[SYCL][NVPTX] Enable -fcuda-short-ptr by default

This makes pointers to CUDA shared, const, and local address spaces as
being 32-bit pointers. This should bring decent performance improvements
in certain programs.

Author: frasercrmck

clang/lib/Driver/ToolChains/Clang.cpp

@@ -8537,9 +8537,10 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
     }
   }
 
-  if (IsCuda) {
+  if (IsCuda || (IsSYCLDevice && Triple.isNVPTX())) {
+    bool UseShortPtr = IsSYCLDevice && Triple.isNVPTX();
     if (Args.hasFlag(options::OPT_fcuda_short_ptr,
-                     options::OPT_fno_cuda_short_ptr, false))
+                     options::OPT_fno_cuda_short_ptr, UseShortPtr))
       CmdArgs.push_back("-fcuda-short-ptr");
   }
 

clang/lib/Driver/ToolChains/Cuda.cpp

@@ -1010,6 +1010,11 @@ void CudaToolChain::addClangTargetOptions(
     CC1Args.push_back(DriverArgs.MakeArgString(LibSpirvFile));
   }
 
+  bool UseShortPtr = DeviceOffloadingKind == Action::OFK_SYCL;
+  if (DriverArgs.hasFlag(options::OPT_fcuda_short_ptr,
+                         options::OPT_fno_cuda_short_ptr, UseShortPtr))
+    CC1Args.append({"-mllvm", "--nvptx-short-ptr"});
+
   if (DriverArgs.hasArg(options::OPT_nogpulib))
     return;
 
@@ -1035,10 +1040,6 @@ void CudaToolChain::addClangTargetOptions(
 
   clang::CudaVersion CudaInstallationVersion = CudaInstallation.version();
 
-  if (DriverArgs.hasFlag(options::OPT_fcuda_short_ptr,
-                         options::OPT_fno_cuda_short_ptr, false))
-    CC1Args.append({"-mllvm", "--nvptx-short-ptr"});
-
   if (CudaInstallationVersion >= CudaVersion::UNKNOWN)
     CC1Args.push_back(
         DriverArgs.MakeArgString(Twine("-target-sdk-version=") +

libclc/CMakeLists.txt

@@ -450,10 +450,15 @@ foreach( t ${LIBCLC_TARGETS_TO_BUILD} )
       list(APPEND flags -D__unix__)
     endif()
 
+    set(spirv_flags ${flags})
+    if( ARCH STREQUAL nvptx OR ARCH STREQUAL nvptx64 )
+      list(APPEND spirv_flags -Xclang -fcuda-short-ptr -mllvm -nvptx-short-ptr)
+    endif()
+
     add_libclc_builtin_set(libspirv-${arch_suffix}
       TRIPLE ${clang_triple}
       TARGET_ENV libspirv
-      COMPILE_OPT ${flags}
+      COMPILE_OPT ${spirv_flags}
       OPT_FLAGS ${opt_flags}
       FILES ${libspirv_files}
       GEN_FILES ${libspirv_gen_files}