New additions to Sun Grid Engine allow integration with Clouds and Hadoop (map-reduce) jobs

nVidia CUDA may be the rage, but OpenCL is a standard that has some features you may need.

This month we are supposed to hear about new multi-core processors from both AMD and Intel. Should we be happy?

Managing power can save money especially if it is from your wallet

Introduced less than three years ago, the rapid growth of the CUDA software model is no accident

Can a solution for HPC software live within MPI, OpenMP, CUDA, OpenCL, and/or Ct?

Commodity trends at the low end are generating interesting ideas in HPC

Our final videos include Appro, 10GigE, and making sense of it all

Let's all help the Haiti relief effort and then watch some cutting edge videos

I get the latest from AMD, talk with Don Becker, and then get disruptive

A new year is upon us, but wait, I'm not done with the old one yet!

Truth is stranger than fiction. The connection that helped end HPC careers and companies in 2009

This week we hear from Intel, Numascale, and Mellanox. Plus some thoughts on single node HPC solutions

One of the challenges facing HPC are I/O rates and new clusters designs are paving the way to new levels of performance.

The first videos from SC09 are here. We take a look at the Beowulf Bash, SCinet, NVidia, and Adaptive Computing (previously Cluster Resources

The big show is over and now all that remains is to make sense of it all

Let's use the HPC fist bump this year.

Your guide to navigating the coolest tradeshow on the planet.

Are you a Geek or a Droid? Take the simple quiz to find out!

Preserving program state is necessary for parallel computation, but should we keep doing it the hard way?

The New Fermi GPU shows NVidia has been listening to the HPC crowd

Hitching a ride to a fast moving technology is a welcome trend

In stark contrast to one year ago, this year's show was well-attended and upbeat.

Will a new feature make C the answer to the parallel programmer's dreams?

The 10 GigE train is on its way. Simplicity and low cost have left the station.

Hybridizing MPI applications with cores and GP-GPUs. Is this a good idea?

The acquisition of Sun by Oracle raises many questions and recalls some past experiences

Hiding the details of the multi-core and GP-GPU hardware is a really cool goal

How big of a cluster can you build? With a little math and the speed of light you can find out.

Matching the right solution with the right problem takes skill, flexibility, and a little luck.

Commodity hardware is the norm in HPC. What about commodity software?

How can the community help create better HPC software?

Large insect populations synchronize globally, but communicate locally. Is there a lesson for parallel computing?

SGI/Rackable Walks away from a PFLOP deal. No, this is actually good news.

Pick one: portability or efficiency. Neither is guaranteed when writing explicit parallel code

How can getting to the ocean help with HPC computing?

SMPs may have cores, but clusters have bandwidth.

Data locality is the key to efficient code.

Will multi-core split HPC into two programming camps? Which one will you join?

As multi-core solutions continue to grow, a new power saving single-core server approach takes hold