The Clouds Can Do Mathematics
Wolfram Research has announced the availability of its product, Mathematica 7, to perform computations using cloud computing services from within the application. Mathematica is a computing environment providing support for numerous numeric and symbolic computations through a dedicated symbolic language.
Beside numerical and symbolic computational support, Mathematica includes image processing, parallel High-Performance Computing (HPC), interactive documents, and others. The latest feature announced by Wolfram Research is Mathematica’s integration with cloud computing being able “to access many diverse HPC systems, including TOP500 supercomputers and the Amazon Elastic Compute Cloud”. Tom Wickham-Jones, a Wolfram Research Executive Director, commented:
The two largest challenges in using HPC are programming the HPC application itself and ensuring that you can get enough computing power to do the job.
Mathematica answers the programming challenge by providing an integrated technical computing platform, enabling computation, visualization, and data access. Cloud computing offers consistent access to large-scale computing capabilities.
Jinesh Varia, an Amazon Web Services Evangelist, explained how it works:
The workflow is very simple to understand and it takes very few clicks to deploy your code in the cloud. A typical Mathematica user develops code in their standard notebook interface, a programming concept that defines their input code and output results, including graphics. The user specifies input cells, output cells and other parameters. Mathematica will evaluate one input cell at a time so evaluation could take a lot of time to process on one machine. Now, with the new Cloud service, users can evaluate the entire notebook in one shot by pushing it to the cloud.
The HPC Cloud Service lets users take the entire notebook, click a few buttons in the HPC Cloud Service GUI and ask it to run it in the cloud. The HPC Cloud Service evaluates the code, runs it in parallel Mathematica sessions, bundles up the results and notifies the user. In other words, a user can test the code (a Mathematica Notebook) with a small amount of input and then increase size of the input to a more realistic size, push it to the cloud so it runs on hundreds and even thousands of nodes in parallel, and get notified when its done.
What is interesting is how a computational demanding application, like Mathematica, can be scaled to run on hundreds or even thousands of nodes in the services cloud by simply clicking a few buttons.