[X86][AVX] combineTargetShuffle - simplify the X86ISD::VPERM2X128 subvector matching
Simplify vperm2x128(concat(X,Y),concat(Z,W)) folding. Use collectConcatOps / ISD::INSERT_SUBVECTOR to find the source subvectors instead of hardcoded immediate matching.
Loading
Please sign in to comment