llvm-project.git/llvm/test/CodeGen/AMDGPU/fdot2.ll, branch users/nico/python-2

[SelectionDAG] Remove UnsafeFPMath check in `visitFADDForFMACombine` (#127770)

2025-06-25T04:31:23+00:00

As requested in #127488, remove reference to `Options.UnsafeFPMath`,
which should be obsolete and `AllowFPOpFusion` also handles it.

[AMDGPU] Fix FMA combine (#119217)

2024-12-10T09:11:19+00:00

Update the check in the FMA combine to check dot10-insts instead of
dot7-insts.

The target of the combine, v_dot2_f32_f16, is available only if
dot10-insts target feature is enabled.

The issue probably dates back to the change that split out dot10-insts
out of dot7-insts.

As far as I can see, this does not affect any current targets, but if a
future target has dot7-insts, but not dot10-insts that would cause a
crash ("cannot select") for the input ir in the test.

[AMDGPU,test] Change llc -march= to -mtriple= (#75982)

2024-01-17T05:54:58+00:00

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][MC] Remove incorrect `_e32` suffix from `v_dot2c_f32_f16` and `v_dot4c_i32_i8` (#77993)

2024-01-16T04:11:50+00:00

The two VOP2 instructions cannot be encoded as VOP3.

Fix #54691.

[AMDGPU] Convert some tests to opaque pointers (NFC)

2022-12-19T11:41:13+00:00

AMDGPU: Remove denormal subtarget features

2020-04-02T21:17:12+00:00

Switch to using the denormal-fp-math/denormal-fp-math-f32 attributes.

AMDGPU: Assume f32 denormals are enabled by default

2020-04-02T21:17:12+00:00

This will likely introduce catastrophic performance regressions on
older subtargets, but should be correct. A follow up change will
remove the old fp32-denormals subtarget features, and switch to using
the new denormal-fp-math/denormal-fp-math-f32 attributes. Frontends
should be making sure to add the denormal-fp-math-f32 attribute when
appropriate to avoid performance regressions.

[AMDGPU] gfx1011/gfx1012 targets

2019-06-14T00:33:31+00:00

Differential Revision: https://reviews.llvm.org/D63307

llvm-svn: 363344

AMDGPU: Fix V_FMA_F16 selection on GFX9

2018-11-19T21:10:16+00:00

GFX9 should select opsel version.

Differential Revision: https://reviews.llvm.org/D54545

llvm-svn: 347265

AMDGPU: Fix check lines in fdot2 test:

2018-11-15T02:42:04+00:00

	GCN900 -> GFX900

llvm-svn: 346925