From: eopXD <eop.c...@sifive.com>
`vmadc` and `vmsbc` produces a mask value, they always operate with
a tail agnostic policy.
Signed-off-by: eop Chen <eop.c...@sifive.com>
Reviewed-by: Frank Chang <frank.ch...@sifive.com>
---
target/riscv/insn_trans/trans_rvv.c.inc | 29 +++
target/riscv/internals.h | 5 +-
target/riscv/translate.c | 2 +
target/riscv/vector_helper.c | 317 +++++++++++++-----------
4 files changed, 213 insertions(+), 140 deletions(-)
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc
b/target/riscv/insn_trans/trans_rvv.c.inc
index 99691f1b9f..d15858fc6f 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -1299,6 +1299,8 @@ static bool opivx_trans(uint32_t vd, uint32_t rs1,
uint32_t vs2, uint32_t vm,
data = FIELD_DP32(data, VDATA, VM, vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
+ data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);
desc = tcg_constant_i32(simd_desc(s->cfg_ptr->vlen / 8,
s->cfg_ptr->vlen / 8, data));
@@ -1335,6 +1337,16 @@ do_opivx_gvec(DisasContext *s, arg_rmrr *a, GVecGen2sFn
*gvec_fn,
}
if (a->vm && s->vl_eq_vlmax) {
+ if (s->vta && s->lmul < 0) {
+ /*
+ * tail elements may pass vlmax when lmul < 0
+ * set tail elements to 1s
+ */
+ uint32_t vlenb = s->cfg_ptr->vlen >> 3;
+ tcg_gen_gvec_ori(s->sew, vreg_ofs(s, a->rd),
+ vreg_ofs(s, a->rd), -1,
+ vlenb, vlenb);
+ }
TCGv_i64 src1 = tcg_temp_new_i64();
tcg_gen_ext_tl_i64(src1, get_gpr(s, a->rs1, EXT_SIGN));
@@ -1464,6 +1476,8 @@ static bool opivi_trans(uint32_t vd, uint32_t imm,
uint32_t vs2, uint32_t vm,
data = FIELD_DP32(data, VDATA, VM, vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
+ data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);
desc = tcg_constant_i32(simd_desc(s->cfg_ptr->vlen / 8,
s->cfg_ptr->vlen / 8, data));
@@ -1493,6 +1507,16 @@ do_opivi_gvec(DisasContext *s, arg_rmrr *a, GVecGen2iFn
*gvec_fn,
}
if (a->vm && s->vl_eq_vlmax) {
+ if (s->vta && s->lmul < 0) {
+ /*
+ * tail elements may pass vlmax when lmul < 0
+ * set tail elements to 1s
+ */
+ uint32_t vlenb = s->cfg_ptr->vlen >> 3;
+ tcg_gen_gvec_ori(s->sew, vreg_ofs(s, a->rd),
+ vreg_ofs(s, a->rd), -1,
+ vlenb, vlenb);
+ }
gvec_fn(s->sew, vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2),
