Running HPC Workload on Cloud - A Real-life Case Study

Running high-performance computing (HPC) workload in public cloud has been an interesting yet challenging issue for many researchers and research institutes. The aspect of having large computational power on the finger tip with moment's notice is alluring yet the potential pitfall of poor performance and high cost can be scary.

I came upon a thoughtful and insightful blog post from "Astronomy Computing Today". It presented a research by Ewa Deelman of USC and G. Bruce Berriman of CaTech on the interesting topic of running HPC workload on Cloud. In this case, running astronomical applications on Amazon EC2 HPC Cloud. 

The conclusion of the research are two folds: 1) the cost-performance to run on Cloud depends on application requirement and needs to be carefully evaluated; 2) for now, avoid workload that demands mass storage as this is still the most expensive aspect of running on public cloud such as EC2.

You can access the post here.

Update:

• 2012.08.15: original post