diff --git a/clang/test/Driver/linker-wrapper.c b/clang/test/Driver/linker-wrapper.c
--- a/clang/test/Driver/linker-wrapper.c
+++ b/clang/test/Driver/linker-wrapper.c
@@ -102,7 +102,7 @@
 // RUN:   --image=file=%S/Inputs/dummy-elf.o,kind=cuda,triple=nvptx64-nvidia-cuda,arch=sm_52
 // RUN: %clang -cc1 %s -triple x86_64-unknown-linux-gnu -emit-obj -o %t.o \
 // RUN:   -fembed-offload-object=%t.out
-// RUN: clang-linker-wrapper --dry-run --host-triple=x86_64-unknown-linux-gnu \
+// RUN: clang-linker-wrapper --dry-run --host-triple=x86_64-unknown-linux-gnu --wrapper-jobs=1 \
 // RUN: --linker-path=/usr/bin/ld -- %t.o -o a.out 2>&1 | FileCheck %s --check-prefix=CUDA
 
 // CUDA: nvlink{{.*}}-m64 -o {{.*}}.out -arch sm_52 {{.*}}.o
@@ -116,7 +116,7 @@
 // RUN: %clang -cc1 %s -triple x86_64-unknown-linux-gnu -emit-obj -o %t.o \
 // RUN:   -fembed-offload-object=%t.out
 // RUN: clang-linker-wrapper --dry-run --host-triple=x86_64-unknown-linux-gnu -linker-path \
-// RUN:   /usr/bin/ld -- %t.o -o a.out 2>&1 | FileCheck %s --check-prefix=HIP
+// RUN:   --wrapper-jobs=1 /usr/bin/ld -- %t.o -o a.out 2>&1 | FileCheck %s --check-prefix=HIP
 
 // HIP: lld{{.*}}-flavor gnu --no-undefined -shared -plugin-opt=-amdgpu-internalize-symbols -plugin-opt=mcpu=gfx908 -o {{.*}}.out {{.*}}.o
 // HIP: lld{{.*}}-flavor gnu --no-undefined -shared -plugin-opt=-amdgpu-internalize-symbols -plugin-opt=mcpu=gfx90a -o {{.*}}.out {{.*}}.o
@@ -127,7 +127,7 @@
 // RUN:   --image=file=%S/Inputs/dummy-elf.o,kind=openmp,triple=nvptx64-nvidia-cuda,arch=sm_70
 // RUN: %clang -cc1 %s -triple x86_64-unknown-linux-gnu -emit-obj -o %t.o \
 // RUN:   -fembed-offload-object=%t.out
-// RUN: clang-linker-wrapper --dry-run --host-triple=x86_64-unknown-linux-gnu \
+// RUN: clang-linker-wrapper --dry-run --host-triple=x86_64-unknown-linux-gnu --wrapper-jobs=1 \
 // RUN:   --linker-path=/usr/bin/ld --device-linker=a --device-linker=nvptx64-nvidia-cuda=b -- \
 // RUN:   %t.o -o a.out 2>&1 | FileCheck %s --check-prefix=LINKER_ARGS
 
diff --git a/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp b/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
--- a/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
+++ b/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
@@ -42,6 +42,7 @@
 #include "llvm/Support/Host.h"
 #include "llvm/Support/InitLLVM.h"
 #include "llvm/Support/MemoryBuffer.h"
+#include "llvm/Support/Parallel.h"
 #include "llvm/Support/Path.h"
 #include "llvm/Support/Program.h"
 #include "llvm/Support/Signals.h"
@@ -1082,6 +1083,7 @@
 /// Returns a new ArgList containg arguments used for the device linking phase.
 DerivedArgList getLinkerArgs(ArrayRef<OffloadFile> Input,
                              const InputArgList &Args) {
+
   DerivedArgList DAL = DerivedArgList(DerivedArgList(Args));
   for (Arg *A : Args)
     DAL.append(A);
@@ -1119,19 +1121,34 @@
 /// be registered by the runtime.
 Expected<SmallVector<StringRef>>
 linkAndWrapDeviceFiles(SmallVectorImpl<OffloadFile> &LinkerInputFiles,
-                       const InputArgList &Args) {
+                       const InputArgList &Args, char **Argv, int Argc) {
   llvm::TimeTraceScope TimeScope("Handle all device input");
 
-  DenseMap<OffloadFile::TargetID, SmallVector<OffloadFile, 4>> InputsForTarget;
+  DenseMap<OffloadFile::TargetID, SmallVector<OffloadFile>> InputMap;
   for (auto &File : LinkerInputFiles)
-    InputsForTarget[File].emplace_back(std::move(File));
+    InputMap[File].emplace_back(std::move(File));
   LinkerInputFiles.clear();
 
-  DenseMap<OffloadKind, SmallVector<OffloadingImage, 2>> Images;
-  for (auto &[ID, Input] : InputsForTarget) {
+  SmallVector<SmallVector<OffloadFile>> InputsForTarget;
+  for (auto &[ID, Input] : InputMap)
+    InputsForTarget.emplace_back(std::move(Input));
+  InputMap.clear();
+
+  std::mutex ImageMtx;
+  DenseMap<OffloadKind, SmallVector<OffloadingImage>> Images;
+  auto Err = parallelForEachError(InputsForTarget, [&](auto &Input) -> Error {
     llvm::TimeTraceScope TimeScope("Link device input");
 
