[X86] combineConcatVectorOps - fold 512-bit...
[X86] combineConcatVectorOps - fold 512-bit concat(GF2P8AFFINEQB(x,y,c),GF2P8AFFINEQB(z,w,c)) -> GF2P8AFFINEQB(concat(x,z),concat(y,w),c) Now that D137036 has landed, we just need AVX512F support to generate 512-bit GF2P8AFFINEQB ops
Loading
Please sign in to comment