diff --git a/llvm/include/llvm/ProfileData/SampleProf.h b/llvm/include/llvm/ProfileData/SampleProf.h
--- a/llvm/include/llvm/ProfileData/SampleProf.h
+++ b/llvm/include/llvm/ProfileData/SampleProf.h
@@ -387,14 +387,17 @@
     if (FS != iter->second.end())
       return &FS->second;
     // If we cannot find exact match of the callee name, return the FS with
-    // the max total count.
+    // the max total count. Only do this when CalleeName is not provided, 
+    // i.e., only for indirect calls.
     uint64_t MaxTotalSamples = 0;
     const FunctionSamples *R = nullptr;
-    for (const auto &NameFS : iter->second)
-      if (NameFS.second.getTotalSamples() >= MaxTotalSamples) {
-        MaxTotalSamples = NameFS.second.getTotalSamples();
-        R = &NameFS.second;
-      }
+    if (CalleeName.empty()) {
+      for (const auto &NameFS : iter->second)
+        if (NameFS.second.getTotalSamples() >= MaxTotalSamples) {
+          MaxTotalSamples = NameFS.second.getTotalSamples();
+          R = &NameFS.second;
+        }
+    }
     return R;
   }
 
diff --git a/llvm/include/llvm/ProfileData/SampleProfReader.h b/llvm/include/llvm/ProfileData/SampleProfReader.h
--- a/llvm/include/llvm/ProfileData/SampleProfReader.h
+++ b/llvm/include/llvm/ProfileData/SampleProfReader.h
@@ -358,6 +358,15 @@
     return getSamplesFor(CanonName);
   }
 
+  /// Return the samples collected for function \p F, create empty
+  /// FunctionSamples if it doesn't exist.
+  FunctionSamples *getOrCreateSamplesFor(const Function &F) {
+    std::string FGUID;
+    StringRef CanonName = FunctionSamples::getCanonicalFnName(F);
+    CanonName = getRepInFormat(CanonName, getFormat(), FGUID);
+    return &Profiles[CanonName];
+  }
+
   /// Return the samples collected for function \p F.
   virtual FunctionSamples *getSamplesFor(StringRef Fname) {
     if (Remapper) {
diff --git a/llvm/lib/Transforms/IPO/SampleProfile.cpp b/llvm/lib/Transforms/IPO/SampleProfile.cpp
--- a/llvm/lib/Transforms/IPO/SampleProfile.cpp
+++ b/llvm/lib/Transforms/IPO/SampleProfile.cpp
@@ -137,6 +137,11 @@
     cl::desc("For symbols in profile symbol list, regard their profiles to "
              "be accurate. It may be overriden by profile-sample-accurate. "));
 
+static cl::opt<bool> ProfileMergeInlinee(
+    "sample-profile-merge-inlinee", cl::Hidden, cl::init(false),
+    cl::desc("Merge past inlinee's profile to outline version if sample "
+             "profile loader decided not to inline a call site."));
+
 namespace {
 
 using BlockWeightMap = DenseMap<const BasicBlock *, uint64_t>;
@@ -1008,9 +1013,26 @@
     if (!Callee || Callee->isDeclaration())
       continue;
     const FunctionSamples *FS = Pair.getSecond();
-    auto pair =
-        notInlinedCallInfo.try_emplace(Callee, NotInlinedProfileInfo{0});
-    pair.first->second.entryCount += FS->getEntrySamples();
+    if (FS->getTotalSamples() == 0 && FS->getEntrySamples() == 0) {
+      continue;
+    }
+
+    if (ProfileMergeInlinee) {
+      // Use entry samples as head samples during the merge, as inlinees
+      // don't have head samples.
+      assert(FS->getHeadSamples() == 0 && "Expect 0 head sample for inlinee");
+      const_cast<FunctionSamples *>(FS)->addHeadSamples(FS->getEntrySamples());
+
+      // Note that we have to do the merge right after processing function.
+      // This allows OutlineFS's profile to be used for annotation during
+      // top-down processing of functions' annotation.
