[llvm] edcf3ef - [IRSim] Treat Branch OperVals different from regular operands to ensure correct ordering

[Andrew Litteken via llvm-commits]

Author: Andrew Litteken
Date: 2023-03-19T18:43:53-05:00
New Revision: edcf3efd914409b2413c227fb333427585ea4957

URL: https://github.com/llvm/llvm-project/commit/edcf3efd914409b2413c227fb333427585ea4957
DIFF: https://github.com/llvm/llvm-project/commit/edcf3efd914409b2413c227fb333427585ea4957.diff

LOG: [IRSim] Treat Branch OperVals different from regular operands to ensure correct ordering

Branch operands are different from regular instructions. They can have a mix of boolean values and branch instructions. This makes sure that branches are treated as more of a special case and makes sure that the successor blocks are always in the same order, and that they do not include the conditional argument.

Reviewer: paquette
Differential Revision: https://reviews.llvm.org/D139337

Added: 
    

Modified: 
    llvm/include/llvm/Analysis/IRSimilarityIdentifier.h
    llvm/lib/Analysis/IRSimilarityIdentifier.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/include/llvm/Analysis/IRSimilarityIdentifier.h b/llvm/include/llvm/Analysis/IRSimilarityIdentifier.h
index 91af95b3f002f..bbc2385fb4bbc 100644
--- a/llvm/include/llvm/Analysis/IRSimilarityIdentifier.h
+++ b/llvm/include/llvm/Analysis/IRSimilarityIdentifier.h
@@ -226,6 +226,11 @@ struct IRInstructionData
   void
   setPHIPredecessors(DenseMap<BasicBlock *, unsigned> &BasicBlockToInteger);
 
+  /// Get the BasicBlock based operands for PHINodes and BranchInsts.
+  ///
+  /// \returns A list of relevant BasicBlocks.
+  ArrayRef<Value *> getBlockOperVals();
+
   /// Hashes \p Value based on its opcode, types, and operand types.
   /// Two IRInstructionData instances produce the same hash when they perform
   /// the same operation.

diff  --git a/llvm/lib/Analysis/IRSimilarityIdentifier.cpp b/llvm/lib/Analysis/IRSimilarityIdentifier.cpp
index a56539717ee08..930985a955456 100644
--- a/llvm/lib/Analysis/IRSimilarityIdentifier.cpp
+++ b/llvm/lib/Analysis/IRSimilarityIdentifier.cpp
@@ -14,6 +14,7 @@
 
 #include "llvm/Analysis/IRSimilarityIdentifier.h"
 #include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/SetOperations.h"
 #include "llvm/IR/Intrinsics.h"
 #include "llvm/IR/Operator.h"
 #include "llvm/IR/User.h"
@@ -97,7 +98,8 @@ void IRInstructionData::setBranchSuccessors(
 
   int CurrentBlockNumber = static_cast<int>(BBNumIt->second);
 
-  for (BasicBlock *Successor : BI->successors()) {
+  for (Value *V : getBlockOperVals()) {
+    BasicBlock *Successor = cast<BasicBlock>(V);
     BBNumIt = BasicBlockToInteger.find(Successor);
     assert(BBNumIt != BasicBlockToInteger.end() &&
            "Could not find number for BasicBlock!");
@@ -108,6 +110,25 @@ void IRInstructionData::setBranchSuccessors(
   }
 }
 
+ArrayRef<Value *> IRInstructionData::getBlockOperVals() {
+  assert((isa<BranchInst>(Inst) ||
+         isa<PHINode>(Inst)) && "Instruction must be branch or PHINode");
+  
+  if (BranchInst *BI = dyn_cast<BranchInst>(Inst))
+    return ArrayRef<Value *>(
+      std::next(OperVals.begin(), BI->isConditional() ? 1 : 0),
+      OperVals.end()
+    );
+
+  if (PHINode *PN = dyn_cast<PHINode>(Inst))
+    return ArrayRef<Value *>(
+      std::next(OperVals.begin(), PN->getNumIncomingValues()),
+      OperVals.end()
+    );
+
+  return ArrayRef<Value *>();
+}
+
 void IRInstructionData::setCalleeName(bool MatchByName) {
   CallInst *CI = dyn_cast<CallInst>(Inst);
   assert(CI && "Instruction must be call");
@@ -159,7 +180,6 @@ void IRInstructionData::setPHIPredecessors(
 
     int Relative = OtherBlockNumber - CurrentBlockNumber;
     RelativeBlockLocations.push_back(Relative);
-    RelativeBlockLocations.push_back(Relative);
   }
 }
 
@@ -701,8 +721,8 @@ bool IRSimilarityCandidate::compareCommutativeOperandMapping(
 bool IRSimilarityCandidate::checkRelativeLocations(RelativeLocMapping A,
                                                    RelativeLocMapping B) {
   // Get the basic blocks the label refers to.
-  BasicBlock *ABB = static_cast<BasicBlock *>(A.OperVal);
-  BasicBlock *BBB = static_cast<BasicBlock *>(B.OperVal);
+  BasicBlock *ABB = cast<BasicBlock>(A.OperVal);
+  BasicBlock *BBB = cast<BasicBlock>(B.OperVal);
 
   // Get the basic blocks contained in each region.
   DenseSet<BasicBlock *> BasicBlockA;
@@ -715,7 +735,7 @@ bool IRSimilarityCandidate::checkRelativeLocations(RelativeLocMapping A,
   bool BContained = BasicBlockB.contains(BBB);
 
   // Both blocks need to be contained in the region, or both need to be outside
-  // the reigon.
+  // the region.
   if (AContained != BContained)
     return false;
   
@@ -826,12 +846,22 @@ bool IRSimilarityCandidate::compareStructure(
 
     SmallVector<int, 4> &RelBlockLocsA = ItA->RelativeBlockLocations;
     SmallVector<int, 4> &RelBlockLocsB = ItB->RelativeBlockLocations;
+    ArrayRef<Value *> ABL = ItA->getBlockOperVals();
+    ArrayRef<Value *> BBL = ItB->getBlockOperVals();
+
+    // Check to make sure that the number of operands, and branching locations
+    // between BranchInsts is the same.
     if (RelBlockLocsA.size() != RelBlockLocsB.size() &&
-        OperValsA.size() != OperValsB.size())
+        ABL.size() != BBL.size())
       return false;
 
+    assert(RelBlockLocsA.size() == ABL.size() &&
+           "Block information vectors not the same size.");
+    assert(RelBlockLocsB.size() == BBL.size() &&
+           "Block information vectors not the same size.");
+
     ZippedRelativeLocationsT ZippedRelativeLocations =
-        zip(RelBlockLocsA, RelBlockLocsB, OperValsA, OperValsB);
+        zip(RelBlockLocsA, RelBlockLocsB, ABL, BBL);
     if (any_of(ZippedRelativeLocations,
                [&A, &B](std::tuple<int, int, Value *, Value *> R) {
                  return !checkRelativeLocations(