target/arm: Implement SVE2 signed saturating doubling multiply high

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-59-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Richard Henderson 2021-05-24 18:03:24 -07:00 committed by Peter Maydell
parent b95f5eebf6
commit 169d7c5825
4 changed files with 116 additions and 0 deletions

View File

@ -957,6 +957,16 @@ DEF_HELPER_FLAGS_5(neon_sqrdmulh_h, TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_5(neon_sqrdmulh_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_sqdmulh_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_sqdmulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_sqdmulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_sqdmulh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_sqrdmulh_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_sqrdmulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_sqrdmulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_sqrdmulh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_xar_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
#ifdef TARGET_AARCH64

View File

@ -1202,6 +1202,10 @@ SMULH_zzz 00000100 .. 1 ..... 0110 10 ..... ..... @rd_rn_rm
UMULH_zzz 00000100 .. 1 ..... 0110 11 ..... ..... @rd_rn_rm
PMUL_zzz 00000100 00 1 ..... 0110 01 ..... ..... @rd_rn_rm_e0
# SVE2 signed saturating doubling multiply high (unpredicated)
SQDMULH_zzz 00000100 .. 1 ..... 0111 00 ..... ..... @rd_rn_rm
SQRDMULH_zzz 00000100 .. 1 ..... 0111 01 ..... ..... @rd_rn_rm
### SVE2 Integer - Predicated
SADALP_zpzz 01000100 .. 000 100 101 ... ..... ..... @rdm_pg_rn

View File

@ -6433,6 +6433,24 @@ static bool trans_PMUL_zzz(DisasContext *s, arg_rrr_esz *a)
return do_sve2_zzz_ool(s, a, gen_helper_gvec_pmul_b);
}
static bool trans_SQDMULH_zzz(DisasContext *s, arg_rrr_esz *a)
{
static gen_helper_gvec_3 * const fns[4] = {
gen_helper_sve2_sqdmulh_b, gen_helper_sve2_sqdmulh_h,
gen_helper_sve2_sqdmulh_s, gen_helper_sve2_sqdmulh_d,
};
return do_sve2_zzz_ool(s, a, fns[a->esz]);
}
static bool trans_SQRDMULH_zzz(DisasContext *s, arg_rrr_esz *a)
{
static gen_helper_gvec_3 * const fns[4] = {
gen_helper_sve2_sqrdmulh_b, gen_helper_sve2_sqrdmulh_h,
gen_helper_sve2_sqrdmulh_s, gen_helper_sve2_sqrdmulh_d,
};
return do_sve2_zzz_ool(s, a, fns[a->esz]);
}
/*
* SVE2 Integer - Predicated
*/

View File

@ -81,6 +81,26 @@ void HELPER(sve2_sqrdmlsh_b)(void *vd, void *vn, void *vm,
}
}
void HELPER(sve2_sqdmulh_b)(void *vd, void *vn, void *vm, uint32_t desc)
{
intptr_t i, opr_sz = simd_oprsz(desc);
int8_t *d = vd, *n = vn, *m = vm;
for (i = 0; i < opr_sz; ++i) {
d[i] = do_sqrdmlah_b(n[i], m[i], 0, false, false);
}
}
void HELPER(sve2_sqrdmulh_b)(void *vd, void *vn, void *vm, uint32_t desc)
{
intptr_t i, opr_sz = simd_oprsz(desc);
int8_t *d = vd, *n = vn, *m = vm;
for (i = 0; i < opr_sz; ++i) {
d[i] = do_sqrdmlah_b(n[i], m[i], 0, false, true);
}
}
/* Signed saturating rounding doubling multiply-accumulate high half, 16-bit */
int16_t do_sqrdmlah_h(int16_t src1, int16_t src2, int16_t src3,
bool neg, bool round, uint32_t *sat)
@ -198,6 +218,28 @@ void HELPER(sve2_sqrdmlsh_h)(void *vd, void *vn, void *vm,
}
}
void HELPER(sve2_sqdmulh_h)(void *vd, void *vn, void *vm, uint32_t desc)
{
intptr_t i, opr_sz = simd_oprsz(desc);
int16_t *d = vd, *n = vn, *m = vm;
uint32_t discard;
for (i = 0; i < opr_sz / 2; ++i) {
d[i] = do_sqrdmlah_h(n[i], m[i], 0, false, false, &discard);
}
}
void HELPER(sve2_sqrdmulh_h)(void *vd, void *vn, void *vm, uint32_t desc)
{
intptr_t i, opr_sz = simd_oprsz(desc);
int16_t *d = vd, *n = vn, *m = vm;
uint32_t discard;
for (i = 0; i < opr_sz / 2; ++i) {
d[i] = do_sqrdmlah_h(n[i], m[i], 0, false, true, &discard);
}
}
/* Signed saturating rounding doubling multiply-accumulate high half, 32-bit */
int32_t do_sqrdmlah_s(int32_t src1, int32_t src2, int32_t src3,
bool neg, bool round, uint32_t *sat)
@ -309,6 +351,28 @@ void HELPER(sve2_sqrdmlsh_s)(void *vd, void *vn, void *vm,
}
}
void HELPER(sve2_sqdmulh_s)(void *vd, void *vn, void *vm, uint32_t desc)
{
intptr_t i, opr_sz = simd_oprsz(desc);
int32_t *d = vd, *n = vn, *m = vm;
uint32_t discard;
for (i = 0; i < opr_sz / 4; ++i) {
d[i] = do_sqrdmlah_s(n[i], m[i], 0, false, false, &discard);
}
}
void HELPER(sve2_sqrdmulh_s)(void *vd, void *vn, void *vm, uint32_t desc)
{
intptr_t i, opr_sz = simd_oprsz(desc);
int32_t *d = vd, *n = vn, *m = vm;
uint32_t discard;
for (i = 0; i < opr_sz / 4; ++i) {
d[i] = do_sqrdmlah_s(n[i], m[i], 0, false, true, &discard);
}
}
/* Signed saturating rounding doubling multiply-accumulate high half, 64-bit */
static int64_t do_sat128_d(Int128 r)
{
@ -368,6 +432,26 @@ void HELPER(sve2_sqrdmlsh_d)(void *vd, void *vn, void *vm,
}
}
void HELPER(sve2_sqdmulh_d)(void *vd, void *vn, void *vm, uint32_t desc)
{
intptr_t i, opr_sz = simd_oprsz(desc);
int64_t *d = vd, *n = vn, *m = vm;
for (i = 0; i < opr_sz / 8; ++i) {
d[i] = do_sqrdmlah_d(n[i], m[i], 0, false, false);
}
}
void HELPER(sve2_sqrdmulh_d)(void *vd, void *vn, void *vm, uint32_t desc)
{
intptr_t i, opr_sz = simd_oprsz(desc);
int64_t *d = vd, *n = vn, *m = vm;
for (i = 0; i < opr_sz / 8; ++i) {
d[i] = do_sqrdmlah_d(n[i], m[i], 0, false, true);
}
}
/* Integer 8 and 16-bit dot-product.
*
* Note that for the loops herein, host endianness does not matter