Index: include/clang/Driver/Options.td
===================================================================
--- include/clang/Driver/Options.td
+++ include/clang/Driver/Options.td
@@ -2250,7 +2250,7 @@
   HelpText<"Do not add -rpath with architecture-specific resource directory to the linker flags">;
 def r : Flag<["-"], "r">, Flags<[LinkerInput,NoArgumentUnused]>,
         Group<Link_Group>;
-def save_temps_EQ : Joined<["-", "--"], "save-temps=">, Flags<[DriverOption]>,
+def save_temps_EQ : Joined<["-", "--"], "save-temps=">, Flags<[CC1Option, DriverOption]>,
   HelpText<"Save intermediate compilation results.">;
 def save_temps : Flag<["-", "--"], "save-temps">, Flags<[DriverOption]>,
   Alias<save_temps_EQ>, AliasArgs<["cwd"]>,
Index: include/clang/Frontend/CodeGenOptions.h
===================================================================
--- include/clang/Frontend/CodeGenOptions.h
+++ include/clang/Frontend/CodeGenOptions.h
@@ -205,6 +205,9 @@
   /// the summary and module symbol table (and not, e.g. any debug metadata).
   std::string ThinLinkBitcodeFile;
 
+  /// Prefix to use for -save-temps output.
+  std::string SaveTempsFilePrefix;
+
   /// Name of file passed with -fcuda-include-gpubinary option to forward to
   /// CUDA runtime back-end for incorporating them into host-side object file.
   std::string CudaGpuBinaryFileName;
Index: lib/CodeGen/BackendUtil.cpp
===================================================================
--- lib/CodeGen/BackendUtil.cpp
+++ lib/CodeGen/BackendUtil.cpp
@@ -1107,6 +1107,15 @@
     return llvm::make_unique<lto::NativeObjectStream>(std::move(OS));
   };
   lto::Config Conf;
+  if (CGOpts.SaveTempsFilePrefix != "") {
+    if (Error E = Conf.addSaveTemps(CGOpts.SaveTempsFilePrefix + ".",
+                                    /* UseInputModulePath */ false)) {
+      handleAllErrors(std::move(E), [&](ErrorInfoBase &EIB) {
+        errs() << "Error setting up ThinLTO save-temps: " << EIB.message()
+               << '\n';
+      });
+    }
+  }
   Conf.CPU = TOpts.CPU;
   Conf.CodeModel = getCodeModel(CGOpts);
   Conf.MAttrs = TOpts.Features;
Index: lib/Driver/Driver.cpp
===================================================================
--- lib/Driver/Driver.cpp
+++ lib/Driver/Driver.cpp
@@ -3371,19 +3371,34 @@
   const Tool *combineBackendCompile(ArrayRef<JobActionInfo> ActionInfo,
                                     const ActionList *&Inputs,
                                     ActionList &CollapsedOffloadAction) {
-    if (ActionInfo.size() < 2 || !canCollapsePreprocessorAction())
+    if (ActionInfo.size() < 2)
       return nullptr;
     auto *BJ = dyn_cast<BackendJobAction>(ActionInfo[0].JA);
     auto *CJ = dyn_cast<CompileJobAction>(ActionInfo[1].JA);
     if (!BJ || !CJ)
       return nullptr;
 
+    // Check if the initial input (to the compile job or its predessor if one
+    // exists) is LLVM bitcode. In that case, no preprocessor step is required
+    // and we can still collapse the compile and backend jobs when we have
+    // -save-temps. I.e. there is no need for a separate compile job just to
+    // emit unoptimized bitcode.
+    bool InputIsBitcode = true;
+    for (size_t i = 1; i < ActionInfo.size(); i++)
+      if (ActionInfo[i].JA->getType() != types::TY_LLVM_BC &&
+          ActionInfo[i].JA->getType() != types::TY_LTO_BC) {
+        InputIsBitcode = false;
+        break;
+      }
+    if (!InputIsBitcode && !canCollapsePreprocessorAction())
+      return nullptr;
+
     // Get compiler tool.
     const Tool *T = TC.SelectTool(*CJ);
     if (!T)
       return nullptr;
 
-    if (T->canEmitIR() && (SaveTemps || EmbedBitcode))
+    if (T->canEmitIR() && ((SaveTemps && !InputIsBitcode) || EmbedBitcode))
       return nullptr;
 
     Inputs = &CJ->getInputs();
Index: lib/Driver/ToolChains/Clang.cpp
===================================================================
--- lib/Driver/ToolChains/Clang.cpp
+++ lib/Driver/ToolChains/Clang.cpp
@@ -3272,6 +3272,9 @@
     Args.AddLastArg(CmdArgs, options::OPT_fthinlto_index_EQ);
   }
 
+  if (const Arg *A = Args.getLastArg(options::OPT_save_temps_EQ))
+    Args.AddLastArg(CmdArgs, options::OPT_save_temps_EQ);
+
   // Embed-bitcode option.
   if (C.getDriver().embedBitcodeInObject() && !C.getDriver().isUsingLTO() &&
       (isa<BackendJobAction>(JA) || isa<AssembleJobAction>(JA))) {
Index: lib/Frontend/CompilerInvocation.cpp
===================================================================
--- lib/Frontend/CompilerInvocation.cpp
+++ lib/Frontend/CompilerInvocation.cpp
@@ -487,7 +487,8 @@
 
 static bool ParseCodeGenArgs(CodeGenOptions &Opts, ArgList &Args, InputKind IK,
                              DiagnosticsEngine &Diags,
-                             const TargetOptions &TargetOpts) {
+                             const TargetOptions &TargetOpts,
+                             const FrontendOptions &FrontendOpts) {
   bool Success = true;
   llvm::Triple Triple = llvm::Triple(TargetOpts.Triple);
 
