[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH v4 30/60] target/riscv: vector widening floating-point add/subtra
|
From: |
LIU Zhiwei |
|
Subject: |
[PATCH v4 30/60] target/riscv: vector widening floating-point add/subtract instructions |
|
Date: |
Wed, 11 Mar 2020 13:06:49 +0800 |
Signed-off-by: LIU Zhiwei <address@hidden>
---
target/riscv/helper.h | 17 +++
target/riscv/insn32.decode | 8 ++
target/riscv/insn_trans/trans_rvv.inc.c | 131 ++++++++++++++++++++++++
target/riscv/vector_helper.c | 77 ++++++++++++++
4 files changed, 233 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 6b46677eeb..f242fa4e4b 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -801,3 +801,20 @@ DEF_HELPER_6(vfsub_vf_d, void, ptr, ptr, i64, ptr, env,
i32)
DEF_HELPER_6(vfrsub_vf_h, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfrsub_vf_w, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfrsub_vf_d, void, ptr, ptr, i64, ptr, env, i32)
+
+DEF_HELPER_6(vfwadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwadd_wv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwadd_wv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwsub_wv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwsub_wv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwadd_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwadd_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwsub_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwsub_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwadd_wf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwadd_wf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwsub_wf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwsub_wf_w, void, ptr, ptr, i64, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 32918c4d11..5ec95541c6 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -443,6 +443,14 @@ vfadd_vf 000000 . ..... ..... 101 ..... 1010111
@r_vm
vfsub_vv 000010 . ..... ..... 001 ..... 1010111 @r_vm
vfsub_vf 000010 . ..... ..... 101 ..... 1010111 @r_vm
vfrsub_vf 100111 . ..... ..... 101 ..... 1010111 @r_vm
+vfwadd_vv 110000 . ..... ..... 001 ..... 1010111 @r_vm
+vfwadd_vf 110000 . ..... ..... 101 ..... 1010111 @r_vm
+vfwadd_wv 110100 . ..... ..... 001 ..... 1010111 @r_vm
+vfwadd_wf 110100 . ..... ..... 101 ..... 1010111 @r_vm
+vfwsub_vv 110010 . ..... ..... 001 ..... 1010111 @r_vm
+vfwsub_vf 110010 . ..... ..... 101 ..... 1010111 @r_vm
+vfwsub_wv 110110 . ..... ..... 001 ..... 1010111 @r_vm
+vfwsub_wf 110110 . ..... ..... 101 ..... 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 af4dcb96c6..ab04f469af 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1664,3 +1664,134 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)
\
GEN_OPFVF_TRANS(vfadd_vf, opfvf_check)
GEN_OPFVF_TRANS(vfsub_vf, opfvf_check)
GEN_OPFVF_TRANS(vfrsub_vf, opfvf_check)
+
+/* Vector Widening Floating-Point Add/Subtract Instructions */
+static bool opfvv_widen_check(DisasContext *s, arg_rmrr *a)
+{
+ return (vext_check_isa_ill(s, RVV) &&
+ 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) && (s->sew != 0));
+}
+
+/* OPFVV with WIDEN */
+#define GEN_OPFVV_WIDEN_TRANS(NAME, CHECK) \
+static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
+{ \
+ if (CHECK(s, a)) { \
+ uint32_t data = 0; \
+ static gen_helper_gvec_4_ptr * const fns[2] = { \
+ gen_helper_##NAME##_h, gen_helper_##NAME##_w, \
+ }; \
+ 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, fns[s->sew - 1]); \
+ return true; \
+ } \
+ return false; \
+}
+
+GEN_OPFVV_WIDEN_TRANS(vfwadd_vv, opfvv_widen_check)
+GEN_OPFVV_WIDEN_TRANS(vfwsub_vv, opfvv_widen_check)
+
