diff options
| author | Kyrylo Tkachov <ktkachov@nvidia.com> | 2026-02-06 02:34:29 -0800 |
|---|---|---|
| committer | Kyrylo Tkachov <ktkachov@nvidia.com> | 2026-02-10 11:02:10 +0100 |
| commit | 4d2af0735063ab7d38c4da0ec6f992276af855af (patch) | |
| tree | 6afcd055596f770f6e220d9e1eb5e1a2d56ac879 /libjava/classpath/gnu/xml | |
| parent | e55de74d50d236db0472431fe242f3244e41b884 (diff) | |
| download | gcc-4d2af0735063ab7d38c4da0ec6f992276af855af.zip gcc-4d2af0735063ab7d38c4da0ec6f992276af855af.tar.gz gcc-4d2af0735063ab7d38c4da0ec6f992276af855af.tar.bz2 | |
aarch64: Adjust SVE vector costs for NVIDIA Olympus
After some more analysis, I'd like to adjust the SVE load
cost for NVIDIA Olympus to more accurately reflect the core SWOG.
This leads to more sensible Advanced SIMD vs SVE autovec decisions.
Bootstrapped and tested on aarch64-none-linux-gnu.
Signed-off-by: Kyrylo Tkachov <ktkachov@nvidia.com>
gcc/ChangeLog
* config/aarch64/tuning_models/olympus.h (olympus_sve_vector_cost):
Set align_load_cost to 6.
Diffstat (limited to 'libjava/classpath/gnu/xml')
0 files changed, 0 insertions, 0 deletions