If one attempts to pass a slice of an existing 1D GPUArray instance to a kernel compiled by SourceModule, an exception is raised because the gpudata member is a longint rather than a DeviceAllocation instance. Is there some way to obtain a slice of an existing GPUArray (without copying) that can be passed to a kernel?
(I'm using PyCUDA 0.94.2.)
L.G.
_______________________________________________
PyCUDA mailing list
PyCUDA@tiker.net
http://lists.tiker.net/listinfo/pycuda