-    auto LinkerArgs = getLinkerArgs(Input, Args);
+    // Each thread needs its own copy of the base arguments to maintain
+    // per-device argument storage of synthetic strings.
+    const OptTable &Tbl = getOptTable();
+    BumpPtrAllocator Alloc;
+    StringSaver Saver(Alloc);
+    auto BaseArgs =
+        Tbl.parseArgs(Argc, Argv, OPT_INVALID, Saver, [](StringRef Err) {
+          reportError(createStringError(inconvertibleErrorCode(), Err));
+        });
+    auto LinkerArgs = getLinkerArgs(Input, BaseArgs);
 
     DenseSet<OffloadKind> ActiveOffloadKinds;
     for (const auto &File : Input)
@@ -1142,7 +1159,7 @@
     if (Error Err = linkBitcodeFiles(Input, InputFiles, LinkerArgs))
       return std::move(Err);
 
-    // Write any remaining device inputs to an output file for the linker job.
+    // Write any remaining device inputs to an output file for the linker.
     for (const OffloadFile &File : Input) {
       auto FileNameOrErr = writeOffloadFile(File);
       if (!FileNameOrErr)
@@ -1150,7 +1167,7 @@
       InputFiles.emplace_back(*FileNameOrErr);
     }
 
-    // Link the remaining device files, if necessary, using the device linker.
+    // Link the remaining device files using the device linker.
     llvm::Triple Triple(LinkerArgs.getLastArgValue(OPT_triple_EQ));
     bool RequiresLinking =
         !Args.hasArg(OPT_embed_bitcode) &&
@@ -1171,12 +1188,19 @@
       TheImage.TheImageKind = IMG_Object;
       TheImage.TheOffloadKind = Kind;
       TheImage.StringData = {
-          {"triple", LinkerArgs.getLastArgValue(OPT_triple_EQ)},
-          {"arch", LinkerArgs.getLastArgValue(OPT_arch_EQ)}};
+          {"triple",
+           Args.MakeArgString(LinkerArgs.getLastArgValue(OPT_triple_EQ))},
+          {"arch",
+           Args.MakeArgString(LinkerArgs.getLastArgValue(OPT_arch_EQ))}};
       TheImage.Image = std::move(*FileOrErr);
+
+      std::lock_guard<decltype(ImageMtx)> Guard(ImageMtx);
       Images[Kind].emplace_back(std::move(TheImage));
     }
-  }
+    return Error::success();
+  });
+  if (Err)
+    return std::move(Err);
 
   // Create a binary image of each offloading image and embed it into a new
   // object file.
@@ -1351,6 +1375,15 @@
   if (!CudaBinaryPath.empty())
     CudaBinaryPath = CudaBinaryPath + "/bin";
 
+  if (auto *Arg = Args.getLastArg(OPT_wrapper_jobs)) {
+    unsigned Threads = 0;
+    if (!llvm::to_integer(Arg->getValue(), Threads) || Threads == 0)
+      reportError(createStringError(
+          inconvertibleErrorCode(), "%s: expected a positive integer, got '%s'",
+          Arg->getSpelling().data(), Arg->getValue()));
+    parallel::strategy = hardware_concurrency(Threads);
+  }
+
   if (Args.hasArg(OPT_wrapper_time_trace_eq)) {
     unsigned Granularity;
     Args.getLastArgValue(OPT_wrapper_time_trace_granularity, "500")
@@ -1367,7 +1400,8 @@
       reportError(DeviceInputFiles.takeError());
 
     // Link and wrap the device images extracted from the linker input.
-    auto FilesOrErr = linkAndWrapDeviceFiles(*DeviceInputFiles, Args);
+    auto FilesOrErr =
+        linkAndWrapDeviceFiles(*DeviceInputFiles, Args, Argv, Argc);
     if (!FilesOrErr)
       reportError(FilesOrErr.takeError());
 
diff --git a/clang/tools/clang-linker-wrapper/LinkerWrapperOpts.td b/clang/tools/clang-linker-wrapper/LinkerWrapperOpts.td
--- a/clang/tools/clang-linker-wrapper/LinkerWrapperOpts.td
+++ b/clang/tools/clang-linker-wrapper/LinkerWrapperOpts.td
@@ -59,6 +59,10 @@
   Flags<[WrapperOnlyOption]>, MetaVarName<"<number>">,
   HelpText<"Set the granularity of time-trace updates">;
 
+def wrapper_jobs : Joined<["--"], "wrapper-jobs=">,
+  Flags<[WrapperOnlyOption]>, MetaVarName<"<number>">,
+  HelpText<"Sets the number of parallel jobs to use for device linking">;
+
 // Flags passed to the device linker.
 def arch_EQ : Joined<["--"], "arch=">,
   Flags<[DeviceOnlyOption, HelpHidden]>, MetaVarName<"<arch>">,