@@ -739,6 +740,12 @@
           << A->getAsString(Args) << "-x ir";
     Opts.ThinLTOIndexFile = Args.getLastArgValue(OPT_fthinlto_index_EQ);
   }
+  if (Arg *A = Args.getLastArg(OPT_save_temps_EQ))
+    Opts.SaveTempsFilePrefix =
+        llvm::StringSwitch<std::string>(A->getValue())
+            .Case("obj", FrontendOpts.OutputFile)
+            .Default(llvm::sys::path::filename(FrontendOpts.OutputFile).str());
+
   Opts.ThinLinkBitcodeFile = Args.getLastArgValue(OPT_fthin_link_bitcode_EQ);
 
   Opts.MSVolatile = Args.hasArg(OPT_fms_volatile);
@@ -2890,7 +2897,7 @@
                                       LangOpts.IsHeaderFile);
   ParseTargetArgs(Res.getTargetOpts(), Args, Diags);
   Success &= ParseCodeGenArgs(Res.getCodeGenOpts(), Args, DashX, Diags,
-                              Res.getTargetOpts());
+                              Res.getTargetOpts(), Res.getFrontendOpts());
   ParseHeaderSearchArgs(Res.getHeaderSearchOpts(), Args,
                         Res.getFileSystemOpts().WorkingDir);
   if (DashX.getFormat() == InputKind::Precompiled ||
Index: test/CodeGen/thinlto_backend.ll
===================================================================
--- test/CodeGen/thinlto_backend.ll
+++ test/CodeGen/thinlto_backend.ll
@@ -26,8 +26,16 @@
 ; RUN: %clang -target x86_64-unknown-linux-gnu -O2 -o %t4.o -x ir %t5.o -c -fthinlto-index=%t.thinlto.bc
 ; RUN: llvm-nm %t4.o | count 0
 
-; Ensure f2 was imported
-; RUN: %clang -target x86_64-unknown-linux-gnu -O2 -o %t3.o -x ir %t1.o -c -fthinlto-index=%t.thinlto.bc
+; Ensure f2 was imported. Check for all 3 flavors of -save-temps[=cwd|obj].
+; RUN: %clang -target x86_64-unknown-linux-gnu -O2 -o %t3.o -x ir %t1.o -c -fthinlto-index=%t.thinlto.bc -save-temps=obj
+; RUN: llvm-dis %t1.s.0.3.import.bc -o - | FileCheck --check-prefix=CHECK-IMPORT %s
+; RUN: mkdir -p %T/dir1
+; RUN: (cd %T/dir1 && %clang -target x86_64-unknown-linux-gnu -O2 -o %t3.o -x ir %t1.o -c -fthinlto-index=%t.thinlto.bc -save-temps=cwd)
+; RUN: llvm-dis %T/dir1/*1.s.0.3.import.bc -o - | FileCheck --check-prefix=CHECK-IMPORT %s
+; RUN: mkdir -p %T/dir2
+; RUN: (cd %T/dir2 && %clang -target x86_64-unknown-linux-gnu -O2 -o %t3.o -x ir %t1.o -c -fthinlto-index=%t.thinlto.bc -save-temps)
+; RUN: llvm-dis %T/dir2/*1.s.0.3.import.bc -o - | FileCheck --check-prefix=CHECK-IMPORT %s
+; CHECK-IMPORT: define available_externally void @f2()
 ; RUN: llvm-nm %t3.o | FileCheck --check-prefix=CHECK-OBJ %s
 ; CHECK-OBJ: T f1
 ; CHECK-OBJ-NOT: U f2
Index: test/Driver/thinlto_backend.c
===================================================================
--- test/Driver/thinlto_backend.c
+++ test/Driver/thinlto_backend.c
@@ -5,6 +5,15 @@
 // RUN: %clang -O2 -o %t1.o -x ir %t.o -c -fthinlto-index=%t.thinlto.bc -### 2>&1 | FileCheck %s -check-prefix=CHECK-THINLTOBE-ACTION
 // CHECK-THINLTOBE-ACTION: -fthinlto-index=
 
+// -save-temps should be passed to cc1
+// RUN: %clang -O2 -o %t1.o -x ir %t.o -c -fthinlto-index=%t.thinlto.bc -save-temps -### 2>&1 | FileCheck %s -check-prefix=CHECK-SAVE-TEMPS -check-prefix=CHECK-SAVE-TEMPS-CWD
+// RUN: %clang -O2 -o %t1.o -x ir %t.o -c -fthinlto-index=%t.thinlto.bc -save-temps=cwd -### 2>&1 | FileCheck %s -check-prefix=CHECK-SAVE-TEMPS -check-prefix=CHECK-SAVE-TEMPS-CWD
+// RUN: %clang -O2 -o %t1.o -x ir %t.o -c -fthinlto-index=%t.thinlto.bc -save-temps=obj -### 2>&1 | FileCheck %s -check-prefix=CHECK-SAVE-TEMPS -check-prefix=CHECK-SAVE-TEMPS-OBJ
+// CHECK-SAVE-TEMPS-NOT: -emit-llvm-bc
+// CHECK-SAVE-TEMPS-CWD: -save-temps=cwd
+// CHECK-SAVE-TEMPS-OBJ: -save-temps=obj
+// CHECK-SAVE-TEMPS-NOT: -emit-llvm-bc
+
 // Ensure clang driver gives the expected error for incorrect input type
 // RUN: not %clang -O2 -o %t1.o %s -c -fthinlto-index=%t.thinlto.bc 2>&1 | FileCheck %s -check-prefix=CHECK-WARNING
 // CHECK-WARNING: error: invalid argument '-fthinlto-index={{.*}}' only allowed with '-x ir'