+static bool opfvf_widen_check(DisasContext *s, arg_rmrr *a)
+{
+ return (vext_check_isa_ill(s, RVV) &&
+ 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) && (s->sew != 0));
+}
+/* OPFVF with WIDEN */
+#define GEN_OPFVF_WIDEN_TRANS(NAME) \
+static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
+{ \
+ if (opfvf_widen_check(s, a)) { \
+ uint32_t data = 0; \
+ static gen_helper_opfvf const fns[2] = { \
+ gen_helper_##NAME##_h, gen_helper_##NAME##_w, \
+ }; \
+ data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \
+ data = FIELD_DP32(data, VDATA, VM, a->vm); \
+ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ return opfvf_trans(a->rd, a->rs1, a->rs2, data, \
+ fns[s->sew - 1], s); \
+ } \
+ return false; \
+}
+GEN_OPFVF_WIDEN_TRANS(vfwadd_vf)
+GEN_OPFVF_WIDEN_TRANS(vfwsub_vf)
+
+static bool opfwv_widen_check(DisasContext *s, arg_rmrr *a)
+{
+ return (vext_check_isa_ill(s, RVV) &&
+ 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) && (s->sew != 0));
+}
+
+/* WIDEN OPFVV with WIDEN */
+#define GEN_OPFWV_WIDEN_TRANS(NAME) \
+static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
+{ \
+ if (opfwv_widen_check(s, a)) { \
+ uint32_t data = 0; \
+ static gen_helper_gvec_4_ptr * const fns[2] = { \
+ gen_helper_##NAME##_h, gen_helper_##NAME##_w, \
+ }; \
+ 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, fns[s->sew - 1]); \
+ return true; \
+ } \
+ return false; \
+}
+GEN_OPFWV_WIDEN_TRANS(vfwadd_wv)
+GEN_OPFWV_WIDEN_TRANS(vfwsub_wv)
+
+static bool opfwf_widen_check(DisasContext *s, arg_rmrr *a)
+{
+ return (vext_check_isa_ill(s, RVV) &&
+ 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) && (s->sew != 0));
+}
+
+/* WIDEN OPFVF with WIDEN */
+#define GEN_OPFWF_WIDEN_TRANS(NAME) \
+static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
+{ \
+ if (opfwf_widen_check(s, a)) { \
+ uint32_t data = 0; \
+ static gen_helper_opfvf const fns[2] = { \
+ gen_helper_##NAME##_h, gen_helper_##NAME##_w, \
+ }; \
+ data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \
+ data = FIELD_DP32(data, VDATA, VM, a->vm); \
+ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ return opfvf_trans(a->rd, a->rs1, a->rs2, data, \
+ fns[s->sew - 1], s); \
+ } \
+ return false; \
+}
+GEN_OPFWF_WIDEN_TRANS(vfwadd_wf)
+GEN_OPFWF_WIDEN_TRANS(vfwsub_wf)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index d49a7194f7..0840c5d662 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -3029,3 +3029,80 @@ RVVCALL(OPFVF2, vfrsub_vf_d, OP_UUU_D, H8, H8,
float64_rsub)
GEN_VEXT_VF(vfrsub_vf_h, 2, 2, clearh)
GEN_VEXT_VF(vfrsub_vf_w, 4, 4, clearl)
GEN_VEXT_VF(vfrsub_vf_d, 8, 8, clearq)
+
+/* Vector Widening Floating-Point Add/Subtract Instructions */
+static uint32_t vfwadd16(uint16_t a, uint16_t b, float_status *s)
+{
+ return float32_add(float16_to_float32(a, true, s),
+ float16_to_float32(b, true, s), s);
+}
+static uint64_t vfwadd32(uint32_t a, uint32_t b, float_status *s)
+{
+ return float64_add(float32_to_float64(a, s),
+ float32_to_float64(b, s), s);
+
+}
+RVVCALL(OPFVV2, vfwadd_vv_h, WOP_UUU_H, H4, H2, H2, vfwadd16)
+RVVCALL(OPFVV2, vfwadd_vv_w, WOP_UUU_W, H8, H4, H4, vfwadd32)
+GEN_VEXT_VV_ENV(vfwadd_vv_h, 2, 4, clearl)
+GEN_VEXT_VV_ENV(vfwadd_vv_w, 4, 8, clearq)
+RVVCALL(OPFVF2, vfwadd_vf_h, WOP_UUU_H, H4, H2, vfwadd16)
+RVVCALL(OPFVF2, vfwadd_vf_w, WOP_UUU_W, H8, H4, vfwadd32)
+GEN_VEXT_VF(vfwadd_vf_h, 2, 4, clearl)
+GEN_VEXT_VF(vfwadd_vf_w, 4, 8, clearq)
+
+static uint32_t vfwsub16(uint16_t a, uint16_t b, float_status *s)
+{
+ return float32_sub(float16_to_float32(a, true, s),
+ float16_to_float32(b, true, s), s);
+}
+
+static uint64_t vfwsub32(uint32_t a, uint32_t b, float_status *s)
