[PATCH] D86347: [SimplifyCFG] Two entry phi select costs

Roman Lebedev via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Thu Sep 10 00:40:28 PDT 2020


lebedev.ri added a comment.

So we have two thresholds at play here?
That doesn't seem right to me..



================
Comment at: llvm/lib/Transforms/Utils/SimplifyCFG.cpp:2026-2028
     BudgetRemaining -=
         TTI.getCmpSelInstrCost(Instruction::Select, PN.getType(), nullptr,
                                CostKind);
----------------
here


================
Comment at: llvm/lib/Transforms/Utils/SimplifyCFG.cpp:2044-2049
     unsigned OrigCost = OrigCE ? ComputeSpeculationCost(OrigCE, TTI) : 0;
     unsigned ThenCost = ThenCE ? ComputeSpeculationCost(ThenCE, TTI) : 0;
     unsigned MaxCost =
         2 * PHINodeFoldingThreshold * TargetTransformInfo::TCC_Basic;
     if (OrigCost + ThenCost > MaxCost)
       return false;
----------------
and here


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D86347/new/

https://reviews.llvm.org/D86347



More information about the llvm-commits mailing list