diff --git a/llvm/test/tools/dsymutil/cmdline.test b/llvm/test/tools/dsymutil/cmdline.test
new file mode 100644
index 00000000000000..983df4bf8f009d
--- /dev/null
+++ b/llvm/test/tools/dsymutil/cmdline.test
@@ -0,0 +1,21 @@
+RUN: llvm-dsymutil -help 2>&1 | FileCheck --check-prefix=HELP %s
+HELP: OVERVIEW: manipulate archived DWARF debug symbol files.
+HELP: USAGE: llvm-dsymutil [options] <input files>
+HELP-NOT: -reverse-iterate
+HELP: Specific Options:
+HELP: -arch=<string>
+HELP: -dump-debug-map
+HELP: -flat
+HELP: -no-odr
+HELP: -no-output
+HELP: -no-swiftmodule-timestamp
+HELP: -o=<filename>
+HELP: -oso-prepend-path=<path>
+HELP: -symtab
+HELP: -threads=<n>
+HELP: -verbose
+HELP: -y
+HELP-NOT: -reverse-iterate
+
+RUN: llvm-dsymutil --version 2>&1 | FileCheck --check-prefix=VERSION %s
+VERSION: {{ version }}
diff --git a/llvm/tools/dsymutil/DwarfLinker.cpp b/llvm/tools/dsymutil/DwarfLinker.cpp
index b22b7a9dd1ad56..a726ba4e7b61b1 100644
--- a/llvm/tools/dsymutil/DwarfLinker.cpp
+++ b/llvm/tools/dsymutil/DwarfLinker.cpp
@@ -35,6 +35,7 @@
 #include "llvm/Object/MachO.h"
 #include "llvm/Support/LEB128.h"
 #include "llvm/Support/TargetRegistry.h"
+#include "llvm/Support/ToolOutputFile.h"
 #include "llvm/Target/TargetMachine.h"
 #include "llvm/Target/TargetOptions.h"
 #include <memory>
@@ -479,7 +480,7 @@ class DwarfStreamer {
   /// @}
 
   /// The file we stream the linked Dwarf to.
-  std::unique_ptr<raw_fd_ostream> OutFile;
+  std::unique_ptr<ToolOutputFile> OutFile;
 
   uint32_t RangesSectionSize;
   uint32_t LocSectionSize;
@@ -617,13 +618,13 @@ bool DwarfStreamer::init(Triple TheTriple, StringRef OutputFilename) {
   // Create the output file.
   std::error_code EC;
   OutFile =
-      llvm::make_unique<raw_fd_ostream>(OutputFilename, EC, sys::fs::F_None);
+      llvm::make_unique<ToolOutputFile>(OutputFilename, EC, sys::fs::F_None);
   if (EC)
     return error(Twine(OutputFilename) + ": " + EC.message(), Context);
 
   MCTargetOptions MCOptions = InitMCTargetOptionsFromFlags();
   MS = TheTarget->createMCObjectStreamer(
-      TheTriple, *MC, std::unique_ptr<MCAsmBackend>(MAB), *OutFile,
+      TheTriple, *MC, std::unique_ptr<MCAsmBackend>(MAB), OutFile->os(),
       std::unique_ptr<MCCodeEmitter>(MCE), *MSTI, MCOptions.MCRelaxAll,
       MCOptions.MCIncrementalLinkerCompatible,
       /*DWARFMustBeAtTheEnd*/ false);
@@ -649,11 +650,16 @@ bool DwarfStreamer::init(Triple TheTriple, StringRef OutputFilename) {
 }
 
 bool DwarfStreamer::finish(const DebugMap &DM) {
+  bool Result = true;
   if (DM.getTriple().isOSDarwin() && !DM.getBinaryPath().empty())
-    return MachOUtils::generateDsymCompanion(DM, *MS, *OutFile);
+    Result = MachOUtils::generateDsymCompanion(DM, *MS, OutFile->os());
+  else
+    MS->Finish();
 
