diff options
author | Kyrylo Tkachov <ktkachov@nvidia.com> | 2025-04-22 06:17:34 -0700 |
---|---|---|
committer | Kyrylo Tkachov <ktkachov@nvidia.com> | 2025-04-22 15:55:11 +0200 |
commit | 5d5e8e87a42af8c0d962fa16dc9835fb71778250 (patch) | |
tree | 410bc078b2c68372e3680b8c22fd58b1e0feb118 /gcc | |
parent | 6390fc86995fbd5239497cb9e1797a3af51d3936 (diff) | |
download | gcc-5d5e8e87a42af8c0d962fa16dc9835fb71778250.zip gcc-5d5e8e87a42af8c0d962fa16dc9835fb71778250.tar.gz gcc-5d5e8e87a42af8c0d962fa16dc9835fb71778250.tar.bz2 |
aarch64: Update FP8 dependencies for -mcpu=olympus
We had not noticed that after g:299a8e2dc667e795991bc439d2cad5ea5bd379e2 the
FP8FMA and FP8DOT4 features aren't implied by FP8FMA. The intent is for
-mcpu=olympus to support all of them.
Fix the definition to include the relevant sub-features explicitly.
Signed-off-by: Kyrylo Tkachov <ktkachov@nvidia.com>
gcc/
* config/aarch64/aarch64-cores.def (olympus): Add fp8fma, fp8dot4
explicitly.
Diffstat (limited to 'gcc')
-rw-r--r-- | gcc/config/aarch64/aarch64-cores.def | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/gcc/config/aarch64/aarch64-cores.def b/gcc/config/aarch64/aarch64-cores.def index 7f204fd..1209630 100644 --- a/gcc/config/aarch64/aarch64-cores.def +++ b/gcc/config/aarch64/aarch64-cores.def @@ -224,7 +224,7 @@ AARCH64_CORE("neoverse-v3ae", neoversev3ae, cortexa57, V9_2A, (SVE2_BITPERM, RNG AARCH64_CORE("demeter", demeter, cortexa57, V9A, (I8MM, BF16, SVE2_BITPERM, RNG, MEMTAG, PROFILE), neoversev2, 0x41, 0xd4f, -1) /* NVIDIA ('N') cores. */ -AARCH64_CORE("olympus", olympus, cortexa57, V9_2A, (SVE2_BITPERM, RNG, LS64, MEMTAG, PROFILE, FAMINMAX, FP8DOT2, LUT, SVE2_AES, SVE2_SHA3, SVE2_SM4), neoversev3, 0x4e, 0x10, -1) +AARCH64_CORE("olympus", olympus, cortexa57, V9_2A, (SVE2_BITPERM, RNG, LS64, MEMTAG, PROFILE, FAMINMAX, FP8FMA, FP8DOT2, FP8DOT4, LUT, SVE2_AES, SVE2_SHA3, SVE2_SM4), neoversev3, 0x4e, 0x10, -1) /* Generic Architecture Processors. */ AARCH64_CORE("generic", generic, cortexa53, V8A, (), generic, 0x0, 0x0, -1) |