diff options
| author | Konstantin Zhuravlyov <kzhuravl_dev@outlook.com> | 2018-02-20 23:30:21 +0000 |
|---|---|---|
| committer | Konstantin Zhuravlyov <kzhuravl_dev@outlook.com> | 2018-02-20 23:30:21 +0000 |
| commit | 5c1237a1fd94243b7cf7bcd7cb85619977ceaf03 (patch) | |
| tree | 8da30148e22a990451c249fa6f243c6e2fa48c4f /llvm/test/CodeGen/AMDGPU/waitcnt-looptest.ll | |
| parent | 3e569ac0cc711d8a9c7271243711f41dbb93d945 (diff) | |
| download | bcm5719-llvm-5c1237a1fd94243b7cf7bcd7cb85619977ceaf03.tar.gz bcm5719-llvm-5c1237a1fd94243b7cf7bcd7cb85619977ceaf03.zip | |
Revert "[AMDGPU] Increased vector length for global/constant loads."
https://reviews.llvm.org/rL325518
It breaks following OpenCL conformance tests:
- Basic - parameter_types
- Basic - vload_private
llvm-svn: 325643
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/waitcnt-looptest.ll')
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/waitcnt-looptest.ll | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/waitcnt-looptest.ll b/llvm/test/CodeGen/AMDGPU/waitcnt-looptest.ll index a941e5fb1f7..0af9bbcc25e 100644 --- a/llvm/test/CodeGen/AMDGPU/waitcnt-looptest.ll +++ b/llvm/test/CodeGen/AMDGPU/waitcnt-looptest.ll @@ -1,4 +1,4 @@ -; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=fiji -mattr=-flat-for-global -amdgpu-load-store-vectorizer=0 | FileCheck --check-prefix=GCN %s +; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=fiji -mattr=-flat-for-global | FileCheck --check-prefix=GCN %s ; Check that the waitcnt insertion algorithm correctly propagates wait counts ; from before a loop to the loop header. |
