[SimpleLoopUnswitch] Fix exponential unswitch

When unswitching via invariant condition injection, we currently
mark the condition in the old loop, so that it does not get
unswitched again. However, if there are multiple branches for
which conditions can be injected, then we can do that for both
the old and new loop. This means that the number of unswitches
increases exponentially.

Change the handling to be more similar to partial unswitching,
where we instead mark the whole loop, rather than a single
condition. This means that we will only generate a linear number
of loops.

TBH I think even that is still highly undesirable, and we should
probably be unswitching all candidates at the same time, so that
we end up with only two loops. But at least this mitigates the
worst case.

The test case is a reduced variant that generates 1700 lines of IR
without this patch and 290 with it.

Fixes #66868.

Author: nikic

llvm/lib/Transforms/Scalar/SimpleLoopUnswitch.cpp

@@ -2127,9 +2127,10 @@ static void unswitchNontrivialInvariants(
     Loop &L, Instruction &TI, ArrayRef<Value *> Invariants,
     IVConditionInfo &PartialIVInfo, DominatorTree &DT, LoopInfo &LI,
     AssumptionCache &AC,
-    function_ref<void(bool, bool, ArrayRef<Loop *>)> UnswitchCB,
+    function_ref<void(bool, bool, bool, ArrayRef<Loop *>)> UnswitchCB,
     ScalarEvolution *SE, MemorySSAUpdater *MSSAU,
-    function_ref<void(Loop &, StringRef)> DestroyLoopCB, bool InsertFreeze) {
+    function_ref<void(Loop &, StringRef)> DestroyLoopCB, bool InsertFreeze,
+    bool InjectedCondition) {
   auto *ParentBB = TI.getParent();
   BranchInst *BI = dyn_cast<BranchInst>(&TI);
   SwitchInst *SI = BI ? nullptr : cast<SwitchInst>(&TI);
@@ -2582,7 +2583,7 @@ static void unswitchNontrivialInvariants(
   for (Loop *UpdatedL : llvm::concat<Loop *>(NonChildClonedLoops, HoistedLoops))
     if (UpdatedL->getParentLoop() == ParentL)
       SibLoops.push_back(UpdatedL);
-  UnswitchCB(IsStillLoop, PartiallyInvariant, SibLoops);
+  UnswitchCB(IsStillLoop, PartiallyInvariant, InjectedCondition, SibLoops);
 
   if (MSSAU && VerifyMemorySSA)
     MSSAU->getMemorySSA()->verifyMemorySSA();
@@ -2980,13 +2981,6 @@ static bool shouldTryInjectInvariantCondition(
 /// the metadata.
 bool shouldTryInjectBasingOnMetadata(const BranchInst *BI,
                                      const BasicBlock *TakenSucc) {
-  // Skip branches that have already been unswithed this way. After successful
-  // unswitching of injected condition, we will still have a copy of this loop
-  // which looks exactly the same as original one. To prevent the 2nd attempt
-  // of unswitching it in the same pass, mark this branch as "nothing to do
-  // here".
-  if (BI->hasMetadata("llvm.invariant.condition.injection.disabled"))
-    return false;
   SmallVector<uint32_t> Weights;
   if (!extractBranchWeights(*BI, Weights))
     return false;
@@ -3069,13 +3063,9 @@ injectPendingInvariantConditions(NonTrivialUnswitchCandidate Candidate, Loop &L,
       Builder.CreateCondBr(InjectedCond, InLoopSucc, CheckBlock);
 
   Builder.SetInsertPoint(CheckBlock);
-  auto *NewTerm = Builder.CreateCondBr(TI->getCondition(), TI->getSuccessor(0),
-                                       TI->getSuccessor(1));
-
+  Builder.CreateCondBr(TI->getCondition(), TI->getSuccessor(0),
+                       TI->getSuccessor(1));
   TI->eraseFromParent();
-  // Prevent infinite unswitching.
-  NewTerm->setMetadata("llvm.invariant.condition.injection.disabled",
-                       MDNode::get(BB->getContext(), {}));
 
   // Fixup phis.
   for (auto &I : *InLoopSucc) {
@@ -3443,7 +3433,7 @@ static bool shouldInsertFreeze(Loop &L, Instruction &TI, DominatorTree &DT,
 static bool unswitchBestCondition(
     Loop &L, DominatorTree &DT, LoopInfo &LI, AssumptionCache &AC,
     AAResults &AA, TargetTransformInfo &TTI,
-    function_ref<void(bool, bool, ArrayRef<Loop *>)> UnswitchCB,
+    function_ref<void(bool, bool, bool, ArrayRef<Loop *>)> UnswitchCB,
     ScalarEvolution *SE, MemorySSAUpdater *MSSAU,
     function_ref<void(Loop &, StringRef)> DestroyLoopCB) {
   // Collect all invariant conditions within this loop (as opposed to an inner
@@ -3453,9 +3443,10 @@ static bool unswitchBestCondition(
   Instruction *PartialIVCondBranch = nullptr;
   collectUnswitchCandidates(UnswitchCandidates, PartialIVInfo,
                             PartialIVCondBranch, L, LI, AA, MSSAU);
-  collectUnswitchCandidatesWithInjections(UnswitchCandidates, PartialIVInfo,
-                                          PartialIVCondBranch, L, DT, LI, AA,
-                                          MSSAU);
+  if (!findOptionMDForLoop(&L, "llvm.loop.unswitch.injection.disable"))
+    collectUnswitchCandidatesWithInjections(UnswitchCandidates, PartialIVInfo,
+                                            PartialIVCondBranch, L, DT, LI, AA,
+                                            MSSAU);
   // If we didn't find any candidates, we're done.
   if (UnswitchCandidates.empty())
     return false;
@@ -3476,8 +3467,11 @@ static bool unswitchBestCondition(
     return false;
   }
 
-  if (Best.hasPendingInjection())
+  bool InjectedCondition = false;
+  if (Best.hasPendingInjection()) {
     Best = injectPendingInvariantConditions(Best, L, DT, LI, AC, MSSAU);
+    InjectedCondition = true;
+  }
   assert(!Best.hasPendingInjection() &&
          "All injections should have been done by now!");
 
@@ -3505,7 +3499,7 @@ static bool unswitchBestCondition(
                     << ") terminator: " << *Best.TI << "\n");
   unswitchNontrivialInvariants(L, *Best.TI, Best.Invariants, PartialIVInfo, DT,
                                LI, AC, UnswitchCB, SE, MSSAU, DestroyLoopCB,
-                               InsertFreeze);
+                               InsertFreeze, InjectedCondition);
   return true;
 }
 
@@ -3534,7 +3528,7 @@ static bool
 unswitchLoop(Loop &L, DominatorTree &DT, LoopInfo &LI, AssumptionCache &AC,
              AAResults &AA, TargetTransformInfo &TTI, bool Trivial,
              bool NonTrivial,
-             function_ref<void(bool, bool, ArrayRef<Loop *>)> UnswitchCB,
+             function_ref<void(bool, bool, bool, ArrayRef<Loop *>)> UnswitchCB,
              ScalarEvolution *SE, MemorySSAUpdater *MSSAU,
              ProfileSummaryInfo *PSI, BlockFrequencyInfo *BFI,
              function_ref<void(Loop &, StringRef)> DestroyLoopCB) {
@@ -3549,7 +3543,8 @@ unswitchLoop(Loop &L, DominatorTree &DT, LoopInfo &LI, AssumptionCache &AC,
   if (Trivial && unswitchAllTrivialConditions(L, DT, LI, SE, MSSAU)) {
     // If we unswitched successfully we will want to clean up the loop before
     // processing it further so just mark it as unswitched and return.
-    UnswitchCB(/*CurrentLoopValid*/ true, false, {});
+    UnswitchCB(/*CurrentLoopValid*/ true, /*PartiallyInvariant*/ false,
+               /*InjectedCondition*/ false, {});
     return true;
   }
 
@@ -3645,6 +3640,7 @@ PreservedAnalyses SimpleLoopUnswitchPass::run(Loop &L, LoopAnalysisManager &AM,
 
   auto UnswitchCB = [&L, &U, &LoopName](bool CurrentLoopValid,
                                         bool PartiallyInvariant,
+                                        bool InjectedCondition,
                                         ArrayRef<Loop *> NewLoops) {
     // If we did a non-trivial unswitch, we have added new (cloned) loops.
     if (!NewLoops.empty())
@@ -3664,6 +3660,16 @@ PreservedAnalyses SimpleLoopUnswitchPass::run(Loop &L, LoopAnalysisManager &AM,
             Context, L.getLoopID(), {"llvm.loop.unswitch.partial"},
             {DisableUnswitchMD});
         L.setLoopID(NewLoopID);
+      } else if (InjectedCondition) {
+        // Do the same for injection of invariant conditions.
+        auto &Context = L.getHeader()->getContext();
+        MDNode *DisableUnswitchMD = MDNode::get(
+            Context,
+            MDString::get(Context, "llvm.loop.unswitch.injection.disable"));
+        MDNode *NewLoopID = makePostTransformationMetadata(
+            Context, L.getLoopID(), {"llvm.loop.unswitch.injection"},
+            {DisableUnswitchMD});
+        L.setLoopID(NewLoopID);
       } else
         U.revisitCurrentLoop();
     } else
@@ -3756,6 +3762,7 @@ bool SimpleLoopUnswitchLegacyPass::runOnLoop(Loop *L, LPPassManager &LPM) {
   auto *SE = SEWP ? &SEWP->getSE() : nullptr;
 
   auto UnswitchCB = [&L, &LPM](bool CurrentLoopValid, bool PartiallyInvariant,
+                               bool InjectedCondition,
                                ArrayRef<Loop *> NewLoops) {
     // If we did a non-trivial unswitch, we have added new (cloned) loops.
     for (auto *NewL : NewLoops)
@@ -3766,9 +3773,9 @@ bool SimpleLoopUnswitchLegacyPass::runOnLoop(Loop *L, LPPassManager &LPM) {
     // but it is the best we can do in the old PM.
     if (CurrentLoopValid) {
       // If the current loop has been unswitched using a partially invariant
-      // condition, we should not re-add the current loop to avoid unswitching
-      // on the same condition again.
-      if (!PartiallyInvariant)
+      // condition or injected invariant condition, we should not re-add the
+      // current loop to avoid unswitching on the same condition again.
+      if (!PartiallyInvariant && !InjectedCondition)
         LPM.addLoop(*L);
     } else
       LPM.markLoopAsDeleted(*L);