Malleable applications for scalable high performance computing

Malleable Components for Scalable High Performance Computing

This paper describes a modular decentralized middleware framework for dynamic application reconfiguration in large scale heterogeneous environments. Component malleability is presented as a dynamic reconfiguration strategy. Dynamic component granularity enables improved load balancing by component migration, and most importantly, it enables applications to scale up to arbitrarily large numbers ...

Techniques for Optimizing Applications: High Performance Computing

Designing Scalable Heterogeneous Memory for High-Performance Computing

As different DRAM memory protocols and emerging memory technologies present themselves as competitive alternatives to current DDR3-based HPC memory systems, the need for a memory system that can handle heterogeneity increases. To satisfy this need, this paper proposes an architecture for a scalable, heterogeneous memory system based on hierarchical memory controllers. In addition, use of multi-...

SST + gem5 = a scalable simulation infrastructure for high performance computing

High Performance Computing (HPC) faces new challenges in scalability, performance, reliability, and power consumption. Solving these challenges will require radically new hardware and software approaches. It is impractical to explore this vast design space without detailed system-level simulations. However, most of the existing simulators are either not sufficiently detailed, not scalable, or c...

Benchmarking Methodology for Real-time Embedded Scalable High Performance Computing

This report has been reviewed by the Rome Laboratory Public Affairs Office (PA) and is releasable to the National Technical Information Service (NTIS). At NTIS it will be releasable to the general public, including foreign nations. If your address has changed or if you wish to be removed from the Rome Laboratory mailing list, or if the addressee is no longer employed by your organization, pleas...