OSDN Git Service

(root) / android-x86 / external-llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: cc9f5cb) | patch
AMDGPU/SI: Fix regression with no-return atomics
authorNicolai Haehnle <nhaehnle@gmail.com>
Fri, 15 Apr 2016 14:42:36 +0000 (14:42 +0000)
committerNicolai Haehnle <nhaehnle@gmail.com>
Fri, 15 Apr 2016 14:42:36 +0000 (14:42 +0000)
commit4c4aae4a7785717b3b98fbcc5447d356de4f075a
treee9b4d49fbe73addf3cc1604c8377a50772e5ace7tree | snapshot
parentcc9f5cb25ccf11739ef6ee7d84e1e8f2dfca18bbcommit | diff
AMDGPU/SI: Fix regression with no-return atomics

Summary:
In the added test-case, the atomic instruction feeds into a non-machine
CopyToReg node which hasn't been selected yet, so guard against
non-machine opcodes here.

Reviewers: arsenm, tstellarAMD

Subscribers: arsenm, llvm-commits

Differential Revision: http://reviews.llvm.org/D19043

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@266433 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/AMDGPU/SIISelLowering.cpp diff | blob | history
test/CodeGen/AMDGPU/llvm.amdgcn.buffer.atomic.ll diff | blob | history
external/llvm
About OSDN
Find Software
Develop Software
Help