[LLVMbugs] [Bug 15866] New: SROA builds needlessly complex shufflevectors

[bugzilla-daemon at llvm.org]

http://llvm.org/bugs/show_bug.cgi?id=15866

            Bug ID: 15866
           Summary: SROA builds needlessly complex shufflevectors
           Product: libraries
           Version: trunk
          Hardware: PC
                OS: All
            Status: NEW
          Severity: normal
          Priority: P
         Component: Scalar Optimizations
          Assignee: unassignedbugs at nondot.org
          Reporter: grosbach at apple.com
                CC: llvmbugs at cs.uiuc.edu
    Classification: Unclassified

Created attachment 10439
  --> http://llvm.org/bugs/attachment.cgi?id=10439&action=edit
fubarness inside!

For the attached input, SROA creates a series of vector shuffles that just end
up recreating the original vector before storing it. No other optimization
cleans it up and codegen doesn't either, so we end up with horrible scalarized
vector operations.

In the attached testcase, using the inline function causes the above nastiness.
Interestingly, just replacing the call with the actual stores results in code
that works fine. See if "#if 0/#else" in the testcase.

-- 
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/20130429/63039c02/attachment.html>