[llvm-bugs] [Bug 21356] [loop vectorizer] failure to vectorize int to fp conversions for <256 bit vectors

[via llvm-bugs]

https://llvm.org/bugs/show_bug.cgi?id=21356

Sanjay Patel <spatel+llvm at rotateright.com> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|NEW                         |RESOLVED
         Resolution|---                         |FIXED

--- Comment #7 from Sanjay Patel <spatel+llvm at rotateright.com> ---
Should be fixed with:
http://reviews.llvm.org/rL274658

$ ./opt -loop-vectorize 21356.ll -mcpu=core2 -S|grep sito
  %28 = sitofp <4 x i32> %wide.load to <4 x float>
  %29 = sitofp <4 x i32> %wide.load7 to <4 x float>
  %conv = sitofp i32 %55 to float

-- 
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/20160706/6a018404/attachment.html>