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
@@ -29,6 +29,7 @@
 #include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/ADT/SmallSet.h"
 #include "llvm/ADT/SmallVector.h"
+#include "llvm/ADT/Statistic.h" 
 #include "llvm/ADT/StringMap.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/ADT/Twine.h"
@@ -92,6 +93,11 @@
 using ProfileCount = Function::ProfileCount;
 #define DEBUG_TYPE "sample-profile"
 
+STATISTIC(NumCSInlined,
+          "Number of functions inlined with context sensitive profile");
+STATISTIC(NumCSNotInlined,
+          "Number of functions not inlined with context sensitive profile");
+
 // Command line option to specify the file to read samples from. This is
 // mainly used for debugging.
 static cl::opt<std::string> SampleProfileFile(
@@ -870,14 +876,14 @@
       getInlineCost(cast<CallBase>(*I), Params, GetTTI(*CalledFunction), GetAC,
                     None, nullptr, nullptr);
   if (Cost.isNever()) {
-    ORE->emit(OptimizationRemark(DEBUG_TYPE, "Not inline", DLoc, BB)
+    ORE->emit(OptimizationRemark("sample-profile-inline", "NotInline", DLoc, BB)
               << "incompatible inlining");
     return false;
   }
   InlineFunctionInfo IFI(nullptr, &GetAC);
   if (InlineFunction(CS, IFI)) {
     // The call to InlineFunction erases I, so we can't pass it here.
-    ORE->emit(OptimizationRemark(DEBUG_TYPE, "HotInline", DLoc, BB)
+    ORE->emit(OptimizationRemark("sample-profile-inline", "HotInline", DLoc, BB)
               << "inlined hot callee '" << ore::NV("Callee", CalledFunction)
               << "' into '" << ore::NV("Caller", BB->getParent()) << "'");
     return true;
@@ -932,6 +938,18 @@
       if (Hot) {
         CIS.insert(CIS.begin(), Candidates.begin(), Candidates.end());
       }
+      else {
+        for (auto I : Candidates) {
+          Function *CalledFunction = CallSite(I).getCalledFunction();
+          if (CalledFunction) {
+            ORE->emit(OptimizationRemark("sample-profile-inline", "NotInline",
+                                         I->getDebugLoc(), I->getParent())
+                      << "previous inline not repeated '"
+                      << ore::NV("Callee", CalledFunction) << "' into '"
+                      << ore::NV("Caller", &F) << "'");
+          }
+        }
+      }
     }
     for (auto I : CIS) {
       Function *CalledFunction = CallSite(I).getCalledFunction();
@@ -976,6 +994,7 @@
                 inlineCallInstruction(DI)) {
               localNotInlinedCallSites.erase(I);
               LocalChanged = true;
+              ++NumCSInlined;
             }
           } else {
             LLVM_DEBUG(dbgs()
@@ -988,6 +1007,7 @@
         if (inlineCallInstruction(I)) {
           localNotInlinedCallSites.erase(I);
           LocalChanged = true;
+          ++NumCSInlined;
         }
       } else if (IsThinLTOPreLink) {
         findCalleeFunctionSamples(*I)->findInlinedFunctions(
@@ -1011,6 +1031,7 @@
     auto pair =
         notInlinedCallInfo.try_emplace(Callee, NotInlinedProfileInfo{0});
     pair.first->second.entryCount += FS->getEntrySamples();
+    ++NumCSNotInlined;
   }
   return Changed;
 }
diff --git a/llvm/test/Transforms/SampleProfile/inline-stats.ll b/llvm/test/Transforms/SampleProfile/inline-stats.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Transforms/SampleProfile/inline-stats.ll
@@ -0,0 +1,110 @@
+; REQUIRES: asserts
+; RUN: opt < %s -sample-profile -sample-profile-file=%S/Inputs/inline.prof -stats -S 2>&1 | FileCheck %s
+
+; Original C++ test case
+;
+; #include <stdio.h>
+;
+; int sum(int x, int y) {
+;   return x + y;
+; }
+;
+; int main() {
+;   int s, i = 0;
+;   while (i++ < 20000 * 20000)
+;     if (i != 100) s = sum(i, s); else s = 30;
+;   printf("sum is %d\n", s);
+;   return 0;
+; }
+;
+@.str = private unnamed_addr constant [11 x i8] c"sum is %d\0A\00", align 1
+
+; 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
+  ret i32 %add, !dbg !11
+}
+
+; Function Attrs: uwtable
+define i32 @main() !dbg !7 {
+entry:
+  %retval = alloca i32, align 4
+  %s = alloca i32, align 4
+  %i = alloca i32, align 4
+  store i32 0, i32* %retval
+  store i32 0, i32* %i, align 4, !dbg !12
+  br label %while.cond, !dbg !13
+
+while.cond:                                       ; preds = %if.end, %entry
+  %0 = load i32, i32* %i, align 4, !dbg !14
+  %inc = add nsw i32 %0, 1, !dbg !14
+  store i32 %inc, i32* %i, align 4, !dbg !14
+  %cmp = icmp slt i32 %0, 400000000, !dbg !14
+  br i1 %cmp, label %while.body, label %while.end, !dbg !14
+
+while.body:                                       ; preds = %while.cond
+  %1 = load i32, i32* %i, align 4, !dbg !16
+  %cmp1 = icmp ne i32 %1, 100, !dbg !16
+  br i1 %cmp1, label %if.then, label %if.else, !dbg !16
+
+
+if.then:                                          ; preds = %while.body
+  %2 = load i32, i32* %i, align 4, !dbg !18
+  %3 = load i32, i32* %s, align 4, !dbg !18
+  %call = call i32 @_Z3sumii(i32 %2, i32 %3), !dbg !18
+  store i32 %call, i32* %s, align 4, !dbg !18
+  br label %if.end, !dbg !18
+
+if.else:                                          ; preds = %while.body
+  store i32 30, i32* %s, align 4, !dbg !20
+  br label %if.end
+
+if.end:                                           ; preds = %if.else, %if.then
+  br label %while.cond, !dbg !22
+
+while.end:                                        ; preds = %while.cond
+  %4 = load i32, i32* %s, align 4, !dbg !24
+  %call2 = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([11 x i8], [11 x i8]* @.str, i32 0, i32 0), i32 %4), !dbg !24
+  ret i32 0, !dbg !25
+}
+
+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)
+
+; CHECK: 1 sample-profile - Number of functions inlined with context sensitive profile
\ No newline at end of file