-
- Downloads
aarch64: modify Ampere CPU tunings on reassociation/FMA
1. Allow reassociation on FP additions. 2. Avoid generating loop-dependant FMA chains. Added a tuning option 'AARCH64_EXTRA_TUNE_AVOID_CROSS_LOOP_FMA' for this. gcc/ChangeLog: * config/aarch64/aarch64-tuning-flags.def (AARCH64_EXTRA_TUNING_OPTION): New tuning option to avoid cross-loop FMA. * config/aarch64/aarch64.cc (aarch64_override_options_internal): Set param_avoid_fma_max_bits according to tuning option. * config/aarch64/tuning_models/ampere1.h (ampere1_tunings): Modify tunings related with FMA. * config/aarch64/tuning_models/ampere1a.h (ampere1a_tunings): Likewise. * config/aarch64/tuning_models/ampere1b.h (ampere1b_tunings): Likewise.
Showing
- gcc/config/aarch64/aarch64-tuning-flags.def 2 additions, 0 deletionsgcc/config/aarch64/aarch64-tuning-flags.def
- gcc/config/aarch64/aarch64.cc 6 additions, 0 deletionsgcc/config/aarch64/aarch64.cc
- gcc/config/aarch64/tuning_models/ampere1.h 1 addition, 1 deletiongcc/config/aarch64/tuning_models/ampere1.h
- gcc/config/aarch64/tuning_models/ampere1a.h 2 additions, 2 deletionsgcc/config/aarch64/tuning_models/ampere1a.h
- gcc/config/aarch64/tuning_models/ampere1b.h 3 additions, 2 deletionsgcc/config/aarch64/tuning_models/ampere1b.h
Loading
Please register or sign in to comment