diff options
author | Palmer Dabbelt <palmer@rivosinc.com> | 2023-03-01 18:09:48 -0800 |
---|---|---|
committer | Palmer Dabbelt <palmer@rivosinc.com> | 2023-03-01 18:09:48 -0800 |
commit | 37151032989ecf6e7ce8b65bc7bcb400d0318b2c (patch) | |
tree | 6ec20fbbafd6a6002581b0bc927535f9131e9a88 /target/riscv | |
parent | 0b28c7ea0edbb6858adcce7f0ddf761441e730e8 (diff) | |
parent | 86247c51fff458fb238a1690232c16e8425b15d3 (diff) | |
download | qemu-37151032989ecf6e7ce8b65bc7bcb400d0318b2c.zip qemu-37151032989ecf6e7ce8b65bc7bcb400d0318b2c.tar.gz qemu-37151032989ecf6e7ce8b65bc7bcb400d0318b2c.tar.bz2 |
Merge patch series "target/riscv: some vector_helper.c cleanups"
Daniel Henrique Barboza <dbarboza@ventanamicro.com> says:
This is a re-send of patch 1, which is already reviewed, with a
follow-up that uses riscv_cpu_cfg() in the remaining of the file. This
was suggested by Weiwei Li in the "[PATCH 0/4] RISCVCPUConfig related
cleanups" review. Patch 1 makes the work of patch 2 easier since it
eliminated some uses of env_archcpu() we want to avoid.
* b4-shazam-merge:
target/riscv/vector_helper.c: avoid env_archcpu() when reading RISCVCPUConfig
target/riscv/vector_helper.c: create vext_set_tail_elems_1s()
Message-ID: <20230226170514.588071-1-dbarboza@ventanamicro.com>
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
Diffstat (limited to 'target/riscv')
-rw-r--r-- | target/riscv/vector_helper.c | 104 |
1 files changed, 39 insertions, 65 deletions
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 3073c54..2423aff 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -267,6 +267,28 @@ GEN_VEXT_ST_ELEM(ste_h, int16_t, H2, stw) GEN_VEXT_ST_ELEM(ste_w, int32_t, H4, stl) GEN_VEXT_ST_ELEM(ste_d, int64_t, H8, stq) +static void vext_set_tail_elems_1s(CPURISCVState *env, target_ulong vl, + void *vd, uint32_t desc, uint32_t nf, + uint32_t esz, uint32_t max_elems) +{ + uint32_t total_elems = vext_get_total_elems(env, desc, esz); + uint32_t vlenb = riscv_cpu_cfg(env)->vlen >> 3; + uint32_t vta = vext_vta(desc); + uint32_t registers_used; + int k; + + for (k = 0; k < nf; ++k) { + vext_set_elems_1s(vd, vta, (k * max_elems + vl) * esz, + (k * max_elems + max_elems) * esz); + } + + if (nf * max_elems % total_elems != 0) { + registers_used = ((nf * max_elems) * esz + (vlenb - 1)) / vlenb; + vext_set_elems_1s(vd, vta, (nf * max_elems) * esz, + registers_used * vlenb); + } +} + /* *** stride: access vector element from strided memory */ @@ -281,8 +303,6 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base, uint32_t nf = vext_nf(desc); uint32_t max_elems = vext_max_elems(desc, log2_esz); uint32_t esz = 1 << log2_esz; - uint32_t total_elems = vext_get_total_elems(env, desc, esz); - uint32_t vta = vext_vta(desc); uint32_t vma = vext_vma(desc); for (i = env->vstart; i < env->vl; i++, env->vstart++) { @@ -301,18 +321,8 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base, } } env->vstart = 0; - /* set tail elements to 1s */ - for (k = 0; k < nf; ++k) { - vext_set_elems_1s(vd, vta, (k * max_elems + env->vl) * esz, - (k * max_elems + max_elems) * esz); - } - if (nf * max_elems % total_elems != 0) { - uint32_t vlenb = env_archcpu(env)->cfg.vlen >> 3; - uint32_t registers_used = - ((nf * max_elems) * esz + (vlenb - 1)) / vlenb; - vext_set_elems_1s(vd, vta, (nf * max_elems) * esz, - registers_used * vlenb); - } + + vext_set_tail_elems_1s(env, env->vl, vd, desc, nf, esz, max_elems); } #define GEN_VEXT_LD_STRIDE(NAME, ETYPE, LOAD_FN) \ @@ -359,8 +369,6 @@ vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc, uint32_t nf = vext_nf(desc); uint32_t max_elems = vext_max_elems(desc, log2_esz); uint32_t esz = 1 << log2_esz; - uint32_t total_elems = vext_get_total_elems(env, desc, esz); - uint32_t vta = vext_vta(desc); /* load bytes from guest memory */ for (i = env->vstart; i < evl; i++, env->vstart++) { @@ -372,18 +380,8 @@ vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc, } } env->vstart = 0; - /* set tail elements to 1s */ - for (k = 0; k < nf; ++k) { - vext_set_elems_1s(vd, vta, (k * max_elems + evl) * esz, - (k * max_elems + max_elems) * esz); - } - if (nf * max_elems % total_elems != 0) { - uint32_t vlenb = env_archcpu(env)->cfg.vlen >> 3; - uint32_t registers_used = - ((nf * max_elems) * esz + (vlenb - 1)) / vlenb; - vext_set_elems_1s(vd, vta, (nf * max_elems) * esz, - registers_used * vlenb); - } + + vext_set_tail_elems_1s(env, evl, vd, desc, nf, esz, max_elems); } /* @@ -484,8 +482,6 @@ vext_ldst_index(void *vd, void *v0, target_ulong base, uint32_t vm = vext_vm(desc); uint32_t max_elems = vext_max_elems(desc, log2_esz); uint32_t esz = 1 << log2_esz; - uint32_t total_elems = vext_get_total_elems(env, desc, esz); - uint32_t vta = vext_vta(desc); uint32_t vma = vext_vma(desc); /* load bytes from guest memory */ @@ -505,18 +501,8 @@ vext_ldst_index(void *vd, void *v0, target_ulong base, } } env->vstart = 0; - /* set tail elements to 1s */ - for (k = 0; k < nf; ++k) { - vext_set_elems_1s(vd, vta, (k * max_elems + env->vl) * esz, - (k * max_elems + max_elems) * esz); - } - if (nf * max_elems % total_elems != 0) { - uint32_t vlenb = env_archcpu(env)->cfg.vlen >> 3; - uint32_t registers_used = - ((nf * max_elems) * esz + (vlenb - 1)) / vlenb; - vext_set_elems_1s(vd, vta, (nf * max_elems) * esz, - registers_used * vlenb); - } + + vext_set_tail_elems_1s(env, env->vl, vd, desc, nf, esz, max_elems); } #define GEN_VEXT_LD_INDEX(NAME, ETYPE, INDEX_FN, LOAD_FN) \ @@ -585,8 +571,6 @@ vext_ldff(void *vd, void *v0, target_ulong base, uint32_t vm = vext_vm(desc); uint32_t max_elems = vext_max_elems(desc, log2_esz); uint32_t esz = 1 << log2_esz; - uint32_t total_elems = vext_get_total_elems(env, desc, esz); - uint32_t vta = vext_vta(desc); uint32_t vma = vext_vma(desc); target_ulong addr, offset, remain; @@ -647,18 +631,8 @@ ProbeSuccess: } } env->vstart = 0; - /* set tail elements to 1s */ - for (k = 0; k < nf; ++k) { - vext_set_elems_1s(vd, vta, (k * max_elems + env->vl) * esz, - (k * max_elems + max_elems) * esz); - } - if (nf * max_elems % total_elems != 0) { - uint32_t vlenb = env_archcpu(env)->cfg.vlen >> 3; - uint32_t registers_used = - ((nf * max_elems) * esz + (vlenb - 