diff options
| author | Jakub Jelinek <jakub@redhat.com> | 2022-11-15 08:14:45 +0100 |
|---|---|---|
| committer | Jakub Jelinek <jakub@redhat.com> | 2022-11-15 08:14:45 +0100 |
| commit | 4a7a846687e076eae58ad3ea959245b2bf7fdc07 (patch) | |
| tree | 4fd2d998cea2d0f56ef21f6297d55e1af8f42066 | |
| parent | 7cf165de63c5d2726bba9f0809a233bd63b84842 (diff) | |
| download | gcc-4a7a846687e076eae58ad3ea959245b2bf7fdc07.zip gcc-4a7a846687e076eae58ad3ea959245b2bf7fdc07.tar.gz gcc-4a7a846687e076eae58ad3ea959245b2bf7fdc07.tar.bz2 | |
libatomic: Handle AVX+CX16 AMD like Intel for 16b atomics [PR104688]
We got a response from AMD in
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104688#c10
so the following patch starts treating AMD with AVX and CMPXCHG16B
ISAs like Intel by using vmovdqa for atomic load/store in libatomic.
We still don't have confirmation from Zhaoxin and VIA (anything else
with CPUs featuring AVX and CX16?).
2022-11-15 Jakub Jelinek <jakub@redhat.com>
PR target/104688
* config/x86/init.c (__libat_feat1_init): Don't clear
bit_AVX on AMD CPUs.
| -rw-r--r-- | libatomic/config/x86/init.c | 6 |
1 files changed, 4 insertions, 2 deletions
diff --git a/libatomic/config/x86/init.c b/libatomic/config/x86/init.c index 6f6499c..10e1c5f 100644 --- a/libatomic/config/x86/init.c +++ b/libatomic/config/x86/init.c @@ -39,10 +39,12 @@ __libat_feat1_init (void) == (bit_AVX | bit_CMPXCHG16B)) { /* Intel SDM guarantees that 16-byte VMOVDQA on 16-byte aligned address - is atomic, but so far we don't have this guarantee from AMD. */ + is atomic, and AMD is going to do something similar soon. + We don't have a guarantee from vendors of other CPUs with AVX, + like Zhaoxin and VIA. */ unsigned int ecx2 = 0; __get_cpuid (0, &eax, &ebx, &ecx2, &edx); - if (ecx2 != signature_INTEL_ecx) + if (ecx2 != signature_INTEL_ecx && ecx2 != signature_AMD_ecx) FEAT1_REGISTER &= ~bit_AVX; } #endif |