UF President Bernie Machen joins HPCC, ICBR, and IFAS team members at the Phase III Expansion Dedication. Six people in the front from left to right: President Machen, Senior Vice President for Research Win Philips, Prof. Don McCarty, ICBR Assistant Director Connie Nicklin, ICBR Director Robert J. Ferl, and IFAS-ABE Chair Dorota Haman.

In January 2009, the Phase III expansion of the UF High Performance Computing (HPC) cluster was completed. The effort to build the coalition started in early 2007, with planning complete in November of 2007. This expansion brought the total computing capacity of the HPC cluster to 2,500 cores, which translates to about 10 Tflops (floating point operations per second).

The Phase III expansion effort was spearheaded with crucial initial fundraising by the Interdisciplinary Center for Biotechnology Research (ICBR) and the Institute for Food and Agricultural Sciences (IFAS). The Large Hadron Collider (LHC) and collaboration and the Open Science Grid (OSG) collaborated and several faculty in CLAS also made direct investments.

IFAS Dean of Research, Mark McLellan, 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. The HPC Center staff provided support that dramatically improved their productivity by using the cores in the cluster in parallel versus using them as individual compute servers. 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. A smaller cluster with fewer cores could not process the same set of jobs as quickly as our current HPC configuration.

IFAS Dean of Research McClellan (left) and ABE Chair Haman (right) listen as HPCC engineer Prescott (middle) shows the Phase III cluster nodes.

Working closely with 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 & aroma volatiles and drought & 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. 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.