extract_imm(s, a->rs1, imm_mode), MAXSZ(s), MAXSZ(s));
mark_vs_dirty(s);
@@ -1546,6 +1570,7 @@ static bool do_opivv_widen(DisasContext *s, arg_rmrr *a,
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),
vreg_ofs(s, a->rs1),
vreg_ofs(s, a->rs2),
@@ -1627,6 +1652,7 @@ static bool do_opiwv_widen(DisasContext *s, arg_rmrr *a,
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+ data = FIELD_DP32(data, VDATA, VTA, s->vta);
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),
vreg_ofs(s, a->rs1),
vreg_ofs(s, a->rs2),
@@ -1705,6 +1731,9 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)
\
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
+ data = \
+ FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);\
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, \
diff --git a/target/riscv/internals.h b/target/riscv/internals.h
index 512c6c30cf..193ce57a6d 100644
--- a/target/riscv/internals.h
+++ b/target/riscv/internals.h
@@ -25,8 +25,9 @@
FIELD(VDATA, VM, 0, 1)
FIELD(VDATA, LMUL, 1, 3)
FIELD(VDATA, VTA, 4, 1)
-FIELD(VDATA, NF, 5, 4)
-FIELD(VDATA, WD, 5, 1)
+FIELD(VDATA, VTA_ALL_1S, 5, 1)
+FIELD(VDATA, NF, 6, 4)
+FIELD(VDATA, WD, 6, 1)
/* float point classify helpers */
target_ulong fclass_h(uint64_t frs1);
diff --git a/target/riscv/translate.c b/target/riscv/translate.c
index 7775dade26..58cbb6ded3 100644
--- a/target/riscv/translate.c
+++ b/target/riscv/translate.c
@@ -95,6 +95,7 @@ typedef struct DisasContext {
int8_t lmul;
uint8_t sew;
uint8_t vta;
+ bool cfg_vta_all_1s;
target_ulong vstart;
bool vl_eq_vlmax;
uint8_t ntemp;
@@ -1085,6 +1086,7 @@ static void riscv_tr_init_disas_context(DisasContextBase
*dcbase, CPUState *cs)
ctx->sew = FIELD_EX32(tb_flags, TB_FLAGS, SEW);
ctx->lmul = sextract32(FIELD_EX32(tb_flags, TB_FLAGS, LMUL), 0, 3);
ctx->vta = FIELD_EX32(tb_flags, TB_FLAGS, VTA) && cpu->cfg.rvv_ta_all_1s;
+ ctx->cfg_vta_all_1s = cpu->cfg.rvv_ta_all_1s;
ctx->vstart = env->vstart;
ctx->vl_eq_vlmax = FIELD_EX32(tb_flags, TB_FLAGS, VL_EQ_VLMAX);
ctx->misa_mxl_max = env->misa_mxl_max;
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 1541d97b08..cd2283321f 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -127,6 +127,11 @@ static inline uint32_t vext_vta(uint32_t desc)
