[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH v6 35/61] target/riscv: vector widening floating-point fused mult
From: |
LIU Zhiwei |
Subject: |
[PATCH v6 35/61] target/riscv: vector widening floating-point fused multiply-add instructions |
Date: |
Tue, 17 Mar 2020 23:06:27 +0800 |
Signed-off-by: LIU Zhiwei <address@hidden>
Reviewed-by: Richard Henderson <address@hidden>
---
target/riscv/helper.h | 17 +++++
target/riscv/insn32.decode | 8 +++
target/riscv/insn_trans/trans_rvv.inc.c | 10 +++
target/riscv/vector_helper.c | 84 +++++++++++++++++++++++++
4 files changed, 119 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 55ea95b425..1ccfb6405b 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -896,3 +896,20 @@ DEF_HELPER_6(vfmsub_vf_d, void, ptr, ptr, i64, ptr, env,
i32)
DEF_HELPER_6(vfnmsub_vf_h, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfnmsub_vf_w, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfnmsub_vf_d, void, ptr, ptr, i64, ptr, env, i32)
+
+DEF_HELPER_6(vfwmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwnmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwnmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwmsac_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwmsac_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwnmsac_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwnmsac_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwmacc_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwmacc_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwnmacc_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwnmacc_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwmsac_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwmsac_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwnmsac_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwnmsac_vf_w, void, ptr, ptr, i64, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index c42bcd141c..56bfd4a919 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -479,6 +479,14 @@ vfmsub_vv 101010 . ..... ..... 001 ..... 1010111
@r_vm
vfmsub_vf 101010 . ..... ..... 101 ..... 1010111 @r_vm
vfnmsub_vv 101011 . ..... ..... 001 ..... 1010111 @r_vm
vfnmsub_vf 101011 . ..... ..... 101 ..... 1010111 @r_vm
+vfwmacc_vv 111100 . ..... ..... 001 ..... 1010111 @r_vm
+vfwmacc_vf 111100 . ..... ..... 101 ..... 1010111 @r_vm
+vfwnmacc_vv 111101 . ..... ..... 001 ..... 1010111 @r_vm
+vfwnmacc_vf 111101 . ..... ..... 101 ..... 1010111 @r_vm
+vfwmsac_vv 111110 . ..... ..... 001 ..... 1010111 @r_vm
+vfwmsac_vf 111110 . ..... ..... 101 ..... 1010111 @r_vm
+vfwnmsac_vv 111111 . ..... ..... 001 ..... 1010111 @r_vm
+vfwnmsac_vf 111111 . ..... ..... 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 d253ef7003..5b68ca7130 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1939,3 +1939,13 @@ GEN_OPFVF_TRANS(vfmadd_vf, opfvf_check)
GEN_OPFVF_TRANS(vfnmadd_vf, opfvf_check)
GEN_OPFVF_TRANS(vfmsub_vf, opfvf_check)
