsgnjn64(uint64_t a, uint64_t b, float_status *s)
RVVCALL(OPFVV2, vfsgnjn_vv_h, OP_UUU_H, H2, H2, H2, fsgnjn16)
RVVCALL(OPFVV2, vfsgnjn_vv_w, OP_UUU_W, H4, H4, H4, fsgnjn32)
RVVCALL(OPFVV2, vfsgnjn_vv_d, OP_UUU_D, H8, H8, H8, fsgnjn64)
-GEN_VEXT_VV_ENV(vfsgnjn_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfsgnjn_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfsgnjn_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfsgnjn_vv_h)
+GEN_VEXT_VV_ENV(vfsgnjn_vv_w)
+GEN_VEXT_VV_ENV(vfsgnjn_vv_d)
RVVCALL(OPFVF2, vfsgnjn_vf_h, OP_UUU_H, H2, H2, fsgnjn16)
RVVCALL(OPFVF2, vfsgnjn_vf_w, OP_UUU_W, H4, H4, fsgnjn32)
RVVCALL(OPFVF2, vfsgnjn_vf_d, OP_UUU_D, H8, H8, fsgnjn64)
-GEN_VEXT_VF(vfsgnjn_vf_h, 2, 2)
-GEN_VEXT_VF(vfsgnjn_vf_w, 4, 4)
-GEN_VEXT_VF(vfsgnjn_vf_d, 8, 8)
+GEN_VEXT_VF(vfsgnjn_vf_h)
+GEN_VEXT_VF(vfsgnjn_vf_w)
+GEN_VEXT_VF(vfsgnjn_vf_d)
static uint16_t fsgnjx16(uint16_t a, uint16_t b, float_status *s)
{
@@ -3911,15 +3909,15 @@ static uint64_t fsgnjx64(uint64_t a, uint64_t b, float_status *s)
RVVCALL(OPFVV2, vfsgnjx_vv_h, OP_UUU_H, H2, H2, H2, fsgnjx16)
RVVCALL(OPFVV2, vfsgnjx_vv_w, OP_UUU_W, H4, H4, H4, fsgnjx32)
RVVCALL(OPFVV2, vfsgnjx_vv_d, OP_UUU_D, H8, H8, H8, fsgnjx64)
-GEN_VEXT_VV_ENV(vfsgnjx_vv_h, 2, 2)
-GEN_VEXT_VV_ENV(vfsgnjx_vv_w, 4, 4)
-GEN_VEXT_VV_ENV(vfsgnjx_vv_d, 8, 8)
+GEN_VEXT_VV_ENV(vfsgnjx_vv_h)
+GEN_VEXT_VV_ENV(vfsgnjx_vv_w)
+GEN_VEXT_VV_ENV(vfsgnjx_vv_d)
RVVCALL(OPFVF2, vfsgnjx_vf_h, OP_UUU_H, H2, H2, fsgnjx16)
RVVCALL(OPFVF2, vfsgnjx_vf_w, OP_UUU_W, H4, H4, fsgnjx32)
RVVCALL(OPFVF2, vfsgnjx_vf_d, OP_UUU_D, H8, H8, fsgnjx64)
-GEN_VEXT_VF(vfsgnjx_vf_h, 2, 2)
-GEN_VEXT_VF(vfsgnjx_vf_w, 4, 4)
-GEN_VEXT_VF(vfsgnjx_vf_d, 8, 8)
+GEN_VEXT_VF(vfsgnjx_vf_h)
+GEN_VEXT_VF(vfsgnjx_vf_w)
+GEN_VEXT_VF(vfsgnjx_vf_d)
/* Vector Floating-Point Compare Instructions */
#define GEN_VEXT_CMP_VV_ENV(NAME, ETYPE, H, DO_OP) \
@@ -4063,7 +4061,7 @@ static void do_##NAME(void *vd, void *vs2, int i) \
*((TD *)vd + HD(i)) = OP(s2); \
}
-#define GEN_VEXT_V(NAME, ESZ, DSZ) \
+#define GEN_VEXT_V(NAME) \
void HELPER(NAME)(void *vd, void *v0, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
@@ -4140,9 +4138,9 @@ target_ulong fclass_d(uint64_t frs1)
RVVCALL(OPIVV1, vfclass_v_h, OP_UU_H, H2, H2, fclass_h)
RVVCALL(OPIVV1, vfclass_v_w, OP_UU_W, H4, H4, fclass_s)
RVVCALL(OPIVV1, vfclass_v_d, OP_UU_D, H8, H8, fclass_d)
-GEN_VEXT_V(vfclass_v_h, 2, 2)
-GEN_VEXT_V(vfclass_v_w, 4, 4)
-GEN_VEXT_V(vfclass_v_d, 8, 8)
+GEN_VEXT_V(vfclass_v_h)
+GEN_VEXT_V(vfclass_v_w)
+GEN_VEXT_V(vfclass_v_d)
/* Vector Floating-Point Merge Instruction */
#define GEN_VFMERGE_VF(NAME, ETYPE, H) \
@@ -4170,33 +4168,33 @@ GEN_VFMERGE_VF(vfmerge_vfm_d, int64_t, H8)
RVVCALL(OPFVV1, vfcvt_xu_f_v_h, OP_UU_H, H2, H2, float16_to_uint16)
RVVCALL(OPFVV1, vfcvt_xu_f_v_w, OP_UU_W, H4, H4, float32_to_uint32)
RVVCALL(OPFVV1, vfcvt_xu_f_v_d, OP_UU_D, H8, H8, float64_to_uint64)
-GEN_VEXT_V_ENV(vfcvt_xu_f_v_h, 2, 2)
-GEN_VEXT_V_ENV(vfcvt_xu_f_v_w, 4, 4)
-GEN_VEXT_V_ENV(vfcvt_xu_f_v_d, 8, 8)
+GEN_VEXT_V_ENV(vfcvt_xu_f_v_h)
+GEN_VEXT_V_ENV(vfcvt_xu_f_v_w)
+GEN_VEXT_V_ENV(vfcvt_xu_f_v_d)
/* vfcvt.x.f.v vd, vs2, vm # Convert float to signed integer. */
RVVCALL(OPFVV1, vfcvt_x_f_v_h, OP_UU_H, H2, H2, float16_to_int16)
RVVCALL(OPFVV1, vfcvt_x_f_v_w, OP_UU_W, H4, H4, float32_to_int32)
RVVCALL(OPFVV1, vfcvt_x_f_v_d, OP_UU_D, H8, H8, float64_to_int64)
-GEN_VEXT_V_ENV(vfcvt_x_f_v_h, 2, 2)
-GEN_VEXT_V_ENV(vfcvt_x_f_v_w, 4, 4)
-GEN_VEXT_V_ENV(vfcvt_x_f_v_d, 8, 8)
+GEN_VEXT_V_ENV(vfcvt_x_f_v_h)
+GEN_VEXT_V_ENV(vfcvt_x_f_v_w)
+GEN_VEXT_V_ENV(vfcvt_x_f_v_d)
/* vfcvt.f.xu.v vd, vs2, vm # Convert unsigned integer to float. */
RVVCALL(OPFVV1, vfcvt_f_xu_v_h, OP_UU_H, H2, H2, uint16_to_float16)
RVVCALL(OPFVV1, vfcvt_f_xu_v_w, OP_UU_W, H4, H4, uint32_to_float32)
RVVCALL(OPFVV1, vfcvt_f_xu_v_d, OP_UU_D, H8, H8, uint64_to_float64)
-GEN_VEXT_V_ENV(vfcvt_f_xu_v_h, 2, 2)
-GEN_VEXT_V_ENV(vfcvt_f_xu_v_w, 4, 4)
-GEN_VEXT_V_ENV(vfcvt_f_xu_v_d, 8, 8)
+GEN_VEXT_V_ENV(vfcvt_f_xu_v_h)
+GEN_VEXT_V_ENV(vfcvt_f_xu_v_w)
+GEN_VEXT_V_ENV(vfcvt_f_xu_v_d)
/* vfcvt.f.x.v vd, vs2, vm # Convert integer to float. */
RVVCALL(OPFVV1, vfcvt_f_x_v_h, OP_UU_H, H2, H2, int16_to_float16)
RVVCALL(OPFVV1, vfcvt_f_x_v_w, OP_UU_W, H4, H4, int32_to_float32)
RVVCALL(OPFVV1, vfcvt_f_x_v_d, OP_UU_D, H8, H8, int64_to_float64)
-GEN_VEXT_V_ENV(vfcvt_f_x_v_h, 2, 2)
-GEN_VEXT_V_ENV(vfcvt_f_x_v_w, 4, 4)
-GEN_VEXT_V_ENV(vfcvt_f_x_v_d, 8, 8)
+GEN_VEXT_V_ENV(vfcvt_f_x_v_h)
+GEN_VEXT_V_ENV(vfcvt_f_x_v_w)
+GEN_VEXT_V_ENV(vfcvt_f_x_v_d)
/* Widening Floating-Point/Integer Type-Convert Instructions */
/* (TD, T2, TX2) */
@@ -4206,30 +4204,30 @@ GEN_VEXT_V_ENV(vfcvt_f_x_v_d, 8, 8)
/* vfwcvt.xu.f.v vd, vs2, vm # Convert float to double-width unsigned integer.*/
RVVCALL(OPFVV1, vfwcvt_xu_f_v_h, WOP_UU_H, H4, H2, float16_to_uint32)
RVVCALL(OPFVV1, vfwcvt_xu_f_v_w, WOP_UU_W, H8, H4, float32_to_uint64)
-GEN_VEXT_V_ENV(vfwcvt_xu_f_v_h, 2, 4)
-GEN_VEXT_V_ENV(vfwcvt_xu_f_v_w, 4, 8)
+GEN_VEXT_V_ENV(vfwcvt_xu_f_v_h)
+GEN_VEXT_V_ENV(vfwcvt_xu_f_v_w)
/* vfwcvt.x.f.v vd, vs2, vm # Convert float to double-width signed integer. */
RVVCALL(OPFVV1, vfwcvt_x_f_v_h, WOP_UU_H, H4, H2, float16_to_int32)
RVVCALL(OPFVV1, vfwcvt_x_f_v_w, WOP_UU_W, H8, H4, float32_to_int64)
-GEN_VEXT_V_ENV(vfwcvt_x_f_v_h, 2, 4)
-GEN_VEXT_V_ENV(vfwcvt_x_f_v_w, 4, 8)
+GEN_VEXT_V_ENV(vfwcvt_x_f_v_h)
+GEN_VEXT_V_ENV(vfwcvt_x_f_v_w)
/* vfwcvt.f.xu.v vd, vs2, vm # Convert unsigned integer to double-width float */
RVVCALL(OPFVV1, vfwcvt_f_xu_v_b, WOP_UU_B, H2, H1, uint8_to_float16)
RVVCALL(OPFVV1, vfwcvt_f_xu_v_h, WOP_UU_H, H4, H2, uint16_to_float32)
RVVCALL(OPFVV1, vfwcvt_f_xu_v_w, WOP_UU_W, H8, H4, uint32_to_float64)
-GEN_VEXT_V_ENV(vfwcvt_f_xu_v_b, 1, 2)
-GEN_VEXT_V_ENV(vfwcvt_f_xu_v_h, 2, 4)
-GEN_VEXT_V_ENV(vfwcvt_f_xu_v_w, 4, 8)
+GEN_VEXT_V_ENV(vfwcvt_f_xu_v_b)
+GEN_VEXT_V_ENV(vfwcvt_f_xu_v_h)
+GEN_VEXT_V_ENV(vfwcvt_f_xu_v_w)
/* vfwcvt.f.x.v vd, vs2, vm # Convert integer to double-width float. */
RVVCALL(OPFVV1, vfwcvt_f_x_v_b, WOP_UU_B, H2, H1, int8_to_float16)
RVVCALL(OPFVV1, vfwcvt_f_x_v_h, WOP_UU_H, H4, H2, int16_to_float32)
RVVCALL(OPFVV1, vfwcvt_f_x_v_w, WOP_UU_W, H8, H4, int32_to_float64)
-GEN_VEXT_V_ENV(vfwcvt_f_x_v_b, 1, 2)
-GEN_VEXT_V_ENV(vfwcvt_f_x_v_h, 2, 4)
-GEN_VEXT_V_ENV(vfwcvt_f_x_v_w, 4, 8)
+GEN_VEXT_V_ENV(vfwcvt_f_x_v_b)
+GEN_VEXT_V_ENV(vfwcvt_f_x_v_h)
+GEN_VEXT_V_ENV(vfwcvt_f_x_v_w)
/*
* vfwcvt.f.f.v vd, vs2, vm
@@ -4242,8 +4240,8 @@ static uint32_t vfwcvtffv16(uint16_t a, float_status *s)
RVVCALL(OPFVV1, vfwcvt_f_f_v_h, WOP_UU_H, H4, H2, vfwcvtffv16)
RVVCALL(OPFVV1, vfwcvt_f_f_v_w, WOP_UU_W, H8, H4, float32_to_float64)
-GEN_VEXT_V_ENV(vfwcvt_f_f_v_h, 2, 4)
-GEN_VEXT_V_ENV(vfwcvt_f_f_v_w, 4, 8)
+GEN_VEXT_V_ENV(vfwcvt_f_f_v_h)
+GEN_VEXT_V_ENV(vfwcvt_f_f_v_w)
/* Narrowing Floating-Point/Integer Type-Convert Instructions */
/* (TD, T2, TX2) */
@@ -4254,29 +4252,29 @@ GEN_VEXT_V_ENV(vfwcvt_f_f_v_w, 4, 8)
RVVCALL(OPFVV1, vfncvt_xu_f_w_b, NOP_UU_B, H1, H2, float16_to_uint8)
RVVCALL(OPFVV1, vfncvt_xu_f_w_h, NOP_UU_H, H2, H4, float32_to_uint16)
RVVCALL(OPFVV1, vfncvt_xu_f_w_w, NOP_UU_W, H4, H8, float64_to_uint32)
-GEN_VEXT_V_ENV(vfncvt_xu_f_w_b, 1, 1)
-GEN_VEXT_V_ENV(vfncvt_xu_f_w_h, 2, 2)
-GEN_VEXT_V_ENV(vfncvt_xu_f_w_w, 4, 4)
+GEN_VEXT_V_ENV(vfncvt_xu_f_w_b)
+GEN_VEXT_V_ENV(vfncvt_xu_f_w_h)
+GEN_VEXT_V_ENV(vfncvt_xu_f_w_w)
/* vfncvt.x.f.v vd, vs2, vm # Convert double-width float to signed integer. */
RVVCALL(OPFVV1, vfncvt_x_f_w_b, NOP_UU_B, H1, H2, float16_to_int8)
RVVCALL(OPFVV1, vfncvt_x_f_w_h, NOP_UU_H, H2, H4, float32_to_int16)
RVVCALL(OPFVV1, vfncvt_x_f_w_w, NOP_UU_W, H4, H8, float64_to_int32)
-GEN_VEXT_V_ENV(vfncvt_x_f_w_b, 1, 1)
-GEN_VEXT_V_ENV(vfncvt_x_f_w_h, 2, 2)
-GEN_VEXT_V_ENV(vfncvt_x_f_w_w, 4, 4)
+GEN_VEXT_V_ENV(vfncvt_x_f_w_b)
+GEN_VEXT_V_ENV(vfncvt_x_f_w_h)
+GEN_VEXT_V_ENV(vfncvt_x_f_w_w)
/* vfncvt.f.xu.v vd, vs2, vm # Convert double-width unsigned integer to float */
RVVCALL(OPFVV1, vfncvt_f_xu_w_h, NOP_UU_H, H2, H4, uint32_to_float16)
RVVCALL(OPFVV1, vfncvt_f_xu_w_w, NOP_UU_W, H4, H8, uint64_to_float32)
-GEN_VEXT_V_ENV(vfncvt_f_xu_w_h, 2, 2)
-GEN_VEXT_V_ENV(vfncvt_f_xu_w_w, 4, 4)
+GEN_VEXT_V_ENV(vfncvt_f_xu_w_h)
+GEN_VEXT_V_ENV(vfncvt_f_xu_w_w)
/* vfncvt.f.x.v vd, vs2, vm # Convert double-width integer to float. */
RVVCALL(OPFVV1, vfncvt_f_x_w_h, NOP_UU_H, H2, H4, int32_to_float16)
RVVCALL(OPFVV1, vfncvt_f_x_w_w, NOP_UU_W, H4, H8, int64_to_float32)
-GEN_VEXT_V_ENV(vfncvt_f_x_w_h, 2, 2)
-GEN_VEXT_V_ENV(vfncvt_f_x_w_w, 4, 4)
+GEN_VEXT_V_ENV(vfncvt_f_x_w_h)
+GEN_VEXT_V_ENV(vfncvt_f_x_w_w)
/* vfncvt.f.f.v vd, vs2, vm # Convert double float to single-width float. */
static uint16_t vfncvtffv16(uint32_t a, float_status *s)
@@ -4286,8 +4284,8 @@ static uint16_t vfncvtffv16(uint32_t a, float_status *s)
RVVCALL(OPFVV1, vfncvt_f_f_w_h, NOP_UU_H, H2, H4, vfncvtffv16)
RVVCALL(OPFVV1, vfncvt_f_f_w_w, NOP_UU_W, H4, H8, float64_to_float32)
-GEN_VEXT_V_ENV(vfncvt_f_f_w_h, 2, 2)
-GEN_VEXT_V_ENV(vfncvt_f_f_w_w, 4, 4)
+GEN_VEXT_V_ENV(vfncvt_f_f_w_h)
+GEN_VEXT_V_ENV(vfncvt_f_f_w_w)
/*
*** Vector Reduction Operations
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 10/16] target/riscv: rvv: Add tail agnostic for vector integer merge and move instructions
@ 2022-05-13 11:50 ` ~eopxd
0 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-05-13 11:50 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/insn_trans/trans_rvv.c.inc | 12 ++++++++----
target/riscv/vector_helper.c | 20 ++++++++++++++++++++
2 files changed, 28 insertions(+), 4 deletions(-)
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index b03d459d84..50f874ceae 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -2082,12 +2082,13 @@ static bool trans_vmv_v_v(DisasContext *s, arg_vmv_v_v *a)
vext_check_isa_ill(s) &&
/* vmv.v.v has rs2 = 0 and vm = 1 */
vext_check_sss(s, a->rd, a->rs1, 0, 1)) {
- if (s->vl_eq_vlmax) {
+ if (s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
tcg_gen_gvec_mov(s->sew, vreg_ofs(s, a->rd),
vreg_ofs(s, a->rs1),
MAXSZ(s), MAXSZ(s));
} else {
uint32_t data = FIELD_DP32(0, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
static gen_helper_gvec_2_ptr * const fns[4] = {
gen_helper_vmv_v_v_b, gen_helper_vmv_v_v_h,
gen_helper_vmv_v_v_w, gen_helper_vmv_v_v_d,
@@ -2122,7 +2123,7 @@ static bool trans_vmv_v_x(DisasContext *s, arg_vmv_v_x *a)
s1 = get_gpr(s, a->rs1, EXT_SIGN);
- if (s->vl_eq_vlmax) {
+ if (s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
tcg_gen_gvec_dup_tl(s->sew, vreg_ofs(s, a->rd),
MAXSZ(s), MAXSZ(s), s1);
} else {
@@ -2130,6 +2131,7 @@ static bool trans_vmv_v_x(DisasContext *s, arg_vmv_v_x *a)
TCGv_i64 s1_i64 = tcg_temp_new_i64();
TCGv_ptr dest = tcg_temp_new_ptr();
uint32_t data = FIELD_DP32(0, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
static gen_helper_vmv_vx * const fns[4] = {
gen_helper_vmv_v_x_b, gen_helper_vmv_v_x_h,
gen_helper_vmv_v_x_w, gen_helper_vmv_v_x_d,
@@ -2159,7 +2161,7 @@ static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_i *a)
/* vmv.v.i has rs2 = 0 and vm = 1 */
vext_check_ss(s, a->rd, 0, 1)) {
int64_t simm = sextract64(a->rs1, 0, 5);
- if (s->vl_eq_vlmax) {
+ if (s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
tcg_gen_gvec_dup_imm(s->sew, vreg_ofs(s, a->rd),
MAXSZ(s), MAXSZ(s), simm);
mark_vs_dirty(s);
@@ -2168,6 +2170,7 @@ static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_i *a)
TCGv_i64 s1;
TCGv_ptr dest;
uint32_t data = FIELD_DP32(0, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
static gen_helper_vmv_vx * const fns[4] = {
gen_helper_vmv_v_x_b, gen_helper_vmv_v_x_h,
gen_helper_vmv_v_x_w, gen_helper_vmv_v_x_d,
@@ -2739,7 +2742,7 @@ static bool trans_vfmv_v_f(DisasContext *s, arg_vfmv_v_f *a)
TCGv_i64 t1;
- if (s->vl_eq_vlmax) {
+ if (s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
t1 = tcg_temp_new_i64();
/* NaN-box f[rs1] */
do_nanbox(s, t1, cpu_fpr[a->rs1]);
@@ -2751,6 +2754,7 @@ static bool trans_vfmv_v_f(DisasContext *s, arg_vfmv_v_f *a)
TCGv_ptr dest;
TCGv_i32 desc;
uint32_t data = FIELD_DP32(0, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
static gen_helper_vmv_vx * const fns[3] = {
gen_helper_vmv_v_x_h,
gen_helper_vmv_v_x_w,
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index b964b01a15..2bf670920a 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -1968,6 +1968,9 @@ void HELPER(NAME)(void *vd, void *vs1, CPURISCVState *env, \
uint32_t desc) \
{ \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -1975,6 +1978,8 @@ void HELPER(NAME)(void *vd, void *vs1, CPURISCVState *env, \
