Are PC-Clusters ready for Supercomputing?
نویسنده
چکیده
Recently one of the first two early installations of the new Siemens hpcLine parallel computer was installed at the Computing Center of the Aachen University of Technology (RWTH). This machine is configured with off the shelf Intel processor boards and connected with a fast SCI network. We investigate the question how such a machine fits into a UNIX environment containing vector supercomputers, SMP machines, and workstations and present first experiences, measurements and comparisons.
منابع مشابه
Cluster Computing : The Commodity Supercomputing
The availability of high-speed networks and increasingly powerful commodity microprocessors is making the usage of clusters, or networks, of computers an appealing vehicle for cost effective parallel computing. Clusters, built using commodity-off-the-shelf (COTS) hardware components as well as free, or commonly used, software, are playing a major role in redefining the concept of supercomputing...
متن کاملDevelopment of a University-based High Performance Computing System of Pc Clusters
The rapid increase in performance of mass-market commodity microprocessors and significant disparity in pricing between PCs and scientific workstations, has provided an opportunity for substantial gains in performance to cost by harnessing PC technology in parallel ensembles to provide high-end capability for scientific and engineering applications. AHPCG is an Ateneo de Manila University initi...
متن کاملScalability of a tera-scale linux-based clusters for parallel ab initio molecular dynamics applications
KISTI supercomputing center has initiated a TeraCluster project to build a linux-based cluster with tera-flops performance. The main goal of the project is to provide a resources composed of PC clusters that meet the level of computing power required by the grand challenge applications in Korea. In the beginning of 2002, we have built a prototype of TeraCluster with 128 computing nodes, Phase-I...
متن کاملOn Graph-Based Symmetric Clusters with Single-Switch Latency
Cluster computing is now an accepted form of supercomputing. A cluster is a collection of computer (node) interconnected by a high-speed network. Each cluster node is either a workstation, a personal computer (PC), or a symmetric multiprocessor (SMP). The performance of a cluster system depends mainly on the bandwidth and latency of the network. In this paper, we propose a two new designs for a...
متن کاملThe Design and Implementation of Berkeley Lab’s Linux Checkpoint/Restart
Clusters of commodity computers running Linux are becoming an increasingly popular platform for highperformance computing, as they provide the best price/performance ratio in the marketplace. But while the size and raw power of Linux clusters continues to increase, many aspects of their software environments continue to lag behind those provided by proprietary supercomputing systems. One featur...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2007