Index: include/clang/Driver/CC1Options.td
===================================================================
--- include/clang/Driver/CC1Options.td
+++ include/clang/Driver/CC1Options.td
@@ -507,6 +507,9 @@
 def arcmt_migrate : Flag<["-"], "arcmt-migrate">,
   HelpText<"Apply modifications and produces temporary files that conform to ARC">;
 
+def opt_record_file : Separate<["-"], "opt-record-file">,
+  HelpText<"File name to use for YAML optimization record output">;
+
 def print_stats : Flag<["-"], "print-stats">,
   HelpText<"Print performance metrics and statistics">;
 def stats_file : Joined<["-"], "stats-file=">,
Index: include/clang/Driver/Options.td
===================================================================
--- include/clang/Driver/Options.td
+++ include/clang/Driver/Options.td
@@ -1189,6 +1189,15 @@
                                    Group<f_Group>;
 def foperator_arrow_depth_EQ : Joined<["-"], "foperator-arrow-depth=">,
                                Group<f_Group>;
+
+def fsave_optimization_record : Flag<["-"], "fsave-optimization-record">,
+  Group<f_Group>, HelpText<"Generate a YAML optimization record file">;
+def fno_save_optimization_record : Flag<["-"], "fno-save-optimization-record">,
+  Group<f_Group>, Flags<[NoArgumentUnused]>;
+def fsave_optimization_record_EQ : Joined<["-"], "fsave-optimization-record=">,
+  Group<f_Group>,
+  HelpText<"Generate a YAML optimization record file with the specified name">;
+
 def ftest_coverage : Flag<["-"], "ftest-coverage">, Group<f_Group>;
 def fvectorize : Flag<["-"], "fvectorize">, Group<f_Group>,
   HelpText<"Enable the loop vectorization passes">;
Index: include/clang/Frontend/CodeGenOptions.h
===================================================================
--- include/clang/Frontend/CodeGenOptions.h
+++ include/clang/Frontend/CodeGenOptions.h
@@ -181,6 +181,10 @@
   /// object file.
   std::vector<std::string> CudaGpuBinaryFileNames;
 
+  /// The name of the file to which the backend should save YAML optimization
+  /// records.
+  std::string OptRecordFile;
+
   /// Regular expression to select optimizations for which we should enable
   /// optimization remarks. Transformation passes whose name matches this
   /// expression (and support this feature), will emit a diagnostic
Index: lib/CodeGen/CodeGenAction.cpp
===================================================================
--- lib/CodeGen/CodeGenAction.cpp
+++ lib/CodeGen/CodeGenAction.cpp
@@ -33,6 +33,8 @@
 #include "llvm/Support/MemoryBuffer.h"
 #include "llvm/Support/SourceMgr.h"
 #include "llvm/Support/Timer.h"
+#include "llvm/Support/ToolOutputFile.h"
+#include "llvm/Support/YAMLTraits.h"
 #include <memory>
 using namespace clang;
 using namespace llvm;
@@ -181,6 +183,24 @@
       Ctx.setDiagnosticHandler(DiagnosticHandler, this);
       Ctx.setDiagnosticHotnessRequested(CodeGenOpts.DiagnosticsWithHotness);
 
+      std::unique_ptr<llvm::tool_output_file> OptRecordFile;
+      if (!CodeGenOpts.OptRecordFile.empty()) {
+        std::error_code EC;
+        OptRecordFile =
+          llvm::make_unique<llvm::tool_output_file>(CodeGenOpts.OptRecordFile,
+                                                    EC, sys::fs::F_None);
+        if (EC) {
+          Diags.Report(diag::err_cannot_open_file) <<
+            CodeGenOpts.OptRecordFile << EC.message();
+          return;
+        }
+
+        Ctx.setDiagnosticsOutputFile(new yaml::Output(OptRecordFile->os()));
+
+        if (CodeGenOpts.getProfileUse() != CodeGenOptions::ProfileNone)
+          Ctx.setDiagnosticHotnessRequested(true);
+      }
+
       // Link LinkModule into this module if present, preserving its validity.
       for (auto &I : LinkModules) {
         unsigned LinkFlags = I.first;
@@ -198,6 +218,9 @@
       Ctx.setInlineAsmDiagnosticHandler(OldHandler, OldContext);
 
       Ctx.setDiagnosticHandler(OldDiagnosticHandler, OldDiagnosticContext);
+
+      if (OptRecordFile)
+        OptRecordFile->keep();
     }
 
     void HandleTagDeclDefinition(TagDecl *D) override {
Index: lib/Driver/Tools.cpp
===================================================================
--- lib/Driver/Tools.cpp
+++ lib/Driver/Tools.cpp
@@ -6068,6 +6068,40 @@
     CmdArgs.push_back("-fno-math-builtin");
   }
 