*((ETYPE *)vd + H(i)) = s1; \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VEXT_VMV_VV(vmv_v_v_b, int8_t, H1)
@@ -1987,12 +1992,17 @@ void HELPER(NAME)(void *vd, uint64_t s1, CPURISCVState *env, \
uint32_t desc) \
{ \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
*((ETYPE *)vd + H(i)) = (ETYPE)s1; \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VEXT_VMV_VX(vmv_v_x_b, int8_t, H1)
@@ -2005,6 +2015,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -2012,6 +2025,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
*((ETYPE *)vd + H(i)) = *(vt + H(i)); \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VEXT_VMERGE_VV(vmerge_vvm_b, int8_t, H1)
@@ -2024,6 +2039,9 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
void *vs2, CPURISCVState *env, uint32_t desc) \
{ \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -2033,6 +2051,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
*((ETYPE *)vd + H(i)) = d; \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VEXT_VMERGE_VX(vmerge_vxm_b, int8_t, H1)
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 11/16] target/riscv: rvv: Add tail agnostic for vector fix-point arithmetic instructions
@ 2022-05-13 11:50 ` ~eopxd
0 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-05-13 11:50 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/vector_helper.c | 220 ++++++++++++++++++-----------------
1 file changed, 114 insertions(+), 106 deletions(-)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 2bf670920a..db221797c6 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -2102,10 +2102,12 @@ static inline void
vext_vv_rm_2(void *vd, void *v0, void *vs1, void *vs2,
CPURISCVState *env,
uint32_t desc,
- opivv2_rm_fn *fn)
+ opivv2_rm_fn *fn, uint32_t esz)
{
uint32_t vm = vext_vm(desc);
uint32_t vl = env->vl;
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+ uint32_t vta = vext_vta(desc);
switch (env->vxrm) {
case 0: /* rnu */
@@ -2125,15 +2127,17 @@ vext_vv_rm_2(void *vd, void *v0, void *vs1, void *vs2,
env, vl, vm, 3, fn);
break;
}
+ /* set tail elements to 1s */
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz);
}
/* generate helpers for fixed point instructions with OPIVV format */
-#define GEN_VEXT_VV_RM(NAME) \
+#define GEN_VEXT_VV_RM(NAME, ESZ) \
void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
vext_vv_rm_2(vd, v0, vs1, vs2, env, desc, \
- do_##NAME); \
+ do_##NAME, ESZ); \
}
static inline uint8_t saddu8(CPURISCVState *env, int vxrm, uint8_t a, uint8_t b)
@@ -2183,10 +2187,10 @@ RVVCALL(OPIVV2_RM, vsaddu_vv_b, OP_UUU_B, H1, H1, H1, saddu8)
RVVCALL(OPIVV2_RM, vsaddu_vv_h, OP_UUU_H, H2, H2, H2, saddu16)
RVVCALL(OPIVV2_RM, vsaddu_vv_w, OP_UUU_W, H4, H4, H4, saddu32)
RVVCALL(OPIVV2_RM, vsaddu_vv_d, OP_UUU_D, H8, H8, H8, saddu64)
-GEN_VEXT_VV_RM(vsaddu_vv_b)
-GEN_VEXT_VV_RM(vsaddu_vv_h)
-GEN_VEXT_VV_RM(vsaddu_vv_w)
-GEN_VEXT_VV_RM(vsaddu_vv_d)
+GEN_VEXT_VV_RM(vsaddu_vv_b, 1)
+GEN_VEXT_VV_RM(vsaddu_vv_h, 2)
+GEN_VEXT_VV_RM(vsaddu_vv_w, 4)
+GEN_VEXT_VV_RM(vsaddu_vv_d, 8)
typedef void opivx2_rm_fn(void *vd, target_long s1, void *vs2, int i,
CPURISCVState *env, int vxrm);
@@ -2219,10 +2223,12 @@ static inline void
vext_vx_rm_2(void *vd, void *v0, target_long s1, void *vs2,
CPURISCVState *env,
uint32_t desc,
- opivx2_rm_fn *fn)
+ opivx2_rm_fn *fn, uint32_t esz)
{
uint32_t vm = vext_vm(desc);
uint32_t vl = env->vl;
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+ uint32_t vta = vext_vta(desc);
switch (env->vxrm) {
case 0: /* rnu */
@@ -2242,25 +2248,27 @@ vext_vx_rm_2(void *vd, void *v0, target_long s1, void *vs2,
env, vl, vm, 3, fn);
break;
}
+ /* set tail elements to 1s */
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz);
}
/* generate helpers for fixed point instructions with OPIVX format */
-#define GEN_VEXT_VX_RM(NAME) \
+#define GEN_VEXT_VX_RM(NAME, ESZ) \
void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
void *vs2, CPURISCVState *env, uint32_t desc) \
{ \
vext_vx_rm_2(vd, v0, s1, vs2, env, desc, \
- do_##NAME); \
+ do_##NAME, ESZ); \
}
RVVCALL(OPIVX2_RM, vsaddu_vx_b, OP_UUU_B, H1, H1, saddu8)
RVVCALL(OPIVX2_RM, vsaddu_vx_h, OP_UUU_H, H2, H2, saddu16)
RVVCALL(OPIVX2_RM, vsaddu_vx_w, OP_UUU_W, H4, H4, saddu32)
RVVCALL(OPIVX2_RM, vsaddu_vx_d, OP_UUU_D, H8, H8, saddu64)
-GEN_VEXT_VX_RM(vsaddu_vx_b)
-GEN_VEXT_VX_RM(vsaddu_vx_h)
-GEN_VEXT_VX_RM(vsaddu_vx_w)
-GEN_VEXT_VX_RM(vsaddu_vx_d)
+GEN_VEXT_VX_RM(vsaddu_vx_b, 1)
+GEN_VEXT_VX_RM(vsaddu_vx_h, 2)
+GEN_VEXT_VX_RM(vsaddu_vx_w, 4)
+GEN_VEXT_VX_RM(vsaddu_vx_d, 8)
static inline int8_t sadd8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
{
@@ -2306,19 +2314,19 @@ RVVCALL(OPIVV2_RM, vsadd_vv_b, OP_SSS_B, H1, H1, H1, sadd8)
RVVCALL(OPIVV2_RM, vsadd_vv_h, OP_SSS_H, H2, H2, H2, sadd16)
RVVCALL(OPIVV2_RM, vsadd_vv_w, OP_SSS_W, H4, H4, H4, sadd32)
RVVCALL(OPIVV2_RM, vsadd_vv_d, OP_SSS_D, H8, H8, H8, sadd64)
-GEN_VEXT_VV_RM(vsadd_vv_b)
-GEN_VEXT_VV_RM(vsadd_vv_h)
-GEN_VEXT_VV_RM(vsadd_vv_w)
-GEN_VEXT_VV_RM(vsadd_vv_d)
+GEN_VEXT_VV_RM(vsadd_vv_b, 1)
+GEN_VEXT_VV_RM(vsadd_vv_h, 2)
+GEN_VEXT_VV_RM(vsadd_vv_w, 4)
+GEN_VEXT_VV_RM(vsadd_vv_d, 8)
RVVCALL(OPIVX2_RM, vsadd_vx_b, OP_SSS_B, H1, H1, sadd8)
RVVCALL(OPIVX2_RM, vsadd_vx_h, OP_SSS_H, H2, H2, sadd16)
RVVCALL(OPIVX2_RM, vsadd_vx_w, OP_SSS_W, H4, H4, sadd32)
RVVCALL(OPIVX2_RM, vsadd_vx_d, OP_SSS_D, H8, H8, sadd64)
-GEN_VEXT_VX_RM(vsadd_vx_b)
-GEN_VEXT_VX_RM(vsadd_vx_h)
-GEN_VEXT_VX_RM(vsadd_vx_w)
-GEN_VEXT_VX_RM(vsadd_vx_d)
+GEN_VEXT_VX_RM(vsadd_vx_b, 1)
+GEN_VEXT_VX_RM(vsadd_vx_h, 2)
+GEN_VEXT_VX_RM(vsadd_vx_w, 4)
+GEN_VEXT_VX_RM(vsadd_vx_d, 8)
static inline uint8_t ssubu8(CPURISCVState *env, int vxrm, uint8_t a, uint8_t b)
{
@@ -2367,19 +2375,19 @@ RVVCALL(OPIVV2_RM, vssubu_vv_b, OP_UUU_B, H1, H1, H1, ssubu8)
RVVCALL(OPIVV2_RM, vssubu_vv_h, OP_UUU_H, H2, H2, H2, ssubu16)
RVVCALL(OPIVV2_RM, vssubu_vv_w, OP_UUU_W, H4, H4, H4, ssubu32)
RVVCALL(OPIVV2_RM, vssubu_vv_d, OP_UUU_D, H8, H8, H8, ssubu64)
-GEN_VEXT_VV_RM(vssubu_vv_b)
-GEN_VEXT_VV_RM(vssubu_vv_h)
-GEN_VEXT_VV_RM(vssubu_vv_w)
-GEN_VEXT_VV_RM(vssubu_vv_d)
+GEN_VEXT_VV_RM(vssubu_vv_b, 1)
+GEN_VEXT_VV_RM(vssubu_vv_h, 2)
+GEN_VEXT_VV_RM(vssubu_vv_w, 4)
+GEN_VEXT_VV_RM(vssubu_vv_d, 8)
RVVCALL(OPIVX2_RM, vssubu_vx_b, OP_UUU_B, H1, H1, ssubu8)
RVVCALL(OPIVX2_RM, vssubu_vx_h, OP_UUU_H, H2, H2, ssubu16)
RVVCALL(OPIVX2_RM, vssubu_vx_w, OP_UUU_W, H4, H4, ssubu32)
RVVCALL(OPIVX2_RM, vssubu_vx_d, OP_UUU_D, H8, H8, ssubu64)
-GEN_VEXT_VX_RM(vssubu_vx_b)
-GEN_VEXT_VX_RM(vssubu_vx_h)
-GEN_VEXT_VX_RM(vssubu_vx_w)
-GEN_VEXT_VX_RM(vssubu_vx_d)
+GEN_VEXT_VX_RM(vssubu_vx_b, 1)
+GEN_VEXT_VX_RM(vssubu_vx_h, 2)
+GEN_VEXT_VX_RM(vssubu_vx_w, 4)
+GEN_VEXT_VX_RM(vssubu_vx_d, 8)
static inline int8_t ssub8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
{
@@ -2425,19 +2433,19 @@ RVVCALL(OPIVV2_RM, vssub_vv_b, OP_SSS_B, H1, H1, H1, ssub8)
RVVCALL(OPIVV2_RM, vssub_vv_h, OP_SSS_H, H2, H2, H2, ssub16)
RVVCALL(OPIVV2_RM, vssub_vv_w, OP_SSS_W, H4, H4, H4, ssub32)
RVVCALL(OPIVV2_RM, vssub_vv_d, OP_SSS_D, H8, H8, H8, ssub64)
-GEN_VEXT_VV_RM(vssub_vv_b)
-GEN_VEXT_VV_RM(vssub_vv_h)
-GEN_VEXT_VV_RM(vssub_vv_w)
-GEN_VEXT_VV_RM(vssub_vv_d)
+GEN_VEXT_VV_RM(vssub_vv_b, 1)
+GEN_VEXT_VV_RM(vssub_vv_h, 2)
+GEN_VEXT_VV_RM(vssub_vv_w, 4)
+GEN_VEXT_VV_RM(vssub_vv_d, 8)
RVVCALL(OPIVX2_RM, vssub_vx_b, OP_SSS_B, H1, H1, ssub8)
RVVCALL(OPIVX2_RM, vssub_vx_h, OP_SSS_H, H2, H2, ssub16)
RVVCALL(OPIVX2_RM, vssub_vx_w, OP_SSS_W, H4, H4, ssub32)
RVVCALL(OPIVX2_RM, vssub_vx_d, OP_SSS_D, H8, H8, ssub64)
-GEN_VEXT_VX_RM(vssub_vx_b)
-GEN_VEXT_VX_RM(vssub_vx_h)
-GEN_VEXT_VX_RM(vssub_vx_w)
-GEN_VEXT_VX_RM(vssub_vx_d)
+GEN_VEXT_VX_RM(vssub_vx_b, 1)
+GEN_VEXT_VX_RM(vssub_vx_h, 2)
+GEN_VEXT_VX_RM(vssub_vx_w, 4)
+GEN_VEXT_VX_RM(vssub_vx_d, 8)
/* Vector Single-Width Averaging Add and Subtract */
static inline uint8_t get_round(int vxrm, uint64_t v, uint8_t shift)
@@ -2489,19 +2497,19 @@ RVVCALL(OPIVV2_RM, vaadd_vv_b, OP_SSS_B, H1, H1, H1, aadd32)
RVVCALL(OPIVV2_RM, vaadd_vv_h, OP_SSS_H, H2, H2, H2, aadd32)
RVVCALL(OPIVV2_RM, vaadd_vv_w, OP_SSS_W, H4, H4, H4, aadd32)
RVVCALL(OPIVV2_RM, vaadd_vv_d, OP_SSS_D, H8, H8, H8, aadd64)
-GEN_VEXT_VV_RM(vaadd_vv_b)
-GEN_VEXT_VV_RM(vaadd_vv_h)
-GEN_VEXT_VV_RM(vaadd_vv_w)
-GEN_VEXT_VV_RM(vaadd_vv_d)
+GEN_VEXT_VV_RM(vaadd_vv_b, 1)
+GEN_VEXT_VV_RM(vaadd_vv_h, 2)
+GEN_VEXT_VV_RM(vaadd_vv_w, 4)
+GEN_VEXT_VV_RM(vaadd_vv_d, 8)
RVVCALL(OPIVX2_RM, vaadd_vx_b, OP_SSS_B, H1, H1, aadd32)
RVVCALL(OPIVX2_RM, vaadd_vx_h, OP_SSS_H, H2, H2, aadd32)
RVVCALL(OPIVX2_RM, vaadd_vx_w, OP_SSS_W, H4, H4, aadd32)
RVVCALL(OPIVX2_RM, vaadd_vx_d, OP_SSS_D, H8, H8, aadd64)
-GEN_VEXT_VX_RM(vaadd_vx_b)
-GEN_VEXT_VX_RM(vaadd_vx_h)
-GEN_VEXT_VX_RM(vaadd_vx_w)
-GEN_VEXT_VX_RM(vaadd_vx_d)
+GEN_VEXT_VX_RM(vaadd_vx_b, 1)
+GEN_VEXT_VX_RM(vaadd_vx_h, 2)
+GEN_VEXT_VX_RM(vaadd_vx_w, 4)
+GEN_VEXT_VX_RM(vaadd_vx_d, 8)
static inline uint32_t aaddu32(CPURISCVState *env, int vxrm,
uint32_t a, uint32_t b)
@@ -2526,19 +2534,19 @@ RVVCALL(OPIVV2_RM, vaaddu_vv_b, OP_UUU_B, H1, H1, H1, aaddu32)
RVVCALL(OPIVV2_RM, vaaddu_vv_h, OP_UUU_H, H2, H2, H2, aaddu32)
RVVCALL(OPIVV2_RM, vaaddu_vv_w, OP_UUU_W, H4, H4, H4, aaddu32)
RVVCALL(OPIVV2_RM, vaaddu_vv_d, OP_UUU_D, H8, H8, H8, aaddu64)
-GEN_VEXT_VV_RM(vaaddu_vv_b)
-GEN_VEXT_VV_RM(vaaddu_vv_h)
-GEN_VEXT_VV_RM(vaaddu_vv_w)
-GEN_VEXT_VV_RM(vaaddu_vv_d)
+GEN_VEXT_VV_RM(vaaddu_vv_b, 1)
+GEN_VEXT_VV_RM(vaaddu_vv_h, 2)
+GEN_VEXT_VV_RM(vaaddu_vv_w, 4)
+GEN_VEXT_VV_RM(vaaddu_vv_d, 8)
RVVCALL(OPIVX2_RM, vaaddu_vx_b, OP_UUU_B, H1, H1, aaddu32)
RVVCALL(OPIVX2_RM, vaaddu_vx_h, OP_UUU_H, H2, H2, aaddu32)
RVVCALL(OPIVX2_RM, vaaddu_vx_w, OP_UUU_W, H4, H4, aaddu32)
RVVCALL(OPIVX2_RM, vaaddu_vx_d, OP_UUU_D, H8, H8, aaddu64)
-GEN_VEXT_VX_RM(vaaddu_vx_b)
-GEN_VEXT_VX_RM(vaaddu_vx_h)
-GEN_VEXT_VX_RM(vaaddu_vx_w)
-GEN_VEXT_VX_RM(vaaddu_vx_d)
+GEN_VEXT_VX_RM(vaaddu_vx_b, 1)
+GEN_VEXT_VX_RM(vaaddu_vx_h, 2)
+GEN_VEXT_VX_RM(vaaddu_vx_w, 4)
+GEN_VEXT_VX_RM(vaaddu_vx_d, 8)
static inline int32_t asub32(CPURISCVState *env, int vxrm, int32_t a, int32_t b)
{
@@ -2562,19 +2570,19 @@ RVVCALL(OPIVV2_RM, vasub_vv_b, OP_SSS_B, H1, H1, H1, asub32)
RVVCALL(OPIVV2_RM, vasub_vv_h, OP_SSS_H, H2, H2, H2, asub32)
RVVCALL(OPIVV2_RM, vasub_vv_w, OP_SSS_W, H4, H4, H4, asub32)
RVVCALL(OPIVV2_RM, vasub_vv_d, OP_SSS_D, H8, H8, H8, asub64)
-GEN_VEXT_VV_RM(vasub_vv_b)
-GEN_VEXT_VV_RM(vasub_vv_h)
-GEN_VEXT_VV_RM(vasub_vv_w)
-GEN_VEXT_VV_RM(vasub_vv_d)
+GEN_VEXT_VV_RM(vasub_vv_b, 1)
+GEN_VEXT_VV_RM(vasub_vv_h, 2)
+GEN_VEXT_VV_RM(vasub_vv_w, 4)
+GEN_VEXT_VV_RM(vasub_vv_d, 8)
RVVCALL(OPIVX2_RM, vasub_vx_b, OP_SSS_B, H1, H1, asub32)
RVVCALL(OPIVX2_RM, vasub_vx_h, OP_SSS_H, H2, H2, asub32)
RVVCALL(OPIVX2_RM, vasub_vx_w, OP_SSS_W, H4, H4, asub32)
RVVCALL(OPIVX2_RM, vasub_vx_d, OP_SSS_D, H8, H8, asub64)
-GEN_VEXT_VX_RM(vasub_vx_b)
-GEN_VEXT_VX_RM(vasub_vx_h)
-GEN_VEXT_VX_RM(vasub_vx_w)
-GEN_VEXT_VX_RM(vasub_vx_d)
+GEN_VEXT_VX_RM(vasub_vx_b, 1)
+GEN_VEXT_VX_RM(vasub_vx_h, 2)
+GEN_VEXT_VX_RM(vasub_vx_w, 4)
+GEN_VEXT_VX_RM(vasub_vx_d, 8)
static inline uint32_t asubu32(CPURISCVState *env, int vxrm,
uint32_t a, uint32_t b)
@@ -2599,19 +2607,19 @@ RVVCALL(OPIVV2_RM, vasubu_vv_b, OP_UUU_B, H1, H1, H1, asubu32)
RVVCALL(OPIVV2_RM, vasubu_vv_h, OP_UUU_H, H2, H2, H2, asubu32)
RVVCALL(OPIVV2_RM, vasubu_vv_w, OP_UUU_W, H4, H4, H4, asubu32)
RVVCALL(OPIVV2_RM, vasubu_vv_d, OP_UUU_D, H8, H8, H8, asubu64)
-GEN_VEXT_VV_RM(vasubu_vv_b)
-GEN_VEXT_VV_RM(vasubu_vv_h)
-GEN_VEXT_VV_RM(vasubu_vv_w)
-GEN_VEXT_VV_RM(vasubu_vv_d)
+GEN_VEXT_VV_RM(vasubu_vv_b, 1)
+GEN_VEXT_VV_RM(vasubu_vv_h, 2)
+GEN_VEXT_VV_RM(vasubu_vv_w, 4)
+GEN_VEXT_VV_RM(vasubu_vv_d, 8)
RVVCALL(OPIVX2_RM, vasubu_vx_b, OP_UUU_B, H1, H1, asubu32)
RVVCALL(OPIVX2_RM, vasubu_vx_h, OP_UUU_H, H2, H2, asubu32)
RVVCALL(OPIVX2_RM, vasubu_vx_w, OP_UUU_W, H4, H4, asubu32)
RVVCALL(OPIVX2_RM, vasubu_vx_d, OP_UUU_D, H8, H8, asubu64)
-GEN_VEXT_VX_RM(vasubu_vx_b)
-GEN_VEXT_VX_RM(vasubu_vx_h)
-GEN_VEXT_VX_RM(vasubu_vx_w)
-GEN_VEXT_VX_RM(vasubu_vx_d)
+GEN_VEXT_VX_RM(vasubu_vx_b, 1)
+GEN_VEXT_VX_RM(vasubu_vx_h, 2)
+GEN_VEXT_VX_RM(vasubu_vx_w, 4)
+GEN_VEXT_VX_RM(vasubu_vx_d, 8)
/* Vector Single-Width Fractional Multiply with Rounding and Saturation */
static inline int8_t vsmul8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
@@ -2706,19 +2714,19 @@ RVVCALL(OPIVV2_RM, vsmul_vv_b, OP_SSS_B, H1, H1, H1, vsmul8)
RVVCALL(OPIVV2_RM, vsmul_vv_h, OP_SSS_H, H2, H2, H2, vsmul16)
RVVCALL(OPIVV2_RM, vsmul_vv_w, OP_SSS_W, H4, H4, H4, vsmul32)
RVVCALL(OPIVV2_RM, vsmul_vv_d, OP_SSS_D, H8, H8, H8, vsmul64)
-GEN_VEXT_VV_RM(vsmul_vv_b)
-GEN_VEXT_VV_RM(vsmul_vv_h)
