The instructions have the same function as RVV1.0. Overall there are only
general differences between XTheadVector and RVV1.0.
Signed-off-by: Huang Tao <eric.huang@linux.alibaba.com>
---
target/riscv/helper.h | 5 +++++
target/riscv/insn_trans/trans_xtheadvector.c.inc | 6 ++++--
target/riscv/vector_helper.c | 4 ++--
target/riscv/vector_internals.h | 3 +++
target/riscv/xtheadvector_helper.c | 11 +++++++++++
5 files changed, 25 insertions(+), 4 deletions(-)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index f63239676a..3102b078e4 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -2045,3 +2045,8 @@ DEF_HELPER_6(th_vfdiv_vf_d, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(th_vfrdiv_vf_h, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(th_vfrdiv_vf_w, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(th_vfrdiv_vf_d, void, ptr, ptr, i64, ptr, env, i32)
+
+DEF_HELPER_6(th_vfwmul_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(th_vfwmul_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(th_vfwmul_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(th_vfwmul_vf_w, void, ptr, ptr, i64, ptr, env, i32)
diff --git a/target/riscv/insn_trans/trans_xtheadvector.c.inc b/target/riscv/insn_trans/trans_xtheadvector.c.inc
index 940b212f5e..3d0370f220 100644
--- a/target/riscv/insn_trans/trans_xtheadvector.c.inc
+++ b/target/riscv/insn_trans/trans_xtheadvector.c.inc
@@ -2015,14 +2015,16 @@ GEN_OPFVF_TRANS_TH(th_vfmul_vf, opfvf_check_th)
GEN_OPFVF_TRANS_TH(th_vfdiv_vf, opfvf_check_th)
GEN_OPFVF_TRANS_TH(th_vfrdiv_vf, opfvf_check_th)
+/* Vector Widening Floating-Point Multiply */
+GEN_OPFVV_WIDEN_TRANS_TH(th_vfwmul_vv, opfvv_widen_check_th)
+GEN_OPFVF_WIDEN_TRANS_TH(th_vfwmul_vf)
+
#define TH_TRANS_STUB(NAME) \
static bool trans_##NAME(DisasContext *s, arg_##NAME *a) \
{ \
return require_xtheadvector(s); \
}
-TH_TRANS_STUB(th_vfwmul_vv)
-TH_TRANS_STUB(th_vfwmul_vf)
TH_TRANS_STUB(th_vfmacc_vv)
TH_TRANS_STUB(th_vfnmacc_vv)
TH_TRANS_STUB(th_vfnmacc_vf)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index d65b32c584..aa7714d651 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -3059,13 +3059,13 @@ GEN_VEXT_VF(vfrdiv_vf_w, 4)
GEN_VEXT_VF(vfrdiv_vf_d, 8)
/* Vector Widening Floating-Point Multiply */
-static uint32_t vfwmul16(uint16_t a, uint16_t b, float_status *s)
+uint32_t vfwmul16(uint16_t a, uint16_t b, float_status *s)
{
return float32_mul(float16_to_float32(a, true, s),
float16_to_float32(b, true, s), s);
}
-static uint64_t vfwmul32(uint32_t a, uint32_t b, float_status *s)
+uint64_t vfwmul32(uint32_t a, uint32_t b, float_status *s)
{
return float64_mul(float32_to_float64(a, s),
float32_to_float64(b, s), s);
diff --git a/target/riscv/vector_internals.h b/target/riscv/vector_internals.h
index 29263c6a53..8903a894d7 100644
--- a/target/riscv/vector_internals.h
+++ b/target/riscv/vector_internals.h
@@ -357,4 +357,7 @@ uint16_t float16_rdiv(uint16_t a, uint16_t b, float_status *s);
uint32_t float32_rdiv(uint32_t a, uint32_t b, float_status *s);
uint64_t float64_rdiv(uint64_t a, uint64_t b, float_status *s);
+uint32_t vfwmul16(uint16_t a, uint16_t b, float_status *s);
+uint64_t vfwmul32(uint32_t a, uint32_t b, float_status *s);
+
#endif /* TARGET_RISCV_VECTOR_INTERNALS_H */
diff --git a/target/riscv/xtheadvector_helper.c b/target/riscv/xtheadvector_helper.c
index 770f36346f..dd01d66933 100644
--- a/target/riscv/xtheadvector_helper.c
+++ b/target/riscv/xtheadvector_helper.c
@@ -2768,3 +2768,14 @@ THCALL(TH_OPFVF2, th_vfrdiv_vf_d, OP_UUU_D, H8, H8, float64_rdiv)
GEN_TH_VF(th_vfrdiv_vf_h, 2, 2, clearh_th)
GEN_TH_VF(th_vfrdiv_vf_w, 4, 4, clearl_th)
GEN_TH_VF(th_vfrdiv_vf_d, 8, 8, clearq_th)
+
+/* Vector Widening Floating-Point Multiply */
+
+THCALL(TH_OPFVV2, th_vfwmul_vv_h, WOP_UUU_H, H4, H2, H2, vfwmul16)
+THCALL(TH_OPFVV2, th_vfwmul_vv_w, WOP_UUU_W, H8, H4, H4, vfwmul32)
+GEN_TH_VV_ENV(th_vfwmul_vv_h, 2, 4, clearl_th)
+GEN_TH_VV_ENV(th_vfwmul_vv_w, 4, 8, clearq_th)
+THCALL(TH_OPFVF2, th_vfwmul_vf_h, WOP_UUU_H, H4, H2, vfwmul16)
+THCALL(TH_OPFVF2, th_vfwmul_vf_w, WOP_UUU_W, H8, H4, vfwmul32)
+GEN_TH_VF(th_vfwmul_vf_h, 2, 4, clearl_th)
+GEN_TH_VF(th_vfwmul_vf_w, 4, 8, clearq_th)
--
2.44.0