[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PULL 58/59] target/riscv/vector_helper.c: create vext_set_tail_elems_1s
|
From: |
Palmer Dabbelt |
|
Subject: |
[PULL 58/59] target/riscv/vector_helper.c: create vext_set_tail_elems_1s() |
|
Date: |
Fri, 3 Mar 2023 00:37:39 -0800 |
From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Commit 752614cab8e6 ("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>
---
target/riscv/vector_helper.c | 86 +++++++++++++-----------------------
1 file changed, 30 insertions(+), 56 deletions(-)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 3073c54871..7e476ea8c3 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 = 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) \
--
2.39.2
- [PULL 48/59] target/riscv: Fix the relationship between menvcfg.PBMTE/STCE and Svpbmt/Sstc extensions, (continued)
- [PULL 48/59] target/riscv: Fix the relationship between menvcfg.PBMTE/STCE and Svpbmt/Sstc extensions, Palmer Dabbelt, 2023/03/03
- [PULL 45/59] target/riscv: Add support for Zicond extension, Palmer Dabbelt, 2023/03/03
- [PULL 55/59] target/riscv/csr.c: simplify mctr(), Palmer Dabbelt, 2023/03/03
- [PULL 47/59] hw/riscv: Move the dtb load bits outside of create_fdt(), Palmer Dabbelt, 2023/03/03
- [PULL 49/59] target/riscv: Fix the relationship of PBMTE/STCE fields between menvcfg and henvcfg, Palmer Dabbelt, 2023/03/03
- [PULL 50/59] target/riscv: Add csr support for svadu, Palmer Dabbelt, 2023/03/03
- [PULL 51/59] target/riscv: Add *envcfg.PBMTE related check in address translation, Palmer Dabbelt, 2023/03/03
- [PULL 52/59] target/riscv: Add *envcfg.HADE related check in address translation, Palmer Dabbelt, 2023/03/03
- [PULL 53/59] target/riscv: Export Svadu property, Palmer Dabbelt, 2023/03/03
- [PULL 57/59] target/riscv/csr.c: avoid env_archcpu() usages when reading RISCVCPUConfig, Palmer Dabbelt, 2023/03/03
- [PULL 58/59] target/riscv/vector_helper.c: create vext_set_tail_elems_1s(),
Palmer Dabbelt <=
- [PULL 56/59] target/riscv/csr.c: use riscv_cpu_cfg() to avoid env_cpu() pointers, Palmer Dabbelt, 2023/03/03
- [PULL 54/59] target/riscv/csr.c: use env_archcpu() in ctr(), Palmer Dabbelt, 2023/03/03
- [PULL 59/59] target/riscv/vector_helper.c: avoid env_archcpu() when reading RISCVCPUConfig, Palmer Dabbelt, 2023/03/03
- Re: [PULL 00/59] Fifth RISC-V PR for QEMU 8.0, Peter Maydell, 2023/03/03
- Re: [PULL 00/59] Fifth RISC-V PR for QEMU 8.0, Peter Maydell, 2023/03/03