IT logo, Information Technology, University of OklahomaPhoto of City Skyline


OKLAHOMA SUPERCOMPUTING SYMPOSIUM 2015



OSCER

OU IT

OK EPSCoR

Great Plains Network


Table of Contents

Other speakers to be announced


PLENARY SPEAKERS

KEYNOTE SPEAKER
Jim Kurose
Jim Kurose

Assistant Director
Directorate for Computer & Information Science & Engineering (CISE)
National Science Foundation

Topic:
KEYNOTE
"Cyberinfrastructure: An NSF Update and Reflections on Architecture, Reference Models and Community"

Slides: available after the Symposium

Abstract

Cyberinfrastructure is critical to accelerating discovery and innovation across all disciplines. In order to support these advances, the National Science Foundation (NSF) supports a dynamic cyberinfrastructure ecosystem composed of multiple resources including data, software, networks, high-end computing, and people. I will discuss NSF's strategy to ensure that researchers across the U.S. have access to a diversity of these resources to continue our nation's ability to be the discovery and innovation engine of the world. I will also provide an update on cyberinfrastructure activities within NSF, and reflect on the importance of layered CI architectures and reference models for accelerating the pace of scientific discovery.

Biography

Dr. Jim Kurose is the Assistant Director of the National Science Foundation (NSF) for Computer and Information Science and Engineering (CISE). He leads the CISE Directorate, with an annual budget of more than $900 million, in its mission to uphold the nation's leadership in scientific discovery and engineering innovation through its support of fundamental research in computer and information science and engineering and transformative advances in cyberinfrastructure. Dr. Kurose is on leave from the University of Massachusetts, Amherst, where he is a Distinguished Professor in the School of Computer Science. He has also served in a number of administrative roles at UMass and has been a Visiting Scientist at IBM Research, INRIA, Institut EURECOM , the University of Paris, the Laboratory for Information, Network and Communication Sciences, and Technicolor Research Labs. His research interests include network protocols and architecture, network measurement, sensor networks, multimedia communication, and modeling and performance evaluation. Dr. Kurose has served on many national and international advisory boards. He has received numerous awards for his research and teaching, including several conference best paper awards, the IEEE Infocom Achievement Award, the ACM Sigcomm Test of Time Award, a number of outstanding teacher awards, and the IEEE/CS Taylor Booth Education Medal. With Keith Ross, he is the co-author of the textbook, Computer Networking, a top down approach (6th edition) published by Addison-Wesley/Pearson. Dr. Kurose received his Ph.D. in computer science from Columbia University and a Bachelor of Arts degree in physics from Wesleyan University. He is a Fellow of the Association for Computing Machinery (ACM) and the Institute of Electrical and Electronic Engineers (IEEE).

Henry Neeman
Henry Neeman

Assistant Vice President/Research Strategy Advisor
Information Technology
Director
OU Supercomputing Center for Education & Research (OSCER)
Information Technology
Associate Professor
College of Engineering
Adjunct Associate Professor
School of Computer Science
University of Oklahoma

Topic: "OSCER State of the Center Address"

Slides:   PowerPoint   PDF

Talk Abstract

The OU Supercomputing Center for Education & Research (OSCER) celebrated its 14th anniversary on August 31 2015. In this report, we examine what OSCER is, what OSCER does, what OSCER has accomplished in its 13 years, and where OSCER is going.

Biography

Dr. Henry Neeman is the Director of the OU Supercomputing Center for Education & Research, Assistant Vice President Information Techology – Research Strategy Advisor, Associate Professor in the College of Engineering and Adjunct Associate Professor in the School of Computer Science at the University of Oklahoma. He received his BS in computer science and his BA in statistics with a minor in mathematics from the State University of New York at Buffalo in 1987, his MS in CS from the University of Illinois at Urbana-Champaign in 1990 and his PhD in CS from UIUC in 1996. Prior to coming to OU, Dr. Neeman was a postdoctoral research associate at the National Center for Supercomputing Applications at UIUC, and before that served as a graduate research assistant both at NCSA and at the Center for Supercomputing Research & Development.

