[BPI] Refactor post domination calculation and simple fix for ColdCall

[skatkov]

Summary

Collection of PostDominatedByUnreachable and PostDominatedByColdCall have been split
out of heuristics itself. Update of the data happens now for each basic block (before update
for PostDominatedByColdCall might be skipped if unreachable or matadata heuristic
handled this basic block).

This separation allows re-ordering of heuristics without loosing the post-domination information.

[chandlerc]

lib/Analysis/BranchProbabilityInfo.cpp

150–156 ↗

(On Diff #94175)

You can rewrite this without the loop:

if (llvm::all_of(successors(BB), [&](BasicBlock *SuccBB) {
      return PostDominatedByColdCall.count(SuccBB);
    })) {
  PostDominatedByColdCall.insert(BB);
  return;
}

161–166 ↗

(On Diff #94175)

Use a range based for loop over the instructions, and directly insert and return here?

170–174 ↗

(On Diff #94175)

Do this first (before walking successors)? Then you can just insert and return rather than needing a bool.

[skatkov]

The original idea was to separate the checks and action. However I'm ok with that as well.

[chandlerc]

LGTM as well.

llvm/trunk/include/llvm/Analysis/BranchProbabilityInfo.h

private:
   const Function *LastF;
 
   /// \brief Track the set of blocks directly succeeded by a returning block.
   SmallPtrSet<const BasicBlock *, 16> PostDominatedByUnreachable;
 
   /// \brief Track the set of blocks that always lead to a cold call.
   SmallPtrSet<const BasicBlock *, 16> PostDominatedByColdCall;
 
+  void updatePostDominatedByUnreachable(const BasicBlock *BB);
+  void updatePostDominatedByColdCall(const BasicBlock *BB);
   bool calcUnreachableHeuristics(const BasicBlock *BB);
   bool calcMetadataWeights(const BasicBlock *BB);
   bool calcColdCallHeuristics(const BasicBlock *BB);
   bool calcPointerHeuristics(const BasicBlock *BB);
   bool calcLoopBranchHeuristics(const BasicBlock *BB, const LoopInfo &LI);
   bool calcZeroHeuristics(const BasicBlock *BB);
   bool calcFloatingPointHeuristics(const BasicBlock *BB);
   bool calcInvokeHeuristics(const BasicBlock *BB);

llvm/trunk/lib/Analysis/BranchProbabilityInfo.cpp

 static const uint32_t IH_TAKEN_WEIGHT = 1024 * 1024 - 1;
 
 /// \brief Invoke-terminating normal branch not-taken weight.
 ///
 /// This is the weight for branching to the unwind destination of an invoke
 /// instruction. This is essentially never taken.
 static const uint32_t IH_NONTAKEN_WEIGHT = 1;
 
