Symposium on Application Accelerators in High-Performance Computing (SAAHPC)

Stevens to give keynote on challenges of designing software library for genomics

Rick Stevens, the Associate Laboratory Director for Computing, Environment and Life Sciences at Argonne National Lab, will give a keynote talk on "The Challenges of Designing and Building a Next-Generation High-Performance Software Library for Genomic Sequence Analysis" at SAAHPC 2012.

Abstract: In this talk I will discuss a new community project aimed at developing a portable, high-performance library for writing a variety of genomic sequence analysis codes.  The library is aimed at current and future parallel architectures, multicore and many core systems as well as accelerator based nodes.  The goal is to develop a library of common low-level sequence analysis kernels to serve as a foundation for a wide variety of higher-level tools such as multiple sequence aligners, genome assemblers, short-read mappers, clustering and searching tools, profiling and non-alignment similarity tools, and phylogenetic tools.   The effort has the following objectives: Making available in an easy-to-use, high-quality, open-source form the best algorithms and data structures for representing, hashing, clustering, indexing, searching, aligning, compressing and mapping biological sequences; Enabling these algorithms and data structures to be readily ported to current and future HPC node architectures, including traditional multicore, many core, GPUs, processor in memory and FPGA type accelerators, enabling tool developers to code to a common library API yet take advantage of new technologies without having to manually create optimized routines for each target; Designing benchmarks that use the library to represent the computationally intensive operations relevant to sequence analysis such that new computer systems and CPU architectures can be evaluated for this important class of problems; Building a community that is interested in working together in the future to impact HPC architectures so they have better support for the features needed to support computational genomics; I will motivate the this effort by providing a set of core workflows from the DOE-supported systems biology knowledge base project.