-GEN_VEXT_VV_RM(vsmul_vv_w)
-GEN_VEXT_VV_RM(vsmul_vv_d)
+GEN_VEXT_VV_RM(vsmul_vv_b, 1)
+GEN_VEXT_VV_RM(vsmul_vv_h, 2)
+GEN_VEXT_VV_RM(vsmul_vv_w, 4)
+GEN_VEXT_VV_RM(vsmul_vv_d, 8)
RVVCALL(OPIVX2_RM, vsmul_vx_b, OP_SSS_B, H1, H1, vsmul8)
RVVCALL(OPIVX2_RM, vsmul_vx_h, OP_SSS_H, H2, H2, vsmul16)
RVVCALL(OPIVX2_RM, vsmul_vx_w, OP_SSS_W, H4, H4, vsmul32)
RVVCALL(OPIVX2_RM, vsmul_vx_d, OP_SSS_D, H8, H8, vsmul64)
-GEN_VEXT_VX_RM(vsmul_vx_b)
-GEN_VEXT_VX_RM(vsmul_vx_h)
-GEN_VEXT_VX_RM(vsmul_vx_w)
-GEN_VEXT_VX_RM(vsmul_vx_d)
+GEN_VEXT_VX_RM(vsmul_vx_b, 1)
+GEN_VEXT_VX_RM(vsmul_vx_h, 2)
+GEN_VEXT_VX_RM(vsmul_vx_w, 4)
+GEN_VEXT_VX_RM(vsmul_vx_d, 8)
/* Vector Single-Width Scaling Shift Instructions */
static inline uint8_t
@@ -2765,19 +2773,19 @@ RVVCALL(OPIVV2_RM, vssrl_vv_b, OP_UUU_B, H1, H1, H1, vssrl8)
RVVCALL(OPIVV2_RM, vssrl_vv_h, OP_UUU_H, H2, H2, H2, vssrl16)
RVVCALL(OPIVV2_RM, vssrl_vv_w, OP_UUU_W, H4, H4, H4, vssrl32)
RVVCALL(OPIVV2_RM, vssrl_vv_d, OP_UUU_D, H8, H8, H8, vssrl64)
-GEN_VEXT_VV_RM(vssrl_vv_b)
-GEN_VEXT_VV_RM(vssrl_vv_h)
-GEN_VEXT_VV_RM(vssrl_vv_w)
-GEN_VEXT_VV_RM(vssrl_vv_d)
+GEN_VEXT_VV_RM(vssrl_vv_b, 1)
+GEN_VEXT_VV_RM(vssrl_vv_h, 2)
+GEN_VEXT_VV_RM(vssrl_vv_w, 4)
+GEN_VEXT_VV_RM(vssrl_vv_d, 8)
RVVCALL(OPIVX2_RM, vssrl_vx_b, OP_UUU_B, H1, H1, vssrl8)
RVVCALL(OPIVX2_RM, vssrl_vx_h, OP_UUU_H, H2, H2, vssrl16)
RVVCALL(OPIVX2_RM, vssrl_vx_w, OP_UUU_W, H4, H4, vssrl32)
RVVCALL(OPIVX2_RM, vssrl_vx_d, OP_UUU_D, H8, H8, vssrl64)
-GEN_VEXT_VX_RM(vssrl_vx_b)
-GEN_VEXT_VX_RM(vssrl_vx_h)
-GEN_VEXT_VX_RM(vssrl_vx_w)
-GEN_VEXT_VX_RM(vssrl_vx_d)
+GEN_VEXT_VX_RM(vssrl_vx_b, 1)
+GEN_VEXT_VX_RM(vssrl_vx_h, 2)
+GEN_VEXT_VX_RM(vssrl_vx_w, 4)
+GEN_VEXT_VX_RM(vssrl_vx_d, 8)
static inline int8_t
vssra8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
@@ -2824,19 +2832,19 @@ RVVCALL(OPIVV2_RM, vssra_vv_b, OP_SSS_B, H1, H1, H1, vssra8)
RVVCALL(OPIVV2_RM, vssra_vv_h, OP_SSS_H, H2, H2, H2, vssra16)
RVVCALL(OPIVV2_RM, vssra_vv_w, OP_SSS_W, H4, H4, H4, vssra32)
RVVCALL(OPIVV2_RM, vssra_vv_d, OP_SSS_D, H8, H8, H8, vssra64)
-GEN_VEXT_VV_RM(vssra_vv_b)
-GEN_VEXT_VV_RM(vssra_vv_h)
-GEN_VEXT_VV_RM(vssra_vv_w)
-GEN_VEXT_VV_RM(vssra_vv_d)
+GEN_VEXT_VV_RM(vssra_vv_b, 1)
+GEN_VEXT_VV_RM(vssra_vv_h, 2)
+GEN_VEXT_VV_RM(vssra_vv_w, 4)
+GEN_VEXT_VV_RM(vssra_vv_d, 8)
RVVCALL(OPIVX2_RM, vssra_vx_b, OP_SSS_B, H1, H1, vssra8)
RVVCALL(OPIVX2_RM, vssra_vx_h, OP_SSS_H, H2, H2, vssra16)
RVVCALL(OPIVX2_RM, vssra_vx_w, OP_SSS_W, H4, H4, vssra32)
RVVCALL(OPIVX2_RM, vssra_vx_d, OP_SSS_D, H8, H8, vssra64)
-GEN_VEXT_VX_RM(vssra_vx_b)
-GEN_VEXT_VX_RM(vssra_vx_h)
-GEN_VEXT_VX_RM(vssra_vx_w)
-GEN_VEXT_VX_RM(vssra_vx_d)
+GEN_VEXT_VX_RM(vssra_vx_b, 1)
+GEN_VEXT_VX_RM(vssra_vx_h, 2)
+GEN_VEXT_VX_RM(vssra_vx_w, 4)
+GEN_VEXT_VX_RM(vssra_vx_d, 8)
/* Vector Narrowing Fixed-Point Clip Instructions */
static inline int8_t
@@ -2899,16 +2907,16 @@ vnclip32(CPURISCVState *env, int vxrm, int64_t a, int32_t b)
RVVCALL(OPIVV2_RM, vnclip_wv_b, NOP_SSS_B, H1, H2, H1, vnclip8)
RVVCALL(OPIVV2_RM, vnclip_wv_h, NOP_SSS_H, H2, H4, H2, vnclip16)
RVVCALL(OPIVV2_RM, vnclip_wv_w, NOP_SSS_W, H4, H8, H4, vnclip32)
-GEN_VEXT_VV_RM(vnclip_wv_b)
-GEN_VEXT_VV_RM(vnclip_wv_h)
-GEN_VEXT_VV_RM(vnclip_wv_w)
+GEN_VEXT_VV_RM(vnclip_wv_b, 1)
+GEN_VEXT_VV_RM(vnclip_wv_h, 2)
+GEN_VEXT_VV_RM(vnclip_wv_w, 4)
RVVCALL(OPIVX2_RM, vnclip_wx_b, NOP_SSS_B, H1, H2, vnclip8)
RVVCALL(OPIVX2_RM, vnclip_wx_h, NOP_SSS_H, H2, H4, vnclip16)
RVVCALL(OPIVX2_RM, vnclip_wx_w, NOP_SSS_W, H4, H8, vnclip32)
-GEN_VEXT_VX_RM(vnclip_wx_b)
-GEN_VEXT_VX_RM(vnclip_wx_h)
-GEN_VEXT_VX_RM(vnclip_wx_w)
+GEN_VEXT_VX_RM(vnclip_wx_b, 1)
+GEN_VEXT_VX_RM(vnclip_wx_h, 2)
+GEN_VEXT_VX_RM(vnclip_wx_w, 4)
static inline uint8_t
vnclipu8(CPURISCVState *env, int vxrm, uint16_t a, uint8_t b)
@@ -2961,16 +2969,16 @@ vnclipu32(CPURISCVState *env, int vxrm, uint64_t a, uint32_t b)
RVVCALL(OPIVV2_RM, vnclipu_wv_b, NOP_UUU_B, H1, H2, H1, vnclipu8)
RVVCALL(OPIVV2_RM, vnclipu_wv_h, NOP_UUU_H, H2, H4, H2, vnclipu16)
RVVCALL(OPIVV2_RM, vnclipu_wv_w, NOP_UUU_W, H4, H8, H4, vnclipu32)
-GEN_VEXT_VV_RM(vnclipu_wv_b)
-GEN_VEXT_VV_RM(vnclipu_wv_h)
-GEN_VEXT_VV_RM(vnclipu_wv_w)
+GEN_VEXT_VV_RM(vnclipu_wv_b, 1)
+GEN_VEXT_VV_RM(vnclipu_wv_h, 2)
+GEN_VEXT_VV_RM(vnclipu_wv_w, 4)
RVVCALL(OPIVX2_RM, vnclipu_wx_b, NOP_UUU_B, H1, H2, vnclipu8)
RVVCALL(OPIVX2_RM, vnclipu_wx_h, NOP_UUU_H, H2, H4, vnclipu16)
RVVCALL(OPIVX2_RM, vnclipu_wx_w, NOP_UUU_W, H4, H8, vnclipu32)
-GEN_VEXT_VX_RM(vnclipu_wx_b)
-GEN_VEXT_VX_RM(vnclipu_wx_h)
-GEN_VEXT_VX_RM(vnclipu_wx_w)
+GEN_VEXT_VX_RM(vnclipu_wx_b, 1)
+GEN_VEXT_VX_RM(vnclipu_wx_h, 2)
+GEN_VEXT_VX_RM(vnclipu_wx_w, 4)
/*
*** Vector Float Point Arithmetic Instructions
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 09/16] target/riscv: rvv: Add tail agnostic for vector integer comparison instructions
@ 2022-05-13 11:50 ` ~eopxd
0 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-05-13 11:50 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
Compares write mask registers, and so always operate under a tail-
agnostic policy.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/vector_helper.c | 18 ++++++++++++++++++
1 file changed, 18 insertions(+)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 9738c50222..b964b01a15 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -1370,6 +1370,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t total_elems = env_archcpu(env)->cfg.vlen; \
+ uint32_t vta_all_1s = vext_vta_all_1s(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -1381,6 +1383,13 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
vext_set_elem_mask(vd, i, DO_OP(s2, s1)); \
} \
env->vstart = 0; \
+ /* mask destination register are always tail-agnostic */ \
+ /* set tail elements to 1s */ \
+ if (vta_all_1s) { \
+ for (; i < total_elems; i++) { \
+ vext_set_elem_mask(vd, i, 1); \
+ } \
+ } \
}
GEN_VEXT_CMP_VV(vmseq_vv_b, uint8_t, H1, DO_MSEQ)
@@ -1419,6 +1428,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t total_elems = env_archcpu(env)->cfg.vlen; \
+ uint32_t vta_all_1s = vext_vta_all_1s(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -1430,6 +1441,13 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
DO_OP(s2, (ETYPE)(target_long)s1)); \
} \
env->vstart = 0; \
+ /* mask destination register are always tail-agnostic */ \
+ /* set tail elements to 1s */ \
+ if (vta_all_1s) { \
+ for (; i < total_elems; i++) { \
+ vext_set_elem_mask(vd, i, 1); \
+ } \
+ } \
}
GEN_VEXT_CMP_VX(vmseq_vx_b, uint8_t, H1, DO_MSEQ)
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 13/16] target/riscv: rvv: Add tail agnostic for vector reduction instructions
@ 2022-05-13 11:50 ` ~eopxd
0 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-05-13 11:50 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/vector_helper.c | 20 ++++++++++++++++++++
1 file changed, 20 insertions(+)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 8ac7fabb05..2ab4308ef0 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4534,6 +4534,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(TD); \
+ uint32_t vlenb = simd_maxsz(desc); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
TD s1 = *((TD *)vs1 + HD(0)); \
\
@@ -4546,6 +4549,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
} \
*((TD *)vd + HD(0)) = s1; \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, esz, vlenb); \
}
/* vd[0] = sum(vs1[0], vs2[*]) */
@@ -4615,6 +4620,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(TD); \
+ uint32_t vlenb = simd_maxsz(desc); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
TD s1 = *((TD *)vs1 + HD(0)); \
\
@@ -4627,6 +4635,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
} \
*((TD *)vd + HD(0)) = s1; \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, esz, vlenb); \
}
/* Unordered sum */
@@ -4651,6 +4661,9 @@ void HELPER(vfwredsum_vs_h)(void *vd, void *v0, void *vs1,
{
uint32_t vm = vext_vm(desc);
uint32_t vl = env->vl;
+ uint32_t esz = sizeof(uint32_t);
+ uint32_t vlenb = simd_maxsz(desc);
+ uint32_t vta = vext_vta(desc);
uint32_t i;
uint32_t s1 = *((uint32_t *)vs1 + H4(0));
@@ -4664,6 +4677,8 @@ void HELPER(vfwredsum_vs_h)(void *vd, void *v0, void *vs1,
}
*((uint32_t *)vd + H4(0)) = s1;
env->vstart = 0;
+ /* set tail elements to 1s */
+ vext_set_elems_1s(vd, vta, esz, vlenb);
}
void HELPER(vfwredsum_vs_w)(void *vd, void *v0, void *vs1,
@@ -4671,6 +4686,9 @@ void HELPER(vfwredsum_vs_w)(void *vd, void *v0, void *vs1,
{
uint32_t vm = vext_vm(desc);
uint32_t vl = env->vl;
+ uint32_t esz = sizeof(uint64_t);
+ uint32_t vlenb = simd_maxsz(desc);
+ uint32_t vta = vext_vta(desc);
uint32_t i;
uint64_t s1 = *((uint64_t *)vs1);
@@ -4684,6 +4702,8 @@ void HELPER(vfwredsum_vs_w)(void *vd, void *v0, void *vs1,
}
*((uint64_t *)vd) = s1;
env->vstart = 0;
+ /* set tail elements to 1s */
+ vext_set_elems_1s(vd, vta, esz, vlenb);
}
/*
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 14/16] target/riscv: rvv: Add tail agnostic for vector mask instructions
@ 2022-05-13 11:50 ` ~eopxd
0 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-05-13 11:50 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
The tail elements in the destination mask register are updated under
a tail-agnostic policy.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/insn_trans/trans_rvv.c.inc | 6 +++++
target/riscv/vector_helper.c | 30 +++++++++++++++++++++++++
2 files changed, 36 insertions(+)
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index 76dee1ba20..430d4e4460 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -3131,6 +3131,8 @@ static bool trans_##NAME(DisasContext *s, arg_r *a) \
tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = \
+ FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);\
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs1), \
vreg_ofs(s, a->rs2), cpu_env, \
@@ -3235,6 +3237,8 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = \
+ FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);\
tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), \
vreg_ofs(s, 0), vreg_ofs(s, a->rs2), \
cpu_env, s->cfg_ptr->vlen / 8, \
@@ -3272,6 +3276,7 @@ static bool trans_viota_m(DisasContext *s, arg_viota_m *a)
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
static gen_helper_gvec_3_ptr * const fns[4] = {
gen_helper_viota_m_b, gen_helper_viota_m_h,
gen_helper_viota_m_w, gen_helper_viota_m_d,
@@ -3301,6 +3306,7 @@ static bool trans_vid_v(DisasContext *s, arg_vid_v *a)
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
static gen_helper_gvec_2_ptr * const fns[4] = {
gen_helper_vid_v_b, gen_helper_vid_v_h,
gen_helper_vid_v_w, gen_helper_vid_v_d,
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 2ab4308ef0..5c2d1c02f4 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4716,6 +4716,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
uint32_t desc) \
{ \
uint32_t vl = env->vl; \
+ uint32_t total_elems = env_archcpu(env)->cfg.vlen; \
+ uint32_t vta_all_1s = vext_vta_all_1s(desc); \
uint32_t i; \
int a, b; \
\
@@ -4725,6 +4727,15 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
vext_set_elem_mask(vd, i, OP(b, a)); \
} \
env->vstart = 0; \
+ /* mask destination register are always tail- \
+ * agnostic \
+ */ \
+ /* set tail elements to 1s */ \
+ if (vta_all_1s) { \
+ for (; i < total_elems; i++) { \
+ vext_set_elem_mask(vd, i, 1); \
+ } \
+ } \
}
#define DO_NAND(N, M) (!(N & M))
@@ -4792,6 +4803,8 @@ static void vmsetm(void *vd, void *v0, void *vs2, CPURISCVState *env,
{
uint32_t vm = vext_vm(desc);
uint32_t vl = env->vl;
+ uint32_t total_elems = env_archcpu(env)->cfg.vlen;
+ uint32_t vta_all_1s = vext_vta_all_1s(desc);
int i;
bool first_mask_bit = false;
@@ -4820,6 +4833,13 @@ static void vmsetm(void *vd, void *v0, void *vs2, CPURISCVState *env,
}
}
env->vstart = 0;
+ /* mask destination register are always tail-agnostic */
+ /* set tail elements to 1s */
+ if (vta_all_1s) {
+ for (; i < total_elems; i++) {
+ vext_set_elem_mask(vd, i, 1);
+ }
+ }
}
void HELPER(vmsbf_m)(void *vd, void *v0, void *vs2, CPURISCVState *env,
@@ -4847,6 +4867,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, CPURISCVState *env, \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t sum = 0; \
int i; \
\
@@ -4860,6 +4883,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, CPURISCVState *env, \
} \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VEXT_VIOTA_M(viota_m_b, uint8_t, H1)
@@ -4873,6 +4898,9 @@ void HELPER(NAME)(void *vd, void *v0, CPURISCVState *env, uint32_t desc) \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