return FIELD_EX32(simd_data(desc), VDATA, VTA);
}
+static inline uint32_t vext_vta_all_1s(uint32_t desc)
+{
+ return FIELD_EX32(simd_data(desc), VDATA, VTA_ALL_1S);
+}
+
/*
* Get the maximum number of elements can be operated.
*
@@ -838,10 +843,12 @@ RVVCALL(OPIVX2, vrsub_vx_d, OP_SSS_D, H8, H8, DO_RSUB)
static void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2,
CPURISCVState *env, uint32_t desc,
- opivx2_fn fn)
+ opivx2_fn fn, uint32_t esz)
{
uint32_t vm = vext_vm(desc);
uint32_t vl = env->vl;
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+ uint32_t vta = vext_vta(desc);
uint32_t i;
for (i = env->vstart; i < vl; i++) {
@@ -851,30 +858,32 @@ static void do_vext_vx(void *vd, void *v0, target_long
s1, void *vs2,
fn(vd, s1, vs2, i);
}
env->vstart = 0;
+ /* set tail elements to 1s */
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz);
}
/* generate the helpers for OPIVX */
-#define GEN_VEXT_VX(NAME) \
+#define GEN_VEXT_VX(NAME, ESZ) \
void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
void *vs2, CPURISCVState *env, \
uint32_t desc) \
{ \
do_vext_vx(vd, v0, s1, vs2, env, desc, \
- do_##NAME); \
-}
-
-GEN_VEXT_VX(vadd_vx_b)
-GEN_VEXT_VX(vadd_vx_h)
-GEN_VEXT_VX(vadd_vx_w)
-GEN_VEXT_VX(vadd_vx_d)
-GEN_VEXT_VX(vsub_vx_b)
-GEN_VEXT_VX(vsub_vx_h)
-GEN_VEXT_VX(vsub_vx_w)
-GEN_VEXT_VX(vsub_vx_d)
-GEN_VEXT_VX(vrsub_vx_b)
-GEN_VEXT_VX(vrsub_vx_h)
-GEN_VEXT_VX(vrsub_vx_w)
-GEN_VEXT_VX(vrsub_vx_d)
+ do_##NAME, ESZ); \
+}
+
+GEN_VEXT_VX(vadd_vx_b, 1)
+GEN_VEXT_VX(vadd_vx_h, 2)
+GEN_VEXT_VX(vadd_vx_w, 4)
+GEN_VEXT_VX(vadd_vx_d, 8)
+GEN_VEXT_VX(vsub_vx_b, 1)
+GEN_VEXT_VX(vsub_vx_h, 2)
+GEN_VEXT_VX(vsub_vx_w, 4)
+GEN_VEXT_VX(vsub_vx_d, 8)
+GEN_VEXT_VX(vrsub_vx_b, 1)
+GEN_VEXT_VX(vrsub_vx_h, 2)
+GEN_VEXT_VX(vrsub_vx_w, 4)
+GEN_VEXT_VX(vrsub_vx_d, 8)
void HELPER(vec_rsubs8)(void *d, void *a, uint64_t b, uint32_t desc)
{
@@ -1002,30 +1011,30 @@ 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)
-GEN_VEXT_VX(vwaddu_vx_h)
-GEN_VEXT_VX(vwaddu_vx_w)
-GEN_VEXT_VX(vwsubu_vx_b)
-GEN_VEXT_VX(vwsubu_vx_h)
-GEN_VEXT_VX(vwsubu_vx_w)
-GEN_VEXT_VX(vwadd_vx_b)
-GEN_VEXT_VX(vwadd_vx_h)
-GEN_VEXT_VX(vwadd_vx_w)
-GEN_VEXT_VX(vwsub_vx_b)
-GEN_VEXT_VX(vwsub_vx_h)
-GEN_VEXT_VX(vwsub_vx_w)
-GEN_VEXT_VX(vwaddu_wx_b)
