* [PATCH v2 0/2] Enhanced VSTART and VL Checks for Vector Instructions
@ 2024-12-18 7:15 Chao Liu
2024-12-18 7:15 ` [PATCH v2 1/2] target/riscv: refactor VSTART_CHECK_EARLY_EXIT() to accept vl as a parameter Chao Liu
2024-12-18 7:15 ` [PATCH v2 2/2] target/riscv: fix handling of nop for vstart >= vl in some vector instruction Chao Liu
0 siblings, 2 replies; 5+ messages in thread
From: Chao Liu @ 2024-12-18 7:15 UTC (permalink / raw)
To: bmeng.cn, liwei1518, palmer, alistair.francis, dbarboza,
zhiwei_liu, max.chou, alistair23
Cc: qemu-riscv, qemu-devel, zqz00548, Chao Liu
Hi, all:
In the second version of this patch, I addressed the issue that other vector
instructions didn't check for vstart >= vl correctly.
I refactored the VSTART_CHECK_EARLY_EXIT() macro. This change is intended to:
Vector instructions with special vl values can also be checked with this macro,
such as vlm.v instruction (real vl = ceil(vl / 8)).
PATCH v1:
https://lore.kernel.org/qemu-riscv/cover.1734423785.git.lc00631@tecorigin.com/
Chao Liu (2):
target/riscv: refactor VSTART_CHECK_EARLY_EXIT() to accept vl as a
parameter
target/riscv: fix handling of nop for vstart >= vl in some vector
instruction
target/riscv/vcrypto_helper.c | 32 ++++++-------
target/riscv/vector_helper.c | 83 ++++++++++++++++++---------------
target/riscv/vector_internals.c | 4 +-
target/riscv/vector_internals.h | 12 ++---
4 files changed, 69 insertions(+), 62 deletions(-)
--
2.47.1
^ permalink raw reply [flat|nested] 5+ messages in thread* [PATCH v2 1/2] target/riscv: refactor VSTART_CHECK_EARLY_EXIT() to accept vl as a parameter 2024-12-18 7:15 [PATCH v2 0/2] Enhanced VSTART and VL Checks for Vector Instructions Chao Liu @ 2024-12-18 7:15 ` Chao Liu 2024-12-26 13:16 ` Daniel Henrique Barboza 2024-12-18 7:15 ` [PATCH v2 2/2] target/riscv: fix handling of nop for vstart >= vl in some vector instruction Chao Liu 1 sibling, 1 reply; 5+ messages in thread From: Chao Liu @ 2024-12-18 7:15 UTC (permalink / raw) To: bmeng.cn, liwei1518, palmer, alistair.francis, dbarboza, zhiwei_liu, max.chou, alistair23 Cc: qemu-riscv, qemu-devel, zqz00548, Chao Liu Some vector instructions are special, such as the vlm.v instruction, where setting its vl actually sets evl = (vl + 7) >> 3. To improve maintainability, we will uniformly use VSTART_CHECK_EARLY_EXIT() to check for the condition vstart >= vl. This function will also handle cases involving evl. Signed-off-by: Chao Liu <lc00631@tecorigin.com> --- target/riscv/vcrypto_helper.c | 32 +++++++-------- target/riscv/vector_helper.c | 69 ++++++++++++++++----------------- target/riscv/vector_internals.c | 4 +- target/riscv/vector_internals.h | 12 +++--- 4 files changed, 57 insertions(+), 60 deletions(-) diff --git a/target/riscv/vcrypto_helper.c b/target/riscv/vcrypto_helper.c index f7423df226..1526de96f5 100644 --- a/target/riscv/vcrypto_helper.c +++ b/target/riscv/vcrypto_helper.c @@ -222,7 +222,7 @@ 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); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { \ AESState round_key; \ @@ -248,7 +248,7 @@ 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); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { \ AESState round_key; \ @@ -309,7 +309,7 @@ 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); + VSTART_CHECK_EARLY_EXIT(env, vl); uimm &= 0b1111; if (uimm > 10 || uimm == 0) { @@ -357,7 +357,7 @@ 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); + VSTART_CHECK_EARLY_EXIT(env, vl); uimm &= 0b1111; if (uimm > 14 || uimm < 2) { @@ -465,7 +465,7 @@ 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); + VSTART_CHECK_EARLY_EXIT(env, env->vl); for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { if (sew == MO_32) { @@ -582,7 +582,7 @@ 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); + VSTART_CHECK_EARLY_EXIT(env, env->vl); for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { vsha2c_32(((uint32_t *)vs2) + 4 * i, ((uint32_t *)vd) + 4 * i, @@ -602,7 +602,7 @@ 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); + VSTART_CHECK_EARLY_EXIT(env, env->vl); for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { vsha2c_64(((uint64_t *)vs2) + 4 * i, ((uint64_t *)vd) + 4 * i, @@ -622,7 +622,7 @@ 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); + VSTART_CHECK_EARLY_EXIT(env, env->vl); for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { vsha2c_32(((uint32_t *)vs2) + 4 * i, ((uint32_t *)vd) + 4 * i, @@ -642,7 +642,7 @@ 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); + VSTART_CHECK_EARLY_EXIT(env, env->vl); for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { vsha2c_64(((uint64_t *)vs2) + 4 * i, ((uint64_t *)vd) + 4 * i, @@ -676,7 +676,7 @@ 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); + VSTART_CHECK_EARLY_EXIT(env, env->vl); for (int i = env->vstart / 8; i < env->vl / 8; i++) { uint32_t w[24]; @@ -777,7 +777,7 @@ 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); + VSTART_CHECK_EARLY_EXIT(env, env->vl); for (int i = env->vstart / 8; i < env->vl / 8; i++) { for (int k = 0; k < 8; k++) { @@ -802,7 +802,7 @@ 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); + VSTART_CHECK_EARLY_EXIT(env, env->vl); for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { uint64_t Y[2] = {vd[i * 2 + 0], vd[i * 2 + 1]}; @@ -841,7 +841,7 @@ 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); + VSTART_CHECK_EARLY_EXIT(env, env->vl); 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])}; @@ -879,7 +879,7 @@ 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); + VSTART_CHECK_EARLY_EXIT(env, env->vl); for (uint32_t i = group_start; i < group_end; ++i) { uint32_t vstart = i * egs; @@ -937,7 +937,7 @@ 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); + VSTART_CHECK_EARLY_EXIT(env, env->vl); for (uint32_t i = group_start; i < group_end; ++i) { uint32_t vstart = i * egs; @@ -973,7 +973,7 @@ 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); + VSTART_CHECK_EARLY_EXIT(env, env->vl); for (uint32_t i = group_start; i < group_end; ++i) { uint32_t vstart = i * egs; diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index a85dd1d200..4f14395808 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -265,7 +265,7 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base, target_ulong stride, uint32_t esz = 1 << log2_esz; uint32_t vma = vext_vma(desc); - VSTART_CHECK_EARLY_EXIT(env); + VSTART_CHECK_EARLY_EXIT(env, env->vl); for (i = env->vstart; i < env->vl; env->vstart = ++i) { k = 0; @@ -388,10 +388,7 @@ vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc, uint32_t msize = nf * esz; int mmu_index = riscv_env_mmu_index(env, false); - if (env->vstart >= evl) { - env->vstart = 0; - return; - } + VSTART_CHECK_EARLY_EXIT(env, evl); /* Calculate the page range of first page */ addr = base + ((env->vstart * nf) << log2_esz); @@ -533,7 +530,7 @@ 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); + VSTART_CHECK_EARLY_EXIT(env, env->vl); /* load bytes from guest memory */ for (i = env->vstart; i < env->vl; env->vstart = ++i) { @@ -625,7 +622,7 @@ vext_ldff(void *vd, void *v0, target_ulong base, CPURISCVState *env, target_ulong addr, offset, remain, page_split, elems; int mmu_index = riscv_env_mmu_index(env, false); - VSTART_CHECK_EARLY_EXIT(env); + VSTART_CHECK_EARLY_EXIT(env, env->vl); /* probe every access */ for (i = env->vstart; i < env->vl; i++) { @@ -1092,7 +1089,7 @@ 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); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (i = env->vstart; i < vl; i++) { \ ETYPE s1 = *((ETYPE *)vs1 + H(i)); \ @@ -1126,7 +1123,7 @@ 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); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (i = env->vstart; i < vl; i++) { \ ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ @@ -1163,7 +1160,7 @@ 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); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (i = env->vstart; i < vl; i++) { \ ETYPE s1 = *((ETYPE *)vs1 + H(i)); \ @@ -1203,7 +1200,7 @@ 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); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (i = env->vstart; i < vl; i++) { \ ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ @@ -1301,7 +1298,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ uint32_t vma = vext_vma(desc); \ uint32_t i; \ \ - VSTART_CHECK_EARLY_EXIT(env); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (i = env->vstart; i < vl; i++) { \ if (!vm && !vext_elem_mask(v0, i)) { \ @@ -1350,7 +1347,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \ uint32_t vma = vext_vma(desc); \ uint32_t i; \ \ - VSTART_CHECK_EARLY_EXIT(env); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (i = env->vstart; i < vl; i++) { \ if (!vm && !vext_elem_mask(v0, i)) { \ @@ -1414,7 +1411,7 @@ 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); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (i = env->vstart; i < vl; i++) { \ ETYPE s1 = *((ETYPE *)vs1 + H(i)); \ @@ -1481,7 +1478,7 @@ 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); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (i = env->vstart; i < vl; i++) { \ ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ @@ -2030,7 +2027,7 @@ void HELPER(NAME)(void *vd, void *vs1, CPURISCVState *env, \ uint32_t vta = vext_vta(desc); \ uint32_t i; \ \ - VSTART_CHECK_EARLY_EXIT(env); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (i = env->vstart; i < vl; i++) { \ ETYPE s1 = *((ETYPE *)vs1 + H(i)); \ @@ -2056,7 +2053,7 @@ void HELPER(NAME)(void *vd, uint64_t s1, CPURISCVState *env, \ uint32_t vta = vext_vta(desc); \ uint32_t i; \ \ - VSTART_CHECK_EARLY_EXIT(env); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (i = env->vstart; i < vl; i++) { \ *((ETYPE *)vd + H(i)) = (ETYPE)s1; \ @@ -2081,7 +2078,7 @@ 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); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (i = env->vstart; i < vl; i++) { \ ETYPE *vt = (!vext_elem_mask(v0, i) ? vs2 : vs1); \ @@ -2107,7 +2104,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \ uint32_t vta = vext_vta(desc); \ uint32_t i; \ \ - VSTART_CHECK_EARLY_EXIT(env); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (i = env->vstart; i < vl; i++) { \ ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ @@ -2154,7 +2151,7 @@ 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); + VSTART_CHECK_EARLY_EXIT(env, vl); for (uint32_t i = env->vstart; i < vl; i++) { if (!vm && !vext_elem_mask(v0, i)) { @@ -2281,7 +2278,7 @@ 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); + VSTART_CHECK_EARLY_EXIT(env, vl); for (uint32_t i = env->vstart; i < vl; i++) { if (!vm && !vext_elem_mask(v0, i)) { @@ -3080,7 +3077,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ uint32_t vma = vext_vma(desc); \ uint32_t i; \ \ - VSTART_CHECK_EARLY_EXIT(env); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (i = env->vstart; i < vl; i++) { \ if (!vm && !vext_elem_mask(v0, i)) { \ @@ -3125,7 +3122,7 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, \ uint32_t vma = vext_vma(desc); \ uint32_t i; \ \ - VSTART_CHECK_EARLY_EXIT(env); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (i = env->vstart; i < vl; i++) { \ if (!vm && !vext_elem_mask(v0, i)) { \ @@ -3713,7 +3710,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \ uint32_t vma = vext_vma(desc); \ uint32_t i; \ \ - VSTART_CHECK_EARLY_EXIT(env); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ if (vl == 0) { \ return; \ @@ -4236,7 +4233,7 @@ 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); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (i = env->vstart; i < vl; i++) { \ ETYPE s1 = *((ETYPE *)vs1 + H(i)); \ @@ -4278,7 +4275,7 @@ 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); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (i = env->vstart; i < vl; i++) { \ ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ @@ -4473,7 +4470,7 @@ 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); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (i = env->vstart; i < vl; i++) { \ ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ @@ -4799,7 +4796,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ uint32_t i; \ int a, b; \ \ - VSTART_CHECK_EARLY_EXIT(env); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (i = env->vstart; i < vl; i++) { \ a = vext_elem_mask(vs1, i); \ @@ -4994,7 +4991,7 @@ 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); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (i = env->vstart; i < vl; i++) { \ if (!vm && !vext_elem_mask(v0, i)) { \ @@ -5031,7 +5028,7 @@ 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); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ i_min = MAX(env->vstart, offset); \ for (i = i_min; i < vl; i++) { \ @@ -5066,7 +5063,7 @@ 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); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ i_min = MIN(s1 < vlmax ? vlmax - s1 : 0, vl); \ i_max = MAX(i_min, env->vstart); \ @@ -5110,7 +5107,7 @@ 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); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (i = env->vstart; i < vl; i++) { \ if (!vm && !vext_elem_mask(v0, i)) { \ @@ -5161,7 +5158,7 @@ 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); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (i = env->vstart; i < vl; i++) { \ if (!vm && !vext_elem_mask(v0, i)) { \ @@ -5238,7 +5235,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ uint64_t index; \ uint32_t i; \ \ - VSTART_CHECK_EARLY_EXIT(env); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (i = env->vstart; i < vl; i++) { \ if (!vm && !vext_elem_mask(v0, i)) { \ @@ -5283,7 +5280,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ uint64_t index = s1; \ uint32_t i; \ \ - VSTART_CHECK_EARLY_EXIT(env); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (i = env->vstart; i < vl; i++) { \ if (!vm && !vext_elem_mask(v0, i)) { \ @@ -5379,7 +5376,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \ uint32_t vma = vext_vma(desc); \ uint32_t i; \ \ - VSTART_CHECK_EARLY_EXIT(env); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (i = env->vstart; i < vl; i++) { \ if (!vm && !vext_elem_mask(v0, i)) { \ diff --git a/target/riscv/vector_internals.c b/target/riscv/vector_internals.c index 05b2d01e58..b490b1d398 100644 --- a/target/riscv/vector_internals.c +++ b/target/riscv/vector_internals.c @@ -66,7 +66,7 @@ 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); + VSTART_CHECK_EARLY_EXIT(env, vl); for (i = env->vstart; i < vl; i++) { if (!vm && !vext_elem_mask(v0, i)) { @@ -92,7 +92,7 @@ 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); + VSTART_CHECK_EARLY_EXIT(env, vl); for (i = env->vstart; i < vl; i++) { if (!vm && !vext_elem_mask(v0, i)) { diff --git a/target/riscv/vector_internals.h b/target/riscv/vector_internals.h index 9e1e15b575..9d41bb3b10 100644 --- a/target/riscv/vector_internals.h +++ b/target/riscv/vector_internals.h @@ -24,11 +24,11 @@ #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; \ - } \ +#define VSTART_CHECK_EARLY_EXIT(env, vl) do { \ + if (env->vstart >= vl) { \ + env->vstart = 0; \ + return; \ + } \ } while (0) static inline uint32_t vext_nf(uint32_t desc) @@ -158,7 +158,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \ uint32_t vma = vext_vma(desc); \ uint32_t i; \ \ - VSTART_CHECK_EARLY_EXIT(env); \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ \ for (i = env->vstart; i < vl; i++) { \ if (!vm && !vext_elem_mask(v0, i)) { \ -- 2.47.1 ^ permalink raw reply related [flat|nested] 5+ messages in thread
* Re: [PATCH v2 1/2] target/riscv: refactor VSTART_CHECK_EARLY_EXIT() to accept vl as a parameter 2024-12-18 7:15 ` [PATCH v2 1/2] target/riscv: refactor VSTART_CHECK_EARLY_EXIT() to accept vl as a parameter Chao Liu @ 2024-12-26 13:16 ` Daniel Henrique Barboza 0 siblings, 0 replies; 5+ messages in thread From: Daniel Henrique Barboza @ 2024-12-26 13:16 UTC (permalink / raw) To: Chao Liu, bmeng.cn, liwei1518, palmer, alistair.francis, zhiwei_liu, max.chou, alistair23 Cc: qemu-riscv, qemu-devel, zqz00548 On 12/18/24 4:15 AM, Chao Liu wrote: > Some vector instructions are special, such as the vlm.v instruction, > where setting its vl actually sets evl = (vl + 7) >> 3. To improve > maintainability, we will uniformly use VSTART_CHECK_EARLY_EXIT() to > check for the condition vstart >= vl. This function will also handle > cases involving evl. > > Signed-off-by: Chao Liu <lc00631@tecorigin.com> > --- Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com> > target/riscv/vcrypto_helper.c | 32 +++++++-------- > target/riscv/vector_helper.c | 69 ++++++++++++++++----------------- > target/riscv/vector_internals.c | 4 +- > target/riscv/vector_internals.h | 12 +++--- > 4 files changed, 57 insertions(+), 60 deletions(-) > > diff --git a/target/riscv/vcrypto_helper.c b/target/riscv/vcrypto_helper.c > index f7423df226..1526de96f5 100644 > --- a/target/riscv/vcrypto_helper.c > +++ b/target/riscv/vcrypto_helper.c > @@ -222,7 +222,7 @@ 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); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { \ > AESState round_key; \ > @@ -248,7 +248,7 @@ 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); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { \ > AESState round_key; \ > @@ -309,7 +309,7 @@ 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); > + VSTART_CHECK_EARLY_EXIT(env, vl); > > uimm &= 0b1111; > if (uimm > 10 || uimm == 0) { > @@ -357,7 +357,7 @@ 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); > + VSTART_CHECK_EARLY_EXIT(env, vl); > > uimm &= 0b1111; > if (uimm > 14 || uimm < 2) { > @@ -465,7 +465,7 @@ 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); > + VSTART_CHECK_EARLY_EXIT(env, env->vl); > > for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { > if (sew == MO_32) { > @@ -582,7 +582,7 @@ 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); > + VSTART_CHECK_EARLY_EXIT(env, env->vl); > > for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { > vsha2c_32(((uint32_t *)vs2) + 4 * i, ((uint32_t *)vd) + 4 * i, > @@ -602,7 +602,7 @@ 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); > + VSTART_CHECK_EARLY_EXIT(env, env->vl); > > for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { > vsha2c_64(((uint64_t *)vs2) + 4 * i, ((uint64_t *)vd) + 4 * i, > @@ -622,7 +622,7 @@ 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); > + VSTART_CHECK_EARLY_EXIT(env, env->vl); > > for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { > vsha2c_32(((uint32_t *)vs2) + 4 * i, ((uint32_t *)vd) + 4 * i, > @@ -642,7 +642,7 @@ 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); > + VSTART_CHECK_EARLY_EXIT(env, env->vl); > > for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { > vsha2c_64(((uint64_t *)vs2) + 4 * i, ((uint64_t *)vd) + 4 * i, > @@ -676,7 +676,7 @@ 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); > + VSTART_CHECK_EARLY_EXIT(env, env->vl); > > for (int i = env->vstart / 8; i < env->vl / 8; i++) { > uint32_t w[24]; > @@ -777,7 +777,7 @@ 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); > + VSTART_CHECK_EARLY_EXIT(env, env->vl); > > for (int i = env->vstart / 8; i < env->vl / 8; i++) { > for (int k = 0; k < 8; k++) { > @@ -802,7 +802,7 @@ 