1)) / vlenb; - vext_set_elems_1s(vd, vta, (nf * max_elems) * esz, - registers_used * vlenb); - } + + vext_set_tail_elems_1s(env, env->vl, vd, desc, nf, esz, max_elems); } #define GEN_VEXT_LDFF(NAME, ETYPE, LOAD_FN) \ @@ -697,7 +671,7 @@ vext_ldst_whole(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc, { uint32_t i, k, off, pos; uint32_t nf = vext_nf(desc); - uint32_t vlenb = env_archcpu(env)->cfg.vlen >> 3; + uint32_t vlenb = riscv_cpu_cfg(env)->vlen >> 3; uint32_t max_elems = vlenb >> log2_esz; k = env->vstart / max_elems; @@ -1167,7 +1141,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ { \ uint32_t vl = env->vl; \ uint32_t vm = vext_vm(desc); \ - uint32_t total_elems = env_archcpu(env)->cfg.vlen; \ + uint32_t total_elems = riscv_cpu_cfg(env)->vlen; \ uint32_t vta_all_1s = vext_vta_all_1s(desc); \ uint32_t i; \ \ @@ -1203,7 +1177,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \ { \ uint32_t vl = env->vl; \ uint32_t vm = vext_vm(desc); \ - uint32_t total_elems = env_archcpu(env)->cfg.vlen; \ + uint32_t total_elems = riscv_cpu_cfg(env)->vlen; \ uint32_t vta_all_1s = vext_vta_all_1s(desc); \ uint32_t i; \ \ @@ -1402,7 +1376,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ { \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ - uint32_t total_elems = env_archcpu(env)->cfg.vlen; \ + uint32_t total_elems = riscv_cpu_cfg(env)->vlen; \ uint32_t vta_all_1s = vext_vta_all_1s(desc); \ uint32_t vma = vext_vma(desc); \ uint32_t i; \ @@ -1465,7 +1439,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ { \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ - uint32_t total_elems = env_archcpu(env)->cfg.vlen; \ + uint32_t total_elems = riscv_cpu_cfg(env)->vlen; \ uint32_t vta_all_1s = vext_vta_all_1s(desc); \ uint32_t vma = vext_vma(desc); \ uint32_t i; \ @@ -4178,7 +4152,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ { \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ - uint32_t total_elems = env_archcpu(env)->cfg.vlen; \ + uint32_t total_elems = riscv_cpu_cfg(env)->vlen; \ uint32_t vta_all_1s = vext_vta_all_1s(desc); \ uint32_t vma = vext_vma(desc); \ uint32_t i; \ @@ -4216,7 +4190,7 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \ { \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ - uint32_t total_elems = env_archcpu(env)->cfg.vlen; \ + uint32_t total_elems = riscv_cpu_cfg(env)->vlen; \ uint32_t vta_all_1s = vext_vta_all_1s(desc); \ uint32_t vma = vext_vma(desc); \ uint32_t i; \ @@ -4747,7 +4721,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ uint32_t desc) \ { \ uint32_t vl = env->vl; \ - uint32_t total_elems = env_archcpu(env)->cfg.vlen; \ + uint32_t total_elems = riscv_cpu_cfg(env)->vlen; \ uint32_t vta_all_1s = vext_vta_all_1s(desc); \ uint32_t i; \ int a, b; \ @@ -4834,7 +4808,7 @@ static void vmsetm(void *vd, void *v0, void *vs2, CPURISCVState *env, { uint32_t vm = vext_vm(desc); uint32_t vl = env->vl; - uint32_t total_elems = env_archcpu(env)->cfg.vlen; + uint32_t total_elems = riscv_cpu_cfg(env)->vlen; uint32_t vta_all_1s = vext_vta_all_1s(desc); uint32_t vma = vext_vma(desc); int i; |