r253387 - [CUDA] Detect and link with CUDA's libdevice bitcode library.
Artem Belevich via cfe-commits
cfe-commits at lists.llvm.org
Tue Nov 17 14:28:50 PST 2015
Author: tra
Date: Tue Nov 17 16:28:50 2015
New Revision: 253387
URL: http://llvm.org/viewvc/llvm-project?rev=253387&view=rev
Log:
[CUDA] Detect and link with CUDA's libdevice bitcode library.
- added detection of libdevice bitcode file and API to find one appropriate for the GPU we're compiling for.
- pass additional cc1 options for linking with detected libdevice bitcode
- added -nocudalib to prevent automatic linking with libdevice
- added test cases to verify new functionality
Differential Revision: http://reviews.llvm.org/D14556
Added:
cfe/trunk/test/Driver/Inputs/CUDA/usr/local/cuda/nvvm/libdevice/libdevice.compute_20.10.bc
- copied, changed from r253386, cfe/trunk/test/Driver/Inputs/CUDA/usr/local/cuda/nvvm/libdevice/.keep
cfe/trunk/test/Driver/Inputs/CUDA/usr/local/cuda/nvvm/libdevice/libdevice.compute_35.10.bc
- copied, changed from r253386, cfe/trunk/test/Driver/Inputs/CUDA/usr/local/cuda/nvvm/libdevice/.keep
Removed:
cfe/trunk/test/Driver/Inputs/CUDA/usr/local/cuda/nvvm/libdevice/.keep
Modified:
cfe/trunk/include/clang/Driver/Options.td
cfe/trunk/lib/Driver/ToolChains.cpp
cfe/trunk/lib/Driver/ToolChains.h
cfe/trunk/test/Driver/cuda-detect.cu
Modified: cfe/trunk/include/clang/Driver/Options.td
URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/include/clang/Driver/Options.td?rev=253387&r1=253386&r2=253387&view=diff
==============================================================================
--- cfe/trunk/include/clang/Driver/Options.td (original)
+++ cfe/trunk/include/clang/Driver/Options.td Tue Nov 17 16:28:50 2015
@@ -1597,6 +1597,7 @@ def no__dead__strip__inits__and__terms :
def nobuiltininc : Flag<["-"], "nobuiltininc">, Flags<[CC1Option]>,
HelpText<"Disable builtin #include directories">;
def nocudainc : Flag<["-"], "nocudainc">;
+def nocudalib : Flag<["-"], "nocudalib">;
def nodefaultlibs : Flag<["-"], "nodefaultlibs">;
def nofixprebinding : Flag<["-"], "nofixprebinding">;
def nolibc : Flag<["-"], "nolibc">;
Modified: cfe/trunk/lib/Driver/ToolChains.cpp
URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/lib/Driver/ToolChains.cpp?rev=253387&r1=253386&r2=253387&view=diff
==============================================================================
--- cfe/trunk/lib/Driver/ToolChains.cpp (original)
+++ cfe/trunk/lib/Driver/ToolChains.cpp Tue Nov 17 16:28:50 2015
@@ -1647,6 +1647,31 @@ void Generic_GCC::CudaInstallationDetect
D.getVFS().exists(CudaLibDevicePath)))
continue;
+ std::error_code EC;
+ for (llvm::sys::fs::directory_iterator LI(CudaLibDevicePath, EC), LE;
+ !EC && LI != LE; LI = LI.increment(EC)) {
+ StringRef FilePath = LI->path();
+ StringRef FileName = llvm::sys::path::filename(FilePath);
+ // Process all bitcode filenames that look like libdevice.compute_XX.YY.bc
+ const StringRef LibDeviceName = "libdevice.";
+ if (!(FileName.startswith(LibDeviceName) && FileName.endswith(".bc")))
+ continue;
+ StringRef GpuArch = FileName.slice(
+ LibDeviceName.size(), FileName.find('.', LibDeviceName.size()));
+ CudaLibDeviceMap[GpuArch] = FilePath.str();
+ // Insert map entries for specifc devices with this compute capability.
