Update sample profile propagation algorithm.

http://reviews.llvm.org/D13218

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@248968 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/llvm/ProfileData/SampleProf.h b/include/llvm/ProfileData/SampleProf.h
index 0f1f4ed9a92e51e327118e0b5cba845619a8dedb..ef5afc7eb3b0b39dfc03f5f08a93356a3c95b148 100644 (file)
--- a/include/llvm/ProfileData/SampleProf.h
+++ b/include/llvm/ProfileData/SampleProf.h
@@ -213,12 +213,6 @@ public:
   void addHeadSamples(unsigned Num) { TotalHeadSamples += Num; }
   void addBodySamples(int LineOffset, unsigned Discriminator, unsigned Num) {
     assert(LineOffset >= 0);
-    // When dealing with instruction weights, we use the value
-    // zero to indicate the absence of a sample. If we read an
-    // actual zero from the profile file, use the value 1 to
-    // avoid the confusion later on.
-    if (Num == 0)
-      Num = 1;
     BodySamples[LineLocation(LineOffset, Discriminator)].addSamples(Num);
   }
   void addCalledTargetSamples(int LineOffset, unsigned Discriminator,

diff --git a/lib/Transforms/IPO/SampleProfile.cpp b/lib/Transforms/IPO/SampleProfile.cpp
index 4d6ed522774e985f6b3b40a4b694e95b1299d11a..a4ce65fd4abd5bf1dbabd1583be1a3dfb25346a1 100644 (file)
--- a/lib/Transforms/IPO/SampleProfile.cpp
+++ b/lib/Transforms/IPO/SampleProfile.cpp
@@ -282,6 +282,7 @@ bool SampleProfileLoader::computeBlockWeights(Function &F) {
     ErrorOr<unsigned> Weight = getBlockWeight(&BB);
     if (Weight) {
       BlockWeights[&BB] = Weight.get();
+      VisitedBlocks.insert(&BB);
       Changed = true;
     }
     DEBUG(printBlockWeight(dbgs(), &BB));
@@ -431,12 +432,13 @@ bool SampleProfileLoader::inlineHotFunctions(Function &F) {
 void SampleProfileLoader::findEquivalencesFor(
     BasicBlock *BB1, SmallVector<BasicBlock *, 8> Descendants,
     DominatorTreeBase<BasicBlock> *DomTree) {
+  const BasicBlock *EC = EquivalenceClass[BB1];
+  unsigned Weight = BlockWeights[EC];
   for (const auto *BB2 : Descendants) {
     bool IsDomParent = DomTree->dominates(BB2, BB1);
     bool IsInSameLoop = LI->getLoopFor(BB1) == LI->getLoopFor(BB2);
-    if (BB1 != BB2 && VisitedBlocks.insert(BB2).second && IsDomParent &&
-        IsInSameLoop) {
-      EquivalenceClass[BB2] = BB1;
+    if (BB1 != BB2 && IsDomParent && IsInSameLoop) {
+      EquivalenceClass[BB2] = EC;
 
       // If BB2 is heavier than BB1, make BB2 have the same weight
       // as BB1.
@@ -446,11 +448,10 @@ void SampleProfileLoader::findEquivalencesFor(
       // during the propagation phase. Right now, we just want to
       // make sure that BB1 has the largest weight of all the
       // members of its equivalence set.
-      unsigned &BB1Weight = BlockWeights[BB1];
-      unsigned &BB2Weight = BlockWeights[BB2];
-      BB1Weight = std::max(BB1Weight, BB2Weight);
+      Weight = std::max(Weight, BlockWeights[BB2]);
     }
   }
+  BlockWeights[EC] = Weight;
 }
 
 /// \brief Find equivalence classes.
@@ -492,18 +493,6 @@ void SampleProfileLoader::findEquivalenceClasses(Function &F) {
     DT->getDescendants(BB1, DominatedBBs);
     findEquivalencesFor(BB1, DominatedBBs, PDT.get());
 
-    // Repeat the same logic for all the blocks post-dominated by BB1.
-    // We are looking for every basic block BB2 such that:
-    //
-    // 1- BB1 post-dominates BB2.
-    // 2- BB2 dominates BB1.
-    // 3- BB1 and BB2 are in the same loop nest.
-    //
-    // If all those conditions hold, BB2's equivalence class is BB1.
-    DominatedBBs.clear();
-    PDT->getDescendants(BB1, DominatedBBs);
-    findEquivalencesFor(BB1, DominatedBBs, DT.get());
-
     DEBUG(printBlockEquivalence(dbgs(), BB1));
   }
 
