QEMU-Devel Archive on lore.kernel.org
 help / color / Atom feed
From: LIU Zhiwei <zhiwei_liu@c-sky.com>
To: richard.henderson@linaro.org, alistair23@gmail.com,
	chihmin.chao@sifive.com, palmer@dabbelt.com
Cc: guoren@linux.alibaba.com, qemu-riscv@nongnu.org,
	qemu-devel@nongnu.org, wxy194768@alibaba-inc.com,
	wenmeng_zhang@c-sky.com, LIU Zhiwei <zhiwei_liu@c-sky.com>
Subject: [PATCH v6 11/61] target/riscv: vector widening integer add and subtract
Date: Tue, 17 Mar 2020 23:06:03 +0800
Message-ID: <20200317150653.9008-12-zhiwei_liu@c-sky.com> (raw)
In-Reply-To: <20200317150653.9008-1-zhiwei_liu@c-sky.com>

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
---
 target/riscv/helper.h                   |  49 +++++++
 target/riscv/insn32.decode              |  16 +++
 target/riscv/insn_trans/trans_rvv.inc.c | 178 ++++++++++++++++++++++++
 target/riscv/vector_helper.c            | 111 +++++++++++++++
 4 files changed, 354 insertions(+)

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index e73701d4bb..1256defb6c 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -290,3 +290,52 @@ DEF_HELPER_6(vrsub_vx_b, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vrsub_vx_h, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vrsub_vx_w, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vrsub_vx_d, void, ptr, ptr, tl, ptr, env, 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 c68f6ffe3b..8f17faa3f3 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -128,6 +128,14 @@ 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)\
@@ -991,3 +999,173 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)                   \
 }
 
 GEN_OPIVI_TRANS(vrsub_vi, 0, vrsub_vx, opivx_check)
+
+/* 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;
+        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);
+        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;
+        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);
+        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 27934e291b..d0e6f12f43 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -976,3 +976,114 @@ GEN_VEXT_VX(vrsub_vx_b, 1, 1, clearb)
 GEN_VEXT_VX(vrsub_vx_h, 2, 2, clearh)
 GEN_VEXT_VX(vrsub_vx_w, 4, 4, clearl)
 GEN_VEXT_VX(vrsub_vx_d, 8, 8, clearq)
+
+/* 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