+ if (GpuArch == "compute_20") {
+ CudaLibDeviceMap["sm_20"] = FilePath;
+ CudaLibDeviceMap["sm_21"] = FilePath;
+ } else if (GpuArch == "compute_30") {
+ CudaLibDeviceMap["sm_30"] = FilePath;
+ CudaLibDeviceMap["sm_32"] = FilePath;
+ } else if (GpuArch == "compute_35") {
+ CudaLibDeviceMap["sm_35"] = FilePath;
+ CudaLibDeviceMap["sm_37"] = FilePath;
+ }
+ }
+
IsValid = true;
break;
}
@@ -4195,6 +4220,22 @@ CudaToolChain::addClangTargetOptions(con
llvm::opt::ArgStringList &CC1Args) const {
Linux::addClangTargetOptions(DriverArgs, CC1Args);
CC1Args.push_back("-fcuda-is-device");
+
+ if (DriverArgs.hasArg(options::OPT_nocudalib))
+ return;
+
+ std::string LibDeviceFile = CudaInstallation.getLibDeviceFile(
+ DriverArgs.getLastArgValue(options::OPT_march_EQ));
+ if (!LibDeviceFile.empty()) {
+ CC1Args.push_back("-mlink-cuda-bitcode");
+ CC1Args.push_back(DriverArgs.MakeArgString(LibDeviceFile));
+
+ // Libdevice in CUDA-7.0 requires PTX version that's more recent
+ // than LLVM defaults to. Use PTX4.2 which is the PTX version that
+ // came with CUDA-7.0.
+ CC1Args.push_back("-target-feature");
+ CC1Args.push_back("+ptx42");
+ }
}
llvm::opt::DerivedArgList *
Modified: cfe/trunk/lib/Driver/ToolChains.h
URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/lib/Driver/ToolChains.h?rev=253387&r1=253386&r2=253387&view=diff
==============================================================================
--- cfe/trunk/lib/Driver/ToolChains.h (original)
+++ cfe/trunk/lib/Driver/ToolChains.h Tue Nov 17 16:28:50 2015
@@ -166,6 +166,7 @@ protected:
std::string CudaLibPath;
std::string CudaLibDevicePath;
std::string CudaIncludePath;
+ llvm::StringMap<std::string> CudaLibDeviceMap;
public:
CudaInstallationDetector(const Driver &D) : IsValid(false), D(D) {}
@@ -185,6 +186,9 @@ protected:
/// \brief Get the detected Cuda device library path.
StringRef getLibDevicePath() const { return CudaLibDevicePath; }
/// \brief Get libdevice file for given architecture
+ StringRef getLibDeviceFile(StringRef Gpu) const {
+ return CudaLibDeviceMap.lookup(Gpu);
+ }
};
CudaInstallationDetector CudaInstallation;
Removed: cfe/trunk/test/Driver/Inputs/CUDA/usr/local/cuda/nvvm/libdevice/.keep
URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/test/Driver/Inputs/CUDA/usr/local/cuda/nvvm/libdevice/.keep?rev=253386&view=auto
==============================================================================
(empty)
Copied: cfe/trunk/test/Driver/Inputs/CUDA/usr/local/cuda/nvvm/libdevice/libdevice.compute_20.10.bc (from r253386, cfe/trunk/test/Driver/Inputs/CUDA/usr/local/cuda/nvvm/libdevice/.keep)
URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/test/Driver/Inputs/CUDA/usr/local/cuda/nvvm/libdevice/libdevice.compute_20.10.bc?p2=cfe/trunk/test/Driver/Inputs/CUDA/usr/local/cuda/nvvm/libdevice/libdevice.compute_20.10.bc&p1=cfe/trunk/test/Driver/Inputs/CUDA/usr/local/cuda/nvvm/libdevice/.keep&r1=253386&r2=253387&rev=253387&view=diff
==============================================================================
(empty)
Copied: cfe/trunk/test/Driver/Inputs/CUDA/usr/local/cuda/nvvm/libdevice/libdevice.compute_35.10.bc (from r253386, cfe/trunk/test/Driver/Inputs/CUDA/usr/local/cuda/nvvm/libdevice/.keep)
URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/test/Driver/Inputs/CUDA/usr/local/cuda/nvvm/libdevice/libdevice.compute_35.10.bc?p2=cfe/trunk/test/Driver/Inputs/CUDA/usr/local/cuda/nvvm/libdevice/libdevice.compute_35.10.bc&p1=cfe/trunk/test/Driver/Inputs/CUDA/usr/local/cuda/nvvm/libdevice/.keep&r1=253386&r2=253387&rev=253387&view=diff
==============================================================================
(empty)
Modified: cfe/trunk/test/Driver/cuda-detect.cu
URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/test/Driver/cuda-detect.cu?rev=253387&r1=253386&r2=253387&view=diff
==============================================================================
--- cfe/trunk/test/Driver/cuda-detect.cu (original)
+++ cfe/trunk/test/Driver/cuda-detect.cu Tue Nov 17 16:28:50 2015
@@ -8,26 +8,51 @@
// RUN: %clang -v --target=i386-unknown-linux \
// RUN: --sysroot=%S/Inputs/CUDA 2>&1 | FileCheck %s
// RUN: %clang -v --target=i386-unknown-linux \
+// RUN: --sysroot=%S/Inputs/CUDA 2>&1 | FileCheck %s
+// RUN: %clang -v --target=i386-unknown-linux \
// RUN: --cuda-path=%S/Inputs/CUDA/usr/local/cuda 2>&1 | FileCheck %s
-// Verify that CUDA include path gets added
+// Make sure we map libdevice bitcode files to proper GPUs.
