Index: include/clang/Driver/Driver.h
===================================================================
--- include/clang/Driver/Driver.h
+++ include/clang/Driver/Driver.h
@@ -359,8 +359,10 @@
   /// \param C - The compilation that is being built.
   /// \param Args - The input arguments.
   /// \param Actions - The list to store the resulting actions onto.
+  /// \param MultipleArchs - Whether multiple -arch options were supplied.
   void BuildActions(Compilation &C, llvm::opt::DerivedArgList &Args,
-                    const InputList &Inputs, ActionList &Actions) const;
+                    const InputList &Inputs, ActionList &Actions,
+                    bool MultipleArchs) const;
 
   /// BuildUniversalActions - Construct the list of actions to perform
   /// for the given arguments, which may require a universal build.
Index: lib/Driver/Driver.cpp
===================================================================
--- lib/Driver/Driver.cpp
+++ lib/Driver/Driver.cpp
@@ -707,7 +707,7 @@
   if (TC.getTriple().isOSBinFormatMachO())
     BuildUniversalActions(*C, C->getDefaultToolChain(), Inputs);
   else
-    BuildActions(*C, C->getArgs(), Inputs, C->getActions());
+    BuildActions(*C, C->getArgs(), Inputs, C->getActions(), false);
 
   if (CCCPrintPhases) {
     PrintActions(*C);
@@ -910,7 +910,7 @@
   if (TC.getTriple().isOSBinFormatMachO())
     BuildUniversalActions(C, TC, Inputs);
   else
-    BuildActions(C, C.getArgs(), Inputs, C.getActions());
+    BuildActions(C, C.getArgs(), Inputs, C.getActions(), false);
 
   BuildJobs(C);
 
@@ -1392,7 +1392,8 @@
     Archs.push_back(Args.MakeArgString(TC.getDefaultUniversalArchName()));
 
   ActionList SingleActions;
-  BuildActions(C, Args, BAInputs, SingleActions);
+  bool MultipleArchs = Archs.size() > 1;
+  BuildActions(C, Args, BAInputs, SingleActions, MultipleArchs);
 
   // Add in arch bindings for every top level action, as well as lipo and
   // dsymutil steps if needed.
@@ -2389,7 +2390,8 @@
 } // anonymous namespace.
 
 void Driver::BuildActions(Compilation &C, DerivedArgList &Args,
-                          const InputList &Inputs, ActionList &Actions) const {
+                          const InputList &Inputs, ActionList &Actions,
+                          bool MultipleArchs) const {
   llvm::PrettyStackTraceString CrashInfo("Building compilation actions");
 
   if (!SuppressMissingInputWarning && Inputs.empty()) {
@@ -2595,6 +2597,21 @@
         break;
       }
 
+      // When saving temps, add extra actions to write unoptimized and optimized
+      // IR besides the normal bitcode outputs if possible. This is not possible
+      // for multi-arch builds because in these builds we check that we can lipo
+      // all action outputs.
+      if (!MultipleArchs) {
+        if (isSaveTempsEnabled() && Phase == phases::Compile) {
+          Actions.push_back(
+              C.MakeAction<CompileJobAction>(Current, types::TY_LLVM_IR));
+        }
+        if (isSaveTempsEnabled() && Phase == phases::Backend) {
+          Actions.push_back(
+              C.MakeAction<BackendJobAction>(Current, types::TY_LLVM_IR));
+        }
+      }
+
       // Otherwise construct the appropriate action.
       auto *NewCurrent = ConstructPhaseAction(C, Args, Phase, Current);
 
@@ -3544,6 +3561,11 @@
     if (!AtTopLevel && C.getArgs().hasArg(options::OPT_emit_llvm) &&
         JA.getType() == types::TY_LLVM_BC)
       Suffixed += ".tmp";
+    // When using -save-temps, append a ".unoptimized" suffix so that the
+    // optimized .ll file doesn't overwrite the unoptimized one.
+    if (isSaveTempsEnabled() && JA.getType() == types::TY_LLVM_IR &&
+        JA.getKind() == Action::CompileJobClass)
+      Suffixed += ".unoptimized";
     Suffixed += '.';
     Suffixed += Suffix;
     NamedOutput = C.getArgs().MakeArgString(Suffixed.c_str());
Index: test/Driver/cuda-options.cu
===================================================================
--- test/Driver/cuda-options.cu
+++ test/Driver/cuda-options.cu
@@ -151,6 +151,12 @@
 // NOARCH-SM35-NOT: "-cc1"{{.*}}"-target-cpu" "sm_35"
 // ARCHALLERROR: error: Unsupported CUDA gpu architecture: all
 
+// Match host-side preprocessor job with -save-temps.
+// HOST-SAVE: "-cc1" "-triple" "x86_64--linux-gnu"
+// HOST-SAVE-SAME: "-aux-triple" "nvptx64-nvidia-cuda"
+// HOST-SAVE-NOT: "-fcuda-is-device"
+// HOST-SAVE-SAME: "-x" "cuda"
+
 // Match device-side preprocessor and compiler phases with -save-temps.
 // DEVICE-SAVE: "-cc1" "-triple" "nvptx64-nvidia-cuda"
 // DEVICE-SAVE-SAME: "-aux-triple" "x86_64--linux-gnu"
@@ -194,12 +200,6 @@
 // INCLUDES-DEVICE-DAG: "--image=profile=sm_{{[0-9]+}},file=[[CUBINFILE]]"
 // INCLUDES-DEVICE-DAG: "--image=profile=compute_{{[0-9]+}},file=[[PTXFILE]]"
 
-// Match host-side preprocessor job with -save-temps.
-// HOST-SAVE: "-cc1" "-triple" "x86_64--linux-gnu"
-// HOST-SAVE-SAME: "-aux-triple" "nvptx64-nvidia-cuda"
-// HOST-SAVE-NOT: "-fcuda-is-device"
-// HOST-SAVE-SAME: "-x" "cuda"
-
 // Match host-side compilation.
 // HOST: "-cc1" "-triple" "x86_64--linux-gnu"
 // HOST-SAME: "-aux-triple" "nvptx64-nvidia-cuda"
Index: test/Driver/save-temps.c
===================================================================
--- test/Driver/save-temps.c
+++ test/Driver/save-temps.c
@@ -1,9 +1,11 @@
 // RUN: %clang -target x86_64-apple-darwin -save-temps -arch x86_64 %s -### 2>&1 \
 // RUN:   | FileCheck %s
 // CHECK: "-o" "save-temps.i"
+// CHECK: "-o" "save-temps.unoptimized.ll"
 // CHECK: "-emit-llvm-uselists"
 // CHECK: "-disable-llvm-passes"
 // CHECK: "-o" "save-temps.bc"
+// CHECK: "-o" "save-temps.ll"
 // CHECK: "-o" "save-temps.s"
 // CHECK: "-o" "save-temps.o"
 // CHECK: "-o" "a.out"