This is an archive of the discontinued LLVM Phabricator instance.

[InstCombine][SSE] Add MOVMSK constant folding (PR27982)
ClosedPublic

Authored by RKSimon on Jun 4 2016, 9:08 AM.

Details

Summary

This patch adds support for folding undef/zero/constant inputs to MOVMSK instructions.

The SSE/AVX versions can be fully folded, but the MMX version can only handle undef inputs.

Diff Detail

Repository
rL LLVM

Event Timeline

RKSimon updated this revision to Diff 59650.Jun 4 2016, 9:08 AM
RKSimon retitled this revision from to [InstCombine][SSE] Add MOVMSK constant folding (PR27982).
RKSimon updated this object.
RKSimon added reviewers: spatel, andreadb, ab.
RKSimon set the repository for this revision to rL LLVM.
RKSimon added a subscriber: llvm-commits.
ab accepted this revision.Jun 5 2016, 7:48 PM
ab edited edge metadata.

LGTM, with one nit.

lib/Transforms/InstCombine/InstCombineCalls.cpp
348

i -> I ?
Or, since I is confusing: EI/EE? AI/AE?

This revision is now accepted and ready to land.Jun 5 2016, 7:48 PM
This revision was automatically updated to reflect the committed changes.