diff options
| author | Di Zhao <dizhao@os.amperecomputing.com> | 2023-12-01 16:16:40 +0800 |
|---|---|---|
| committer | Di Zhao <dizhao@os.amperecomputing.com> | 2023-12-01 17:02:46 +0800 |
| commit | 6563d6767ed0f702458f8975cd5d73676c4604cc (patch) | |
| tree | 6f9fabbd0e345e03b15cc84b19096552a4b82c98 /gcc/tree-vectorizer.h | |
| parent | 82288550012c9382ddfd75a0b4b1bb467d445744 (diff) | |
| download | gcc-6563d6767ed0f702458f8975cd5d73676c4604cc.zip gcc-6563d6767ed0f702458f8975cd5d73676c4604cc.tar.gz gcc-6563d6767ed0f702458f8975cd5d73676c4604cc.tar.bz2 | |
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.
Diffstat (limited to 'gcc/tree-vectorizer.h')
0 files changed, 0 insertions, 0 deletions