Back by popular demand, the ARC at Georgetown University has for some strange reason decided to offer my Intermediate Beowulf Administration and Optimization course for a second time this March (18th-20th). The details and background are on the ARC HPC Training Page. Class size is limited, so if you have interest, sign up early. Course description is below. Excellent donuts.

From the "I'll take eight department"

The Linux cluster world is moving towards InfiniBand for many reasons: bandwidth, latency, message rate, N/2, price/performance, and other factors that affect performance and price. But usually it's focused on larger systems, many times greater 64 nodes up to multiple thousand nodes. At that same time the reasons for moving to InfiniBand are still valid for smaller clusters, particularly performance, but the economics are not. Basically InfiniBand is just too expensive for smaller systems and usually does not make sense from a price/performance perspective. But that has just changed...

A special article for IO Knuckleheads

In my experience there are quite a few people who don't really know the IO performance of their application(s) nor the IO pattern. So rather than complain about this situation, as I'm apt to do, I decided to write a column that talks about how to capture the IO behavior of your code(s). These steps can be done for codes where you only have the binary, not necessarily the source. It's fairly easy to capture the information. Processing it is another story, however.

This article will give you an introduction in how to use strace, a commonly used debugging tool for system administrators, as a tool to gather information on the IO pattern of your code(s). I'll show you how to use and gather the information, including how you use it for MPI codes. Read on if you want to learn more about how to use this simple tool to make yourself a better cluster, well..., monkey.

At long last, a new poll question about compilers. The question was prompted by a surprising post on Joe Landman's Scalbility.org. The GNU 4.x series seems to be performing surprisingly well -- in one test at least. Update: Joe has posted Fortran results.

The previous poll asked about cluster education. It seems there is a need for everything cluster these days with an emphasis on construction and design techniques. The number of respondents was a record 703! (of course if you do not change the poll question for half a year...) Past polls and other links to surveys can be found on our Cluster Links page.