@@ -558,8 +547,9 @@ unsigned SampleProfileLoader::visitEdge(Edge E, unsigned *NumUnknownEdges,
 bool SampleProfileLoader::propagateThroughEdges(Function &F) {
   bool Changed = false;
   DEBUG(dbgs() << "\nPropagation through edges\n");
-  for (auto &BI : F) {
-    BasicBlock *BB = &BI;
+  for (const auto &BI : F) {
+    const BasicBlock *BB = &BI;
+    const BasicBlock *EC = EquivalenceClass[BB];
 
     // Visit all the predecessor and successor edges to determine
     // which ones have a weight assigned already. Note that it doesn't
@@ -611,7 +601,7 @@ bool SampleProfileLoader::propagateThroughEdges(Function &F) {
       // all edges will get a weight, or iteration will stop when
       // it reaches SampleProfileMaxPropagateIterations.
       if (NumUnknownEdges <= 1) {
-        unsigned &BBWeight = BlockWeights[BB];
+        unsigned &BBWeight = BlockWeights[EC];
         if (NumUnknownEdges == 0) {
           // If we already know the weight of all edges, the weight of the
           // basic block can be computed. It should be no larger than the sum
@@ -623,9 +613,9 @@ bool SampleProfileLoader::propagateThroughEdges(Function &F) {
                          << " known. Set weight for block: ";
                   printBlockWeight(dbgs(), BB););
           }
-          if (VisitedBlocks.insert(BB).second)
+          if (VisitedBlocks.insert(EC).second)
             Changed = true;
-        } else if (NumUnknownEdges == 1 && VisitedBlocks.count(BB)) {
+        } else if (NumUnknownEdges == 1 && VisitedBlocks.count(EC)) {
           // If there is a single unknown edge and the block has been
           // visited, then we can compute E's weight.
           if (BBWeight >= TotalWeight)
@@ -637,7 +627,7 @@ bool SampleProfileLoader::propagateThroughEdges(Function &F) {
           DEBUG(dbgs() << "Set weight for edge: ";
                 printEdgeWeight(dbgs(), UnknownEdge));
         }
-      } else if (SelfReferentialEdge.first && VisitedBlocks.count(BB)) {
+      } else if (SelfReferentialEdge.first && VisitedBlocks.count(EC)) {
         unsigned &BBWeight = BlockWeights[BB];
         // We have a self-referential edge and the weight of BB is known.
         if (BBWeight >= TotalWeight)

diff --git a/test/Transforms/SampleProfile/Inputs/branch.prof b/test/Transforms/SampleProfile/Inputs/branch.prof
index 5977a386c7ec0445572b96b111f65bf86c50e366..ac958e325c4005d6697fddfa103017ec32dddd25 100644 (file)
--- a/test/Transforms/SampleProfile/Inputs/branch.prof
+++ b/test/Transforms/SampleProfile/Inputs/branch.prof
@@ -1,7 +1,9 @@
 main:15680:0
- 0: 0
- 4: 0
- 7: 0
+ 1: 2500
+ 4: 1000
+ 5: 1000
+ 6: 800
+ 7: 500
  9: 10226
  10: 2243
  16: 0

diff --git a/test/Transforms/SampleProfile/Inputs/propagate.prof b/test/Transforms/SampleProfile/Inputs/propagate.prof
index 715321a46116940866cef4197d52711104264567..ee9c6d62dfd1c089857b853a2344bba2ef6201ee 100644 (file)
--- a/test/Transforms/SampleProfile/Inputs/propagate.prof
+++ b/test/Transforms/SampleProfile/Inputs/propagate.prof
@@ -4,7 +4,7 @@ _Z3fooiil:58139:0
  2: 0
  4: 1
  5: 10
- 6: 0
+ 6: 2
  7: 5
  8: 3
  9: 0

