[CUDA] Invoke ptxas and fatbinary during compilation.

Summary:
Previously we compiled CUDA device code to PTX assembly and embedded
that asm as text in our host binary.  Now we compile to PTX assembly and
then invoke ptxas to assemble the PTX into a cubin file.  We gather the
ptx and cubin files for each of our --cuda-gpu-archs and combine them
using fatbinary, and then embed that into the host binary.

Adds two new command-line flags, -Xcuda_ptxas and -Xcuda_fatbinary,
which pass args down to the external tools.

Reviewers: tra, echristo

Subscribers: cfe-commits, jhen

Differential Revision: http://reviews.llvm.org/D16082

llvm-svn: 257809

1 files changed, 20 insertions, 7 deletions

diff --git a/clang/lib/Driver/ToolChains.cpp b/clang/lib/Driver/ToolChains.cpp
index e3f25f1e32e..15b36778220 100644
--- a/clang/lib/Driver/ToolChains.cpp
+++ b/clang/lib/Driver/ToolChains.cpp
@@ -1652,13 +1652,14 @@ void Generic_GCC::CudaInstallationDetector::init(
       continue;
 
     CudaInstallPath = CudaPath;
+    CudaBinPath = CudaPath + "/bin";
     CudaIncludePath = CudaInstallPath + "/include";
     CudaLibDevicePath = CudaInstallPath + "/nvvm/libdevice";
     CudaLibPath =
         CudaInstallPath + (TargetTriple.isArch64Bit() ? "/lib64" : "/lib");
 
     if (!(D.getVFS().exists(CudaIncludePath) &&
-          D.getVFS().exists(CudaLibPath) &&
+          D.getVFS().exists(CudaBinPath) && D.getVFS().exists(CudaLibPath) &&
           D.getVFS().exists(CudaLibDevicePath)))
       continue;
 
@@ -4182,13 +4183,16 @@ Tool *DragonFly::buildLinker() const {
   return new tools::dragonfly::Linker(*this);
 }
 
-/// Stub for CUDA toolchain. At the moment we don't have assembler or
-/// linker and need toolchain mainly to propagate device-side options
-/// to CC1.
+/// CUDA toolchain.  Our assembler is ptxas, and our "linker" is fatbinary,
+/// which isn't properly a linker but nonetheless performs the step of stitching
+/// together object files from the assembler into a single blob.
 
 CudaToolChain::CudaToolChain(const Driver &D, const llvm::Triple &Triple,
                              const ArgList &Args)
-    : Linux(D, Triple, Args) {}
+    : Linux(D, Triple, Args) {
+  if (CudaInstallation.isValid())
+    getProgramPaths().push_back(CudaInstallation.getBinPath());
+}
 
 void
 CudaToolChain::addClangTargetOptions(const llvm::opt::ArgList &DriverArgs,
@@ -4222,7 +4226,7 @@ CudaToolChain::TranslateArgs(const llvm::opt::DerivedArgList &Args,
   for (Arg *A : Args) {
     if (A->getOption().matches(options::OPT_Xarch__)) {
       // Skip this argument unless the architecture matches BoundArch
-      if (A->getValue(0) != StringRef(BoundArch))
+      if (!BoundArch || A->getValue(0) != StringRef(BoundArch))
         continue;
 
       unsigned Index = Args.getBaseArgs().MakeIndex(A->getValue(1));
@@ -4253,10 +4257,19 @@ CudaToolChain::TranslateArgs(const llvm::opt::DerivedArgList &Args,
     DAL->append(A);
   }
 
-  DAL->AddJoinedArg(nullptr, Opts.getOption(options::OPT_march_EQ), BoundArch);
+  if (BoundArch)
+    DAL->AddJoinedArg(nullptr, Opts.getOption(options::OPT_march_EQ), BoundArch);
   return DAL;
 }
 
+Tool *CudaToolChain::buildAssembler() const {
+  return new tools::NVPTX::Assembler(*this);
+}
+
+Tool *CudaToolChain::buildLinker() const {
+  return new tools::NVPTX::Linker(*this);
+}
+
 /// XCore tool chain
 XCoreToolChain::XCoreToolChain(const Driver &D, const llvm::Triple &Triple,
                                const ArgList &Args)