-GEN_VEXT_VX(vwaddu_wx_h)
-GEN_VEXT_VX(vwaddu_wx_w)
-GEN_VEXT_VX(vwsubu_wx_b)
-GEN_VEXT_VX(vwsubu_wx_h)
-GEN_VEXT_VX(vwsubu_wx_w)
-GEN_VEXT_VX(vwadd_wx_b)
-GEN_VEXT_VX(vwadd_wx_h)
-GEN_VEXT_VX(vwadd_wx_w)
-GEN_VEXT_VX(vwsub_wx_b)
-GEN_VEXT_VX(vwsub_wx_h)
-GEN_VEXT_VX(vwsub_wx_w)
+GEN_VEXT_VX(vwaddu_vx_b, 2)
+GEN_VEXT_VX(vwaddu_vx_h, 4)
+GEN_VEXT_VX(vwaddu_vx_w, 8)
+GEN_VEXT_VX(vwsubu_vx_b, 2)
+GEN_VEXT_VX(vwsubu_vx_h, 4)
+GEN_VEXT_VX(vwsubu_vx_w, 8)
+GEN_VEXT_VX(vwadd_vx_b, 2)
+GEN_VEXT_VX(vwadd_vx_h, 4)
+GEN_VEXT_VX(vwadd_vx_w, 8)
+GEN_VEXT_VX(vwsub_vx_b, 2)
+GEN_VEXT_VX(vwsub_vx_h, 4)
+GEN_VEXT_VX(vwsub_vx_w, 8)
+GEN_VEXT_VX(vwaddu_wx_b, 2)
+GEN_VEXT_VX(vwaddu_wx_h, 4)
+GEN_VEXT_VX(vwaddu_wx_w, 8)
+GEN_VEXT_VX(vwsubu_wx_b, 2)
+GEN_VEXT_VX(vwsubu_wx_h, 4)
+GEN_VEXT_VX(vwsubu_wx_w, 8)
+GEN_VEXT_VX(vwadd_wx_b, 2)
+GEN_VEXT_VX(vwadd_wx_h, 4)
+GEN_VEXT_VX(vwadd_wx_w, 8)
+GEN_VEXT_VX(vwsub_wx_b, 2)
+GEN_VEXT_VX(vwsub_wx_h, 4)
+GEN_VEXT_VX(vwsub_wx_w, 8)
/* Vector Integer Add-with-Carry / Subtract-with-Borrow Instructions */
#define DO_VADC(N, M, C) (N + M + C)
@@ -1036,6 +1045,10 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void
*vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = \
+ vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -1046,6 +1059,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void
*vs2, \
*((ETYPE *)vd + H(i)) = DO_OP(s2, s1, carry); \
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VEXT_VADC_VVM(vadc_vvm_b, uint8_t, H1, DO_VADC)
@@ -1063,6 +1078,9 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,
void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
uint32_t vl = env->vl; \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
+ uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -1072,6 +1090,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,
void *vs2, \
*((ETYPE *)vd + H(i)) = DO_OP(s2, (ETYPE)(target_long)s1, carry);\
} \
env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VEXT_VADC_VXM(vadc_vxm_b, uint8_t, H1, DO_VADC)
@@ -1094,6 +1114,10 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void
*vs2, \
{ \
uint32_t vl = env->vl; \
uint32_t vm = vext_vm(desc); \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = \
