[PATCH] D156301: [WIP] Support FAdd/FSub global atomics in AMDGPUAtomicOptimizer.

[Pravin Jagtap via Phabricator via llvm-commits]

pravinjagtap updated this revision to Diff 546342.
pravinjagtap added a comment.

Supported `float` type for Atomic Ops in Atomic Optimizer for DPP strategy.
This mostly requires the bitcasting noise before and after:

- amdgcn.set.inactive
- amdgcn.update.dpp
- amdgcn.readlane
- amdgcn.writelane
- amdgcn.permlanex16
- amdgcn.permlanex64

We can get rid of this noise after D147732 <https://reviews.llvm.org/D147732> and D156647 <https://reviews.llvm.org/D156647>.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D156301/new/

https://reviews.llvm.org/D156301

Files:
  llvm/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp
  llvm/test/CodeGen/AMDGPU/GlobalISel/global-atomic-fadd.f32-no-rtn.ll
  llvm/test/CodeGen/AMDGPU/GlobalISel/global-atomic-fadd.f32-rtn.ll
  llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.global.atomic.fadd.ll
  llvm/test/CodeGen/AMDGPU/cgp-addressing-modes-gfx908.ll
  llvm/test/CodeGen/AMDGPU/global-atomic-fadd.f32-no-rtn.ll
  llvm/test/CodeGen/AMDGPU/global-atomic-fadd.f32-rtn.ll
  llvm/test/CodeGen/AMDGPU/global-atomics-fp.ll
  llvm/test/CodeGen/AMDGPU/global_atomics_iterative_scan_fp.ll
  llvm/test/CodeGen/AMDGPU/llvm.amdgcn.atomic.fadd.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D156301.546342.patch
Type: text/x-patch
Size: 102803 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230802/8317287b/attachment.bin>