java cuMemcpyDtoH生成CUDA_错误_无效_值

Question

我有一个非常简单的scala jcuda程序，它添加了一个非常大的数组。在我想将超过4字节的数据从设备复制到主机之前，一切都可以正常编译和运行。当我试图复制超过4个字节时，我得到了CUDA_ERROR_INVALID_值

// This does pukes and gives CUDA_ERROR_INVALID_VALUE
var hostOutput = new Array[Int](numElements)
cuMemcpyDtoH(
  Pointer.to(hostOutput),
  deviceOutput,
  8
)

// This runs just fine
var hostOutput = new Array[Int](numElements)
cuMemcpyDtoH(
  Pointer.to(hostOutput),
  deviceOutput,
  4
)

为了更好地了解实际程序的上下文，下面是我的内核代码，它编译和运行得很好：

extern "C"
__global__ void add(int n, int *a, int *b, int *sum) {
    int i = blockIdx.x * blockDim.x + threadIdx.x;
    if (i<n)
    {
        sum[i] = a[i] + b[i];
    }
}

然后我还将一些java示例代码翻译成scala代码。总之，下面是运行的整个程序：

package dev

import jcuda.driver.JCudaDriver._

import jcuda._
import jcuda.driver._
import jcuda.runtime._

/**
 * Created by dev on 6/7/15.
 */
object TestCuda {
  def init = {
    JCudaDriver.setExceptionsEnabled(true)

    // Input vector

    // Output vector

    // Load module
    // Load the ptx file.

    val kernelPath = "/home/dev/IdeaProjects/jniopencl/src/main/resources/kernels/JCudaVectorAddKernel30.cubin"

    cuInit(0)

    val device = new CUdevice
    cuDeviceGet(device, 0)
    val context = new CUcontext
    cuCtxCreate(context, 0, device)

    // Create and load module
    val module = new CUmodule()
    cuModuleLoad(module, kernelPath)

    // Obtain a function pointer to the kernel function.
    var add = new CUfunction()
    cuModuleGetFunction(add, module, "add")

    val numElements = 100000

    val hostInputA = 1 to numElements toArray
    val hostInputB = 1 to numElements toArray
    val SI: Int = Sizeof.INT.asInstanceOf[Int]

    // Allocate the device input data, and copy
    // the host input data to the device
    var deviceInputA = new CUdeviceptr
    cuMemAlloc(deviceInputA, numElements * SI)
    cuMemcpyHtoD(
      deviceInputA,
      Pointer.to(hostInputA),
      numElements * SI
    )

    var deviceInputB = new CUdeviceptr
    cuMemAlloc(deviceInputB, numElements * SI)
    cuMemcpyHtoD(
      deviceInputB,
      Pointer.to(hostInputB),
      numElements * SI
    )

    // Allocate device output memory
    val deviceOutput = new CUdeviceptr()
    cuMemAlloc(deviceOutput, SI)

    // Set up the kernel parameters: A pointer to an array
    // of pointers which point to the actual values.
    val kernelParameters = Pointer.to(
      Pointer.to(Array[Int](numElements)),
      Pointer.to(deviceInputA),
      Pointer.to(deviceInputB),
      Pointer.to(deviceOutput)
    )

    // Call the kernel function
    val blockSizeX = 256
    val gridSizeX = Math.ceil(numElements / blockSizeX).asInstanceOf[Int]
    cuLaunchKernel(
      add,
      gridSizeX, 1, 1,
      blockSizeX, 1, 1,
      0, null,
      kernelParameters, null
    )

    cuCtxSynchronize

    // **** Code pukes here with that error
    // If I comment this out the program runs fine
    var hostOutput = new Array[Int](numElements)
    cuMemcpyDtoH(
      Pointer.to(hostOutput),
      deviceOutput,
      numElements
    )

    hostOutput.foreach(print(_))
  }
}

总之，我只是想让你知道我电脑的规格。我在optimus上运行Ubuntu14.04，安装了GTX 770M卡，支持计算3.0。我也在运行NVCC 5.5版。最后，我使用Java 8运行scala 2.11.6版。我是个笨蛋，非常感谢你的帮助