[LLVMbugs] [Bug 21296] New: Performance regression on ARM within (219545, 219569]

[bugzilla-daemon at llvm.org]

http://llvm.org/bugs/show_bug.cgi?id=21296

            Bug ID: 21296
           Summary: Performance regression on ARM within (219545, 219569]
           Product: new-bugs
           Version: unspecified
          Hardware: PC
                OS: Linux
            Status: NEW
          Severity: normal
          Priority: P
         Component: new bugs
          Assignee: unassignedbugs at nondot.org
          Reporter: renato.golin at linaro.org
                CC: llvmbugs at cs.uiuc.edu
    Classification: Unclassified

Our benchmark buildbot detected a regression on ARM:

http://llvm.org/perf/db_default/v4/nts/graph?plot.0=49.128.2&highlight_run=31861

According to Hal:

Based on the commit logs, it does seem like the best candidates are:
  r219566, r219567, r219568 - InstCombine bug fixes re: no-wrap flags
  r219550, r219562 - Fixes to trip-count computations in the
vectorizer/unroller

and given the magnitude of the change, I think that the trip-count changes are
more likely.

Since those were bug fixes, we should proceed with caution and make sure there
isn't a fix on top of those patches before considering anything more radical.

It may very well be that the ARM back-end is not dealing with some new patterns
correctly, or that the transformation has generated unoptimal sequences.

-- 
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/20141016/19dbe389/attachment.html>