| Message ID | 20240313220141.427730-5-dbarboza@ventanamicro.com |
|---|---|
| State | New |
| Headers | show |
| Series | riscv: set vstart_eq_zero on vector insns | expand |
Hi Daniel, According the v spec section 15.2 & 15.3. "The vcpop.m instruction writes x[rd] even if vl=0 (with the value 0, since no mask elements are active). Traps on vcpop.m are always reported with a vstart of 0. The vcpop.m instruction will raise an illegal instruction exception if vstart is non-zero." "The vfirst.m instruction writes x[rd] even if vl=0 (with the value -1, since no mask elements are active). Traps on vfirst are always reported with a vstart of 0. The vfirst instruction will raise an illegal instruction exception if vstart is non-zero." Both the vcpop.m and vfirst.m instructions will raise illegal instruction exception with non-zero vstart. And currently both the trans_vcpop_m and trans_vfirst_m translate functions check the vstart_eq_zero flag. So I think the early exit checking in the vcpop.m and vfirstm helper functions may be redundant. > @@ -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)) { According v spec section 15.3 ""The vfirst.m instruction writes x[rd] even if vl=0 (with the value -1, since no mask elements are active)." If both the vstart and vl are 0 here, the early exit checking will return the wrong value 0 (the return value should be -1) here. > @@ -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)) { >
On 3/14/24 00:52, Max Chou wrote: > Hi Daniel, > > According the v spec section 15.2 & 15.3. > > "The vcpop.m instruction writes x[rd] even if vl=0 (with the value 0, since no mask elements are active). > Traps on vcpop.m are always reported with a vstart of 0. The vcpop.m instruction will raise an illegal instruction exception if vstart is non-zero." > > "The vfirst.m instruction writes x[rd] even if vl=0 (with the value -1, since no mask elements are active). > Traps on vfirst are always reported with a vstart of 0. The vfirst instruction will raise an illegal instruction exception if vstart is non-zero." > > Both the vcpop.m and vfirst.m instructions will raise illegal instruction exception with non-zero vstart. > > And currently both the trans_vcpop_m and trans_vfirst_m translate functions check the vstart_eq_zero flag. > So I think the early exit checking in the vcpop.m and vfirstm helper functions may be redundant. > >> @@ -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)) { > > According v spec section 15.3 > > ""The vfirst.m instruction writes x[rd] even if vl=0 (with the value -1, since no mask elements are active)." > > If both the vstart and vl are 0 here, the early exit checking will return the wrong value 0 (the return value should be -1) here. Let's just remove these early exits from both vcpop.m and vfirst.m functions then. Thanks, Daniel > >> @@ -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)) { >>
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 */ \
On 3/14/24 10:14, Max Chou wrote: > 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; + } Do we need to do an early exit in this case? If the function is able to handle gracefully whatever env->vstart value it faces (it seems to be the case) then we should just remove the exit entirely. In fact I removed all the early exits from all helpers that are guarded by vstart_eq_zero: vcpop_m(), vfirst_m(), vmsetm(), GEN_VEXT_VIOTA_M(), GEN_VEXT_VCOMPRESS_VM(), GEN_VEXT_RED() and GEN_VEXT_FRED(). For these case the helpers can either do nothing if vl = 0 or throw some exception like vcpop and first does. Thanks, Daniel > >> @@ -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 */ \
