Compiler Explorer

Source code

define void @load_i8_stride4_vf8(<32 x i8>* %in.vec, <8 x i8>* %out.vec0, <8 x i8>* %out.vec1, <8 x i8>* %out.vec2, <8 x i8>* %out.vec3) nounwind {
  %wide.vec = load <32 x i8>, <32 x i8>* %in.vec, align 32

tail call void asm sideeffect "# LLVM-MCA-BEGIN", "~{dirflag},~{fpsr},~{flags}"()

%strided.vec0 = shufflevector <32 x i8> %wide.vec, <32 x i8> poison, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
  %strided.vec1 = shufflevector <32 x i8> %wide.vec, <32 x i8> poison, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
  %strided.vec2 = shufflevector <32 x i8> %wide.vec, <32 x i8> poison, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
  %strided.vec3 = shufflevector <32 x i8> %wide.vec, <32 x i8> poison, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>

tail call void asm sideeffect "# LLVM-MCA-END", "~{dirflag},~{fpsr},~{flags}"()

store <8 x i8> %strided.vec0, <8 x i8>* %out.vec0, align 32
  store <8 x i8> %strided.vec1, <8 x i8>* %out.vec1, align 32
  store <8 x i8> %strided.vec2, <8 x i8>* %out.vec2, align 32
  store <8 x i8> %strided.vec3, <8 x i8>* %out.vec3, align 32

ret void
}