[PATCH] D93708: [AMDGPU] Add a new Clamp Pattern to the GlobalISel Path.

Matt Arsenault via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Mon Jan 4 10:40:11 PST 2021


arsenm added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUPostLegalizerCombiner.cpp:2
+//=== lib/CodeGen/GlobalISel/AMDGPUPostLegalizerCombiner.cpp
+//---------------===//
 //
----------------
This has too many -s then


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUPostLegalizerCombiner.cpp:285
+
+  if (!mi_match(Base, MRI, m_GISelect(m_GICmp(m_Pred(Predicate2), m_Reg(), m_Reg()), m_Reg(MatchInfo.AssignValue), m_ICst(MatchInfo.Cmp2))))
+    return false;
----------------
This should still be trying to match against the min/max opcodes, not looking for compare and selects


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D93708/new/

https://reviews.llvm.org/D93708



More information about the llvm-commits mailing list