Brain Murmurs

SEATTLE, WA, April 27th 2006 - Brain Murmurs, Inc, a Seattle-based software research and development company, today announced that the JIVA Grid Computing System now provides support for applications based on the JMSL libraries from Visual Numerics.
“This move will allow current users of the JMSL libraries to parallelize their existing applications through the use […]

Filed under: Press Releases by Daniel
No Comments »

SEATTLE, WA, April 27th 2006 - Brain Murmurs, Inc, a Seattle-based software research and development company, today announced a new 30-day evaluation program for its JIVA grid-computing product.   Under the new program, prospective customers will be able to run the JIVA grid computing system on their networks for 30-days at no cost.
“This is […]

Filed under: Press Releases by Daniel
No Comments »

The decision to implement JIVA applications in Java came down to one simple point: at this point in time, only Java byte code meets all of our requirements.
We knew at the start that the implementation depended on several forces, all in tension:
Performance
Mutability
Backwards compatibility
Developer acceptance
Customer acceptance
Security
Platform independence
Performance: Since the object of this exercise was […]

Filed under: JIVA, JIVA (Technical) by Daniel
No Comments »

For us, security is king. In a volunteer grid system the computing software has to run on a computer that belongs to someone and is used for things besides supercomputing. I used to work as a network administrator at Kistler Aerospace. People are paranoid about their computers. People are suspicious of […]

Filed under: JIVA, JIVA (Technical) by Daniel
No Comments »

There’s been a lot of hype about using virtualization for grid computing, so I decided to do a little bit of elementary benchmarking and see how VMWare stacked up against JIVA.
I decided to compare the performance of the Scimark 2 benchmarks running in three different ways (native, JIVA, and virtual native) on the same machine, […]

Filed under: JIVA, JIVA (Technical) by Daniel
No Comments »

Setting up the new task in the simulator was pretty straightforward, but testing was cut a bit short by a meeting. I’ve included a screenshot of the new task running in the simulator.

Filed under: JIVA (Technical) by Daniel
No Comments »

The scimark task is written up, including write/read scratch file routines and the final output file creation, after about 1.5 hours of work. Time to start testing in the SDK.

Filed under: JIVA (Technical) by Daniel
No Comments »

I am writing a JIVA Task based on the NIST Scimark2 benchmark suite that I will hopefully have up and running in the next hour or so, at least on our JIVA Simulator.
Once I’m convinced that it is working correctly I’m going to deploy the task to our internal JIVA Server and see […]

Filed under: JIVA (Technical) by Daniel
No Comments »

I was doing a bit of administrative work on one of our lesser used, Sun servers this morning and noticed that it had a hearty uptime of 288 days. Since this machines is a fairly slow but reliable JIVA Client as well I decided to look and see exactly how long the client had […]

Filed under: JIVA by Daniel
No Comments »

We have an old SGI Octane here and I couldn’t resist setting it up with the JIVA Client. It is now arduously cranking away, looking for Mersenne Primes
If you are interested in seeing how it is doing, feel free to look at our server stats page

Filed under: JIVA by Administrator
No Comments »