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); > + VSTART_CHECK_EARLY_EXIT(env, env->vl); > > for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { > uint64_t Y[2] = {vd[i * 2 + 0], vd[i * 2 + 1]}; > @@ -841,7 +841,7 @@ 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); > + VSTART_CHECK_EARLY_EXIT(env, env->vl); > > 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])}; > @@ -879,7 +879,7 @@ 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); > + VSTART_CHECK_EARLY_EXIT(env, env->vl); > > for (uint32_t i = group_start; i < group_end; ++i) { > uint32_t vstart = i * egs; > @@ -937,7 +937,7 @@ 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); > + VSTART_CHECK_EARLY_EXIT(env, env->vl); > > for (uint32_t i = group_start; i < group_end; ++i) { > uint32_t vstart = i * egs; > @@ -973,7 +973,7 @@ 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); > + VSTART_CHECK_EARLY_EXIT(env, env->vl); > > for (uint32_t i = group_start; i < group_end; ++i) { > uint32_t vstart = i * egs; > diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c > index a85dd1d200..4f14395808 100644 > --- a/target/riscv/vector_helper.c > +++ b/target/riscv/vector_helper.c > @@ -265,7 +265,7 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base, target_ulong stride, > uint32_t esz = 1 << log2_esz; > uint32_t vma = vext_vma(desc); > > - VSTART_CHECK_EARLY_EXIT(env); > + VSTART_CHECK_EARLY_EXIT(env, env->vl); > > for (i = env->vstart; i < env->vl; env->vstart = ++i) { > k = 0; > @@ -388,10 +388,7 @@ vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc, > uint32_t msize = nf * esz; > int mmu_index = riscv_env_mmu_index(env, false); > > - if (env->vstart >= evl) { > - env->vstart = 0; > - return; > - } > + VSTART_CHECK_EARLY_EXIT(env, evl); > > /* Calculate the page range of first page */ > addr = base + ((env->vstart * nf) << log2_esz); > @@ -533,7 +530,7 @@ 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); > + VSTART_CHECK_EARLY_EXIT(env, env->vl); > > /* load bytes from guest memory */ > for (i = env->vstart; i < env->vl; env->vstart = ++i) { > @@ -625,7 +622,7 @@ vext_ldff(void *vd, void *v0, target_ulong base, CPURISCVState *env, > target_ulong addr, offset, remain, page_split, elems; > int mmu_index = riscv_env_mmu_index(env, false); > > - VSTART_CHECK_EARLY_EXIT(env); > + VSTART_CHECK_EARLY_EXIT(env, env->vl); > > /* probe every access */ > for (i = env->vstart; i < env->vl; i++) { > @@ -1092,7 +1089,7 @@ 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); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (i = env->vstart; i < vl; i++) { \ > ETYPE s1 = *((ETYPE *)vs1 + H(i)); \ > @@ -1126,7 +1123,7 @@ 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); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (i = env->vstart; i < vl; i++) { \ > ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ > @@ -1163,7 +1160,7 @@ 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); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (i = env->vstart; i < vl; i++) { \ > ETYPE s1 = *((ETYPE *)vs1 + H(i)); \ > @@ -1203,7 +1200,7 @@ 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); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (i = env->vstart; i < vl; i++) { \ > ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ > @@ -1301,7 +1298,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ > uint32_t vma = vext_vma(desc); \ > uint32_t i; \ > \ > - VSTART_CHECK_EARLY_EXIT(env); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (i = env->vstart; i < vl; i++) { \ > if (!vm && !vext_elem_mask(v0, i)) { \ > @@ -1350,7 +1347,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \ > uint32_t vma = vext_vma(desc); \ > uint32_t i; \ > \ > - VSTART_CHECK_EARLY_EXIT(env); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (i = env->vstart; i < vl; i++) { \ > if (!vm && !vext_elem_mask(v0, i)) { \ > @@ -1414,7 +1411,7 @@ 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); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (i = env->vstart; i < vl; i++) { \ > ETYPE s1 = *((ETYPE *)vs1 + H(i)); \ > @@ -1481,7 +1478,7 @@ 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); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (i = env->vstart; i < vl; i++) { \ > ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ > @@ -2030,7 +2027,7 @@ void HELPER(NAME)(void *vd, void *vs1, CPURISCVState *env, \ > uint32_t vta = vext_vta(desc); \ > uint32_t i; \ > \ > - VSTART_CHECK_EARLY_EXIT(env); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (i = env->vstart; i < vl; i++) { \ > ETYPE s1 = *((ETYPE *)vs1 + H(i)); \ > @@ -2056,7 +2053,7 @@ void HELPER(NAME)(void *vd, uint64_t s1, CPURISCVState *env, \ > uint32_t vta = vext_vta(desc); \ > uint32_t i; \ > \ > - VSTART_CHECK_EARLY_EXIT(env); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (i = env->vstart; i < vl; i++) { \ > *((ETYPE *)vd + H(i)) = (ETYPE)s1; \ > @@ -2081,7 +2078,7 @@ 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); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (i = env->vstart; i < vl; i++) { \ > ETYPE *vt = (!vext_elem_mask(v0, i) ? vs2 : vs1); \ > @@ -2107,7 +2104,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \ > uint32_t vta = vext_vta(desc); \ > uint32_t i; \ > \ > - VSTART_CHECK_EARLY_EXIT(env); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (i = env->vstart; i < vl; i++) { \ > ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ > @@ -2154,7 +2151,7 @@ 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); > + VSTART_CHECK_EARLY_EXIT(env, vl); > > for (uint32_t i = env->vstart; i < vl; i++) { > if (!vm && !vext_elem_mask(v0, i)) { > @@ -2281,7 +2278,7 @@ 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); > + VSTART_CHECK_EARLY_EXIT(env, vl); > > for (uint32_t i = env->vstart; i < vl; i++) { > if (!vm && !vext_elem_mask(v0, i)) { > @@ -3080,7 +3077,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ > uint32_t vma = vext_vma(desc); \ > uint32_t i; \ > \ > - VSTART_CHECK_EARLY_EXIT(env); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (i = env->vstart; i < vl; i++) { \ > if (!vm && !vext_elem_mask(v0, i)) { \ > @@ -3125,7 +3122,7 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, \ > uint32_t vma = vext_vma(desc); \ > uint32_t i; \ > \ > - VSTART_CHECK_EARLY_EXIT(env); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (i = env->vstart; i < vl; i++) { \ > if (!vm && !vext_elem_mask(v0, i)) { \ > @@ -3713,7 +3710,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \ > uint32_t vma = vext_vma(desc); \ > uint32_t i; \ > \ > - VSTART_CHECK_EARLY_EXIT(env); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > if (vl == 0) { \ > return; \ > @@ -4236,7 +4233,7 @@ 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); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (i = env->vstart; i < vl; i++) { \ > ETYPE s1 = *((ETYPE *)vs1 + H(i)); \ > @@ -4278,7 +4275,7 @@ 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); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (i = env->vstart; i < vl; i++) { \ > ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ > @@ -4473,7 +4470,7 @@ 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); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (i = env->vstart; i < vl; i++) { \ > ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ > @@ -4799,7 +4796,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ > uint32_t i; \ > int a, b; \ > \ > - VSTART_CHECK_EARLY_EXIT(env); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (i = env->vstart; i < vl; i++) { \ > a = vext_elem_mask(vs1, i); \ > @@ -4994,7 +4991,7 @@ 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); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (i = env->vstart; i < vl; i++) { \ > if (!vm && !vext_elem_mask(v0, i)) { \ > @@ -5031,7 +5028,7 @@ 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); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > i_min = MAX(env->vstart, offset); \ > for (i = i_min; i < vl; i++) { \ > @@ -5066,7 +5063,7 @@ 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); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > i_min = MIN(s1 < vlmax ? vlmax - s1 : 0, vl); \ > i_max = MAX(i_min, env->vstart); \ > @@ -5110,7 +5107,7 @@ 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); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (i = env->vstart; i < vl; i++) { \ > if (!vm && !vext_elem_mask(v0, i)) { \ > @@ -5161,7 +5158,7 @@ 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); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (i = env->vstart; i < vl; i++) { \ > if (!vm && !vext_elem_mask(v0, i)) { \ > @@ -5238,7 +5235,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ > uint64_t index; \ > uint32_t i; \ > \ > - VSTART_CHECK_EARLY_EXIT(env); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (i = env->vstart; i < vl; i++) { \ > if (!vm && !vext_elem_mask(v0, i)) { \ > @@ -5283,7 +5280,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ > uint64_t index = s1; \ > uint32_t i; \ > \ > - VSTART_CHECK_EARLY_EXIT(env); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (i = env->vstart; i < vl; i++) { \ > if (!vm && !vext_elem_mask(v0, i)) { \ > @@ -5379,7 +5376,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \ > uint32_t vma = vext_vma(desc); \ > uint32_t i; \ > \ > - VSTART_CHECK_EARLY_EXIT(env); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (i = env->vstart; i < vl; i++) { \ > if (!vm && !vext_elem_mask(v0, i)) { \ > diff --git a/target/riscv/vector_internals.c b/target/riscv/vector_internals.c > index 05b2d01e58..b490b1d398 100644 > --- a/target/riscv/vector_internals.c > +++ b/target/riscv/vector_internals.c > @@ -66,7 +66,7 @@ 