projects / oota-llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: b2f521b) | patch
[InstCombine/PowerPC] Convert aligned QPX load/store intrinsics into loads/stores
authorHal Finkel <hfinkel@anl.gov>
Thu, 26 Feb 2015 18:56:03 +0000 (18:56 +0000)
committerHal Finkel <hfinkel@anl.gov>
Thu, 26 Feb 2015 18:56:03 +0000 (18:56 +0000)
commit532af6859f9a59cc3cf29f6ba704004f4c09fbd1
treed00053f8640e557afe0725bbe50eaaf327a1c7cctree | snapshot
parentb2f521b6475fb2edd4ff13ecdfe100b84321603ccommit | diff
[InstCombine/PowerPC] Convert aligned QPX load/store intrinsics into loads/stores

InstCombine has long had logic to convert aligned Altivec load/store intrinsics
into regular loads and stores. This mirrors that functionality for QPX vector
load/store intrinsics.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@230660 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Transforms/InstCombine/InstCombineCalls.cpp diff | blob | history
test/Transforms/InstCombine/aligned-qpx.ll [new file with mode: 0644] blob
C/C++ LLVM-based compilers that forbids OOTA behaviors