diff options
| author | Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com> | 2017-09-19 20:54:38 +0000 |
|---|---|---|
| committer | Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com> | 2017-09-19 20:54:38 +0000 |
| commit | d4ae470d2e7a967331a5bb3ae5be29a4f0b6c764 (patch) | |
| tree | 9065b407288d50bfeb20d5827ea6fb2dcbf008ca /llvm/test/CodeGen/AMDGPU/callee-special-input-vgprs.ll | |
| parent | 59a01a958a55c75af4076e35ba67e2a4a38d8dce (diff) | |
| download | bcm5719-llvm-d4ae470d2e7a967331a5bb3ae5be29a4f0b6c764.tar.gz bcm5719-llvm-d4ae470d2e7a967331a5bb3ae5be29a4f0b6c764.zip | |
[AMDGPU] Prevent post-RA scheduler from breaking memory clauses
The pre-RA scheduler does load/store clustering, but post-RA
scheduler undoes it. Add mutation to prevent it.
Differential Revision: https://reviews.llvm.org/D38014
llvm-svn: 313670
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/callee-special-input-vgprs.ll')
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/callee-special-input-vgprs.ll | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/callee-special-input-vgprs.ll b/llvm/test/CodeGen/AMDGPU/callee-special-input-vgprs.ll index f2db5733689..9b3bb69dc9c 100644 --- a/llvm/test/CodeGen/AMDGPU/callee-special-input-vgprs.ll +++ b/llvm/test/CodeGen/AMDGPU/callee-special-input-vgprs.ll @@ -327,8 +327,8 @@ define void @func_call_too_many_args_use_workitem_id_x(i32 %arg0) #1 { ; Requires loading and storing to stack slot. ; GCN-LABEL: {{^}}too_many_args_call_too_many_args_use_workitem_id_x: ; GCN: buffer_store_dword v32, off, s[0:3], s5 offset:8 ; 4-byte Folded Spill -; GCN: buffer_load_dword v32, off, s[0:3], s5 offset:4 ; GCN: s_add_u32 s32, s32, 0x400{{$}} +; GCN: buffer_load_dword v32, off, s[0:3], s5 offset:4 ; GCN: buffer_store_dword v32, off, s[0:3], s32 offset:8{{$}} |
