r277542 - [CUDA] Fix libdevice selection.

Artem Belevich via cfe-commits cfe-commits at lists.llvm.org
Tue Aug 2 16:48:58 PDT 2016


Sorry about that. I'll commit the fix shortly.

On Tue, Aug 2, 2016 at 4:33 PM, Bruno Cardoso Lopes <bruno.cardoso at gmail.com
> wrote:

> Hi Artem,
>
> This broke
> http://lab.llvm.org:8080/green/job/clang-stage1-cmake-RA-incremental_check/26856
> ,
> can you take a look?
>
> Thanks,
>
> On Tue, Aug 2, 2016 at 4:12 PM, Artem Belevich via cfe-commits
> <cfe-commits at lists.llvm.org> wrote:
> > Author: tra
> > Date: Tue Aug  2 18:12:51 2016
> > New Revision: 277542
> >
> > URL: http://llvm.org/viewvc/llvm-project?rev=277542&view=rev
> > Log:
> > [CUDA] Fix libdevice selection.
> >
> > This makes clang's libdevice selection match that of NVCC as described in
> >
> http://docs.nvidia.com/cuda/libdevice-users-guide/basic-usage.html#version-selection
> >
> > If required libdevice variant is not found, driver now fails with an
> error.
> >
> > Differential Revision: https://reviews.llvm.org/D23037
> >
> > Added:
> >
>  cfe/trunk/test/Driver/Inputs/CUDA_80/usr/local/cuda/nvvm/libdevice/libdevice.compute_30.10.bc
> > Modified:
> >     cfe/trunk/include/clang/Basic/DiagnosticDriverKinds.td
> >     cfe/trunk/lib/Driver/ToolChains.cpp
> >     cfe/trunk/test/Driver/cuda-detect.cu
> >
> > Modified: cfe/trunk/include/clang/Basic/DiagnosticDriverKinds.td
> > URL:
> http://llvm.org/viewvc/llvm-project/cfe/trunk/include/clang/Basic/DiagnosticDriverKinds.td?rev=277542&r1=277541&r2=277542&view=diff
> >
> ==============================================================================
> > --- cfe/trunk/include/clang/Basic/DiagnosticDriverKinds.td (original)
> > +++ cfe/trunk/include/clang/Basic/DiagnosticDriverKinds.td Tue Aug  2
> 18:12:51 2016
> > @@ -26,6 +26,9 @@ def err_drv_cuda_bad_gpu_arch : Error<"U
> >  def err_drv_no_cuda_installation : Error<
> >    "cannot find CUDA installation.  Provide its path via --cuda-path, or
> pass "
> >    "-nocudainc to build without CUDA includes.">;
> > +def err_drv_no_cuda_libdevice : Error<
> > +  "cannot find libdevice for %0. Provide path to different CUDA
> installation "
> > +  "via --cuda-path, or pass -nocudalib to build without linking with
> libdevice.">;
> >  def err_drv_cuda_version_too_low : Error<
> >    "GPU arch %1 requires CUDA version at least %3, but installation at
> %0 is %2. "
> >    "Use --cuda-path to specify a different CUDA install, or pass "
> >
> > Modified: cfe/trunk/lib/Driver/ToolChains.cpp
> > URL:
> http://llvm.org/viewvc/llvm-project/cfe/trunk/lib/Driver/ToolChains.cpp?rev=277542&r1=277541&r2=277542&view=diff
> >
> ==============================================================================
> > --- cfe/trunk/lib/Driver/ToolChains.cpp (original)
> > +++ cfe/trunk/lib/Driver/ToolChains.cpp Tue Aug  2 18:12:51 2016
> > @@ -1791,22 +1791,32 @@ void Generic_GCC::CudaInstallationDetect
> >            LibDeviceName.size(), FileName.find('.',
> LibDeviceName.size()));
> >        LibDeviceMap[GpuArch] = FilePath.str();
> >        // Insert map entries for specifc devices with this compute
> capability.
> > +      // NVCC's choice of libdevice library version is rather peculiar:
> > +      //
> http://docs.nvidia.com/cuda/libdevice-users-guide/basic-usage.html#version-selection
> > +      // TODO: this will need to be updated once CUDA-8 is released.
> >        if (GpuArch == "compute_20") {
> >          LibDeviceMap["sm_20"] = FilePath;
