“With the advent of massively parallel computing coprocessors, numerical optimization for deep-learning disciplines is now possible. Complex real-time pattern recognition, for example, that can be used for self driving cars and augmented reality can be developed and high performance achieved with the use of specialized, highly tuned libraries. By just using the Message Passing Interface (MPI) API, very high performance can be attained on hundreds to thousands of Intel Xeon Phi processors.”
In this video from the 2014 Argonne Training Program on Extreme-Scale Computing, Bill Gropp from NCSA presents: Cost of Unintended Synchronization. “At ATPESC 2014, we captured 67 hours of lectures in 86 videos of presentations by pioneers and elites in the HPC community on topics ranging from programming techniques and numerical algorithms best suited for leading-edge HPC systems to trends in HPC architectures and software most likely to provide performance portability through the next decade and beyond.”
A new MPI book is available for pre-order on Amazon. Written by William Gropp, Torsten Hoefler, Ewing Lusk, and Rajeev Thakur, Using Advanced MPI: Modern Features of the Message-Passing Interface offers a practical guide to the advanced features of the MPI (Message-Passing Interface) standard library for writing programs for parallel computers. It covers new features added in MPI-3, the latest version of the MPI standard, and updates from MPI-2.
“MPI is in the national interest. The U.S. government tasks Lawrence Livermore National Laboratory with solving the nation’s and the world’s most difficult problems. This ranges from global security, disaster response and planning, drug discovery, energy production, and climate change to name a few. To meet this challenge, LLNL scientists utilize large-scale computer simulations on Linux clusters with Infiniband networks. As such, MVAPICH serves a critical role in this effort. In this talk, I will highlight some of this recent work that MVAPICH has enabled.”