[CUDA] Added --[no-]cuda-include-ptx=sm_XX|all option.
Currently we always include PTX into the fatbin along
with the GPU code.It about doubles the size of the GPU binary
we need to carry in the executable. These options allow control
inclusion of PTX into GPU binary.
This patch does not change the defaults, though we may consider
making no-PTX the default in the future.
Differential Revision: https://reviews.llvm.org/D45495
llvm-svn: 329737
diff --git a/clang/lib/Driver/ToolChains/Cuda.cpp b/clang/lib/Driver/ToolChains/Cuda.cpp
index f383e01..c83d066 100644
--- a/clang/lib/Driver/ToolChains/Cuda.cpp
+++ b/clang/lib/Driver/ToolChains/Cuda.cpp
@@ -377,6 +377,22 @@
C.addCommand(llvm::make_unique<Command>(JA, *this, Exec, CmdArgs, Inputs));
}
+static bool shouldIncludePTX(const ArgList &Args, const char *gpu_arch) {
+ bool includePTX = true;
+ for (Arg *A : Args) {
+ if (!(A->getOption().matches(options::OPT_cuda_include_ptx_EQ) ||
+ A->getOption().matches(options::OPT_no_cuda_include_ptx_EQ)))
+ continue;
+ A->claim();
+ const StringRef ArchStr = A->getValue();
+ if (ArchStr == "all" || ArchStr == gpu_arch) {
+ includePTX = A->getOption().matches(options::OPT_cuda_include_ptx_EQ);
+ continue;
+ }
+ }
+ return includePTX;
+}
+
// All inputs to this linker must be from CudaDeviceActions, as we need to look
// at the Inputs' Actions in order to figure out which GPU architecture they
// correspond to.
@@ -404,6 +420,9 @@
"Device action expected to have associated a GPU architecture!");
CudaArch gpu_arch = StringToCudaArch(gpu_arch_str);
+ if (II.getType() == types::TY_PP_Asm &&
+ !shouldIncludePTX(Args, gpu_arch_str))
+ continue;
// We need to pass an Arch of the form "sm_XX" for cubin files and
// "compute_XX" for ptx.
const char *Arch =