From: ~eopxd <eopxd@git.sr.ht>
To: qemu-devel@nongnu.org, qemu-riscv@nongnu.org
Cc: WeiWei Li <liweiwei@iscas.ac.cn>,
Frank Chang <frank.chang@sifive.com>,
eop Chen <eop.chen@sifive.com>, Bin Meng <bin.meng@windriver.com>,
Alistair Francis <alistair.francis@wdc.com>,
Palmer Dabbelt <palmer@dabbelt.com>
Subject: [PATCH qemu v8 10/14] target/riscv: rvv: Add tail agnostic for vector fix-point arithmetic instructions
Date: Mon, 07 Mar 2022 02:04:21 -0800 [thread overview]
Message-ID: <165099671854.27992.10018115463292837504-10@git.sr.ht> (raw)
In-Reply-To: <165099671854.27992.10018115463292837504-0@git.sr.ht>
From: eopXD <eop.chen@sifive.com>
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.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 bd0aeda03f..057d67211b 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -2094,10 +2094,12 @@ 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(desc, esz);
+ uint32_t vta = vext_vta(desc);
switch (env->vxrm) {
case 0: /* rnu */
@@ -2117,15 +2119,17 @@ 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_fns[ctzl(esz)](vd, vta, vl, 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)
@@ -2175,10 +2179,10 @@ 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);
@@ -2211,10 +2215,12 @@ 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(desc, esz);
+ uint32_t vta = vext_vta(desc);
switch (env->vxrm) {
case 0: /* rnu */
@@ -2234,25 +2240,27 @@ 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_fns[ctzl(esz)](vd, vta, vl, 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)
{
@@ -2298,19 +2306,19 @@ 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)
{
@@ -2359,19 +2367,19 @@ 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)
{
@@ -2417,19 +2425,19 @@ 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)
@@ -2481,19 +2489,19 @@ 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)
@@ -2518,19 +2526,19 @@ 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)
{
@@ -2554,19 +2562,19 @@ 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)
@@ -2591,19 +2599,19 @@ 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)
@@ -2698,19 +2706,19 @@ 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
@@ -2757,19 +2765,19 @@ 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)
@@ -2816,19 +2824,19 @@ 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
@@ -2891,16 +2899,16 @@ 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)
@@ -2953,16 +2961,16 @@ 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
WARNING: multiple messages have this Message-ID (diff)
From: ~eopxd <eopxd@git.sr.ht>
To: qemu-devel@nongnu.org, qemu-riscv@nongnu.org
Cc: Palmer Dabbelt <palmer@dabbelt.com>,
Alistair Francis <alistair.francis@wdc.com>,
Bin Meng <bin.meng@windriver.com>,
Frank Chang <frank.chang@sifive.com>,
WeiWei Li <liweiwei@iscas.ac.cn>, eop Chen <eop.chen@sifive.com>
Subject: [PATCH qemu v8 10/14] target/riscv: rvv: Add tail agnostic for vector fix-point arithmetic instructions
Date: Tue, 26 Apr 2022 18:12:28 -0000 [thread overview]
Message-ID: <165099671854.27992.10018115463292837504-10@git.sr.ht> (raw)
In-Reply-To: <165099671854.27992.10018115463292837504-0@git.sr.ht>
From: eopXD <eop.chen@sifive.com>
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.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 bd0aeda03f..057d67211b 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -2094,10 +2094,12 @@ 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(desc, esz);
+ uint32_t vta = vext_vta(desc);
switch (env->vxrm) {
case 0: /* rnu */
@@ -2117,15 +2119,17 @@ 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_fns[ctzl(esz)](vd, vta, vl, 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)
@@ -2175,10 +2179,10 @@ 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);
@@ -2211,10 +2215,12 @@ 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(desc, esz);