On 3/14/24 10:27, Daniel Henrique Barboza wrote: > > > On 3/14/24 10:14, Max Chou wrote: >> 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; + } > > Do we need to do an early exit in this case? If the function is able to handle > gracefully whatever env->vstart value it faces (it seems to be the case) then we > should just remove the exit entirely. Nevermind. Here's the guard that I am removing in the next patch for vext_lsdt_whole: - uint32_t evl = s->cfg_ptr->vlenb * nf / width; - TCGLabel *over = gen_new_label(); - tcg_gen_brcondi_tl(TCG_COND_GEU, cpu_vstart, evl, over); If we just remove it and put nothing else in its place we'll end up breaking it. To preserve the existing behavior we'll have to change the early exit to if (vstart >= evl) {...} 'evl' is being calculated as uint32_t evl = s->cfg_ptr->vlenb * nf / width; So yeah, your suggestion to exit the helper early with: + if (env->vstart >= ((vlenb * nf) >> log2_esz)) { + env->vstart = 0; + return; + } Is correct. I'll change it in v15. Thanks, Daniel > > In fact I removed all the early exits from all helpers that are guarded > by vstart_eq_zero: vcpop_m(), vfirst_m(), vmsetm(), GEN_VEXT_VIOTA_M(), > GEN_VEXT_VCOMPRESS_VM(), GEN_VEXT_RED() and GEN_VEXT_FRED(). For these case > the helpers can either do nothing if vl = 0 or throw some exception like > vcpop and first does. > > > Thanks, > > Daniel > > > >> >>> @@ -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 */ \
diff --git a/target/riscv/vcrypto_helper.c b/target/riscv/vcrypto_helper.c index e2d719b13b..f7423df226 100644 --- a/target/riscv/vcrypto_helper.c +++ b/target/riscv/vcrypto_helper.c @@ -222,6 +222,8 @@ static inline void xor_round_key(AESState *round_state, AESState *round_key) uint32_t total_elems = vext_get_total_elems(env, desc, 4); \ uint32_t vta = vext_vta(desc); \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { \ AESState round_key; \ round_key.d[0] = *((uint64_t *)vs2 + H8(i * 2 + 0)); \ @@ -246,6 +248,8 @@ static inline void xor_round_key(AESState *round_state, AESState *round_key) uint32_t total_elems = vext_get_total_elems(env, desc, 4); \ uint32_t vta = vext_vta(desc); \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { \ AESState round_key; \ round_key.d[0] = *((uint64_t *)vs2 + H8(0)); \ @@ -305,6 +309,8 @@ void HELPER(vaeskf1_vi)(void *vd_vptr, void *vs2_vptr, uint32_t uimm, uint32_t total_elems = vext_get_total_elems(env, desc, 4); uint32_t vta = vext_vta(desc); + VSTART_CHECK_EARLY_EXIT(env); + uimm &= 0b1111; if (uimm > 10 || uimm == 0) { uimm ^= 0b1000; @@ -351,6 +357,8 @@ void HELPER(vaeskf2_vi)(void *vd_vptr, void *vs2_vptr, uint32_t uimm, uint32_t total_elems = vext_get_total_elems(env, desc, 4); uint32_t vta = vext_vta(desc); + VSTART_CHECK_EARLY_EXIT(env); + uimm &= 0b1111; if (uimm > 14 || uimm < 2) { uimm ^= 0b1000; @@ -457,6 +465,8 @@ void HELPER(vsha2ms_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env, uint32_t total_elems; uint32_t vta = vext_vta(desc); + VSTART_CHECK_EARLY_EXIT(env); + for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { if (sew == MO_32) { vsha2ms_e32(((uint32_t *)vd) + i * 4, ((uint32_t *)vs1) + i * 4, @@ -572,6 +582,8 @@ void HELPER(vsha2ch32_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env, uint32_t total_elems; uint32_t vta = vext_vta(desc); + VSTART_CHECK_EARLY_EXIT(env); + for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { vsha2c_32(((uint32_t *)vs2) + 4 * i, ((uint32_t *)vd) + 4 * i, ((uint32_t *)vs1) + 4 * i + 2); @@ -590,6 +602,8 @@ void HELPER(vsha2ch64_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env, uint32_t total_elems; uint32_t vta = vext_vta(desc); + VSTART_CHECK_EARLY_EXIT(env); + for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { vsha2c_64(((uint64_t *)vs2) + 4 * i, ((uint64_t *)vd) + 4 * i, ((uint64_t *)vs1) + 4 * i + 2); @@ -608,6 +622,8 @@ void HELPER(vsha2cl32_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env, uint32_t total_elems; uint32_t vta = vext_vta(desc); + VSTART_CHECK_EARLY_EXIT(env); + for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { vsha2c_32(((uint32_t *)vs2) + 4 * i, ((uint32_t *)vd) + 4 * i, (((uint32_t *)vs1) + 4 * i)); @@ -626,6 +642,8 @@ void