[CUDA] Added -f[no-]cuda-short-ptr option

The option enables use of 32-bit pointers for accessing
const/local/shared memory. The feature is disabled by default.

Differential Revision: https://reviews.llvm.org/D46148

llvm-svn: 331938

4 files changed, 12 insertions, 2 deletions

diff --git a/clang/lib/Basic/Targets/NVPTX.cpp b/clang/lib/Basic/Targets/NVPTX.cpp
index 04293b3ce10..fd4ee160606 100644
--- a/clang/lib/Basic/Targets/NVPTX.cpp
+++ b/clang/lib/Basic/Targets/NVPTX.cpp
@@ -68,6 +68,9 @@ NVPTXTargetInfo::NVPTXTargetInfo(const llvm::Triple &Triple,
 
   if (TargetPointerWidth == 32)
     resetDataLayout("e-p:32:32-i64:64-i128:128-v16:16-v32:32-n16:32:64");
+  else if (Opts.NVPTXUseShortPointers)
+    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");
 
diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
index 4165afcfa9c..cc26b5e04ec 100644
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -4714,6 +4714,9 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
 
     if (Args.hasFlag(options::OPT_fcuda_rdc, options::OPT_fno_cuda_rdc, false))
       CmdArgs.push_back("-fcuda-rdc");
+    if (Args.hasFlag(options::OPT_fcuda_short_ptr,
+                     options::OPT_fno_cuda_short_ptr, false))
+      CmdArgs.push_back("-fcuda-short-ptr");
   }
 
   // OpenMP offloading device jobs take the argument -fopenmp-host-ir-file-path
diff --git a/clang/lib/Driver/ToolChains/Cuda.cpp b/clang/lib/Driver/ToolChains/Cuda.cpp
index 3978cb27429..5916ad033c2 100644
--- a/clang/lib/Driver/ToolChains/Cuda.cpp
+++ b/clang/lib/Driver/ToolChains/Cuda.cpp
@@ -635,8 +635,10 @@ void CudaToolChain::addClangTargetOptions(
     // 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({"-mllvm", "--nvptx-short-ptr"});
 
   if (DeviceOffloadingKind == Action::OFK_OpenMP) {
     SmallVector<StringRef, 8> LibraryPaths;
diff --git a/clang/lib/Frontend/CompilerInvocation.cpp b/clang/lib/Frontend/CompilerInvocation.cpp
index 71c946442d7..05e5196e32d 100644
--- a/clang/lib/Frontend/CompilerInvocation.cpp
+++ b/clang/lib/Frontend/CompilerInvocation.cpp
@@ -2922,6 +2922,8 @@ static void ParseTargetArgs(TargetOptions &Opts, ArgList &Args,
     Opts.Triple = llvm::sys::getDefaultTargetTriple();
   Opts.OpenCLExtensionsAsWritten = Args.getAllArgValues(OPT_cl_ext_EQ);
   Opts.ForceEnableInt128 = Args.hasArg(OPT_fforce_enable_int128);
+  Opts.NVPTXUseShortPointers = Args.hasFlag(
+      options::OPT_fcuda_short_ptr, options::OPT_fno_cuda_short_ptr, false);
 }
 
 bool CompilerInvocation::CreateFromArgs(CompilerInvocation &Res,