HPC's version of the tortoise and hare.

Parallel fundamentals, what constitutes an actual parallel program, and why some applications may or may not run faster on multi-core systems.

Readers respond to Doug Eadline's execution in determining the "Total Cost of Parallelization" for a given system. Join the discussion.

Doug Eadline talks with Intel's Richard Dracott, General Manager of the High Performance Computing Organization.

Learn how to obtain, build, and use an MPI stack for Linux machines. This tutorial will take you from "hello world" to parallel matrix multiplication in a matter of minutes.

Building affordable, balanced clusters without sacrificing performance is the challenge facing everyone in high-performance computing. But what really drives performance in today's HPC systems?

The fastest computers in the United States have their work cut out.

Some relief for cluster consternation.

Microway's MPI Link Checker enabled a cluster user to pinpoint problem nodes in the cluster. By graphically representing the bandwidth and latency of all links in the cluster, a user can see the exact pattern of communication occuring in their cluster. As one underperforming node can slow the performance of an entire MPI job, it is imperative to ensure full speed of all systems.

Vendors aim to put a cluster in every department.

Install Linux on your Playstation 3

A sneak peak at the world's fastest systems.

Program includes a global team of 300+ consultants and a $1,000 discount for enterprises that migrate from HP.

Server vendor beefs up its storage solution with Terrascale's clustered file system.

What’s on your nodes? Do you really need all that stuff? Uh, it depends.

In case you haven’t noticed, the high-performance computing (HPC) market is now ruled by the Linux cluster. And while Linux clusters have made serious number crunching affordable, this disruptive change still has perils. Unlike more traditional HPC methods, a cluster presents a myriad of variables and trade-offs to the cluster designer and end-user. However, whenever there are choices that aren’t completely right or wrong, there is an opportunity for the artist and engineer to shine in all of us.

A hard to swallow conclusion from the table of cluster.

Dynamic Parallel Execution: Loosing control at the high end.

You can’t always get what you want. But that doesn’t stop me from asking. Besides, Buddha’s got my back. Here's my HPC wish list.

A new, federally-funded prograim called the High Productivity Computing Systems Initiative aims to to make high-performance computing more afforadable and more accessible to more scientists. Here’s a look at the goals of the project, including an example of a better way to program in parallel today.

The cluster community needs to be pull together and connect the dots. It’s a join or die kind of thing.

Off to see the wizards… of high-performance computing.

Supercomputing extremists converged on Seattle, Washington, last fall to share their experiences, exhibit their research, flaunt their wares, and award their pioneers.

Those who say that the “Top 500” (http://www.top500.org/) is nothing more than “a high-tech pissing contest” are wrong. As the history of the Top 500 has shown, “The List” has an unfailing ability to predict the future of and inexorably impact plebeian, everyday computing.

Two months ago, the Kronos “value cluster” set a new record for price-to-performance, yielding 14.53 gigaflops at the cost of $171 per gigaflop. But is that the best Kronos can do? Or can some additional investment of time and effort push the extremes a little further? Discover if Kronos hits the proverbial wall, learning more cluster optimization techniques along the way.

With the introduction of multi-core processors, parallel programmers face a tough decision.

LOVELAND, Colorado - 30 November 2005 - Terra Soft Solutions, the leading developer of integrated Power Architecture Linux solutions is pleased to announce its role in COLSA Corporation's success with MACH5, the world’s largest Apple Xserve-based cluster.

Quick, hand me the open source “clue stick.”

If you need to monitor and manage such a configuration, try syslog-ng (syslog, next generation), a drop-in replacement for syslogd. syslog-ng provides more sophisticated log management capabilities and enables log transfers over the Internet.

To date, the Message Passing Interface has been instrumental in simplifying application development for clusters. But as clusters change to embrace multiple cores, multiple platforms, and multiple advanced interconnects, MPI is no longer adequate. What can replace it? Donald Becker asks, “How about Unix? ”

Getting the most out of your cluster is always important. But how exactly is that done? Do you really need to dissect your code and analyze every instruction to get optimal performance? Do you need to build custom kernels? Not necessarily. By testing some basic assumptions, you may be able to eke ten-node performance out of an eight-node cluster. Here’s how.

What are cluster builders up to these days? Cluster maven peeks into some machine rooms.

With advances in many facets of networking, diskless clusters are now quite practical. Better yet, nodes without local storage are cheaper to build and cheaper to maintain. Here’s a survey of the relevant technologies and techniques.

Today’s basic building blocks are Intel and AMD servers and high-speed networks. Tomorrow’s toys? Let’s take a look.

Explore some of the factors involved in designing a cluster from scratch. A case study serves as a pedagogical example.

Systems with multiple cores are just like clusters. But there’s good news, too…

Scyld Beowulf, a commercial cluster operating system, rounds out our coverage of the most popular Linux cluster software distributions.

What’s next (and current) in cluster computing? Multiple cores, blades, new networks, plus plenty of small, traditional clusters.

In the past few weeks, I've received two new titles on Linux performance Tuning; Performance Tuning for Linux Servers from IBM Press and Optimizing Linux Performance: A Hands-On Guide to Linux Performance Tools from Prentice Hall Professional Technical Reference.

I'm quite happy to see books of a more advanced nature coming out about Linux. Beginner's books are nice, but the real need for documentation is on the more advanced topics, where man pages and HOWTOs aren't quite sufficient to get it done. Performance tuning, in particular, is of heavy interest to admins who are deploying or thinking about deploying Linux, and they need to get the most bang for their buck.

Our coverage of Linux-based cluster distributions continues this month with OSCAR, the Open Source Cluster Application Resource software bundle available free from the Open Cluster Group.