diff --git a/test/Transforms/SampleProfile/branch.ll b/test/Transforms/SampleProfile/branch.ll
index d367a8495bdad1ced9fe93f4b2df6394cf94aab1..9ee124b8d8c4709977cac9dbabdefe25a4684c6a 100644 (file)
--- a/test/Transforms/SampleProfile/branch.ll
+++ b/test/Transforms/SampleProfile/branch.ll
@@ -4,14 +4,14 @@
 ;
 ; #include <stdio.h>
 ; #include <stdlib.h>
-;
+
 ; int main(int argc, char *argv[]) {
 ;   if (argc < 2)
 ;     return 1;
 ;   double result;
 ;   int limit = atoi(argv[1]);
 ;   if (limit > 100) {
-;     double s = 23.041968;
+;     double s = 23.041968 * atoi(argv[2]);
 ;     for (int u = 0; u < limit; u++) {
 ;       double x = s;
 ;       s = x + 3.049 + (double)u;
@@ -19,7 +19,7 @@
 ;     }
 ;     result = s;
 ;   } else {
-;     result = 0;
+;     result = atoi(argv[2]);
 ;   }
 ;   printf("result is %lf\n", result);
 ;   return 0;
@@ -27,117 +27,213 @@
 
 @.str = private unnamed_addr constant [15 x i8] c"result is %lf\0A\00", align 1
 
-; Function Attrs: nounwind uwtable
-define i32 @main(i32 %argc, i8** nocapture readonly %argv) #0 {
+; Function Attrs: uwtable
+define i32 @main(i32 %argc, i8** %argv) #0 {
 ; CHECK: Printing analysis 'Branch Probability Analysis' for function 'main':
 
 entry:
-  tail call void @llvm.dbg.value(metadata i32 %argc, i64 0, metadata !13, metadata !DIExpression()), !dbg !27
-  tail call void @llvm.dbg.value(metadata i8** %argv, i64 0, metadata !14, metadata !DIExpression()), !dbg !27
-  %cmp = icmp slt i32 %argc, 2, !dbg !28
-  br i1 %cmp, label %return, label %if.end, !dbg !28
-; CHECK: edge entry -> return probability is 0x00000000 / 0x80000000 = 0.00%
-; CHECK: edge entry -> if.end probability is 0x80000000 / 0x80000000 = 100.00% [HOT edge]
+  %retval = alloca i32, align 4
+  %argc.addr = alloca i32, align 4
+  %argv.addr = alloca i8**, align 8
+  %result = alloca double, align 8
+  %limit = alloca i32, align 4
+  %s = alloca double, align 8
+  %u = alloca i32, align 4
+  %x = alloca double, align 8
+  store i32 0, i32* %retval, align 4
+  store i32 %argc, i32* %argc.addr, align 4
+  call void @llvm.dbg.declare(metadata i32* %argc.addr, metadata !16, metadata !17), !dbg !18
+  store i8** %argv, i8*** %argv.addr, align 8
+  call void @llvm.dbg.declare(metadata i8*** %argv.addr, metadata !19, metadata !17), !dbg !20
+  %0 = load i32, i32* %argc.addr, align 4, !dbg !21
+  %cmp = icmp slt i32 %0, 2, !dbg !23
+  br i1 %cmp, label %if.then, label %if.end, !dbg !24
+; CHECK:  edge entry -> if.then probability is 0x4ccccccd / 0x80000000 = 60.00%
+; CHECK:  edge entry -> if.end probability is 0x33333333 / 0x80000000 = 40.00%
+
+if.then:                                          ; preds = %entry
+  store i32 1, i32* %retval, align 4, !dbg !25
+  br label %return, !dbg !25
 