  parent reply index

Thread overview: 120+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-17 15:05 [PATCH v6 00/61] target/riscv: support vector extension v0.7.1 LIU Zhiwei
2020-03-17 15:05 ` [PATCH v6 01/61] target/riscv: add vector extension field in CPURISCVState LIU Zhiwei
2020-03-17 15:05 ` [PATCH v6 02/61] target/riscv: implementation-defined constant parameters LIU Zhiwei
2020-03-17 15:05 ` [PATCH v6 03/61] target/riscv: support vector extension csr LIU Zhiwei
2020-03-17 15:05 ` [PATCH v6 04/61] target/riscv: add vector configure instruction LIU Zhiwei
2020-03-23  6:51   ` Kito Cheng
2020-03-23  7:10     ` LIU Zhiwei
2020-03-17 15:05 ` [PATCH v6 05/61] target/riscv: add an internals.h header LIU Zhiwei
2020-03-18 23:45   ` Alistair Francis
2020-03-27 23:41   ` Richard Henderson
2020-03-17 15:05 ` [PATCH v6 06/61] target/riscv: add vector stride load and store instructions LIU Zhiwei
2020-03-18 23:54   ` Alistair Francis
2020-03-17 15:05 ` [PATCH v6 07/61] target/riscv: add vector index " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 08/61] target/riscv: add fault-only-first unit stride load LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 09/61] target/riscv: add vector amo operations LIU Zhiwei
2020-03-19 17:01   ` Alistair Francis
2020-03-27 23:44   ` Richard Henderson
2020-03-17 15:06 ` [PATCH v6 10/61] target/riscv: vector single-width integer add and subtract LIU Zhiwei
2020-03-20 18:31   ` Alistair Francis
2020-03-27 23:54   ` Richard Henderson
2020-03-28 14:42     ` LIU Zhiwei
2020-03-17 15:06 ` LIU Zhiwei [this message]
2020-03-19 16:28   ` [PATCH v6 11/61] target/riscv: vector widening " Alistair Francis
2020-03-17 15:06 ` [PATCH v6 12/61] target/riscv: vector integer add-with-carry / subtract-with-borrow instructions LIU Zhiwei
2020-03-19 17:29   ` Alistair Francis
2020-03-28  0:00   ` Richard Henderson
2020-03-17 15:06 ` [PATCH v6 13/61] target/riscv: vector bitwise logical instructions LIU Zhiwei
2020-03-20 18:34   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 14/61] target/riscv: vector single-width bit shift instructions LIU Zhiwei
2020-03-19 20:10   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 15/61] target/riscv: vector narrowing integer right " LIU Zhiwei
2020-03-20 18:43   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 16/61] target/riscv: vector integer comparison instructions LIU Zhiwei
2020-03-25 17:32   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 17/61] target/riscv: vector integer min/max instructions LIU Zhiwei
2020-03-20 18:49   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 18/61] target/riscv: vector single-width integer multiply instructions LIU Zhiwei
2020-03-25 17:36   ` Alistair Francis
2020-03-28  0:06   ` Richard Henderson
2020-03-28 15:17     ` LIU Zhiwei
2020-03-28 15:47       ` Richard Henderson
2020-03-28 16:13         ` LIU Zhiwei
2020-03-29  4:00           ` LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 19/61] target/riscv: vector integer divide instructions LIU Zhiwei
2020-03-20 18:51   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 20/61] target/riscv: vector widening integer multiply instructions LIU Zhiwei
2020-03-25 17:25   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 21/61] target/riscv: vector single-width integer multiply-add instructions LIU Zhiwei
2020-03-25 17:27   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 22/61] target/riscv: vector widening " LIU Zhiwei
2020-03-25 17:42   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 23/61] target/riscv: vector integer merge and move instructions LIU Zhiwei
2020-03-26 17:57   ` Alistair Francis
2020-03-28  0:18   ` Richard Henderson
2020-03-17 15:06 ` [PATCH v6 24/61] target/riscv: vector single-width saturating add and subtract LIU Zhiwei
2020-03-28  0:20   ` Richard Henderson
2020-03-17 15:06 ` [PATCH v6 25/61] target/riscv: vector single-width averaging " LIU Zhiwei
2020-03-19  3:46   ` LIU Zhiwei
2020-03-28  0:32     ` Richard Henderson
2020-03-28  1:07       ` LIU Zhiwei
2020-03-28  1:22         ` Richard Henderson
2020-03-28 15:37           ` LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 26/61] target/riscv: vector single-width fractional multiply with rounding and saturation LIU Zhiwei
2020-03-28  1:08   ` Richard Henderson
2020-03-28 15:41     ` LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 27/61] target/riscv: vector widening saturating scaled multiply-add LIU Zhiwei
2020-03-28  1:23   ` Richard Henderson
2020-03-17 15:06 ` [PATCH v6 28/61] target/riscv: vector single-width scaling shift instructions LIU Zhiwei
2020-03-28  1:24   ` Richard Henderson
2020-03-17 15:06 ` [PATCH v6 29/61] target/riscv: vector narrowing fixed-point clip instructions LIU Zhiwei
2020-03-28  1:50   ` Richard Henderson
2020-03-17 15:06 ` [PATCH v6 30/61] target/riscv: vector single-width floating-point add/subtract instructions LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 31/61] target/riscv: vector widening " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 32/61] target/riscv: vector single-width floating-point multiply/divide instructions LIU Zhiwei
2020-03-25 17:46   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 33/61] target/riscv: vector widening floating-point multiply LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 34/61] target/riscv: vector single-width floating-point fused multiply-add instructions LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 35/61] target/riscv: vector widening " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 36/61] target/riscv: vector floating-point square-root instruction LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 37/61] target/riscv: vector floating-point min/max instructions LIU Zhiwei
2020-03-25 17:47   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 38/61] target/riscv: vector floating-point sign-injection instructions LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 39/61] target/riscv: vector floating-point compare instructions LIU Zhiwei
2020-03-28  2:01   ` Richard Henderson
2020-03-28 15:44     ` LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 40/61] target/riscv: vector floating-point classify instructions LIU Zhiwei
2020-03-28  2:06   ` Richard Henderson
2020-03-17 15:06 ` [PATCH v6 41/61] target/riscv: vector floating-point merge instructions LIU Zhiwei
2020-03-28  3:23   ` Richard Henderson
2020-03-28 15:47     ` LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 42/61] target/riscv: vector floating-point/integer type-convert instructions LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 43/61] target/riscv: widening " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 44/61] target/riscv: narrowing " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 45/61] target/riscv: vector single-width integer reduction instructions LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 46/61] target/riscv: vector wideing " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 47/61] target/riscv: vector single-width floating-point " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 48/61] target/riscv: vector widening " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 49/61] target/riscv: vector mask-register logical instructions LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 50/61] target/riscv: vector mask population count vmpopc LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 51/61] target/riscv: vmfirst find-first-set mask bit LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 52/61] target/riscv: set-X-first " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 53/61] target/riscv: vector iota instruction LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 54/61] target/riscv: vector element index instruction LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 55/61] target/riscv: integer extract instruction LIU Zhiwei
2020-03-28  3:36   ` Richard Henderson
2020-03-28 16:23     ` LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 56/61] target/riscv: integer scalar move instruction LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 57/61] target/riscv: floating-point scalar move instructions LIU Zhiwei
2020-03-28  3:44   ` Richard Henderson
2020-03-28 16:31     ` LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 58/61] target/riscv: vector slide instructions LIU Zhiwei
2020-03-28  3:50   ` Richard Henderson
2020-03-28 13:40   ` LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 59/61] target/riscv: vector register gather instruction LIU Zhiwei
2020-03-28  3:57   ` Richard Henderson
2020-03-17 15:06 ` [PATCH v6 60/61] target/riscv: vector compress instruction LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 61/61] target/riscv: configure and turn on vector extension from command line LIU Zhiwei
2020-03-25 17:49   ` Alistair Francis
2020-03-28  4:00   ` Richard Henderson
2020-03-17 20:47 ` [PATCH v6 00/61] 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=20200317150653.9008-12-zhiwei_liu@c-sky.com \
    --to=zhiwei_liu@c-sky.com \
    --cc=alistair23@gmail.com \
    --cc=chihmin.chao@sifive.com \
    --cc=guoren@linux.alibaba.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

QEMU-Devel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/qemu-devel/0 qemu-devel/git/0.git
	git clone --mirror https://lore.kernel.org/qemu-devel/1 qemu-devel/git/1.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 qemu-devel qemu-devel/ https://lore.kernel.org/qemu-devel \
		qemu-devel@nongnu.org
	public-inbox-index qemu-devel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.nongnu.qemu-devel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git