summaryrefslogtreecommitdiffstats
path: root/llvm/test/CodeGen/AMDGPU/default-fp-mode.ll
Commit message (Collapse)AuthorAgeFilesLines
* AMDGPU: Drop remnants of byval support for shadersMatt Arsenault2019-07-121-1/+1
| | | | | | | | Before 2018, mesa used to use byval interchangably with inreg, which didn't really make sense. Fix tests still using it to avoid breaking in a future commit. llvm-svn: 365953
* AMDGPU: Remove llvm.AMDGPU.killMatt Arsenault2018-12-071-8/+6
| | | | | | This is the last of the old AMDGPU intrinsics. llvm-svn: 348615
* AMDGPU: Fix tests using old number for constant address spaceMatt Arsenault2018-09-101-1/+1
| | | | llvm-svn: 341770
* AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernelMatt Arsenault2017-03-211-9/+9
| | | | | | | | | | | | 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: Remove some uses of llvm.SI.export in testsMatt Arsenault2017-02-221-5/+2
| | | | | | Merge some of the old, smaller tests into more complete versions. llvm-svn: 295792
* AMDGPU: Combine fp16/fp64 subtarget featuresMatt Arsenault2017-01-231-1/+32
| | | | | | | The same control register controls both, and are set to the same defaults. Keep the old names around as aliases. llvm-svn: 292837
* AMDGPU : Add a function to enable and disable IEEEBit for SC and shaderWei Ding2016-10-191-6/+34
| | | | | | | | respectively. Differential Revision: http://reviews.llvm.org/D25789 llvm-svn: 284655
* AMDGPU: Simplify tests with per function subtargetsMatt Arsenault2016-07-091-26/+52
| | | | llvm-svn: 274971
* R600 -> AMDGPU renameTom Stellard2015-06-131-0/+36
llvm-svn: 239657
OpenPOWER on IntegriCloud