-  MS->Finish();
-  return true;
+  // Declare success.
+  OutFile->keep();
+
+  return Result;
 }
 
 /// Set the current output section to debug_info and change
diff --git a/llvm/tools/dsymutil/dsymutil.cpp b/llvm/tools/dsymutil/dsymutil.cpp
index 975f8a5f09507f..5f224b6bb8a116 100644
--- a/llvm/tools/dsymutil/dsymutil.cpp
+++ b/llvm/tools/dsymutil/dsymutil.cpp
@@ -12,9 +12,9 @@
 //
 //===----------------------------------------------------------------------===//
 
+#include "dsymutil.h"
 #include "DebugMap.h"
 #include "MachOUtils.h"
-#include "dsymutil.h"
 #include "llvm/Object/MachO.h"
 #include "llvm/Support/FileSystem.h"
 #include "llvm/Support/FileUtilities.h"
@@ -22,8 +22,9 @@
 #include "llvm/Support/Options.h"
 #include "llvm/Support/PrettyStackTrace.h"
 #include "llvm/Support/Signals.h"
-#include "llvm/Support/raw_ostream.h"
 #include "llvm/Support/TargetSelect.h"
+#include "llvm/Support/ThreadPool.h"
+#include "llvm/Support/raw_ostream.h"
 #include <cstdint>
 #include <string>
 
@@ -61,6 +62,13 @@ static opt<bool> FlatOut("flat",
                          init(false), cat(DsymCategory));
 static alias FlatOutA("f", desc("Alias for --flat"), aliasopt(FlatOut));
 
+static opt<unsigned> Threads(
+    "threads",
+    desc("Specifies the maximum number (n) of simultaneous threads to use\n"
+         "when linking multiple architectures."),
+    value_desc("n"), init(0), cat(DsymCategory));
+static alias ThreadsA("t", desc("Alias for --threads"), aliasopt(Threads));
+
 static opt<bool> Verbose("verbose", desc("Verbosity level"), init(false),
                          cat(DsymCategory));
 
@@ -316,6 +324,15 @@ int main(int argc, char **argv) {
       exitDsymutil(1);
     }
 
+    unsigned NumThreads = Threads;
+    if (!NumThreads)
+      NumThreads = llvm::thread::hardware_concurrency();
+    if (DumpDebugMap || Verbose)
+      NumThreads = 1;
+    NumThreads = std::min(NumThreads, (unsigned)DebugMapPtrsOrErr->size());
+
+    llvm::ThreadPool Threads(NumThreads);
+
     // If there is more than one link to execute, we need to generate
     // temporary files.
     bool NeedsTempFiles = !DumpDebugMap && (*DebugMapPtrsOrErr).size() != 1;
@@ -333,14 +350,27 @@ int main(int argc, char **argv) {
                      << ")\n";
 
       std::string OutputFile = getOutputFileName(InputFile, NeedsTempFiles);
-      if (OutputFile.empty() || !linkDwarf(OutputFile, *Map, Options))
-        exitDsymutil(1);
+
+      auto LinkLambda = [OutputFile, Options, &Map]() {
+        if (OutputFile.empty() || !linkDwarf(OutputFile, *Map, Options))
+          exitDsymutil(1);
+      };
+
+      // FIXME: The DwarfLinker can have some very deep recursion that can max
+      // out the (significantly smaller) stack when using threads. We don't
+      // want this limitation when we only have a single thread.
+      if (NumThreads == 1)
+        LinkLambda();
+      else
+        Threads.async(LinkLambda);
 
       if (NeedsTempFiles)
         TempFiles.emplace_back(Map->getTriple().getArchName().str(),
                                OutputFile);
     }
 
+    Threads.wait();
+
     if (NeedsTempFiles &&
         !MachOUtils::generateUniversalBinary(
             TempFiles, getOutputFileName(InputFile), Options, SDKPath))