I am not going to attempt to answer everything in this question, it is just too large. Having said that here are some observations about the code you posted which might help: The GPU side new operator allocates memory from a private runtime heap. As of CUDA 6, that memory cannot be accessed by the … Read more
As it was originally written, Thrust is purely a host side abstraction. It cannot be used inside kernels. You can pass the device memory encapsulated inside a thrust::device_vector to your own kernel like this: thrust::device_vector< Foo > fooVector; // Do something thrust-y with fooVector Foo* fooArray = thrust::raw_pointer_cast( fooVector.data() ); // Pass raw array and … Read more
I can think of 2 possibilities, one of which is suggested already by @JaredHoberock. I don’t know of a general methodology to fuse for-loop iterations in thrust, but the second method is the more general approach. My guess is that the first method would be the faster of the two approaches, in this case. Use … Read more