+  if (Args.hasFlag(options::OPT_fsave_optimization_record,
+                   options::OPT_fsave_optimization_record_EQ,
+                   options::OPT_fno_save_optimization_record, false)) {
+    CmdArgs.push_back("-opt-record-file");
+
+    const Arg *A = Args.getLastArg(options::OPT_fsave_optimization_record_EQ);
+    if (A) {
+      CmdArgs.push_back(A->getValue());
+    } else {
+      SmallString<128> F;
+      if (Output.isFilename() && (Args.hasArg(options::OPT_c) ||
+                                  Args.hasArg(options::OPT_S))) {
+        F = Output.getFilename();
+      } else {
+        // Use the compilation directory.
+        F = llvm::sys::path::stem(Input.getBaseInput());
+
+        // If we're compiling for an offload architecture (i.e. a CUDA device),
+        // we need to make the file name for the device compilation different
+        // from the host compilation.
+        if (!JA.isDeviceOffloading(Action::OFK_None) &&
+            !JA.isDeviceOffloading(Action::OFK_Host)) {
+          llvm::sys::path::replace_extension(F, "");
+          F += JA.getOffloadingFileNamePrefix(Triple.normalize());
+          F += "-";
+          F += JA.getOffloadingArch();
+        }
+      }
+
+      llvm::sys::path::replace_extension(F, "opt.yaml");
+      CmdArgs.push_back(Args.MakeArgString(F));
+    }
+  }
+
 // Default to -fno-builtin-str{cat,cpy} on Darwin for ARM.
 //
 // FIXME: Now that PR4941 has been fixed this can be enabled.
Index: lib/Frontend/CompilerInvocation.cpp
===================================================================
--- lib/Frontend/CompilerInvocation.cpp
+++ lib/Frontend/CompilerInvocation.cpp
@@ -823,6 +823,10 @@
   Opts.LinkerOptions = Args.getAllArgValues(OPT_linker_option);
   bool NeedLocTracking = false;
 
+  Opts.OptRecordFile = Args.getLastArgValue(OPT_opt_record_file);
+  if (!Opts.OptRecordFile.empty())
+    NeedLocTracking = true;
+
   if (Arg *A = Args.getLastArg(OPT_Rpass_EQ)) {
     Opts.OptimizationRemarkPattern =
         GenerateOptimizationRemarkRegex(Diags, Args, A);
Index: test/CodeGen/Inputs/opt-record.proftext
===================================================================
--- /dev/null
+++ test/CodeGen/Inputs/opt-record.proftext
@@ -0,0 +1,26 @@
+foo
+# Func Hash:
+0
+# Num Counters:
+1
+# Counter Values:
+30
+
+bar
+# Func Hash:
+0
+# Num Counters:
+1
+# Counter Values:
+30
+
+Test
+# Func Hash:
+269
+# Num Counters:
+3
+# Counter Values:
+1
+30
+15
+
Index: test/CodeGen/opt-record.c
===================================================================
--- /dev/null
+++ test/CodeGen/opt-record.c
@@ -0,0 +1,33 @@
+// RUN: %clang_cc1 -O3 -triple x86_64-unknown-linux-gnu -target-cpu x86-64 %s -o %t -dwarf-column-info -opt-record-file %t.yaml -emit-obj
+// RUN: cat %t.yaml | FileCheck %s
+// RUN: llvm-profdata merge %S/Inputs/opt-record.proftext -o %t.profdata
+// RUN: %clang_cc1 -O3 -triple x86_64-unknown-linux-gnu -target-cpu x86-64 -fprofile-instrument-use-path=%t.profdata %s -o %t -dwarf-column-info -opt-record-file %t.yaml -emit-obj
+// RUN: cat %t.yaml | FileCheck -check-prefix=CHECK -check-prefix=CHECK-PGO %s
+// REQUIRES: x86-registered-target
+
+void bar();
+void foo() { bar(); }
+
+void Test(int *res, int *c, int *d, int *p, int n) {
+  int i;
+
+#pragma clang loop vectorize(assume_safety)
+  for (i = 0; i < 1600; i++) {
+    res[i] = (p[i] == 0) ? res[i] : res[i] + d[i];
+  }
+}
+
+// CHECK: --- !Missed
+// CHECK: Pass:            inline
+// CHECK: Name:            NoDefinition
+// CHECK: DebugLoc:
+// CHECK: Function:        foo
+// CHECK-PGO: Hotness:
+
+// CHECK: --- !Passed
+// CHECK: Pass:            loop-vectorize
+// CHECK: Name:            Vectorized
+// CHECK: DebugLoc:
+// CHECK: Function:        Test
+// CHECK-PGO: Hotness:
+
Index: test/Driver/opt-record.c
===================================================================
--- /dev/null
+++ test/Driver/opt-record.c
@@ -0,0 +1,18 @@
+// RUN: %clang -### -S -o FOO -fsave-optimization-record %s 2>&1 | FileCheck %s
+// RUN: %clang -### -c -o FOO -fsave-optimization-record %s 2>&1 | FileCheck %s
+// RUN: %clang -### -c -fsave-optimization-record %s 2>&1 | FileCheck %s -check-prefix=CHECK-NO-O
+// RUN: %clang -### -fsave-optimization-record %s 2>&1 | FileCheck %s -check-prefix=CHECK-NO-O
+// RUN: %clang -### -S -fsave-optimization-record -x cuda -nocudainc -nocudalib %s 2>&1 | FileCheck %s -check-prefix=CHECK-NO-O -check-prefix=CHECK-CUDA-DEV
+// RUN: %clang -### -fsave-optimization-record -x cuda -nocudainc -nocudalib %s 2>&1 | FileCheck %s -check-prefix=CHECK-NO-O -check-prefix=CHECK-CUDA-DEV
+// RUN: %clang -### -S -o FOO -fsave-optimization-record=BAR.txt %s 2>&1 | FileCheck %s -check-prefix=CHECK-EQ
+
+// CHECK: "-cc1"
+// CHECK: "-opt-record-file" "FOO.opt.yaml"
+
+// CHECK-NO-O: "-cc1"
+// CHECK-NO-O-DAG: "-opt-record-file" "opt-record.opt.yaml"
+// CHECK-CUDA-DEV-DAG: "-opt-record-file" "opt-record-device-cuda-nvptx64-nvidia-cuda-sm_20.opt.yaml"
+
+// CHECK-EQ: "-cc1"
+// CHECK-EQ: "-opt-record-file" "BAR.txt"
+