+ uint32_t vta = vext_vta(desc);
switch (env->vxrm) {
case 0: /* rnu */
@@ -2234,25 +2240,27 @@ 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_fns[ctzl(esz)](vd, vta, vl, 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)
{
@@ -2298,19 +2306,19 @@ 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)
{
@@ -2359,19 +2367,19 @@ 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)
{
@@ -2417,19 +2425,19 @@ 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)
@@ -2481,19 +2489,19 @@ 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)
@@ -2518,19 +2526,19 @@ 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)
{
@@ -2554,19 +2562,19 @@ 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)
@@ -2591,19 +2599,19 @@ 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)
@@ -2698,19 +2706,19 @@ 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
@@ -2757,19 +2765,19 @@ 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)
@@ -2816,19 +2824,19 @@ 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
@@ -2891,16 +2899,16 @@ 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)
@@ -2953,16 +2961,16 @@ 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
next prev parent reply other threads:[~2022-04-26 18:14 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-04-26 18:11 [PATCH qemu v8 00/14] Add tail agnostic behavior for rvv instructions ~eopxd
2022-04-26 18:11 ` ~eopxd
2022-03-01 9:07 ` [PATCH qemu v8 04/14] target/riscv: rvv: Add tail agnostic for vv instructions ~eopxd
2022-04-26 18:12 ` ~eopxd
2022-03-07 7:10 ` [PATCH qemu v8 05/14] target/riscv: rvv: Add tail agnostic for vector load / store instructions ~eopxd
2022-04-26 18:12 ` ~eopxd
2022-03-07 7:32 ` [PATCH qemu v8 06/14] target/riscv: rvv: Add tail agnostic for vx, vvm, vxm instructions ~eopxd
2022-04-26 18:12 ` ~eopxd
2022-03-07 9:38 ` [PATCH qemu v8 07/14] target/riscv: rvv: Add tail agnostic for vector integer shift instructions ~eopxd
2022-04-26 18:12 ` ~eopxd
2022-03-07 9:43 ` [PATCH qemu v8 08/14] target/riscv: rvv: Add tail agnostic for vector integer comparison instructions ~eopxd
2022-04-26 18:12 ` ~eopxd
2022-03-07 9:53 ` [PATCH qemu v8 09/14] target/riscv: rvv: Add tail agnostic for vector integer merge and move instructions ~eopxd
2022-04-26 18:12 ` ~eopxd
2022-03-07 10:04 ` ~eopxd [this message]
2022-04-26 18:12 ` [PATCH qemu v8 10/14] target/riscv: rvv: Add tail agnostic for vector fix-point arithmetic instructions ~eopxd
2022-03-07 10:05 ` [PATCH qemu v8 11/14] target/riscv: rvv: Add tail agnostic for vector floating-point instructions ~eopxd
2022-04-26 18:12 ` ~eopxd
2022-03-07 12:21 ` [PATCH qemu v8 12/14] target/riscv: rvv: Add tail agnostic for vector reduction instructions ~eopxd
2022-04-26 18:12 ` ~eopxd
2022-03-07 15:26 ` [PATCH qemu v8 13/14] target/riscv: rvv: Add tail agnostic for vector mask instructions ~eopxd
2022-04-26 18:12 ` ~eopxd
2022-03-07 15:59 ` [PATCH qemu v8 14/14] target/riscv: rvv: Add tail agnostic for vector permutation instructions ~eopxd
2022-04-26 18:12 ` ~eopxd
2022-03-09 8:34 ` [PATCH qemu v8 02/14] target/riscv: rvv: Rename ambiguous esz ~eopxd
2022-04-26 18:12 ` ~eopxd
2022-03-12 6:28 ` [PATCH qemu v8 03/14] target/riscv: rvv: Early exit when vstart >= vl ~eopxd
2022-04-26 18:12 ` ~eopxd
2022-03-14 7:38 ` [PATCH qemu v8 01/14] target/riscv: rvv: Prune redundant ESZ, DSZ parameter passed ~eopxd
2022-04-26 18:12 ` ~eopxd
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=165099671854.27992.10018115463292837504-10@git.sr.ht \
--to=eopxd@git.sr.ht \
--cc=alistair.francis@wdc.com \
--cc=bin.meng@windriver.com \
--cc=eop.chen@sifive.com \
--cc=frank.chang@sifive.com \
--cc=liweiwei@iscas.ac.cn \
--cc=palmer@dabbelt.com \
--cc=qemu-devel@nongnu.org \
--cc=qemu-riscv@nongnu.org \
--cc=yueh.ting.chen@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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.