Dean's Faculty Update
HPC Phase III Expansion Brings Opportunities to IFAS Faculty
Date: July 16th, 2009
From: Mark R. McLellan, Dean
IFAS Faculty ----
IFAS faculty and researchers now have a resource to extend exploration into cellular function and basic biology and utilize high performance computing. In January 2009, the Phase III expansion of the UF High Performance Computing (HPC) cluster was completed.
The Dean for Research Office led the effort to bring HPC to the researchers in IFAS and committed the resources to join the HPC center in the fall of 2007. Researchers in IFAS immediately started using the 1,600-core Phase II cluster for their projects, and many have subsequently invested in the Center as inependent investigators. Since January 2009, IFAS computations have been running on the Phase III equipment. The majority of the IFAS computational work is composed of thousands of relatively short jobs. On a large, shared cluster like the 2,500-core HPC cluster, many cores may begin processing a large collection of jobs simultaneously so that they all are completed in parallel. Consequently the total time researchers must wait becomes very short.
Pictured: IFAS Dean of Research Mark McClellan (left) and IFAS-ABE Chair Dorota Haman (right) listen as HPCC engineer Craig Prescott (middle) shows the Phase III cluster nodes.
Working closely with the Interdisciplinary Center for Biotechnology Research (ICBR) and others, IFAS faculty recognize the HPC cluster as a way to extend our exploration of basic biology into a more comprehensive understanding of cellular function. Our goal is to explore everything from basic genomics to related phenotype and map gene function to biological process. Our plant scientists are exploring key metabolic pathways and their connectivity to behavior affecting traits such as flavor and aroma volatiles and drought and salt tolerance. With a vision to the future, our agricultural engineers will model complex interactions between agricultural land uses and climate as well as adaptive responses to climate change. And from a global vision to a nano focus, we expect to map how nano-scale interactions might affect nutrient flow and transport dynamics in a soil matrix.
According to ICBR Director Robert Ferl, who is also a professor in the Horticultural Science Department, there are more than 20 IFAS faculty currently using HPC. In his own work, and as part of ICBR, he uses the HPC cluster for the extremely demanding task of comparing genome sequences against one another. This is the main process of using existing genomes as templates for understanding and even putting together the sequences of unknown genomes, and for searching for variability that marks important genes. These important genes can have all kinds of implications for IFAS breeders, developers and scientists as they correlate genetic data with fundamental plant and animal traits and as they correlate those genetic data with increased productivity or specifically desired traits.
"We are entering the era where the personal genome sequence is around the corner, where cultivars, lines and even individuals will have their genomes sequenced," Ferl said. "HPC and associated technologies make those sequences possible, but moreover they make possible the understanding of the relationships among sequences and traits."
Our world is full of compelling questions and the HPC is another important tool that will help us explore possible solutions. IFAS is proud to be a committed supporter of the HPC cluster, and I encourage all of the faculty to think about the center as a new resource available to them to help further their research on a new level.
Mark R. McLellan
Dean for Research, IFAS
Director, Florida Agricultural Experiment Station
