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

[Joe Nash via Phabricator via llvm-commits]

Joe_Nash created this revision.
Joe_Nash added reviewers: arsenm, rampitec, foad.
Herald added subscribers: kerbowa, jfb, hiraditya, t-tye, tpr, dstuttard, yaxunl, nhaehnle, jvesely, kzhuravl.
Joe_Nash requested review of this revision.
Herald added subscribers: llvm-commits, wdng.
Herald added a project: LLVM.

Adds patterns for f64 ds_min/ds_max. Shrinks HasLDSFPAtomics
scope to enable f32.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D108994

Files:
  llvm/lib/Target/AMDGPU/DSInstructions.td
  llvm/test/CodeGen/AMDGPU/lds-atomic-add.ll
  llvm/test/CodeGen/AMDGPU/lds-atomic-min-max.ll
  llvm/test/CodeGen/AMDGPU/lds_atomic_f32.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D108994.369691.patch
Type: text/x-patch
Size: 60206 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210831/313436ce/attachment-0001.bin>