[LLVMbugs] [Bug 16592] New: loop-vectorizer regression on x86-32

[bugzilla-daemon at llvm.org]

http://llvm.org/bugs/show_bug.cgi?id=16592

            Bug ID: 16592
           Summary: loop-vectorizer regression on x86-32
           Product: new-bugs
           Version: trunk
          Hardware: PC
                OS: Linux
            Status: NEW
          Severity: normal
          Priority: P
         Component: new bugs
          Assignee: unassignedbugs at nondot.org
          Reporter: baldrick at free.fr
                CC: llvmbugs at cs.uiuc.edu
    Classification: Unclassified

Created attachment 10856
  --> http://llvm.org/bugs/attachment.cgi?id=10856&action=edit
IR that used to loop-vectorize

This

void bar(float *A, float* B, float K) {
  int i;
  for (i = 0; i < 64; ++i)
    A[i] *= B[i] + K;
}

used to vectorize with dragonegg on x86-32 (with -O3 -msse), but stopped
vectorizing recently.  Note that it still vectorizes with clang, I think
because clang outputs inbounds GEPs for the array accesses while dragonegg
doesn't.

It still vectorizes on x86-64, but it's not clear to me why it is better on 64
bit.

IR attached.

-- 
You are receiving this mail because:
You are on the CC list for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-bugs/attachments/20130710/2d97431e/attachment.html>