Re:An Even Easier Introduction to CUDA
by ape4 on Saturday February 04, 2017 @09:40AM
(#13567102)
Is there a preprocessor in the chain? Because
isn't regular C++. Sorry if I missed something.
[ Parent
| on HN ]
Re:An Even Easier Introduction to CUDA
by haldean on Saturday February 04, 2017 @10:23AM
(#13567224)
CUDA C++ is technically its own language, which is mostly implemented using a preprocessor; nvcc performs some translation and then passes generated C++ to your compiler of choice. The kernel launch syntax, along with a few implicit includes and macros for __device__ and __global__ are (afaik) the only things that really distinguish it from vanilla C++.
Re:An Even Easier Introduction to CUDA
by verandaguy on Saturday February 04, 2017 @02:22PM
(#13568516)
The triple angle bracket syntax is used to specify execution details when the device code's sent to the GPU -- the details are outlined under "Picking up the threads" in the OP.