+      FunctionSamples *OutlineFS = Reader->getOrCreateSamplesFor(*Callee);
+      OutlineFS->merge(*FS);
+    } else {
+      auto pair =
+          notInlinedCallInfo.try_emplace(Callee, NotInlinedProfileInfo{0});
+      pair.first->second.entryCount += FS->getEntrySamples();
+    }
   }
   return Changed;
 }
diff --git a/llvm/test/CodeGen/X86/insert-prefetch-inline.afdo b/llvm/test/CodeGen/X86/insert-prefetch-inline.afdo
--- a/llvm/test/CodeGen/X86/insert-prefetch-inline.afdo
+++ b/llvm/test/CodeGen/X86/insert-prefetch-inline.afdo
@@ -1,4 +1,4 @@
 caller:0:0
- 2:sum:0
+ 2: sum:0
   3: 0 __prefetch_nta_0:23456
   3.1: 0 __prefetch_nta_0:8764 __prefetch_nta_1:64
\ No newline at end of file
diff --git a/llvm/test/Transforms/SampleProfile/Inputs/einline.prof b/llvm/test/Transforms/SampleProfile/Inputs/einline.prof
--- a/llvm/test/Transforms/SampleProfile/Inputs/einline.prof
+++ b/llvm/test/Transforms/SampleProfile/Inputs/einline.prof
@@ -1,7 +1,7 @@
 _Z3foov:200:100
- 1: _Z3barv:0
+ 1: _ZL3barv:0
  2: no_inline:100
- 3: _Z3barv:100
+ 3: _ZL3barv:100
 recursive:200:100
  1: recursive:100
  2: recursive:100
diff --git a/llvm/test/Transforms/SampleProfile/Inputs/inline-callee-update.prof b/llvm/test/Transforms/SampleProfile/Inputs/inline-callee-update.prof
--- a/llvm/test/Transforms/SampleProfile/Inputs/inline-callee-update.prof
+++ b/llvm/test/Transforms/SampleProfile/Inputs/inline-callee-update.prof
@@ -4,7 +4,7 @@
  1: direct_leaf_func:35000
   11: 3000
 test_cgscc_inline:63067:0
- 1: sample_loader_inlinee:1
+ 1: cgscc_inlinee:1
 cgscc_inlinee:3000:0
  1: direct_leaf_func:35000
   11: 3000
\ No newline at end of file
diff --git a/llvm/test/Transforms/SampleProfile/Inputs/inline-mergeprof.prof b/llvm/test/Transforms/SampleProfile/Inputs/inline-mergeprof.prof
new file mode 100644
--- /dev/null
+++ b/llvm/test/Transforms/SampleProfile/Inputs/inline-mergeprof.prof
@@ -0,0 +1,13 @@
+main:225715:0
+ 2.1: 5553
+ 3: 5391
+ 3.1: _Z3sumii:46
+  1: 23
+  2: _Z3subii:2
+   1: 2
+  3: 21
+
+_Z3sumii:11:22
+ 1: 11
+ 2: 10 _Z3subii:10
+ 3: 1
\ No newline at end of file
diff --git a/llvm/test/Transforms/SampleProfile/inline-mergeprof.ll b/llvm/test/Transforms/SampleProfile/inline-mergeprof.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Transforms/SampleProfile/inline-mergeprof.ll
@@ -0,0 +1,109 @@
+; Test we lose details of not inlined profile without '-sample-profile-merge-inlinee'
+; RUN: opt < %s -sample-profile -sample-profile-file=%S/Inputs/inline-mergeprof.prof -S | FileCheck -check-prefix=SCALE %s
+; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/inline-mergeprof.prof -S | FileCheck -check-prefix=SCALE %s
+
+; Test we properly merge not inlined profile properly with '-sample-profile-merge-inlinee'
+; RUN: opt < %s -sample-profile -sample-profile-file=%S/Inputs/inline-mergeprof.prof -sample-profile-merge-inlinee -S | FileCheck -check-prefix=MERGE %s
+; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/inline-mergeprof.prof -sample-profile-merge-inlinee -S | FileCheck -check-prefix=MERGE  %s
+
+@.str = private unnamed_addr constant [11 x i8] c"sum is %d\0A\00", align 1
+
+; Function Attrs: uwtable
+define i32 @main() !dbg !7 {
+entry:
+  %retval = alloca i32, align 4
+  %s = alloca i32, align 4
+  %i = alloca i32, align 4
+  %0 = load i32, i32* %i, align 4, !dbg !18
+  %1 = load i32, i32* %s, align 4, !dbg !18
+  %call = call i32 @_Z3sumii(i32 %0, i32 %1), !dbg !18
+; SCALE: call i32 @_Z3sumii
+; MERGE: call i32 @_Z3sumii
+  store i32 %call, i32* %s, align 4, !dbg !18
+  ret i32 0, !dbg !25
+}
+
+; Function Attrs: nounwind uwtable
+define i32 @_Z3sumii(i32 %x, i32 %y) !dbg !4 {
+entry:
