“This talk will focus on programming models and their designs for upcoming exascale systems with millions of processors and accelerators. Current status and future trends of MPI and PGAS (UPC and OpenSHMEM) programming models will be presented. We will discuss challenges in designing runtime environments for these programming models by taking into account support for multi-core, high-performance networks, GPGPUs, Intel MIC, scalable collectives (multi-core-aware, topology-aware, and power-aware), non-blocking collectives using Offload framework, one-sided RMA operations, schemes and architectures for fault-tolerance/fault-resilience.”
Archives for March 2015
Video: High-Performance and Scalable Designs of Programming Models for Exascale Systems
March 25, 2015 by
insideHPC Guide to Open Computing
March 24, 2015 by
The Open Compute Project, initiated by Facebook as a way to increase computing power while lowering associated costs with hyper-scale computing, has gained a significant industry following. This guide to Open Computing is design to help organizations optimize their HPC environment to achieve higher performance at a lower operating cost.
UK Atomic Weapons Establishment Signs up for SGI ICE XA Supercomputer
March 24, 2015 by
Today SGI announced that the UK Atomic Weapons Establishment (AWE) will be one of the first customers to install SGI’s record-breaking SGI ICE XA supercomputers.
Video: Lustre Based Enterprise Storage – Tuning Clients for Optimal Performance
March 24, 2015 by
“The architecture of the ClusterStor product line builds on 25 years of experience with storage systems, Seagate (formerly Xyratex) and Lustre on a parallel open source high performance storage system that is commonly used for scalable computing.”
Microsoft Update on RDMA
March 24, 2015 by
In this video from the 2015 OFS Developer’s Workshop, Tom Talpey from Microsoft presents: Microsoft Update on RDMA.
Is Europe Leading the Energy Efficiency Race?
March 24, 2015 by
Europe is notorious for its high energy costs. In the first of three articles on energy efficiency in high-performance computing, Tom Wilkie from Scientific Computing World asks if that’s why so much of the initiative appears to be coming from Europe.
Petroleum Geo-Services to Acquire 5 Petaflop Cray XC40
March 24, 2015 by
Today Cray announced a contract to provide Petroleum Geo-Services (PGS) with a 5 Petaflop Cray XC40 supercomputer. The system will be one of the largest supercomputers ever deployed in the commercial sector.
Video: Dimensioning Data Centre Resiliency at CSCS
March 24, 2015 by
“The Swiss National Supercomputing Centre (CSCS) offers a range of computing and storage services to Swiss and international research communities. These services are provisioned by an array of solutions including leading edge Cray XC40 and hybrid XC30 systems, commodity clusters, files systems such as Lustre and site-wide GPFS storage as well as centre-wide Ethernet and InfiniBand networks.”
Video: Welcome to the 2015 HPC Advisory Council Switzerland Conference
March 24, 2015 by
In this video, Gilad Shainer and Hussein Harake kick off the 2015 HPC Advisory Council Switzerland Conference. The event will focus on High-Performance Computing essentials, new developments and emerging technologies, best practices and hands-on training.
Video: Adaptive Routing for Scalable Topologies
March 23, 2015 by
“Adaptive Routing has been added to the static routing capability available in previous switch families. InfiniBand supports moving traffic via multiple parallel paths. Adaptive routing dynamically and automatically re-routes traffic to alleviate congested ports. In networks where traffic patterns are more predictable, static routing has been shown to produce superior results. The InfiniScale IV architecture provides the best of both static and adaptive routing.”
