Index: clang/include/clang/Driver/Options.td
===================================================================
--- clang/include/clang/Driver/Options.td
+++ clang/include/clang/Driver/Options.td
@@ -579,6 +579,9 @@
 def fcuda_rdc : Flag<["-"], "fcuda-rdc">, Flags<[CC1Option]>,
   HelpText<"Generate relocatable device code, also known as separate compilation mode.">;
 def fno_cuda_rdc : Flag<["-"], "fno-cuda-rdc">;
+def fcuda_short_ptr : Flag<["-"], "fcuda-short-ptr">, Flags<[CC1Option]>,
+  HelpText<"Use 32-bit pointers for accessing const/local/shared address spaces.">;
+def fno_cuda_short_ptr : Flag<["-"], "fno-cuda-short-ptr">;
 def dA : Flag<["-"], "dA">, Group<d_Group>;
 def dD : Flag<["-"], "dD">, Group<d_Group>, Flags<[CC1Option]>,
   HelpText<"Print macro definitions in -E mode in addition to normal output">;
Index: clang/lib/Basic/Targets/NVPTX.cpp
===================================================================
--- clang/lib/Basic/Targets/NVPTX.cpp
+++ clang/lib/Basic/Targets/NVPTX.cpp
@@ -41,19 +41,21 @@
          "NVPTX only supports 32- and 64-bit modes.");
 
   PTXVersion = 32;
+  bool UseShortPtr = false;
   for (const StringRef Feature : Opts.FeaturesAsWritten) {
-    if (!Feature.startswith("+ptx"))
-      continue;
-    PTXVersion = llvm::StringSwitch<unsigned>(Feature)
-                     .Case("+ptx61", 61)
-                     .Case("+ptx60", 60)
-                     .Case("+ptx50", 50)
-                     .Case("+ptx43", 43)
-                     .Case("+ptx42", 42)
-                     .Case("+ptx41", 41)
-                     .Case("+ptx40", 40)
-                     .Case("+ptx32", 32)
-                     .Default(32);
+    if (Feature == "+short-ptr")
+      UseShortPtr = true;
+    else if (Feature.startswith("+ptx"))
+      PTXVersion = llvm::StringSwitch<unsigned>(Feature)
+                       .Case("+ptx61", 61)
+                       .Case("+ptx60", 60)
+                       .Case("+ptx50", 50)
+                       .Case("+ptx43", 43)
+                       .Case("+ptx42", 42)
+                       .Case("+ptx41", 41)
+                       .Case("+ptx40", 40)
+                       .Case("+ptx32", 32)
+                       .Default(32);
   }
 
   TLSSupported = false;
@@ -68,6 +70,9 @@
 
   if (TargetPointerWidth == 32)
     resetDataLayout("e-p:32:32-i64:64-i128:128-v16:16-v32:32-n16:32:64");
+  else if (UseShortPtr)
+    resetDataLayout(
+        "e-p3:32:32-p4:32:32-p5:32:32-i64:64-i128:128-v16:16-v32:32-n16:32:64");
   else
     resetDataLayout("e-i64:64-i128:128-v16:16-v32:32-n16:32:64");
 
Index: clang/lib/Driver/ToolChains/Cuda.cpp
===================================================================
--- clang/lib/Driver/ToolChains/Cuda.cpp
+++ clang/lib/Driver/ToolChains/Cuda.cpp
@@ -633,8 +633,10 @@
     // CUDA-9.0 uses new instructions that are only available in PTX6.0+
     PtxFeature = "+ptx60";
   }
-  CC1Args.push_back("-target-feature");
-  CC1Args.push_back(PtxFeature);
+  CC1Args.append({"-target-feature", PtxFeature});
+  if (DriverArgs.hasFlag(options::OPT_fcuda_short_ptr,
+                         options::OPT_fno_cuda_short_ptr, false))
+    CC1Args.append({"-target-feature", "+short-ptr"});
 
   if (DeviceOffloadingKind == Action::OFK_OpenMP) {
     SmallVector<StringRef, 8> LibraryPaths;