+ vext_get_total_elems(env, desc, esz); \
+ uint32_t vta_all_1s = vext_vta_all_1s(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -1103,6 +1127,13 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void
*vs2, \
vext_set_elem_mask(vd, i, DO_OP(s2, s1, carry)); \
} \
env->vstart = 0; \
+ /* mask destination register are always tail-agnostic */ \
+ /* set tail elements to 1s */ \
+ if (vta_all_1s) { \
+ for (; i < total_elems; i++) { \
+ vext_set_elem_mask(vd, i, 1); \
+ } \
+ } \
}
GEN_VEXT_VMADC_VVM(vmadc_vvm_b, uint8_t, H1, DO_MADC)
@@ -1121,6 +1152,9 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,
\
{ \
uint32_t vl = env->vl; \
uint32_t vm = vext_vm(desc); \
+ uint32_t esz = sizeof(ETYPE); \
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz);\
+ uint32_t vta_all_1s = vext_vta_all_1s(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -1130,6 +1164,13 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,
\
DO_OP(s2, (ETYPE)(target_long)s1, carry)); \
} \
env->vstart = 0; \
+ /* mask destination register are always tail-agnostic */ \
+ /* set tail elements to 1s */ \
+ if (vta_all_1s) { \
+ for (; i < total_elems; i++) { \
+ vext_set_elem_mask(vd, i, 1); \
+ } \
+ } \
}
GEN_VEXT_VMADC_VXM(vmadc_vxm_b, uint8_t, H1, DO_MADC)
@@ -1180,18 +1221,18 @@ RVVCALL(OPIVX2, vxor_vx_b, OP_SSS_B, H1, H1, DO_XOR)
RVVCALL(OPIVX2, vxor_vx_h, OP_SSS_H, H2, H2, DO_XOR)
RVVCALL(OPIVX2, vxor_vx_w, OP_SSS_W, H4, H4, DO_XOR)
RVVCALL(OPIVX2, vxor_vx_d, OP_SSS_D, H8, H8, DO_XOR)
-GEN_VEXT_VX(vand_vx_b)
-GEN_VEXT_VX(vand_vx_h)
-GEN_VEXT_VX(vand_vx_w)
-GEN_VEXT_VX(vand_vx_d)
-GEN_VEXT_VX(vor_vx_b)
-GEN_VEXT_VX(vor_vx_h)
-GEN_VEXT_VX(vor_vx_w)
-GEN_VEXT_VX(vor_vx_d)
-GEN_VEXT_VX(vxor_vx_b)
-GEN_VEXT_VX(vxor_vx_h)
-GEN_VEXT_VX(vxor_vx_w)
-GEN_VEXT_VX(vxor_vx_d)
+GEN_VEXT_VX(vand_vx_b, 1)
+GEN_VEXT_VX(vand_vx_h, 2)
+GEN_VEXT_VX(vand_vx_w, 4)
+GEN_VEXT_VX(vand_vx_d, 8)
+GEN_VEXT_VX(vor_vx_b, 1)
+GEN_VEXT_VX(vor_vx_h, 2)
+GEN_VEXT_VX(vor_vx_w, 4)
+GEN_VEXT_VX(vor_vx_d, 8)
+GEN_VEXT_VX(vxor_vx_b, 1)
+GEN_VEXT_VX(vxor_vx_h, 2)
+GEN_VEXT_VX(vxor_vx_w, 4)
+GEN_VEXT_VX(vxor_vx_d, 8)
/* Vector Single-Width Bit Shift Instructions */
#define DO_SLL(N, M) (N << (M))
@@ -1445,22 +1486,22 @@ RVVCALL(OPIVX2, vmax_vx_b, OP_SSS_B, H1, H1, DO_MAX)
