[PATCH] D154858: [WIP] [AMDGPU] Add llvm.amdgcn.reduce.add Intrinsic.

[Pravin Jagtap via Phabricator via llvm-commits]

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

When input to intrinsic is uniform value, lowering uses ctpop to
compute reduced value whereas if input value is divergent,
iterates over only active lanes using cttz.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D154858

Files:
  llvm/include/llvm/IR/IntrinsicsAMDGPU.td
  llvm/lib/Target/AMDGPU/AMDGPU.h
  llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
  llvm/lib/Target/AMDGPU/CMakeLists.txt
  llvm/lib/Target/AMDGPU/SIISelLowering.cpp
  llvm/lib/Target/AMDGPU/SIISelLowering.h
  llvm/lib/Target/AMDGPU/SIInstructions.td
  llvm/lib/Target/AMDGPU/SILowerReduceAndScanPseudo.cpp
  llvm/test/CodeGen/AMDGPU/llc-pipeline.ll
  llvm/test/CodeGen/AMDGPU/llvm.amdgpu.reduce.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D154858.538679.patch
Type: text/x-patch
Size: 19157 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230710/3f70fe95/attachment.bin>