[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH v8 04/10] target/riscv/vector_helper.c: update tail with vext_set
|
From: |
Daniel Henrique Barboza |
|
Subject: |
[PATCH v8 04/10] target/riscv/vector_helper.c: update tail with vext_set_tail_elems_1s() |
|
Date: |
Fri, 8 Mar 2024 18:53:44 -0300 |
Change all code that updates tail elems to use vext_set_tail_elems_1s()
instead of vext_set_elems_1s().
Setting 'env->vstart=0' needs to be the very last thing a helper does
because env->vstart is being checked by vext_set_tail_elems_1s().
A side effect of this change is that a lot of 'vta' local variables got
unused. The reason is that 'vta' was being fetched to be used with
vext_set_elems_1s() but vext_set_tail_elems_1s() doesn't use it - 'vta' is
retrieve inside the helper using 'desc'.
Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
---
target/riscv/vector_helper.c | 130 ++++++++++++++---------------------
1 file changed, 52 insertions(+), 78 deletions(-)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 544234c2d8..2f715fea5e 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -878,7 +878,6 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, 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 i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -888,9 +887,9 @@ 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); \
+ vext_set_tail_elems_1s(env, vd, desc, esz, total_elems); \
+ env->vstart = 0; \
}
GEN_VEXT_VADC_VVM(vadc_vvm_b, uint8_t, H1, DO_VADC)
@@ -910,7 +909,6 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void
*vs2, \
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++) { \
@@ -919,9 +917,9 @@ 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); \
+ vext_set_tail_elems_1s(env, vd, desc, esz, total_elems); \
+ env->vstart = 0; \
}
GEN_VEXT_VADC_VXM(vadc_vxm_b, uint8_t, H1, DO_VADC)
@@ -1078,7 +1076,6 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1,
\
uint32_t vl = env->vl; \
uint32_t esz = sizeof(TS1); \
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; \
\
@@ -1092,9 +1089,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1,
\
TS2 s2 = *((TS2 *)vs2 + HS2(i)); \
*((TS1 *)vd + HS1(i)) = OP(s2, s1 & MASK); \
} \
- env->vstart = 0; \
/* set tail elements to 1s */ \
- vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
+ vext_set_tail_elems_1s(env, vd, desc, esz, total_elems); \
+ env->vstart = 0; \
}
GEN_VEXT_SHIFT_VV(vsll_vv_b, uint8_t, uint8_t, H1, H1, DO_SLL, 0x7)
@@ -1125,7 +1122,6 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,
\
uint32_t esz = sizeof(TD); \
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; \
\
@@ -1139,9 +1135,9 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,
\
TS2 s2 = *((TS2 *)vs2 + HS2(i)); \
*((TD *)vd + HD(i)) = OP(s2, s1 & MASK); \
} \
- env->vstart = 0; \
/* set tail elements to 1s */ \
- vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz);\
+ vext_set_tail_elems_1s(env, vd, desc, esz, total_elems);\
+ env->vstart = 0; \
}
GEN_VEXT_SHIFT_VX(vsll_vx_b, uint8_t, int8_t, H1, H1, DO_SLL, 0x7)
@@ -1800,16 +1796,15 @@ void HELPER(NAME)(void *vd, void *vs1, CPURISCVState
*env, \
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++) { \
ETYPE s1 = *((ETYPE *)vs1 + H(i)); \
*((ETYPE *)vd + H(i)) = s1; \
} \
- env->vstart = 0; \
/* set tail elements to 1s */ \
- vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
+ vext_set_tail_elems_1s(env, vd, desc, esz, total_elems); \
+ env->vstart = 0; \
}
GEN_VEXT_VMV_VV(vmv_v_v_b, int8_t, H1)
@@ -1824,15 +1819,14 @@ void HELPER(NAME)(void *vd, uint64_t s1, CPURISCVState
*env, \
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++) { \
*((ETYPE *)vd + H(i)) = (ETYPE)s1; \
} \
- env->vstart = 0; \
/* set tail elements to 1s */ \
- vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
+ vext_set_tail_elems_1s(env, vd, desc, esz, total_elems); \
+ env->vstart = 0; \
}
GEN_VEXT_VMV_VX(vmv_v_x_b, int8_t, H1)
@@ -1847,16 +1841,15 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void
*vs2, \
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++) { \
