|
| From: | Max Chou |
| Subject: | Re: [PATCH for-9.0 v14 4/8] target/riscv/vector_helpers: do early exit when vstart >= vl |
| Date: | Thu, 14 Mar 2024 21:14:48 +0800 |
| User-agent: | Mozilla Thunderbird |
According v spec section 7.9. Vector Load/Store Whole Register Instructions
"The instructions operate with an effective vector length, evl=NFIELDS*VLEN/EEW, regardless of current settings in vtype and vl. The usual property that no elements are written if vstart ≥ vl does not apply to these instructions. Instead, no elements are written if vstart ≥ evl."
The VSTART_CHECK_EARLY_EXIT in vext_ldst_whole function may causes unexpected result. We may replace the VSTART_CHECK_EARLY_EXIT function by
- VSTART_CHECK_EARLY_EXIT(env); + if (env->vstart >= ((vlenb * nf) >> log2_esz)) { + env->vstart = 0; + return; + }
@@ -572,6 +580,8 @@ vext_ldst_whole(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
uint32_t vlenb = riscv_cpu_cfg(env)->vlenb;
uint32_t max_elems = vlenb >> log2_esz;
+ VSTART_CHECK_EARLY_EXIT(env);
+
k = env->vstart / max_elems;
off = env->vstart % max_elems;
@@ -877,6 +887,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
ETYPE s1 = *((ETYPE *)vs1 + H(i)); \
ETYPE s2 = *((ETYPE *)vs2 + H(i)); \
@@ -909,6 +921,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
ETYPE s2 = *((ETYPE *)vs2 + H(i)); \
ETYPE carry = vext_elem_mask(v0, i); \
@@ -944,6 +958,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
uint32_t vta_all_1s = vext_vta_all_1s(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
ETYPE s1 = *((ETYPE *)vs1 + H(i)); \
ETYPE s2 = *((ETYPE *)vs2 + H(i)); \
@@ -982,6 +998,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
uint32_t vta_all_1s = vext_vta_all_1s(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
ETYPE s2 = *((ETYPE *)vs2 + H(i)); \
ETYPE carry = !vm && vext_elem_mask(v0, i); \
@@ -1078,6 +1096,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
/* set masked-off elements to 1s */ \
@@ -1125,6 +1145,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
/* set masked-off elements to 1s */ \
@@ -1187,6 +1209,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
ETYPE s1 = *((ETYPE *)vs1 + H(i)); \
ETYPE s2 = *((ETYPE *)vs2 + H(i)); \
@@ -1252,6 +1276,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
ETYPE s2 = *((ETYPE *)vs2 + H(i)); \
if (!vm && !vext_elem_mask(v0, i)) { \
@@ -1799,6 +1825,8 @@ void HELPER(NAME)(void *vd, void *vs1, CPURISCVState *env, \
uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
ETYPE s1 = *((ETYPE *)vs1 + H(i)); \
*((ETYPE *)vd + H(i)) = s1; \
@@ -1823,6 +1851,8 @@ void HELPER(NAME)(void *vd, uint64_t s1, CPURISCVState *env, \
uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
*((ETYPE *)vd + H(i)) = (ETYPE)s1; \
} \
@@ -1846,6 +1876,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
ETYPE *vt = (!vext_elem_mask(v0, i) ? vs2 : vs1); \
*((ETYPE *)vd + H(i)) = *(vt + H(i)); \
@@ -1870,6 +1902,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
ETYPE s2 = *((ETYPE *)vs2 + H(i)); \
ETYPE d = (!vext_elem_mask(v0, i) ? s2 : \
@@ -1915,6 +1949,8 @@ vext_vv_rm_1(void *vd, void *v0, void *vs1, void *vs2,
uint32_t vl, uint32_t vm, int vxrm,
opivv2_rm_fn *fn, uint32_t vma, uint32_t esz)
{
+ VSTART_CHECK_EARLY_EXIT(env);
+
for (uint32_t i = env->vstart; i < vl; i++) {
if (!vm && !vext_elem_mask(v0, i)) {
/* set masked-off elements to 1s */
@@ -2040,6 +2076,8 @@ vext_vx_rm_1(void *vd, void *v0, target_long s1, void *vs2,
uint32_t vl, uint32_t vm, int vxrm,
opivx2_rm_fn *fn, uint32_t vma, uint32_t esz)
{
+ VSTART_CHECK_EARLY_EXIT(env);
+
for (uint32_t i = env->vstart; i < vl; i++) {
if (!vm && !vext_elem_mask(v0, i)) {
/* set masked-off elements to 1s */
@@ -2837,6 +2875,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
/* set masked-off elements to 1s */ \
@@ -2880,6 +2920,8 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
/* set masked-off elements to 1s */ \
@@ -3466,6 +3508,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
if (vl == 0) { \
return; \
} \
@@ -3987,6 +4031,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
ETYPE s1 = *((ETYPE *)vs1 + H(i)); \
ETYPE s2 = *((ETYPE *)vs2 + H(i)); \
@@ -4027,6 +4073,8 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
ETYPE s2 = *((ETYPE *)vs2 + H(i)); \
if (!vm && !vext_elem_mask(v0, i)) { \
@@ -4220,6 +4268,8 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \
uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
ETYPE s2 = *((ETYPE *)vs2 + H(i)); \
*((ETYPE *)vd + H(i)) = \
@@ -4386,6 +4436,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
uint32_t i; \
TD s1 = *((TD *)vs1 + HD(0)); \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
TS2 s2 = *((TS2 *)vs2 + HS2(i)); \
if (!vm && !vext_elem_mask(v0, i)) { \
