High Performance Parallelism Pearls Volume One

<p>1. Introduction2. Towards an efficient Godunov's scheme on Phi3. Better Concurrency and SIMD on HBM4. Case Study: Analyzing and Optimizing Concurrency5. Plesiochronous Phasing Barriers6. Parallel Evaluation of Fault Tree Expressions7. Deep-learning and Numerical Optimization8. Optimizing Gather/Scatter Patterns9. A many core implementation of the direct N-body problem10. N-body Methods on Intel® Xeon Phi™ Coprocessors11. Dynamic Load Balancing using OpenMP 4.012. Concurrent Kernel Offloading13. Heterogeneous Computing with MPI14. Power Analysis on the Intel® Xeon Phi™ Coprocessor15. Integrating Intel Xeon Phis into a Cluster16. Native File systems17. NWChem: Quantum Chemistry Simulations at Scale18. Efficient nested parallelism on large scale system19. Performance optimization of Black-Scholes pricing20. Host and Coprocessor Data Transfer through the COI21. High Performance Ray Tracing with Embree22. Portable and Perform with OpenCL23. Characterization and Auto-tuning of 3DFD.24. Profiling-guided optimization of cache performance25. Heterogeneous MPI optimization with ITAC26. Scalable Out-of-core Solvers on a Cluster27. Sparse matrix-vector multiplication: parallelization and vectorization28. Morton Order Improves Performance</p>