[llvm] [SystemZ] Fix compile time regression in adjustInliningThreshold(). (PR #137527)

[Jonas Paulsson via llvm-commits]

================
@@ -92,29 +91,38 @@ 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.
+  if (Callee->getInstructionCount() < 200) {
+    std::map<const Value *, unsigned> Ptr2NumUses;
+    for (auto &BB : *Callee)
+      for (auto &I : BB) {
+        if (const auto *SI = dyn_cast<StoreInst>(&I)) {
+          if (!SI->isVolatile())
+            Ptr2NumUses[SI->getPointerOperand()]++;
+        } else if (const auto *LI = dyn_cast<LoadInst>(&I)) {
+          if (!LI->isVolatile())
+            Ptr2NumUses[LI->getPointerOperand()]++;
+        } else if (const auto *GEP = dyn_cast<GetElementPtrInst>(&I)) {
+          unsigned NumStores = 0, NumLoads = 0;
+          countNumMemAccesses(GEP, NumStores, NumLoads, Callee);
+          Ptr2NumUses[GEP->getPointerOperand()] += NumLoads + NumStores;
----------------
JonPsson1 wrote:

There actually is a bit further down - separate checks for number of loads and stores. It may be that these could be combined there as well, but that should probably wait and be benchmarked after this.

https://github.com/llvm/llvm-project/pull/137527