cudaMemcpy3D invalid argument

Accelerated Computing CUDA CUDA Programming and Performance
1

Hi,

When I run the following code I get an invalid argument error at the line:

cutilSafeCall(cudaMemcpy3D(&copyParams2) );

Oddly, everything is fine in emulation mode.

What am I doing wrong?

Here is the code:

[codebox]const size_t nx = 541;

const size_t ny = 541;

const size_t nz = 114;

const size_t pad = 4;

dim3 dimBlock(16, 16, 1);

dim3 dimGrid(((nx-2pad)(ny-2*pad) -1)/ dimBlock.x+1, (nz-1)/ dimBlock.y+1, 1);

cudaChannelFormatDesc channelDesc = cudaCreateChannelDesc();

const cudaExtent textSize = make_cudaExtent(nx, ny, nz+2*pad);

cutilSafeCall( cudaMalloc3DArray(&d_volumeArray, &channelDesc, textSize) );

float* d_res;

cutilSafeCall(cudaMalloc((void**)&d_res, (nz+2pad)nxnysizeof(float)));

cutilSafeCall(cudaMemset(d_res, 0, nxny(nz+2*pad)*sizeof(float)));

setValKernel<<< dimGrid, dimBlock, 0 >>>(nx, ny, nz, d_res);

cutilSafeCall(cudaThreadSynchronize());

cudaMemcpy3DParms copyParams2 = {0};

copyParams2.srcPtr.ptr = d_res;

copyParams2.srcPtr.pitch = nx*sizeof(float);

copyParams2.srcPtr.xsize = nx;

copyParams2.srcPtr.ysize = ny;

copyParams2.dstArray = d_volumeArray;

copyParams2.extent = textSize;

copyParams2.kind = cudaMemcpyDeviceToDevice;

cutilSafeCall(cudaMemcpy3D(&copyParams2) );[/codebox]

here are my device properties:

Clock rate=1296000

Device overlap=1

Major=1

Minor=3

Max grid size=65535 65535 1

maxThreadsDim=512 512 64

maxThreadsPerBlock=512

memPitch=262144

multiProcessorCount=30

name=Tesla C1060

regsPerBlock=16384

sharedMemPerBlock=16384

textureAlignment=256

totalConstMem=65536

totalGlobalMem=4294705152

warpSize=32

Thanks for the help.

sd.