tree 8d1e59cd68cd5a426682696585ef329052a302fd
parent 9f53ba413e6fc879236dcaa3e008915973d67a4f
author benoitjacob <benoitjacob@google.com> 1587098845 -0700
committer Copybara-Service <copybara-worker@google.com> 1587099979 -0700

Use ruy's newly curated default set of paths.
This:
 - on all CPU architecturesremoves the reference code path, which is never used (the need for a portable non-simd fallback is already filled by the 'standard c++' path).
 - on x86, with --define=tflite_with_ruy=true (non-default), this removes a couple of experimental paths, keeping only AVX2 and AVX512 paths.
 - on x86 for per-channel-quantized ops where ruy is unconditionally used (no alternativee implementation), this enables AVX2 and AVX512 paths. This should fix slowness issues for such per-channel-quantized ops on x86.

PiperOrigin-RevId: 306981662