RVVCALL(OPIVX2, vmax_vx_h, OP_SSS_H, H2, H2, DO_MAX)
RVVCALL(OPIVX2, vmax_vx_w, OP_SSS_W, H4, H4, DO_MAX)
RVVCALL(OPIVX2, vmax_vx_d, OP_SSS_D, H8, H8, DO_MAX)
-GEN_VEXT_VX(vminu_vx_b)
-GEN_VEXT_VX(vminu_vx_h)
-GEN_VEXT_VX(vminu_vx_w)
-GEN_VEXT_VX(vminu_vx_d)
-GEN_VEXT_VX(vmin_vx_b)
-GEN_VEXT_VX(vmin_vx_h)
-GEN_VEXT_VX(vmin_vx_w)
-GEN_VEXT_VX(vmin_vx_d)
-GEN_VEXT_VX(vmaxu_vx_b)
-GEN_VEXT_VX(vmaxu_vx_h)
-GEN_VEXT_VX(vmaxu_vx_w)
-GEN_VEXT_VX(vmaxu_vx_d)
-GEN_VEXT_VX(vmax_vx_b)
-GEN_VEXT_VX(vmax_vx_h)
-GEN_VEXT_VX(vmax_vx_w)
-GEN_VEXT_VX(vmax_vx_d)
+GEN_VEXT_VX(vminu_vx_b, 1)
+GEN_VEXT_VX(vminu_vx_h, 2)
+GEN_VEXT_VX(vminu_vx_w, 4)
+GEN_VEXT_VX(vminu_vx_d, 8)
+GEN_VEXT_VX(vmin_vx_b, 1)
+GEN_VEXT_VX(vmin_vx_h, 2)
+GEN_VEXT_VX(vmin_vx_w, 4)
+GEN_VEXT_VX(vmin_vx_d, 8)
+GEN_VEXT_VX(vmaxu_vx_b, 1)
+GEN_VEXT_VX(vmaxu_vx_h, 2)
+GEN_VEXT_VX(vmaxu_vx_w, 4)
+GEN_VEXT_VX(vmaxu_vx_d, 8)
+GEN_VEXT_VX(vmax_vx_b, 1)
+GEN_VEXT_VX(vmax_vx_h, 2)
+GEN_VEXT_VX(vmax_vx_w, 4)
+GEN_VEXT_VX(vmax_vx_d, 8)
/* Vector Single-Width Integer Multiply Instructions */
#define DO_MUL(N, M) (N * M)
@@ -1604,22 +1645,22 @@ RVVCALL(OPIVX2, vmulhsu_vx_b, OP_SUS_B, H1, H1,
do_mulhsu_b)
RVVCALL(OPIVX2, vmulhsu_vx_h, OP_SUS_H, H2, H2, do_mulhsu_h)
RVVCALL(OPIVX2, vmulhsu_vx_w, OP_SUS_W, H4, H4, do_mulhsu_w)
RVVCALL(OPIVX2, vmulhsu_vx_d, OP_SUS_D, H8, H8, do_mulhsu_d)
-GEN_VEXT_VX(vmul_vx_b)
-GEN_VEXT_VX(vmul_vx_h)
-GEN_VEXT_VX(vmul_vx_w)
-GEN_VEXT_VX(vmul_vx_d)
-GEN_VEXT_VX(vmulh_vx_b)
-GEN_VEXT_VX(vmulh_vx_h)
-GEN_VEXT_VX(vmulh_vx_w)
-GEN_VEXT_VX(vmulh_vx_d)
-GEN_VEXT_VX(vmulhu_vx_b)
-GEN_VEXT_VX(vmulhu_vx_h)
-GEN_VEXT_VX(vmulhu_vx_w)
-GEN_VEXT_VX(vmulhu_vx_d)
-GEN_VEXT_VX(vmulhsu_vx_b)
-GEN_VEXT_VX(vmulhsu_vx_h)
-GEN_VEXT_VX(vmulhsu_vx_w)
-GEN_VEXT_VX(vmulhsu_vx_d)
+GEN_VEXT_VX(vmul_vx_b, 1)
+GEN_VEXT_VX(vmul_vx_h, 2)
+GEN_VEXT_VX(vmul_vx_w, 4)
+GEN_VEXT_VX(vmul_vx_d, 8)
+GEN_VEXT_VX(vmulh_vx_b, 1)
+GEN_VEXT_VX(vmulh_vx_h, 2)
+GEN_VEXT_VX(vmulh_vx_w, 4)
+GEN_VEXT_VX(vmulh_vx_d, 8)
+GEN_VEXT_VX(vmulhu_vx_b, 1)
+GEN_VEXT_VX(vmulhu_vx_h, 2)
+GEN_VEXT_VX(vmulhu_vx_w, 4)
+GEN_VEXT_VX(vmulhu_vx_d, 8)
+GEN_VEXT_VX(vmulhsu_vx_b, 1)
+GEN_VEXT_VX(vmulhsu_vx_h, 2)
+GEN_VEXT_VX(vmulhsu_vx_w, 4)
+GEN_VEXT_VX(vmulhsu_vx_d, 8)
