diff options
| author | Richard Henderson <richard.henderson@linaro.org> | 2021-05-24 18:03:32 -0700 |
|---|---|---|
| committer | Peter Maydell <peter.maydell@linaro.org> | 2021-05-25 16:01:44 +0100 |
| commit | 2867039a9fb68866673f73d48d43761c1133e4db (patch) | |
| tree | 374d1e0007d616f0f3981ad99ceff69b2ee35a6c /target | |
| parent | 7020ffd656a5980f4aca87e61c95d82cc4707fd6 (diff) | |
| download | qemu-2867039a9fb68866673f73d48d43761c1133e4db.zip qemu-2867039a9fb68866673f73d48d43761c1133e4db.tar.gz qemu-2867039a9fb68866673f73d48d43761c1133e4db.tar.bz2 | |
target/arm: Implement SVE mixed sign dot product (indexed)
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-67-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Diffstat (limited to 'target')
| -rw-r--r-- | target/arm/cpu.h | 5 | ||||
| -rw-r--r-- | target/arm/helper.h | 4 | ||||
| -rw-r--r-- | target/arm/sve.decode | 4 | ||||
| -rw-r--r-- | target/arm/translate-sve.c | 16 | ||||
| -rw-r--r-- | target/arm/vec_helper.c | 2 |
5 files changed, 31 insertions, 0 deletions
diff --git a/target/arm/cpu.h b/target/arm/cpu.h index 7ad79ff..dcdde85 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -4256,6 +4256,11 @@ static inline bool isar_feature_aa64_sve2_bitperm(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, BITPERM) != 0; } +static inline bool isar_feature_aa64_sve_i8mm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, I8MM) != 0; +} + static inline bool isar_feature_aa64_sve_f32mm(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, F32MM) != 0; diff --git a/target/arm/helper.h b/target/arm/helper.h index e7c463f..e4c6458 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -621,6 +621,10 @@ DEF_HELPER_FLAGS_5(gvec_sdot_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_udot_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sudot_idx_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_usdot_idx_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fcaddh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index 0339410..c6b32a3 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -816,6 +816,10 @@ 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 +# SVE mixed sign dot product (indexed) +USDOT_zzxw_s 01000100 10 1 ..... 000110 ..... ..... @rrxr_2 esz=2 +SUDOT_zzxw_s 01000100 10 1 ..... 000111 ..... ..... @rrxr_2 esz=2 + # SVE2 saturating multiply-add (indexed) SQDMLALB_zzxw_s 01000100 10 1 ..... 0010.0 ..... ..... @rrxr_3a esz=2 SQDMLALB_zzxw_d 01000100 11 1 ..... 0010.0 ..... ..... @rrxr_2a esz=3 diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index b454f50..30894a4 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -3838,6 +3838,22 @@ DO_RRXR(trans_SDOT_zzxw_d, gen_helper_gvec_sdot_idx_h) DO_RRXR(trans_UDOT_zzxw_s, gen_helper_gvec_udot_idx_b) DO_RRXR(trans_UDOT_zzxw_d, gen_helper_gvec_udot_idx_h) +static bool trans_SUDOT_zzxw_s(DisasContext *s, arg_rrxr_esz *a) +{ + if (!dc_isar_feature(aa64_sve_i8mm, s)) { + return false; + } + return do_zzxz_ool(s, a, gen_helper_gvec_sudot_idx_b); +} + +static bool trans_USDOT_zzxw_s(DisasContext *s, arg_rrxr_esz *a) +{ + if (!dc_isar_feature(aa64_sve_i8mm, s)) { + return false; + } + return do_zzxz_ool(s, a, gen_helper_gvec_usdot_idx_b); +} + #undef DO_RRXR static bool do_sve2_zzz_data(DisasContext *s, int rd, int rn, int rm, int data, diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index 1c4266a..f128b41 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -598,6 +598,8 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ DO_DOT_IDX(gvec_sdot_idx_b, int32_t, int8_t, int8_t, H4) DO_DOT_IDX(gvec_udot_idx_b, uint32_t, uint8_t, uint8_t, H4) +DO_DOT_IDX(gvec_sudot_idx_b, int32_t, int8_t, uint8_t, H4) +DO_DOT_IDX(gvec_usdot_idx_b, int32_t, uint8_t, int8_t, H4) DO_DOT_IDX(gvec_sdot_idx_h, int64_t, int16_t, int16_t, ) DO_DOT_IDX(gvec_udot_idx_h, uint64_t, uint16_t, uint16_t, ) |