+ // Look at all of the allocas that we inlined through this call site. If we
+ // have already inlined other allocas through other calls into this function,
+ // then we know that they have disjoint lifetimes and that we can merge them.
+ //
+ // There are many heuristics possible for merging these allocas, and the
+ // different options have different tradeoffs. One thing that we *really*
+ // don't want to hurt is SRoA: once inlining happens, often allocas are no
+ // longer address taken and so they can be promoted.
+ //
+ // Our "solution" for that is to only merge allocas whose outermost type is an
+ // array type. These are usually not promoted because someone is using a
+ // variable index into them. These are also often the most important ones to
+ // merge.
+ //
+ // A better solution would be to have real memory lifetime markers in the IR
+ // and not have the inliner do any merging of allocas at all. This would
+ // allow the backend to do proper stack slot coloring of all allocas that
+ // *actually make it to the backend*, which is really what we want.
+ //
+ // Because we don't have this information, we do this simple and useful hack.
+ //
+ SmallPtrSet<AllocaInst*, 16> UsedAllocas;
+
+ // When processing our SCC, check to see if CS was inlined from some other
+ // call site. For example, if we're processing "A" in this code:
+ // A() { B() }
+ // B() { x = alloca ... C() }
+ // C() { y = alloca ... }
+ // Assume that C was not inlined into B initially, and so we're processing A
+ // and decide to inline B into A. Doing this makes an alloca available for
+ // reuse and makes a callsite (C) available for inlining. When we process
+ // the C call site we don't want to do any alloca merging between X and Y
+ // because their scopes are not disjoint. We could make this smarter by
+ // keeping track of the inline history for each alloca in the
+ // InlinedArrayAllocas but this isn't likely to be a significant win.
+ if (InlineHistory != -1) // Only do merging for top-level call sites in SCC.
+ return true;
+
+ // Loop over all the allocas we have so far and see if they can be merged with
+ // a previously inlined alloca. If not, remember that we had it.
+ for (unsigned AllocaNo = 0, e = IFI.StaticAllocas.size();
+ AllocaNo != e; ++AllocaNo) {
+ AllocaInst *AI = IFI.StaticAllocas[AllocaNo];
+
+ // Don't bother trying to merge array allocations (they will usually be
+ // canonicalized to be an allocation *of* an array), or allocations whose
+ // type is not itself an array (because we're afraid of pessimizing SRoA).
+ const ArrayType *ATy = dyn_cast<ArrayType>(AI->getAllocatedType());
+ if (ATy == 0 || AI->isArrayAllocation())
+ continue;
+
+ // Get the list of all available allocas for this array type.
+ std::vector<AllocaInst*> &AllocasForType = InlinedArrayAllocas[ATy];
+
+ // Loop over the allocas in AllocasForType to see if we can reuse one. Note
+ // that we have to be careful not to reuse the same "available" alloca for
+ // multiple different allocas that we just inlined, we use the 'UsedAllocas'
+ // set to keep track of which "available" allocas are being used by this
+ // function. Also, AllocasForType can be empty of course!
+ bool MergedAwayAlloca = false;
+ for (unsigned i = 0, e = AllocasForType.size(); i != e; ++i) {
+ AllocaInst *AvailableAlloca = AllocasForType[i];
+
+ // The available alloca has to be in the right function, not in some other
+ // function in this SCC.
+ if (AvailableAlloca->getParent() != AI->getParent())
+ continue;
+
+ // If the inlined function already uses this alloca then we can't reuse
+ // it.
+ if (!UsedAllocas.insert(AvailableAlloca))
+ continue;
+
+ // Otherwise, we *can* reuse it, RAUW AI into AvailableAlloca and declare
+ // success!
+ DEBUG(dbgs() << " ***MERGED ALLOCA: " << *AI << "\n\t\tINTO: "
+ << *AvailableAlloca << '\n');
+
+ AI->replaceAllUsesWith(AvailableAlloca);
+ AI->eraseFromParent();
+ MergedAwayAlloca = true;
+ ++NumMergedAllocas;
+ IFI.StaticAllocas[AllocaNo] = 0;
+ break;
+ }