[PATCH] D148199: [AMDGPU] Add a new command line argument amdgpu-atomic-optimizer-use-dpp

[Pravin Jagtap via Phabricator via llvm-commits]

pravinjagtap created this revision.
pravinjagtap added reviewers: foad, ruiling, b-sumner, arsenm, nhaehnle.
Herald added subscribers: kosarev, StephenFan, kerbowa, hiraditya, tpr, dstuttard, yaxunl, jvesely, kzhuravl.
Herald added a project: All.
pravinjagtap requested review of this revision.
Herald added subscribers: llvm-commits, wdng.
Herald added a project: LLVM.

The current implementation of atomic optimization uses DPP and WWM for
scan computations. This new command line argument has exactly the same
behavior as old amdgpu-atomic-optimizations.

This will allow the graphics pipeline to set the new argument instead of the old one.
The old command line argument will be deprecated when graphics pipeline
switches to the new option


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D148199

Files:
  llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
  llvm/test/CodeGen/AMDGPU/atomic_load_add.ll
  llvm/test/CodeGen/AMDGPU/atomic_load_sub.ll
  llvm/test/CodeGen/AMDGPU/atomic_optimizations_buffer.ll
  llvm/test/CodeGen/AMDGPU/atomic_optimizations_global_pointer.ll
  llvm/test/CodeGen/AMDGPU/atomic_optimizations_local_pointer.ll
  llvm/test/CodeGen/AMDGPU/atomic_optimizations_pixelshader.ll
  llvm/test/CodeGen/AMDGPU/atomic_optimizations_raw_buffer.ll
  llvm/test/CodeGen/AMDGPU/atomic_optimizations_struct_buffer.ll
  llvm/test/CodeGen/AMDGPU/divergence-at-use.ll
  llvm/test/CodeGen/AMDGPU/global_atomics.ll
  llvm/test/CodeGen/AMDGPU/global_atomics_i64.ll
  llvm/test/CodeGen/AMDGPU/global_atomics_i64_min_max_system.ll
  llvm/test/CodeGen/AMDGPU/global_atomics_min_max_system.ll
  llvm/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.atomic.ll
  llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.atomic.fadd.ll
  llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.atomic.ll
  llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.atomic.fadd.ll
  llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.atomic.ll
  llvm/test/CodeGen/AMDGPU/local-atomics.ll
  llvm/test/CodeGen/AMDGPU/local-atomics64.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D148199.513083.patch
Type: text/x-patch
Size: 37877 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230413/8b8a173b/attachment.bin>