In addition to his own teaching and research, Dr. Neeman collaborates with dozens of research groups, applying High Performance Computing techniques in fields such as numerical weather prediction, bioinformatics and genomics, data mining, high energy physics, astronomy, nanotechnology, petroleum reservoir management, river basin modeling and engineering optimization. He serves as an ad hoc advisor to student researchers in many of these fields.

Dr. Neeman's research interests include high performance computing, scientific computing, parallel and distributed computing and computer science education.

Carl Grant
Carl Grant

Associate Dean &
Chief Technology Officer
University of Oklahoma Libraries
University of Oklahoma

Topic: "Panel: Are We Wrangling, Managing or Maximizing Our Organizations' Research Data?"
(Moderator)

Abstract

Organizations are facing a wide range of issues and challenges in dealing with the complexity of meeting government mandates for open access to research data. These considerations include knowing how to inventory the datasets, describe them with relevant metadata, enable and promote their access so researchers can find them, enable dataset reusability. The panel will also explore the issues involved in developing citation and curation guidelines/policies. Finally, the costs involved in doing all this will be examined, including whether these costs should be part of the Indirect Cost rates, and how that might be achieved. The goal is for the session to provide attendees a richer understanding of the full range of issues involved in maximizing their organizations' research data and to examine ideas on how to proceed.

Biography

Carl Grant is the Associate Dean & Chief Technology Officer at the University of Oklahoma Libraries. Previously, he was the Chief Librarian and President of Ex Libris North America. Mr. Grant has held senior executive positions in, and/or been the founder of, a number of other library-automation companies. He has shown his commitment to libraries, librarianship, and industry standards via his participation in the Coalition for Networked Information (CNI), the American Library Association (ALA) and the Association of College & Research Libraries (ACRL), the Library Information Technology Association (LITA), and on the board of the National Information Standards Organization (NISO), where he has held offices as board member, treasurer, and chair. Under Mr. Grant's chairmanship, NISO underwent a transformation that resulted in a revitalized library standards organization. In recognition of his contribution to the library industry, Library Journal has named Mr. Grant an "Industry Notable." Mr. Grant holds a master's degree in Library & Information Science from the University of Missouri at Columbia.

Adrian W. Alexander
Adrian W. Alexander

R. M. and Ida McFarlin Dean of the Library
McFarlin Library
University of Tulsa
Topic: "Panel: Are We Wrangling, Managing or Maximizing Our Organizations' Research Data?"

Panel Abstract

Organizations are facing a wide range of issues and challenges in dealing with the complexity of meeting government mandates for open access to research data. These considerations include knowing how to inventory the datasets, describe them with relevant metadata, enable and promote their access so researchers can find them, enable dataset reusability. The panel will also explore the issues involved in developing citation and curation guidelines/policies. Finally, the costs involved in doing all this will be examined, including whether these costs should be part of the Indirect Cost rates, and how that might be achieved. The goal is for the session to provide attendees a richer understanding of the full range of issues involved in maximizing their organizations' research data and to examine ideas on how to proceed.

Biography

Adrian Alexander has served as the first R. M. and Ida McFarlin Dean of the McFarlin Library at the University of Tulsa since February 2007. Prior to that, he was the first Executive Director of the Greater Western Library Alliance, a non-profit consortium representing 31 academic research libraries. In his nine years at GWLA, he organized and managed a variety of collaborative library projects, including cooperative collection development, electronic database licensing, digital library development, electronic publishing, and interlibrary loan. He also spent 13 years on the commercial side of the information industry, in a variety of sales, sales management and marketing management roles with a major serials subscription company. Adrian was also a co-founder of BioOne, Inc., a not-for-profit, electronic publishing enterprise that launched a new scholarly publishing model based on collaboration between scholarly societies and academic libraries.

Adrian holds a Masters' degree in Library Science and a Certificate of Advanced Study in academic library administration from the University of North Texas. He is also the 2010 recipient of the Outstanding Alumnus Award from the College of Information at the University of North Texas.

