From: LIU Zhiwei <zhiwei_liu@c-sky.com>
To: qemu-devel@nongnu.org, qemu-riscv@nongnu.org
Cc: richard.henderson@linaro.org, wxy194768@alibaba-inc.com,
wenmeng_zhang@c-sky.com, alistair.francis@wdc.com,
palmer@dabbelt.com, LIU Zhiwei <zhiwei_liu@c-sky.com>
Subject: [PATCH v8 11/62] target/riscv: vector widening integer add and subtract
Date: Thu, 21 May 2020 17:43:22 +0800 [thread overview]
Message-ID: <20200521094413.10425-12-zhiwei_liu@c-sky.com> (raw)
In-Reply-To: <20200521094413.10425-1-zhiwei_liu@c-sky.com>
Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/helper.h | 49 +++++++
target/riscv/insn32.decode | 16 ++
target/riscv/insn_trans/trans_rvv.inc.c | 186 ++++++++++++++++++++++++
target/riscv/vector_helper.c | 111 ++++++++++++++
4 files changed, 362 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index f791f2dbc6..608704850a 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -294,3 +294,52 @@ DEF_HELPER_FLAGS_4(vec_rsubs8, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
DEF_HELPER_FLAGS_4(vec_rsubs16, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
DEF_HELPER_FLAGS_4(vec_rsubs32, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
DEF_HELPER_FLAGS_4(vec_rsubs64, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+
+DEF_HELPER_6(vwaddu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwaddu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwaddu_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsubu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsubu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsubu_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwadd_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsub_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwaddu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwaddu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwaddu_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsubu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsubu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsubu_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwadd_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwadd_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwadd_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsub_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsub_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsub_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwaddu_wv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwaddu_wv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwaddu_wv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsubu_wv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsubu_wv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsubu_wv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwadd_wv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwadd_wv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwadd_wv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsub_wv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsub_wv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsub_wv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwaddu_wx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwaddu_wx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwaddu_wx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsubu_wx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsubu_wx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsubu_wx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwadd_wx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwadd_wx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwadd_wx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsub_wx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsub_wx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsub_wx_w, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index d1034a0e61..4bdbfd16fa 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -284,6 +284,22 @@ vsub_vv 000010 . ..... ..... 000 ..... 1010111 @r_vm
