“A parallel implementation of SpMV can be implemented, using OpenMP directives. However, by allocating memory for each core, data races can be eliminated and data locality can be exploited, leading to higher performance. Besides running on the main CPU, vectorization can be implemented on the Intel Xeon Phi coprocessor. By blocking the data in various chunks, various implementations on the Intel Xeon Phi coprocessor can be run and evaluated.”
Rich Brueckner from insideHPC moderated this panel discussion on current trends in HPC. “President Obama’s Executive Order establishing the National Strategic Computing Initiative (NSCI) will set the stage for a new chapter in leadership computing for the United States. In this panel discussion, thought leaders from leading supercomputing vendors share their perspectives on current HPC trends and the way forward.”
Jack Dongarra from the University of Tennessee will keynote the first-ever Intel HPC Developer Conference, Nov. 14-15 in Austin, Texas. “The Intel HPC Developer Conference offers high levels of access. This is your best opportunity to connect with Intel architecture experts, meet HPC industry leaders, and build a lasting network of peers. This is your best opportunity to connect with Intel architecture experts, meet HPC industry leaders, and build a lasting network of peers. The conference will also offer insights into the future of HPC with Intel experts on visualization, machine learning, software tools and much more.”
One of the most used algorithms in numerical simulation is the solving of large, dense matrices. Thermal analysis, boundary element methods and electromagnetic wave calculations all depend on the ability to solve these large matrices as fast as possible. The ability to use a coprocessor such as the Intel Xeon Phi coprocessor will greatly speed up these calculations.
Linding Lab at the University of Copenhagen used an SGI UV system to discover how genetic diseases such as cancer systematically attack the networks controlling human cells. By developing advanced algorithms to integrate data from quantitative mass-spectrometry and next generation sequencing of tumor samples, the UCPH researchers have been able to uncover cancer related changes to phospho-signaling networks at a global scale. The studies are some of the early results of the strategic collaboration between SGI and the Linding Lab at UCPH. The landmark findings have been published in two back-to-back papers in today’s Cell journal.
Last week, SC15 announced that Diane Bryant, senior vice president and general manager of Intel’s Data Center Group, has been selected as the HPC Matters plenary speaker. Recently named as one of Fortune’s Most Powerful Women, Bryant offers her perspectives on high performance computing, U.S. competitiveness, and the goal of reaching Exascale.
Today SGI and IT4Innovations national supercomputing center in the Czech Republic announced the deployment of the Salomon supercomputer. With a peak performance of 2 Petaflops, the Salomon supercomputer is twenty times more powerful than its predecessor and is the most powerful supercomputer in Europe running on the Xeon Phi coprocessors.
“Starting in 2013, the SC conference organizers launched “HPC Matters” to encourage members of the computational sciences community to share their thoughts, vision, and experiences with how high performance computers are used to improve the lives of people all over the world in more simple terms. Four pillars provide structure to the program: Influencing Daily Lives; Science and Engineering; Economic Impact; and Education.”
Through profiling, developers and users can get ideas on where an application’s hotspots are, in order to optimize certain sections of the code. In addition to locating where time is spent within an application, profiling tools can locate where there is little or no parallelism and a number of other factors that may affect performance. Performance tuning can help tremendously in many cases.