> >          LibDeviceMap["sm_21"] = FilePath;
> > +        LibDeviceMap["sm_32"] = FilePath;
> >        } else if (GpuArch == "compute_30") {
> >          LibDeviceMap["sm_30"] = FilePath;
> > -        LibDeviceMap["sm_32"] = FilePath;
> > -      } else if (GpuArch == "compute_35") {
> > -        LibDeviceMap["sm_35"] = FilePath;
> > -        LibDeviceMap["sm_37"] = FilePath;
> > -      } else if (GpuArch == "compute_50") {
> > +        // compute_30 is the fallback libdevice variant for sm_30+,
> > +        // unless CUDA specifies different version for specific GPU
> > +        // arch.
> >          LibDeviceMap["sm_50"] = FilePath;
> >          LibDeviceMap["sm_52"] = FilePath;
> >          LibDeviceMap["sm_53"] = FilePath;
> > +        // sm_6? are currently all aliases for sm_53 in LLVM and
> > +        // should use compute_30.
> >          LibDeviceMap["sm_60"] = FilePath;
> >          LibDeviceMap["sm_61"] = FilePath;
> >          LibDeviceMap["sm_62"] = FilePath;
> > +      } else if (GpuArch == "compute_35") {
> > +        LibDeviceMap["sm_35"] = FilePath;
> > +        LibDeviceMap["sm_37"] = FilePath;
> > +      } else if (GpuArch == "compute_50") {
> > +        // NVCC does not use compute_50 libdevice at all at the moment.
> > +        // The version that's shipped with CUDA-7.5 is a copy of
> compute_30.
> >        }
> >      }
> >
> > @@ -4759,18 +4769,23 @@ CudaToolChain::addClangTargetOptions(con
> >    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");
> > +  StringRef GpuArch = DriverArgs.getLastArgValue(options::OPT_march_EQ);
> > +  assert(!GpuArch.empty() && "Must have an explicit GPU arch.");
> > +  std::string LibDeviceFile =
> CudaInstallation.getLibDeviceFile(GpuArch);
> > +
> > +  if (LibDeviceFile.empty()) {
> > +    getDriver().Diag(diag::err_drv_no_cuda_libdevice) << GpuArch;
> > +    return;
> >    }
> > +
> > +  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");
> >  }
> >
> >  void CudaToolChain::AddCudaIncludeArgs(const ArgList &DriverArgs,
> >
> > Added:
> cfe/trunk/test/Driver/Inputs/CUDA_80/usr/local/cuda/nvvm/libdevice/libdevice.compute_30.10.bc
> > URL:
> http://llvm.org/viewvc/llvm-project/cfe/trunk/test/Driver/Inputs/CUDA_80/usr/local/cuda/nvvm/libdevice/libdevice.compute_30.10.bc?rev=277542&view=auto
> >
> ==============================================================================
> >     (empty)
> >
> > Modified: cfe/trunk/test/Driver/cuda-detect.cu
> > URL:
> http://llvm.org/viewvc/llvm-project/cfe/trunk/test/Driver/cuda-detect.cu?rev=277542&r1=277541&r2=277542&view=diff
> >
> ==============================================================================
> > --- cfe/trunk/test/Driver/cuda-detect.cu (original)
> > +++ cfe/trunk/test/Driver/cuda-detect.cu Tue Aug  2 18:12:51 2016
> > @@ -10,15 +10,41 @@
> >  // RUN: %clang -v --target=i386-unknown-linux \
> >  // RUN:   --cuda-path=%S/Inputs/CUDA/usr/local/cuda 2>&1 | FileCheck %s
> >
> > -// Make sure we map libdevice bitcode files to proper GPUs.
> > +// Make sure we map libdevice bitcode files to proper GPUs. These
> > +// tests use Inputs/CUDA_80 which has full set of libdevice files.
> > +// However, libdevice mapping only matches CUDA-7.x at the moment.
> > +// sm_2x, sm_32 -> compute_20
> >  // 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:   --cuda-path=%S/Inputs/CUDA_80/usr/local/cuda %s 2>&1 \
> > +// RUN:   | FileCheck %s -check-prefix COMMON \