+{
+ return float64_sub(float32_to_float64(a, s),
+ float32_to_float64(b, s), s);
+
+}
+RVVCALL(OPFVV2, vfwsub_vv_h, WOP_UUU_H, H4, H2, H2, vfwsub16)
+RVVCALL(OPFVV2, vfwsub_vv_w, WOP_UUU_W, H8, H4, H4, vfwsub32)
+GEN_VEXT_VV_ENV(vfwsub_vv_h, 2, 4, clearl)
+GEN_VEXT_VV_ENV(vfwsub_vv_w, 4, 8, clearq)
+RVVCALL(OPFVF2, vfwsub_vf_h, WOP_UUU_H, H4, H2, vfwsub16)
+RVVCALL(OPFVF2, vfwsub_vf_w, WOP_UUU_W, H8, H4, vfwsub32)
+GEN_VEXT_VF(vfwsub_vf_h, 2, 4, clearl)
+GEN_VEXT_VF(vfwsub_vf_w, 4, 8, clearq)
+
+static uint32_t vfwaddw16(uint32_t a, uint16_t b, float_status *s)
+{
+ return float32_add(a, float16_to_float32(b, true, s), s);
+}
+static uint64_t vfwaddw32(uint64_t a, uint32_t b, float_status *s)
+{
+ return float64_add(a, float32_to_float64(b, s), s);
+}
+RVVCALL(OPFVV2, vfwadd_wv_h, WOP_WUUU_H, H4, H2, H2, vfwaddw16)
+RVVCALL(OPFVV2, vfwadd_wv_w, WOP_WUUU_W, H8, H4, H4, vfwaddw32)
+GEN_VEXT_VV_ENV(vfwadd_wv_h, 2, 4, clearl)
+GEN_VEXT_VV_ENV(vfwadd_wv_w, 4, 8, clearq)
+RVVCALL(OPFVF2, vfwadd_wf_h, WOP_WUUU_H, H4, H2, vfwaddw16)
+RVVCALL(OPFVF2, vfwadd_wf_w, WOP_WUUU_W, H8, H4, vfwaddw32)
+GEN_VEXT_VF(vfwadd_wf_h, 2, 4, clearl)
+GEN_VEXT_VF(vfwadd_wf_w, 4, 8, clearq)
+
+static uint32_t vfwsubw16(uint32_t a, uint16_t b, float_status *s)
+{
+ return float32_sub(a, float16_to_float32(b, true, s), s);
+}
+
+static uint64_t vfwsubw32(uint64_t a, uint32_t b, float_status *s)
+{
+ return float64_sub(a, float32_to_float64(b, s), s);
+}
+RVVCALL(OPFVV2, vfwsub_wv_h, WOP_WUUU_H, H4, H2, H2, vfwsubw16)
+RVVCALL(OPFVV2, vfwsub_wv_w, WOP_WUUU_W, H8, H4, H4, vfwsubw32)
+GEN_VEXT_VV_ENV(vfwsub_wv_h, 2, 4, clearl)
+GEN_VEXT_VV_ENV(vfwsub_wv_w, 4, 8, clearq)
+RVVCALL(OPFVF2, vfwsub_wf_h, WOP_WUUU_H, H4, H2, vfwsubw16)
+RVVCALL(OPFVF2, vfwsub_wf_w, WOP_WUUU_W, H8, H4, vfwsubw32)
+GEN_VEXT_VF(vfwsub_wf_h, 2, 4, clearl)
+GEN_VEXT_VF(vfwsub_wf_w, 4, 8, clearq)
--
2.23.0
- [PATCH v4 22/60] target/riscv: vector integer merge and move instructions, (continued)
- [PATCH v4 22/60] target/riscv: vector integer merge and move instructions, LIU Zhiwei, 2020/03/11
- [PATCH v4 24/60] target/riscv: vector single-width averaging add and subtract, LIU Zhiwei, 2020/03/11
- [PATCH v4 25/60] target/riscv: vector single-width fractional multiply with rounding and saturation, LIU Zhiwei, 2020/03/11
- [PATCH v4 21/60] target/riscv: vector widening integer multiply-add instructions, LIU Zhiwei, 2020/03/11
- [PATCH v4 26/60] target/riscv: vector widening saturating scaled multiply-add, LIU Zhiwei, 2020/03/11
- [PATCH v4 23/60] target/riscv: vector single-width saturating add and subtract, LIU Zhiwei, 2020/03/11
- [PATCH v4 28/60] target/riscv: vector narrowing fixed-point clip instructions, LIU Zhiwei, 2020/03/11
- [PATCH v4 27/60] target/riscv: vector single-width scaling shift instructions, LIU Zhiwei, 2020/03/11
- [PATCH v4 29/60] target/riscv: vector single-width floating-point add/subtract instructions, LIU Zhiwei, 2020/03/11
- [PATCH v4 32/60] target/riscv: vector widening floating-point multiply, LIU Zhiwei, 2020/03/11
- [PATCH v4 30/60] target/riscv: vector widening floating-point add/subtract instructions,
LIU Zhiwei <=
- [PATCH v4 31/60] target/riscv: vector single-width floating-point multiply/divide instructions, LIU Zhiwei, 2020/03/11
- [PATCH v4 34/60] target/riscv: vector widening floating-point fused multiply-add instructions, LIU Zhiwei, 2020/03/11
- [PATCH v4 33/60] target/riscv: vector single-width floating-point fused multiply-add instructions, LIU Zhiwei, 2020/03/11
- [PATCH v4 35/60] target/riscv: vector floating-point square-root instruction, LIU Zhiwei, 2020/03/11