https://gcc.gnu.org/g:f1b9d0380a4b5896b95f088799661d903ede80b5
commit r15-9571-gf1b9d0380a4b5896b95f088799661d903ede80b5
Author: Kyrylo Tkachov <ktkac...@nvidia.com>
Date: Tue Apr 22 06:17:34 2025 -0700
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 <ktkac...@nvidia.com>
gcc/
* config/aarch64/aarch64-cores.def (olympus): Add fp8fma, fp8dot4
explicitly.
(cherry picked from commit 5d5e8e87a42af8c0d962fa16dc9835fb71778250)
Diff:
---
gcc/config/aarch64/aarch64-cores.def | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/gcc/config/aarch64/aarch64-cores.def
b/gcc/config/aarch64/aarch64-cores.def
index 7f204fd0ac92..12096300d012 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)
