From 26c3bafbf355f8aa8cb9197ccc4136c878c8bbfb Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Fri, 4 Jul 2025 08:20:07 -0600 Subject: [PATCH] target/arm: Implement SDOT, UDOT (2-way) for SME2/SVE2p1 Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20250704142112.1018902-45-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/sve.decode | 8 +++++++- target/arm/tcg/translate-sve.c | 10 ++++++++++ 2 files changed, 17 insertions(+), 1 deletion(-) diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index 401c0258527..83c259def6e 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -856,6 +856,9 @@ SDOT_zzxw_4d 01000100 11 1 ..... 000000 ..... ..... @rrxr_1 esz=3 UDOT_zzxw_4s 01000100 10 1 ..... 000001 ..... ..... @rrxr_2 esz=2 UDOT_zzxw_4d 01000100 11 1 ..... 000001 ..... ..... @rrxr_1 esz=3 +SDOT_zzxw_2s 01000100 10 0 ..... 110010 ..... ..... @rrxr_2 esz=2 +UDOT_zzxw_2s 01000100 10 0 ..... 110011 ..... ..... @rrxr_2 esz=2 + # SVE2 integer multiply-add (indexed) MLA_zzxz_h 01000100 0. 1 ..... 000010 ..... ..... @rrxr_3 esz=1 MLA_zzxz_s 01000100 10 1 ..... 000010 ..... ..... @rrxr_2 esz=2 @@ -1597,7 +1600,10 @@ UMLSLT_zzzw 01000100 .. 0 ..... 010 111 ..... ..... @rda_rn_rm CMLA_zzzz 01000100 esz:2 0 rm:5 0010 rot:2 rn:5 rd:5 ra=%reg_movprfx SQRDCMLAH_zzzz 01000100 esz:2 0 rm:5 0011 rot:2 rn:5 rd:5 ra=%reg_movprfx -## SVE mixed sign dot product +## SVE dot product + +SDOT_zzzz_2s 01000100 00 0 ..... 110 010 ..... ..... @rda_rn_rm_ex esz=2 +UDOT_zzzz_2s 01000100 00 0 ..... 110 011 ..... ..... @rda_rn_rm_ex esz=2 USDOT_zzzz_4s 01000100 10 0 ..... 011 110 ..... ..... @rda_rn_rm_ex esz=2 diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c index c82a0f771db..10261e25f92 100644 --- a/target/arm/tcg/translate-sve.c +++ b/target/arm/tcg/translate-sve.c @@ -3426,6 +3426,11 @@ TRANS_FEAT(SUDOT_zzxw_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz, TRANS_FEAT(USDOT_zzxw_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz, gen_helper_gvec_usdot_idx_4b, a) +TRANS_FEAT(SDOT_zzxw_2s, aa64_sme2_or_sve2p1, gen_gvec_ool_arg_zzxz, + gen_helper_gvec_sdot_idx_2h, a) +TRANS_FEAT(UDOT_zzxw_2s, aa64_sme2_or_sve2p1, gen_gvec_ool_arg_zzxz, + gen_helper_gvec_udot_idx_2h, a) + #define DO_SVE2_RRX(NAME, FUNC) \ TRANS_FEAT(NAME, aa64_sve, gen_gvec_ool_zzz, FUNC, \ a->rd, a->rn, a->rm, a->index) @@ -7154,6 +7159,11 @@ TRANS_FEAT(SQRDCMLAH_zzzz, aa64_sve2, gen_gvec_ool_zzzz, TRANS_FEAT(USDOT_zzzz_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, gen_helper_gvec_usdot_4b, a, 0) +TRANS_FEAT(SDOT_zzzz_2s, aa64_sme2_or_sve2p1, gen_gvec_ool_arg_zzzz, + gen_helper_gvec_sdot_2h, a, 0) +TRANS_FEAT(UDOT_zzzz_2s, aa64_sme2_or_sve2p1, gen_gvec_ool_arg_zzzz, + gen_helper_gvec_udot_2h, a, 0) + TRANS_FEAT_NONSTREAMING(AESMC, aa64_sve2_aes, gen_gvec_ool_zz, gen_helper_crypto_aesmc, a->rd, a->rd, 0) TRANS_FEAT_NONSTREAMING(AESIMC, aa64_sve2_aes, gen_gvec_ool_zz, -- 2.47.2