Big Programs and the Use of High-Performance Computing

• Activity Number: 573
• Type: Invited
• Date/Time: Wednesday, August 7, 2013 : 2:00 PM to 3:50 PM
• Sponsor: Section for Statistical Programmers and Analysts
• Author(s): Natalie Cheung Hall*+
• Companies: Eli Lilly and Company
• Keywords: Big data ; parallel programming ; Clinical Trial Optimization ; High Performance Computing

Abstract

It's the era of Big Data! Doesn't Big Data imply Big Programs? Big programs, in this context, are programs that process big data, programs that require a great amount of complex computation, or both. An area that uses programs to process big data is Pharmacogenomics, which uses large gene expression data. An area that uses complex programs is Clinical Trial Optimization, which creates trial simulation programs that simulate patient data, every operational aspect of several clinical trials, and data analysis models, to find the best design.

The running of these programs requires more computing power than a statistical program or analyst has at their desk. Thus, there is a need for High Performance Computing (HPC), such as cluster computing and cloud computing. Practical examples of how to parallelize existing code to be run using HPC will be given in this talk.