By Matthew Dublin

For those of you that missed it, Edward Walker, a research scientist at the Texas Advanced Computing Center at the University of Texas at Austin, has a paper out that provides a bit of a reality check for cloud computing. In "The Real Cost of a CPU Hour," Walker starts by asking whether or not outsourcing your cyberinfrastructure needs to the cloud is really all it's cracked up to be — the answer seems to be no. Just because cloud computing is cheap, doesn't mitigate the performance drops when compared to a cluster. The article describes a significant gap between performing HPC computations on a traditional scientific cluster versus a EC2 provisioned scientific cluster using macro- and micro-benchmarks. Walker used the NAS Parallel Benchmarks, a small set of programs designed to help evaluate the performance of parallel supercomputers, to measure the performance of the clusters for common scientific calculations, as well as examining the performance of the Massage Passing Interface library with the mpptest micro-benchmark. "The opportunity of using commercial cloud computing services for HPC is compelling. It unburdens the large majority of computational scientists from maintaining permanent cluster fixtures, and it encourages free open-market competition, allowing researchers to pick the best service based on the price they are willing to pay. However, the delivery of HPC performance with commercial cloud computing services such as Amazon EC2 is not yet mature," Walker writes. "For cloud computing to be a viable alternative for the computational science community, vendors will need to upgrade their service offerings, especially in the area of high-performance network provisioning, to cater to this unique class of users."