> > +// RUN:     -check-prefix LIBDEVICE -check-prefix LIBDEVICE20
> > +// RUN: %clang -### -v --target=i386-unknown-linux
> --cuda-gpu-arch=sm_32 \
> > +// RUN:   --cuda-path=%S/Inputs/CUDA_80/usr/local/cuda %s 2>&1 \
> > +// RUN:   | FileCheck %s -check-prefix COMMON \
> > +// RUN:     -check-prefix LIBDEVICE -check-prefix LIBDEVICE20
> > +// sm_30, sm_5x and sm_6x map to compute_30
> > +// RUN: %clang -### -v --target=i386-unknown-linux
> --cuda-gpu-arch=sm_30 \
> > +// RUN:   --cuda-path=%S/Inputs/CUDA_80/usr/local/cuda %s 2>&1 \
> >  // RUN:   | FileCheck %s -check-prefix COMMON \
> > -// RUN:     -check-prefix LIBDEVICE -check-prefix LIBDEVICE21
> > +// RUN:     -check-prefix LIBDEVICE -check-prefix LIBDEVICE30
> > +// RUN: %clang -### -v --target=i386-unknown-linux
> --cuda-gpu-arch=sm_50 \
> > +// RUN:   --cuda-path=%S/Inputs/CUDA_80/usr/local/cuda %s 2>&1 \
> > +// RUN:   | FileCheck %s -check-prefix COMMON \
> > +// RUN:     -check-prefix LIBDEVICE -check-prefix LIBDEVICE30
> > +// RUN: %clang -### -v --target=i386-unknown-linux
> --cuda-gpu-arch=sm_60 \
> > +// RUN:   --cuda-path=%S/Inputs/CUDA_80/usr/local/cuda %s 2>&1 \
> > +// RUN:   | FileCheck %s -check-prefix COMMON \
> > +// RUN:     -check-prefix LIBDEVICE -check-prefix LIBDEVICE30
> > +// sm_35 and sm_37 -> compute_35
> >  // 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:   --cuda-path=%S/Inputs/CUDA_80/usr/local/cuda %s 2>&1 \
> >  // RUN:   | FileCheck %s -check-prefix COMMON -check-prefix CUDAINC \
> >  // RUN:     -check-prefix LIBDEVICE -check-prefix LIBDEVICE35
> > +// RUN: %clang -### -v --target=i386-unknown-linux
> --cuda-gpu-arch=sm_37 \
> > +// RUN:   --cuda-path=%S/Inputs/CUDA_80/usr/local/cuda %s 2>&1 \
> > +// 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 \
> > @@ -29,12 +55,13 @@
> >  // 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.
> > +// Verify that we get an error if there's no libdevice library to link
> with.
> > +// NOTE: Inputs/CUDA deliberately does *not* have libdevice.compute_30
> for this purpose.
> >  // 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:   | FileCheck %s -check-prefix COMMON -check-prefix
> MISSINGLIBDEVICE
> > +
> > +// Verify that  -nocudalib prevents linking libdevice bitcode in.
> >  // 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
> > @@ -48,16 +75,19 @@
> >  // CHECK: Found CUDA installation: {{.*}}/Inputs/CUDA/usr/local/cuda
> >  // NOCUDA-NOT: Found CUDA installation:
> >
> > +// MISSINGLIBDEVICE: error: cannot find libdevice for sm_30.
> > +
> >  // 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
> > +// LIBDEVICE20-SAME: libdevice.compute_20.10.bc
> > +// LIBDEVICE30-SAME: libdevice.compute_30.10.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"
> > +// CUDAINC-SAME: "-internal-isystem"
> "{{.*}}/Inputs/CUDA{{[_0-9]+}}/usr/local/cuda/include"
> >  // NOCUDAINC-NOT: "-internal-isystem" "{{.*}}/cuda/include"
> >  // CUDAINC-SAME: "-include" "__clang_cuda_runtime_wrapper.h"
> >  // NOCUDAINC-NOT: "-include" "__clang_cuda_runtime_wrapper.h"
> >
> >
> > _______________________________________________
> > cfe-commits mailing list
> > cfe-commits at lists.llvm.org
> > http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
>
>
>
> --
> Bruno Cardoso Lopes
> http://www.brunocardoso.cc
>



-- 
--Artem Belevich
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20160802/3a8a0b04/attachment-0001.html>


More information about the cfe-commits mailing list