cudaMemcpy2DFromArray -- docs unclear

[jmutch]

I just tracked down a bug that resulted from my thinking that the “srcX” parameter in this function was an element index, where in fact it is a byte position within its row.

cudaError_t cudaMemcpy2DFromArray(

void* dst, size_t dpitch,

const struct cudaArray* srcArray,

size_t srcX, size_t srcY,

size_t width, size_t height,

enum cudaMemcpyKind kind);

copies a matrix (height rows of width bytes each) from the CUDA array srcArray starting at the upper left corner (srcX, srcY) to the memory area pointed to by dst, where kind is one of cudaMemcpyHostToHost, cudaMemcpyHostToDevice, cudaMemcpyDeviceToHost, or cudaMemcpyDeviceToDevice, and specifies the direction of the copy. dpitch is the width in memory in bytes of the 2D array pointed to by dst, including any padding added to the end of each row (see Section D.3.2).

I think I assumed it would be an element index because when you use cudaMallocArray to create the array, you specify a number of elements, not a number of bytes. And the doc doesn’t explicitly say.

There are probably a few functions for which this should be clarified in the docs.

Jim

[kristleifur]

I just tracked down a bug that resulted from my thinking that the “srcX” parameter in this function was an element index, where in fact it is a byte position within its row.

I think I assumed it would be an element index because when you use cudaMallocArray to create the array, you specify a number of elements, not a number of bytes.  And the doc doesn’t explicitly say.

There are probably a few functions for which this should be clarified in the docs.

Jim

[snapback]232957[/snapback]

Nice, thanks!