cudaMemcpy / cudaMalloc

[andreaaz]

Sorry for my english…
I have in a kernel’s function with cudaMemCopy:

cudaMemcpy(hackbuff, header, sizeof(char)*12, cudaMemcpyDeviceToDevice);

and i have the error:

calling a host function from a device/global function is
only allowed in device emulation mode
cudaMemcpy(hackbuff, header, sizeof(char)*12, cudaMemcpyDeviceToDevice);

i can’t call cudaMemcpy or cudaMalloc in the kernel function?

Thanks

[seibert]

That is correct. You can only allocate memory on the device from the host, and then pass the pointer to your kernel.

[andreaaz]

That is correct.  You can only allocate memory on the device from the host, and then pass the pointer to your kernel.

[snapback]362829[/snapback]

Thank you :)