Jennifer Fitzgerald
Jennifer Fitzgerald

Data Curator
Library
Samuel Roberts Noble Foundation
Topic: "Panel: Are We Wrangling, Managing or Maximizing Our Organizations' Research Data?"

Panel Abstract

Organizations are facing a wide range of issues and challenges in dealing with the complexity of meeting government mandates for open access to research data. These considerations include knowing how to inventory the datasets, describe them with relevant metadata, enable and promote their access so researchers can find them, enable dataset reusability. The panel will also explore the issues involved in developing citation and curation guidelines/policies. Finally, the costs involved in doing all this will be examined, including whether these costs should be part of the Indirect Cost rates, and how that might be achieved. The goal is for the session to provide attendees a richer understanding of the full range of issues involved in maximizing their organizations' research data and to examine ideas on how to proceed.

Biography

Jennifer Fitzgerald is the data curator at the Samuel Roberts Noble Foundation Library. Her involvement includes new employee orientations, oversight of the electronic laboratory notebook (ELN) for researchers, recommendations and training for the Foundation's upcoming enterprise content management system, and serving on the Data Management Committee. She received a master's degree from Southeastern Oklahoma State University in 2009.

Mark Laufersweiler
Mark Laufersweiler

Research Data Specialist
University of Oklahoma Libraries
University of Oklahoma

Topic: "Panel: Are We Wrangling, Managing or Maximizing Our Organizations' Research Data?"

Abstract

Organizations are facing a wide range of issues and challenges in dealing with the complexity of meeting government mandates for open access to research data. These considerations include knowing how to inventory the datasets, describe them with relevant metadata, enable and promote their access so researchers can find them, enable dataset reusability. The panel will also explore the issues involved in developing citation and curation guidelines/policies. Finally, the costs involved in doing all this will be examined, including whether these costs should be part of the Indirect Cost rates, and how that might be achieved. The goal is for the session to provide attendees a richer understanding of the full range of issues involved in maximizing their organizations' research data and to examine ideas on how to proceed.

Biography

Dr. Mark Laufersweiler has always had a strong interest in computers, computing, data and data visualization. Upon completing his post-doc work for the Atmospheric Radiation Measurement (ARM) program, he was the lead computer systems administrator for 3.5 years serving the Florida State University Department of Earth, Ocean and Atmospheric Science. He was then the Computer Systems Coordinator for the University of Oklahoma School of Meteorology from 1999-2013. Part of his duties included managing the real time data feed and maintaining the departmental data archive. He assisted with faculty in their courses to help foster computing skills needed for the classroom and instruction based on current best practices regarding research data and code development. Since the Fall of 2013, he has served as the Research Data Specialist for the University of Oklahoma Libraries. He is currently assisting the educational mission of the Libraries by developing and offering workshops, seminars and short courses, helping to inform the university community on best practices for data management and data management planning. He is also working on the formation of a data repository to host research data generated by the university community. He is a strong advocate of open source software and open access to data.

In 2008, Dr. Laufersweiler was awarded the Russell L. DeSouza Award. This award, sponsored by Unidata is for individuals whose energy, expertise, and active involvement enable the Unidata program to better serve geoscience. Honorees personify Unidata's ideal of a community that shares data, software, and ideas through computing and networking technologies.

Robin Leech
Robin Leech

Associate Dean for Library Operations
Oklahoma State University
Topic: "Panel: Are We Wrangling, Managing or Maximizing Our Organizations' Research Data?"

Panel Abstract

Organizations are facing a wide range of issues and challenges in dealing with the complexity of meeting government mandates for open access to research data. These considerations include knowing how to inventory the datasets, describe them with relevant metadata, enable and promote their access so researchers can find them, enable dataset reusability. The panel will also explore the issues involved in developing citation and curation guidelines/policies. Finally, the costs involved in doing all this will be examined, including whether these costs should be part of the Indirect Cost rates, and how that might be achieved. The goal is for the session to provide attendees a richer understanding of the full range of issues involved in maximizing their organizations' research data and to examine ideas on how to proceed.

