Skip to main content

GridGain + Multi-Core processors

Submitted by cahn on 16 November, 2008 - 3:24pm

GridGain is an open source product written in Java providing a grid computing platform. It is known to be one of the more widely used grid product, certainly, as far as I see, one of the easiest to "gridify" or grid-enable an existing product.

One of the applications of the product is to couple with Amazon EC2 to make a "cloud" computing platform. See Gridgain + Amazon EC2

The widespread use of "multi-core" PCs also means that the product can be used to "parallelise" to take advantage of this increased power.

My setup involves one "broker" node and three "worker" nodes. The grid job is sent from one of the worker nodes.

I use ActiveMQ for communication between nodes, GridSharedFsCheckpointSpi for saving down intermediate data (to be picked up during the "Reduce" phase) and JobStealing SPI for automatic load-balancing and failover.

[coolcode lang="xml" linenum="on" download="gridgain-broker.xml"] <?xml version="1.0" encoding="UTF-8"?> GridGain configuration tcp://localhost:39210 org.apache.activemq.jndi.ActiveMQInitialContextFactory vm://localhost [/coolcode] [coolcode lang="xml" linenum="on" download="gridgain-worker.xml"] <?xml version="1.0" encoding="UTF-8"?> GridGain configuration org.apache.activemq.jndi.ActiveMQInitialContextFactory failover:tcp://localhost:39210 [/coolcode]
AttachmentSize
gridgain-broker.xml3.91 KB
gridgain-worker.xml3.43 KB

Comments

#1 its realy good thank

Submitted by By-passer on 30 June, 2009 - 8:17pm.

its realy good thank you....evden eve nakliyat

What did I say then?

Pricing and hedging derivative securities in markets with uncertain volatilities

Submitted by cahn on 19 June, 2007 - 5:30pm

...a model for pricing and hedging derivative securities and option portfolios in an environment where the volatility is not known precisely, but is assumed instead to lie between two extreme values $ \sigma_{min} $ and $ \sigma_{max} $.... ...the "pricing" volatility is selected dynamically from the two extreme values $ \sigma_{min} $, $ \sigma_{max} $, according to the convexity of the value-function.....