On 26/11/2024 12:19, Sam Russell wrote:
> Now I think what you are saying is there was no SIGILL with the adjusted
cksum,
and that issue was only with the less protected benchmarking code.
Correct, the benchmarking code has zero protections, and the servers I got
SIGILL they were not setting the VPCLMULQDQ flag so cksum will catch this and
fall back
Thanks for the confirmation.
I've tweaked NEWS a bit and also adjusted the avx2_supported() and
avx512_supported()
functions to avoid a build failure which I think would happen on x86 with gcc 8
for example,
by protecting the builtin_cpu_supports() calls with USE_AVX2_CRC32 and
USE_AVX512_CRC32.
I'll push in a couple of hours.
thanks!
Pádraig
