[llvm] [VPlan] Implment VPReductionRecipe::computeCost(). NFC (PR #107790)
Elvis Wang via llvm-commits
llvm-commits at lists.llvm.org
Sun Sep 8 17:19:35 PDT 2024
https://github.com/ElvisWang123 created https://github.com/llvm/llvm-project/pull/107790
Implementation of `computeCost()` function for `VPReductionRecipe`.
>From d6775970a0a18fab11f4c8909d997b4a3371e9b3 Mon Sep 17 00:00:00 2001
From: Elvis Wang <elvis.wang at sifive.com>
Date: Wed, 4 Sep 2024 20:52:14 -0700
Subject: [PATCH] [VPlan] Implment VPReductionRecipe::computeCost(). NFC
Implementation of `computeCost()` function for `VPReductionRecipe`.
---
llvm/lib/Transforms/Vectorize/VPlan.h | 4 ++++
.../lib/Transforms/Vectorize/VPlanRecipes.cpp | 24 +++++++++++++++++++
2 files changed, 28 insertions(+)
diff --git a/llvm/lib/Transforms/Vectorize/VPlan.h b/llvm/lib/Transforms/Vectorize/VPlan.h
index bd71dbffa929e7..68f8ea3dea0db3 100644
--- a/llvm/lib/Transforms/Vectorize/VPlan.h
+++ b/llvm/lib/Transforms/Vectorize/VPlan.h
@@ -2242,6 +2242,10 @@ class VPReductionRecipe : public VPSingleDefRecipe {
/// Generate the reduction in the loop
void execute(VPTransformState &State) override;
+ /// Return the cost of VPReductionRecipe.
+ InstructionCost computeCost(ElementCount VF,
+ VPCostContext &Ctx) const override;
+
#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
/// Print the recipe.
void print(raw_ostream &O, const Twine &Indent,
diff --git a/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp b/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
index 3d08e3cefbf633..12b6d2c7d06dd1 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
@@ -1897,6 +1897,30 @@ void VPReductionEVLRecipe::execute(VPTransformState &State) {
State.set(this, NewRed, 0, /*IsScalar*/ true);
}
+InstructionCost VPReductionRecipe::computeCost(ElementCount VF,
+ VPCostContext &Ctx) const {
+ RecurKind RdxKind = RdxDesc.getRecurrenceKind();
+ Type *ElementTy = RdxDesc.getRecurrenceType();
+ auto *VectorTy = dyn_cast<VectorType>(ToVectorTy(ElementTy, VF));
+ TTI::TargetCostKind CostKind = TTI::TCK_RecipThroughput;
+ unsigned Opcode = RdxDesc.getOpcode();
+
+ if (VectorTy == nullptr)
+ return InstructionCost::getInvalid();
+
+ // Cost = Reduction cost + BinOp cost
+ InstructionCost Cost =
+ Ctx.TTI.getArithmeticInstrCost(Opcode, ElementTy, CostKind);
+ if (RecurrenceDescriptor::isMinMaxRecurrenceKind(RdxKind)) {
+ Intrinsic::ID Id = getMinMaxReductionIntrinsicOp(RdxKind);
+ return Cost + Ctx.TTI.getMinMaxReductionCost(
+ Id, VectorTy, RdxDesc.getFastMathFlags(), CostKind);
+ }
+
+ return Cost + Ctx.TTI.getArithmeticReductionCost(
+ Opcode, VectorTy, RdxDesc.getFastMathFlags(), CostKind);
+}
+
#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
void VPReductionRecipe::print(raw_ostream &O, const Twine &Indent,
VPSlotTracker &SlotTracker) const {
More information about the llvm-commits
mailing list