/* Vector Integer Divide Instructions */
#define DO_DIVU(N, M) (unlikely(M == 0) ? (__typeof(N))(-1) : N / M)
@@ -1678,22 +1719,22 @@ RVVCALL(OPIVX2, vrem_vx_b, OP_SSS_B, H1, H1, DO_REM)
RVVCALL(OPIVX2, vrem_vx_h, OP_SSS_H, H2, H2, DO_REM)
RVVCALL(OPIVX2, vrem_vx_w, OP_SSS_W, H4, H4, DO_REM)
RVVCALL(OPIVX2, vrem_vx_d, OP_SSS_D, H8, H8, DO_REM)
-GEN_VEXT_VX(vdivu_vx_b)
-GEN_VEXT_VX(vdivu_vx_h)
-GEN_VEXT_VX(vdivu_vx_w)
-GEN_VEXT_VX(vdivu_vx_d)
-GEN_VEXT_VX(vdiv_vx_b)
-GEN_VEXT_VX(vdiv_vx_h)
-GEN_VEXT_VX(vdiv_vx_w)
-GEN_VEXT_VX(vdiv_vx_d)
-GEN_VEXT_VX(vremu_vx_b)
-GEN_VEXT_VX(vremu_vx_h)
-GEN_VEXT_VX(vremu_vx_w)
-GEN_VEXT_VX(vremu_vx_d)
-GEN_VEXT_VX(vrem_vx_b)
-GEN_VEXT_VX(vrem_vx_h)
-GEN_VEXT_VX(vrem_vx_w)
-GEN_VEXT_VX(vrem_vx_d)
+GEN_VEXT_VX(vdivu_vx_b, 1)
+GEN_VEXT_VX(vdivu_vx_h, 2)
+GEN_VEXT_VX(vdivu_vx_w, 4)
+GEN_VEXT_VX(vdivu_vx_d, 8)
+GEN_VEXT_VX(vdiv_vx_b, 1)
+GEN_VEXT_VX(vdiv_vx_h, 2)
+GEN_VEXT_VX(vdiv_vx_w, 4)
+GEN_VEXT_VX(vdiv_vx_d, 8)
+GEN_VEXT_VX(vremu_vx_b, 1)
+GEN_VEXT_VX(vremu_vx_h, 2)
+GEN_VEXT_VX(vremu_vx_w, 4)
+GEN_VEXT_VX(vremu_vx_d, 8)
+GEN_VEXT_VX(vrem_vx_b, 1)
+GEN_VEXT_VX(vrem_vx_h, 2)
+GEN_VEXT_VX(vrem_vx_w, 4)
+GEN_VEXT_VX(vrem_vx_d, 8)
/* Vector Widening Integer Multiply Instructions */
RVVCALL(OPIVV2, vwmul_vv_b, WOP_SSS_B, H2, H1, H1, DO_MUL)
@@ -1724,15 +1765,15 @@ RVVCALL(OPIVX2, vwmulu_vx_w, WOP_UUU_W, H8, H4, DO_MUL)
RVVCALL(OPIVX2, vwmulsu_vx_b, WOP_SUS_B, H2, H1, DO_MUL)
RVVCALL(OPIVX2, vwmulsu_vx_h, WOP_SUS_H, H4, H2, DO_MUL)
RVVCALL(OPIVX2, vwmulsu_vx_w, WOP_SUS_W, H8, H4, DO_MUL)
-GEN_VEXT_VX(vwmul_vx_b)
-GEN_VEXT_VX(vwmul_vx_h)
-GEN_VEXT_VX(vwmul_vx_w)
-GEN_VEXT_VX(vwmulu_vx_b)
-GEN_VEXT_VX(vwmulu_vx_h)
-GEN_VEXT_VX(vwmulu_vx_w)
-GEN_VEXT_VX(vwmulsu_vx_b)
-GEN_VEXT_VX(vwmulsu_vx_h)
-GEN_VEXT_VX(vwmulsu_vx_w)
+GEN_VEXT_VX(vwmul_vx_b, 2)
+GEN_VEXT_VX(vwmul_vx_h, 4)
+GEN_VEXT_VX(vwmul_vx_w, 8)
+GEN_VEXT_VX(vwmulu_vx_b, 2)
+GEN_VEXT_VX(vwmulu_vx_h, 4)
+GEN_VEXT_VX(vwmulu_vx_w, 8)
+GEN_VEXT_VX(vwmulsu_vx_b, 2)
+GEN_VEXT_VX(vwmulsu_vx_h, 4)
+GEN_VEXT_VX(vwmulsu_vx_w, 8)
/* Vector Single-Width Integer Multiply-Add Instructions */
#define OPIVV3(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP) \
@@ -1805,22 +1846,22 @@ RVVCALL(OPIVX3, vnmsub_vx_b, OP_SSS_B, H1, H1, DO_NMSUB)