vsub_vx 000010 . ..... ..... 100 ..... 1010111 @r_vm
vrsub_vx 000011 . ..... ..... 100 ..... 1010111 @r_vm
vrsub_vi 000011 . ..... ..... 011 ..... 1010111 @r_vm
+vwaddu_vv 110000 . ..... ..... 010 ..... 1010111 @r_vm
+vwaddu_vx 110000 . ..... ..... 110 ..... 1010111 @r_vm
+vwadd_vv 110001 . ..... ..... 010 ..... 1010111 @r_vm
+vwadd_vx 110001 . ..... ..... 110 ..... 1010111 @r_vm
+vwsubu_vv 110010 . ..... ..... 010 ..... 1010111 @r_vm
+vwsubu_vx 110010 . ..... ..... 110 ..... 1010111 @r_vm
+vwsub_vv 110011 . ..... ..... 010 ..... 1010111 @r_vm
+vwsub_vx 110011 . ..... ..... 110 ..... 1010111 @r_vm
+vwaddu_wv 110100 . ..... ..... 010 ..... 1010111 @r_vm
+vwaddu_wx 110100 . ..... ..... 110 ..... 1010111 @r_vm
+vwadd_wv 110101 . ..... ..... 010 ..... 1010111 @r_vm
+vwadd_wx 110101 . ..... ..... 110 ..... 1010111 @r_vm
+vwsubu_wv 110110 . ..... ..... 010 ..... 1010111 @r_vm
+vwsubu_wx 110110 . ..... ..... 110 ..... 1010111 @r_vm
+vwsub_wv 110111 . ..... ..... 010 ..... 1010111 @r_vm
+vwsub_wx 110111 . ..... ..... 110 ..... 1010111 @r_vm
vsetvli 0 ........... ..... 111 ..... 1010111 @r2_zimm
vsetvl 1000000 ..... ..... 111 ..... 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c
index b70ccccd2e..3b26d72c64 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -138,6 +138,14 @@ static bool vext_check_nf(DisasContext *s, uint32_t nf)
return (1 << s->lmul) * nf <= 8;
}
+/*
+ * The destination vector register group cannot overlap a source vector register
+ * group of a different element width. (Section 11.2)
+ */
+static inline bool vext_check_overlap_group(int rd, int dlen, int rs, int slen)
+{
+ return ((rd >= rs + slen) || (rs >= rd + dlen));
+}
/* common translation macro */
#define GEN_VEXT_TRANS(NAME, SEQ, ARGTYPE, OP, CHECK) \
static bool trans_##NAME(DisasContext *s, arg_##ARGTYPE *a)\
@@ -1063,3 +1071,181 @@ static void tcg_gen_gvec_rsubi(unsigned vece, uint32_t dofs, uint32_t aofs,
}
GEN_OPIVI_GVEC_TRANS(vrsub_vi, 0, vrsub_vx, rsubi)
+
+/* Vector Widening Integer Add/Subtract */
+
+/* OPIVV with WIDEN */
+static bool opivv_widen_check(DisasContext *s, arg_rmrr *a)
+{
+ return (vext_check_isa_ill(s) &&
+ vext_check_overlap_mask(s, a->rd, a->vm, true) &&
+ vext_check_reg(s, a->rd, true) &&
+ vext_check_reg(s, a->rs2, false) &&
+ vext_check_reg(s, a->rs1, false) &&
+ vext_check_overlap_group(a->rd, 2 << s->lmul, a->rs2,
+ 1 << s->lmul) &&
+ vext_check_overlap_group(a->rd, 2 << s->lmul, a->rs1,
+ 1 << s->lmul) &&
+ (s->lmul < 0x3) && (s->sew < 0x3));
+}
+
+static bool do_opivv_widen(DisasContext *s, arg_rmrr *a,
+ gen_helper_gvec_4_ptr *fn,
+ bool (*checkfn)(DisasContext *, arg_rmrr *))
+{
+ if (checkfn(s, a)) {
+ uint32_t data = 0;
+ TCGLabel *over = gen_new_label();
+ tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+
+ data = FIELD_DP32(data, VDATA, MLEN, s->mlen);
+ data = FIELD_DP32(data, VDATA, VM, a->vm);
+ data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+ 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, 0, s->vlen / 8,