HELPER(vsha2cl64_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env, uint32_t total_elems; uint32_t vta = vext_vta(desc); + VSTART_CHECK_EARLY_EXIT(env); + for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { vsha2c_64(((uint64_t *)vs2) + 4 * i, ((uint64_t *)vd) + 4 * i, (((uint64_t *)vs1) + 4 * i)); @@ -658,6 +676,8 @@ void HELPER(vsm3me_vv)(void *vd_vptr, void *vs1_vptr, void *vs2_vptr, uint32_t *vs1 = vs1_vptr; uint32_t *vs2 = vs2_vptr; + VSTART_CHECK_EARLY_EXIT(env); + for (int i = env->vstart / 8; i < env->vl / 8; i++) { uint32_t w[24]; for (int j = 0; j < 8; j++) { @@ -757,6 +777,8 @@ void HELPER(vsm3c_vi)(void *vd_vptr, void *vs2_vptr, uint32_t uimm, uint32_t *vs2 = vs2_vptr; uint32_t v1[8], v2[8], v3[8]; + VSTART_CHECK_EARLY_EXIT(env); + for (int i = env->vstart / 8; i < env->vl / 8; i++) { for (int k = 0; k < 8; k++) { v2[k] = bswap32(vd[H4(i * 8 + k)]); @@ -780,6 +802,8 @@ void HELPER(vghsh_vv)(void *vd_vptr, void *vs1_vptr, void *vs2_vptr, uint32_t vta = vext_vta(desc); uint32_t total_elems = vext_get_total_elems(env, desc, 4); + VSTART_CHECK_EARLY_EXIT(env); + for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { uint64_t Y[2] = {vd[i * 2 + 0], vd[i * 2 + 1]}; uint64_t H[2] = {brev8(vs2[i * 2 + 0]), brev8(vs2[i * 2 + 1])}; @@ -817,6 +841,8 @@ void HELPER(vgmul_vv)(void *vd_vptr, void *vs2_vptr, CPURISCVState *env, uint32_t vta = vext_vta(desc); uint32_t total_elems = vext_get_total_elems(env, desc, 4); + VSTART_CHECK_EARLY_EXIT(env); + for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { uint64_t Y[2] = {brev8(vd[i * 2 + 0]), brev8(vd[i * 2 + 1])}; uint64_t H[2] = {brev8(vs2[i * 2 + 0]), brev8(vs2[i * 2 + 1])}; @@ -853,6 +879,8 @@ void HELPER(vsm4k_vi)(void *vd, void *vs2, uint32_t uimm5, CPURISCVState *env, uint32_t esz = sizeof(uint32_t); uint32_t total_elems = vext_get_total_elems(env, desc, esz); + VSTART_CHECK_EARLY_EXIT(env); + for (uint32_t i = group_start; i < group_end; ++i) { uint32_t vstart = i * egs; uint32_t vend = (i + 1) * egs; @@ -909,6 +937,8 @@ void HELPER(vsm4r_vv)(void *vd, void *vs2, CPURISCVState *env, uint32_t desc) uint32_t esz = sizeof(uint32_t); uint32_t total_elems = vext_get_total_elems(env, desc, esz); + VSTART_CHECK_EARLY_EXIT(env); + for (uint32_t i = group_start; i < group_end; ++i) { uint32_t vstart = i * egs; uint32_t vend = (i + 1) * egs; @@ -943,6 +973,8 @@ void HELPER(vsm4r_vs)(void *vd, void *vs2, CPURISCVState *env, uint32_t desc) uint32_t esz = sizeof(uint32_t); uint32_t total_elems = vext_get_total_elems(env, desc, esz); + VSTART_CHECK_EARLY_EXIT(env); + for (uint32_t i = group_start; i < group_end; ++i) { uint32_t vstart = i * egs; uint32_t vend = (i + 1) * egs; diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index cd8235ea98..48d041dd4e 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -207,6 +207,8 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base, uint32_t esz = 1 << log2_esz; uint32_t vma = vext_vma(desc); + VSTART_CHECK_EARLY_EXIT(env); + for (i = env->vstart; i < env->vl; i++, env->vstart++) { k = 0; while (k < nf) { @@ -272,6 +274,8 @@ vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc, uint32_t max_elems = vext_max_elems(desc, log2_esz); uint32_t esz = 1 << log2_esz; + VSTART_CHECK_EARLY_EXIT(env); + /* load bytes from guest memory */ for (i = env->vstart; i < evl; i++, env->vstart++) { k = 0; @@ -386,6 +390,8 @@ vext_ldst_index(void *vd, void *v0, target_ulong base, uint32_t esz = 1 << log2_esz; uint32_t vma = vext_vma(desc); + VSTART_CHECK_EARLY_EXIT(env); + /* load bytes from guest memory */ for (i = env->vstart; i < env->vl; i++, env->vstart++) { k = 0; @@ -477,6 +483,8 @@ vext_ldff(void *vd, void *v0, target_ulong base, target_ulong addr, offset, remain; int mmu_index = riscv_env_mmu_index(env, false); + VSTART_CHECK_EARLY_EXIT(env); + /* probe every access */ for (i = env->vstart; i < env->vl; i++) { if (!vm && !vext_elem_mask(v0, i)) { @@ -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 */ \