Skip to content

Commit

Permalink
target/arm: Implement SVE2 integer add/subtract long
Browse files Browse the repository at this point in the history
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-11-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
  • Loading branch information
rth7680 authored and pm215 committed May 25, 2021
1 parent 4f07fbe commit 0ce1dda
Show file tree
Hide file tree
Showing 4 changed files with 132 additions and 0 deletions.
24 changes: 24 additions & 0 deletions target/arm/helper-sve.h
Expand Up @@ -1367,6 +1367,30 @@ DEF_HELPER_FLAGS_5(sve_ftmad_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve_ftmad_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve_ftmad_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)

DEF_HELPER_FLAGS_4(sve2_saddl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_saddl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_saddl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)

DEF_HELPER_FLAGS_4(sve2_ssubl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_ssubl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_ssubl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)

DEF_HELPER_FLAGS_4(sve2_sabdl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_sabdl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_sabdl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)

DEF_HELPER_FLAGS_4(sve2_uaddl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_uaddl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_uaddl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)

DEF_HELPER_FLAGS_4(sve2_usubl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_usubl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_usubl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)

DEF_HELPER_FLAGS_4(sve2_uabdl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_uabdl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_uabdl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)

DEF_HELPER_FLAGS_4(sve_ld1bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ld2bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ld3bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
Expand Down
19 changes: 19 additions & 0 deletions target/arm/sve.decode
Expand Up @@ -1159,3 +1159,22 @@ SUQADD 01000100 .. 011 100 100 ... ..... ..... @rdn_pg_rm
USQADD 01000100 .. 011 101 100 ... ..... ..... @rdn_pg_rm
SQSUB_zpzz 01000100 .. 011 110 100 ... ..... ..... @rdm_pg_rn # SQSUBR
UQSUB_zpzz 01000100 .. 011 111 100 ... ..... ..... @rdm_pg_rn # UQSUBR

#### SVE2 Widening Integer Arithmetic

## SVE2 integer add/subtract long

SADDLB 01000101 .. 0 ..... 00 0000 ..... ..... @rd_rn_rm
SADDLT 01000101 .. 0 ..... 00 0001 ..... ..... @rd_rn_rm
UADDLB 01000101 .. 0 ..... 00 0010 ..... ..... @rd_rn_rm
UADDLT 01000101 .. 0 ..... 00 0011 ..... ..... @rd_rn_rm

SSUBLB 01000101 .. 0 ..... 00 0100 ..... ..... @rd_rn_rm
SSUBLT 01000101 .. 0 ..... 00 0101 ..... ..... @rd_rn_rm
USUBLB 01000101 .. 0 ..... 00 0110 ..... ..... @rd_rn_rm
USUBLT 01000101 .. 0 ..... 00 0111 ..... ..... @rd_rn_rm

SABDLB 01000101 .. 0 ..... 00 1100 ..... ..... @rd_rn_rm
SABDLT 01000101 .. 0 ..... 00 1101 ..... ..... @rd_rn_rm
UABDLB 01000101 .. 0 ..... 00 1110 ..... ..... @rd_rn_rm
UABDLT 01000101 .. 0 ..... 00 1111 ..... ..... @rd_rn_rm
43 changes: 43 additions & 0 deletions target/arm/sve_helper.c
Expand Up @@ -1122,6 +1122,49 @@ DO_ZZW(sve_lsl_zzw_s, uint32_t, uint64_t, H1_4, DO_LSL)
#undef DO_ZPZ
#undef DO_ZPZ_D

/*
* Three-operand expander, unpredicated, in which the two inputs are
* selected from the top or bottom half of the wide column.
*/
#define DO_ZZZ_TB(NAME, TYPEW, TYPEN, HW, HN, OP) \
void HELPER(NAME)(void *vd, void *vn, void *vm, 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 *)(vd + HW(i)) = OP(nn, mm); \
} \
}

DO_ZZZ_TB(sve2_saddl_h, int16_t, int8_t, H1_2, H1, DO_ADD)
DO_ZZZ_TB(sve2_saddl_s, int32_t, int16_t, H1_4, H1_2, DO_ADD)
DO_ZZZ_TB(sve2_saddl_d, int64_t, int32_t, , H1_4, DO_ADD)

DO_ZZZ_TB(sve2_ssubl_h, int16_t, int8_t, H1_2, H1, DO_SUB)
DO_ZZZ_TB(sve2_ssubl_s, int32_t, int16_t, H1_4, H1_2, DO_SUB)
DO_ZZZ_TB(sve2_ssubl_d, int64_t, int32_t, , H1_4, DO_SUB)

