diff options
| author | Changpeng Fang <changpeng.fang@gmail.com> | 2015-12-22 19:32:28 +0000 |
|---|---|---|
| committer | Changpeng Fang <changpeng.fang@gmail.com> | 2015-12-22 19:32:28 +0000 |
| commit | 9b8a9be058706d2d37ce3a15b1f720c5113ea97d (patch) | |
| tree | 2718e1dec5b034eb0749d23abbf4565301b18f52 /llvm/test/CodeGen/AMDGPU/register-count-comments.ll | |
| parent | 9f0bebc3dab3d2541e9f2342a4658d08fc8d1bd8 (diff) | |
| download | bcm5719-llvm-9b8a9be058706d2d37ce3a15b1f720c5113ea97d.tar.gz bcm5719-llvm-9b8a9be058706d2d37ce3a15b1f720c5113ea97d.zip | |
AMDGPU/SI: Use flat for global load/store when targeting HSA
Summary:
For some reason doing executing an MUBUF instruction with the addr64
bit set and a zero base pointer in the resource descriptor causes
the memory operation to be dropped when the shader is executed using
the HSA runtime.
This kind of MUBUF instruction is commonly used when the pointer is
stored in VGPRs. The base pointer field in the resource descriptor
is set to zero and and the pointer is stored in the vaddr field.
This patch resolves the issue by only using flat instructions for
global memory operations when targeting HSA. This is an overly
conservative fix as all other configurations of MUBUF instructions
appear to work.
Reviewers: tstellarAMD
Subscribers: arsenm, llvm-commits
Differential Revision: http://reviews.llvm.org/D15543
llvm-svn: 256273
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/register-count-comments.ll')
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/register-count-comments.ll | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/register-count-comments.ll b/llvm/test/CodeGen/AMDGPU/register-count-comments.ll index 8c104d9e34b..4bb315049be 100644 --- a/llvm/test/CodeGen/AMDGPU/register-count-comments.ll +++ b/llvm/test/CodeGen/AMDGPU/register-count-comments.ll @@ -1,5 +1,5 @@ ; RUN: llc -march=amdgcn -verify-machineinstrs -asm-verbose < %s | FileCheck -check-prefix=SI %s -; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -verify-machineinstrs -asm-verbose < %s | FileCheck -check-prefix=SI %s +; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -verify-machineinstrs -asm-verbose -mattr=-flat-for-global < %s | FileCheck -check-prefix=SI %s declare i32 @llvm.SI.tid() nounwind readnone |