+ data, fn);
+ gen_set_label(over);
+ return true;
+ }
+ return false;
+}
+
+#define GEN_OPIVV_WIDEN_TRANS(NAME, CHECK) \
+static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
+{ \
+ static gen_helper_gvec_4_ptr * const fns[3] = { \
+ gen_helper_##NAME##_b, \
+ gen_helper_##NAME##_h, \
+ gen_helper_##NAME##_w \
+ }; \
+ return do_opivv_widen(s, a, fns[s->sew], CHECK); \
+}
+
+GEN_OPIVV_WIDEN_TRANS(vwaddu_vv, opivv_widen_check)
+GEN_OPIVV_WIDEN_TRANS(vwadd_vv, opivv_widen_check)
+GEN_OPIVV_WIDEN_TRANS(vwsubu_vv, opivv_widen_check)
+GEN_OPIVV_WIDEN_TRANS(vwsub_vv, opivv_widen_check)
+
+/* OPIVX with WIDEN */
+static bool opivx_widen_check(DisasContext *s, arg_rmrr *a)
+{
+ return (vext_check_isa_ill(s) &&
+ vext_check_overlap_mask(s, a->rd, a->vm, true) &&
+ vext_check_reg(s, a->rd, true) &&
+ vext_check_reg(s, a->rs2, false) &&
+ vext_check_overlap_group(a->rd, 2 << s->lmul, a->rs2,
+ 1 << s->lmul) &&
+ (s->lmul < 0x3) && (s->sew < 0x3));
+}
+
+static bool do_opivx_widen(DisasContext *s, arg_rmrr *a,
+ gen_helper_opivx *fn)
+{
+ if (opivx_widen_check(s, a)) {
+ return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s);
+ }
+ return true;
+}
+
+#define GEN_OPIVX_WIDEN_TRANS(NAME) \
+static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
+{ \
+ static gen_helper_opivx * const fns[3] = { \
+ gen_helper_##NAME##_b, \
+ gen_helper_##NAME##_h, \
+ gen_helper_##NAME##_w \
+ }; \
+ return do_opivx_widen(s, a, fns[s->sew]); \
+}
+
+GEN_OPIVX_WIDEN_TRANS(vwaddu_vx)
+GEN_OPIVX_WIDEN_TRANS(vwadd_vx)
+GEN_OPIVX_WIDEN_TRANS(vwsubu_vx)
+GEN_OPIVX_WIDEN_TRANS(vwsub_vx)
+
+/* WIDEN OPIVV with WIDEN */
+static bool opiwv_widen_check(DisasContext *s, arg_rmrr *a)
+{
+ return (vext_check_isa_ill(s) &&
+ vext_check_overlap_mask(s, a->rd, a->vm, true) &&
+ vext_check_reg(s, a->rd, true) &&
+ vext_check_reg(s, a->rs2, true) &&
+ vext_check_reg(s, a->rs1, false) &&
+ vext_check_overlap_group(a->rd, 2 << s->lmul, a->rs1,
+ 1 << s->lmul) &&
+ (s->lmul < 0x3) && (s->sew < 0x3));
+}
+
+static bool do_opiwv_widen(DisasContext *s, arg_rmrr *a,
+ gen_helper_gvec_4_ptr *fn)
+{
+ if (opiwv_widen_check(s, a)) {
+ uint32_t data = 0;
+ TCGLabel *over = gen_new_label();
+ tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+
+ data = FIELD_DP32(data, VDATA, MLEN, s->mlen);
+ data = FIELD_DP32(data, VDATA, VM, a->vm);
+ data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+ 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, 0, s->vlen / 8, data, fn);
+ gen_set_label(over);
+ return true;
+ }
+ return false;
+}
+
+#define GEN_OPIWV_WIDEN_TRANS(NAME) \
+static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
+{ \
+ static gen_helper_gvec_4_ptr * const fns[3] = { \
+ gen_helper_##NAME##_b, \
+ gen_helper_##NAME##_h, \
+ gen_helper_##NAME##_w \
+ }; \
+ return do_opiwv_widen(s, a, fns[s->sew]); \
+}
+
+GEN_OPIWV_WIDEN_TRANS(vwaddu_wv)
+GEN_OPIWV_WIDEN_TRANS(vwadd_wv)
+GEN_OPIWV_WIDEN_TRANS(vwsubu_wv)
+GEN_OPIWV_WIDEN_TRANS(vwsub_wv)
+
+/* WIDEN OPIVX with WIDEN */
+static bool opiwx_widen_check(DisasContext *s, arg_rmrr *a)
+{
+ return (vext_check_isa_ill(s) &&
+ vext_check_overlap_mask(s, a->rd, a->vm, true) &&
+ vext_check_reg(s, a->rd, true) &&
+ vext_check_reg(s, a->rs2, true) &&
+ (s->lmul < 0x3) && (s->sew < 0x3));
+}
+
+static bool do_opiwx_widen(DisasContext *s, arg_rmrr *a,
+ gen_helper_opivx *fn)
+{
+ if (opiwx_widen_check(s, a)) {
+ return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s);
+ }
+ return false;
+}
+