ETYPE *vt = (!vext_elem_mask(v0, i) ? vs2 : vs1); \
*((ETYPE *)vd + H(i)) = *(vt + H(i)); \
} \
- env->vstart = 0; \
/* set tail elements to 1s */ \
- vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
+ vext_set_tail_elems_1s(env, vd, desc, esz, total_elems); \
+ env->vstart = 0; \
}
GEN_VEXT_VMERGE_VV(vmerge_vvm_b, int8_t, H1)
@@ -1871,7 +1864,6 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,
\
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++) { \
@@ -1880,9 +1872,9 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,
\
(ETYPE)(target_long)s1); \
*((ETYPE *)vd + H(i)) = d; \
} \
- env->vstart = 0; \
/* set tail elements to 1s */ \
- vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
+ vext_set_tail_elems_1s(env, vd, desc, esz, total_elems); \
+ env->vstart = 0; \
}
GEN_VEXT_VMERGE_VX(vmerge_vxm_b, int8_t, H1)
@@ -1938,7 +1930,6 @@ vext_vv_rm_2(void *vd, void *v0, void *vs1, void *vs2,
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 vma = vext_vma(desc);
switch (env->vxrm) {
@@ -1960,7 +1951,7 @@ vext_vv_rm_2(void *vd, void *v0, void *vs1, void *vs2,
break;
}
/* set tail elements to 1s */
- vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz);
+ vext_set_tail_elems_1s(env, vd, desc, esz, total_elems);
env->vstart = 0;
}
@@ -2063,7 +2054,6 @@ vext_vx_rm_2(void *vd, void *v0, target_long s1, void
*vs2,
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 vma = vext_vma(desc);
switch (env->vxrm) {
@@ -2085,7 +2075,7 @@ vext_vx_rm_2(void *vd, void *v0, target_long s1, void
*vs2,
break;
}
/* set tail elements to 1s */
- vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz);
+ vext_set_tail_elems_1s(env, vd, desc, esz, total_elems);
env->vstart = 0;
}
@@ -2837,7 +2827,6 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1,
\
uint32_t vl = env->vl; \
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; \
\
@@ -2850,10 +2839,10 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1,
\
} \
do_##NAME(vd, vs1, vs2, i, env); \
} \
- env->vstart = 0; \
/* set tail elements to 1s */ \
- vext_set_elems_1s(vd, vta, vl * ESZ, \
- total_elems * ESZ); \
+ vext_set_tail_elems_1s(env, vd, desc, ESZ, \
+ total_elems); \
+ env->vstart = 0; \
}
RVVCALL(OPFVV2, vfadd_vv_h, OP_UUU_H, H2, H2, H2, float16_add)
@@ -2880,7 +2869,6 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1,
\
uint32_t vl = env->vl; \
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; \
\
@@ -2893,10 +2881,10 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1,
\
} \
do_##NAME(vd, s1, vs2, i, env); \
} \
- env->vstart = 0; \
/* set tail elements to 1s */ \
- vext_set_elems_1s(vd, vta, vl * ESZ, \
- total_elems * ESZ); \
+ vext_set_tail_elems_1s(env, vd, desc, ESZ, \
+ total_elems); \
+ env->vstart = 0; \
}
RVVCALL(OPFVF2, vfadd_vf_h, OP_UUU_H, H2, H2, float16_add)
@@ -3466,7 +3454,6 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \
uint32_t vl = env->vl; \
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; \
\
@@ -3482,9 +3469,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \
} \
do_##NAME(vd, vs2, i, env); \
} \
+ vext_set_tail_elems_1s(env, vd, desc, ESZ, \
+ total_elems); \
env->vstart = 0; \
- vext_set_elems_1s(vd, vta, vl * ESZ, \
- total_elems * ESZ); \
}
RVVCALL(OPFVV1, vfsqrt_v_h, OP_UU_H, H2, H2, float16_sqrt)
@@ -4221,7 +4208,6 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t 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 i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -4229,9 +4215,9 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void
*vs2, \
*((ETYPE *)vd + H(i)) = \
(!vm && !vext_elem_mask(v0, i) ? s2 : s1); \
} \
- env->vstart = 0; \
/* set tail elements to 1s */ \
- vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
+ vext_set_tail_elems_1s(env, vd, desc, esz, total_elems); \
+ env->vstart = 0; \
}
GEN_VFMERGE_VF(vfmerge_vfm_h, int16_t, H2)
@@ -4386,7 +4372,6 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1,
\
uint32_t vl = env->vl; \
uint32_t esz = sizeof(TD); \
uint32_t vlenb = simd_maxsz(desc); \
