[X86][AVX] lowerShuffleWithPERMV - adjust binary shuffle masks to account for...
[X86][AVX] lowerShuffleWithPERMV - adjust binary shuffle masks to account for widening on non-VLX targets rGabd33bf5eff2 enabled us to pad 128/256-bit shuffles to 512-bit on non-VLX targets, but wasn't updating binary shuffles to account for the new vector width.
Loading
Please sign in to comment