Biography

Robin Leech is Associate Dean for Library Operations at Oklahoma State University, supervising Technical Services, Systems, Digital Initiatives and Access Services. She lead the OSU institutional repository team in the development of SHAREOK.org, a joint repository with the University of Oklahoma Libraries. After completion of an MLS from the University of Oklahoma, she worked in a wide variety of libraries: public, school and academic. Since 1990, Robin has concentrated in academic library automation/technical services, first at the OSU-Tulsa campus Library, and since 2006, at the main OSU Campus in Stillwater, Oklahoma.

Robin is a member of the American Library Association (ALA), the Association of College & Research Libraries (ACRL), the Library Information Technology Association (LITA), the Oklahoma Chapter of ACRL, the Oklahoma Library Association, and the Society of Southwest Archivists.

Habib Tabatabai
Habib Tabatabai

Executive Director
Chambers Library
University of Central Oklahoma
Topic: "Panel: Are We Wrangling, Managing or Maximizing Our Organizations' Research Data?"

Panel Abstract

Organizations are facing a wide range of issues and challenges in dealing with the complexity of meeting government mandates for open access to research data. These considerations include knowing how to inventory the datasets, describe them with relevant metadata, enable and promote their access so researchers can find them, enable dataset reusability. The panel will also explore the issues involved in developing citation and curation guidelines/policies. Finally, the costs involved in doing all this will be examined, including whether these costs should be part of the Indirect Cost rates, and how that might be achieved. The goal is for the session to provide attendees a richer understanding of the full range of issues involved in maximizing their organizations' research data and to examine ideas on how to proceed.

Biography:

Habib Tabatabai currently serves as the Executive Director of Chambers Library at the University of Central Oklahoma (UCO). He has more than 25 years of experience working and leading in the library profession, implementing and using technology to facilitate research, discovery, and preservation for UCO users. He is the current Chair of Ex Libris Users of North America (ELUNA), which advocates on behalf of close to 3500 libraries worldwide to improve user experience and student learning.

Monica Martinez-Canales
Monica Martinez-Canales

Principal Engineer and Director of Big Data for Science and Technology
Big Data Pathfinding Group
Intel Corp

Topic: "How HPC is Central to Bringing Next Generation Sequencing from the Lab to the Patient"
(with Stephen Wheat)

Slides:   PDF

Talk Abstract

Next Generation Sequencing (NGS), the basis for volume sequencing enablement, has been around for several years. The volume of sequencers deployed per year remains on an exponential growth path. Nevertheless, the vision of sequencing-enabled personalized medicine has come to fruition for relatively few people. The community consensus is that bringing this to large populations remains 5-7 years out. Nevertheless, some projects are underway to path-find means to accelerate this. In this talk, we will review the solution architecture that will enable this from a technology perspective. Furthermore, we will review the efforts of the Intel/HP HPC Alliance with respect to driving these solutions into actual implementation. While the solutions architecture will be focused on the NGS work flow, the elements of the architecture are pertinent to other HPC work flows.

Biography

Monica Martinez-Canales is Principal Engineer and Director of Big Data for Science and Technology in the Big Data Pathfinding Group at Intel Corporation. The Pathfinding team is focused on end-to-end research and development to accelerate scientific and technological big data, predictive analytics, and high performance computing efforts.

Monica joined Intel in 2008 leading Strategic Initiatives in Validation Business Intelligence and Analytics programs within the Platform Validation Engineering Group. Monica's work on dynamic risk-based resource allocation strategies, under schedule pressure and resource constraints, enabled the on-time completion of post-silicon validation of the 4th generation Intel CPU family of products, including a market-responsive ultra-low power derivative.

Prior to joining Intel, Monica had been a Principal Member of the Technical Staff at Sandia National Laboratories, leading award-winning research in verification, validation, and quantifications of margins under uncertainty in complex systems within defense and energy programs.

Monica completed a National Science Foundation Post-Doctoral Fellowship at Stanford University. Monica earned a Ph.D. in Computational and Applied Mathematics from Rice University and received a B.S. in Mathematics from Stanford University. Monica is author of multiple peer-reviewed journal articles.