+  %x.addr = alloca i32, align 4
+  %y.addr = alloca i32, align 4
+  store i32 %x, i32* %x.addr, align 4
+  store i32 %y, i32* %y.addr, align 4
+  %0 = load i32, i32* %x.addr, align 4, !dbg !11
+  %1 = load i32, i32* %y.addr, align 4, !dbg !11
+  %add = add nsw i32 %0, %1, !dbg !11
+  %2 = load i32, i32* %x.addr, align 4, !dbg !11
+  %3 = load i32, i32* %y.addr, align 4, !dbg !11
+  %cmp1 = icmp ne i32 %3, 100, !dbg !11
+  br i1 %cmp1, label %if.then, label %if.else, !dbg !11
+if.then:
+  %call = call i32 @_Z3subii(i32 %2, i32 %3), !dbg !29
+  ret i32 %add, !dbg !29
+if.else:
+  ret i32 %add, !dbg !30
+}
+
+; Function Attrs: nounwind uwtable
+define i32 @_Z3subii(i32 %x, i32 %y) !dbg !26 {
+entry:
+  %x.addr = alloca i32, align 4
+  %y.addr = alloca i32, align 4
+  store i32 %x, i32* %x.addr, align 4
+  store i32 %y, i32* %y.addr, align 4
+  %0 = load i32, i32* %x.addr, align 4, !dbg !27
+  %1 = load i32, i32* %y.addr, align 4, !dbg !27
+  %add = sub nsw i32 %0, %1, !dbg !27
+  ret i32 %add, !dbg !28
+}
+
+declare i32 @printf(i8*, ...) #2
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!8, !9}
+!llvm.ident = !{!10}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, producer: "clang version 3.5 ", isOptimized: false, emissionKind: NoDebug, file: !1, enums: !2, retainedTypes: !2, globals: !2, imports: !2)
+!1 = !DIFile(filename: "calls.cc", directory: ".")
+!2 = !{}
+!4 = distinct !DISubprogram(name: "sum", line: 3, isLocal: false, isDefinition: true, virtualIndex: 6, flags: DIFlagPrototyped, isOptimized: false, unit: !0, scopeLine: 3, file: !1, scope: !5, type: !6, retainedNodes: !2)
+!5 = !DIFile(filename: "calls.cc", directory: ".")
+!6 = !DISubroutineType(types: !2)
+!7 = distinct !DISubprogram(name: "main", line: 7, isLocal: false, isDefinition: true, virtualIndex: 6, flags: DIFlagPrototyped, isOptimized: false, unit: !0, scopeLine: 7, file: !1, scope: !5, type: !6, retainedNodes: !2)
+!8 = !{i32 2, !"Dwarf Version", i32 4}
+!9 = !{i32 1, !"Debug Info Version", i32 3}
+!10 = !{!"clang version 3.5 "}
+!11 = !DILocation(line: 4, scope: !4)
+!12 = !DILocation(line: 8, scope: !7)
+!13 = !DILocation(line: 9, scope: !7)
+!14 = !DILocation(line: 9, scope: !15)
+!15 = !DILexicalBlockFile(discriminator: 2, file: !1, scope: !7)
+!16 = !DILocation(line: 10, scope: !17)
+!17 = distinct !DILexicalBlock(line: 10, column: 0, file: !1, scope: !7)
+!18 = !DILocation(line: 10, scope: !19)
+!19 = !DILexicalBlockFile(discriminator: 2, file: !1, scope: !17)
+!20 = !DILocation(line: 10, scope: !21)
+!21 = !DILexicalBlockFile(discriminator: 4, file: !1, scope: !17)
+!22 = !DILocation(line: 10, scope: !23)
+!23 = !DILexicalBlockFile(discriminator: 6, file: !1, scope: !17)
+!24 = !DILocation(line: 11, scope: !7)
+!25 = !DILocation(line: 12, scope: !7)
+!26 = distinct !DISubprogram(name: "sub", line: 20, isLocal: false, isDefinition: true, virtualIndex: 6, flags: DIFlagPrototyped, isOptimized: false, unit: !0, scopeLine: 20, file: !1, scope: !5, type: !6, retainedNodes: !2)
+!27 = !DILocation(line: 20, scope: !26)
+!28 = !DILocation(line: 21, scope: !26)
+!29 = !DILocation(line: 5, scope: !4)
+!30 = !DILocation(line: 6, scope: !4)
+
+; SCALE: name: "sum"
+; SCALE-NEXT: {!"function_entry_count", i64 46}
+; SCALE: !{!"branch_weights", i32 11, i32 2}
+; SCALE: !{!"branch_weights", i64 20}
+; SCALE: name: "sub"
+; SCALE-NEXT: {!"function_entry_count", i64 -1}
+
+; MERGE: name: "sum"
+; MERGE-NEXT: {!"function_entry_count", i64 46}
+; MERGE: !{!"branch_weights", i32 11, i32 23}
+; MERGE: !{!"branch_weights", i32 10}
+; MERGE: name: "sub"
+; MERGE-NEXT: {!"function_entry_count", i64 3}
\ No newline at end of file