- uint32_t vta = vext_vta(desc); \
uint32_t i; \
TD s1 = *((TD *)vs1 + HD(0)); \
\
@@ -4398,9 +4383,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1,
\
s1 = OP(s1, (TD)s2); \
} \
*((TD *)vd + HD(0)) = s1; \
- env->vstart = 0; \
/* set tail elements to 1s */ \
- vext_set_elems_1s(vd, vta, esz, vlenb); \
+ vext_set_tail_elems_1s(env, vd, desc, esz, vlenb); \
+ env->vstart = 0; \
}
/* vd[0] = sum(vs1[0], vs2[*]) */
@@ -4472,7 +4457,6 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1,
\
uint32_t vl = env->vl; \
uint32_t esz = sizeof(TD); \
uint32_t vlenb = simd_maxsz(desc); \
- uint32_t vta = vext_vta(desc); \
uint32_t i; \
TD s1 = *((TD *)vs1 + HD(0)); \
\
@@ -4484,9 +4468,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1,
\
s1 = OP(s1, (TD)s2, &env->fp_status); \
} \
*((TD *)vd + HD(0)) = s1; \
- env->vstart = 0; \
/* set tail elements to 1s */ \
- vext_set_elems_1s(vd, vta, esz, vlenb); \
+ vext_set_tail_elems_1s(env, vd, desc, esz, vlenb); \
+ env->vstart = 0; \
}
/* Unordered sum */
@@ -4703,7 +4687,6 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2,
CPURISCVState *env, \
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 vma = vext_vma(desc); \
uint32_t sum = 0; \
int i; \
@@ -4719,9 +4702,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2,
CPURISCVState *env, \
sum++; \
} \
} \
- env->vstart = 0; \
/* set tail elements to 1s */ \
- vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
+ vext_set_tail_elems_1s(env, vd, desc, esz, total_elems); \
+ env->vstart = 0; \
}
GEN_VEXT_VIOTA_M(viota_m_b, uint8_t, H1)
@@ -4737,7 +4720,6 @@ void HELPER(NAME)(void *vd, void *v0, 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 vma = vext_vma(desc); \
int i; \
\
@@ -4749,9 +4731,9 @@ void HELPER(NAME)(void *vd, void *v0, CPURISCVState *env,
uint32_t desc) \
} \
*((ETYPE *)vd + H(i)) = i; \
} \
- env->vstart = 0; \
/* set tail elements to 1s */ \
- vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
+ vext_set_tail_elems_1s(env, vd, desc, esz, total_elems); \
+ env->vstart = 0; \
}
GEN_VEXT_VID_V(vid_v_b, uint8_t, H1)
@@ -4772,7 +4754,6 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,
void *vs2, \
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 vma = vext_vma(desc); \
target_ulong offset = s1, i_min, i; \
\
@@ -4785,9 +4766,9 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,
void *vs2, \
} \
*((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(i - offset)); \
} \
- env->vstart = 0; \
/* set tail elements to 1s */ \
- vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
+ vext_set_tail_elems_1s(env, vd, desc, esz, total_elems); \
+ env->vstart = 0; \
}
/* vslideup.vx vd, vs2, rs1, vm # vd[i+rs1] = vs2[i] */
@@ -4805,7 +4786,6 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,
void *vs2, \
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 vma = vext_vma(desc); \
target_ulong i_max, i_min, i; \
\
@@ -4826,9 +4806,9 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,
void *vs2, \
} \
} \
\
- env->vstart = 0; \
/* set tail elements to 1s */ \
- vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
+ vext_set_tail_elems_1s(env, vd, desc, esz, total_elems); \
+ env->vstart = 0; \
}
/* vslidedown.vx vd, vs2, rs1, vm # vd[i] = vs2[i+rs1] */
@@ -4847,7 +4827,6 @@ static void vslide1up_##BITWIDTH(void *vd, void *v0,
uint64_t s1, \
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 vma = vext_vma(desc); \
uint32_t i; \
\
@@ -4863,9 +4842,9 @@ static void vslide1up_##BITWIDTH(void *vd, void *v0,
uint64_t s1, \
*((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(i - 1)); \
} \
} \
- env->vstart = 0; \
/* set tail elements to 1s */ \
- vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
+ vext_set_tail_elems_1s(env, vd, desc, esz, total_elems); \
+ env->vstart = 0; \
}
GEN_VEXT_VSLIE1UP(8, H1)
@@ -4896,7 +4875,6 @@ static void vslide1down_##BITWIDTH(void *vd, void *v0,
uint64_t s1, \
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 vma = vext_vma(desc); \
uint32_t i; \
\
@@ -4912,9 +4890,9 @@ static void vslide1down_##BITWIDTH(void *vd, void *v0,