Stephen Wheat
Stephen Wheat

Director, HPC Pursuits
Hewlett-Packard

Topic: "How HPC is Central to Bringing Next Generation Sequencing from the Lab to the Patient"
(with Monica Martinez-Canales)

Slides:   PDF

Talk Abstract

Next Generation Sequencing (NGS), the basis for volume sequencing enablement, has been around for several years. The volume of sequencers deployed per year remains on an exponential growth path. Nevertheless, the vision of sequencing-enabled personalized medicine has come to fruition for relatively few people. The community consensus is that bringing this to large populations remains 5-7 years out. Nevertheless, some projects are underway to path-find means to accelerate this. In this talk, we will review the solution architecture that will enable this from a technology perspective. Furthermore, we will review the efforts of the Intel/HP HPC Alliance with respect to driving these solutions into actual implementation. While the solutions architecture will be focused on the NGS work flow, the elements of the architecture are pertinent to other HPC work flows.

Biography

Dr. Stephen Wheat is the Director of the HPC Pursuits team within Hewlett-Packard's HPC business unit. In this role, he is responsible for driving higher-end HPC world-wide business strategies to meet the challenges of leadership-class institutions. Having recently joined HP's HPC business unit, Dr. Wheat brings his 35-year HPC career to bear on his new role. He started in the Oil and Gas applications domain in Houston, then going to AT&T Bell Labs, where the majority of his tenure was on parallel HPC systems software for sonar processing, then going to Sandia National Labs, where his research was in massively parallel systems software. It was during his tenure at Sandia that he won the 1994 Gordon Bell Prize for performance. Subsequently, he spent 20 years at Intel, where he served in many leadership HPC roles, including being WW GM of HPC.

Dr. Wheat's Ph.D. is in Computer Science, with a focus on massively parallel systems software. His M.S. and B.S. were also in Computer Science.

Dr. Wheat's extracurricular activities include photography, recreational bicycling, and flying, where he is a commercial multi-engine pilot and certified flight instructor for instrument/multi-engine aircraft.

He is the father of four and grandfather of nine. He and his wife of 35 years, Charlene, live in Houston, Texas.


BREAKOUT SPEAKERS

Kate Adams

Research Assistant
Great Plains Network

Topic: "All About ENCITE Metrics"

Slides:   PowerPoint   PDF

Talk Abstract

ENCITE is the Great Plains Network's National Science Foundation Campus Cyberinfrastructure – Infrastructure, Innovation and Engineering (CC*IIE) grant, a two year grant that started in August 2014. ENCITE provides training on networking topics. Network engineers use this information to help researchers get their research done. This talk will discuss metrics of success of the project so far.

Biography

Kate Adams has been with the Great Plains Network since November of 2009. She is the project coordinator for ENCITE, helps facilitate various working groups, keeps the website up to date, and is the system administrator, layout artist, and was also GPN's first regional XSEDE Champion. She enjoys sewing, writing, gardening, and martial arts in her free time.

Daniel Andresen
Daniel Andresen

Associate Professor
Department of Computing & Information Sciences
Kansas State University
Director
Institute for Computational Research

Topic: "Big Storage, Little Budget" (with Kyle Hutson and Adam Tygart)

Slides: available after the Symposium

Abstract

Kansas State University's HPC cluster was running out of storage space last year. Vendors of traditional HPC storage solutions were either too expensive to be feasible or too little capacity to be of long-term use.  The system that ended up providing the best storage capacity for the available budget was Ceph, an open-source project that provides storage striped across many commodity servers. This session is a case study of the pros and cons of our implementation of a 1.5 PB Ceph-based storage cluster, discussing the history of network-based filesystems, including why our previous Gluster-based was no longer suitable.  Questions and discussion are encouraged.

Biography

Daniel Andresen, Ph.D. is an associate professor of Computing & Information Sciences at Kansas State University and Director of the Institute for Computational Research. His research includes embedded and distributed computing, biomedical systems, and high performance scientific computing. Dr. Andresen coordinates the activities of the K-State research computing cluster, Beocat, and advises the local chapter of the Association for Computing Machinery (ACM). He is a National Science Foundation CAREER award winner, and has been granted research funding from the NSF, the Defense Advanced Research Projects Agency (DARPA), and industry. He is a member of the Association for Computing Machinery, the IEEE Computer Society, the Electronic Frontier Foundation, and the American Society for Engineering Education.

