[CGP] Lazily compute domtree only when needed during address matching

This is a compile time optimization for d9e93e8e5.  As pointed out in post dommit review on the original review (D96399), there was a moderately large compile time regression with this patch and the eager computation of domtree on matcher construction is the first obvious candidate for why.

1 files changed, 20 insertions, 12 deletions

diff --git a/llvm/lib/CodeGen/CodeGenPrepare.cpp b/llvm/lib/CodeGen/CodeGenPrepare.cpp
index a7e1aef..875a0ee 100644
--- a/llvm/lib/CodeGen/CodeGenPrepare.cpp
+++ b/llvm/lib/CodeGen/CodeGenPrepare.cpp
@@ -3083,7 +3083,7 @@ class AddressingModeMatcher {
   const TargetRegisterInfo &TRI;
   const DataLayout &DL;
   const LoopInfo &LI;
-  const DominatorTree &DT;
+  const std::function<const DominatorTree &()> getDTFn;
 
   /// AccessTy/MemoryInst - This is the type for the access (e.g. double) and
   /// the memory instruction that we're computing this address for.
@@ -3120,14 +3120,15 @@ class AddressingModeMatcher {
   AddressingModeMatcher(
       SmallVectorImpl<Instruction *> &AMI, const TargetLowering &TLI,
       const TargetRegisterInfo &TRI, const LoopInfo &LI,
-      const DominatorTree &DT, Type *AT, unsigned AS, Instruction *MI,
-      ExtAddrMode &AM, const SetOfInstrs &InsertedInsts,
-      InstrToOrigTy &PromotedInsts, TypePromotionTransaction &TPT,
+      const std::function<const DominatorTree &()> getDTFn,
+      Type *AT, unsigned AS, Instruction *MI, ExtAddrMode &AM,
+      const SetOfInstrs &InsertedInsts, InstrToOrigTy &PromotedInsts,
+      TypePromotionTransaction &TPT,
       std::pair<AssertingVH<GetElementPtrInst>, int64_t> &LargeOffsetGEP,
       bool OptSize, ProfileSummaryInfo *PSI, BlockFrequencyInfo *BFI)
       : AddrModeInsts(AMI), TLI(TLI), TRI(TRI),
-        DL(MI->getModule()->getDataLayout()), LI(LI), DT(DT), AccessTy(AT),
-        AddrSpace(AS), MemoryInst(MI), AddrMode(AM),
+        DL(MI->getModule()->getDataLayout()), LI(LI), getDTFn(getDTFn),
+        AccessTy(AT), AddrSpace(AS), MemoryInst(MI), AddrMode(AM),
         InsertedInsts(InsertedInsts), PromotedInsts(PromotedInsts), TPT(TPT),
         LargeOffsetGEP(LargeOffsetGEP), OptSize(OptSize), PSI(PSI), BFI(BFI) {
     IgnoreProfitability = false;
@@ -3144,7 +3145,8 @@ public:
   static ExtAddrMode
   Match(Value *V, Type *AccessTy, unsigned AS, Instruction *MemoryInst,
         SmallVectorImpl<Instruction *> &AddrModeInsts,
-        const TargetLowering &TLI, const LoopInfo &LI, const DominatorTree &DT,
+        const TargetLowering &TLI, const LoopInfo &LI,
+        const std::function<const DominatorTree &()> getDTFn,
         const TargetRegisterInfo &TRI, const SetOfInstrs &InsertedInsts,
         InstrToOrigTy &PromotedInsts, TypePromotionTransaction &TPT,
         std::pair<AssertingVH<GetElementPtrInst>, int64_t> &LargeOffsetGEP,
@@ -3152,7 +3154,7 @@ public:
     ExtAddrMode Result;
 
     bool Success = AddressingModeMatcher(
-        AddrModeInsts, TLI, TRI, LI, DT, AccessTy, AS, MemoryInst, Result,
+        AddrModeInsts, TLI, TRI, LI, getDTFn, AccessTy, AS, MemoryInst, Result,
         InsertedInsts, PromotedInsts, TPT, LargeOffsetGEP, OptSize, PSI,
         BFI).matchAddr(V, 0);
     (void)Success; assert(Success && "Couldn't select *anything*?");
@@ -3910,7 +3912,7 @@ bool AddressingModeMatcher::matchScaledValue(Value *ScaleReg, int64_t Scale,
       Instruction *IVInc = IVStep->first;
       APInt Step = IVStep->second;
       APInt Offset = Step * AddrMode.Scale;
-      if (Offset.isSignedIntN(64) && DT.dominates(IVInc, MemoryInst)) {
+      if (Offset.isSignedIntN(64) && getDTFn().dominates(IVInc, MemoryInst)) {
         TestAddrMode.InBounds = false;
         TestAddrMode.ScaledReg = IVInc;
         TestAddrMode.BaseOffs -= Offset.getLimitedValue();
@@ -5016,7 +5018,7 @@ isProfitableToFoldIntoAddressingMode(Instruction *I, ExtAddrMode &AMBefore,
                                                                       0);
     TypePromotionTransaction::ConstRestorationPt LastKnownGood =
         TPT.getRestorationPoint();
-    AddressingModeMatcher Matcher(MatchedAddrModeInsts, TLI, TRI, LI, DT,
+    AddressingModeMatcher Matcher(MatchedAddrModeInsts, TLI, TRI, LI, getDTFn,
                                   AddressAccessTy, AS, MemoryInst, Result,
                                   InsertedInsts, PromotedInsts, TPT,
                                   LargeOffsetGEP, OptSize, PSI, BFI);
@@ -5122,9 +5124,15 @@ bool CodeGenPrepare::optimizeMemoryInst(Instruction *MemoryInst, Value *Addr,
     AddrModeInsts.clear();
     std::pair<AssertingVH<GetElementPtrInst>, int64_t> LargeOffsetGEP(nullptr,
                                                                       0);
-    Function *F = MemoryInst->getParent()->getParent();
+    // Defer the query (and possible computation of) the dom tree to point of
+    // actual use.  It's expected that most address matches don't actually need
+    // the domtree.
+    auto getDTFn = [MemoryInst, this]() -> const DominatorTree & {
+      Function *F = MemoryInst->getParent()->getParent();
+      return this->getDT(*F);
+    };
     ExtAddrMode NewAddrMode = AddressingModeMatcher::Match(
-        V, AccessTy, AddrSpace, MemoryInst, AddrModeInsts, *TLI, *LI, getDT(*F),
+        V, AccessTy, AddrSpace, MemoryInst, AddrModeInsts, *TLI, *LI, getDTFn,
         *TRI, InsertedInsts, PromotedInsts, TPT, LargeOffsetGEP, OptSize, PSI,
         BFI.get());