在抛出'cl::sycl::detail::exception_implementation<(cl::sycl::detail::exception_types)9>‘实例后终止调用

Question

我是SYCL/OpenCL/GPGPU的新手。我试图构建并运行常量加法程序的示例代码，

#include <iostream>
#include <array>
#include <algorithm>

#include <CL/sycl.hpp>

namespace sycl = cl::sycl;

//<<Define ConstantAdder>>
template<typename T, typename Acc, size_t N>
class ConstantAdder {
public:
  ConstantAdder(Acc accessor, T val)
    : accessor(accessor)
    , val(val) {}

  void operator() () {
    for (size_t i = 0; i < N; i++) {
      accessor[i] += val;
    }
  }

private:
  Acc accessor;
  const T val;
};

int main(int, char**) {
  std::array<int, 4> vals = {{ 1, 2, 3, 4 }};

  sycl::queue queue(sycl::cpu_selector{});
  std::cout << "Running on "
      << queue.get_device().get_info<sycl::info::device::name>()
      << "\n";

  {
    sycl::buffer<int, 1> buf(vals.data(), sycl::range<1>(4));
    queue.submit([&] (sycl::handler& cgh) {
    auto acc = buf.get_access<sycl::access::mode::read_write>(cgh);

    cgh.single_task(ConstantAdder<int, decltype(acc), 4>(acc, 1));
      } );
  }

  std::for_each(vals.begin(), vals.end(), [] (int i) { std::cout << i << " "; } );
  std::cout << std::endl;

  return 0;
}

我正在构建这段代码

$ g++ constantAdder_backup.cpp -g -std=c++11 -o constantAdder -I /usr/local/computecpp/include -I/usr/include/ -L /usr/local/computecpp/lib -lComputeCpp -L /usr/lib/x86_64-linux-gnu -lOpenCL

并得到错误

$ ./constantAdder
./constantAdder: /usr/local/cuda-8.0/lib64/libOpenCL.so.1: no version information available (required by /usr/local/computecpp/lib/libComputeCpp.so)
./constantAdder: /usr/local/cuda-8.0/lib64/libOpenCL.so.1: no version information available (required by /usr/local/computecpp/lib/libComputeCpp.so)\
./constantAdder: /usr/local/cuda-8.0/lib64/libOpenCL.so.1: no version information available (required by /usr/local/computecpp/lib/libComputeCpp.so)
Running on Intel(R) Core(TM) i7-4790 CPU @ 3.60GHz
terminate called after throwing an instance of 'cl::sycl::detail::exception_implementation<(cl::sycl::detail::exception_types)9, cl::sycl::detail::exception_implementation<(cl::sycl::detail::exception_types)6, cl::sycl::exception> >'
Aborted (core dumped)

是什么

在抛出'cl::sycl::detail::exception_implementation<(cl::sycl::detail::exception_types)9，cl::sycl::detail::exception_implementation<(cl::sycl::detail::exception_types)6，cl::sycl::exception> >的实例“中止(内核转储)错误意味着？我怎么才能解决这个问题？请帮帮我。

系统硬件是

$ /usr/local/computecpp/bin/computecpp_info 
/usr/local/computecpp/bin/computecpp_info: /usr/local/cuda-8.0/lib64/libOpenCL.so.1: no version information available (required by /usr/local/computecpp/bin/computecpp_info)
/usr/local/computecpp/bin/computecpp_info: /usr/local/cuda-8.0/lib64/libOpenCL.so.1: no version information available (required by /usr/local/computecpp/bin/computecpp_info)
********************************************************************************

ComputeCpp Info (CE 0.7.0)

********************************************************************************

Toolchain information:

GLIBC version: 2.19
GLIBCXX: 20150426
This version of libstdc++ is supported.

********************************************************************************


Device Info:

Discovered 3 devices matching:
  platform    : <any>
  device type : <any>

--------------------------------------------------------------------------------
Device 0:

  Device is supported                     : NO - Device does not support SPIR
  CL_DEVICE_NAME                          : GeForce GTX 750 Ti
  CL_DEVICE_VENDOR                        : NVIDIA Corporation
  CL_DRIVER_VERSION                       : 384.111
  CL_DEVICE_TYPE                          : CL_DEVICE_TYPE_GPU 
--------------------------------------------------------------------------------
Device 1:

  Device is supported                     : UNTESTED - Device not tested on this OS
  CL_DEVICE_NAME                          : Intel(R) HD Graphics
  CL_DEVICE_VENDOR                        : Intel(R) Corporation
  CL_DRIVER_VERSION                       : r5.0.63503
  CL_DEVICE_TYPE                          : CL_DEVICE_TYPE_GPU 
--------------------------------------------------------------------------------
Device 2:

  Device is supported                     : YES - Tested internally by Codeplay Software Ltd.
  CL_DEVICE_NAME                          : Intel(R) Core(TM) i7-4790 CPU @ 3.60GHz
  CL_DEVICE_VENDOR                        : Intel(R) Corporation
  CL_DRIVER_VERSION                       : 1.2.0.475
  CL_DEVICE_TYPE                          : CL_DEVICE_TYPE_CPU 

If you encounter problems when using any of these OpenCL devices, please consult
this website for known issues:
https://computecpp.codeplay.com/releases/v0.7.0/platform-support-notes

********************************************************************************

P.S.我更新了代码以了解我正在运行代码的设备。

修改的片段是

sycl::queue queue(sycl::cpu_selector{});

std::cout << "Running on "
    << queue.get_device().get_info<sycl::info::device::name>()
    << "\n";

现在我要使用cpu::selector (不是nvidia硬件)，并打印设备。它清楚地表明它正在Intel(R) Core(TM) i7-4790 CPU @ 3.60GHz上运行。输出.

couputecpp_info

显示

Device is supported                     : YES - Tested internally by Codeplay Software Ltd

但是，它仍然显示出了与

在抛出'cl::sycl::detail::exception_implementation<(cl::sycl::detail::exception_types)9，cl::sycl::detail::exception_implementation<(cl::sycl::detail::exception_types)6，cl::sycl::exception> >的实例“中止”后调用的终止(内核转储)

Answer 1

有一个异常类型cl::sycl::detail::exception_implementation<(cl::sycl::detail::exception_types)9, cl::sycl::detail::exception_implementation<(cl::sycl::detail::exception_types)6, cl::sycl::exception> >被抛出而没有被捕获。

若要查看异常的详细信息，请在主文件中添加“尝试捕获”，或在调试器中运行代码。例如：

int main(int, char**) {
  try
  {
     /*your code here*/
  }
  catch (std::exception& ex)
  {
    std::cerr << "exception caught: " << ex.what() << std::endl;
    return 1;
  }
  return 0;
}

Answer 2

生成代码时不使用SYCL编译器。可以使用以下命令来执行此操作。

/bin/compute++ constantAdder_backup.cpp -g -std=c++11 -o constantAdder -I /usr/local/computecpp/include -I/usr/include/ -L /usr/local/computecpp/lib -lComputeCpp -L /usr/lib/x86_64-linux-gnu -lOpenCL

您还需要确保在执行输出时将LD_LIBRARY_PATH设置为指向ComputeCpp安装的lib文件夹。

Answer 3

我注意到同样的错误，当cuda 9.2安装时，尝试卸载cuda并再次运行您的代码