Question

我正在编写一个简单的测试代码，以了解如何包装包含openacc区域的fortran代码并从python调用。这是代码。

module test

 use iso_c_binding, only: sp => C_FLOAT, dp => C_DOUBLE, i8 => C_INT

 implicit none

 contains

  subroutine add (a, b, n, c)
      integer(kind=i8), intent(in)  :: n
      real(kind=dp), intent(in)  :: a(n)
      real(kind=dp), intent(in)  :: b(n)
      real(kind=dp), intent(out) :: c(n)

      integer(kind=i8)  :: i

      !$acc enter data create(a, b, c)

      do i = 1, n
          c(i) = a(i) + b(i)
      end do

      !$acc exit data delete(a, b, c)

  end subroutine add

  subroutine mult (a, b, c)
      real(kind=dp), intent(in)  :: a
      real(kind=dp), intent(in)  :: b
      real(kind=dp), intent(out) :: c

      c = a * b

  end subroutine mult

end module test

现在，如果我不使用openacc，它工作正常，我可以使用python中的add和mult。但是在我放入openacc区域之后，f2py编译得很好，但是当我尝试导入到python时，我收到以下错误

ImportError: /home/vikram/Experiments/Experiments/fortran_python/hello.cpython-35m-x86_64-linux-gnu.so: undefined symbol: GOACC_enter_exit_data

这似乎告诉我Python需要知道如何找到GOACC_enter_exit_data，我看到GOACC_enter_exit_data在libgomp.so.1中。我如何告诉python它的路径。

Answer 1

我决定通过编译链接来查看我直接创建的可执行文件。这样做

ldd a.out

给了我

linux-vdso.so.1 =>  (0x00007ffed24a0000)
libcublas.so.7.5 => /usr/local/cuda/lib64/libcublas.so.7.5 (0x00007f04c2d45000)
libcudart.so.7.5 => /usr/local/cuda/lib64/libcudart.so.7.5 (0x00007f04c2ae7000)
libgfortran.so.3 => /home//Experiments/Nvidia/OpenACC/OLCFHack15/gcc6/install/lib64/libgfortran.so.3 (0x00007f04c27c1000)
libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 (0x00007f04c24bb000)
libgomp.so.1 => /home//Experiments/Nvidia/OpenACC/OLCFHack15/gcc6/install/lib64/libgomp.so.1 (0x00007f04c228d000)
libgcc_s.so.1 => /home//Experiments/Nvidia/OpenACC/OLCFHack15/gcc6/install/lib64/libgcc_s.so.1 (0x00007f04c2077000)
libquadmath.so.0 => /home//Experiments/Nvidia/OpenACC/OLCFHack15/gcc6/install/lib64/libquadmath.so.0 (0x00007f04c1e38000)
libpthread.so.0 => /lib/x86_64-linux-gnu/libpthread.so.0 (0x00007f04c1c1a000)
libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 (0x00007f04c1855000)
librt.so.1 => /lib/x86_64-linux-gnu/librt.so.1 (0x00007f04c164d000)
libdl.so.2 => /lib/x86_64-linux-gnu/libdl.so.2 (0x00007f04c1449000)
libstdc++.so.6 => /home//Experiments/Nvidia/OpenACC/OLCFHack15/gcc6/install/lib64/libstdc++.so.6 (0x00007f04c10c9000)
/lib64/ld-linux-x86-64.so.2 (0x00007f04c4624000)

而f2py使用

创建的模块

f2py -c -m  --f90flags='-fopenacc -foffload=nvptx-none -foffload=-O3 -O3 - fPIC' hello hello.f90

给了我

linux-vdso.so.1 =>  (0x00007ffeeef63000)
libpython3.5m.so.1.0 => not found
libgfortran.so.3 => /home//Experiments/Nvidia/OpenACC/OLCFHack15/gcc6/install/lib64/libgfortran.so.3 (0x00007f841918f000)
libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 (0x00007f8418e89000)
libgcc_s.so.1 => /home//Experiments/Nvidia/OpenACC/OLCFHack15/gcc6/install/lib64/libgcc_s.so.1 (0x00007f8418c73000)
libquadmath.so.0 => /home//Experiments/Nvidia/OpenACC/OLCFHack15/gcc6/install/lib64/libquadmath.so.0 (0x00007f8418a34000)
libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 (0x00007f841866f000)
/lib64/ld-linux-x86-64.so.2 (0x00007f84196be000)

