[X86][AVX] combineHorizontalPredicateResult - split any/allof v16i16/v32i8 reduction on AVX1
Perform the 2 x 128-bit lo/hi OR/AND on the vectors before calling PMOVMSKB on the 128-bit result. llvm-svn: 357611
Loading
Please sign in to comment
Perform the 2 x 128-bit lo/hi OR/AND on the vectors before calling PMOVMSKB on the 128-bit result. llvm-svn: 357611