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

target/arm: Convert integer multiply-add (indexed) to gvec for aa64 advsimd 

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20200815013145.539409-20-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Richard Henderson 2020-08-28 10:02:50 +01:00 committed by Peter Maydell
parent 2e5a265e6a
commit 3607440c4d
3 changed files with 73 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
target/arm/helper.h
View File

@ -762,6 +762,20 @@ DEF_HELPER_FLAGS_4(gvec_mul_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_mul_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_mul_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_mla_idx_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_mla_idx_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_mla_idx_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_mls_idx_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_mls_idx_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_mls_idx_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
#ifdef TARGET_AARCH64
#include "helper-a64.h"
#include "helper-sve.h"

34
target/arm/translate-a64.c
View File

@ -13504,6 +13504,40 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
return;
}
break;
case 0x10: /* MLA */
if (!is_long && !is_scalar) {
static gen_helper_gvec_4 * const fns[3] = {
gen_helper_gvec_mla_idx_h,
gen_helper_gvec_mla_idx_s,
gen_helper_gvec_mla_idx_d,
};
tcg_gen_gvec_4_ool(vec_full_reg_offset(s, rd),
vec_full_reg_offset(s, rn),
vec_full_reg_offset(s, rm),
vec_full_reg_offset(s, rd),
is_q ? 16 : 8, vec_full_reg_size(s),
index, fns[size - 1]);
return;
}
break;
case 0x14: /* MLS */
if (!is_long && !is_scalar) {
static gen_helper_gvec_4 * const fns[3] = {
gen_helper_gvec_mls_idx_h,
gen_helper_gvec_mls_idx_s,
gen_helper_gvec_mls_idx_d,
};
tcg_gen_gvec_4_ool(vec_full_reg_offset(s, rd),
vec_full_reg_offset(s, rn),
vec_full_reg_offset(s, rm),
vec_full_reg_offset(s, rd),
is_q ? 16 : 8, vec_full_reg_size(s),
index, fns[size - 1]);
return;
}
break;
}
if (size == 3) {

25
target/arm/vec_helper.c
View File

@ -731,6 +731,31 @@ DO_MUL_IDX(gvec_mul_idx_d, uint64_t, )
#undef DO_MUL_IDX
#define DO_MLA_IDX(NAME, TYPE, OP, H) \
void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \
{ \
intptr_t i, j, oprsz = simd_oprsz(desc), segment = 16 / sizeof(TYPE); \
intptr_t idx = simd_data(desc); \
TYPE *d = vd, *n = vn, *m = vm, *a = va; \
for (i = 0; i < oprsz / sizeof(TYPE); i += segment) { \
TYPE mm = m[H(i + idx)]; \
for (j = 0; j < segment; j++) { \
d[i + j] = a[i + j] OP n[i + j] * mm; \
} \
} \
clear_tail(d, oprsz, simd_maxsz(desc)); \
}
DO_MLA_IDX(gvec_mla_idx_h, uint16_t, +, H2)
DO_MLA_IDX(gvec_mla_idx_s, uint32_t, +, H4)
DO_MLA_IDX(gvec_mla_idx_d, uint64_t, +, )
DO_MLA_IDX(gvec_mls_idx_h, uint16_t, -, H2)
DO_MLA_IDX(gvec_mls_idx_s, uint32_t, -, H4)
DO_MLA_IDX(gvec_mls_idx_d, uint64_t, -, )
#undef DO_MLA_IDX
#define DO_FMUL_IDX(NAME, TYPE, H) \
void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \
{ \