多GPU，可用于同伴

Question

我有一些困难设置2 GPU，以使对等通信。我正在使用CUDA 4.0和FORTRAN编程。PGI编译器

我写了一个程序，该程序确认我的节点上有4个GPU。

我决定使用其中两个，但有以下错误： 0：DealLocate：无效设备指针。

subroutine  directTransfer()
        use cudafor
        implicit none
        integer, parameter :: N = 4*1024*1024
        real, pinned, allocatable :: a(:), b(:)
        real, device, allocatable :: a_d(:), b_d(:)

        !these hold free and total memory before and after
        !allocation, used to verify  allocation happening on proper devices
        integer (int_ptr_kind()),allocatable ::
     &   freeBefore(:), totalBefore(:),
     &   freeAfter(:), totalAfter(:)
        integer :: istat, nDevices, i, accessPeer, timingDev
        type(cudaDeviceProp)::prop
        type(cudaEvent)::startEvent,stopEvent
        real :: time
        !allocate host arrays
        allocate(a(N), b(N))
        allocate(freeBefore(0:nDevices -1),
     &      totalBefore(0:nDevices -1))
        allocate(freeAfter(0:nDevices -1),
     &      totalAfter(0:nDevices -1))
        write(*,*) 'Start!'
        !get devices ionfo (including total and free memory)
        !before allocation
        istat = cudaGetDeviceCount(nDevices)
        if(nDevices < 2) then
            write(*,*) 'Need at least two CUDA capable devices'
            stop
        end if
          write(*,"('Number of CUDA-capable devices: ',
     &       i0, /)"),nDevices
        do i = 0, nDevices - 1
            istat = cudaGetDeviceProperties(prop, i)
            istat = cudaSetDevice(i)
            istat = cudaMemGetInfo(freeBefore(i), totalBefore(i))
        end do
       !!!Here is the trouble zone!!!!
        istat = cudaSetDevice(0)
        allocate(a_d(N))
        istat = cudaSetDevice(1)
        allocate(b_d(N))

       deallocate(freeBefore, totalBefore,freeAfter,totalAfter)
       deallocate(a,b,a_d,b_d)
       end subroutine  directTransfer 

在以下我没有错误的情况下：

istat = cudaSetDevice(0)
allocate(a_d(N))
!istat = cudaSetDevice(1)
!allocate(b_d(N))

这样，也没有错误：

!istat = cudaSetDevice(0)
!allocate(a_d(N))
istat = cudaSetDevice(1)
allocate(b_d(N))

但是此返回错误

istat = cudaSetDevice(0)
allocate(a_d(N))
istat = cudaSetDevice(1)
allocate(b_d(N))

所以看来我无法设置2GPU来启动我的程序。您能帮我理解为什么无法设置2GPU并提示解决这个问题？

Answer 1

谢谢jackolantern !!

这是诀窍。我更改了代码如下，它可以完美地工作

!clean up      
deallocate(freeBefore, totalBefore,freeAfter,totalAfter)
istat = cudaSetDevice(0)
deallocate(a_d)
istat = cudaSetDevice(1)
deallocate(b_d)
deallocate(a,b)

这是我的问题答案。希望它能帮助他人。