Parallel Programming for Modern High Performance Computing Systems

This book describes the state-of-the-art computing devices and systems available, including multi-core CPUs, accelerators, such as GPUs, coprocessors, and clusters. It introduces approaches to parallelization using important programming paradigms, and covers the useful elements of the most popular APIs for programming parallel HPC systems.

Pawel Czanul

1. Understanding the Need for Parallel Computing 2. Overview of Selected Parallel and Distributed Systems for High Performance Computing 3. Typical Paradigms for Parallel Applications 4. Selected APIs for Parallel Programming 5. Programming Parallel Paradigms Using Selected APIS 6. Optimization Techniques and Best Practices for Parallel Codes Appendix A. Resources Appendix B. Further reading