[PATCH] D67771: [AMDGPU] fixed underflow in getOccupancyWithNumVGPRs

Matt Arsenault via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Thu Sep 19 13:03:02 PDT 2019


arsenm accepted this revision.
arsenm added inline comments.
This revision is now accepted and ready to land.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp:602
   unsigned RoundedRegs = ((VGPRs + Granule - 1) / Granule) * Granule;
-  return std::min(getTotalNumVGPRs() / RoundedRegs, MaxWaves);
+  return std::min(std::max(getTotalNumVGPRs() / RoundedRegs, 1u), MaxWaves);
 }
----------------
(Could also do getTotalNumVGPRs() + RoundedRegs - 1) / RoundedRegs


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D67771/new/

https://reviews.llvm.org/D67771





More information about the llvm-commits mailing list