Skip to content

release/20.x: [SystemZ] Fix compile time regression in adjustInliningThreshold(). (#137527) #137628

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Apr 29, 2025
Merged

release/20.x: [SystemZ] Fix compile time regression in adjustInliningThreshold(). (#137527) #137628

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
48 changes: 30 additions & 18 deletions llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@
#include "llvm/CodeGen/BasicTTIImpl.h"
#include "llvm/CodeGen/TargetLowering.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/InstIterator.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Intrinsics.h"
#include "llvm/Support/Debug.h"
Expand Down Expand Up @@ -80,7 +81,6 @@ unsigned SystemZTTIImpl::adjustInliningThreshold(const CallBase *CB) const {
const Function *Callee = CB->getCalledFunction();
if (!Callee)
return 0;
const Module *M = Caller->getParent();

// Increase the threshold if an incoming argument is used only as a memcpy
// source.
Expand All @@ -92,25 +92,37 @@ unsigned SystemZTTIImpl::adjustInliningThreshold(const CallBase *CB) const {
}
}

// Give bonus for globals used much in both caller and callee.
std::set<const GlobalVariable *> CalleeGlobals;
std::set<const GlobalVariable *> CallerGlobals;
for (const GlobalVariable &Global : M->globals())
for (const User *U : Global.users())
if (const Instruction *User = dyn_cast<Instruction>(U)) {
if (User->getParent()->getParent() == Callee)
CalleeGlobals.insert(&Global);
if (User->getParent()->getParent() == Caller)
CallerGlobals.insert(&Global);
// Give bonus for globals used much in both caller and a relatively small
// callee.
unsigned InstrCount = 0;
SmallDenseMap<const Value *, unsigned> Ptr2NumUses;
for (auto &I : instructions(Callee)) {
if (++InstrCount == 200) {
Ptr2NumUses.clear();
break;
}
if (const auto *SI = dyn_cast<StoreInst>(&I)) {
if (!SI->isVolatile())
if (auto *GV = dyn_cast<GlobalVariable>(SI->getPointerOperand()))
Ptr2NumUses[GV]++;
} else if (const auto *LI = dyn_cast<LoadInst>(&I)) {
if (!LI->isVolatile())
if (auto *GV = dyn_cast<GlobalVariable>(LI->getPointerOperand()))
Ptr2NumUses[GV]++;
} else if (const auto *GEP = dyn_cast<GetElementPtrInst>(&I)) {
if (auto *GV = dyn_cast<GlobalVariable>(GEP->getPointerOperand())) {
unsigned NumStores = 0, NumLoads = 0;
countNumMemAccesses(GEP, NumStores, NumLoads, Callee);
Ptr2NumUses[GV] += NumLoads + NumStores;
}
for (auto *GV : CalleeGlobals)
if (CallerGlobals.count(GV)) {
unsigned CalleeStores = 0, CalleeLoads = 0;
}
}

for (auto [Ptr, NumCalleeUses] : Ptr2NumUses)
if (NumCalleeUses > 10) {
unsigned CallerStores = 0, CallerLoads = 0;
countNumMemAccesses(GV, CalleeStores, CalleeLoads, Callee);
countNumMemAccesses(GV, CallerStores, CallerLoads, Caller);
if ((CalleeStores + CalleeLoads) > 10 &&
(CallerStores + CallerLoads) > 10) {
countNumMemAccesses(Ptr, CallerStores, CallerLoads, Caller);
if (CallerStores + CallerLoads > 10) {
Bonus = 1000;
break;
}
Expand Down
Loading