GEN_OPFVF_TRANS(vfnmsub_vf, opfvf_check)
+
+/* Vector Widening Floating-Point Fused Multiply-Add Instructions */
+GEN_OPFVV_WIDEN_TRANS(vfwmacc_vv, opfvv_widen_check)
+GEN_OPFVV_WIDEN_TRANS(vfwnmacc_vv, opfvv_widen_check)
+GEN_OPFVV_WIDEN_TRANS(vfwmsac_vv, opfvv_widen_check)
+GEN_OPFVV_WIDEN_TRANS(vfwnmsac_vv, opfvv_widen_check)
+GEN_OPFVF_WIDEN_TRANS(vfwmacc_vf)
+GEN_OPFVF_WIDEN_TRANS(vfwnmacc_vf)
+GEN_OPFVF_WIDEN_TRANS(vfwmsac_vf)
+GEN_OPFVF_WIDEN_TRANS(vfwnmsac_vf)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index e9f37b08d1..36cffde4b3 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -3641,3 +3641,87 @@ RVVCALL(OPFVF3, vfnmsub_vf_d, OP_UUU_D, H8, H8, fnmsub64)
GEN_VEXT_VF(vfnmsub_vf_h, 2, 2, clearh)
GEN_VEXT_VF(vfnmsub_vf_w, 4, 4, clearl)
GEN_VEXT_VF(vfnmsub_vf_d, 8, 8, clearq)
+
+/* Vector Widening Floating-Point Fused Multiply-Add Instructions */
+static uint32_t fwmacc16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
+{
+ return float32_muladd(float16_to_float32(a, true, s),
+ float16_to_float32(b, true, s), d, 0, s);
+}
+static uint64_t fwmacc32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
+{
+ return float64_muladd(float32_to_float64(a, s),
+ float32_to_float64(b, s), d, 0, s);
+}
+RVVCALL(OPFVV3, vfwmacc_vv_h, WOP_UUU_H, H4, H2, H2, fwmacc16)
+RVVCALL(OPFVV3, vfwmacc_vv_w, WOP_UUU_W, H8, H4, H4, fwmacc32)
+GEN_VEXT_VV_ENV(vfwmacc_vv_h, 2, 4, clearl)
+GEN_VEXT_VV_ENV(vfwmacc_vv_w, 4, 8, clearq)
+RVVCALL(OPFVF3, vfwmacc_vf_h, WOP_UUU_H, H4, H2, fwmacc16)
+RVVCALL(OPFVF3, vfwmacc_vf_w, WOP_UUU_W, H8, H4, fwmacc32)
+GEN_VEXT_VF(vfwmacc_vf_h, 2, 4, clearl)
+GEN_VEXT_VF(vfwmacc_vf_w, 4, 8, clearq)
+
+static uint32_t fwnmacc16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
+{
+ return float32_muladd(float16_to_float32(a, true, s),
+ float16_to_float32(b, true, s), d,
+ float_muladd_negate_c | float_muladd_negate_product,
s);
+}
+static uint64_t fwnmacc32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
+{
+ return float64_muladd(float32_to_float64(a, s),
+ float32_to_float64(b, s), d,
+ float_muladd_negate_c | float_muladd_negate_product,
s);
+}
+RVVCALL(OPFVV3, vfwnmacc_vv_h, WOP_UUU_H, H4, H2, H2, fwnmacc16)
+RVVCALL(OPFVV3, vfwnmacc_vv_w, WOP_UUU_W, H8, H4, H4, fwnmacc32)
+GEN_VEXT_VV_ENV(vfwnmacc_vv_h, 2, 4, clearl)
+GEN_VEXT_VV_ENV(vfwnmacc_vv_w, 4, 8, clearq)
+RVVCALL(OPFVF3, vfwnmacc_vf_h, WOP_UUU_H, H4, H2, fwnmacc16)
+RVVCALL(OPFVF3, vfwnmacc_vf_w, WOP_UUU_W, H8, H4, fwnmacc32)
+GEN_VEXT_VF(vfwnmacc_vf_h, 2, 4, clearl)
+GEN_VEXT_VF(vfwnmacc_vf_w, 4, 8, clearq)
+
+static uint32_t fwmsac16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
+{
+ return float32_muladd(float16_to_float32(a, true, s),
+ float16_to_float32(b, true, s), d,
+ float_muladd_negate_c, s);
+}
+static uint64_t fwmsac32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
+{
+ return float64_muladd(float32_to_float64(a, s),
