summaryrefslogtreecommitdiffstats
path: root/llvm/test/CodeGen/AMDGPU/drop-mem-operand-move-smrd.ll
Commit message (Collapse)AuthorAgeFilesLines
* AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernelMatt Arsenault2017-03-211-1/+1
| | | | | | | | | | | | Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
* AMDGPU/SI: Enable load-store-opt by default.Changpeng Fang2016-05-261-2/+1
| | | | | | | | | | Summary: Enable load-store-opt by default, and update LIT tests. Reviewers: arsenm Differential Revision: http://reviews.llvm.org/D20694 llvm-svn: 270894
* AMDGPU: Make vectorization defeating test changesMatt Arsenault2016-05-251-1/+1
| | | | | | Simplifies test updates in the future. llvm-svn: 270736
* AMDGPU: Remove some old intrinsic uses from testsMatt Arsenault2016-02-111-5/+2
| | | | llvm-svn: 260493
* AMDGPU: Switch barrier intrinsics to using convergentMatt Arsenault2015-12-191-1/+1
| | | | | | | | noduplicate prevents unrolling of small loops that happen to have barriers in them. If a loop has a barrier in it, it is OK to duplicate it for the unroll. llvm-svn: 256075
* AMDGPU: Fix dropping mem operands when moving to VALUMatt Arsenault2015-08-291-0/+52
Without a memory operand, mayLoad or mayStore instructions are treated as hasUnorderedMemRef, which results in much worse scheduling. We really should have a verifier check that any non-side effecting mayLoad or mayStore has a memory operand. There are a few instructions (interp and images) which I'm not sure what / where to add these. llvm-svn: 246356
OpenPOWER on IntegriCloud