target/riscv: rvv: Add tail agnostic for vx, vvm, vxm instructions

`vmadc` and `vmsbc` produces a mask value, they always operate with
a tail agnostic policy.

Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <165449614532.19704.7000832880482980398-7@git.sr.ht>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>

3 files changed, 190 insertions, 142 deletions

diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index cd73fd6..22edf62 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -1293,6 +1293,8 @@ 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));
 
@@ -1328,7 +1330,7 @@ do_opivx_gvec(DisasContext *s, arg_rmrr *a, GVecGen2sFn *gvec_fn,
         return false;
     }
 
-    if (a->vm && s->vl_eq_vlmax) {
+    if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
         TCGv_i64 src1 = tcg_temp_new_i64();
 
         tcg_gen_ext_tl_i64(src1, get_gpr(s, a->rs1, EXT_SIGN));
@@ -1458,6 +1460,8 @@ 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));
 
@@ -1486,7 +1490,7 @@ do_opivi_gvec(DisasContext *s, arg_rmrr *a, GVecGen2iFn *gvec_fn,
         return false;
     }
 
-    if (a->vm && s->vl_eq_vlmax) {
+    if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
         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);
@@ -1540,6 +1544,7 @@ 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),
@@ -1621,6 +1626,7 @@ 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),
@@ -1699,6 +1705,9 @@ 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 512c6c3..193ce57 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/vector_helper.c b/target/riscv/vector_helper.c
index ee28e1b..7cdb5d1 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.
  *
@@ -867,10 +872,12 @@ 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++) {
@@ -880,30 +887,32 @@ 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)
 {
@@ -1031,30 +1040,30 @@ 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)
@@ -1065,6 +1074,10 @@ 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++) {                      \
@@ -1075,6 +1088,8 @@ 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)
@@ -1092,6 +1107,9 @@ 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++) {                                 \
@@ -1101,6 +1119,8 @@ 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)
@@ -1123,6 +1143,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2,   \
 {                                                             \
     uint32_t vl = env->vl;                                    \
     uint32_t vm = vext_vm(desc);                              \
+    uint32_t total_elems = env_archcpu(env)->cfg.vlen;        \
+    uint32_t vta_all_1s = vext_vta_all_1s(desc);              \
     uint32_t i;                                               \
                                                               \
     for (i = env->vstart; i < vl; i++) {                      \
@@ -1132,6 +1154,13 @@ 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)
@@ -1150,6 +1179,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,          \
 {                                                               \
     uint32_t vl = env->vl;                                      \
     uint32_t vm = vext_vm(desc);                                \
+    uint32_t total_elems = env_archcpu(env)->cfg.vlen;          \
+    uint32_t vta_all_1s = vext_vta_all_1s(desc);                \
     uint32_t i;                                                 \
                                                                 \
     for (i = env->vstart; i < vl; i++) {                        \
@@ -1159,6 +1190,13 @@ 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)
@@ -1209,18 +1247,18 @@ 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))
@@ -1474,22 +1512,22 @@ 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)
@@ -1633,22 +1671,22 @@ 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)
@@ -1707,22 +1745,22 @@ 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)
@@ -1753,15 +1791,15 @@ 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)   \
@@ -1834,22 +1872,22 @@ 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)
@@ -1883,18 +1921,18 @@ 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)                              \