很明显，libgomp在可执行文件中被链接，但在f2py创建的对象中没有。所以我将f2py命令修改为

f2py -c -m  --f90flags='-fopenacc -foffload=nvptx-none -foffload=-O3 -O3 -fPIC' hello hello.f90 -L/usr/local/cuda/lib64 -lcublas -lcudart -lgomp

现在它编译了，我可以导入python而不会出现错误。

Answer 2

正如我通过邮件告诉您的那样，我终于设法通过f2py正确调用了acc_init和某些内核。我的代码目前还不是很正确，我仍然需要进行处理，但这是我用来调用f2py的CMakeLists.txt的一部分（基本上我添加了-L / data_local / sw / pgi / linuxpower / 19.9 / -L / usr / lib64 -L。-laccapi -laccg -laccn -laccg2 -ldl -lcudadevice -lpthread -lpgc -lm到f2py调用以下c - Linking a PGI OpenACC-enabled library with gcc中的说明）：

@Transactional(rollbackFor = Exception.class)
public void receiveInEventRequest(TransactionDto transactionDto) throws 
    InterruptedException, ExecutionException {
    // db insert    
    TransactionRequest transactionRequest = requestDbDumpService.dumpToDb(transactionDto);
    // kafka insert
    ListenableFuture<SendResult<String, TransactionDto>> kafkaResult = kafkaTemplate.send(kafkaProducerQueueName, “ID”, transactionDto);
    SendResult<String, TransactionDto> kafkaSendResult = kafkaResult.get();
}

事实上，我似乎只需要-laccn：

  set(OPENACC_Fortran_FLAGS -Mnorpath)
  list(APPEND OPENACC_Fortran_FLAGS -Minfo)
  list(APPEND OPENACC_Fortran_FLAGS -acc)
  list(APPEND OPENACC_Fortran_FLAGS -ta=tesla:nordc)
  list(APPEND OPENACC_Fortran_FLAGS -ta=tesla:cc60,cc70)
  list(APPEND OPENACC_Fortran_FLAGS -Mextend)
  list(APPEND OPENACC_Fortran_FLAGS -Mbackslash)
  list(APPEND OPENACC_Fortran_FLAGS -Mcuda=cuda10.1)
  list(APPEND OPENACC_Fortran_FLAGS -lcuda)
  set(EXTRA_Fortran_FLAGS ${OPENACC_Fortran_FLAGS})

    ## BUILD python wrapper
    add_custom_command(OUTPUT ${SOURCE_LIST_WRAP}
        COMMAND f90wrap -m my_module ${SOURCE_LIST_TO_WRAP}
        DEPENDS ${SOURCE_LIST_TO_WRAP})
    add_custom_target(_my_module ALL
      DEPENDS ${SOURCE_LIST_WRAP}
      COMMAND CC=gcc f2py --fcompiler=pg --f90flags="${EXTRA_Fortran_FLAGS}" -m _my_module -c ${SOURCE_LIST_WRAP} -L. -lmy_kernels_lib -L/data_local/sw/pgi/linuxpower/19.9/ -L/usr/lib64 -L. -laccapi -laccg -laccn -laccg2 -ldl -lcudadevice -lpthread  -lpgc -lm )

PS：这对于带有20.x的PGI 19.x是正确的，我需要更改标志：

add_custom_target(_my_module ALL
  DEPENDS ${SOURCE_LIST_WRAP}
  COMMAND CC=gcc f2py --fcompiler=pg  --f90flags="${EXTRA_Fortran_FLAGS}" -m _my_module -c ${SOURCE_LIST_WRAP} -L. -lmy_kernels_lib -laccn )

在OpenACC中使用F2Py会在Python中导致导入错误

2 个答案: