0

I read manual deep-copying of Fortran derived types is possible, but the following simple test program fails at run time; program compiled cleanly with PGI v16.10. What am getting wrong ?

program Test

    implicit none

    type dt
        integer :: n
        real, dimension(:), allocatable :: xm
    end type dt

    type(dt) :: grid
    integer :: i

    grid%n = 10
    allocate(grid%xm(grid%n))

!$acc enter data copyin(grid)
!$acc enter data pcreate(grid%xm)

!$acc kernels
   do i = 1, grid%n
      grid%xm(i) = i * i
   enddo
!$acc end kernels

   print*,grid%xm

end program Test

The error I am getting is:

call to cuStreamSynchronize returned error 700: Illegal address during kernel execution
call to cuMemFreeHost returned error 700: Illegal address during kernel execution
4

1 回答 1

1

您只需要在 kernels 指令上添加一个“present(grid)”子句。

这是您的程序示例，其中包含修复程序以及其他一些内容，例如更新数据以便可以将其打印在主机上。

% cat test.f90
program Test

    implicit none

    type dt
        integer :: n
        real, dimension(:), allocatable :: xm
    end type dt

    type(dt) :: grid
    integer :: i

    grid%n = 10
    allocate(grid%xm(grid%n))

!$acc enter data copyin(grid)
!$acc enter data create(grid%xm)
!$acc kernels present(grid)
   do i = 1, grid%n
      grid%xm(i) = i * i
   enddo
!$acc end kernels
!$acc update host(grid%xm)
   print*,grid%xm

!$acc exit data delete(grid%xm, grid)
   deallocate(grid%xm)

end program Test

% pgf90 -acc test.f90 -Minfo=accel -ta=tesla -V16.10; a.out
test:
     16, Generating enter data copyin(grid)
     17, Generating enter data create(grid%xm(:))
     18, Generating present(grid)
     19, Loop is parallelizable
         Accelerator kernel generated
         Generating Tesla code
         19, !$acc loop gang, vector(128) ! blockidx%x threadidx%x
     23, Generating update self(grid%xm(:))
    1.000000        4.000000        9.000000        16.00000
    25.00000        36.00000        49.00000        64.00000
    81.00000        100.0000

请注意，PGI 17.7 将在 Fortran 中包含对真正深拷贝的 beta 支持。与上面的手动深拷贝相反。下面是一个使用真正深拷贝的例子：

% cat test_deep.f90
program Test

    implicit none

    type dt
        integer :: n
        real, dimension(:), allocatable :: xm
    end type dt

    type(dt) :: grid
    integer :: i

    grid%n = 10
    allocate(grid%xm(grid%n))

!$acc enter data copyin(grid)
!$acc kernels present(grid)
   do i = 1, grid%n
      grid%xm(i) = i * i
   enddo
!$acc end kernels
!$acc update host(grid)
   print*,grid%xm

!$acc exit data delete(grid)
   deallocate(grid%xm)

end program Test

% pgf90 -acc test_deep.f90 -Minfo=accel -ta=tesla:deepcopy -V17.7 ; a.out
test:
     16, Generating enter data copyin(grid)
     17, Generating present(grid)
     18, Loop is parallelizable
         Accelerator kernel generated
         Generating Tesla code
         18, !$acc loop gang, vector(128) ! blockidx%x threadidx%x
     22, Generating update self(grid)
    1.000000        4.000000        9.000000        16.00000
    25.00000        36.00000        49.00000        64.00000
    81.00000        100.0000
于 2017-08-07T23:12:15.680 回答