 if.end:                                           ; preds = %entry
-  %arrayidx = getelementptr inbounds i8*, i8** %argv, i64 1, !dbg !30
-  %0 = load i8*, i8** %arrayidx, align 8, !dbg !30, !tbaa !31
-  %call = tail call i32 @atoi(i8* %0) #4, !dbg !30
-  tail call void @llvm.dbg.value(metadata i32 %call, i64 0, metadata !17, metadata !DIExpression()), !dbg !30
-  %cmp1 = icmp sgt i32 %call, 100, !dbg !35
-  br i1 %cmp1, label %for.body, label %if.end6, !dbg !35
-; CHECK: edge if.end -> for.body probability is 0x00000000 / 0x80000000 = 0.00%
-; CHECK: edge if.end -> if.end6 probability is 0x80000000 / 0x80000000 = 100.00% [HOT edge]
-
-for.body:                                         ; preds = %if.end, %for.body
-  %u.016 = phi i32 [ %inc, %for.body ], [ 0, %if.end ]
-  %s.015 = phi double [ %sub, %for.body ], [ 0x40370ABE6A337A81, %if.end ]
-  %add = fadd double %s.015, 3.049000e+00, !dbg !36
-  %conv = sitofp i32 %u.016 to double, !dbg !36
-  %add4 = fadd double %add, %conv, !dbg !36
-  tail call void @llvm.dbg.value(metadata double %add4, i64 0, metadata !18, metadata !DIExpression()), !dbg !36
-  %div = fdiv double 3.940000e+00, %s.015, !dbg !37
-  %mul = fmul double %div, 3.200000e-01, !dbg !37
-  %add5 = fadd double %add4, %mul, !dbg !37
-  %sub = fsub double %add4, %add5, !dbg !37
-  tail call void @llvm.dbg.value(metadata double %sub, i64 0, metadata !18, metadata !DIExpression()), !dbg !37
-  %inc = add nsw i32 %u.016, 1, !dbg !38
-  tail call void @llvm.dbg.value(metadata i32 %inc, i64 0, metadata !21, metadata !DIExpression()), !dbg !38
-  %exitcond = icmp eq i32 %inc, %call, !dbg !38
-  br i1 %exitcond, label %if.end6, label %for.body, !dbg !38
-; CHECK: edge for.body -> if.end6 probability is 0x00000000 / 0x80000000 = 0.00%
-; CHECK: edge for.body -> for.body probability is 0x80000000 / 0x80000000 = 100.00% [HOT edge]
-
-if.end6:                                          ; preds = %for.body, %if.end
-  %result.0 = phi double [ 0.000000e+00, %if.end ], [ %sub, %for.body ]
-  %call7 = tail call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([15 x i8], [15 x i8]* @.str, i64 0, i64 0), double %result.0), !dbg !39
-  br label %return, !dbg !40
-; CHECK: edge if.end6 -> return probability is 0x80000000 / 0x80000000 = 100.00% [HOT edge]
-
-return:                                           ; preds = %entry, %if.end6
-  %retval.0 = phi i32 [ 0, %if.end6 ], [ 1, %entry ]
-  ret i32 %retval.0, !dbg !41
-}
+  call void @llvm.dbg.declare(metadata double* %result, metadata !26, metadata !17), !dbg !27
+  call void @llvm.dbg.declare(metadata i32* %limit, metadata !28, metadata !17), !dbg !29
+  %1 = load i8**, i8*** %argv.addr, align 8, !dbg !30
+  %arrayidx = getelementptr inbounds i8*, i8** %1, i64 1, !dbg !30
+  %2 = load i8*, i8** %arrayidx, align 8, !dbg !30
+  %call = call i32 @atoi(i8* %2) #4, !dbg !31
+  store i32 %call, i32* %limit, align 4, !dbg !29
+  %3 = load i32, i32* %limit, align 4, !dbg !32
+  %cmp1 = icmp sgt i32 %3, 100, !dbg !34
+  br i1 %cmp1, label %if.then.2, label %if.else, !dbg !35
+; CHECK: edge if.end -> if.then.2 probability is 0x66666666 / 0x80000000 = 80.00%
+; CHECK: edge if.end -> if.else probability is 0x1999999a / 0x80000000 = 20.00%
 
