target/riscv: vector widening floating-point fused multiply-add instructions

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>
Message-Id: <20200701152549.1218-36-zhiwei_liu@c-sky.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>

4 files changed, 126 insertions, 0 deletions

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 108a177..b537030 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -906,3 +906,20 @@ 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 9ca765d..c9d5078 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -481,6 +481,14 @@ 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 ee601fd..3a5fd0c 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2079,3 +2079,13 @@ 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 29dc1d1..607fcc8 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -3683,3 +3683,94 @@ 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)