[SimlifyCFG] Prevent passes from destroying canonical loop structure, especially for nested loops

When eliminating or merging almost empty basic blocks, the existence of non-trivial PHI nodes
is currently used to recognize potential loops of which the block is the header and keep the block.
However, the current algorithm fails if the loops' exit condition is evaluated only with volatile
values hence no PHI nodes in the header. Especially when such a loop is an outer loop of a nested
loop, the loop is collapsed into a single loop which prevent later optimizations from being 
applied (e.g., transforming nested loops into simplified forms and loop vectorization).

The patch augments the existing PHI node-based check by adding a pre-test if the BB actually 
belongs to a set of loop headers and not eliminating it if yes. 

llvm-svn: 264596

1 files changed, 20 insertions, 5 deletions

diff --git a/llvm/lib/Transforms/Utils/SimplifyCFG.cpp b/llvm/lib/Transforms/Utils/SimplifyCFG.cpp
index 75d42617a6a..197ac510949 100644
--- a/llvm/lib/Transforms/Utils/SimplifyCFG.cpp
+++ b/llvm/lib/Transforms/Utils/SimplifyCFG.cpp
@@ -135,6 +135,7 @@ class SimplifyCFGOpt {
   const DataLayout &DL;
   unsigned BonusInstThreshold;
   AssumptionCache *AC;
+  SmallPtrSetImpl<BasicBlock *> *LoopHeaders;
   Value *isValueEqualityComparison(TerminatorInst *TI);
   BasicBlock *GetValueEqualityComparisonCases(TerminatorInst *TI,
                                std::vector<ValueEqualityComparisonCase> &Cases);
@@ -157,8 +158,10 @@ class SimplifyCFGOpt {
 
 public:
   SimplifyCFGOpt(const TargetTransformInfo &TTI, const DataLayout &DL,
-                 unsigned BonusInstThreshold, AssumptionCache *AC)
-      : TTI(TTI), DL(DL), BonusInstThreshold(BonusInstThreshold), AC(AC) {}
+                 unsigned BonusInstThreshold, AssumptionCache *AC,
+                 SmallPtrSetImpl<BasicBlock *> *LoopHeaders)
+      : TTI(TTI), DL(DL), BonusInstThreshold(BonusInstThreshold), AC(AC),
+        LoopHeaders(LoopHeaders) {}
   bool run(BasicBlock *BB);
 };
 }
@@ -3362,6 +3365,7 @@ bool SimplifyCFGOpt::SimplifySingleResume(ResumeInst *RI) {
 
   // The landingpad is now unreachable.  Zap it.
   BB->eraseFromParent();
+  if (LoopHeaders) LoopHeaders->erase(BB);
   return true;
 }
 
@@ -3480,6 +3484,7 @@ static bool removeEmptyCleanup(CleanupReturnInst *RI) {
 
   // The cleanup pad is now unreachable.  Zap it.
   BB->eraseFromParent();
+  if (LoopHeaders) LoopHeaders->erase(BB);
   return true;
 }
 
@@ -3560,9 +3565,11 @@ bool SimplifyCFGOpt::SimplifyReturn(ReturnInst *RI, IRBuilder<> &Builder) {
     }
 
     // If we eliminated all predecessors of the block, delete the block now.
-    if (pred_empty(BB))
+    if (pred_empty(BB)) {
       // We know there are no successors, so just nuke the block.
       BB->eraseFromParent();
+      if (LoopHeaders) LoopHeaders->erase(BB);
+    }
 
     return true;
   }
@@ -3719,6 +3726,7 @@ bool SimplifyCFGOpt::SimplifyUnreachable(UnreachableInst *UI) {
       BB != &BB->getParent()->getEntryBlock()) {
     // We know there are no successors, so just nuke the block.
     BB->eraseFromParent();
+    if (LoopHeaders) LoopHeaders->erase(BB);
     return true;
   }
 
@@ -5062,8 +5070,14 @@ bool SimplifyCFGOpt::SimplifyUncondBranch(BranchInst *BI, IRBuilder<> &Builder){
     return true;
 
   // If the Terminator is the only non-phi instruction, simplify the block.
+  // if LoopHeader is provided, check if the block is a loop header
+  // (This is for early invocations before loop simplify and vectorization
+  // to keep canonical loop forms for nested loops.
+  // These blocks can be eliminated when the pass is invoked later 
+  // in the back-end.)
   BasicBlock::iterator I = BB->getFirstNonPHIOrDbg()->getIterator();
   if (I->isTerminator() && BB != &BB->getParent()->getEntryBlock() &&
+      (!LoopHeaders || (LoopHeaders && !LoopHeaders->count(BB))) &&
       TryToSimplifyUncondBranchFromEmptyBlock(BB))
     return true;
 
@@ -5343,7 +5357,8 @@ bool SimplifyCFGOpt::run(BasicBlock *BB) {
 /// of the CFG.  It returns true if a modification was made.
 ///
 bool llvm::SimplifyCFG(BasicBlock *BB, const TargetTransformInfo &TTI,
-                       unsigned BonusInstThreshold, AssumptionCache *AC) {
+                       unsigned BonusInstThreshold, AssumptionCache *AC,
+                       SmallPtrSetImpl<BasicBlock *> *LoopHeaders) {
   return SimplifyCFGOpt(TTI, BB->getModule()->getDataLayout(),
-                        BonusInstThreshold, AC).run(BB);
+                        BonusInstThreshold, AC, LoopHeaders).run(BB);
 }