+#define GEN_OPIWX_WIDEN_TRANS(NAME) \
+static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
+{ \
+ static gen_helper_opivx * const fns[3] = { \
+ gen_helper_##NAME##_b, \
+ gen_helper_##NAME##_h, \
+ gen_helper_##NAME##_w \
+ }; \
+ return do_opiwx_widen(s, a, fns[s->sew]); \
+}
+
+GEN_OPIWX_WIDEN_TRANS(vwaddu_wx)
+GEN_OPIWX_WIDEN_TRANS(vwadd_wx)
+GEN_OPIWX_WIDEN_TRANS(vwsubu_wx)
+GEN_OPIWX_WIDEN_TRANS(vwsub_wx)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 6b321d3114..f2520332c8 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -1016,3 +1016,114 @@ void HELPER(vec_rsubs64)(void *d, void *a, uint64_t b, uint32_t desc)
*(uint64_t *)(d + i) = b - *(uint64_t *)(a + i);
}
}
+
+/* Vector Widening Integer Add/Subtract */
+#define WOP_UUU_B uint16_t, uint8_t, uint8_t, uint16_t, uint16_t
+#define WOP_UUU_H uint32_t, uint16_t, uint16_t, uint32_t, uint32_t
+#define WOP_UUU_W uint64_t, uint32_t, uint32_t, uint64_t, uint64_t
+#define WOP_SSS_B int16_t, int8_t, int8_t, int16_t, int16_t
+#define WOP_SSS_H int32_t, int16_t, int16_t, int32_t, int32_t
+#define WOP_SSS_W int64_t, int32_t, int32_t, int64_t, int64_t
+#define WOP_WUUU_B uint16_t, uint8_t, uint16_t, uint16_t, uint16_t
+#define WOP_WUUU_H uint32_t, uint16_t, uint32_t, uint32_t, uint32_t
+#define WOP_WUUU_W uint64_t, uint32_t, uint64_t, uint64_t, uint64_t
+#define WOP_WSSS_B int16_t, int8_t, int16_t, int16_t, int16_t
+#define WOP_WSSS_H int32_t, int16_t, int32_t, int32_t, int32_t
+#define WOP_WSSS_W int64_t, int32_t, int64_t, int64_t, int64_t
+RVVCALL(OPIVV2, vwaddu_vv_b, WOP_UUU_B, H2, H1, H1, DO_ADD)
+RVVCALL(OPIVV2, vwaddu_vv_h, WOP_UUU_H, H4, H2, H2, DO_ADD)
+RVVCALL(OPIVV2, vwaddu_vv_w, WOP_UUU_W, H8, H4, H4, DO_ADD)
+RVVCALL(OPIVV2, vwsubu_vv_b, WOP_UUU_B, H2, H1, H1, DO_SUB)
+RVVCALL(OPIVV2, vwsubu_vv_h, WOP_UUU_H, H4, H2, H2, DO_SUB)
+RVVCALL(OPIVV2, vwsubu_vv_w, WOP_UUU_W, H8, H4, H4, DO_SUB)
+RVVCALL(OPIVV2, vwadd_vv_b, WOP_SSS_B, H2, H1, H1, DO_ADD)
+RVVCALL(OPIVV2, vwadd_vv_h, WOP_SSS_H, H4, H2, H2, DO_ADD)
+RVVCALL(OPIVV2, vwadd_vv_w, WOP_SSS_W, H8, H4, H4, DO_ADD)
+RVVCALL(OPIVV2, vwsub_vv_b, WOP_SSS_B, H2, H1, H1, DO_SUB)
+RVVCALL(OPIVV2, vwsub_vv_h, WOP_SSS_H, H4, H2, H2, DO_SUB)
+RVVCALL(OPIVV2, vwsub_vv_w, WOP_SSS_W, H8, H4, H4, DO_SUB)
+RVVCALL(OPIVV2, vwaddu_wv_b, WOP_WUUU_B, H2, H1, H1, DO_ADD)
+RVVCALL(OPIVV2, vwaddu_wv_h, WOP_WUUU_H, H4, H2, H2, DO_ADD)
+RVVCALL(OPIVV2, vwaddu_wv_w, WOP_WUUU_W, H8, H4, H4, DO_ADD)
+RVVCALL(OPIVV2, vwsubu_wv_b, WOP_WUUU_B, H2, H1, H1, DO_SUB)
+RVVCALL(OPIVV2, vwsubu_wv_h, WOP_WUUU_H, H4, H2, H2, DO_SUB)
+RVVCALL(OPIVV2, vwsubu_wv_w, WOP_WUUU_W, H8, H4, H4, DO_SUB)
+RVVCALL(OPIVV2, vwadd_wv_b, WOP_WSSS_B, H2, H1, H1, DO_ADD)
+RVVCALL(OPIVV2, vwadd_wv_h, WOP_WSSS_H, H4, H2, H2, DO_ADD)
+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, clearh)
+GEN_VEXT_VV(vwaddu_vv_h, 2, 4, clearl)
+GEN_VEXT_VV(vwaddu_vv_w, 4, 8, clearq)
+GEN_VEXT_VV(vwsubu_vv_b, 1, 2, clearh)
+GEN_VEXT_VV(vwsubu_vv_h, 2, 4, clearl)
+GEN_VEXT_VV(vwsubu_vv_w, 4, 8, clearq)
+GEN_VEXT_VV(vwadd_vv_b, 1, 2, clearh)
+GEN_VEXT_VV(vwadd_vv_h, 2, 4, clearl)
+GEN_VEXT_VV(vwadd_vv_w, 4, 8, clearq)
+GEN_VEXT_VV(vwsub_vv_b, 1, 2, clearh)
+GEN_VEXT_VV(vwsub_vv_h, 2, 4, clearl)
+GEN_VEXT_VV(vwsub_vv_w, 4, 8, clearq)
+GEN_VEXT_VV(vwaddu_wv_b, 1, 2, clearh)
+GEN_VEXT_VV(vwaddu_wv_h, 2, 4, clearl)
+GEN_VEXT_VV(vwaddu_wv_w, 4, 8, clearq)
+GEN_VEXT_VV(vwsubu_wv_b, 1, 2, clearh)
+GEN_VEXT_VV(vwsubu_wv_h, 2, 4, clearl)
+GEN_VEXT_VV(vwsubu_wv_w, 4, 8, clearq)
+GEN_VEXT_VV(vwadd_wv_b, 1, 2, clearh)