-; Function Attrs: nounwind readonly
-declare i32 @atoi(i8* nocapture) #1
+if.then.2:                                        ; preds = %if.end
+  call void @llvm.dbg.declare(metadata double* %s, metadata !36, metadata !17), !dbg !38
+  %4 = load i8**, i8*** %argv.addr, align 8, !dbg !39
+  %arrayidx3 = getelementptr inbounds i8*, i8** %4, i64 2, !dbg !39
+  %5 = load i8*, i8** %arrayidx3, align 8, !dbg !39
+  %call4 = call i32 @atoi(i8* %5) #4, !dbg !40
+  %conv = sitofp i32 %call4 to double, !dbg !40
+  %mul = fmul double 0x40370ABE6A337A81, %conv, !dbg !41
+  store double %mul, double* %s, align 8, !dbg !38
+  call void @llvm.dbg.declare(metadata i32* %u, metadata !42, metadata !17), !dbg !44
+  store i32 0, i32* %u, align 4, !dbg !44
+  br label %for.cond, !dbg !45
+
+for.cond:                                         ; preds = %for.inc, %if.then.2
+  %6 = load i32, i32* %u, align 4, !dbg !46
+  %7 = load i32, i32* %limit, align 4, !dbg !48
+  %cmp5 = icmp slt i32 %6, %7, !dbg !49
+  br i1 %cmp5, label %for.body, label %for.end, !dbg !50
+
+for.body:                                         ; preds = %for.cond
+  call void @llvm.dbg.declare(metadata double* %x, metadata !51, metadata !17), !dbg !53
+  %8 = load double, double* %s, align 8, !dbg !54
+  store double %8, double* %x, align 8, !dbg !53
+  %9 = load double, double* %x, align 8, !dbg !55
+  %add = fadd double %9, 3.049000e+00, !dbg !56
+  %10 = load i32, i32* %u, align 4, !dbg !57
+  %conv6 = sitofp i32 %10 to double, !dbg !57
+  %add7 = fadd double %add, %conv6, !dbg !58
+  store double %add7, double* %s, align 8, !dbg !59
+  %11 = load double, double* %s, align 8, !dbg !60
+  %12 = load double, double* %x, align 8, !dbg !61
+  %div = fdiv double 3.940000e+00, %12, !dbg !62
+  %mul8 = fmul double %div, 3.200000e-01, !dbg !63
+  %add9 = fadd double %11, %mul8, !dbg !64
+  %13 = load double, double* %s, align 8, !dbg !65
+  %sub = fsub double %13, %add9, !dbg !65
+  store double %sub, double* %s, align 8, !dbg !65
+  br label %for.inc, !dbg !66
+
+for.inc:                                          ; preds = %for.body
+  %14 = load i32, i32* %u, align 4, !dbg !67
+  %inc = add nsw i32 %14, 1, !dbg !67
+  store i32 %inc, i32* %u, align 4, !dbg !67
+  br label %for.cond, !dbg !68
 
-; Function Attrs: nounwind
-declare i32 @printf(i8* nocapture readonly, ...) #2
+for.end:                                          ; preds = %for.cond
+  %15 = load double, double* %s, align 8, !dbg !69
+  store double %15, double* %result, align 8, !dbg !70
+  br label %if.end.13, !dbg !71
+
+if.else:                                          ; preds = %if.end
+  %16 = load i8**, i8*** %argv.addr, align 8, !dbg !72
+  %arrayidx10 = getelementptr inbounds i8*, i8** %16, i64 2, !dbg !72
+  %17 = load i8*, i8** %arrayidx10, align 8, !dbg !72
+  %call11 = call i32 @atoi(i8* %17) #4, !dbg !74
+  %conv12 = sitofp i32 %call11 to double, !dbg !74
+  store double %conv12, double* %result, align 8, !dbg !75
+  br label %if.end.13
+
+if.end.13:                                        ; preds = %if.else, %for.end
+  %18 = load double, double* %result, align 8, !dbg !76
+  %call14 = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([15 x i8], [15 x i8]* @.str, i32 0, i32 0), double %18), !dbg !77
+  store i32 0, i32* %retval, align 4, !dbg !78
+  br label %return, !dbg !78
+
+return:                                           ; preds = %if.end.13, %if.then
+  %19 = load i32, i32* %retval, align 4, !dbg !79
+  ret i32 %19, !dbg !79
+}
 
 ; Function Attrs: nounwind readnone
-declare void @llvm.dbg.value(metadata, i64, metadata, metadata) #3
+declare void @llvm.dbg.declare(metadata, metadata, metadata) #1
+
+; Function Attrs: nounwind readonly
+declare i32 @atoi(i8*) #2
+
+declare i32 @printf(i8*, ...) #3
 
-attributes #0 = { nounwind uwtable "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
-attributes #1 = { nounwind readonly "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
-attributes #2 = { nounwind "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
-attributes #3 = { nounwind readnone }
+attributes #0 = { uwtable "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+sse,+sse2" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #1 = { nounwind readnone }
+attributes #2 = { nounwind readonly "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+sse,+sse2" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #3 = { "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+sse,+sse2" "unsafe-fp-math"="false" "use-soft-float"="false" }
 attributes #4 = { nounwind readonly }
 
