ClusterMonkey.net: In a previous article, we learned how to test an interface with Netpipe. In terms of clusters, Netpipe can be considered a micro-benchmark as it only tests a single (but important) component of the cluster. Can we conclude that good Netpipe performance means we have a good cluster? Well, it depends, maybe we can and then again more testing may be needed. Let's consider the fact that Netpipe performance tells us about the maximum limits of TCP/IP performance between two nodes. When we run parallel applications, there is usually more involved than just raw TCP/IP performance. There is usually an MPI layer between your application and the TCP/IP layer. In addition, there are effects due to compilers and node hardware (i.e. dual vs. single) and even the application itself may stress the interconnect in way not measured by Netpipe. Tests that run over multiple comments are usually referred to as macro-benchmarks because they involve a "whole system test" vs a single component test. Both are valuable, but neither may tell the whole story, however.
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.