Primeur magazine

Edition: flash - Issue: 2015-08-13

Blog

According to Xinhuanet, the supercomputer Tianhe-1A had to be shut down due to the blast in Tianjin Wednesday night. Tianhe-1A, located at the National Supercomputing Center in Tianjin, is just kilometers from the blast center. The shockwaves shattered windows at the center and caused collapsed ceilings inside the building, the center has told this to Xinhuanet. Read further...
David Pellerin, Dougal Ballantyne, Adam Boeglin from Amazon Web Services (AWS) did write a white paper "An Introduction to High Performance Computing on AWS". The paper describes a range of high performance computing (HPC) applications that are running today on Amazon Web Services (AWS). It lists best practices for cloud deployment, for cluster and job management, and for the management of third-party software. The whitepaper covers HPC use cases that include highly distributed, highly parallel grid computing applications, as well as more traditional cluster computing applications that require a high level of node-to-node communications. It also discusses HPC applications that require access to various types of high performance data storage. Read further...
To what extent do past and current HPC software optimization activities predict the future? Current optimization trends and next-gen hardware designs point to more threads, wider vectors, and an increasingly complex memory hierarchy. Is HPC application software ready for the future foretold by this trajectory? What will it be like and how can you be prepared for it? A lot of questions that Aaron Vose tries to answer in the second part of his Cray blog "HPC Software Optimization Trends". And what do we need to do? "While future hardware may require many threads and large vectors to reach peak theoretical Flop/s, this doesn't mean adding more threads or extending vectorization is the correct path forward for your code. Keep the complex memory hierarchy in mind as well. How do you know where to start your software optimization efforts? The key is to focus on your application's memory behavior." Read further...