-/// \brief Calculate edge weights for successors lead to unreachable.
-///
-/// Predict that a successor which leads necessarily to an
-/// unreachable-terminated block as extremely unlikely.
-bool BranchProbabilityInfo::calcUnreachableHeuristics(const BasicBlock *BB) {
+/// \brief Add \p BB to PostDominatedByUnreachable set if applicable.
+void
+BranchProbabilityInfo::updatePostDominatedByUnreachable(const BasicBlock *BB) {
   const TerminatorInst *TI = BB->getTerminator();
   if (TI->getNumSuccessors() == 0) {
     if (isa<UnreachableInst>(TI) ||
         // If this block is terminated by a call to
         // @llvm.experimental.deoptimize then treat it like an unreachable since
         // the @llvm.experimental.deoptimize call is expected to practically
         // never execute.
         BB->getTerminatingDeoptimizeCall())
       PostDominatedByUnreachable.insert(BB);
-    return false;
+    return;
+  }
+
+  // If the terminator is an InvokeInst, check only the normal destination block
+  // as the unwind edge of InvokeInst is also very unlikely taken.
+  if (auto *II = dyn_cast<InvokeInst>(TI)) {
+    if (PostDominatedByUnreachable.count(II->getNormalDest()))
+      PostDominatedByUnreachable.insert(BB);
+    return;
+  }
+
+  for (auto *I : successors(BB))
+    // If any of successor is not post dominated then BB is also not.
+    if (!PostDominatedByUnreachable.count(I))
+      return;
+
+  PostDominatedByUnreachable.insert(BB);
+}
+
+/// \brief Add \p BB to PostDominatedByColdCall set if applicable.
+void
+BranchProbabilityInfo::updatePostDominatedByColdCall(const BasicBlock *BB) {
+  assert(!PostDominatedByColdCall.count(BB));
+  const TerminatorInst *TI = BB->getTerminator();
+  if (TI->getNumSuccessors() == 0)
+    return;
+
+  // If all of successor are post dominated then BB is also done.
+  if (llvm::all_of(successors(BB), [&](const BasicBlock *SuccBB) {
+        return PostDominatedByColdCall.count(SuccBB);
+      })) {
+    PostDominatedByColdCall.insert(BB);
+    return;
+  }
+
+  // If the terminator is an InvokeInst, check only the normal destination
+  // block as the unwind edge of InvokeInst is also very unlikely taken.
+  if (auto *II = dyn_cast<InvokeInst>(TI))
+    if (PostDominatedByColdCall.count(II->getNormalDest())) {
+      PostDominatedByColdCall.insert(BB);
+      return;
+    }
+
+  // Otherwise, if the block itself contains a cold function, add it to the
+  // set of blocks post-dominated by a cold call.
+  for (auto &I : *BB)
+    if (const CallInst *CI = dyn_cast<CallInst>(&I))
+      if (CI->hasFnAttr(Attribute::Cold)) {
+        PostDominatedByColdCall.insert(BB);
+        return;
       }
+}
+
+/// \brief Calculate edge weights for successors lead to unreachable.
+///
+/// Predict that a successor which leads necessarily to an
+/// unreachable-terminated block as extremely unlikely.
+bool BranchProbabilityInfo::calcUnreachableHeuristics(const BasicBlock *BB) {
+  const TerminatorInst *TI = BB->getTerminator();
+  if (TI->getNumSuccessors() == 0)
+    return false;
 
   SmallVector<unsigned, 4> UnreachableEdges;
   SmallVector<unsigned, 4> ReachableEdges;
 
-  for (succ_const_iterator I = succ_begin(BB), E = succ_end(BB); I != E; ++I) {
+  for (succ_const_iterator I = succ_begin(BB), E = succ_end(BB); I != E; ++I)
     if (PostDominatedByUnreachable.count(*I))
       UnreachableEdges.push_back(I.getSuccessorIndex());
     else
       ReachableEdges.push_back(I.getSuccessorIndex());
-  }
-
-  // If all successors are in the set of blocks post-dominated by unreachable,
-  // this block is too.
-  if (UnreachableEdges.size() == TI->getNumSuccessors())
-    PostDominatedByUnreachable.insert(BB);
 
   // Skip probabilities if this block has a single successor or if all were
   // reachable.
   if (TI->getNumSuccessors() == 1 || UnreachableEdges.empty())
     return false;
 
-  // If the terminator is an InvokeInst, check only the normal destination block
-  // as the unwind edge of InvokeInst is also very unlikely taken.
-  if (auto *II = dyn_cast<InvokeInst>(TI))
-    if (PostDominatedByUnreachable.count(II->getNormalDest())) {
-      PostDominatedByUnreachable.insert(BB);
-      // Return false here so that edge weights for InvokeInst could be decided
-      // in calcInvokeHeuristics().
-      return false;
-    }
+  if (isa<InvokeInst>(TI))
 
   if (ReachableEdges.empty()) {
     BranchProbability Prob(1, UnreachableEdges.size());
     for (unsigned SuccIdx : UnreachableEdges)
       setEdgeProbability(BB, SuccIdx, Prob);
     return true;
   }
 
bool BranchProbabilityInfo::calcColdCallHeuristics(const BasicBlock *BB) {
   SmallVector<unsigned, 4> ColdEdges;
   SmallVector<unsigned, 4> NormalEdges;
   for (succ_const_iterator I = succ_begin(BB), E = succ_end(BB); I != E; ++I)
     if (PostDominatedByColdCall.count(*I))
       ColdEdges.push_back(I.getSuccessorIndex());
     else
       NormalEdges.push_back(I.getSuccessorIndex());
 
