[PATCH] Loop Vectorizer doesn't use %zmm registers on targets supporting AVX512.

[Andrea Di Biagio]

  Hi Zinovy,

  A minor comment:
  your new test should be probably moved to 'test/Transforms/LoopVectorize/X86' since it is clearly testing the loop vectorizer behavior on a specific x86 target.


================
Comment at: test/CodeGen/X86/avx512-vectorizer.ll:8
@@ +7,3 @@
+
+define void @foo(float* noalias %a, float* noalias %b, float* noalias %c, i32 %n) #0 {
+entry:
----------------
You can remove the '#0' from the signature of @foo since it is not used.


http://llvm-reviews.chandlerc.com/D3078