Select News
The news in this category has been selected by us because we thought it would be interestingto hard core cluster geeks. Of course, you don't have to be a cluster geek to read the news stories.
- Details
- Written by Douglas Eadline
- Hits: 9361
From the this is way cool department
Open-MX is a message passing stack that offers the Myrinet Express features on top of regular Ethernet hardware. It requires no kernel or driver modifications. In addition any software that support (e.g. various MPIs,PVFS2) Myricom MX libraries can link to directly to Open-MX.
The project page and software can be found here. Recently, project leader Brice Goglin gave a presentation entitled High-Performance Message Passing over Ethernet with Open-MX, why and how? You can find the slides and video at the Distributed Computing Group (DISCO) site. Quick review: I have used Open-MX since version .4 (current version is 1.04) and it is a well designed and run project that works great If you use Ethernet, check out Open-MX!
- Details
- Written by Douglas Eadline
- Hits: 9716
the move from pixels to petaflops
It is not often someone does our job for us and when it happens we like to take advantage of it. Earlier this month, Andrew Humber, Senior PR Manager, Tesla & CUDA Technologies at NVIDIA Corporation sent us a nice recap of the Tesla milestones for the past year. The GP-GPU revolution is moving rather fast as evidenced by Andrew's summary. Take a look you will be surprised how fast things are moving.
- Details
- Written by Douglas Eadline
- Hits: 6779
What does that mean? And what is OpenCL?
This years SC was abuzz with co-processor HPC news. Take a look at how many awards went to the CUDA projects. Developments with co-processors, and GP-GPU's in particular, are moving at a fast pace. Success has been driving this movement and in a very short time we have had more than a few ways to program GP-GPUs (CUDA, Brook+, RapidMind, etc). However, as with any new software paradigm, investing too much time in a non standard approach can be risky. Plus, CUDA and Brook+ only addressed the co-processors.
- Details
- Written by Douglas Eadline
- Hits: 5773
For all you tree hugger HPC geeks, I'm moderating a webinar called:
Cool Crunching: Understanding Green HPC
on Wednesday (December 3, 2008) at 11AM EST. More information and FREE registration click here.
And, I am working on the SC08 stories as well -- stay tuned. I have pictures from the Beowulf Bash -- uh oh.
- Details
- Written by Gilad Shainer, Sharan Kalwani, Art Sedighi, Amar Rao, Russell R Hornung
- Hits: 6168
Where to turn in a time of need. In need of MFLOPS, that is.
"The only constant is change" said Heraclitus, an ancient Greek philosopher. This is certainly true when describing the market of high-performance computing (HPC). The HPC market is characterized by a rapid change of architectures, technologies and usage. The only continuously steady characteristic of HPC is the ever-growing demand for performance, showing an increase of 100X every ten years based on the TOP500 list. The HPC market drives the computing technology further and evaluates many leading edge architectures. Proven solutions that have been widely adopted in the HPC are accepted in commercial high-performance computing markets such as automotive, oil and gas, financial, digital media, bio-science and mathematical modeling.