int i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -4882,6 +4910,8 @@ void HELPER(NAME)(void *vd, void *v0, CPURISCVState *env, uint32_t desc) \
*((ETYPE *)vd + H(i)) = i; \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VEXT_VID_V(vid_v_b, uint8_t, H1)
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 12/16] target/riscv: rvv: Add tail agnostic for vector floating-point instructions
@ 2022-05-13 11:50 ` ~eopxd
0 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-05-13 11:50 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
Compares write mask registers, and so always operate under a tail-
agnostic policy.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/insn_trans/trans_rvv.c.inc | 17 +
target/riscv/vector_helper.c | 440 +++++++++++++-----------
2 files changed, 261 insertions(+), 196 deletions(-)
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index 50f874ceae..76dee1ba20 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -2334,6 +2334,9 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
+ data = \
+ FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);\
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs1), \
vreg_ofs(s, a->rs2), cpu_env, \
@@ -2416,6 +2419,9 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
gen_set_rm(s, RISCV_FRM_DYN); \
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
+ data = FIELD_DP32(data, VDATA, VTA_ALL_1S, \
+ s->cfg_vta_all_1s); \
return opfvf_trans(a->rd, a->rs1, a->rs2, data, \
fns[s->sew - 1], s); \
} \
@@ -2454,6 +2460,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs1), \
vreg_ofs(s, a->rs2), cpu_env, \
@@ -2493,6 +2500,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
gen_set_rm(s, RISCV_FRM_DYN); \
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
return opfvf_trans(a->rd, a->rs1, a->rs2, data, \
fns[s->sew - 1], s); \
} \
@@ -2529,6 +2537,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs1), \
vreg_ofs(s, a->rs2), cpu_env, \
@@ -2568,6 +2577,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
gen_set_rm(s, RISCV_FRM_DYN); \
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
return opfvf_trans(a->rd, a->rs1, a->rs2, data, \
fns[s->sew - 1], s); \
} \
@@ -2651,6 +2661,7 @@ static bool do_opfv(DisasContext *s, arg_rmr *a,
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),
vreg_ofs(s, a->rs2), cpu_env,
s->cfg_ptr->vlen / 8,
@@ -2855,6 +2866,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs2), cpu_env, \
s->cfg_ptr->vlen / 8, \
@@ -2906,6 +2918,8 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
+ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs2), cpu_env, \
s->cfg_ptr->vlen / 8, \
@@ -2973,6 +2987,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs2), cpu_env, \
s->cfg_ptr->vlen / 8, \
@@ -3026,6 +3041,8 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
+ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs2), cpu_env, \
s->cfg_ptr->vlen / 8, \
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index db221797c6..8ac7fabb05 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -2993,13 +2993,16 @@ static void do_##NAME(void *vd, void *vs1, void *vs2, int i, \
*((TD *)vd + HD(i)) = OP(s2, s1, &env->fp_status); \
}
-#define GEN_VEXT_VV_ENV(NAME) \
+#define GEN_VEXT_VV_ENV(NAME, ESZ) \
void HELPER(NAME)(void *vd, void *v0, void *vs1, \
void *vs2, CPURISCVState *env, \
uint32_t desc) \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t total_elems = \
+ vext_get_total_elems(env, desc, ESZ); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -3009,14 +3012,17 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
do_##NAME(vd, vs1, vs2, i, env); \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * ESZ, \
+ total_elems * ESZ); \
}
RVVCALL(OPFVV2, vfadd_vv_h, OP_UUU_H, H2, H2, H2, float16_add)
RVVCALL(OPFVV2, vfadd_vv_w, OP_UUU_W, H4, H4, H4, float32_add)
RVVCALL(OPFVV2, vfadd_vv_d, OP_UUU_D, H8, H8, H8, float64_add)
-GEN_VEXT_VV_ENV(vfadd_vv_h)
-GEN_VEXT_VV_ENV(vfadd_vv_w)
-GEN_VEXT_VV_ENV(vfadd_vv_d)
+GEN_VEXT_VV_ENV(vfadd_vv_h, 2)
+GEN_VEXT_VV_ENV(vfadd_vv_w, 4)
+GEN_VEXT_VV_ENV(vfadd_vv_d, 8)
#define OPFVF2(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \
static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \
@@ -3026,13 +3032,16 @@ static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \
*((TD *)vd + HD(i)) = OP(s2, (TX1)(T1)s1, &env->fp_status);\
}
-#define GEN_VEXT_VF(NAME) \
+#define GEN_VEXT_VF(NAME, ESZ) \
void HELPER(NAME)(void *vd, void *v0, uint64_t s1, \
void *vs2, CPURISCVState *env, \
uint32_t desc) \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t total_elems = \
+ vext_get_total_elems(env, desc, ESZ); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -3042,27 +3051,30 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, \
do_##NAME(vd, s1, vs2, i, env); \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * ESZ, \
+ total_elems * ESZ); \
}
RVVCALL(OPFVF2, vfadd_vf_h, OP_UUU_H, H2, H2, float16_add)
RVVCALL(OPFVF2, vfadd_vf_w, OP_UUU_W, H4, H4, float32_add)
RVVCALL(OPFVF2, vfadd_vf_d, OP_UUU_D, H8, H8, float64_add)
-GEN_VEXT_VF(vfadd_vf_h)
-GEN_VEXT_VF(vfadd_vf_w)
-GEN_VEXT_VF(vfadd_vf_d)
+GEN_VEXT_VF(vfadd_vf_h, 2)
+GEN_VEXT_VF(vfadd_vf_w, 4)
+GEN_VEXT_VF(vfadd_vf_d, 8)
RVVCALL(OPFVV2, vfsub_vv_h, OP_UUU_H, H2, H2, H2, float16_sub)
RVVCALL(OPFVV2, vfsub_vv_w, OP_UUU_W, H4, H4, H4, float32_sub)
RVVCALL(OPFVV2, vfsub_vv_d, OP_UUU_D, H8, H8, H8, float64_sub)
-GEN_VEXT_VV_ENV(vfsub_vv_h)
-GEN_VEXT_VV_ENV(vfsub_vv_w)
-GEN_VEXT_VV_ENV(vfsub_vv_d)
+GEN_VEXT_VV_ENV(vfsub_vv_h, 2)
+GEN_VEXT_VV_ENV(vfsub_vv_w, 4)
+GEN_VEXT_VV_ENV(vfsub_vv_d, 8)
RVVCALL(OPFVF2, vfsub_vf_h, OP_UUU_H, H2, H2, float16_sub)
RVVCALL(OPFVF2, vfsub_vf_w, OP_UUU_W, H4, H4, float32_sub)
RVVCALL(OPFVF2, vfsub_vf_d, OP_UUU_D, H8, H8, float64_sub)
-GEN_VEXT_VF(vfsub_vf_h)
-GEN_VEXT_VF(vfsub_vf_w)
-GEN_VEXT_VF(vfsub_vf_d)
+GEN_VEXT_VF(vfsub_vf_h, 2)
+GEN_VEXT_VF(vfsub_vf_w, 4)
+GEN_VEXT_VF(vfsub_vf_d, 8)
static uint16_t float16_rsub(uint16_t a, uint16_t b, float_status *s)
{
@@ -3082,9 +3094,9 @@ static uint64_t float64_rsub(uint64_t a, uint64_t b, float_status *s)
RVVCALL(OPFVF2, vfrsub_vf_h, OP_UUU_H, H2, H2, float16_rsub)
RVVCALL(OPFVF2, vfrsub_vf_w, OP_UUU_W, H4, H4, float32_rsub)
RVVCALL(OPFVF2, vfrsub_vf_d, OP_UUU_D, H8, H8, float64_rsub)
-GEN_VEXT_VF(vfrsub_vf_h)
-GEN_VEXT_VF(vfrsub_vf_w)
-GEN_VEXT_VF(vfrsub_vf_d)
+GEN_VEXT_VF(vfrsub_vf_h, 2)
+GEN_VEXT_VF(vfrsub_vf_w, 4)
+GEN_VEXT_VF(vfrsub_vf_d, 8)
/* Vector Widening Floating-Point Add/Subtract Instructions */
static uint32_t vfwadd16(uint16_t a, uint16_t b, float_status *s)
@@ -3102,12 +3114,12 @@ static uint64_t vfwadd32(uint32_t a, uint32_t b, float_status *s)
RVVCALL(OPFVV2, vfwadd_vv_h, WOP_UUU_H, H4, H2, H2, vfwadd16)
RVVCALL(OPFVV2, vfwadd_vv_w, WOP_UUU_W, H8, H4, H4, vfwadd32)
-GEN_VEXT_VV_ENV(vfwadd_vv_h)
-GEN_VEXT_VV_ENV(vfwadd_vv_w)
+GEN_VEXT_VV_ENV(vfwadd_vv_h, 4)
+GEN_VEXT_VV_ENV(vfwadd_vv_w, 8)
RVVCALL(OPFVF2, vfwadd_vf_h, WOP_UUU_H, H4, H2, vfwadd16)
RVVCALL(OPFVF2, vfwadd_vf_w, WOP_UUU_W, H8, H4, vfwadd32)
-GEN_VEXT_VF(vfwadd_vf_h)
-GEN_VEXT_VF(vfwadd_vf_w)
+GEN_VEXT_VF(vfwadd_vf_h, 4)
+GEN_VEXT_VF(vfwadd_vf_w, 8)
static uint32_t vfwsub16(uint16_t a, uint16_t b, float_status *s)
{
@@ -3124,12 +3136,12 @@ static uint64_t vfwsub32(uint32_t a, uint32_t b, float_status *s)
RVVCALL(OPFVV2, vfwsub_vv_h, WOP_UUU_H, H4, H2, H2, vfwsub16)
RVVCALL(OPFVV2, vfwsub_vv_w, WOP_UUU_W, H8, H4, H4, vfwsub32)
-GEN_VEXT_VV_ENV(vfwsub_vv_h)
-GEN_VEXT_VV_ENV(vfwsub_vv_w)
+GEN_VEXT_VV_ENV(vfwsub_vv_h, 4)
+GEN_VEXT_VV_ENV(vfwsub_vv_w, 8)
RVVCALL(OPFVF2, vfwsub_vf_h, WOP_UUU_H, H4, H2, vfwsub16)
RVVCALL(OPFVF2, vfwsub_vf_w, WOP_UUU_W, H8, H4, vfwsub32)
-GEN_VEXT_VF(vfwsub_vf_h)
-GEN_VEXT_VF(vfwsub_vf_w)
+GEN_VEXT_VF(vfwsub_vf_h, 4)
+GEN_VEXT_VF(vfwsub_vf_w, 8)
static uint32_t vfwaddw16(uint32_t a, uint16_t b, float_status *s)
{
@@ -3143,12 +3155,12 @@ static uint64_t vfwaddw32(uint64_t a, uint32_t b, float_status *s)
RVVCALL(OPFVV2, vfwadd_wv_h, WOP_WUUU_H, H4, H2, H2, vfwaddw16)
RVVCALL(OPFVV2, vfwadd_wv_w, WOP_WUUU_W, H8, H4, H4, vfwaddw32)
-GEN_VEXT_VV_ENV(vfwadd_wv_h)
-GEN_VEXT_VV_ENV(vfwadd_wv_w)
+GEN_VEXT_VV_ENV(vfwadd_wv_h, 4)
+GEN_VEXT_VV_ENV(vfwadd_wv_w, 8)
RVVCALL(OPFVF2, vfwadd_wf_h, WOP_WUUU_H, H4, H2, vfwaddw16)
RVVCALL(OPFVF2, vfwadd_wf_w, WOP_WUUU_W, H8, H4, vfwaddw32)
-GEN_VEXT_VF(vfwadd_wf_h)
-GEN_VEXT_VF(vfwadd_wf_w)
+GEN_VEXT_VF(vfwadd_wf_h, 4)
+GEN_VEXT_VF(vfwadd_wf_w, 8)
static uint32_t vfwsubw16(uint32_t a, uint16_t b, float_status *s)
{
@@ -3162,39 +3174,39 @@ static uint64_t vfwsubw32(uint64_t a, uint32_t b, float_status *s)
RVVCALL(OPFVV2, vfwsub_wv_h, WOP_WUUU_H, H4, H2, H2, vfwsubw16)
RVVCALL(OPFVV2, vfwsub_wv_w, WOP_WUUU_W, H8, H4, H4, vfwsubw32)
-GEN_VEXT_VV_ENV(vfwsub_wv_h)
-GEN_VEXT_VV_ENV(vfwsub_wv_w)
+GEN_VEXT_VV_ENV(vfwsub_wv_h, 4)
+GEN_VEXT_VV_ENV(vfwsub_wv_w, 8)
RVVCALL(OPFVF2, vfwsub_wf_h, WOP_WUUU_H, H4, H2, vfwsubw16)
RVVCALL(OPFVF2, vfwsub_wf_w, WOP_WUUU_W, H8, H4, vfwsubw32)
-GEN_VEXT_VF(vfwsub_wf_h)
-GEN_VEXT_VF(vfwsub_wf_w)
+GEN_VEXT_VF(vfwsub_wf_h, 4)
+GEN_VEXT_VF(vfwsub_wf_w, 8)
/* Vector Single-Width Floating-Point Multiply/Divide Instructions */
RVVCALL(OPFVV2, vfmul_vv_h, OP_UUU_H, H2, H2, H2, float16_mul)
RVVCALL(OPFVV2, vfmul_vv_w, OP_UUU_W, H4, H4, H4, float32_mul)
RVVCALL(OPFVV2, vfmul_vv_d, OP_UUU_D, H8, H8, H8, float64_mul)
-GEN_VEXT_VV_ENV(vfmul_vv_h)
-GEN_VEXT_VV_ENV(vfmul_vv_w)
-GEN_VEXT_VV_ENV(vfmul_vv_d)
+GEN_VEXT_VV_ENV(vfmul_vv_h, 2)
+GEN_VEXT_VV_ENV(vfmul_vv_w, 4)
+GEN_VEXT_VV_ENV(vfmul_vv_d, 8)
RVVCALL(OPFVF2, vfmul_vf_h, OP_UUU_H, H2, H2, float16_mul)
RVVCALL(OPFVF2, vfmul_vf_w, OP_UUU_W, H4, H4, float32_mul)
RVVCALL(OPFVF2, vfmul_vf_d, OP_UUU_D, H8, H8, float64_mul)
-GEN_VEXT_VF(vfmul_vf_h)
-GEN_VEXT_VF(vfmul_vf_w)
-GEN_VEXT_VF(vfmul_vf_d)
+GEN_VEXT_VF(vfmul_vf_h, 2)
+GEN_VEXT_VF(vfmul_vf_w, 4)
+GEN_VEXT_VF(vfmul_vf_d, 8)
RVVCALL(OPFVV2, vfdiv_vv_h, OP_UUU_H, H2, H2, H2, float16_div)
RVVCALL(OPFVV2, vfdiv_vv_w, OP_UUU_W, H4, H4, H4, float32_div)
RVVCALL(OPFVV2, vfdiv_vv_d, OP_UUU_D, H8, H8, H8, float64_div)
-GEN_VEXT_VV_ENV(vfdiv_vv_h)
-GEN_VEXT_VV_ENV(vfdiv_vv_w)
-GEN_VEXT_VV_ENV(vfdiv_vv_d)
+GEN_VEXT_VV_ENV(vfdiv_vv_h, 2)
+GEN_VEXT_VV_ENV(vfdiv_vv_w, 4)
+GEN_VEXT_VV_ENV(vfdiv_vv_d, 8)
RVVCALL(OPFVF2, vfdiv_vf_h, OP_UUU_H, H2, H2, float16_div)
RVVCALL(OPFVF2, vfdiv_vf_w, OP_UUU_W, H4, H4, float32_div)
RVVCALL(OPFVF2, vfdiv_vf_d, OP_UUU_D, H8, H8, float64_div)
-GEN_VEXT_VF(vfdiv_vf_h)
-GEN_VEXT_VF(vfdiv_vf_w)
-GEN_VEXT_VF(vfdiv_vf_d)
+GEN_VEXT_VF(vfdiv_vf_h, 2)
+GEN_VEXT_VF(vfdiv_vf_w, 4)
+GEN_VEXT_VF(vfdiv_vf_d, 8)
static uint16_t float16_rdiv(uint16_t a, uint16_t b, float_status *s)
{
@@ -3214,9 +3226,9 @@ static uint64_t float64_rdiv(uint64_t a, uint64_t b, float_status *s)
RVVCALL(OPFVF2, vfrdiv_vf_h, OP_UUU_H, H2, H2, float16_rdiv)
RVVCALL(OPFVF2, vfrdiv_vf_w, OP_UUU_W, H4, H4, float32_rdiv)
RVVCALL(OPFVF2, vfrdiv_vf_d, OP_UUU_D, H8, H8, float64_rdiv)
-GEN_VEXT_VF(vfrdiv_vf_h)
-GEN_VEXT_VF(vfrdiv_vf_w)
-GEN_VEXT_VF(vfrdiv_vf_d)
+GEN_VEXT_VF(vfrdiv_vf_h, 2)
+GEN_VEXT_VF(vfrdiv_vf_w, 4)
+GEN_VEXT_VF(vfrdiv_vf_d, 8)
/* Vector Widening Floating-Point Multiply */
static uint32_t vfwmul16(uint16_t a, uint16_t b, float_status *s)
@@ -3233,12 +3245,12 @@ static uint64_t vfwmul32(uint32_t a, uint32_t b, float_status *s)
}
RVVCALL(OPFVV2, vfwmul_vv_h, WOP_UUU_H, H4, H2, H2, vfwmul16)
RVVCALL(OPFVV2, vfwmul_vv_w, WOP_UUU_W, H8, H4, H4, vfwmul32)
-GEN_VEXT_VV_ENV(vfwmul_vv_h)
-GEN_VEXT_VV_ENV(vfwmul_vv_w)
+GEN_VEXT_VV_ENV(vfwmul_vv_h, 4)
+GEN_VEXT_VV_ENV(vfwmul_vv_w, 8)
RVVCALL(OPFVF2, vfwmul_vf_h, WOP_UUU_H, H4, H2, vfwmul16)
RVVCALL(OPFVF2, vfwmul_vf_w, WOP_UUU_W, H8, H4, vfwmul32)
-GEN_VEXT_VF(vfwmul_vf_h)
-GEN_VEXT_VF(vfwmul_vf_w)
+GEN_VEXT_VF(vfwmul_vf_h, 4)
+GEN_VEXT_VF(vfwmul_vf_w, 8)
/* Vector Single-Width Floating-Point Fused Multiply-Add Instructions */
#define OPFVV3(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP) \
@@ -3269,9 +3281,9 @@ static uint64_t fmacc64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfmacc_vv_h, OP_UUU_H, H2, H2, H2, fmacc16)
RVVCALL(OPFVV3, vfmacc_vv_w, OP_UUU_W, H4, H4, H4, fmacc32)
RVVCALL(OPFVV3, vfmacc_vv_d, OP_UUU_D, H8, H8, H8, fmacc64)
-GEN_VEXT_VV_ENV(vfmacc_vv_h)
-GEN_VEXT_VV_ENV(vfmacc_vv_w)
-GEN_VEXT_VV_ENV(vfmacc_vv_d)
+GEN_VEXT_VV_ENV(vfmacc_vv_h, 2)
+GEN_VEXT_VV_ENV(vfmacc_vv_w, 4)
+GEN_VEXT_VV_ENV(vfmacc_vv_d, 8)
#define OPFVF3(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \
static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \
@@ -3285,9 +3297,9 @@ static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \
RVVCALL(OPFVF3, vfmacc_vf_h, OP_UUU_H, H2, H2, fmacc16)
RVVCALL(OPFVF3, vfmacc_vf_w, OP_UUU_W, H4, H4, fmacc32)
RVVCALL(OPFVF3, vfmacc_vf_d, OP_UUU_D, H8, H8, fmacc64)
-GEN_VEXT_VF(vfmacc_vf_h)
-GEN_VEXT_VF(vfmacc_vf_w)
-GEN_VEXT_VF(vfmacc_vf_d)
+GEN_VEXT_VF(vfmacc_vf_h, 2)
+GEN_VEXT_VF(vfmacc_vf_w, 4)
+GEN_VEXT_VF(vfmacc_vf_d, 8)
static uint16_t fnmacc16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3310,15 +3322,15 @@ static uint64_t fnmacc64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfnmacc_vv_h, OP_UUU_H, H2, H2, H2, fnmacc16)
RVVCALL(OPFVV3, vfnmacc_vv_w, OP_UUU_W, H4, H4, H4, fnmacc32)
RVVCALL(OPFVV3, vfnmacc_vv_d, OP_UUU_D, H8, H8, H8, fnmacc64)
-GEN_VEXT_VV_ENV(vfnmacc_vv_h)
-GEN_VEXT_VV_ENV(vfnmacc_vv_w)
-GEN_VEXT_VV_ENV(vfnmacc_vv_d)
+GEN_VEXT_VV_ENV(vfnmacc_vv_h, 2)
+GEN_VEXT_VV_ENV(vfnmacc_vv_w, 4)
+GEN_VEXT_VV_ENV(vfnmacc_vv_d, 8)
RVVCALL(OPFVF3, vfnmacc_vf_h, OP_UUU_H, H2, H2, fnmacc16)
RVVCALL(OPFVF3, vfnmacc_vf_w, OP_UUU_W, H4, H4, fnmacc32)
RVVCALL(OPFVF3, vfnmacc_vf_d, OP_UUU_D, H8, H8, fnmacc64)
-GEN_VEXT_VF(vfnmacc_vf_h)
-GEN_VEXT_VF(vfnmacc_vf_w)
-GEN_VEXT_VF(vfnmacc_vf_d)
+GEN_VEXT_VF(vfnmacc_vf_h, 2)
+GEN_VEXT_VF(vfnmacc_vf_w, 4)
+GEN_VEXT_VF(vfnmacc_vf_d, 8)
static uint16_t fmsac16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3338,15 +3350,15 @@ static uint64_t fmsac64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfmsac_vv_h, OP_UUU_H, H2, H2, H2, fmsac16)
RVVCALL(OPFVV3, vfmsac_vv_w, OP_UUU_W, H4, H4, H4, fmsac32)
RVVCALL(OPFVV3, vfmsac_vv_d, OP_UUU_D, H8, H8, H8, fmsac64)
-GEN_VEXT_VV_ENV(vfmsac_vv_h)
-GEN_VEXT_VV_ENV(vfmsac_vv_w)
-GEN_VEXT_VV_ENV(vfmsac_vv_d)
+GEN_VEXT_VV_ENV(vfmsac_vv_h, 2)
+GEN_VEXT_VV_ENV(vfmsac_vv_w, 4)
+GEN_VEXT_VV_ENV(vfmsac_vv_d, 8)
RVVCALL(OPFVF3, vfmsac_vf_h, OP_UUU_H, H2, H2, fmsac16)
RVVCALL(OPFVF3, vfmsac_vf_w, OP_UUU_W, H4, H4, fmsac32)
RVVCALL(OPFVF3, vfmsac_vf_d, OP_UUU_D, H8, H8, fmsac64)
-GEN_VEXT_VF(vfmsac_vf_h)
-GEN_VEXT_VF(vfmsac_vf_w)
-GEN_VEXT_VF(vfmsac_vf_d)
+GEN_VEXT_VF(vfmsac_vf_h, 2)
+GEN_VEXT_VF(vfmsac_vf_w, 4)
+GEN_VEXT_VF(vfmsac_vf_d, 8)
static uint16_t fnmsac16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3366,15 +3378,15 @@ static uint64_t fnmsac64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfnmsac_vv_h, OP_UUU_H, H2, H2, H2, fnmsac16)
RVVCALL(OPFVV3, vfnmsac_vv_w, OP_UUU_W, H4, H4, H4, fnmsac32)
RVVCALL(OPFVV3, vfnmsac_vv_d, OP_UUU_D, H8, H8, H8, fnmsac64)
-GEN_VEXT_VV_ENV(vfnmsac_vv_h)
-GEN_VEXT_VV_ENV(vfnmsac_vv_w)
-GEN_VEXT_VV_ENV(vfnmsac_vv_d)
+GEN_VEXT_VV_ENV(vfnmsac_vv_h, 2)
+GEN_VEXT_VV_ENV(vfnmsac_vv_w, 4)
+GEN_VEXT_VV_ENV(vfnmsac_vv_d, 8)
RVVCALL(OPFVF3, vfnmsac_vf_h, OP_UUU_H, H2, H2, fnmsac16)
RVVCALL(OPFVF3, vfnmsac_vf_w, OP_UUU_W, H4, H4, fnmsac32)
RVVCALL(OPFVF3, vfnmsac_vf_d, OP_UUU_D, H8, H8, fnmsac64)
-GEN_VEXT_VF(vfnmsac_vf_h)
-GEN_VEXT_VF(vfnmsac_vf_w)
-GEN_VEXT_VF(vfnmsac_vf_d)
+GEN_VEXT_VF(vfnmsac_vf_h, 2)
+GEN_VEXT_VF(vfnmsac_vf_w, 4)
+GEN_VEXT_VF(vfnmsac_vf_d, 8)
static uint16_t fmadd16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3394,15 +3406,15 @@ static uint64_t fmadd64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfmadd_vv_h, OP_UUU_H, H2, H2, H2, fmadd16)
RVVCALL(OPFVV3, vfmadd_vv_w, OP_UUU_W, H4, H4, H4, fmadd32)
RVVCALL(OPFVV3, vfmadd_vv_d, OP_UUU_D, H8, H8, H8, fmadd64)
-GEN_VEXT_VV_ENV(vfmadd_vv_h)
-GEN_VEXT_VV_ENV(vfmadd_vv_w)
-GEN_VEXT_VV_ENV(vfmadd_vv_d)
+GEN_VEXT_VV_ENV(vfmadd_vv_h, 2)
+GEN_VEXT_VV_ENV(vfmadd_vv_w, 4)
+GEN_VEXT_VV_ENV(vfmadd_vv_d, 8)
RVVCALL(OPFVF3, vfmadd_vf_h, OP_UUU_H, H2, H2, fmadd16)
RVVCALL(OPFVF3, vfmadd_vf_w, OP_UUU_W, H4, H4, fmadd32)
RVVCALL(OPFVF3, vfmadd_vf_d, OP_UUU_D, H8, H8, fmadd64)
-GEN_VEXT_VF(vfmadd_vf_h)
-GEN_VEXT_VF(vfmadd_vf_w)
-GEN_VEXT_VF(vfmadd_vf_d)
+GEN_VEXT_VF(vfmadd_vf_h, 2)
+GEN_VEXT_VF(vfmadd_vf_w, 4)
+GEN_VEXT_VF(vfmadd_vf_d, 8)
static uint16_t fnmadd16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3425,15 +3437,15 @@ static uint64_t fnmadd64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfnmadd_vv_h, OP_UUU_H, H2, H2, H2, fnmadd16)
RVVCALL(OPFVV3, vfnmadd_vv_w, OP_UUU_W, H4, H4, H4, fnmadd32)
RVVCALL(OPFVV3, vfnmadd_vv_d, OP_UUU_D, H8, H8, H8, fnmadd64)
-GEN_VEXT_VV_ENV(vfnmadd_vv_h)
-GEN_VEXT_VV_ENV(vfnmadd_vv_w)
-GEN_VEXT_VV_ENV(vfnmadd_vv_d)
+GEN_VEXT_VV_ENV(vfnmadd_vv_h, 2)
+GEN_VEXT_VV_ENV(vfnmadd_vv_w, 4)
+GEN_VEXT_VV_ENV(vfnmadd_vv_d, 8)
RVVCALL(OPFVF3, vfnmadd_vf_h, OP_UUU_H, H2, H2, fnmadd16)
RVVCALL(OPFVF3, vfnmadd_vf_w, OP_UUU_W, H4, H4, fnmadd32)
RVVCALL(OPFVF3, vfnmadd_vf_d, OP_UUU_D, H8, H8, fnmadd64)
-GEN_VEXT_VF(vfnmadd_vf_h)
-GEN_VEXT_VF(vfnmadd_vf_w)
-GEN_VEXT_VF(vfnmadd_vf_d)
+GEN_VEXT_VF(vfnmadd_vf_h, 2)
+GEN_VEXT_VF(vfnmadd_vf_w, 4)
+GEN_VEXT_VF(vfnmadd_vf_d, 8)
static uint16_t fmsub16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3453,15 +3465,15 @@ static uint64_t fmsub64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfmsub_vv_h, OP_UUU_H, H2, H2, H2, fmsub16)
RVVCALL(OPFVV3, vfmsub_vv_w, OP_UUU_W, H4, H4, H4, fmsub32)
RVVCALL(OPFVV3, vfmsub_vv_d, OP_UUU_D, H8, H8, H8, fmsub64)
-GEN_VEXT_VV_ENV(vfmsub_vv_h)
-GEN_VEXT_VV_ENV(vfmsub_vv_w)
-GEN_VEXT_VV_ENV(vfmsub_vv_d)
+GEN_VEXT_VV_ENV(vfmsub_vv_h, 2)
+GEN_VEXT_VV_ENV(vfmsub_vv_w, 4)
+GEN_VEXT_VV_ENV(vfmsub_vv_d, 8)
RVVCALL(OPFVF3, vfmsub_vf_h, OP_UUU_H, H2, H2, fmsub16)
RVVCALL(OPFVF3, vfmsub_vf_w, OP_UUU_W, H4, H4, fmsub32)
RVVCALL(OPFVF3, vfmsub_vf_d, OP_UUU_D, H8, H8, fmsub64)
-GEN_VEXT_VF(vfmsub_vf_h)
-GEN_VEXT_VF(vfmsub_vf_w)
-GEN_VEXT_VF(vfmsub_vf_d)
+GEN_VEXT_VF(vfmsub_vf_h, 2)
+GEN_VEXT_VF(vfmsub_vf_w, 4)
+GEN_VEXT_VF(vfmsub_vf_d, 8)
static uint16_t fnmsub16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@@ -3481,15 +3493,15 @@ static uint64_t fnmsub64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfnmsub_vv_h, OP_UUU_H, H2, H2, H2, fnmsub16)
RVVCALL(OPFVV3, vfnmsub_vv_w, OP_UUU_W, H4, H4, H4, fnmsub32)
RVVCALL(OPFVV3, vfnmsub_vv_d, OP_UUU_D, H8, H8, H8, fnmsub64)
-GEN_VEXT_VV_ENV(vfnmsub_vv_h)
-GEN_VEXT_VV_ENV(vfnmsub_vv_w)
-GEN_VEXT_VV_ENV(vfnmsub_vv_d)
+GEN_VEXT_VV_ENV(vfnmsub_vv_h, 2)
+GEN_VEXT_VV_ENV(vfnmsub_vv_w, 4)
+GEN_VEXT_VV_ENV(vfnmsub_vv_d, 8)
RVVCALL(OPFVF3, vfnmsub_vf_h, OP_UUU_H, H2, H2, fnmsub16)
RVVCALL(OPFVF3, vfnmsub_vf_w, OP_UUU_W, H4, H4, fnmsub32)
RVVCALL(OPFVF3, vfnmsub_vf_d, OP_UUU_D, H8, H8, fnmsub64)
-GEN_VEXT_VF(vfnmsub_vf_h)
-GEN_VEXT_VF(vfnmsub_vf_w)
-GEN_VEXT_VF(vfnmsub_vf_d)
+GEN_VEXT_VF(vfnmsub_vf_h, 2)
+GEN_VEXT_VF(vfnmsub_vf_w, 4)
+GEN_VEXT_VF(vfnmsub_vf_d, 8)
/* Vector Widening Floating-Point Fused Multiply-Add Instructions */
static uint32_t fwmacc16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
@@ -3506,12 +3518,12 @@ static uint64_t fwmacc32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfwmacc_vv_h, WOP_UUU_H, H4, H2, H2, fwmacc16)
RVVCALL(OPFVV3, vfwmacc_vv_w, WOP_UUU_W, H8, H4, H4, fwmacc32)
-GEN_VEXT_VV_ENV(vfwmacc_vv_h)
-GEN_VEXT_VV_ENV(vfwmacc_vv_w)
+GEN_VEXT_VV_ENV(vfwmacc_vv_h, 4)
+GEN_VEXT_VV_ENV(vfwmacc_vv_w, 8)
RVVCALL(OPFVF3, vfwmacc_vf_h, WOP_UUU_H, H4, H2, fwmacc16)
RVVCALL(OPFVF3, vfwmacc_vf_w, WOP_UUU_W, H8, H4, fwmacc32)
-GEN_VEXT_VF(vfwmacc_vf_h)
-GEN_VEXT_VF(vfwmacc_vf_w)
+GEN_VEXT_VF(vfwmacc_vf_h, 4)
+GEN_VEXT_VF(vfwmacc_vf_w, 8)
static uint32_t fwnmacc16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
{
@@ -3529,12 +3541,12 @@ static uint64_t fwnmacc32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfwnmacc_vv_h, WOP_UUU_H, H4, H2, H2, fwnmacc16)
RVVCALL(OPFVV3, vfwnmacc_vv_w, WOP_UUU_W, H8, H4, H4, fwnmacc32)
-GEN_VEXT_VV_ENV(vfwnmacc_vv_h)
-GEN_VEXT_VV_ENV(vfwnmacc_vv_w)
+GEN_VEXT_VV_ENV(vfwnmacc_vv_h, 4)
+GEN_VEXT_VV_ENV(vfwnmacc_vv_w, 8)
RVVCALL(OPFVF3, vfwnmacc_vf_h, WOP_UUU_H, H4, H2, fwnmacc16)
RVVCALL(OPFVF3, vfwnmacc_vf_w, WOP_UUU_W, H8, H4, fwnmacc32)
-GEN_VEXT_VF(vfwnmacc_vf_h)
-GEN_VEXT_VF(vfwnmacc_vf_w)
+GEN_VEXT_VF(vfwnmacc_vf_h, 4)
+GEN_VEXT_VF(vfwnmacc_vf_w, 8)
static uint32_t fwmsac16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
{
@@ -3552,12 +3564,12 @@ static uint64_t fwmsac32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfwmsac_vv_h, WOP_UUU_H, H4, H2, H2, fwmsac16)
RVVCALL(OPFVV3, vfwmsac_vv_w, WOP_UUU_W, H8, H4, H4, fwmsac32)
-GEN_VEXT_VV_ENV(vfwmsac_vv_h)
-GEN_VEXT_VV_ENV(vfwmsac_vv_w)
+GEN_VEXT_VV_ENV(vfwmsac_vv_h, 4)
+GEN_VEXT_VV_ENV(vfwmsac_vv_w, 8)
RVVCALL(OPFVF3, vfwmsac_vf_h, WOP_UUU_H, H4, H2, fwmsac16)
RVVCALL(OPFVF3, vfwmsac_vf_w, WOP_UUU_W, H8, H4, fwmsac32)
-GEN_VEXT_VF(vfwmsac_vf_h)
-GEN_VEXT_VF(vfwmsac_vf_w)
+GEN_VEXT_VF(vfwmsac_vf_h, 4)
+GEN_VEXT_VF(vfwmsac_vf_w, 8)
static uint32_t fwnmsac16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
{
@@ -3575,12 +3587,12 @@ static uint64_t fwnmsac32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfwnmsac_vv_h, WOP_UUU_H, H4, H2, H2, fwnmsac16)
RVVCALL(OPFVV3, vfwnmsac_vv_w, WOP_UUU_W, H8, H4, H4, fwnmsac32)
-GEN_VEXT_VV_ENV(vfwnmsac_vv_h)
-GEN_VEXT_VV_ENV(vfwnmsac_vv_w)
+GEN_VEXT_VV_ENV(vfwnmsac_vv_h, 4)
+GEN_VEXT_VV_ENV(vfwnmsac_vv_w, 8)
RVVCALL(OPFVF3, vfwnmsac_vf_h, WOP_UUU_H, H4, H2, fwnmsac16)
RVVCALL(OPFVF3, vfwnmsac_vf_w, WOP_UUU_W, H8, H4, fwnmsac32)
-GEN_VEXT_VF(vfwnmsac_vf_h)
-GEN_VEXT_VF(vfwnmsac_vf_w)
+GEN_VEXT_VF(vfwnmsac_vf_h, 4)
+GEN_VEXT_VF(vfwnmsac_vf_w, 8)
/* Vector Floating-Point Square-Root Instruction */
/* (TD, T2, TX2) */
@@ -3596,12 +3608,15 @@ static void do_##NAME(void *vd, void *vs2, int i, \
*((TD *)vd + HD(i)) = OP(s2, &env->fp_status); \
}
-#define GEN_VEXT_V_ENV(NAME) \
+#define GEN_VEXT_V_ENV(NAME, ESZ) \
void HELPER(NAME)(void *vd, void *v0, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t total_elems = \
+ vext_get_total_elems(env, desc, ESZ); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
if (vl == 0) { \
@@ -3614,14 +3629,16 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \
do_##NAME(vd, vs2, i, env); \
} \
env->vstart = 0; \
+ vext_set_elems_1s(vd, vta, vl * ESZ, \
+ total_elems * ESZ); \
}
RVVCALL(OPFVV1, vfsqrt_v_h, OP_UU_H, H2, H2, float16_sqrt)
RVVCALL(OPFVV1, vfsqrt_v_w, OP_UU_W, H4, H4, float32_sqrt)
RVVCALL(OPFVV1, vfsqrt_v_d, OP_UU_D, H8, H8, float64_sqrt)
-GEN_VEXT_V_ENV(vfsqrt_v_h)
-GEN_VEXT_V_ENV(vfsqrt_v_w)
-GEN_VEXT_V_ENV(vfsqrt_v_d)
+GEN_VEXT_V_ENV(vfsqrt_v_h, 2)
+GEN_VEXT_V_ENV(vfsqrt_v_w, 4)
+GEN_VEXT_V_ENV(vfsqrt_v_d, 8)
/*
* Vector Floating-Point Reciprocal Square-Root Estimate Instruction
@@ -3801,9 +3818,9 @@ static float64 frsqrt7_d(float64 f, float_status *s)
RVVCALL(OPFVV1, vfrsqrt7_v_h, OP_UU_H, H2, H2, frsqrt7_h)
RVVCALL(OPFVV1, vfrsqrt7_v_w, OP_UU_W, H4, H4, frsqrt7_s)
RVVCALL(OPFVV1, vfrsqrt7_v_d, OP_UU_D, H8, H8, frsqrt7_d)
-GEN_VEXT_V_ENV(vfrsqrt7_v_h)
-GEN_VEXT_V_ENV(vfrsqrt7_v_w)
-GEN_VEXT_V_ENV(vfrsqrt7_v_d)
+GEN_VEXT_V_ENV(vfrsqrt7_v_h, 2)
+GEN_VEXT_V_ENV(vfrsqrt7_v_w, 4)
+GEN_VEXT_V_ENV(vfrsqrt7_v_d, 8)
/*
* Vector Floating-Point Reciprocal Estimate Instruction
@@ -3992,36 +4009,36 @@ static float64 frec7_d(float64 f, float_status *s)
RVVCALL(OPFVV1, vfrec7_v_h, OP_UU_H, H2, H2, frec7_h)
RVVCALL(OPFVV1, vfrec7_v_w, OP_UU_W, H4, H4, frec7_s)
RVVCALL(OPFVV1, vfrec7_v_d, OP_UU_D, H8, H8, frec7_d)
-GEN_VEXT_V_ENV(vfrec7_v_h)
-GEN_VEXT_V_ENV(vfrec7_v_w)
-GEN_VEXT_V_ENV(vfrec7_v_d)
+GEN_VEXT_V_ENV(vfrec7_v_h, 2)
+GEN_VEXT_V_ENV(vfrec7_v_w, 4)
+GEN_VEXT_V_ENV(vfrec7_v_d, 8)
/* Vector Floating-Point MIN/MAX Instructions */
RVVCALL(OPFVV2, vfmin_vv_h, OP_UUU_H, H2, H2, H2, float16_minimum_number)
RVVCALL(OPFVV2, vfmin_vv_w, OP_UUU_W, H4, H4, H4, float32_minimum_number)
RVVCALL(OPFVV2, vfmin_vv_d, OP_UUU_D, H8, H8, H8, float64_minimum_number)
-GEN_VEXT_VV_ENV(vfmin_vv_h)
-GEN_VEXT_VV_ENV(vfmin_vv_w)
-GEN_VEXT_VV_ENV(vfmin_vv_d)
+GEN_VEXT_VV_ENV(vfmin_vv_h, 2)
+GEN_VEXT_VV_ENV(vfmin_vv_w, 4)
+GEN_VEXT_VV_ENV(vfmin_vv_d, 8)
RVVCALL(OPFVF2, vfmin_vf_h, OP_UUU_H, H2, H2, float16_minimum_number)
RVVCALL(OPFVF2, vfmin_vf_w, OP_UUU_W, H4, H4, float32_minimum_number)
RVVCALL(OPFVF2, vfmin_vf_d, OP_UUU_D, H8, H8, float64_minimum_number)
-GEN_VEXT_VF(vfmin_vf_h)
-GEN_VEXT_VF(vfmin_vf_w)
-GEN_VEXT_VF(vfmin_vf_d)
+GEN_VEXT_VF(vfmin_vf_h, 2)
+GEN_VEXT_VF(vfmin_vf_w, 4)
+GEN_VEXT_VF(vfmin_vf_d, 8)
RVVCALL(OPFVV2, vfmax_vv_h, OP_UUU_H, H2, H2, H2, float16_maximum_number)
RVVCALL(OPFVV2, vfmax_vv_w, OP_UUU_W, H4, H4, H4, float32_maximum_number)
RVVCALL(OPFVV2, vfmax_vv_d, OP_UUU_D, H8, H8, H8, float64_maximum_number)
-GEN_VEXT_VV_ENV(vfmax_vv_h)
-GEN_VEXT_VV_ENV(vfmax_vv_w)
-GEN_VEXT_VV_ENV(vfmax_vv_d)
+GEN_VEXT_VV_ENV(vfmax_vv_h, 2)
+GEN_VEXT_VV_ENV(vfmax_vv_w, 4)