+GEN_VEXT_VV(vwadd_wv_h, 2, 4, clearl)
+GEN_VEXT_VV(vwadd_wv_w, 4, 8, clearq)
+GEN_VEXT_VV(vwsub_wv_b, 1, 2, clearh)
+GEN_VEXT_VV(vwsub_wv_h, 2, 4, clearl)
+GEN_VEXT_VV(vwsub_wv_w, 4, 8, clearq)
+
+RVVCALL(OPIVX2, vwaddu_vx_b, WOP_UUU_B, H2, H1, DO_ADD)
+RVVCALL(OPIVX2, vwaddu_vx_h, WOP_UUU_H, H4, H2, DO_ADD)
+RVVCALL(OPIVX2, vwaddu_vx_w, WOP_UUU_W, H8, H4, DO_ADD)
+RVVCALL(OPIVX2, vwsubu_vx_b, WOP_UUU_B, H2, H1, DO_SUB)
+RVVCALL(OPIVX2, vwsubu_vx_h, WOP_UUU_H, H4, H2, DO_SUB)
+RVVCALL(OPIVX2, vwsubu_vx_w, WOP_UUU_W, H8, H4, DO_SUB)
+RVVCALL(OPIVX2, vwadd_vx_b, WOP_SSS_B, H2, H1, DO_ADD)
+RVVCALL(OPIVX2, vwadd_vx_h, WOP_SSS_H, H4, H2, DO_ADD)
+RVVCALL(OPIVX2, vwadd_vx_w, WOP_SSS_W, H8, H4, DO_ADD)
+RVVCALL(OPIVX2, vwsub_vx_b, WOP_SSS_B, H2, H1, DO_SUB)
+RVVCALL(OPIVX2, vwsub_vx_h, WOP_SSS_H, H4, H2, DO_SUB)
+RVVCALL(OPIVX2, vwsub_vx_w, WOP_SSS_W, H8, H4, DO_SUB)
+RVVCALL(OPIVX2, vwaddu_wx_b, WOP_WUUU_B, H2, H1, DO_ADD)
+RVVCALL(OPIVX2, vwaddu_wx_h, WOP_WUUU_H, H4, H2, DO_ADD)
+RVVCALL(OPIVX2, vwaddu_wx_w, WOP_WUUU_W, H8, H4, DO_ADD)
+RVVCALL(OPIVX2, vwsubu_wx_b, WOP_WUUU_B, H2, H1, DO_SUB)
+RVVCALL(OPIVX2, vwsubu_wx_h, WOP_WUUU_H, H4, H2, DO_SUB)
+RVVCALL(OPIVX2, vwsubu_wx_w, WOP_WUUU_W, H8, H4, DO_SUB)
+RVVCALL(OPIVX2, vwadd_wx_b, WOP_WSSS_B, H2, H1, DO_ADD)
+RVVCALL(OPIVX2, vwadd_wx_h, WOP_WSSS_H, H4, H2, DO_ADD)
+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, clearh)
+GEN_VEXT_VX(vwaddu_vx_h, 2, 4, clearl)
+GEN_VEXT_VX(vwaddu_vx_w, 4, 8, clearq)
+GEN_VEXT_VX(vwsubu_vx_b, 1, 2, clearh)
+GEN_VEXT_VX(vwsubu_vx_h, 2, 4, clearl)
+GEN_VEXT_VX(vwsubu_vx_w, 4, 8, clearq)
+GEN_VEXT_VX(vwadd_vx_b, 1, 2, clearh)
+GEN_VEXT_VX(vwadd_vx_h, 2, 4, clearl)
+GEN_VEXT_VX(vwadd_vx_w, 4, 8, clearq)
+GEN_VEXT_VX(vwsub_vx_b, 1, 2, clearh)
+GEN_VEXT_VX(vwsub_vx_h, 2, 4, clearl)
+GEN_VEXT_VX(vwsub_vx_w, 4, 8, clearq)
+GEN_VEXT_VX(vwaddu_wx_b, 1, 2, clearh)
+GEN_VEXT_VX(vwaddu_wx_h, 2, 4, clearl)
+GEN_VEXT_VX(vwaddu_wx_w, 4, 8, clearq)
+GEN_VEXT_VX(vwsubu_wx_b, 1, 2, clearh)
+GEN_VEXT_VX(vwsubu_wx_h, 2, 4, clearl)
+GEN_VEXT_VX(vwsubu_wx_w, 4, 8, clearq)
+GEN_VEXT_VX(vwadd_wx_b, 1, 2, clearh)
+GEN_VEXT_VX(vwadd_wx_h, 2, 4, clearl)
+GEN_VEXT_VX(vwadd_wx_w, 4, 8, clearq)
+GEN_VEXT_VX(vwsub_wx_b, 1, 2, clearh)
+GEN_VEXT_VX(vwsub_wx_h, 2, 4, clearl)
+GEN_VEXT_VX(vwsub_wx_w, 4, 8, clearq)
--
2.23.0
next prev parent reply other threads:[~2020-05-21 10:07 UTC|newest]
Thread overview: 89+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-05-21 9:43 [PATCH v8 00/62] target/riscv: support vector extension v0.7.1 LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 01/62] target/riscv: add vector extension field in CPURISCVState LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 02/62] target/riscv: implementation-defined constant parameters LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 03/62] target/riscv: support vector extension csr LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 04/62] target/riscv: add vector configure instruction LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 05/62] target/riscv: add an internals.h header LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 06/62] target/riscv: add vector stride load and store instructions LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 07/62] target/riscv: add vector index " LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 08/62] target/riscv: add fault-only-first unit stride load LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 09/62] target/riscv: add vector amo operations LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 10/62] target/riscv: vector single-width integer add and subtract LIU Zhiwei
