llvm-project.git/llvm/test/CodeGen/AMDGPU/cube.ll, branch users/nico/python-2 Unnamed repository; edit this file 'description' to name the repository. AMDGPU: Replace insertelement poison with insertelement undef (#130896) 2025-03-12T13:33:33+00:00 Matt Arsenault Matthew.Arsenault@amd.com 2025-03-12T13:33:33+00:00 da42b2f67da603d19be4ab0ee33ae79e20c12c6c This is the bulk update with perl, with cases which require additional update left for later. 
This is the bulk update with perl, with cases which require additional
update left for later.
 [AMDGPU,test] Change llc -march= to -mtriple= (#75982) 2024-01-17T05:54:58+00:00 Fangrui Song i@maskray.me 2024-01-17T05:54:58+00:00 9e9907f1cfa424366fba58d9520f9305b537cec9 Similar to 806761a7629df268c8aed49657aeccffa6bca449. For IR files without a target triple, -mtriple= specifies the full target triple while -march= merely sets the architecture part of the default target triple, leaving a target triple which may not make sense, e.g. amdgpu-apple-darwin. Therefore, -march= is error-prone and not recommended for tests without a target triple. The issue has been benign as we recognize $unknown-apple-darwin as ELF instead of rejecting it outrightly. This patch changes AMDGPU tests to not rely on the default OS/environment components. Tests that need fixes are not changed: ``` LLVM :: CodeGen/AMDGPU/fabs.f64.ll LLVM :: CodeGen/AMDGPU/fabs.ll LLVM :: CodeGen/AMDGPU/floor.ll LLVM :: CodeGen/AMDGPU/fneg-fabs.f64.ll LLVM :: CodeGen/AMDGPU/fneg-fabs.ll LLVM :: CodeGen/AMDGPU/r600-infinite-loop-bug-while-reorganizing-vector.ll LLVM :: CodeGen/AMDGPU/schedule-if-2.ll ``` 
Similar to 806761a7629df268c8aed49657aeccffa6bca449.

For IR files without a target triple, -mtriple= specifies the full
target triple while -march= merely sets the architecture part of the
default target triple, leaving a target triple which may not make sense,
e.g. amdgpu-apple-darwin.

Therefore, -march= is error-prone and not recommended for tests without
a target triple. The issue has been benign as we recognize
$unknown-apple-darwin as ELF instead of rejecting it outrightly.

This patch changes AMDGPU tests to not rely on the default
OS/environment components. Tests that need fixes are not changed:

```
  LLVM :: CodeGen/AMDGPU/fabs.f64.ll
  LLVM :: CodeGen/AMDGPU/fabs.ll
  LLVM :: CodeGen/AMDGPU/floor.ll
  LLVM :: CodeGen/AMDGPU/fneg-fabs.f64.ll
  LLVM :: CodeGen/AMDGPU/fneg-fabs.ll
  LLVM :: CodeGen/AMDGPU/r600-infinite-loop-bug-while-reorganizing-vector.ll
  LLVM :: CodeGen/AMDGPU/schedule-if-2.ll
```
 AMDGPU: Bulk update some intrinsic tests to opaque pointers 2022-11-28T19:21:31+00:00 Matt Arsenault Matthew.Arsenault@amd.com 2022-11-28T19:13:14+00:00 ad386a886b16ad83a982c0eff3f80d8ae8888882 Done entirely with the script. 
Done entirely with the script.
[NFC] Removed unused prefixes in test/CodeGen/AMDGPU 2021-01-05T22:16:52+00:00 Mircea Trofin mtrofin@google.com 2021-01-05T22:15:20+00:00 1ebe86adf52cbddc03f535554b16585b2947b32c More patches to follow. Differential Revision: https://reviews.llvm.org/D94121 
More patches to follow.

Differential Revision: https://reviews.llvm.org/D94121
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21T21:39:51+00:00 Matt Arsenault Matthew.Arsenault@amd.com 2017-03-21T21:39:51+00:00 3dbeefa978fb7e7b231b249f9cd90c67b9e83277 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 
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 llvm.AMDGPU.cube intrinsic 2017-02-16T19:09:04+00:00 Matt Arsenault Matthew.Arsenault@amd.com 2017-02-16T19:09:04+00:00 b95ddd7ceac7011f456fc576e60d391a6e13c312 llvm-svn: 295359 
llvm-svn: 295359
Enable FeatureFlatForGlobal on Volcanic Islands 2017-01-24T22:02:15+00:00 Matt Arsenault Matthew.Arsenault@amd.com 2017-01-24T22:02:15+00:00 7aad8fd8f45e07d72e50792aec18c2b476bdd96e This switches to the workaround that HSA defaults to for the mesa path. This should be applied to the 4.0 branch. Patch by Vedran Miletić <vedran@miletic.net> llvm-svn: 292982 
This switches to the workaround that HSA defaults to
for the mesa path.

This should be applied to the 4.0 branch.

Patch by Vedran Miletić <vedran@miletic.net>

llvm-svn: 292982
AMDGPU: Add VI i16 support 2016-11-10T16:02:37+00:00 Tom Stellard thomas.stellard@amd.com 2016-11-10T16:02:37+00:00 115a61560e24e08ecca0b3e2d16e8f1491b47f61 Patch By: Wei Ding Differential Revision: https://reviews.llvm.org/D18049 llvm-svn: 286464 
Patch By: Wei Ding

Differential Revision: https://reviews.llvm.org/D18049

llvm-svn: 286464
Revert "AMDGPU: Add VI i16 support" 2016-11-04T13:06:34+00:00 Tom Stellard thomas.stellard@amd.com 2016-11-04T13:06:34+00:00 2d2d33f1dc4c976ab41ab5fc814f2aca7fdd99d1 This reverts commit r285939 and r285948. These broke some conformance tests. llvm-svn: 285995 
This reverts commit r285939 and r285948.  These broke some conformance tests.

llvm-svn: 285995
AMDGPU: Add VI i16 support 2016-11-03T17:13:50+00:00 Tom Stellard thomas.stellard@amd.com 2016-11-03T17:13:50+00:00 2b3379cdffaa5d2af96abf0489f9755149be1f8e Patch By: Wei Ding Differential Revision: https://reviews.llvm.org/D18049 llvm-svn: 285939 
Patch By: Wei Ding

Differential Revision: https://reviews.llvm.org/D18049

llvm-svn: 285939