Harnessing the Power of Heterogeneous Computing using Boost.Compute + OpenCL
I presented this webinar on August 15th, 2018 as a part of a series of regular biweekly General Interest Webinars ran by SHARCNET.
The Boost Compute library provides a C++ interface to multi-core CPU and GPGPU computing platforms based on OpenCL. It provides a high-level, STL-like API and is portable to a wide variety of parallel accelerators including GPUs, FPGAs, and multi-core CPUs. This seminar gives an overview of the library and demonstrates how to write and execute high-performance C++ applications on SHARCNET clusters.