OpenE2K
/
qemu-e2k
13
4
Fork 0
Code Issues 4 Pull Requests Projects 2 Releases Activity

target/riscv/vector_helper.c: create vext_set_tail_elems_1s() 

Commit 752614cab8 ("target/riscv: rvv: Add tail agnostic for vector
load / store instructions") added code to set the tail elements to 1 in
the end of vext_ldst_stride(), vext_ldst_us(), vext_ldst_index() and
vext_ldff(). Aside from a env->vl versus an evl value being used in the
first loop, the code is being repeated 4 times.

Create a helper to avoid code repetition in all those functions.
Arguments that are used in the callers (nf, esz and max_elems) are
passed as arguments. All other values are being derived inside the
helper.

Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Message-ID: <20230226170514.588071-2-dbarboza@ventanamicro.com>
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
This commit is contained in:
Daniel Henrique Barboza 2023-02-26 14:05:13 -03:00 committed by Palmer Dabbelt
parent d4ea711704
commit e130683ffb
No known key found for this signature in database
GPG Key ID: 2E1319F35FBB1889
1 changed files with 30 additions and 56 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

86
target/riscv/vector_helper.c
View File

@ -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 = env_archcpu(env)->cfg.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) \