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

target/riscv: vector widening floating-point reduction instructions

Browse Source 
Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <20200701152549.1218-49-zhiwei_liu@c-sky.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
This commit is contained in:
LIU Zhiwei 2020-07-01 23:25:36 +08:00 committed by Alistair Francis
parent 523547f19e
commit 696b0c260a
4 changed files with 54 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
target/riscv/helper.h
View File

@ -1089,3 +1089,6 @@ DEF_HELPER_6(vfredmax_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_6(vfredmin_vs_h, void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_6(vfredmin_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_6(vfredmin_vs_w, void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_6(vfredmin_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_6(vfredmin_vs_d, void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_6(vfredmin_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_6(vfwredsum_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_6(vfwredsum_vs_w, void, ptr, ptr, ptr, ptr, env, i32)

2
target/riscv/insn32.decode
View File

@ -545,6 +545,8 @@ vwredsum_vs 110001 . ..... ..... 000 ..... 1010111 @r_vm
vfredsum_vs 0000-1 . ..... ..... 001 ..... 1010111 @r_vm vfredsum_vs 0000-1 . ..... ..... 001 ..... 1010111 @r_vm
vfredmin_vs 000101 . ..... ..... 001 ..... 1010111 @r_vm vfredmin_vs 000101 . ..... ..... 001 ..... 1010111 @r_vm
vfredmax_vs 000111 . ..... ..... 001 ..... 1010111 @r_vm vfredmax_vs 000111 . ..... ..... 001 ..... 1010111 @r_vm
# Vector widening ordered and unordered float reduction sum
vfwredsum_vs 1100-1 . ..... ..... 001 ..... 1010111 @r_vm
vsetvli 0 ........... ..... 111 ..... 1010111 @r2_zimm vsetvli 0 ........... ..... 111 ..... 1010111 @r2_zimm
vsetvl 1000000 ..... ..... 111 ..... 1010111 @r vsetvl 1000000 ..... ..... 111 ..... 1010111 @r

3
target/riscv/insn_trans/trans_rvv.inc.c
View File

@ -2351,3 +2351,6 @@ GEN_OPIVV_WIDEN_TRANS(vwredsumu_vs, reduction_check)
GEN_OPFVV_TRANS(vfredsum_vs, reduction_check) GEN_OPFVV_TRANS(vfredsum_vs, reduction_check)
GEN_OPFVV_TRANS(vfredmax_vs, reduction_check) GEN_OPFVV_TRANS(vfredmax_vs, reduction_check)
GEN_OPFVV_TRANS(vfredmin_vs, reduction_check) GEN_OPFVV_TRANS(vfredmin_vs, reduction_check)
/* Vector Widening Floating-Point Reduction Instructions */
GEN_OPFVV_WIDEN_TRANS(vfwredsum_vs, reduction_check)

46
target/riscv/vector_helper.c
View File

@ -4456,3 +4456,49 @@ GEN_VEXT_FRED(vfredmax_vs_d, uint64_t, uint64_t, H8, H8, float64_maxnum, clearq)
GEN_VEXT_FRED(vfredmin_vs_h, uint16_t, uint16_t, H2, H2, float16_minnum, clearh) GEN_VEXT_FRED(vfredmin_vs_h, uint16_t, uint16_t, H2, H2, float16_minnum, clearh)
GEN_VEXT_FRED(vfredmin_vs_w, uint32_t, uint32_t, H4, H4, float32_minnum, clearl) GEN_VEXT_FRED(vfredmin_vs_w, uint32_t, uint32_t, H4, H4, float32_minnum, clearl)
GEN_VEXT_FRED(vfredmin_vs_d, uint64_t, uint64_t, H8, H8, float64_minnum, clearq) GEN_VEXT_FRED(vfredmin_vs_d, uint64_t, uint64_t, H8, H8, float64_minnum, clearq)
/* Vector Widening Floating-Point Reduction Instructions */
/* Unordered reduce 2*SEW = 2*SEW + sum(promote(SEW)) */
void HELPER(vfwredsum_vs_h)(void *vd, void *v0, void *vs1,
void *vs2, CPURISCVState *env, uint32_t desc)
{
uint32_t mlen = vext_mlen(desc);
uint32_t vm = vext_vm(desc);
uint32_t vl = env->vl;
uint32_t i;
uint32_t tot = env_archcpu(env)->cfg.vlen / 8;
uint32_t s1 = *((uint32_t *)vs1 + H4(0));
for (i = 0; i < vl; i++) {
uint16_t s2 = *((uint16_t *)vs2 + H2(i));
if (!vm && !vext_elem_mask(v0, mlen, i)) {
continue;
}
s1 = float32_add(s1, float16_to_float32(s2, true, &env->fp_status),
&env->fp_status);
}
*((uint32_t *)vd + H4(0)) = s1;
clearl(vd, 1, sizeof(uint32_t), tot);
}
void HELPER(vfwredsum_vs_w)(void *vd, void *v0, void *vs1,
void *vs2, CPURISCVState *env, uint32_t desc)
{
uint32_t mlen = vext_mlen(desc);
uint32_t vm = vext_vm(desc);
uint32_t vl = env->vl;
uint32_t i;
uint32_t tot = env_archcpu(env)->cfg.vlen / 8;
uint64_t s1 = *((uint64_t *)vs1);
for (i = 0; i < vl; i++) {
uint32_t s2 = *((uint32_t *)vs2 + H4(i));
if (!vm && !vext_elem_mask(v0, mlen, i)) {
continue;
}
s1 = float64_add(s1, float32_to_float64(s2, &env->fp_status),
&env->fp_status);
}
*((uint64_t *)vd) = s1;
clearq(vd, 1, sizeof(uint64_t), tot);
}