Offloading & CUDA: Parallelism in C++ #3/3 (also OpenMP, OpenACC, GPU & Coprocessors like Xeon Phi)Computer programs can be made faster by making them do many things simultaneously. Let’s study three categorical ways to accomplish that in GCC. In the third episode, we study ways to offload code to various accelerators such as GPU on a graphics card. We also explore CUDA. The previous episode can be found at: https://www.youtube.com/watch?v=MfEkOcMILDo As a plot device in this tool-assisted ed
