diff --git a/target/riscv/insn_trans/trans_rvv.c.inc
b/target/riscv/insn_trans/trans_rvv.c.inc
index 18ef9949ad..d853f9f2c4 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -3988,6 +3988,7 @@ static bool int_ext_op(DisasContext *s, arg_rmr *a,
uint8_t seq)
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, VMA, s->vma);
tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),
vreg_ofs(s, a->rs2), cpu_env,
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 8f95e286e8..01a3317ee8 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -5020,11 +5020,14 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,
void *vs2, \
uint32_t esz = sizeof(ETYPE); \
uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
uint32_t vta = vext_vta(desc); \
+ uint32_t vma = vext_vma(desc); \
target_ulong offset = s1, i_min, i; \
\
i_min = MAX(env->vstart, offset); \
for (i = i_min; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
+ /* set masked-off elements to 1s */ \
+ vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz); \
continue; \
} \
*((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(i - offset)); \
@@ -5049,13 +5052,17 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,
void *vs2, \
uint32_t esz = sizeof(ETYPE); \
uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
uint32_t vta = vext_vta(desc); \
+ uint32_t vma = vext_vma(desc); \
target_ulong i_max, i; \
\
i_max = MAX(MIN(s1 < vlmax ? vlmax - s1 : 0, vl), env->vstart); \
for (i = env->vstart; i < i_max; ++i) { \
- if (vm || vext_elem_mask(v0, i)) { \
- *((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(i + s1)); \
+ if (!vm && !vext_elem_mask(v0, i)) { \
+ /* set masked-off elements to 1s */ \
+ vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz); \
+ continue; \
} \
+ *((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(i + s1)); \
} \
\
for (i = i_max; i < vl; ++i) { \
@@ -5085,10 +5092,13 @@ static void vslide1up_##BITWIDTH(void *vd, void *v0,
target_ulong s1, \
uint32_t esz = sizeof(ETYPE); \
uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
uint32_t vta = vext_vta(desc); \
+ uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
+ /* set masked-off elements to 1s */ \
+ vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz); \
continue; \
} \
if (i == 0) { \
@@ -5130,10 +5140,13 @@ static void vslide1down_##BITWIDTH(void *vd, void *v0,
target_ulong s1, \
uint32_t esz = sizeof(ETYPE);
\
uint32_t total_elems = vext_get_total_elems(env, desc, esz);
\
uint32_t vta = vext_vta(desc);
\
+ uint32_t vma = vext_vma(desc); \
uint32_t i;
\
\
for (i = env->vstart; i < vl; i++) {
\
if (!vm && !vext_elem_mask(v0, i)) {
\
+ /* set masked-off elements to 1s */ \
+ vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz); \
continue;
\
}
\
if (i == vl - 1) {
\
@@ -5201,11 +5214,14 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void
*vs2, \
uint32_t esz = sizeof(TS2); \
uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
uint32_t vta = vext_vta(desc); \
+ uint32_t vma = vext_vma(desc); \
uint64_t index; \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
+ /* set masked-off elements to 1s */ \
+ vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz); \
continue; \
} \
index = *((TS1 *)vs1 + HS1(i)); \
@@ -5241,11 +5257,14 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,
void *vs2, \
uint32_t esz = sizeof(ETYPE); \
uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
uint32_t vta = vext_vta(desc); \
+ uint32_t vma = vext_vma(desc); \
uint64_t index = s1; \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
+ /* set masked-off elements to 1s */ \
+ vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz); \
continue; \
} \
if (index >= vlmax) { \
@@ -5320,10 +5339,13 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2,
\
uint32_t esz = sizeof(ETYPE); \
uint32_t total_elems = vext_get_total_elems(env, desc, esz); \
uint32_t vta = vext_vta(desc); \
+ uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
+ /* set masked-off elements to 1s */ \
+ vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz); \
continue; \
} \
*((ETYPE *)vd + HD(i)) = *((DTYPE *)vs2 + HS1(i)); \