@@ -4472,6 +4524,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
uint32_t i; \
TD s1 = *((TD *)vs1 + HD(0)); \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
TS2 s2 = *((TS2 *)vs2 + HS2(i)); \
if (!vm && !vext_elem_mask(v0, i)) { \
@@ -4544,6 +4598,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
uint32_t i; \
int a, b; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
a = vext_elem_mask(vs1, i); \
b = vext_elem_mask(vs2, i); \
@@ -4585,6 +4641,11 @@ target_ulong HELPER(vcpop_m)(void *v0, void *vs2, CPURISCVState *env,
uint32_t vl = env->vl;
int i;
+ if (env->vstart >= env->vl) {
+ env->vstart = 0;
+ return 0;
+ }
+
for (i = env->vstart; i < vl; i++) {
if (vm || vext_elem_mask(v0, i)) {
if (vext_elem_mask(vs2, i)) {
@@ -4604,6 +4665,11 @@ target_ulong HELPER(vfirst_m)(void *v0, void *vs2, CPURISCVState *env,
uint32_t vl = env->vl;
int i;
+ if (env->vstart >= env->vl) {
+ env->vstart = 0;
+ return 0;
+ }
+
for (i = env->vstart; i < vl; i++) {
if (vm || vext_elem_mask(v0, i)) {
if (vext_elem_mask(vs2, i)) {
@@ -4632,6 +4698,8 @@ static void vmsetm(void *vd, void *v0, void *vs2, CPURISCVState *env,
int i;
bool first_mask_bit = false;
+ VSTART_CHECK_EARLY_EXIT(env);
+
for (i = env->vstart; i < vl; i++) {
if (!vm && !vext_elem_mask(v0, i)) {
/* set masked-off elements to 1s */
@@ -4704,6 +4772,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, CPURISCVState *env, \
uint32_t sum = 0; \
int i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
/* set masked-off elements to 1s */ \
@@ -4737,6 +4807,8 @@ void HELPER(NAME)(void *vd, void *v0, CPURISCVState *env, uint32_t desc) \
uint32_t vma = vext_vma(desc); \
int i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
/* set masked-off elements to 1s */ \
@@ -4772,6 +4844,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
uint32_t vma = vext_vma(desc); \
target_ulong offset = s1, i_min, i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
i_min = MAX(env->vstart, offset); \
for (i = i_min; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
@@ -4805,6 +4879,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
uint32_t vma = vext_vma(desc); \
target_ulong i_max, i_min, i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
i_min = MIN(s1 < vlmax ? vlmax - s1 : 0, vl); \
i_max = MAX(i_min, env->vstart); \
for (i = env->vstart; i < i_max; ++i) { \
@@ -4847,6 +4923,8 @@ static void vslide1up_##BITWIDTH(void *vd, void *v0, uint64_t s1, \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
/* set masked-off elements to 1s */ \
@@ -4896,6 +4974,8 @@ static void vslide1down_##BITWIDTH(void *vd, void *v0, uint64_t s1, \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
/* set masked-off elements to 1s */ \
@@ -4971,6 +5051,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
uint64_t index; \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
/* set masked-off elements to 1s */ \
@@ -5014,6 +5096,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
uint64_t index = s1; \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
/* set masked-off elements to 1s */ \
@@ -5048,6 +5132,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
uint32_t vta = vext_vta(desc); \
uint32_t num = 0, i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
if (!vext_elem_mask(vs1, i)) { \
continue; \
@@ -5100,6 +5186,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
/* set masked-off elements to 1s */ \
diff --git a/target/riscv/vector_internals.c b/target/riscv/vector_internals.c
index 12f5964fbb..996c21eb31 100644
--- a/target/riscv/vector_internals.c
+++ b/target/riscv/vector_internals.c
@@ -44,6 +44,8 @@ void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2,
uint32_t vma = vext_vma(desc);
uint32_t i;
+ VSTART_CHECK_EARLY_EXIT(env);
+
for (i = env->vstart; i < vl; i++) {
if (!vm && !vext_elem_mask(v0, i)) {
/* set masked-off elements to 1s */
@@ -68,6 +70,8 @@ void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2,
uint32_t vma = vext_vma(desc);
uint32_t i;
+ VSTART_CHECK_EARLY_EXIT(env);
+
for (i = env->vstart; i < vl; i++) {
if (!vm && !vext_elem_mask(v0, i)) {
/* set masked-off elements to 1s */
diff --git a/target/riscv/vector_internals.h b/target/riscv/vector_internals.h
index 842765f6c1..9e1e15b575 100644
--- a/target/riscv/vector_internals.h
+++ b/target/riscv/vector_internals.h
@@ -24,6 +24,13 @@
#include "tcg/tcg-gvec-desc.h"
#include "internals.h"
+#define VSTART_CHECK_EARLY_EXIT(env) do { \
+ if (env->vstart >= env->vl) { \
+ env->vstart = 0; \
+ return; \
+ } \
+} while (0)
+
static inline uint32_t vext_nf(uint32_t desc)
{
return FIELD_EX32(simd_data(desc), VDATA, NF);
@@ -151,6 +158,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
/* set masked-off elements to 1s */ \
| [Prev in Thread] | Current Thread | [Next in Thread] |