-  // If all successors are in the set of blocks post-dominated by cold calls,
-  // this block is in the set post-dominated by cold calls.
-  if (ColdEdges.size() == TI->getNumSuccessors())
-    PostDominatedByColdCall.insert(BB);
-  else {
-    // Otherwise, if the block itself contains a cold function, add it to the
-    // set of blocks postdominated by a cold call.
-    assert(!PostDominatedByColdCall.count(BB));
-    for (BasicBlock::const_iterator I = BB->begin(), E = BB->end(); I != E; ++I)
-      if (const CallInst *CI = dyn_cast<CallInst>(I))
-        if (CI->hasFnAttr(Attribute::Cold)) {
-          PostDominatedByColdCall.insert(BB);
-          break;
-        }
-  }
-
-  if (auto *II = dyn_cast<InvokeInst>(TI)) {
-    // If the terminator is an InvokeInst, consider only the normal destination
-    // block.
-    if (PostDominatedByColdCall.count(II->getNormalDest()))
-      PostDominatedByColdCall.insert(BB);
-    // Return false here so that edge weights for InvokeInst could be decided
-    // in calcInvokeHeuristics().
+  if (isa<InvokeInst>(TI))
     return false;
-  }
 
   // Skip probabilities if this block has a single successor.
   if (TI->getNumSuccessors() == 1 || ColdEdges.empty())
     return false;
 
   if (NormalEdges.empty()) {
     BranchProbability Prob(1, ColdEdges.size());
     for (unsigned SuccIdx : ColdEdges)
void BranchProbabilityInfo::calculate(const Function &F, const LoopInfo &LI) {
   LastF = &F; // Store the last function we ran on for printing.
   assert(PostDominatedByUnreachable.empty());
   assert(PostDominatedByColdCall.empty());
 
   // Walk the basic blocks in post-order so that we can build up state about
   // the successors of a block iteratively.
   for (auto BB : post_order(&F.getEntryBlock())) {
     DEBUG(dbgs() << "Computing probabilities for " << BB->getName() << "\n");
+    updatePostDominatedByUnreachable(BB);
+    updatePostDominatedByColdCall(BB);
     if (calcUnreachableHeuristics(BB))
       continue;
     if (calcMetadataWeights(BB))
       continue;
     if (calcColdCallHeuristics(BB))
       continue;
     if (calcLoopBranchHeuristics(BB, LI))
       continue;

llvm/trunk/test/Analysis/BranchProbabilityInfo/basic.ll

 
 exit:
   %result = phi i32 [ %a, %then ], [ %b, %else ]
   ret i32 %result
 }
 
 declare i32 @regular_function(i32 %i)
 
+define i32 @test_cold_call_sites_with_prof(i32 %a, i32 %b, i1 %flag, i1 %flag2) {
+; CHECK: Printing analysis {{.*}} for function 'test_cold_call_sites_with_prof'
+entry:
+  br i1 %flag, label %then, label %else
+; CHECK: edge entry -> then probability is 0x07878788 / 0x80000000 = 5.88%
+; CHECK: edge entry -> else probability is 0x78787878 / 0x80000000 = 94.12% [HOT edge]
+
+then:
+  br i1 %flag2, label %then2, label %else2, !prof !3
+; CHECK: edge then -> then2 probability is 0x7ebb907a / 0x80000000 = 99.01% [HOT edge]
+; CHECK: edge then -> else2 probability is 0x01446f86 / 0x80000000 = 0.99%
+
+then2:
+  br label %join
+; CHECK: edge then2 -> join probability is 0x80000000 / 0x80000000 = 100.00% [HOT edge]
+
+else2:
+  br label %join
+; CHECK: edge else2 -> join probability is 0x80000000 / 0x80000000 = 100.00% [HOT edge]
+
+join:
+  %joinresult = phi i32 [ %a, %then2 ], [ %b, %else2 ]
+  call void @coldfunc()
+  br label %exit
+; CHECK: edge join -> exit probability is 0x80000000 / 0x80000000 = 100.00% [HOT edge]
+
+else:
+  br label %exit
+; CHECK: edge else -> exit probability is 0x80000000 / 0x80000000 = 100.00% [HOT edge]
+
+exit:
+  %result = phi i32 [ %joinresult, %join ], [ %b, %else ]
+  ret i32 %result
+}
+
+!3 = !{!"branch_weights", i32 100, i32 1}
+
 define i32 @test_cold_call_sites(i32* %a) {
 ; Test that edges to blocks post-dominated by cold call sites
 ; are marked as not expected to be taken.
 ; TODO(dnovillo) The calls to regular_function should not be merged, but
 ; they are currently being merged. Convert this into a code generation test
 ; after that is fixed.
 
 ; CHECK: Printing analysis {{.*}} for function 'test_cold_call_sites'