As Beowulf-style clusters have proliferated, many computational scientists have discovered that, although clusters provide adequate CPU performance for most applications, more finely-grained models are often limited by the performance of the network that interconnects nodes. While the network is typically Fast Ethernet (100 Mb/s) or Gigabit Ethernet (1.0 Gb/s), it's still not fast enough to run applications originally developed for shared memory parallel systems or commercial memory systems featuring high performance, custom-designed switched interconnects.
Such applications have stimulated the market for scalable networks that provide high bandwidth and low latency on commodity clusters. (Bandwidth is the throughput rate of a data channel, while latency is the time it takes to open the channel and initiate the data transfer.) These custom networks -- often adding 50% or more to the per-node cost of Linux clusters -- are not commodity items, and some people claim that, as a result, a cluster sporting one of these sexy networks can not be called a Beowulf. Religious arguments aside, many researchers consider these high performance interconnects a necessity for their computational clusters.
Video - The Road to PetaFlop Computing
Explore the Scalable Unit concept where multiple clusters of various sizes can be rapidly built and deployed into production. This new architectural approach yields many subtle benefits to dramatically lower total cost of ownership.
White Paper - Optimized HPC Performance
Multi-core processors provide a unique set of challenges and opportunities for the HPC market. Discover MPI strategies for the Next-Generation Quad-Core Processors.
Appro and the Three National Laboratories
[Appro delivers a new breed of highly scalable, dynamic, reliable and effective Linux clusters to create the next generation of supercomputers for the National Laboratories.