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); > + VSTART_CHECK_EARLY_EXIT(env, vl); > > for (i = env->vstart; i < vl; i++) { > if (!vm && !vext_elem_mask(v0, i)) { > @@ -92,7 +92,7 @@ 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); > + VSTART_CHECK_EARLY_EXIT(env, vl); > > for (i = env->vstart; i < vl; i++) { > if (!vm && !vext_elem_mask(v0, i)) { > diff --git a/target/riscv/vector_internals.h b/target/riscv/vector_internals.h > index 9e1e15b575..9d41bb3b10 100644 > --- a/target/riscv/vector_internals.h > +++ b/target/riscv/vector_internals.h > @@ -24,11 +24,11 @@ > #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; \ > - } \ > +#define VSTART_CHECK_EARLY_EXIT(env, vl) do { \ > + if (env->vstart >= vl) { \ > + env->vstart = 0; \ > + return; \ > + } \ > } while (0) > > static inline uint32_t vext_nf(uint32_t desc) > @@ -158,7 +158,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \ > uint32_t vma = vext_vma(desc); \ > uint32_t i; \ > \ > - VSTART_CHECK_EARLY_EXIT(env); \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > \ > for (i = env->vstart; i < vl; i++) { \ > if (!vm && !vext_elem_mask(v0, i)) { \ ^ permalink raw reply [flat|nested] 5+ messages in thread
* [PATCH v2 2/2] target/riscv: fix handling of nop for vstart >= vl in some vector instruction 2024-12-18 7:15 [PATCH v2 0/2] Enhanced VSTART and VL Checks for Vector Instructions Chao Liu 2024-12-18 7:15 ` [PATCH v2 1/2] target/riscv: refactor VSTART_CHECK_EARLY_EXIT() to accept vl as a parameter Chao Liu @ 2024-12-18 7:15 ` Chao Liu 2024-12-26 13:48 ` Daniel Henrique Barboza 1 sibling, 1 reply; 5+ messages in thread From: Chao Liu @ 2024-12-18 7:15 UTC (permalink / raw) To: bmeng.cn, liwei1518, palmer, alistair.francis, dbarboza, zhiwei_liu, max.chou, alistair23 Cc: qemu-riscv, qemu-devel, zqz00548, Chao Liu fix: https://lore.kernel.org/all/20240322085319.1758843-8-alistair.francis@wdc.com/ Signed-off-by: Chao Liu <lc00631@tecorigin.com> --- target/riscv/vector_helper.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 4f14395808..5f1fc24d99 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -2151,8 +2151,6 @@ 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, vl); - for (uint32_t i = env->vstart; i < vl; i++) { if (!vm && !vext_elem_mask(v0, i)) { /* set masked-off elements to 1s */ @@ -2176,6 +2174,8 @@ vext_vv_rm_2(void *vd, void *v0, void *vs1, void *vs2, uint32_t vta = vext_vta(desc); uint32_t vma = vext_vma(desc); + VSTART_CHECK_EARLY_EXIT(env, vl); + switch (env->vxrm) { case 0: /* rnu */ vext_vv_rm_1(vd, v0, vs1, vs2, @@ -2278,8 +2278,6 @@ 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, vl); - for (uint32_t i = env->vstart; i < vl; i++) { if (!vm && !vext_elem_mask(v0, i)) { /* set masked-off elements to 1s */ @@ -2303,6 +2301,8 @@ vext_vx_rm_2(void *vd, void *v0, target_long s1, void *vs2, uint32_t vta = vext_vta(desc); uint32_t vma = vext_vma(desc); + VSTART_CHECK_EARLY_EXIT(env, vl); + switch (env->vxrm) { case 0: /* rnu */ vext_vx_rm_1(vd, v0, s1, vs2, @@ -4638,6 +4638,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ uint32_t i; \ TD s1 = *((TD *)vs1 + HD(0)); \ \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ + \ for (i = env->vstart; i < vl; i++) { \ TS2 s2 = *((TS2 *)vs2 + HS2(i)); \ if (!vm && !vext_elem_mask(v0, i)) { \ @@ -4724,6 +4726,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ uint32_t i; \ TD s1 = *((TD *)vs1 + HD(0)); \ \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ + \ for (i = env->vstart; i < vl; i++) { \ TS2 s2 = *((TS2 *)vs2 + HS2(i)); \ if (!vm && !vext_elem_mask(v0, i)) { \ @@ -4886,6 +4890,8 @@ static void vmsetm(void *vd, void *v0, void *vs2, CPURISCVState *env, int i; bool first_mask_bit = false; + VSTART_CHECK_EARLY_EXIT(env, vl); + for (i = env->vstart; i < vl; i++) { if (!vm && !vext_elem_mask(v0, i)) { /* set masked-off elements to 1s */ @@ -4958,6 +4964,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, CPURISCVState *env, \ uint32_t sum = 0; \ int i; \ \ + VSTART_CHECK_EARLY_EXIT(env, vl); \ + \ for (i = env->vstart; i < vl; i++) { \ if (!vm && !vext_elem_mask(v0, i)) { \ /* set masked-off elements to 1s */ \ @@ -5316,6 +5324,8 @@ 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, vl); \ + \ for (i = env->vstart; i < vl; i++) { \ if (!vext_elem_mask(vs1, i)) { \ continue; \ -- 2.47.1 ^ permalink raw reply related [flat|nested] 5+ messages in thread
