“When the history of HPC is viewed in terms of technological approaches, three epochs emerge. The most recent epoch, that of co-design systems, is new and somewhat unfamiliar to many HPC practitioners. Each epoch is defined by a fundamental shift in design, new technologies, and the economics of the day. “A network co-design model allows data algorithms to be executed more efficiently using smart interface cards and switches. As co-design approaches become more mainstream, design resources will begin to focus on specific issues and move away from optimizing general performance.”
A single issue has always defined the history of HPC systems: performance. While offloading and co-design may seem like new approaches to computing, they actually have been used, to a lesser degree, in the past as a way to enhance performance. Current co-design methods are now going deeper into cluster components than was previously possible. These new capabilities extend from the local cluster nodes into the “computing network.”
At SC15, Intel talked about some transformational high-performance computing technologies and the architecture—Intel® Scalable System Framework (Intel® SSF). Intel describes Intel SSF as “an advanced architectural approach for simplifying the procurement, deployment, and management of HPC systems, while broadening the accessibility of HPC to more industries and workloads.” Intel SSF is designed to eliminate the traditional bottlenecks; the so called power, memory, storage, and I/O walls that system builders and operators have run into over the years.
At Supercomputing 2014 in New Orleans, Altair announced key features for PBS Professional 13.0, scheduled to launch in Q1 2015. The new version will take scalability to the next level, with massive jumps in supported system size, job dispatch speed and throughput; users will also benefit from key resilience, flexibility and scheduling improvements.
As the countdown to Exascale continues, Exascale-like storage problems are already showing up in today’s massively parallel, heterogeneous HPC systems. Historically, storage and I/O have kept pace with growing system demands, but, because of the limitations of spinning media and the cost of solid state storage technologies, storage performance improvements have come at a disproportionately higher cost and lower efficiency than their compute counterparts.
Argonne National Labs is developing Argo, a prototype exascale operating system.