Access violation reading location

Accelerated Computing CUDA CUDA Programming and Performance
1

Hi,

I am getting the following error when I try to run my program:

Unhandled exception at 0x00401eca in template.exe: 0xC0000005: Access violation reading location 0x20104000.

float *t_list_device;

cudaMalloc((void **)&t_list_device, 2001*sizeof(float));

cudaMulC_32f<<< intNumOfBlocks, intNumOfThreads >>>

    (o_device, t_list_device[q], t_device, 100);

__global__ void

cudaMulC_32f( float* cuSrc, float val, float* cuDst, int len)

{

	int idx = blockIdx.x * blockDim.x + threadIdx.x;

	if (idx < len)

	{

  cuDst[idx] = cuSrc[idx] * val;

	}

	__syncthreads();

} // End of cudaMulC_32f

The location 0x20104000 points to t_list_device. There was no error in the cudaMalloc and cudaMemcpy.

What is the limit value in cudaMalloc?