+// RUN: %clang -### -v --target=i386-unknown-linux --cuda-gpu-arch=sm_21 \
+// RUN: --cuda-path=%S/Inputs/CUDA/usr/local/cuda %s 2>&1 \
+// RUN: | FileCheck %s -check-prefix COMMON \
+// RUN: -check-prefix LIBDEVICE -check-prefix LIBDEVICE21
// RUN: %clang -### -v --target=i386-unknown-linux --cuda-gpu-arch=sm_35 \
// RUN: --cuda-path=%S/Inputs/CUDA/usr/local/cuda %s 2>&1 \
-// RUN: | FileCheck %s -check-prefix COMMON -check-prefix CUDAINC
-// Verify that -nocudainc disables CUDA include paths.
+// RUN: | FileCheck %s -check-prefix COMMON -check-prefix CUDAINC \
+// RUN: -check-prefix LIBDEVICE -check-prefix LIBDEVICE35
+// Verify that -nocudainc prevents adding include path to CUDA headers.
// RUN: %clang -### -v --target=i386-unknown-linux --cuda-gpu-arch=sm_35 \
// RUN: -nocudainc --cuda-path=%S/Inputs/CUDA/usr/local/cuda %s 2>&1 \
-// RUN: | FileCheck %s -check-prefix COMMON -check-prefix NOCUDAINC
+// RUN: | FileCheck %s -check-prefix COMMON -check-prefix NOCUDAINC \
+// RUN: -check-prefix LIBDEVICE -check-prefix LIBDEVICE35
// We should not add any CUDA include paths if there's no valid CUDA installation
// RUN: %clang -### -v --target=i386-unknown-linux --cuda-gpu-arch=sm_35 \
// RUN: --cuda-path=%S/no-cuda-there %s 2>&1 \
// RUN: | FileCheck %s -check-prefix COMMON -check-prefix NOCUDAINC
+// Verify that no options related to bitcode linking are passes if
+// there's no bitcode file.
+// RUN: %clang -### -v --target=i386-unknown-linux --cuda-gpu-arch=sm_30 \
+// RUN: --cuda-path=%S/Inputs/CUDA/usr/local/cuda %s 2>&1 \
+// RUN: | FileCheck %s -check-prefix COMMON -check-prefix NOLIBDEVICE
+// .. or if we explicitly passed -nocudalib
+// RUN: %clang -### -v --target=i386-unknown-linux --cuda-gpu-arch=sm_35 \
+// RUN: -nocudalib --cuda-path=%S/Inputs/CUDA/usr/local/cuda %s 2>&1 \
+// RUN: | FileCheck %s -check-prefix COMMON -check-prefix NOLIBDEVICE
+
// CHECK: Found CUDA installation: {{.*}}/Inputs/CUDA/usr/local/cuda
// NOCUDA-NOT: Found CUDA installation:
// COMMON: "-triple" "nvptx-nvidia-cuda"
// COMMON-SAME: "-fcuda-is-device"
+// LIBDEVICE-SAME: "-mlink-cuda-bitcode"
+// NOLIBDEVICE-NOT: "-mlink-cuda-bitcode"
+// LIBDEVICE21-SAME: libdevice.compute_20.10.bc
+// LIBDEVICE35-SAME: libdevice.compute_35.10.bc
+// NOLIBDEVICE-NOT: libdevice.compute_{{.*}}.bc
+// LIBDEVICE-SAME: "-target-feature" "+ptx42"
+// NOLIBDEVICE-NOT: "-target-feature" "+ptx42"
// CUDAINC-SAME: "-internal-isystem" "{{.*}}/Inputs/CUDA/usr/local/cuda/include"
// NOCUDAINC-NOT: "-internal-isystem" "{{.*}}/cuda/include"
// COMMON-SAME: "-x" "cuda"
More information about the cfe-commits
mailing list