[PATCH] D142262: [AMDGPU] Use std::clamp to avoid overflow in the scheduler

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp:93
   SGPRCriticalLimit =
-      std::min(SGPRCriticalLimit - SGPRLimitBias, SGPRCriticalLimit);
-  SGPRCriticalLimit =
-      std::min(SGPRCriticalLimit - ErrorMargin, SGPRCriticalLimit);
-  VGPRCriticalLimit =
-      std::min(VGPRCriticalLimit - VGPRLimitBias, VGPRCriticalLimit);
+      SGPRCriticalLimit -
+      std::clamp(SGPRLimitBias + ErrorMargin, 0u, SGPRCriticalLimit);
----------------
clamp with min of 0 seems weird. Also could use -=


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D142262/new/

https://reviews.llvm.org/D142262