DO_ZZZ_TB(sve2_sabdl_h, int16_t, int8_t, H1_2, H1, DO_ABD)
DO_ZZZ_TB(sve2_sabdl_s, int32_t, int16_t, H1_4, H1_2, DO_ABD)
DO_ZZZ_TB(sve2_sabdl_d, int64_t, int32_t, , H1_4, DO_ABD)

DO_ZZZ_TB(sve2_uaddl_h, uint16_t, uint8_t, H1_2, H1, DO_ADD)
DO_ZZZ_TB(sve2_uaddl_s, uint32_t, uint16_t, H1_4, H1_2, DO_ADD)
DO_ZZZ_TB(sve2_uaddl_d, uint64_t, uint32_t, , H1_4, DO_ADD)

DO_ZZZ_TB(sve2_usubl_h, uint16_t, uint8_t, H1_2, H1, DO_SUB)
DO_ZZZ_TB(sve2_usubl_s, uint32_t, uint16_t, H1_4, H1_2, DO_SUB)
DO_ZZZ_TB(sve2_usubl_d, uint64_t, uint32_t, , H1_4, DO_SUB)

DO_ZZZ_TB(sve2_uabdl_h, uint16_t, uint8_t, H1_2, H1, DO_ABD)
DO_ZZZ_TB(sve2_uabdl_s, uint32_t, uint16_t, H1_4, H1_2, DO_ABD)
DO_ZZZ_TB(sve2_uabdl_d, uint64_t, uint32_t, , H1_4, DO_ABD)

#undef DO_ZZZ_TB

/* Two-operand reduction expander, controlled by a predicate.
* The difference between TYPERED and TYPERET has to do with
* sign-extension. E.g. for SMAX, TYPERED must be signed,
Expand Down
46 changes: 46 additions & 0 deletions target/arm/translate-sve.c
Expand Up @@ -5970,3 +5970,49 @@ DO_SVE2_ZPZZ(SQSUB_zpzz, sqsub)
DO_SVE2_ZPZZ(UQSUB_zpzz, uqsub)
DO_SVE2_ZPZZ(SUQADD, suqadd)
DO_SVE2_ZPZZ(USQADD, usqadd)

/*
* SVE2 Widening Integer Arithmetic
*/

static bool do_sve2_zzw_ool(DisasContext *s, arg_rrr_esz *a,
gen_helper_gvec_3 *fn, int data)
{
if (fn == NULL || !dc_isar_feature(aa64_sve2, s)) {
return false;
}
if (sve_access_check(s)) {
unsigned vsz = vec_full_reg_size(s);
tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->rd),
vec_full_reg_offset(s, a->rn),
vec_full_reg_offset(s, a->rm),
vsz, vsz, data, fn);
}
return true;
}

#define DO_SVE2_ZZZ_TB(NAME, name, SEL1, SEL2) \
static bool trans_##NAME(DisasContext *s, arg_rrr_esz *a) \
{ \
static gen_helper_gvec_3 * const fns[4] = { \
NULL, gen_helper_sve2_##name##_h, \
gen_helper_sve2_##name##_s, gen_helper_sve2_##name##_d, \
}; \
return do_sve2_zzw_ool(s, a, fns[a->esz], (SEL2 << 1) | SEL1); \
}

DO_SVE2_ZZZ_TB(SADDLB, saddl, false, false)
DO_SVE2_ZZZ_TB(SSUBLB, ssubl, false, false)
DO_SVE2_ZZZ_TB(SABDLB, sabdl, false, false)

DO_SVE2_ZZZ_TB(UADDLB, uaddl, false, false)
DO_SVE2_ZZZ_TB(USUBLB, usubl, false, false)
DO_SVE2_ZZZ_TB(UABDLB, uabdl, false, false)

DO_SVE2_ZZZ_TB(SADDLT, saddl, true, true)
DO_SVE2_ZZZ_TB(SSUBLT, ssubl, true, true)
DO_SVE2_ZZZ_TB(SABDLT, sabdl, true, true)

DO_SVE2_ZZZ_TB(UADDLT, uaddl, true, true)
DO_SVE2_ZZZ_TB(USUBLT, usubl, true, true)
DO_SVE2_ZZZ_TB(UABDLT, uabdl, true, true)

0 comments on commit 0ce1dda

Please sign in to comment.