[llvm-bugs] [Bug 11025] Represent hadd, vector shift without target specific builtins.
via llvm-bugs
llvm-bugs at lists.llvm.org
Fri Oct 12 06:55:14 PDT 2018
https://bugs.llvm.org/show_bug.cgi?id=11025
Sanjay Patel <spatel+llvm at rotateright.com> changed:
What |Removed |Added
----------------------------------------------------------------------------
Status|NEW |RESOLVED
Resolution|--- |FIXED
--- Comment #6 from Sanjay Patel <spatel+llvm at rotateright.com> ---
I think we can close this bug now. The examples from the description are using
generic IR now.
The hadd example I showed in comment 5 was fixed with:
https://reviews.llvm.org/rL344141
Note, however, that we intend to disable hadd codegen by default for that same
example here:
https://reviews.llvm.org/D53095
...because horizontal vector ops are generally horrible.
If that change causes regressions, that should be a separate bug report.
--
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/20181012/efc1961c/attachment.html>
More information about the llvm-bugs
mailing list