 !llvm.dbg.cu = !{!0}
-!llvm.module.flags = !{!25, !42}
-!llvm.ident = !{!26}
+!llvm.module.flags = !{!13, !14}
+!llvm.ident = !{!15}
 
-!0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, producer: "clang version 3.4 (trunk 192896) (llvm/trunk 192895)", isOptimized: true, emissionKind: 0, file: !1, enums: !2, retainedTypes: !2, subprograms: !3, globals: !2, imports: !2)
-!1 = !DIFile(filename: "branch.cc", directory: ".")
+!0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !1, producer: "clang version 3.8.0 (trunk 248211) (llvm/trunk 248217)", isOptimized: false, runtimeVersion: 0, emissionKind: 1, enums: !2, retainedTypes: !3, subprograms: !5)
+!1 = !DIFile(filename: "test.cc", directory: "/ssd/llvm_commit")
 !2 = !{}
 !3 = !{!4}
-!4 = distinct !DISubprogram(name: "main", line: 4, isLocal: false, isDefinition: true, virtualIndex: 6, flags: DIFlagPrototyped, isOptimized: true, scopeLine: 4, file: !1, scope: !5, type: !6, function: i32 (i32, i8**)* @main, variables: !12)
-!5 = !DIFile(filename: "branch.cc", directory: ".")
-!6 = !DISubroutineType(types: !7)
-!7 = !{!8, !8, !9}
-!8 = !DIBasicType(tag: DW_TAG_base_type, name: "int", size: 32, align: 32, encoding: DW_ATE_signed)
-!9 = !DIDerivedType(tag: DW_TAG_pointer_type, size: 64, align: 64, baseType: !10)
-!10 = !DIDerivedType(tag: DW_TAG_pointer_type, size: 64, align: 64, baseType: !11)
-!11 = !DIBasicType(tag: DW_TAG_base_type, name: "char", size: 8, align: 8, encoding: DW_ATE_signed_char)
-!12 = !{!13, !14, !15, !17, !18, !21, !23}
-!13 = !DILocalVariable(name: "argc", line: 4, arg: 1, scope: !4, file: !5, type: !8)
-!14 = !DILocalVariable(name: "argv", line: 4, arg: 2, scope: !4, file: !5, type: !9)
-!15 = !DILocalVariable(name: "result", line: 7, scope: !4, file: !5, type: !16)
-!16 = !DIBasicType(tag: DW_TAG_base_type, name: "double", size: 64, align: 64, encoding: DW_ATE_float)
-!17 = !DILocalVariable(name: "limit", line: 8, scope: !4, file: !5, type: !8)
-!18 = !DILocalVariable(name: "s", line: 10, scope: !19, file: !5, type: !16)
-!19 = distinct !DILexicalBlock(line: 9, column: 0, file: !1, scope: !20)
-!20 = distinct !DILexicalBlock(line: 9, column: 0, file: !1, scope: !4)
-!21 = !DILocalVariable(name: "u", line: 11, scope: !22, file: !5, type: !8)
-!22 = distinct !DILexicalBlock(line: 11, column: 0, file: !1, scope: !19)
-!23 = !DILocalVariable(name: "x", line: 12, scope: !24, file: !5, type: !16)
-!24 = distinct !DILexicalBlock(line: 11, column: 0, file: !1, scope: !22)
-!25 = !{i32 2, !"Dwarf Version", i32 4}
-!26 = !{!"clang version 3.4 (trunk 192896) (llvm/trunk 192895)"}
-!27 = !DILocation(line: 4, scope: !4)
-!28 = !DILocation(line: 5, scope: !29)
-!29 = distinct !DILexicalBlock(line: 5, column: 0, file: !1, scope: !4)
-!30 = !DILocation(line: 8, scope: !4)
-!31 = !{!32, !32, i64 0}
-!32 = !{!"any pointer", !33, i64 0}
-!33 = !{!"omnipotent char", !34, i64 0}
-!34 = !{!"Simple C/C++ TBAA"}
-!35 = !DILocation(line: 9, scope: !20)
-!36 = !DILocation(line: 13, scope: !24)
-!37 = !DILocation(line: 14, scope: !24)
-!38 = !DILocation(line: 11, scope: !22)
-!39 = !DILocation(line: 20, scope: !4)
-!40 = !DILocation(line: 21, scope: !4)
-!41 = !DILocation(line: 22, scope: !4)
-!42 = !{i32 1, !"Debug Info Version", i32 3}
+!4 = !DIBasicType(name: "double", size: 64, align: 64, encoding: DW_ATE_float)
+!5 = !{!6}
+!6 = distinct !DISubprogram(name: "main", scope: !1, file: !1, line: 4, type: !7, isLocal: false, isDefinition: true, scopeLine: 4, flags: DIFlagPrototyped, isOptimized: false, function: i32 (i32, i8**)* @main, variables: !2)
+!7 = !DISubroutineType(types: !8)
+!8 = !{!9, !9, !10}
+!9 = !DIBasicType(name: "int", size: 32, align: 32, encoding: DW_ATE_signed)
+!10 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !11, size: 64, align: 64)
+!11 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !12, size: 64, align: 64)
