diff --git a/llvm/lib/Transforms/IPO/OpenMPOpt.cpp b/llvm/lib/Transforms/IPO/OpenMPOpt.cpp
--- a/llvm/lib/Transforms/IPO/OpenMPOpt.cpp
+++ b/llvm/lib/Transforms/IPO/OpenMPOpt.cpp
@@ -97,6 +97,11 @@
     cl::desc("Print the current module after OpenMP optimizations."),
     cl::Hidden, cl::init(false));
 
+static cl::opt<bool> AlwaysInlineDeviceFunctions(
+    "openmp-opt-inline-device", cl::ZeroOrMore,
+    cl::desc("Inline all applicible functions on the device."),
+    cl::Hidden, cl::init(false));
+
 STATISTIC(NumOpenMPRuntimeCallsDeduplicated,
           "Number of OpenMP runtime calls deduplicated");
 STATISTIC(NumOpenMPParallelRegionsDeleted,
@@ -4481,6 +4486,13 @@
   OpenMPOpt OMPOpt(SCC, CGUpdater, OREGetter, InfoCache, A);
   bool Changed = OMPOpt.run(true);
 
+  // Optionally inline device functions for potentially better performance.
+  if (AlwaysInlineDeviceFunctions)
+    if (isOpenMPDevice(M))
+      for (Function &F : M)
+        if (!F.isDeclaration() && !F.hasFnAttribute(Attribute::NoInline))
+          F.addFnAttr(Attribute::AlwaysInline);
+
   if (PrintModuleAfterOptimizations)
     LLVM_DEBUG(dbgs() << TAG << "Module after OpenMPOpt Module Pass:\n" << M);