projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: f328fd4) | patch
[NVPTX] allow register copy between float and int
authorJingyue Wu <jingyue@google.com>
Sat, 1 Aug 2015 18:02:12 +0000 (18:02 +0000)
committerJingyue Wu <jingyue@google.com>
Sat, 1 Aug 2015 18:02:12 +0000 (18:02 +0000)
commitffa09be222a82879ea78c0a71df268325852f3b5
treea34a35beaf805c4115e0f4f1031c1b2da674ddbbtree | snapshot
parentf328fd4441951df7bf59d4b62a70f5d5a950fa9dcommit | diff
[NVPTX] allow register copy between float and int

Summary:
Fixes PR24303. With Bruno's WIP (D11197) on PeepholeOptimizer, across-class
register copying (e.g. i32 to f32) becomes possible. Enhance
NVPTXInstrInfo::copyPhysReg to handle these cases.

Reviewers: jholewinski

Subscribers: eliben, jholewinski, llvm-commits, bruno

Differential Revision: http://reviews.llvm.org/D11622

llvm-svn: 243839
llvm/lib/Target/NVPTX/NVPTXInstrInfo.cpp diff | blob | history
llvm/test/CodeGen/NVPTX/reg-copy.ll [new file with mode: 0644] blob
Domain: System / Toolchain;