+GEN_VEXT_VV_ENV(vfmax_vv_d, 8)
RVVCALL(OPFVF2, vfmax_vf_h, OP_UUU_H, H2, H2, float16_maximum_number)
RVVCALL(OPFVF2, vfmax_vf_w, OP_UUU_W, H4, H4, float32_maximum_number)
RVVCALL(OPFVF2, vfmax_vf_d, OP_UUU_D, H8, H8, float64_maximum_number)
-GEN_VEXT_VF(vfmax_vf_h)
-GEN_VEXT_VF(vfmax_vf_w)
-GEN_VEXT_VF(vfmax_vf_d)
+GEN_VEXT_VF(vfmax_vf_h, 2)
+GEN_VEXT_VF(vfmax_vf_w, 4)
+GEN_VEXT_VF(vfmax_vf_d, 8)
/* Vector Floating-Point Sign-Injection Instructions */
static uint16_t fsgnj16(uint16_t a, uint16_t b, float_status *s)
@@ -4042,15 +4059,15 @@ static uint64_t fsgnj64(uint64_t a, uint64_t b, float_status *s)
RVVCALL(OPFVV2, vfsgnj_vv_h, OP_UUU_H, H2, H2, H2, fsgnj16)
RVVCALL(OPFVV2, vfsgnj_vv_w, OP_UUU_W, H4, H4, H4, fsgnj32)
RVVCALL(OPFVV2, vfsgnj_vv_d, OP_UUU_D, H8, H8, H8, fsgnj64)
-GEN_VEXT_VV_ENV(vfsgnj_vv_h)
-GEN_VEXT_VV_ENV(vfsgnj_vv_w)
-GEN_VEXT_VV_ENV(vfsgnj_vv_d)
+GEN_VEXT_VV_ENV(vfsgnj_vv_h, 2)
+GEN_VEXT_VV_ENV(vfsgnj_vv_w, 4)
+GEN_VEXT_VV_ENV(vfsgnj_vv_d, 8)
RVVCALL(OPFVF2, vfsgnj_vf_h, OP_UUU_H, H2, H2, fsgnj16)
RVVCALL(OPFVF2, vfsgnj_vf_w, OP_UUU_W, H4, H4, fsgnj32)
RVVCALL(OPFVF2, vfsgnj_vf_d, OP_UUU_D, H8, H8, fsgnj64)
-GEN_VEXT_VF(vfsgnj_vf_h)
-GEN_VEXT_VF(vfsgnj_vf_w)
-GEN_VEXT_VF(vfsgnj_vf_d)
+GEN_VEXT_VF(vfsgnj_vf_h, 2)
+GEN_VEXT_VF(vfsgnj_vf_w, 4)
+GEN_VEXT_VF(vfsgnj_vf_d, 8)
static uint16_t fsgnjn16(uint16_t a, uint16_t b, float_status *s)
{
@@ -4070,15 +4087,15 @@ static uint64_t fsgnjn64(uint64_t a, uint64_t b, float_status *s)
RVVCALL(OPFVV2, vfsgnjn_vv_h, OP_UUU_H, H2, H2, H2, fsgnjn16)
RVVCALL(OPFVV2, vfsgnjn_vv_w, OP_UUU_W, H4, H4, H4, fsgnjn32)
RVVCALL(OPFVV2, vfsgnjn_vv_d, OP_UUU_D, H8, H8, H8, fsgnjn64)
-GEN_VEXT_VV_ENV(vfsgnjn_vv_h)
-GEN_VEXT_VV_ENV(vfsgnjn_vv_w)
-GEN_VEXT_VV_ENV(vfsgnjn_vv_d)
+GEN_VEXT_VV_ENV(vfsgnjn_vv_h, 2)
+GEN_VEXT_VV_ENV(vfsgnjn_vv_w, 4)
+GEN_VEXT_VV_ENV(vfsgnjn_vv_d, 8)
RVVCALL(OPFVF2, vfsgnjn_vf_h, OP_UUU_H, H2, H2, fsgnjn16)
RVVCALL(OPFVF2, vfsgnjn_vf_w, OP_UUU_W, H4, H4, fsgnjn32)
RVVCALL(OPFVF2, vfsgnjn_vf_d, OP_UUU_D, H8, H8, fsgnjn64)
-GEN_VEXT_VF(vfsgnjn_vf_h)
-GEN_VEXT_VF(vfsgnjn_vf_w)
-GEN_VEXT_VF(vfsgnjn_vf_d)
+GEN_VEXT_VF(vfsgnjn_vf_h, 2)
+GEN_VEXT_VF(vfsgnjn_vf_w, 4)
+GEN_VEXT_VF(vfsgnjn_vf_d, 8)
static uint16_t fsgnjx16(uint16_t a, uint16_t b, float_status *s)
{
@@ -4098,15 +4115,15 @@ static uint64_t fsgnjx64(uint64_t a, uint64_t b, float_status *s)
RVVCALL(OPFVV2, vfsgnjx_vv_h, OP_UUU_H, H2, H2, H2, fsgnjx16)
RVVCALL(OPFVV2, vfsgnjx_vv_w, OP_UUU_W, H4, H4, H4, fsgnjx32)
RVVCALL(OPFVV2, vfsgnjx_vv_d, OP_UUU_D, H8, H8, H8, fsgnjx64)
-GEN_VEXT_VV_ENV(vfsgnjx_vv_h)
-GEN_VEXT_VV_ENV(vfsgnjx_vv_w)
-GEN_VEXT_VV_ENV(vfsgnjx_vv_d)
+GEN_VEXT_VV_ENV(vfsgnjx_vv_h, 2)
+GEN_VEXT_VV_ENV(vfsgnjx_vv_w, 4)
+GEN_VEXT_VV_ENV(vfsgnjx_vv_d, 8)
RVVCALL(OPFVF2, vfsgnjx_vf_h, OP_UUU_H, H2, H2, fsgnjx16)
RVVCALL(OPFVF2, vfsgnjx_vf_w, OP_UUU_W, H4, H4, fsgnjx32)
RVVCALL(OPFVF2, vfsgnjx_vf_d, OP_UUU_D, H8, H8, fsgnjx64)
-GEN_VEXT_VF(vfsgnjx_vf_h)
-GEN_VEXT_VF(vfsgnjx_vf_w)
-GEN_VEXT_VF(vfsgnjx_vf_d)
+GEN_VEXT_VF(vfsgnjx_vf_h, 2)
+GEN_VEXT_VF(vfsgnjx_vf_w, 4)
+GEN_VEXT_VF(vfsgnjx_vf_d, 8)
/* Vector Floating-Point Compare Instructions */
#define GEN_VEXT_CMP_VV_ENV(NAME, ETYPE, H, DO_OP) \
@@ -4115,6 +4132,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t total_elems = env_archcpu(env)->cfg.vlen; \
+ uint32_t vta_all_1s = vext_vta_all_1s(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -4127,6 +4146,13 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
DO_OP(s2, s1, &env->fp_status)); \
} \
env->vstart = 0; \
+ /* mask destination register are always tail-agnostic */ \
+ /* set tail elements to 1s */ \
+ if (vta_all_1s) { \
+ for (; i < total_elems; i++) { \
+ vext_set_elem_mask(vd, i, 1); \
+ } \
+ } \
}
GEN_VEXT_CMP_VV_ENV(vmfeq_vv_h, uint16_t, H2, float16_eq_quiet)
@@ -4139,6 +4165,8 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t total_elems = env_archcpu(env)->cfg.vlen; \
+ uint32_t vta_all_1s = vext_vta_all_1s(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -4150,6 +4178,13 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \
DO_OP(s2, (ETYPE)s1, &env->fp_status)); \
} \
env->vstart = 0; \
+ /* mask destination register are always tail-agnostic */ \
+ /* set tail elements to 1s */ \
+ if (vta_all_1s) { \
+ for (; i < total_elems; i++) { \
+ vext_set_elem_mask(vd, i, 1); \
+ } \
+ } \
}
GEN_VEXT_CMP_VF(vmfeq_vf_h, uint16_t, H2, float16_eq_quiet)
@@ -4250,12 +4285,15 @@ static void do_##NAME(void *vd, void *vs2, int i) \
*((TD *)vd + HD(i)) = OP(s2); \
}
-#define GEN_VEXT_V(NAME) \
+#define GEN_VEXT_V(NAME, ESZ) \
void HELPER(NAME)(void *vd, void *v0, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t total_elems = \
+ vext_get_total_elems(env, desc, ESZ); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -4265,6 +4303,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \
do_##NAME(vd, vs2, i); \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * ESZ, \
+ total_elems * ESZ); \
}
target_ulong fclass_h(uint64_t frs1)
@@ -4327,17 +4368,22 @@ target_ulong fclass_d(uint64_t frs1)
RVVCALL(OPIVV1, vfclass_v_h, OP_UU_H, H2, H2, fclass_h)
RVVCALL(OPIVV1, vfclass_v_w, OP_UU_W, H4, H4, fclass_s)
RVVCALL(OPIVV1, vfclass_v_d, OP_UU_D, H8, H8, fclass_d)
-GEN_VEXT_V(vfclass_v_h)
-GEN_VEXT_V(vfclass_v_w)
-GEN_VEXT_V(vfclass_v_d)
+GEN_VEXT_V(vfclass_v_h, 2)
+GEN_VEXT_V(vfclass_v_w, 4)
+GEN_VEXT_V(vfclass_v_d, 8)
/* Vector Floating-Point Merge Instruction */
+
#define GEN_VFMERGE_VF(NAME, ETYPE, H) \
void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = \
+ vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -4346,6 +4392,8 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \
= (!vm && !vext_elem_mask(v0, i) ? s2 : s1); \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VFMERGE_VF(vfmerge_vfm_h, int16_t, H2)
@@ -4357,33 +4405,33 @@ GEN_VFMERGE_VF(vfmerge_vfm_d, int64_t, H8)
RVVCALL(OPFVV1, vfcvt_xu_f_v_h, OP_UU_H, H2, H2, float16_to_uint16)
RVVCALL(OPFVV1, vfcvt_xu_f_v_w, OP_UU_W, H4, H4, float32_to_uint32)
RVVCALL(OPFVV1, vfcvt_xu_f_v_d, OP_UU_D, H8, H8, float64_to_uint64)
-GEN_VEXT_V_ENV(vfcvt_xu_f_v_h)
-GEN_VEXT_V_ENV(vfcvt_xu_f_v_w)
-GEN_VEXT_V_ENV(vfcvt_xu_f_v_d)
+GEN_VEXT_V_ENV(vfcvt_xu_f_v_h, 2)
+GEN_VEXT_V_ENV(vfcvt_xu_f_v_w, 4)
+GEN_VEXT_V_ENV(vfcvt_xu_f_v_d, 8)
/* vfcvt.x.f.v vd, vs2, vm # Convert float to signed integer. */
RVVCALL(OPFVV1, vfcvt_x_f_v_h, OP_UU_H, H2, H2, float16_to_int16)
RVVCALL(OPFVV1, vfcvt_x_f_v_w, OP_UU_W, H4, H4, float32_to_int32)
RVVCALL(OPFVV1, vfcvt_x_f_v_d, OP_UU_D, H8, H8, float64_to_int64)
-GEN_VEXT_V_ENV(vfcvt_x_f_v_h)
-GEN_VEXT_V_ENV(vfcvt_x_f_v_w)
-GEN_VEXT_V_ENV(vfcvt_x_f_v_d)
+GEN_VEXT_V_ENV(vfcvt_x_f_v_h, 2)
+GEN_VEXT_V_ENV(vfcvt_x_f_v_w, 4)
+GEN_VEXT_V_ENV(vfcvt_x_f_v_d, 8)
/* vfcvt.f.xu.v vd, vs2, vm # Convert unsigned integer to float. */
RVVCALL(OPFVV1, vfcvt_f_xu_v_h, OP_UU_H, H2, H2, uint16_to_float16)
RVVCALL(OPFVV1, vfcvt_f_xu_v_w, OP_UU_W, H4, H4, uint32_to_float32)
RVVCALL(OPFVV1, vfcvt_f_xu_v_d, OP_UU_D, H8, H8, uint64_to_float64)
-GEN_VEXT_V_ENV(vfcvt_f_xu_v_h)
-GEN_VEXT_V_ENV(vfcvt_f_xu_v_w)
-GEN_VEXT_V_ENV(vfcvt_f_xu_v_d)
+GEN_VEXT_V_ENV(vfcvt_f_xu_v_h, 2)
+GEN_VEXT_V_ENV(vfcvt_f_xu_v_w, 4)
+GEN_VEXT_V_ENV(vfcvt_f_xu_v_d, 8)
/* vfcvt.f.x.v vd, vs2, vm # Convert integer to float. */
RVVCALL(OPFVV1, vfcvt_f_x_v_h, OP_UU_H, H2, H2, int16_to_float16)
RVVCALL(OPFVV1, vfcvt_f_x_v_w, OP_UU_W, H4, H4, int32_to_float32)
RVVCALL(OPFVV1, vfcvt_f_x_v_d, OP_UU_D, H8, H8, int64_to_float64)
-GEN_VEXT_V_ENV(vfcvt_f_x_v_h)
-GEN_VEXT_V_ENV(vfcvt_f_x_v_w)
-GEN_VEXT_V_ENV(vfcvt_f_x_v_d)
+GEN_VEXT_V_ENV(vfcvt_f_x_v_h, 2)
+GEN_VEXT_V_ENV(vfcvt_f_x_v_w, 4)
+GEN_VEXT_V_ENV(vfcvt_f_x_v_d, 8)
/* Widening Floating-Point/Integer Type-Convert Instructions */
/* (TD, T2, TX2) */
@@ -4393,30 +4441,30 @@ GEN_VEXT_V_ENV(vfcvt_f_x_v_d)
/* vfwcvt.xu.f.v vd, vs2, vm # Convert float to double-width unsigned integer.*/
RVVCALL(OPFVV1, vfwcvt_xu_f_v_h, WOP_UU_H, H4, H2, float16_to_uint32)
RVVCALL(OPFVV1, vfwcvt_xu_f_v_w, WOP_UU_W, H8, H4, float32_to_uint64)
-GEN_VEXT_V_ENV(vfwcvt_xu_f_v_h)
-GEN_VEXT_V_ENV(vfwcvt_xu_f_v_w)
+GEN_VEXT_V_ENV(vfwcvt_xu_f_v_h, 4)
+GEN_VEXT_V_ENV(vfwcvt_xu_f_v_w, 8)
/* vfwcvt.x.f.v vd, vs2, vm # Convert float to double-width signed integer. */
RVVCALL(OPFVV1, vfwcvt_x_f_v_h, WOP_UU_H, H4, H2, float16_to_int32)
RVVCALL(OPFVV1, vfwcvt_x_f_v_w, WOP_UU_W, H8, H4, float32_to_int64)
-GEN_VEXT_V_ENV(vfwcvt_x_f_v_h)
-GEN_VEXT_V_ENV(vfwcvt_x_f_v_w)
+GEN_VEXT_V_ENV(vfwcvt_x_f_v_h, 4)
+GEN_VEXT_V_ENV(vfwcvt_x_f_v_w, 8)
/* vfwcvt.f.xu.v vd, vs2, vm # Convert unsigned integer to double-width float */
RVVCALL(OPFVV1, vfwcvt_f_xu_v_b, WOP_UU_B, H2, H1, uint8_to_float16)
RVVCALL(OPFVV1, vfwcvt_f_xu_v_h, WOP_UU_H, H4, H2, uint16_to_float32)
RVVCALL(OPFVV1, vfwcvt_f_xu_v_w, WOP_UU_W, H8, H4, uint32_to_float64)
-GEN_VEXT_V_ENV(vfwcvt_f_xu_v_b)
-GEN_VEXT_V_ENV(vfwcvt_f_xu_v_h)
-GEN_VEXT_V_ENV(vfwcvt_f_xu_v_w)
+GEN_VEXT_V_ENV(vfwcvt_f_xu_v_b, 2)
+GEN_VEXT_V_ENV(vfwcvt_f_xu_v_h, 4)
+GEN_VEXT_V_ENV(vfwcvt_f_xu_v_w, 8)
/* vfwcvt.f.x.v vd, vs2, vm # Convert integer to double-width float. */
RVVCALL(OPFVV1, vfwcvt_f_x_v_b, WOP_UU_B, H2, H1, int8_to_float16)
RVVCALL(OPFVV1, vfwcvt_f_x_v_h, WOP_UU_H, H4, H2, int16_to_float32)
RVVCALL(OPFVV1, vfwcvt_f_x_v_w, WOP_UU_W, H8, H4, int32_to_float64)
-GEN_VEXT_V_ENV(vfwcvt_f_x_v_b)
-GEN_VEXT_V_ENV(vfwcvt_f_x_v_h)
-GEN_VEXT_V_ENV(vfwcvt_f_x_v_w)
+GEN_VEXT_V_ENV(vfwcvt_f_x_v_b, 2)
+GEN_VEXT_V_ENV(vfwcvt_f_x_v_h, 4)
+GEN_VEXT_V_ENV(vfwcvt_f_x_v_w, 8)
/*
* vfwcvt.f.f.v vd, vs2, vm
@@ -4429,8 +4477,8 @@ static uint32_t vfwcvtffv16(uint16_t a, float_status *s)
RVVCALL(OPFVV1, vfwcvt_f_f_v_h, WOP_UU_H, H4, H2, vfwcvtffv16)
RVVCALL(OPFVV1, vfwcvt_f_f_v_w, WOP_UU_W, H8, H4, float32_to_float64)
-GEN_VEXT_V_ENV(vfwcvt_f_f_v_h)
-GEN_VEXT_V_ENV(vfwcvt_f_f_v_w)
+GEN_VEXT_V_ENV(vfwcvt_f_f_v_h, 4)
+GEN_VEXT_V_ENV(vfwcvt_f_f_v_w, 8)
/* Narrowing Floating-Point/Integer Type-Convert Instructions */
/* (TD, T2, TX2) */
@@ -4441,29 +4489,29 @@ GEN_VEXT_V_ENV(vfwcvt_f_f_v_w)
RVVCALL(OPFVV1, vfncvt_xu_f_w_b, NOP_UU_B, H1, H2, float16_to_uint8)
RVVCALL(OPFVV1, vfncvt_xu_f_w_h, NOP_UU_H, H2, H4, float32_to_uint16)
RVVCALL(OPFVV1, vfncvt_xu_f_w_w, NOP_UU_W, H4, H8, float64_to_uint32)
-GEN_VEXT_V_ENV(vfncvt_xu_f_w_b)
-GEN_VEXT_V_ENV(vfncvt_xu_f_w_h)
-GEN_VEXT_V_ENV(vfncvt_xu_f_w_w)
+GEN_VEXT_V_ENV(vfncvt_xu_f_w_b, 1)
+GEN_VEXT_V_ENV(vfncvt_xu_f_w_h, 2)
+GEN_VEXT_V_ENV(vfncvt_xu_f_w_w, 4)
/* vfncvt.x.f.v vd, vs2, vm # Convert double-width float to signed integer. */
RVVCALL(OPFVV1, vfncvt_x_f_w_b, NOP_UU_B, H1, H2, float16_to_int8)
RVVCALL(OPFVV1, vfncvt_x_f_w_h, NOP_UU_H, H2, H4, float32_to_int16)
RVVCALL(OPFVV1, vfncvt_x_f_w_w, NOP_UU_W, H4, H8, float64_to_int32)
-GEN_VEXT_V_ENV(vfncvt_x_f_w_b)
-GEN_VEXT_V_ENV(vfncvt_x_f_w_h)
-GEN_VEXT_V_ENV(vfncvt_x_f_w_w)
+GEN_VEXT_V_ENV(vfncvt_x_f_w_b, 1)
+GEN_VEXT_V_ENV(vfncvt_x_f_w_h, 2)
+GEN_VEXT_V_ENV(vfncvt_x_f_w_w, 4)
/* vfncvt.f.xu.v vd, vs2, vm # Convert double-width unsigned integer to float */
RVVCALL(OPFVV1, vfncvt_f_xu_w_h, NOP_UU_H, H2, H4, uint32_to_float16)
RVVCALL(OPFVV1, vfncvt_f_xu_w_w, NOP_UU_W, H4, H8, uint64_to_float32)
-GEN_VEXT_V_ENV(vfncvt_f_xu_w_h)
-GEN_VEXT_V_ENV(vfncvt_f_xu_w_w)
+GEN_VEXT_V_ENV(vfncvt_f_xu_w_h, 2)
+GEN_VEXT_V_ENV(vfncvt_f_xu_w_w, 4)
/* vfncvt.f.x.v vd, vs2, vm # Convert double-width integer to float. */
RVVCALL(OPFVV1, vfncvt_f_x_w_h, NOP_UU_H, H2, H4, int32_to_float16)
RVVCALL(OPFVV1, vfncvt_f_x_w_w, NOP_UU_W, H4, H8, int64_to_float32)
-GEN_VEXT_V_ENV(vfncvt_f_x_w_h)
-GEN_VEXT_V_ENV(vfncvt_f_x_w_w)
+GEN_VEXT_V_ENV(vfncvt_f_x_w_h, 2)
+GEN_VEXT_V_ENV(vfncvt_f_x_w_w, 4)
/* vfncvt.f.f.v vd, vs2, vm # Convert double float to single-width float. */
static uint16_t vfncvtffv16(uint32_t a, float_status *s)
@@ -4473,8 +4521,8 @@ static uint16_t vfncvtffv16(uint32_t a, float_status *s)
RVVCALL(OPFVV1, vfncvt_f_f_w_h, NOP_UU_H, H2, H4, vfncvtffv16)
RVVCALL(OPFVV1, vfncvt_f_f_w_w, NOP_UU_W, H4, H8, float64_to_float32)
-GEN_VEXT_V_ENV(vfncvt_f_f_w_h)
-GEN_VEXT_V_ENV(vfncvt_f_f_w_w)
+GEN_VEXT_V_ENV(vfncvt_f_f_w_h, 2)
+GEN_VEXT_V_ENV(vfncvt_f_f_w_w, 4)
/*
*** Vector Reduction Operations
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 15/16] target/riscv: rvv: Add tail agnostic for vector permutation instructions
@ 2022-05-13 11:50 ` ~eopxd
0 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-05-13 11:50 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/insn_trans/trans_rvv.c.inc | 7 +++--
target/riscv/vector_helper.c | 40 +++++++++++++++++++++++++