2020-05-21 9:43 ` LIU Zhiwei [this message]
2020-05-21 9:43 ` [PATCH v8 12/62] target/riscv: vector integer add-with-carry / subtract-with-borrow instructions LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 13/62] target/riscv: vector bitwise logical instructions LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 14/62] target/riscv: vector single-width bit shift instructions LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 15/62] target/riscv: vector narrowing integer right " LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 16/62] target/riscv: vector integer comparison instructions LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 17/62] target/riscv: vector integer min/max instructions LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 18/62] target/riscv: vector single-width integer multiply instructions LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 19/62] target/riscv: vector integer divide instructions LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 20/62] target/riscv: vector widening integer multiply instructions LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 21/62] target/riscv: vector single-width integer multiply-add instructions LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 22/62] target/riscv: vector widening " LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 23/62] target/riscv: vector integer merge and move instructions LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 24/62] target/riscv: vector single-width saturating add and subtract LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 25/62] target/riscv: vector single-width averaging " LIU Zhiwei
2020-06-04 20:22 ` Richard Henderson
2020-05-21 9:43 ` [PATCH v8 26/62] target/riscv: vector single-width fractional multiply with rounding and saturation LIU Zhiwei
2020-06-04 20:26 ` Richard Henderson
2020-05-21 9:43 ` [PATCH v8 27/62] target/riscv: vector widening saturating scaled multiply-add LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 28/62] target/riscv: vector single-width scaling shift instructions LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 29/62] target/riscv: vector narrowing fixed-point clip instructions LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 30/62] target/riscv: Update fp_status when float rounding mode changes LIU Zhiwei
2020-05-29 19:59 ` Alistair Francis
2020-06-03 4:27 ` Richard Henderson
2020-06-03 5:46 ` LIU Zhiwei
2020-06-04 20:15 ` Richard Henderson
2020-06-05 2:50 ` LIU Zhiwei
2020-06-05 3:30 ` Richard Henderson
2020-06-08 2:39 ` LIU Zhiwei
2020-06-08 16:28 ` Richard Henderson
2020-05-21 9:43 ` [PATCH v8 31/62] target/riscv: vector single-width floating-point add/subtract instructions LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 32/62] target/riscv: vector widening " LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 33/62] target/riscv: vector single-width floating-point multiply/divide instructions LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 34/62] target/riscv: vector widening floating-point multiply LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 35/62] target/riscv: vector single-width floating-point fused multiply-add instructions LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 36/62] target/riscv: vector widening " LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 37/62] target/riscv: vector floating-point square-root instruction LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 38/62] target/riscv: vector floating-point min/max instructions LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 39/62] target/riscv: vector floating-point sign-injection instructions LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 40/62] target/riscv: vector floating-point compare instructions LIU Zhiwei