uint64_t s1, \
*((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(i + 1)); \
} \
} \
- env->vstart = 0; \
/* set tail elements to 1s */ \
- vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
+ vext_set_tail_elems_1s(env, vd, desc, esz, total_elems); \
+ env->vstart = 0; \
}
GEN_VEXT_VSLIDE1DOWN(8, H1)
@@ -4970,7 +4948,6 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void
*vs2, \
uint32_t vl = env->vl; \
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; \
@@ -4988,9 +4965,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void
*vs2, \
*((TS2 *)vd + HS2(i)) = *((TS2 *)vs2 + HS2(index)); \
} \
} \
- env->vstart = 0; \
/* set tail elements to 1s */ \
- vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
+ vext_set_tail_elems_1s(env, vd, desc, esz, total_elems); \
+ env->vstart = 0; \
}
/* vd[i] = (vs1[i] >= VLMAX) ? 0 : vs2[vs1[i]]; */
@@ -5013,7 +4990,6 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,
void *vs2, \
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 vma = vext_vma(desc); \
uint64_t index = s1; \
uint32_t i; \
@@ -5030,9 +5006,9 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,
void *vs2, \
*((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(index)); \
} \
} \
- env->vstart = 0; \
/* set tail elements to 1s */ \
- vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
+ vext_set_tail_elems_1s(env, vd, desc, esz, total_elems); \
+ env->vstart = 0; \
}
/* vd[i] = (x[rs1] >= VLMAX) ? 0 : vs2[rs1] */
@@ -5049,7 +5025,6 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void
*vs2, \
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 num = 0, i; \
\
for (i = env->vstart; i < vl; i++) { \
@@ -5059,9 +5034,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void
*vs2, \
*((ETYPE *)vd + H(num)) = *((ETYPE *)vs2 + H(i)); \
num++; \
} \
- env->vstart = 0; \
/* set tail elements to 1s */ \
- vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
+ vext_set_tail_elems_1s(env, vd, desc, esz, total_elems); \
+ env->vstart = 0; \
}
/* Compress into vd elements of vs2 where vs1 is enabled */
@@ -5095,7 +5070,6 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2,
\
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 = vext_vta(desc); \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
@@ -5107,9 +5081,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2,
\
} \
*((ETYPE *)vd + HD(i)) = *((DTYPE *)vs2 + HS1(i)); \
} \
- env->vstart = 0; \
/* set tail elements to 1s */ \
- vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
+ vext_set_tail_elems_1s(env, vd, desc, esz, total_elems); \
+ env->vstart = 0; \
}
GEN_VEXT_INT_EXT(vzext_vf2_h, uint16_t, uint8_t, H2, H1)
--
2.43.2
- [PATCH v8 00/10] riscv: set vstart_eq_zero on mark_vs_dirty, Daniel Henrique Barboza, 2024/03/08
- [PATCH v8 02/10] target/riscv: handle vstart >= vl in vext_set_tail_elems_1s(), Daniel Henrique Barboza, 2024/03/08
- [PATCH v8 01/10] target/riscv/vector_helper.c: set vstart = 0 in GEN_VEXT_VSLIDEUP_VX(), Daniel Henrique Barboza, 2024/03/08
- [PATCH v8 03/10] target/riscv/vector_helper.c: do vstart=0 after updating tail, Daniel Henrique Barboza, 2024/03/08
- [PATCH v8 04/10] target/riscv/vector_helper.c: update tail with vext_set_tail_elems_1s(),
Daniel Henrique Barboza <=
- [PATCH v8 05/10] target/riscv: use vext_set_tail_elems_1s() in vcrypto insns, Daniel Henrique Barboza, 2024/03/08
- [PATCH v8 06/10] trans_rvv.c.inc: set vstart = 0 in int scalar move insns, Daniel Henrique Barboza, 2024/03/08
- [PATCH v8 07/10] target/riscv: remove 'over' brconds from vector trans, Daniel Henrique Barboza, 2024/03/08
- [PATCH v8 08/10] trans_rvv.c.inc: remove redundant mark_vs_dirty() calls, Daniel Henrique Barboza, 2024/03/08
- [PATCH v8 09/10] target/riscv: Clear vstart_qe_zero flag, Daniel Henrique Barboza, 2024/03/08
- [PATCH v8 10/10] target/riscv/vector_helper.c: optimize loops in ldst helpers, Daniel Henrique Barboza, 2024/03/08
- Re: [PATCH v8 00/10] riscv: set vstart_eq_zero on mark_vs_dirty, Richard Henderson, 2024/03/09