projects / oota-llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: ad0ddd8) | patch
[NVPTX] truncating 64-bit to 32-bit is free
authorJingyue Wu <jingyue@google.com>
Thu, 20 Aug 2015 20:59:02 +0000 (20:59 +0000)
committerJingyue Wu <jingyue@google.com>
Thu, 20 Aug 2015 20:59:02 +0000 (20:59 +0000)
commit1670bbc481e066c1fc98e9ebb507b6ca12206a60
tree2a29296ce605b150491d7241151dab8d7584f791tree | snapshot
parentad0ddd8e0190ef7ebb162921e53115f9d969f939commit | diff
[NVPTX] truncating 64-bit to 32-bit is free

Summary:
Add an LSR test that exercises isTruncateFree. Without this change, LSR creates
another indvar representing the truncated value.

Reviewers: jholewinski, eliben

Subscribers: jholewinski, llvm-commits

Differential Revision: http://reviews.llvm.org/D12058

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@245611 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/NVPTX/NVPTXISelLowering.h diff | blob | history
test/Transforms/LoopStrengthReduce/NVPTX/lit.local.cfg [new file with mode: 0644] blob
test/Transforms/LoopStrengthReduce/NVPTX/trunc.ll [new file with mode: 0644] blob
C/C++ LLVM-based compilers that forbids OOTA behaviors