target/arm: Implement SVE2 saturating multiply-add long

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-35-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Richard Henderson 2021-05-24 18:03:00 -07:00 committed by Peter Maydell
parent e0ae6ec383
commit bfc9307ee1
4 changed files with 112 additions and 0 deletions

View file

@ -1405,6 +1405,36 @@ void HELPER(sve2_adcl_d)(void *vd, void *vn, void *vm, void *va, uint32_t desc)
}
}
#define DO_SQDMLAL(NAME, TYPEW, TYPEN, HW, HN, DMUL_OP, SUM_OP) \
void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \
{ \
intptr_t i, opr_sz = simd_oprsz(desc); \
int sel1 = extract32(desc, SIMD_DATA_SHIFT, 1) * sizeof(TYPEN); \
int sel2 = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(TYPEN); \
for (i = 0; i < opr_sz; i += sizeof(TYPEW)) { \
TYPEW nn = *(TYPEN *)(vn + HN(i + sel1)); \
TYPEW mm = *(TYPEN *)(vm + HN(i + sel2)); \
TYPEW aa = *(TYPEW *)(va + HW(i)); \
*(TYPEW *)(vd + HW(i)) = SUM_OP(aa, DMUL_OP(nn, mm)); \
} \
}
DO_SQDMLAL(sve2_sqdmlal_zzzw_h, int16_t, int8_t, H1_2, H1,
do_sqdmull_h, DO_SQADD_H)
DO_SQDMLAL(sve2_sqdmlal_zzzw_s, int32_t, int16_t, H1_4, H1_2,
do_sqdmull_s, DO_SQADD_S)
DO_SQDMLAL(sve2_sqdmlal_zzzw_d, int64_t, int32_t, , H1_4,
do_sqdmull_d, do_sqadd_d)
DO_SQDMLAL(sve2_sqdmlsl_zzzw_h, int16_t, int8_t, H1_2, H1,
do_sqdmull_h, DO_SQSUB_H)
DO_SQDMLAL(sve2_sqdmlsl_zzzw_s, int32_t, int16_t, H1_4, H1_2,
do_sqdmull_s, DO_SQSUB_S)
DO_SQDMLAL(sve2_sqdmlsl_zzzw_d, int64_t, int32_t, , H1_4,
do_sqdmull_d, do_sqsub_d)
#undef DO_SQDMLAL
#define DO_BITPERM(NAME, TYPE, OP) \
void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
{ \