[SimplifyCFG] Don't speculatively execute BB[s] if they are predictably not taken

Same as D106650, but for `FoldTwoEntryPHINode()`

Reviewed By: spatel

Differential Revision: https://reviews.llvm.org/D106717

Author: LebedevRI

llvm/lib/Transforms/Utils/SimplifyCFG.cpp

@@ -2736,7 +2736,33 @@ static bool FoldTwoEntryPHINode(PHINode *PN, const TargetTransformInfo &TTI,
       PN->blocks(), std::back_inserter(IfBlocks), [](BasicBlock *IfBlock) {
         return cast<BranchInst>(IfBlock->getTerminator())->isUnconditional();
       });
-  assert(!IfBlocks.empty() && "Will have at least one block to speculate.");
+  assert((IfBlocks.size() == 1 || IfBlocks.size() == 2) &&
+         "Will have either one or two blocks to speculate.");
+
+  // If the branch is non-unpredictable, see if we either predictably jump to
+  // the merge bb (if we have only a single 'then' block), or if we predictably
+  // jump to one specific 'then' block (if we have two of them).
+  // It isn't beneficial to speculatively execute the code
+  // from the block that we know is predictably not entered.
+  if (!DomBI->getMetadata(LLVMContext::MD_unpredictable)) {
+    uint64_t TWeight, FWeight;
+    if (DomBI->extractProfMetadata(TWeight, FWeight) &&
+        (TWeight + FWeight) != 0) {
+      BranchProbability BITrueProb =
+          BranchProbability::getBranchProbability(TWeight, TWeight + FWeight);
+      BranchProbability Likely = TTI.getPredictableBranchThreshold();
+      BranchProbability BIFalseProb = BITrueProb.getCompl();
+      if (IfBlocks.size() == 1) {
+        BranchProbability BIBBProb =
+            DomBI->getSuccessor(0) == BB ? BITrueProb : BIFalseProb;
+        if (BIBBProb >= Likely)
+          return false;
+      } else {
+        if (BITrueProb >= Likely || BIFalseProb >= Likely)
+          return false;
+      }
+    }
+  }
 
   // Don't try to fold an unreachable block. For example, the phi node itself
   // can't be the candidate if-condition for a select that we want to form.

llvm/test/Transforms/PGOProfile/chr.ll

@@ -2013,7 +2013,8 @@ define i64 @test_chr_22(i1 %i, i64* %j, i64 %v0) !prof !14 {
 ; CHECK-NEXT:    [[C1:%.*]] = icmp slt i64 [[V2]], 100
 ; CHECK-NEXT:    br i1 [[C1]], label [[BB0_SPLIT:%.*]], label [[BB0_SPLIT_NONCHR:%.*]], !prof [[PROF15]]
 ; CHECK:       common.ret:
-; CHECK-NEXT:    ret i64 99
+; CHECK-NEXT:    [[COMMON_RET_OP:%.*]] = phi i64 [ 99, [[BB0_SPLIT]] ], [ 99, [[BB0_SPLIT_NONCHR]] ]
+; CHECK-NEXT:    ret i64 [[COMMON_RET_OP]]
 ; CHECK:       bb0.split:
 ; CHECK-NEXT:    [[V299:%.*]] = mul i64 [[V2]], 7860086430977039991
 ; CHECK-NEXT:    store i64 [[V299]], i64* [[J:%.*]], align 4

llvm/test/Transforms/SimplifyCFG/fold-two-entry-phi-node-with-one-block-profmd.ll

@@ -59,8 +59,12 @@ define i32 @predictably_nontaken(i32 %a, i32 %b, i32 %c, i32 %d) {
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    call void @sideeffect0()
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i32 [[A:%.*]], [[B:%.*]]
+; CHECK-NEXT:    br i1 [[CMP]], label [[END:%.*]], label [[COND_TRUE:%.*]], !prof [[PROF0]]
+; CHECK:       cond.true:
 ; CHECK-NEXT:    [[V0:%.*]] = add i32 [[C:%.*]], [[D:%.*]]
-; CHECK-NEXT:    [[RES:%.*]] = select i1 [[CMP]], i32 0, i32 [[V0]], !prof [[PROF0]]
+; CHECK-NEXT:    br label [[END]]
+; CHECK:       end:
+; CHECK-NEXT:    [[RES:%.*]] = phi i32 [ [[V0]], [[COND_TRUE]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    call void @sideeffect1()
 ; CHECK-NEXT:    ret i32 [[RES]]
 ;

llvm/test/Transforms/SimplifyCFG/fold-two-entry-phi-node-with-two-blocks-profmd.ll

@@ -39,9 +39,15 @@ define i32 @predictably_taken(i32 %a, i32 %b, i32 %c, i32 %d) {
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    call void @sideeffect0()
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i32 [[A:%.*]], [[B:%.*]]
+; CHECK-NEXT:    br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]], !prof [[PROF0:![0-9]+]]
+; CHECK:       cond.true:
 ; CHECK-NEXT:    [[V0:%.*]] = add i32 [[C:%.*]], [[D:%.*]]
+; CHECK-NEXT:    br label [[END:%.*]]
+; CHECK:       cond.false:
 ; CHECK-NEXT:    [[V1:%.*]] = sub i32 [[C]], [[D]]
-; CHECK-NEXT:    [[RES:%.*]] = select i1 [[CMP]], i32 [[V0]], i32 [[V1]], !prof [[PROF0:![0-9]+]]
+; CHECK-NEXT:    br label [[END]]
+; CHECK:       end:
+; CHECK-NEXT:    [[RES:%.*]] = phi i32 [ [[V0]], [[COND_TRUE]] ], [ [[V1]], [[COND_FALSE]] ]
 ; CHECK-NEXT:    call void @sideeffect1()
 ; CHECK-NEXT:    ret i32 [[RES]]
 ;
@@ -99,9 +105,15 @@ define i32 @predictably_nontaken(i32 %a, i32 %b, i32 %c, i32 %d) {
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    call void @sideeffect0()
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i32 [[A:%.*]], [[B:%.*]]
+; CHECK-NEXT:    br i1 [[CMP]], label [[COND_FALSE:%.*]], label [[COND_TRUE:%.*]], !prof [[PROF0]]
+; CHECK:       cond.true:
 ; CHECK-NEXT:    [[V0:%.*]] = add i32 [[C:%.*]], [[D:%.*]]
+; CHECK-NEXT:    br label [[END:%.*]]
+; CHECK:       cond.false:
 ; CHECK-NEXT:    [[V1:%.*]] = sub i32 [[C]], [[D]]
-; CHECK-NEXT:    [[RES:%.*]] = select i1 [[CMP]], i32 [[V1]], i32 [[V0]], !prof [[PROF0]]
+; CHECK-NEXT:    br label [[END]]
+; CHECK:       end:
+; CHECK-NEXT:    [[RES:%.*]] = phi i32 [ [[V0]], [[COND_TRUE]] ], [ [[V1]], [[COND_FALSE]] ]
 ; CHECK-NEXT:    call void @sideeffect1()
 ; CHECK-NEXT:    ret i32 [[RES]]
 ;