[PATCH] D108994: [AMDGPU] Enable ds_min/ds_max on more subtargets

[Joe Nash via Phabricator via llvm-commits]

Joe_Nash marked an inline comment as done.
Joe_Nash added a comment.

In D108994#2974626 <https://reviews.llvm.org/D108994#2974626>, @foad wrote:

>> Shrinks HasLDSFPAtomics scope to enable f32.
>
> "... to enable f32 **add**"? Maybe update the description of the feature to reflect this?

Agreed



================
Comment at: llvm/test/CodeGen/AMDGPU/lds-atomic-add.ll:1
+; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,VI %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9 %s
----------------
foad wrote:
> This file looks like a subset of the existing `test/CodeGen/AMDGPU/lds_atomic_f32.ll`?
I split the test because the lds_atomic_fadd is only on gfx8 and gfx9, but the min/max are available on all architectures


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D108994/new/

https://reviews.llvm.org/D108994