+!12 = !DIBasicType(name: "char", size: 8, align: 8, encoding: DW_ATE_signed_char)
+!13 = !{i32 2, !"Dwarf Version", i32 4}
+!14 = !{i32 2, !"Debug Info Version", i32 3}
+!15 = !{!"clang version 3.8.0 (trunk 248211) (llvm/trunk 248217)"}
+!16 = !DILocalVariable(name: "argc", arg: 1, scope: !6, file: !1, line: 4, type: !9)
+!17 = !DIExpression()
+!18 = !DILocation(line: 4, column: 15, scope: !6)
+!19 = !DILocalVariable(name: "argv", arg: 2, scope: !6, file: !1, line: 4, type: !10)
+!20 = !DILocation(line: 4, column: 27, scope: !6)
+!21 = !DILocation(line: 5, column: 8, scope: !22)
+!22 = distinct !DILexicalBlock(scope: !6, file: !1, line: 5, column: 8)
+!23 = !DILocation(line: 5, column: 13, scope: !22)
+!24 = !DILocation(line: 5, column: 8, scope: !6)
+!25 = !DILocation(line: 6, column: 6, scope: !22)
+!26 = !DILocalVariable(name: "result", scope: !6, file: !1, line: 7, type: !4)
+!27 = !DILocation(line: 7, column: 11, scope: !6)
+!28 = !DILocalVariable(name: "limit", scope: !6, file: !1, line: 8, type: !9)
+!29 = !DILocation(line: 8, column: 8, scope: !6)
+!30 = !DILocation(line: 8, column: 21, scope: !6)
+!31 = !DILocation(line: 8, column: 16, scope: !6)
+!32 = !DILocation(line: 9, column: 8, scope: !33)
+!33 = distinct !DILexicalBlock(scope: !6, file: !1, line: 9, column: 8)
+!34 = !DILocation(line: 9, column: 14, scope: !33)
+!35 = !DILocation(line: 9, column: 8, scope: !6)
+!36 = !DILocalVariable(name: "s", scope: !37, file: !1, line: 10, type: !4)
+!37 = distinct !DILexicalBlock(scope: !33, file: !1, line: 9, column: 21)
+!38 = !DILocation(line: 10, column: 13, scope: !37)
+!39 = !DILocation(line: 10, column: 34, scope: !37)
+!40 = !DILocation(line: 10, column: 29, scope: !37)
+!41 = !DILocation(line: 10, column: 27, scope: !37)
+!42 = !DILocalVariable(name: "u", scope: !43, file: !1, line: 11, type: !9)
+!43 = distinct !DILexicalBlock(scope: !37, file: !1, line: 11, column: 6)
+!44 = !DILocation(line: 11, column: 15, scope: !43)
+!45 = !DILocation(line: 11, column: 11, scope: !43)
+!46 = !DILocation(line: 11, column: 22, scope: !47)
+!47 = distinct !DILexicalBlock(scope: !43, file: !1, line: 11, column: 6)
+!48 = !DILocation(line: 11, column: 26, scope: !47)
+!49 = !DILocation(line: 11, column: 24, scope: !47)
+!50 = !DILocation(line: 11, column: 6, scope: !43)
+!51 = !DILocalVariable(name: "x", scope: !52, file: !1, line: 12, type: !4)
+!52 = distinct !DILexicalBlock(scope: !47, file: !1, line: 11, column: 38)
+!53 = !DILocation(line: 12, column: 15, scope: !52)
+!54 = !DILocation(line: 12, column: 19, scope: !52)
+!55 = !DILocation(line: 13, column: 12, scope: !52)
+!56 = !DILocation(line: 13, column: 14, scope: !52)
+!57 = !DILocation(line: 13, column: 32, scope: !52)
+!58 = !DILocation(line: 13, column: 22, scope: !52)
+!59 = !DILocation(line: 13, column: 10, scope: !52)
+!60 = !DILocation(line: 14, column: 13, scope: !52)
+!61 = !DILocation(line: 14, column: 24, scope: !52)
+!62 = !DILocation(line: 14, column: 22, scope: !52)
+!63 = !DILocation(line: 14, column: 26, scope: !52)
+!64 = !DILocation(line: 14, column: 15, scope: !52)
+!65 = !DILocation(line: 14, column: 10, scope: !52)
+!66 = !DILocation(line: 15, column: 6, scope: !52)
+!67 = !DILocation(line: 11, column: 34, scope: !47)
+!68 = !DILocation(line: 11, column: 6, scope: !47)
+!69 = !DILocation(line: 16, column: 15, scope: !37)
+!70 = !DILocation(line: 16, column: 13, scope: !37)
+!71 = !DILocation(line: 17, column: 4, scope: !37)
+!72 = !DILocation(line: 18, column: 20, scope: !73)
+!73 = distinct !DILexicalBlock(scope: !33, file: !1, line: 17, column: 11)
+!74 = !DILocation(line: 18, column: 15, scope: !73)
+!75 = !DILocation(line: 18, column: 13, scope: !73)
+!76 = !DILocation(line: 20, column: 30, scope: !6)
+!77 = !DILocation(line: 20, column: 4, scope: !6)
+!78 = !DILocation(line: 21, column: 4, scope: !6)
+!79 = !DILocation(line: 22, column: 2, scope: !6)