+ float32_to_float64(b, s), d,
+ float_muladd_negate_c, s);
+}
+
+RVVCALL(OPFVV3, vfwmsac_vv_h, WOP_UUU_H, H4, H2, H2, fwmsac16)
+RVVCALL(OPFVV3, vfwmsac_vv_w, WOP_UUU_W, H8, H4, H4, fwmsac32)
+GEN_VEXT_VV_ENV(vfwmsac_vv_h, 2, 4, clearl)
+GEN_VEXT_VV_ENV(vfwmsac_vv_w, 4, 8, clearq)
+RVVCALL(OPFVF3, vfwmsac_vf_h, WOP_UUU_H, H4, H2, fwmsac16)
+RVVCALL(OPFVF3, vfwmsac_vf_w, WOP_UUU_W, H8, H4, fwmsac32)
+GEN_VEXT_VF(vfwmsac_vf_h, 2, 4, clearl)
+GEN_VEXT_VF(vfwmsac_vf_w, 4, 8, clearq)
+
+static uint32_t fwnmsac16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
+{
+ return float32_muladd(float16_to_float32(a, true, s),
+ float16_to_float32(b, true, s), d,
+ float_muladd_negate_product, s);
+}
+static uint64_t fwnmsac32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
+{
+ return float64_muladd(float32_to_float64(a, s),
+ float32_to_float64(b, s), d,
+ float_muladd_negate_product, s);
+}
+RVVCALL(OPFVV3, vfwnmsac_vv_h, WOP_UUU_H, H4, H2, H2, fwnmsac16)
+RVVCALL(OPFVV3, vfwnmsac_vv_w, WOP_UUU_W, H8, H4, H4, fwnmsac32)
+GEN_VEXT_VV_ENV(vfwnmsac_vv_h, 2, 4, clearl)
+GEN_VEXT_VV_ENV(vfwnmsac_vv_w, 4, 8, clearq)
+RVVCALL(OPFVF3, vfwnmsac_vf_h, WOP_UUU_H, H4, H2, fwnmsac16)
+RVVCALL(OPFVF3, vfwnmsac_vf_w, WOP_UUU_W, H8, H4, fwnmsac32)
+GEN_VEXT_VF(vfwnmsac_vf_h, 2, 4, clearl)
+GEN_VEXT_VF(vfwnmsac_vf_w, 4, 8, clearq)
--
2.23.0
- [PATCH v6 28/61] target/riscv: vector single-width scaling shift instructions, (continued)
- [PATCH v6 28/61] target/riscv: vector single-width scaling shift instructions, LIU Zhiwei, 2020/03/17
- [PATCH v6 29/61] target/riscv: vector narrowing fixed-point clip instructions, LIU Zhiwei, 2020/03/17
- [PATCH v6 30/61] target/riscv: vector single-width floating-point add/subtract instructions, LIU Zhiwei, 2020/03/17
- [PATCH v6 31/61] target/riscv: vector widening floating-point add/subtract instructions, LIU Zhiwei, 2020/03/17
- [PATCH v6 32/61] target/riscv: vector single-width floating-point multiply/divide instructions, LIU Zhiwei, 2020/03/17
- [PATCH v6 33/61] target/riscv: vector widening floating-point multiply, LIU Zhiwei, 2020/03/17
- [PATCH v6 34/61] target/riscv: vector single-width floating-point fused multiply-add instructions, LIU Zhiwei, 2020/03/17
- [PATCH v6 35/61] target/riscv: vector widening floating-point fused multiply-add instructions,
LIU Zhiwei <=
- [PATCH v6 36/61] target/riscv: vector floating-point square-root instruction, LIU Zhiwei, 2020/03/17
- [PATCH v6 37/61] target/riscv: vector floating-point min/max instructions, LIU Zhiwei, 2020/03/17
- [PATCH v6 38/61] target/riscv: vector floating-point sign-injection instructions, LIU Zhiwei, 2020/03/17
- [PATCH v6 39/61] target/riscv: vector floating-point compare instructions, LIU Zhiwei, 2020/03/17
- [PATCH v6 40/61] target/riscv: vector floating-point classify instructions, LIU Zhiwei, 2020/03/17
- [PATCH v6 41/61] target/riscv: vector floating-point merge instructions, LIU Zhiwei, 2020/03/17