[skyhawk133]

Quote

Dear Amazon EC2 Customer,

We are excited to announce the immediate availability of Cluster Compute Instances for Amazon EC2, a new instance type specifically designed for high-performance computing (HPC) applications and other demanding network-bound applications. Customers with complex computational workloads such as tightly coupled parallel processes, or with applications sensitive to network performance, can now achieve the same high compute and network performance provided by custom-built infrastructure while benefiting from the elasticity, flexibility and cost advantages of Amazon EC2.

Prior to Cluster Compute Instances for Amazon EC2, organizations with advanced HPC needs have been required to fund expensive, in-house compute clusters by purchasing dedicated, purpose-built hardware. As a result, the demand for high-performance cluster computing often exceeds the capacity of many organizations, and many projects are cut altogether or wait in long queues to access shared resources. With Cluster Compute Instances, businesses and researchers now have access to the high-performance computing capabilities they need with pay-as-you-go pricing, the ability to scale on-demand, and no upfront investments.

Cluster Compute Instances provide similar functionality to other Amazon EC2 instances but have been specifically engineered to provide high-performance compute and network capability. Cluster Compute Instances provide more CPU than any other Amazon EC2 instance. Customers can also group Cluster Compute Instances into clusters allowing applications to get the low-latency network performance required for tightly coupled, node-to-node communication (typical of many HPC applications). Cluster Compute Instances also provide significantly increased network throughput making them well suited for customer applications that need to perform network-intensive operations. Depending on usage patterns, applications can see up to 10 times the network throughput of the largest current Amazon EC2 instance types.

Learn more about the new Cluster Compute instances for Amazon EC2 at http://www.aws.amazon.com/ec2 and their use in running HPC applications. Or, sign-up to attend the Introduction to Cluster Compute Instances webinar on July 21.

Sincerely,

The Amazon EC2 Team

Pretty cool stuff here! What do you forsee some of the uses being for high performance computing in the cloud. This stuff is now accessible to anyone/everyone without any upfront investment!

[Martyr2]

To tell you the truth I really don't know how this would be of use to the little guy. So far this is such a niche market and, from what I understand of it, it is really for enterprise environments who want to offload their high traffic web services. Large commercial sites like Ebay or perhaps department store chains, Walmart etc. Any organization that would need to do a ton of transactions through a web service or run high end computational programs that multiple locations need to get at (oil, aerospace etc).

I think this is Amazon's way of competing with the Google infrastructure, but I am not sure how they are really going to capitalize on it too much. I think most large companies would rather do their own work inhouse unless the price to outsource it to Amazon just can't be beat. We wouldn't know that unless we actually had a price comparison sheet between what organizations pay inhouse verses the prices stated for EC2.

If anyone on DIC is running high performance services through Amazon, please do let yourself be known and toss in your input. I just have not heard of them being used extensively.

This post has been edited by Martyr2: 13 July 2010 - 09:54 AM

[nooblet]

I would find a lot of use for this. I'm a heavy EC2 user. Currently used in conjunction with Right Scale. For those not using it with EC2, I highly recommend.