diff --git a/test/Transforms/SampleProfile/propagate.ll b/test/Transforms/SampleProfile/propagate.ll
index ca58d17302d85afb718ba4b91516bd8c5a6557eb..3945519f6011a4de542c4c680c25b74f7ddc6cbe 100644 (file)
--- a/test/Transforms/SampleProfile/propagate.ll
+++ b/test/Transforms/SampleProfile/propagate.ll
@@ -73,8 +73,8 @@ for.cond:                                         ; preds = %for.inc16, %if.else
   %5 = load i64, i64* %N.addr, align 8, !dbg !15
   %cmp1 = icmp slt i64 %4, %5, !dbg !15
   br i1 %cmp1, label %for.body, label %for.end18, !dbg !15
-; CHECK: edge for.cond -> for.body probability is 0x80000000 / 0x80000000 = 100.00% [HOT edge]
-; CHECK: edge for.cond -> for.end18 probability is 0x00000000 / 0x80000000 = 0.00%
+; CHECK: edge for.cond -> for.body probability is 0x745d1746 / 0x80000000 = 90.91% [HOT edge]
+; CHECK: edge for.cond -> for.end18 probability is 0x0ba2e8ba / 0x80000000 = 9.09%
 
 for.body:                                         ; preds = %for.cond
   %6 = load i64, i64* %i, align 8, !dbg !18
@@ -119,8 +119,8 @@ for.cond8:                                        ; preds = %for.inc, %if.else7
   %14 = load i64, i64* %i, align 8, !dbg !28
   %cmp10 = icmp slt i64 %conv9, %14, !dbg !28
   br i1 %cmp10, label %for.body11, label %for.end, !dbg !28
-; CHECK: edge for.cond8 -> for.body11 probability is 0x80000000 / 0x80000000 = 100.00% [HOT edge]
-; CHECK: edge for.cond8 -> for.end probability is 0x00000000 / 0x80000000 = 0.00%
+; CHECK: edge for.cond8 -> for.body11 probability is 0x5bfc7472 / 0x80000000 = 71.86%
+; CHECK: edge for.cond8 -> for.end probability is 0x24038b8e / 0x80000000 = 28.14%
 
 for.body11:                                       ; preds = %for.cond8
   %15 = load i32, i32* %j, align 4, !dbg !31