2 files changed, 45 insertions(+), 2 deletions(-)
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index 430d4e4460..6e8ed7694c 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -3665,7 +3665,7 @@ static bool trans_vrgather_vx(DisasContext *s, arg_rmrr *a)
return false;
}
- if (a->vm && s->vl_eq_vlmax) {
+ if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
int scale = s->lmul - (s->sew + 3);
int vlmax = s->cfg_ptr->vlen >> -scale;
TCGv_i64 dest = tcg_temp_new_i64();
@@ -3697,7 +3697,7 @@ static bool trans_vrgather_vi(DisasContext *s, arg_rmrr *a)
return false;
}
- if (a->vm && s->vl_eq_vlmax) {
+ if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
int scale = s->lmul - (s->sew + 3);
int vlmax = s->cfg_ptr->vlen >> -scale;
if (a->rs1 >= vlmax) {
@@ -3749,6 +3749,7 @@ static bool trans_vcompress_vm(DisasContext *s, arg_r *a)
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),
vreg_ofs(s, a->rs1), vreg_ofs(s, a->rs2),
cpu_env, s->cfg_ptr->vlen / 8,
@@ -3849,6 +3850,8 @@ static bool int_ext_op(DisasContext *s, arg_rmr *a, uint8_t seq)
}
data = FIELD_DP32(data, VDATA, VM, a->vm);
+ data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),
vreg_ofs(s, a->rs2), cpu_env,
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 5c2d1c02f4..2afbac6e37 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4930,6 +4930,9 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
target_ulong offset = s1, i_min, i; \
\
i_min = MAX(env->vstart, offset); \
@@ -4939,6 +4942,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
} \
*((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(i - offset)); \
} \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
/* vslideup.vx vd, vs2, rs1, vm # vd[i+rs1] = vs2[i] */
@@ -4954,6 +4959,9 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
uint32_t vlmax = vext_max_elems(desc, ctzl(sizeof(ETYPE))); \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
target_ulong i_max, i; \
\
i_max = MAX(MIN(s1 < vlmax ? vlmax - s1 : 0, vl), env->vstart); \
@@ -4970,6 +4978,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
} \
\
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
/* vslidedown.vx vd, vs2, rs1, vm # vd[i] = vs2[i+rs1] */
@@ -4985,6 +4995,9 @@ static void vslide1up_##BITWIDTH(void *vd, void *v0, target_ulong s1, \
typedef uint##BITWIDTH##_t ETYPE; \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -4998,6 +5011,8 @@ static void vslide1up_##BITWIDTH(void *vd, void *v0, target_ulong s1, \
} \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VEXT_VSLIE1UP(8, H1)
@@ -5025,6 +5040,9 @@ static void vslide1down_##BITWIDTH(void *vd, void *v0, target_ulong s1, \
typedef uint##BITWIDTH##_t ETYPE; \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -5038,6 +5056,8 @@ static void vslide1down_##BITWIDTH(void *vd, void *v0, target_ulong s1, \
} \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VEXT_VSLIDE1DOWN(8, H1)
@@ -5091,6 +5111,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
uint32_t vlmax = vext_max_elems(desc, ctzl(sizeof(TS2))); \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(TS2); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint64_t index; \
uint32_t i; \
\
@@ -5106,6 +5129,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
} \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
/* vd[i] = (vs1[i] >= VLMAX) ? 0 : vs2[vs1[i]]; */
@@ -5126,6 +5151,9 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
uint32_t vlmax = vext_max_elems(desc, ctzl(sizeof(ETYPE))); \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint64_t index = s1; \
uint32_t i; \
\
@@ -5140,6 +5168,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
} \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
/* vd[i] = (x[rs1] >= VLMAX) ? 0 : vs2[rs1] */
@@ -5154,6 +5184,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t num = 0, i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -5164,6 +5197,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
num++; \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
/* Compress into vd elements of vs2 where vs1 is enabled */
@@ -5195,6 +5230,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \
{ \
uint32_t vl = env->vl; \
uint32_t vm = vext_vm(desc); \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -5204,6 +5242,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \
*((ETYPE *)vd + HD(i)) = *((DTYPE *)vs2 + HS1(i)); \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VEXT_INT_EXT(vzext_vf2_h, uint16_t, uint8_t, H2, H1)
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* [PATCH qemu v18 16/16] target/riscv: rvv: Add option 'rvv_ta_all_1s' to enable optional tail agnostic behavior
@ 2022-05-13 11:50 ` ~eopxd
0 siblings, 0 replies; 35+ messages in thread
From: ~eopxd @ 2022-05-13 11:50 UTC (permalink / raw)
To: qemu-devel, qemu-riscv
Cc: Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
From: eopXD <eop.chen@sifive.com>
According to v-spec, tail agnostic behavior can be either kept as
undisturbed or set elements' bits to all 1s. To distinguish the
difference of tail policies, QEMU should be able to simulate the tail
agnostic behavior as "set tail elements' bits to all 1s".
There are multiple possibility for agnostic elements according to
v-spec. The main intent of this patch-set tries to add option that
can distinguish between tail policies. Setting agnostic elements to
all 1s allows QEMU to express this.
This commit adds option 'rvv_ta_all_1s' is added to enable the
behavior, it is default as disabled.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/cpu.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
index ccacdee215..720c8b9e5c 100644
--- a/target/riscv/cpu.c
+++ b/target/riscv/cpu.c
@@ -879,6 +879,7 @@ static Property riscv_cpu_properties[] = {
DEFINE_PROP_BOOL("x-aia", RISCVCPU, cfg.aia, false),
DEFINE_PROP_UINT64("resetvec", RISCVCPU, cfg.resetvec, DEFAULT_RSTVEC),
+ DEFINE_PROP_BOOL("rvv_ta_all_1s", RISCVCPU, cfg.rvv_ta_all_1s, false),
DEFINE_PROP_END_OF_LIST(),
};
--
2.34.2
^ permalink raw reply related [flat|nested] 35+ messages in thread
* Re: [PATCH qemu v18 02/16] target/riscv: rvv: Prune redundant access_type parameter passed
2022-05-12 7:47 ` [PATCH qemu v18 02/16] target/riscv: rvv: Prune redundant access_type parameter passed ~eopxd
@ 2022-05-23 21:39 ` Alistair Francis
0 siblings, 0 replies; 35+ messages in thread
From: Alistair Francis @ 2022-05-23 21:39 UTC (permalink / raw)
To: ~eopxd
Cc: qemu-devel@nongnu.org Developers, open list:RISC-V,
Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
On Fri, May 13, 2022 at 9:50 PM ~eopxd <eopxd@git.sr.ht> wrote:
>
> From: eopXD <eop.chen@sifive.com>
>
> No functional change intended in this commit.
>
> Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Alistair
> ---
> target/riscv/vector_helper.c | 35 ++++++++++++++++-------------------
> 1 file changed, 16 insertions(+), 19 deletions(-)
>
> diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
> index 85dd611cd9..60840325c4 100644
> --- a/target/riscv/vector_helper.c
> +++ b/target/riscv/vector_helper.c
> @@ -231,7 +231,7 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base,
> target_ulong stride, CPURISCVState *env,
> uint32_t desc, uint32_t vm,
> vext_ldst_elem_fn *ldst_elem,
> - uint32_t esz, uintptr_t ra, MMUAccessType access_type)
> + uint32_t esz, uintptr_t ra)
> {
> uint32_t i, k;
> uint32_t nf = vext_nf(desc);
> @@ -259,7 +259,7 @@ void HELPER(NAME)(void *vd, void * v0, target_ulong base, \
> { \
> uint32_t vm = vext_vm(desc); \
> vext_ldst_stride(vd, v0, base, stride, env, desc, vm, LOAD_FN, \
> - ctzl(sizeof(ETYPE)), GETPC(), MMU_DATA_LOAD); \
> + ctzl(sizeof(ETYPE)), GETPC()); \
> }
>
> GEN_VEXT_LD_STRIDE(vlse8_v, int8_t, lde_b)
> @@ -274,7 +274,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong base, \
> { \
> uint32_t vm = vext_vm(desc); \
> vext_ldst_stride(vd, v0, base, stride, env, desc, vm, STORE_FN, \
> - ctzl(sizeof(ETYPE)), GETPC(), MMU_DATA_STORE); \
> + ctzl(sizeof(ETYPE)), GETPC()); \
> }
>
> GEN_VEXT_ST_STRIDE(vsse8_v, int8_t, ste_b)
> @@ -290,7 +290,7 @@ GEN_VEXT_ST_STRIDE(vsse64_v, int64_t, ste_d)
> static void
> vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
> vext_ldst_elem_fn *ldst_elem, uint32_t esz, uint32_t evl,
> - uintptr_t ra, MMUAccessType access_type)
> + uintptr_t ra)
> {
> uint32_t i, k;
> uint32_t nf = vext_nf(desc);
> @@ -319,14 +319,14 @@ void HELPER(NAME##_mask)(void *vd, void *v0, target_ulong base, \
> { \
> uint32_t stride = vext_nf(desc) << ctzl(sizeof(ETYPE)); \
> vext_ldst_stride(vd, v0, base, stride, env, desc, false, LOAD_FN, \
> - ctzl(sizeof(ETYPE)), GETPC(), MMU_DATA_LOAD); \
> + ctzl(sizeof(ETYPE)), GETPC()); \
> } \
> \
> void HELPER(NAME)(void *vd, void *v0, target_ulong base, \
> CPURISCVState *env, uint32_t desc) \
> { \
> vext_ldst_us(vd, base, env, desc, LOAD_FN, \
> - ctzl(sizeof(ETYPE)), env->vl, GETPC(), MMU_DATA_LOAD); \
> + ctzl(sizeof(ETYPE)), env->vl, GETPC()); \
> }
>
> GEN_VEXT_LD_US(vle8_v, int8_t, lde_b)
> @@ -340,14 +340,14 @@ void HELPER(NAME##_mask)(void *vd, void *v0, target_ulong base, \
> { \
> uint32_t stride = vext_nf(desc) << ctzl(sizeof(ETYPE)); \
> vext_ldst_stride(vd, v0, base, stride, env, desc, false, STORE_FN, \
> - ctzl(sizeof(ETYPE)), GETPC(), MMU_DATA_STORE); \
> + ctzl(sizeof(ETYPE)), GETPC()); \
> } \
> \
> void HELPER(NAME)(void *vd, void *v0, target_ulong base, \
> CPURISCVState *env, uint32_t desc) \
> { \
> vext_ldst_us(vd, base, env, desc, STORE_FN, \
> - ctzl(sizeof(ETYPE)), env->vl, GETPC(), MMU_DATA_STORE); \
> + ctzl(sizeof(ETYPE)), env->vl, GETPC()); \
> }
>
> GEN_VEXT_ST_US(vse8_v, int8_t, ste_b)
> @@ -364,7 +364,7 @@ void HELPER(vlm_v)(void *vd, void *v0, target_ulong base,
> /* evl = ceil(vl/8) */
> uint8_t evl = (env->vl + 7) >> 3;
> vext_ldst_us(vd, base, env, desc, lde_b,
> - 0, evl, GETPC(), MMU_DATA_LOAD);
> + 0, evl, GETPC());
> }
>
> void HELPER(vsm_v)(void *vd, void *v0, target_ulong base,
> @@ -373,7 +373,7 @@ void HELPER(vsm_v)(void *vd, void *v0, target_ulong base,
> /* evl = ceil(vl/8) */
> uint8_t evl = (env->vl + 7) >> 3;
> vext_ldst_us(vd, base, env, desc, ste_b,
> - 0, evl, GETPC(), MMU_DATA_STORE);
> + 0, evl, GETPC());
> }
>
> /*
> @@ -399,7 +399,7 @@ vext_ldst_index(void *vd, void *v0, target_ulong base,
> void *vs2, CPURISCVState *env, uint32_t desc,
> vext_get_index_addr get_index_addr,
> vext_ldst_elem_fn *ldst_elem,
> - uint32_t esz, uintptr_t ra, MMUAccessType access_type)
> + uint32_t esz, uintptr_t ra)
> {
> uint32_t i, k;
> uint32_t nf = vext_nf(desc);
> @@ -427,7 +427,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong base, \
> void *vs2, CPURISCVState *env, uint32_t desc) \
> { \
> vext_ldst_index(vd, v0, base, vs2, env, desc, INDEX_FN, \
> - LOAD_FN, ctzl(sizeof(ETYPE)), GETPC(), MMU_DATA_LOAD); \
> + LOAD_FN, ctzl(sizeof(ETYPE)), GETPC()); \
> }
>
> GEN_VEXT_LD_INDEX(vlxei8_8_v, int8_t, idx_b, lde_b)
> @@ -453,7 +453,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong base, \
> { \
> vext_ldst_index(vd, v0, base, vs2, env, desc, INDEX_FN, \
> STORE_FN, ctzl(sizeof(ETYPE)), \
> - GETPC(), MMU_DATA_STORE); \
> + GETPC()); \
> }
>
> GEN_VEXT_ST_INDEX(vsxei8_8_v, int8_t, idx_b, ste_b)
> @@ -576,8 +576,7 @@ GEN_VEXT_LDFF(vle64ff_v, int64_t, lde_d)
> */
> static void
> vext_ldst_whole(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
> - vext_ldst_elem_fn *ldst_elem, uint32_t esz, uintptr_t ra,
> - MMUAccessType access_type)
> + vext_ldst_elem_fn *ldst_elem, uint32_t esz, uintptr_t ra)
> {
> uint32_t i, k, off, pos;
> uint32_t nf = vext_nf(desc);
> @@ -612,8 +611,7 @@ void HELPER(NAME)(void *vd, target_ulong base, \
> CPURISCVState *env, uint32_t desc) \
> { \
> vext_ldst_whole(vd, base, env, desc, LOAD_FN, \
> - ctzl(sizeof(ETYPE)), GETPC(), \
> - MMU_DATA_LOAD); \
> + ctzl(sizeof(ETYPE)), GETPC()); \
> }
>
> GEN_VEXT_LD_WHOLE(vl1re8_v, int8_t, lde_b)
> @@ -638,8 +636,7 @@ void HELPER(NAME)(void *vd, target_ulong base, \
> CPURISCVState *env, uint32_t desc) \
> { \
> vext_ldst_whole(vd, base, env, desc, STORE_FN, \
> - ctzl(sizeof(ETYPE)), GETPC(), \
> - MMU_DATA_STORE); \
> + ctzl(sizeof(ETYPE)), GETPC()); \
> }
>
> GEN_VEXT_ST_WHOLE(vs1r_v, int8_t, ste_b)
> --
> 2.34.2
>
>
^ permalink raw reply [flat|nested] 35+ messages in thread
* Re: [PATCH qemu v18 00/16] Add tail agnostic behavior for rvv instructions
2022-05-13 11:49 [PATCH qemu v18 00/16] Add tail agnostic behavior for rvv instructions ~eopxd
` (15 preceding siblings ...)
