[PATCH] D75999: [AMDGPU] Extend macro fusion for ADDC and SUBB to SUBBREV

[Jay Foad via Phabricator via llvm-commits]

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

There's a lot of test case churn but the overall effect is to increase
the number of back-to-back v_sub,v_subbrev pairs, which can execute with
no delay even on gfx10.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D75999

Files:
  llvm/lib/Target/AMDGPU/AMDGPUMacroFusion.cpp
  llvm/test/CodeGen/AMDGPU/amdgpu-codegenprepare-idiv.ll
  llvm/test/CodeGen/AMDGPU/bypass-div.ll
  llvm/test/CodeGen/AMDGPU/srem64.ll
  llvm/test/CodeGen/AMDGPU/sub-zext-cc-zext-cc.ll
  llvm/test/CodeGen/AMDGPU/udiv64.ll
  llvm/test/CodeGen/AMDGPU/urem64.ll
  llvm/test/CodeGen/AMDGPU/wave32.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D75999.249644.patch
Type: text/x-patch
Size: 52981 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200311/7b0bbd2b/attachment-0001.bin>