[TTI] getMemcpyCost

This adds new function getMemcpyCost to TTI so that the cost of a memcpy can be
modeled and queried. The default implementation returns Expensive, but targets
can override this function to model the cost more accurately.

Differential Revision: https://reviews.llvm.org/D59252

llvm-svn: 356555
This commit is contained in:
Sjoerd Meijer 2019-03-20 14:15:46 +00:00
parent 0373bedb41
commit 633fb0f266
3 changed files with 29 additions and 1 deletions

View File

@ -246,6 +246,10 @@ public:
ArrayRef<const Value *> Arguments,
const User *U = nullptr) const;
/// \Return the expected cost of a memcpy, which could e.g. depend on the
/// source/destination type and alignment and the number of bytes copied.
int getMemcpyCost(const Instruction *I) const;
/// \return The estimated number of case clusters when lowering \p 'SI'.
/// \p JTSize Set a jump table size only when \p SI is suitable for a jump
/// table.
@ -1053,6 +1057,7 @@ public:
virtual int getIntrinsicCost(Intrinsic::ID IID, Type *RetTy,
ArrayRef<const Value *> Arguments,
const User *U) = 0;
virtual int getMemcpyCost(const Instruction *I) = 0;
virtual unsigned getEstimatedNumberOfCaseClusters(const SwitchInst &SI,
unsigned &JTSize) = 0;
virtual int
@ -1267,6 +1272,9 @@ public:
const User *U = nullptr) override {
return Impl.getIntrinsicCost(IID, RetTy, Arguments, U);
}
int getMemcpyCost(const Instruction *I) {
return Impl.getMemcpyCost(I);
}
int getUserCost(const User *U, ArrayRef<const Value *> Operands) override {
return Impl.getUserCost(U, Operands);
}

View File

@ -140,15 +140,22 @@ public:
unsigned getInliningThresholdMultiplier() { return 1; }
unsigned getMemcpyCost(const Instruction *I) {
return TTI::TCC_Expensive;
}
unsigned getIntrinsicCost(Intrinsic::ID IID, Type *RetTy,
ArrayRef<Type *> ParamTys, const User *U) {
switch (IID) {
default:
// Intrinsics rarely (if ever) have normal argument setup constraints.
// Model them as having a basic instruction cost.
// FIXME: This is wrong for libc intrinsics.
return TTI::TCC_Basic;
// TODO: other libc intrinsics.
case Intrinsic::memcpy:
return getMemcpyCost(dyn_cast<Instruction>(U));
case Intrinsic::annotation:
case Intrinsic::assume:
case Intrinsic::sideeffect:

View File

@ -0,0 +1,13 @@
; RUN: opt < %s -cost-model -analyze -cost-kind=code-size | FileCheck %s
target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"
target triple = "thumbv7m-arm-unknown-eabi"
define void @memcpy(i8* %d, i8* %s, i32 %N) {
entry:
; CHECK: cost of 4 for instruction: call void @llvm.memcpy.p0i8.p0i8.i32
call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %d, i8* align 1 %s, i32 36, i1 false)
ret void
}
declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture writeonly, i8* nocapture readonly, i32, i1) #1