mirror of
https://github.com/amd/blis.git
synced 2026-05-12 10:05:38 +00:00
16592f79ee
Where a processor has not been targeted for optimization, the slow generic code path may be selected by default. Another code path could perform much better, even if not specifically optimized for this processor. Changes to enable this: - Always call bli_cpuid_query_id() to get actual hardware info, even if the user is overriding the choice at build time or by setting BLIS_ARCH_TYPE. - Use bli_cpuid_query_id() to gather availability of AVX2 and AVX512 instructions. - Include AVX-512 fallback test to select zen4 code path on future AMD processors (that don't yet have a specific codepath). - Also use AVX-512 and AVX2 tests on Intel processors to select zen4 or zen3 code paths over the generic code path. If both zen and skx/haswell code paths are enabled, the zen code path will be given preference as zen paths have additional optimizations that should, in general, benefit Intel processors too. AMD-Internal: [CPUPL-3031] Change-Id: Ib7d0ebdb02fec872f9443a1d20070026f2020516