2020-06-04 20:51 ` Richard Henderson
2020-06-05 2:56 ` LIU Zhiwei
2020-05-21 9:43 ` [PATCH v8 41/62] target/riscv: vector floating-point classify instructions LIU Zhiwei
2020-05-29 20:20 ` Alistair Francis
2020-05-21 9:43 ` [PATCH v8 42/62] target/riscv: vector floating-point merge instructions LIU Zhiwei
2020-05-29 20:36 ` Alistair Francis
2020-06-04 20:57 ` Richard Henderson
2020-05-21 9:43 ` [PATCH v8 43/62] target/riscv: vector floating-point/integer type-convert instructions LIU Zhiwei
2020-05-29 20:40 ` Alistair Francis
2020-05-21 9:43 ` [PATCH v8 44/62] target/riscv: widening " LIU Zhiwei
2020-05-29 20:43 ` Alistair Francis
2020-05-21 9:43 ` [PATCH v8 45/62] target/riscv: narrowing " LIU Zhiwei
2020-05-29 20:51 ` Alistair Francis
2020-05-21 9:43 ` [PATCH v8 46/62] target/riscv: vector single-width integer reduction instructions LIU Zhiwei
2020-05-29 20:58 ` Alistair Francis
2020-05-21 9:43 ` [PATCH v8 47/62] target/riscv: vector wideing " LIU Zhiwei
2020-05-29 20:59 ` Alistair Francis
2020-05-21 9:43 ` [PATCH v8 48/62] target/riscv: vector single-width floating-point " LIU Zhiwei
2020-05-29 21:01 ` Alistair Francis
2020-05-21 9:44 ` [PATCH v8 49/62] target/riscv: vector widening " LIU Zhiwei
2020-05-29 21:03 ` Alistair Francis
2020-05-21 9:44 ` [PATCH v8 50/62] target/riscv: vector mask-register logical instructions LIU Zhiwei
2020-05-21 9:44 ` [PATCH v8 51/62] target/riscv: vector mask population count vmpopc LIU Zhiwei
2020-05-21 9:44 ` [PATCH v8 52/62] target/riscv: vmfirst find-first-set mask bit LIU Zhiwei
2020-05-21 9:44 ` [PATCH v8 53/62] target/riscv: set-X-first " LIU Zhiwei
2020-05-21 9:44 ` [PATCH v8 54/62] target/riscv: vector iota instruction LIU Zhiwei
2020-05-21 9:44 ` [PATCH v8 55/62] target/riscv: vector element index instruction LIU Zhiwei
2020-05-21 9:44 ` [PATCH v8 56/62] target/riscv: integer extract instruction LIU Zhiwei
2020-06-04 21:05 ` Richard Henderson
2020-05-21 9:44 ` [PATCH v8 57/62] target/riscv: integer scalar move instruction LIU Zhiwei
2020-05-21 9:44 ` [PATCH v8 58/62] target/riscv: floating-point scalar move instructions LIU Zhiwei
2020-06-04 21:32 ` Richard Henderson
2020-06-05 2:53 ` LIU Zhiwei
2020-05-21 9:44 ` [PATCH v8 59/62] target/riscv: vector slide instructions LIU Zhiwei
2020-05-21 9:44 ` [PATCH v8 60/62] target/riscv: vector register gather instruction LIU Zhiwei
2020-05-21 9:44 ` [PATCH v8 61/62] target/riscv: vector compress instruction LIU Zhiwei
2020-05-21 9:44 ` [PATCH v8 62/62] target/riscv: configure and turn on vector extension from command line LIU Zhiwei
2020-05-21 13:12 ` [PATCH v8 00/62] target/riscv: support vector extension v0.7.1 no-reply
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=20200521094413.10425-12-zhiwei_liu@c-sky.com \
--to=zhiwei_liu@c-sky.com \
--cc=alistair.francis@wdc.com \
--cc=palmer@dabbelt.com \
--cc=qemu-devel@nongnu.org \
--cc=qemu-riscv@nongnu.org \
--cc=richard.henderson@linaro.org \
--cc=wenmeng_zhang@c-sky.com \
--cc=wxy194768@alibaba-inc.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).