llvm-project.git/llvm/test/CodeGen/AMDGPU/dynamic_stackalloc.ll, branch users/chapuni/cov/single/condop

[AMDGPU] Support divergent sized dynamic alloca (#121148)

2025-01-06T05:28:24+00:00

Currently, AMDGPU backend can handle uniform-sized dynamic allocas. 
This patch extends support for divergent-sized dynamic allocas.
When the size argument of a dynamic alloca is divergent, 
a wave-wide reduction is performed to get the required stack space. 
`@llvm.amdgcn.wave.reduce.umax` is used to perform the 
wave reduction.

Dynamic allocas are not completely supported yet, 
as the stack is not properly restored on function exit.
This patch doesn't attempt to address the aforementioned issue.

Note: Compiler already Zero-Extends or Truncates all other 
types(of alloca size arg) to i32.

Reapply "[NFC][AMDGPU] Pre-commit clang and llvm tests for dynamic allocas" (#120410)

2024-12-18T12:50:45+00:00

This reapplies commit https://github.com/llvm/llvm-project/pull/120063.

A machine-verifier bug was causing a crash in the previous commit. 
This has been addressed in
https://github.com/llvm/llvm-project/pull/120393.

Revert "[NFC][AMDGPU] Pre-commit clang and llvm tests for dynamic allocas" (#120369)

2024-12-18T07:06:49+00:00

Reverts llvm/llvm-project#120063 due to build-bot failures

[NFC][AMDGPU] Pre-commit clang and llvm tests for dynamic allocas (#120063)

2024-12-18T06:44:37+00:00

For #119822

[AMDGPU] Remove duplicate -mtriple options in tests (#91576)

2024-05-09T09:59:25+00:00

[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] Remove repeated -mtriple options from RUN lines (#66486)

2023-09-15T10:29:24+00:00

[test] Change llc -march= to -mtriple=

2023-09-11T21:42:37+00:00

The issue is uncovered by #47698: 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. riscv64-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.

AMDGPU: Convert some assorted tests to opaque pointers

2022-12-02T02:40:30+00:00

AMDGPU: Remove remnants of old address space mapping

2018-08-31T05:49:54+00:00

llvm-svn: 341165