The I8MM field of ID_AA64ZFR0_EL1 is set when the CPU implements FEAT_I8MM and either FEAT_SVE or FEAT_SME. Currently we assume that it is only set for FEAT_SVE. Update the feature checks: * we rename the existing feature check function to sve_sme_i8mm to indicate that it is true for either SVE or SME I8MM * we add a new check function for FEAT_SVE && FEAT_I8MM (giving it the sve_i8mm name that the old function used to have) * the instructions which are (SVE || SME) && I8MM need their checks updating to sve_sme_i8mm: these are SUDOT, USDOT * instructions which are SVE && I8MM (i.e. really SVE-only) stay unchanged with sve_i8mm: these are SMMLA, USMMLA, UMMLA
Signed-off-by: Peter Maydell <[email protected]> --- target/arm/cpu-features.h | 8 +++++++- target/arm/tcg/translate-sve.c | 6 +++--- 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/target/arm/cpu-features.h b/target/arm/cpu-features.h index 40393d88f0..8b8de5db04 100644 --- a/target/arm/cpu-features.h +++ b/target/arm/cpu-features.h @@ -1449,7 +1449,8 @@ static inline bool isar_feature_aa64_sve2_sm4(const ARMISARegisters *id) return FIELD_EX64_IDREG(id, ID_AA64ZFR0, SM4) != 0; } -static inline bool isar_feature_aa64_sve_i8mm(const ARMISARegisters *id) +/* Note that this is true if either SVE or SME are implemented with I8MM */ +static inline bool isar_feature_aa64_sme_sve_i8mm(const ARMISARegisters *id) { return FIELD_EX64_IDREG(id, ID_AA64ZFR0, I8MM) != 0; } @@ -1542,6 +1543,11 @@ static inline bool isar_feature_aa64_sme2_f64f64(const ARMISARegisters *id) return isar_feature_aa64_sme2(id) && isar_feature_aa64_sme_f64f64(id); } +static inline bool isar_feature_aa64_sve_i8mm(const ARMISARegisters *id) +{ + return isar_feature_aa64_sve(id) && isar_feature_aa64_sme_sve_i8mm(id); +} + /* * Feature tests for "does this exist in either 32-bit or 64-bit?" */ diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c index 44eda7b07d..53d35f6de9 100644 --- a/target/arm/tcg/translate-sve.c +++ b/target/arm/tcg/translate-sve.c @@ -3758,9 +3758,9 @@ TRANS_FEAT(UDOT_zzxw_4s, aa64_sme_or_sve, gen_gvec_ool_arg_zzxz, TRANS_FEAT(UDOT_zzxw_4d, aa64_sme_or_sve, gen_gvec_ool_arg_zzxz, gen_helper_gvec_udot_idx_4h, a) -TRANS_FEAT(SUDOT_zzxw_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz, +TRANS_FEAT(SUDOT_zzxw_4s, aa64_sme_sve_i8mm, gen_gvec_ool_arg_zzxz, gen_helper_gvec_sudot_idx_4b, a) -TRANS_FEAT(USDOT_zzxw_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz, +TRANS_FEAT(USDOT_zzxw_4s, aa64_sme_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, @@ -7778,7 +7778,7 @@ static gen_helper_gvec_4 * const sqrdcmlah_fns[] = { TRANS_FEAT(SQRDCMLAH_zzzz, aa64_sme_or_sve2, gen_gvec_ool_zzzz, sqrdcmlah_fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->rot) -TRANS_FEAT(USDOT_zzzz_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, +TRANS_FEAT(USDOT_zzzz_4s, aa64_sme_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, -- 2.43.0
