0

我有一个我正在编译的程序：

(...) Some ifort *.f -c
nvcc -c src/bicgstab.cu -o bicgstab.o -I/home/ricardo/apps/cusp/cusplibrary
(...) Some more *.for -c
ifort *.o -L/usr/local/cuda-5.5/lib64 -lcudart -lcublas -lcusparse -lmkl_intel_lp64 -lmkl_intel_thread -lmkl_core -openmp -o program

一切正常，直到我添加了 CUSP 支持，我有这个包装器（bicgstab.cu）：

#include <cusp/csr_matrix.h>
#include <cusp/krylov/bicgstab.h>

#if defined(__cplusplus)
extern "C" {
#endif

void bicgstab_(int * device_I, int * device_J, float * device_V, float * device_x, float * device_b, int N, int NNZ){

    // *NOTE* raw pointers must be wrapped with thrust::device_ptr!
    thrust::device_ptr<int> wrapped_device_I(device_I);
    thrust::device_ptr<int> wrapped_device_J(device_J);
    thrust::device_ptr<float> wrapped_device_V(device_V);
    thrust::device_ptr<float> wrapped_device_x(device_x);
    thrust::device_ptr<float> wrapped_device_b(device_b);

    // use array1d_view to wrap the individual arrays
    typedef typename cusp::array1d_view< thrust::device_ptr<int> > DeviceIndexArrayView;
    typedef typename cusp::array1d_view< thrust::device_ptr<float> > DeviceValueArrayView;

    DeviceIndexArrayView row_indices (wrapped_device_I, wrapped_device_I + (N+1));
    DeviceIndexArrayView column_indices(wrapped_device_J, wrapped_device_J + NNZ);
    DeviceValueArrayView values (wrapped_device_V, wrapped_device_V + NNZ);
    DeviceValueArrayView x (wrapped_device_x, wrapped_device_x + N);
    DeviceValueArrayView b (wrapped_device_b, wrapped_device_b + N);

    // combine the three array1d_views into a csr_matrix_view
    typedef cusp::csr_matrix_view<DeviceIndexArrayView,
    DeviceIndexArrayView,
    DeviceValueArrayView> DeviceView;

    // construct a csr_matrix_view from the array1d_views
    DeviceView A(N, N, NNZ, row_indices, column_indices, values);

    // set stopping criteria:
    // iteration_limit = 100
    // relative_tolerance = 1e-5
    cusp::verbose_monitor<float> monitor(b, 100, 1e-5);

    // solve the linear system A * x = b with the Conjugate Gradient method
    cusp::krylov::bicgstab(A, x, b, monitor);

}

#if defined(__cplusplus)
}
#endif

Nvcc 编译并生成对象，但是在最后一个命令中，当我将所有链接在一起时，由于链接出现了一堆错误：

ipo: warning #11021: unresolved __gxx_personality_v0
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZTVSt9exception
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZTVSt9bad_alloc
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZdlPv
        Referenced in bicgstab.o
ipo: warning #11021: unresolved __cxa_guard_acquire
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZNSaIcEC1Ev
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZNSsC1EPKcRKSaIcE
        Referenced in bicgstab.o
ipo: warning #11021: unresolved __cxa_guard_release
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZNSsD1Ev
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZNSaIcED1Ev
        Referenced in bicgstab.o
ipo: warning #11021: unresolved __cxa_guard_abort
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZNSsC1ERKSs
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZNSt13runtime_errorD2Ev
        Referenced in bicgstab.o
ipo: warning #11021: unresolved __cxa_call_unexpected
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZNSt13runtime_errorC2ERKSs
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZNSsC1Ev
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZNKSs5emptyEv
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZNKSt13runtime_error4whatEv
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZNSsaSEPKc
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZNSspLEPKc
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZNSspLERKSs
        Referenced in bicgstab.o
ipo: warning #11021: unresolved __cxa_begin_catch
        Referenced in bicgstab.o
ipo: warning #11021: unresolved __cxa_end_catch
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZNKSs5c_strEv
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZNKSt9bad_alloc4whatEv
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZNSt9bad_allocD2Ev
        Referenced in bicgstab.o
ipo: warning #11021: unresolved __cxa_allocate_exception
        Referenced in bicgstab.o
ipo: warning #11021: unresolved __cxa_free_exception
        Referenced in bicgstab.o
ipo: warning #11021: unresolved __cxa_throw
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZNSt9exceptionD2Ev
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZSt4cout
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZStlsISt11char_traitsIcEERSt13basic_ostreamIcT_ES5_PKc
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZNSolsEf
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZNSolsEm
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZSt4endlIcSt11char_traitsIcEERSt13basic_ostreamIT_T0_ES6_
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZNSolsEPFRSoS_E
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZSt9terminatev
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZStlsIcSt11char_traitsIcEERSt13basic_ostreamIT_T0_ES6_St5_Setw
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZNSolsEPFRSt8ios_baseS0_E
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZNSt9bad_allocD1Ev
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZTISt9bad_alloc
        Referenced in bicgstab.o
ipo: warning #11021: unresolved __cxa_pure_virtual
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZTVN10__cxxabiv120__si_class_type_infoE
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZTISt9exception
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZTISt13runtime_error
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZTVN10__cxxabiv117__class_type_infoE
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZNSt8ios_base4InitC1Ev
        Referenced in bicgstab.o
ipo: warning #11021: unresolved _ZNSt8ios_base4InitD1Ev
        Referenced in bicgstab.o

我相信这是因为 ifort 正在添加或删除下划线、添加小写/大写或其他任何内容，因为文件正在编译写入，并且如果我在程序外部生成二进制文件，只是为了测试，它工作得很好。

非常感谢您！

4

1 回答 1

2

当涉及多个文件时，ipo 相当复杂。它实际上是在链接时在所有模块上重新运行编译器。我不是这方面的专家，但这听起来像是相当困难的事情。

一种可能的选择可能是您尝试将您的 cuda 代码编译到共享库 (.so) 中并链接到它。它应该防止英特尔编译器工具链尝试重新编译和优化由 nvcc/gcc 生成的代码。我认为这会将您限制为“单文件优化”。不知道这是否会显着影响你的表现。

在这里使用我的示例，我将修改编译命令如下：

$ nvcc -Xcompiler="-fPIC" -shared bicgstab.cu -o bicgstab.so -I/home-2/robertc/misc/cusp/cusplibrary-master
$ ifort -c -fast bic.f90
$ ifort bic.o bicgstab.so -L/shared/apps/cuda/CUDA-v6.0.37/lib64 -lcudart  -o program
ipo: remark #11001: performing single-file optimizations
ipo: remark #11006: generating object file /tmp/ipo_ifortxEdpin.o
$

您没有指明在编译过程中的哪个位置添加-fast开关。如果仅在ifort编译命令上，我相信上述方法会起作用。如果您在链接命令中也需要/需要它，那么 ifort 似乎想要构建一个完全静态链接的可执行文件（并进行模块间优化......），使用上述过程将无法正常工作。

于 2014-06-28T16:36:40.393 回答