RVVCALL(OPIVX3, vnmsub_vx_h, OP_SSS_H, H2, H2, DO_NMSUB)
RVVCALL(OPIVX3, vnmsub_vx_w, OP_SSS_W, H4, H4, DO_NMSUB)
RVVCALL(OPIVX3, vnmsub_vx_d, OP_SSS_D, H8, H8, DO_NMSUB)
-GEN_VEXT_VX(vmacc_vx_b)
-GEN_VEXT_VX(vmacc_vx_h)
-GEN_VEXT_VX(vmacc_vx_w)
-GEN_VEXT_VX(vmacc_vx_d)
-GEN_VEXT_VX(vnmsac_vx_b)
-GEN_VEXT_VX(vnmsac_vx_h)
-GEN_VEXT_VX(vnmsac_vx_w)
-GEN_VEXT_VX(vnmsac_vx_d)
-GEN_VEXT_VX(vmadd_vx_b)
-GEN_VEXT_VX(vmadd_vx_h)
-GEN_VEXT_VX(vmadd_vx_w)
-GEN_VEXT_VX(vmadd_vx_d)
-GEN_VEXT_VX(vnmsub_vx_b)
-GEN_VEXT_VX(vnmsub_vx_h)
-GEN_VEXT_VX(vnmsub_vx_w)
-GEN_VEXT_VX(vnmsub_vx_d)
+GEN_VEXT_VX(vmacc_vx_b, 1)
+GEN_VEXT_VX(vmacc_vx_h, 2)
+GEN_VEXT_VX(vmacc_vx_w, 4)
+GEN_VEXT_VX(vmacc_vx_d, 8)
+GEN_VEXT_VX(vnmsac_vx_b, 1)
+GEN_VEXT_VX(vnmsac_vx_h, 2)
+GEN_VEXT_VX(vnmsac_vx_w, 4)
+GEN_VEXT_VX(vnmsac_vx_d, 8)
+GEN_VEXT_VX(vmadd_vx_b, 1)
+GEN_VEXT_VX(vmadd_vx_h, 2)
+GEN_VEXT_VX(vmadd_vx_w, 4)
+GEN_VEXT_VX(vmadd_vx_d, 8)
+GEN_VEXT_VX(vnmsub_vx_b, 1)
+GEN_VEXT_VX(vnmsub_vx_h, 2)
+GEN_VEXT_VX(vnmsub_vx_w, 4)
+GEN_VEXT_VX(vnmsub_vx_d, 8)
/* Vector Widening Integer Multiply-Add Instructions */
RVVCALL(OPIVV3, vwmaccu_vv_b, WOP_UUU_B, H2, H1, H1, DO_MACC)
@@ -1854,18 +1895,18 @@ RVVCALL(OPIVX3, vwmaccsu_vx_w, WOP_SSU_W, H8, H4,
DO_MACC)
RVVCALL(OPIVX3, vwmaccus_vx_b, WOP_SUS_B, H2, H1, DO_MACC)
RVVCALL(OPIVX3, vwmaccus_vx_h, WOP_SUS_H, H4, H2, DO_MACC)
RVVCALL(OPIVX3, vwmaccus_vx_w, WOP_SUS_W, H8, H4, DO_MACC)
-GEN_VEXT_VX(vwmaccu_vx_b)
-GEN_VEXT_VX(vwmaccu_vx_h)
-GEN_VEXT_VX(vwmaccu_vx_w)
-GEN_VEXT_VX(vwmacc_vx_b)
-GEN_VEXT_VX(vwmacc_vx_h)
-GEN_VEXT_VX(vwmacc_vx_w)
-GEN_VEXT_VX(vwmaccsu_vx_b)
-GEN_VEXT_VX(vwmaccsu_vx_h)
-GEN_VEXT_VX(vwmaccsu_vx_w)
-GEN_VEXT_VX(vwmaccus_vx_b)
-GEN_VEXT_VX(vwmaccus_vx_h)
-GEN_VEXT_VX(vwmaccus_vx_w)
+GEN_VEXT_VX(vwmaccu_vx_b, 2)
+GEN_VEXT_VX(vwmaccu_vx_h, 4)
+GEN_VEXT_VX(vwmaccu_vx_w, 8)
+GEN_VEXT_VX(vwmacc_vx_b, 2)
+GEN_VEXT_VX(vwmacc_vx_h, 4)
+GEN_VEXT_VX(vwmacc_vx_w, 8)
+GEN_VEXT_VX(vwmaccsu_vx_b, 2)
+GEN_VEXT_VX(vwmaccsu_vx_h, 4)
+GEN_VEXT_VX(vwmaccsu_vx_w, 8)
+GEN_VEXT_VX(vwmaccus_vx_b, 2)
+GEN_VEXT_VX(vwmaccus_vx_h, 4)
+GEN_VEXT_VX(vwmaccus_vx_w, 8)
/* Vector Integer Merge and Move Instructions */
#define GEN_VEXT_VMV_VV(NAME, ETYPE, H) \
--
2.34.2
