haraldwolff/qemu-patch-raspberry4
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

target/arm: Implement SVE2 saturating multiply-add high (indexed)

Browse source 
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-56-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Richard Henderson 2021-05-24 18:03:21 -07:00 committed by Peter Maydell
parent 8a02aac740
commit 75d6d5fc33
4 changed files with 66 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
target/arm/helper-sve.h
View file

@ -2665,3 +2665,17 @@ DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_zzzz_d, TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_6(fmmla_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_6(fmmla_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_sqrdmlah_idx_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_sqrdmlah_idx_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_sqrdmlah_idx_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_idx_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_idx_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_idx_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)

8
target/arm/sve.decode
View file

@ -791,6 +791,14 @@ MLS_zzxz_h 01000100 0. 1 ..... 000011 ..... ..... @rrxr_3 esz=1
MLS_zzxz_s 01000100 10 1 ..... 000011 ..... ..... @rrxr_2 esz=2
MLS_zzxz_d 01000100 11 1 ..... 000011 ..... ..... @rrxr_1 esz=3
# SVE2 saturating multiply-add high (indexed)
SQRDMLAH_zzxz_h 01000100 0. 1 ..... 000100 ..... ..... @rrxr_3 esz=1
SQRDMLAH_zzxz_s 01000100 10 1 ..... 000100 ..... ..... @rrxr_2 esz=2
SQRDMLAH_zzxz_d 01000100 11 1 ..... 000100 ..... ..... @rrxr_1 esz=3
SQRDMLSH_zzxz_h 01000100 0. 1 ..... 000101 ..... ..... @rrxr_3 esz=1
SQRDMLSH_zzxz_s 01000100 10 1 ..... 000101 ..... ..... @rrxr_2 esz=2
SQRDMLSH_zzxz_d 01000100 11 1 ..... 000101 ..... ..... @rrxr_1 esz=3
# SVE2 integer multiply (indexed)
MUL_zzx_h 01000100 0. 1 ..... 111110 ..... ..... @rrx_3 esz=1
MUL_zzx_s 01000100 10 1 ..... 111110 ..... ..... @rrx_2 esz=2

36
target/arm/sve_helper.c
View file

@ -1499,6 +1499,42 @@ DO_CMLA_FUNC(sve2_sqrdcmlah_zzzz_d, int64_t, , DO_SQRDMLAH_D)
#undef DO_SQRDMLAH_S
#undef DO_SQRDMLAH_D
#define DO_ZZXZ(NAME, TYPE, H, OP) \
void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \
{ \
intptr_t oprsz = simd_oprsz(desc), segment = 16 / sizeof(TYPE); \
intptr_t i, j, idx = simd_data(desc); \
TYPE *d = vd, *a = va, *n = vn, *m = (TYPE *)vm + H(idx); \
for (i = 0; i < oprsz / sizeof(TYPE); i += segment) { \
TYPE mm = m[i]; \
for (j = 0; j < segment; j++) { \
d[i + j] = OP(n[i + j], mm, a[i + j]); \
} \
} \
}
#define DO_SQRDMLAH_H(N, M, A) \
({ uint32_t discard; do_sqrdmlah_h(N, M, A, false, true, &discard); })
#define DO_SQRDMLAH_S(N, M, A) \
({ uint32_t discard; do_sqrdmlah_s(N, M, A, false, true, &discard); })
#define DO_SQRDMLAH_D(N, M, A) do_sqrdmlah_d(N, M, A, false, true)
DO_ZZXZ(sve2_sqrdmlah_idx_h, int16_t, H2, DO_SQRDMLAH_H)
DO_ZZXZ(sve2_sqrdmlah_idx_s, int32_t, H4, DO_SQRDMLAH_S)
DO_ZZXZ(sve2_sqrdmlah_idx_d, int64_t, , DO_SQRDMLAH_D)
#define DO_SQRDMLSH_H(N, M, A) \
({ uint32_t discard; do_sqrdmlah_h(N, M, A, true, true, &discard); })
#define DO_SQRDMLSH_S(N, M, A) \
({ uint32_t discard; do_sqrdmlah_s(N, M, A, true, true, &discard); })
#define DO_SQRDMLSH_D(N, M, A) do_sqrdmlah_d(N, M, A, true, true)
DO_ZZXZ(sve2_sqrdmlsh_idx_h, int16_t, H2, DO_SQRDMLSH_H)
DO_ZZXZ(sve2_sqrdmlsh_idx_s, int32_t, H4, DO_SQRDMLSH_S)
DO_ZZXZ(sve2_sqrdmlsh_idx_d, int64_t, , DO_SQRDMLSH_D)
#undef DO_ZZXZ
#define DO_BITPERM(NAME, TYPE, OP) \
void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
{ \

8
target/arm/translate-sve.c
View file

@ -3895,6 +3895,14 @@ DO_SVE2_RRXR(trans_MLS_zzxz_h, gen_helper_gvec_mls_idx_h)
DO_SVE2_RRXR(trans_MLS_zzxz_s, gen_helper_gvec_mls_idx_s)
DO_SVE2_RRXR(trans_MLS_zzxz_d, gen_helper_gvec_mls_idx_d)
DO_SVE2_RRXR(trans_SQRDMLAH_zzxz_h, gen_helper_sve2_sqrdmlah_idx_h)
DO_SVE2_RRXR(trans_SQRDMLAH_zzxz_s, gen_helper_sve2_sqrdmlah_idx_s)
DO_SVE2_RRXR(trans_SQRDMLAH_zzxz_d, gen_helper_sve2_sqrdmlah_idx_d)
DO_SVE2_RRXR(trans_SQRDMLSH_zzxz_h, gen_helper_sve2_sqrdmlsh_idx_h)
DO_SVE2_RRXR(trans_SQRDMLSH_zzxz_s, gen_helper_sve2_sqrdmlsh_idx_s)
DO_SVE2_RRXR(trans_SQRDMLSH_zzxz_d, gen_helper_sve2_sqrdmlsh_idx_d)
#undef DO_SVE2_RRXR
/*