Dr. Furlani serves as Director of the University at Buffalo's Center for Computational Research, a leading academic supercomputing center. As Director of CCR, Dr. Thomas Furlani, whose Ph.D. is in Computational Chemistry, manages the day-to-day operations of the center as well as oversees its research activities. CCR maintains an extensive array of computing resources, including an 8000 core Linux cluster and GPU based cluster. The total aggregate compute capacity of the center is more than 300 Tflop/s. One of the primary focuses of CCR is to support the New York State Center of Excellence in Bioinformatics and Life Sciences, which is comprised of UB, the Roswell Park Cancer Institute, and the Hauptman-Woodward Medical Research Institute. CCR provides several layers of support for the life sciences/bioinformatics initiatives, including access to specialized hardware and software to facilitate research, the development of customized software/databases to support data analysis (ex, REDFly), individual and group training on software packages supported by CCR, and collaboration with CCR staff to facilitate research and for proposal development.
A National Science Foundation Pre-doctoral Fellow, Dr. Furlani has more than 25 years experience in research computing and visualization, including high-performance computing, computational chemistry, and cloud computing. In addition to supporting research, Education and Outreach has been an important component of CCR's mission since its inception, with on-going K-12, undergraduate and graduate level programs. In terms of K-12 outreach, CCR each year runs the Eric Pitman Annual Summer Workshop in Computational Science. Every summer, high school sophomores, juniors, and seniors spend two weeks learning computer programming and its application to problems in chemistry, visualization, and most recently bioinformatics.
HPC Metrics on Demand: Development of metrics and auditing framework for high performance computing systems.
High performance computing (HPC) systems, more commonly known as supercomputers, are essential tools in a diverse range of areas including science, finance, oil and gas exploration, pharmaceutical drug design, and medical and basic research. Given the crucial role they play in research in the U.S., it is important to ensure that HPC systems, which are a complex combination of computer hardware and software, are operating as efficiently as possible. My research focuses on the development of XDMoD, a software tool that system support personnel and scientists can use to achieve the optimal operation of HPC systems, including the scientific computer programs that run on them. XDMoD is designed to meet the following objectives: (1) provide the user community with a tool to optimize their use of HPC resources, (2) provide operational staff with the ability to monitor, diagnose, and tune system performance as well as measure the performance of all applications running on their system, (3) provide software developers with the ability to easily obtain detailed analysis of application performance to aid in optimizing code performance, (4) provide stakeholders with a diagnostic tool to facilitate HPC planning and analysis, and (5) provide metrics to help measure scientific impact. XDMoD is used by academic, industrial, and government HPC centers worldwide, as well as by the NSF XSEDE program which oversees the largest collection of supercomputers in the world. It is available for download at http://ubmod.sourceforge.net/.
Research on the application of Green Technologies to reduce HPC center operational costs.
Our research interests lie in the implementation of state-of-the-art green technologies to reduce operational costs in high performance computing centers. An initial phase (CCR Green IT) focuses on server efficiencies while subsequent phases are focused on more efficient cooling technologies as well as a implementation of a data center monitoring system to dynamically control the data center environment to optimize energy efficiency.
Molecular electronic structure theory, algorithms for parallel computers, molecular cluster chemistry.
Our research interests are in the development and application of computational methods which can be utilized to study structure and reactivity in molecular systems. Areas of interest are as follows:
SUNY at Buffalo
701 Ellicott Street
Buffalo, New York, 14203