* Re: [PATCH v2 2/2] target/riscv: fix handling of nop for vstart >= vl in some vector instruction 2024-12-18 7:15 ` [PATCH v2 2/2] target/riscv: fix handling of nop for vstart >= vl in some vector instruction Chao Liu @ 2024-12-26 13:48 ` Daniel Henrique Barboza 0 siblings, 0 replies; 5+ messages in thread From: Daniel Henrique Barboza @ 2024-12-26 13:48 UTC (permalink / raw) To: Chao Liu, bmeng.cn, liwei1518, palmer, alistair.francis, zhiwei_liu, max.chou, alistair23 Cc: qemu-riscv, qemu-devel, zqz00548 On 12/18/24 4:15 AM, Chao Liu wrote: We want a commit message here because the change is not trivial. You gave an explanation in the v1 cover letter: --- Recently, when I was writing a RISCV test, I found that when VL is set to 0, the instruction should be nop, but when I tested it, I found that QEMU will treat all elements as tail elements, and in the case of VTA=1, write all elements to 1. After troubleshooting, it was found that the vext_vx_rm_1 function was called in the vext_vx_rm_2, and then the vext_set_elems_1s function was called to process the tail element, but only VSTART >= vl was checked in the vext_vx_rm_1 function, which caused the tail element to still be processed even if it was returned in advance. So I've made the following change: put VSTART_CHECK_EARLY_EXIT(env) at the beginning of the vext_vx_rm_2 function, so that the VSTART register is checked correctly. ---- You can add this text as a commit msg for this patch, also mentioning that you're changing vext_vv_rm_1 / vext_vv_rm_2 for the same reason. > fix: https://lore.kernel.org/all/20240322085319.1758843-8-alistair.francis@wdc.com/ The tag format we use in QEMU refers to the commit in the tree, not the link for the pull request email. In this case the tag would be: Fixes: df4252b2ec ("target/riscv/vector_helpers: do early exit when vstart >= vl") > Signed-off-by: Chao Liu <lc00631@tecorigin.com> > --- The code itself looks good to me. Thanks, Daniel > target/riscv/vector_helper.c | 18 ++++++++++++++---- > 1 file changed, 14 insertions(+), 4 deletions(-) > > diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c > index 4f14395808..5f1fc24d99 100644 > --- a/target/riscv/vector_helper.c > +++ b/target/riscv/vector_helper.c > @@ -2151,8 +2151,6 @@ 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, vl); > - > for (uint32_t i = env->vstart; i < vl; i++) { > if (!vm && !vext_elem_mask(v0, i)) { > /* set masked-off elements to 1s */ > @@ -2176,6 +2174,8 @@ vext_vv_rm_2(void *vd, void *v0, void *vs1, void *vs2, > uint32_t vta = vext_vta(desc); > uint32_t vma = vext_vma(desc); > > + VSTART_CHECK_EARLY_EXIT(env, vl); > + > switch (env->vxrm) { > case 0: /* rnu */ > vext_vv_rm_1(vd, v0, vs1, vs2, > @@ -2278,8 +2278,6 @@ 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, vl); > - > for (uint32_t i = env->vstart; i < vl; i++) { > if (!vm && !vext_elem_mask(v0, i)) { > /* set masked-off elements to 1s */ > @@ -2303,6 +2301,8 @@ vext_vx_rm_2(void *vd, void *v0, target_long s1, void *vs2, > uint32_t vta = vext_vta(desc); > uint32_t vma = vext_vma(desc); > > + VSTART_CHECK_EARLY_EXIT(env, vl); > + > switch (env->vxrm) { > case 0: /* rnu */ > vext_vx_rm_1(vd, v0, s1, vs2, > @@ -4638,6 +4638,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ > uint32_t i; \ > TD s1 = *((TD *)vs1 + HD(0)); \ > \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > + \ > for (i = env->vstart; i < vl; i++) { \ > TS2 s2 = *((TS2 *)vs2 + HS2(i)); \ > if (!vm && !vext_elem_mask(v0, i)) { \ > @@ -4724,6 +4726,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ > uint32_t i; \ > TD s1 = *((TD *)vs1 + HD(0)); \ > \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > + \ > for (i = env->vstart; i < vl; i++) { \ > TS2 s2 = *((TS2 *)vs2 + HS2(i)); \ > if (!vm && !vext_elem_mask(v0, i)) { \ > @@ -4886,6 +4890,8 @@ static void vmsetm(void *vd, void *v0, void *vs2, CPURISCVState *env, > int i; > bool first_mask_bit = false; > > + VSTART_CHECK_EARLY_EXIT(env, vl); > + > for (i = env->vstart; i < vl; i++) { > if (!vm && !vext_elem_mask(v0, i)) { > /* set masked-off elements to 1s */ > @@ -4958,6 +4964,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, CPURISCVState *env, \ > uint32_t sum = 0; \ > int i; \ > \ > + VSTART_CHECK_EARLY_EXIT(env, vl); \ > + \ > for (i = env->vstart; i < vl; i++) { \ > if (!vm && !vext_elem_mask(v0, i)) { \ > /* set masked-off elements to 1s */ \ > @@ -5316,6 +5324,8 @@ 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, vl); \ > + \ > for (i = env->vstart; i < vl; i++) { \ > if (!vext_elem_mask(vs1, i)) { \ > continue; \ ^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2024-12-26 13:48 UTC | newest] Thread overview: 5+ messages (download: mbox.gz follow: Atom feed -- links below jump to the message on this page -- 2024-12-18 7:15 [PATCH v2 0/2] Enhanced VSTART and VL Checks for Vector Instructions Chao Liu 2024-12-18 7:15 ` [PATCH v2 1/2] target/riscv: refactor VSTART_CHECK_EARLY_EXIT() to accept vl as a parameter Chao Liu 2024-12-26 13:16 ` Daniel Henrique Barboza 2024-12-18 7:15 ` [PATCH v2 2/2] target/riscv: fix handling of nop for vstart >= vl in some vector instruction Chao Liu 2024-12-26 13:48 ` Daniel Henrique Barboza
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.