2022-05-12 7:47 ` [PATCH qemu v18 02/16] target/riscv: rvv: Prune redundant access_type parameter passed ~eopxd
@ 2022-06-06 1:37 ` Alistair Francis
2022-06-06 6:17 ` eop Chen
16 siblings, 1 reply; 35+ messages in thread
From: Alistair Francis @ 2022-06-06 1:37 UTC (permalink / raw)
To: ~eopxd
Cc: qemu-devel@nongnu.org Developers, open list:RISC-V,
Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li, eop Chen
On Fri, May 13, 2022 at 9:55 PM ~eopxd <eopxd@git.sr.ht> wrote:
>
> According to v-spec, tail agnostic behavior can be either kept as
> undisturbed or set elements' bits to all 1s. To distinguish the
> difference of tail policies, QEMU should be able to simulate the tail
> agnostic behavior as "set tail elements' bits to all 1s". An option
> 'rvv_ta_all_1s' is added to enable the behavior, it is default as
> disabled.
>
> There are multiple possibility for agnostic elements according to
> v-spec. The main intent of this patch-set tries to add option that
> can distinguish between tail policies. Setting agnostic elements to
> all 1s makes things simple and allow QEMU to express this.
>
> We may explore other possibility of agnostic behavior by adding
> other options in the future. Please understand that this patch-set
> is limited.
>
> v2 updates:
> - Addressed comments from Weiwei Li
> - Added commit tail agnostic on load / store instructions (which
> I forgot to include into the patch-set)
>
> v3 updates:
> - Missed the very 1st commit, adding it back
>
> v4 updates:
> - Renamed vlmax to total_elems
> - Deal with tail element when vl_eq_vlmax == true
>
> v5 updates:
> - Let `vext_get_total_elems` take `desc` and `esz`
> - Utilize `simd_maxsz(desc)` to get `vlenb`
> - Fix alignments to code
>
> v6 updates:
> - Fix `vext_get_total_elems`
>
> v7 updates:
> - Reuse `max_elems` for vector load / store helper functions. The
> translation sets desc's `lmul` to `min(1, lmul)`, making
> `vext_max_elems` equivalent to `vext_get_total_elems`.
>
> v8 updates:
> - Simplify `vext_set_elems_1s`, don't need `vext_set_elems_1s_fns`
> - Fix `vext_get_total_elems`, it should derive upon EMUL instead
> of LMUL
>
> v9 updates:
> - Let instructions that is tail agnostic regardless of vta respect the
> option and not the vta.
>
> v10 updates:
> - Correct range to set element to 1s for load instructions
>
> v11 updates:
> - Separate addition of option 'rvv_ta_all_1s' as a new (last) commit
> - Add description to show intent of the option in first commit for the
> optional tail agnostic behavior
> - Tag WeiWei as Reviewed-by for all commits
> - Tag Alistair as Reviewed-by for commit 01, 02
> - Tag Alistair as Acked-by for commit 03
>
> v12 updates:
> - Add missing space in WeiWei's "Reviewed-by" tag
>
> v13 updates:
> - Fix tail agnostic for vext_ldst_us. The function operates on input
> parameter 'evl' rather than 'env->vl'.
> - Fix tail elements for vector segment load / store instructions
> A vector segment load / store instruction may contain fractional
> lmul with nf * lmul > 1. The rest of the elements in the last
> register should be treated as tail elements.
> - Fix tail agnostic length for instructions with mask destination
> register. Instructions with mask destination register should have
> 'vlen - vl' tail elements.
>
> v14 updates:
> - Pass lmul information to into vector helper function.
> `vext_get_total_elems` needs it.
>
> v15 updates:
> - Rebase to latest `master`
> - Tag Alistair as Acked by for commit 04 ~ 14
> - Tag Alistair as Acked by for commit 15
>
> v16 updates:
> - Fix bug, when encountering situation when lmul < 0 and vl_eq_vlmax,
> the original version will override on `vd` but the computation will
> override again, meaning the tail elements will not be set correctly.
> Now, we don't use TCG functions if we are trying to simulate all 1s
> for agnostic and use vector helpers instead.
>
> v17 updates:
> - Add "Prune access_type parameter" commit to cleanup vector load/
> store functions. Then add parameter `is_load` in vector helper
> functions to enable vta behavior in the commit for adding vta on
> vector load/store functions.
>
> v18 updates:
> - Don't use `is_load` parameter in vector helper. Don't let vta pass
> through in `trans_rvv.inc`
>
> eopXD (16):
> target/riscv: rvv: Prune redundant ESZ, DSZ parameter passed
> target/riscv: rvv: Prune redundant access_type parameter passed
> target/riscv: rvv: Rename ambiguous esz
> target/riscv: rvv: Early exit when vstart >= vl
> target/riscv: rvv: Add tail agnostic for vv instructions
> target/riscv: rvv: Add tail agnostic for vector load / store
> instructions
> target/riscv: rvv: Add tail agnostic for vx, vvm, vxm instructions
> target/riscv: rvv: Add tail agnostic for vector integer shift
> instructions
> target/riscv: rvv: Add tail agnostic for vector integer comparison
> instructions
> target/riscv: rvv: Add tail agnostic for vector integer merge and move
> instructions
> target/riscv: rvv: Add tail agnostic for vector fix-point arithmetic
> instructions
> target/riscv: rvv: Add tail agnostic for vector floating-point
> instructions
> target/riscv: rvv: Add tail agnostic for vector reduction instructions
> target/riscv: rvv: Add tail agnostic for vector mask instructions
> target/riscv: rvv: Add tail agnostic for vector permutation
> instructions
> target/riscv: rvv: Add option 'rvv_ta_all_1s' to enable optional tail
> agnostic behavior
Do you mind rebasing this on:
https://github.com/alistair23/qemu/tree/riscv-to-apply.next
Alistair
>
> target/riscv/cpu.c | 1 +
> target/riscv/cpu.h | 2 +
> target/riscv/cpu_helper.c | 2 +
> target/riscv/insn_trans/trans_rvv.c.inc | 94 +-
> target/riscv/internals.h | 6 +-
> target/riscv/translate.c | 4 +
> target/riscv/vector_helper.c | 1587 ++++++++++++++---------
> 7 files changed, 1053 insertions(+), 643 deletions(-)
>
> --
> 2.34.2
>
^ permalink raw reply [flat|nested] 35+ messages in thread
* Re: [PATCH qemu v18 00/16] Add tail agnostic behavior for rvv instructions
2022-06-06 1:37 ` [PATCH qemu v18 00/16] Add tail agnostic behavior for rvv instructions Alistair Francis
@ 2022-06-06 6:17 ` eop Chen
0 siblings, 0 replies; 35+ messages in thread
From: eop Chen @ 2022-06-06 6:17 UTC (permalink / raw)
To: Alistair Francis
Cc: qemu-devel@nongnu.org Developers, open list:RISC-V,
Palmer Dabbelt, Alistair Francis, Bin Meng, Frank Chang,
WeiWei Li
Rebased to riscv-to-apply.next and submitted v19.
Thank you WeiWei, Frank and Alistair for the reviews along the way.
Regards,
eop Chen
> Alistair Francis <alistair23@gmail.com> 於 2022年6月6日 上午9:37 寫道：
>
> On Fri, May 13, 2022 at 9:55 PM ~eopxd <eopxd@git.sr.ht> wrote:
>>
>> According to v-spec, tail agnostic behavior can be either kept as
>> undisturbed or set elements' bits to all 1s. To distinguish the
>> difference of tail policies, QEMU should be able to simulate the tail
>> agnostic behavior as "set tail elements' bits to all 1s". An option
>> 'rvv_ta_all_1s' is added to enable the behavior, it is default as
>> disabled.
>>
>> There are multiple possibility for agnostic elements according to
>> v-spec. The main intent of this patch-set tries to add option that
>> can distinguish between tail policies. Setting agnostic elements to
>> all 1s makes things simple and allow QEMU to express this.
>>
>> We may explore other possibility of agnostic behavior by adding
>> other options in the future. Please understand that this patch-set
>> is limited.
>>
>> v2 updates:
>> - Addressed comments from Weiwei Li
>> - Added commit tail agnostic on load / store instructions (which
>> I forgot to include into the patch-set)
>>
>> v3 updates:
>> - Missed the very 1st commit, adding it back
>>
>> v4 updates:
>> - Renamed vlmax to total_elems
>> - Deal with tail element when vl_eq_vlmax == true
>>
>> v5 updates:
>> - Let `vext_get_total_elems` take `desc` and `esz`
>> - Utilize `simd_maxsz(desc)` to get `vlenb`
>> - Fix alignments to code
>>
>> v6 updates:
>> - Fix `vext_get_total_elems`
>>
>> v7 updates:
>> - Reuse `max_elems` for vector load / store helper functions. The
>> translation sets desc's `lmul` to `min(1, lmul)`, making
>> `vext_max_elems` equivalent to `vext_get_total_elems`.
>>
>> v8 updates:
>> - Simplify `vext_set_elems_1s`, don't need `vext_set_elems_1s_fns`
>> - Fix `vext_get_total_elems`, it should derive upon EMUL instead
>> of LMUL
>>
>> v9 updates:
>> - Let instructions that is tail agnostic regardless of vta respect the
>> option and not the vta.
>>
>> v10 updates:
>> - Correct range to set element to 1s for load instructions
>>
>> v11 updates:
>> - Separate addition of option 'rvv_ta_all_1s' as a new (last) commit
>> - Add description to show intent of the option in first commit for the
>> optional tail agnostic behavior
>> - Tag WeiWei as Reviewed-by for all commits
>> - Tag Alistair as Reviewed-by for commit 01, 02
>> - Tag Alistair as Acked-by for commit 03
>>
>> v12 updates:
>> - Add missing space in WeiWei's "Reviewed-by" tag
>>
>> v13 updates:
>> - Fix tail agnostic for vext_ldst_us. The function operates on input
>> parameter 'evl' rather than 'env->vl'.
>> - Fix tail elements for vector segment load / store instructions
>> A vector segment load / store instruction may contain fractional
>> lmul with nf * lmul > 1. The rest of the elements in the last
>> register should be treated as tail elements.
>> - Fix tail agnostic length for instructions with mask destination
>> register. Instructions with mask destination register should have
>> 'vlen - vl' tail elements.
>>
>> v14 updates:
>> - Pass lmul information to into vector helper function.
>> `vext_get_total_elems` needs it.
>>
>> v15 updates:
>> - Rebase to latest `master`
>> - Tag Alistair as Acked by for commit 04 ~ 14
>> - Tag Alistair as Acked by for commit 15
>>
>> v16 updates:
>> - Fix bug, when encountering situation when lmul < 0 and vl_eq_vlmax,
>> the original version will override on `vd` but the computation will
>> override again, meaning the tail elements will not be set correctly.
>> Now, we don't use TCG functions if we are trying to simulate all 1s
>> for agnostic and use vector helpers instead.
>>
>> v17 updates:
>> - Add "Prune access_type parameter" commit to cleanup vector load/
>> store functions. Then add parameter `is_load` in vector helper
>> functions to enable vta behavior in the commit for adding vta on
>> vector load/store functions.
>>
>> v18 updates:
>> - Don't use `is_load` parameter in vector helper. Don't let vta pass
>> through in `trans_rvv.inc`
>>
>> eopXD (16):
>> target/riscv: rvv: Prune redundant ESZ, DSZ parameter passed
>> target/riscv: rvv: Prune redundant access_type parameter passed
>> target/riscv: rvv: Rename ambiguous esz
>> target/riscv: rvv: Early exit when vstart >= vl
>> target/riscv: rvv: Add tail agnostic for vv instructions
>> target/riscv: rvv: Add tail agnostic for vector load / store
>> instructions
>> target/riscv: rvv: Add tail agnostic for vx, vvm, vxm instructions
>> target/riscv: rvv: Add tail agnostic for vector integer shift
>> instructions
>> target/riscv: rvv: Add tail agnostic for vector integer comparison
>> instructions
>> target/riscv: rvv: Add tail agnostic for vector integer merge and move
>> instructions
>> target/riscv: rvv: Add tail agnostic for vector fix-point arithmetic
>> instructions
>> target/riscv: rvv: Add tail agnostic for vector floating-point
>> instructions
>> target/riscv: rvv: Add tail agnostic for vector reduction instructions
>> target/riscv: rvv: Add tail agnostic for vector mask instructions
>> target/riscv: rvv: Add tail agnostic for vector permutation
>> instructions
>> target/riscv: rvv: Add option 'rvv_ta_all_1s' to enable optional tail
>> agnostic behavior
>
> Do you mind rebasing this on:
> https://github.com/alistair23/qemu/tree/riscv-to-apply.next
>
> Alistair
>
>>
>> target/riscv/cpu.c | 1 +
>> target/riscv/cpu.h | 2 +
>> target/riscv/cpu_helper.c | 2 +
>> target/riscv/insn_trans/trans_rvv.c.inc | 94 +-
>> target/riscv/internals.h | 6 +-
>> target/riscv/translate.c | 4 +
>> target/riscv/vector_helper.c | 1587 ++++++++++++++---------
>> 7 files changed, 1053 insertions(+), 643 deletions(-)
>>
>> --
>> 2.34.2
>>
^ permalink raw reply [flat|nested] 35+ messages in thread
end of thread, other threads:[~2022-06-06 7:02 UTC | newest]
Thread overview: 35+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-05-13 11:49 [PATCH qemu v18 00/16] Add tail agnostic behavior for rvv instructions ~eopxd
2022-03-01 9:07 ` [PATCH qemu v18 05/16] target/riscv: rvv: Add tail agnostic for vv instructions ~eopxd
2022-05-13 11:50 ` ~eopxd
2022-03-07 7:10 ` [PATCH qemu v18 06/16] target/riscv: rvv: Add tail agnostic for vector load / store instructions ~eopxd
2022-05-13 11:50 ` ~eopxd
2022-03-07 7:32 ` [PATCH qemu v18 07/16] target/riscv: rvv: Add tail agnostic for vx, vvm, vxm instructions ~eopxd
2022-05-13 11:50 ` ~eopxd
2022-03-07 9:38 ` [PATCH qemu v18 08/16] target/riscv: rvv: Add tail agnostic for vector integer shift instructions ~eopxd
2022-05-13 11:50 ` ~eopxd
2022-03-07 9:43 ` [PATCH qemu v18 09/16] target/riscv: rvv: Add tail agnostic for vector integer comparison instructions ~eopxd
2022-05-13 11:50 ` ~eopxd
2022-03-07 9:53 ` [PATCH qemu v18 10/16] target/riscv: rvv: Add tail agnostic for vector integer merge and move instructions ~eopxd
2022-05-13 11:50 ` ~eopxd
2022-03-07 10:04 ` [PATCH qemu v18 11/16] target/riscv: rvv: Add tail agnostic for vector fix-point arithmetic instructions ~eopxd
2022-05-13 11:50 ` ~eopxd
2022-03-07 10:05 ` [PATCH qemu v18 12/16] target/riscv: rvv: Add tail agnostic for vector floating-point instructions ~eopxd
2022-05-13 11:50 ` ~eopxd
2022-03-07 12:21 ` [PATCH qemu v18 13/16] target/riscv: rvv: Add tail agnostic for vector reduction instructions ~eopxd
2022-05-13 11:50 ` ~eopxd
2022-03-07 15:26 ` [PATCH qemu v18 14/16] target/riscv: rvv: Add tail agnostic for vector mask instructions ~eopxd
2022-05-13 11:50 ` ~eopxd
2022-03-07 15:59 ` [PATCH qemu v18 15/16] target/riscv: rvv: Add tail agnostic for vector permutation instructions ~eopxd
2022-05-13 11:50 ` ~eopxd
2022-03-09 8:34 ` [PATCH qemu v18 03/16] target/riscv: rvv: Rename ambiguous esz ~eopxd
2022-05-13 11:50 ` ~eopxd
2022-03-12 6:28 ` [PATCH qemu v18 04/16] target/riscv: rvv: Early exit when vstart >= vl ~eopxd
2022-05-13 11:50 ` ~eopxd
2022-03-14 7:38 ` [PATCH qemu v18 01/16] target/riscv: rvv: Prune redundant ESZ, DSZ parameter passed ~eopxd
2022-05-13 11:50 ` ~eopxd
2022-04-28 3:26 ` [PATCH qemu v18 16/16] target/riscv: rvv: Add option 'rvv_ta_all_1s' to enable optional tail agnostic behavior ~eopxd
2022-05-13 11:50 ` ~eopxd
2022-05-12 7:47 ` [PATCH qemu v18 02/16] target/riscv: rvv: Prune redundant access_type parameter passed ~eopxd
2022-05-23 21:39 ` Alistair Francis
2022-06-06 1:37 ` [PATCH qemu v18 00/16] Add tail agnostic behavior for rvv instructions Alistair Francis
2022-06-06 6:17 ` eop Chen
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.