Joseph A. Babb
Joseph A. Babb

Electronics Engineer
Innovation and High Performance Computing Center
Tinker Air Force Base
US Air Force

Topic: "Parallel Techniques for Physics-Based Storm Simulation and Rendering in Real-Time Applications"

Slides: available after the Symposium

Talk Abstract

Commercial flight simulators are used by the military and commercial airlines in order to provide pilots with regular training and evaluation. Unfortunately, these flight simulators have many shortcomings when compared to reality, including a notable lack of adequate weather simulation. Every pilot has to deal with bad weather such as wind shears, turbulence, limited visibility, and precipitation. Despite this, modern commercial flight simulators are incapable of simulating realistic, physics-based weather, and instead either rely on artistically crafted weather or have no weather at all. In order to close this gap, we utilize modern high-performance computing hardware and software to enhance a flight simulator with physics-based weather, allowing for improved pilot training and evaluation. The technologies utilized include the TARDIS supercomputer at Tinker Air Force Base, OU's Advanced Regional Prediction System weather model, NVIDIA CUDA, OpenMP, and the GL shading language.

Biography

Joseph Babb is a Software Engineer at Tinker Air Force Base's Innovation and High Performance Computing Center. He is currently working as the Lead Developer on their Flight Simulation Enhancement initiative.

Joseph graduated with his MS in Computer Science from Arizona State University in 2013. His research focused on Artificial Intelligence and Knowledge Representation and resulted in his thesis entitled "Towards Efficient Online Reasoning about Actions" and a number of conference and journal publications. While attending ASU, he was awarded a number of honors, including selection for the national Science, Mathematics & Research for Transformation (SMART) fellowship program.

Dana Brunson
Dana Brunson

Director
High Performance Computing Center
Adjunct Associate Professor
Department of Computer Science
Oklahoma State University

Topic: "What's New at OSU!"

Slides: available after the Symposium

Abstract

Significant growth in computational and data-intensive research has driven investment in OSU's HPC Center. Highlights include two new full time staff, a new research cloud and a $950K+ NSF award.

Biography

Dana Brunson is Director of the Oklahoma State University High Performance Computing Center (OSUHPCC), Adjunct Associate Professor in the Department of Mathematics and in the Department of Computer Science, and co-leads the OneOklahoma Cyberinfrastructure Initiative (OneOCII). She earned her Ph.D. in Mathematics at the University of Texas at Austin in 2005 and her M.S. and B.S. in Mathematics from OSU. She is PI on OSU's 2011 and new 2015 National Science Foundation (NSF) Major Research Instrumentation (MRI) grants for High Performance Compute clusters for multidisciplinary computational and data-intensive research. She is also co-PI on Oklahoma's NSF Campus Cyberinfrastructure - Network Infrastructure and Engineering CC-NIE grant, "OneOklahoma Friction Free Network" (OFFN), a collaboration among OSU, OU, Langston University and the Tandy Supercomputing Center of the Oklahoma Innovation Institute. Brunson became an XSEDE (initially Teragrid) Campus Champion in 2009. She joined the CC leadership team in 2012. OSUHPCC joined the XSEDE Federation as a Level 3 Service Provider in 2014 and Brunson was elected chair of the XSEDE Level 3 Service Providers in January 2015.

Kashif Chauhan
Kashif Chauhan

Senior System Engineer
Mellanox Technologies

Topic: "New Era of Performance through Co-Design"
(with D. Kent Snider)

Slides:   PDF

Abstract

Mellanox InfiniBand technology is the foundation for scalable and performance demanding computing infrastructures. Delivering more than 100Gb/s throughput, sub 700ns application to application latency and message rates of 150 million messages per second has already placed ConnectX-4 EDR 100Gb/s technology in the Top500 list of the world's most powerful and efficient supercomputers. We will discuss the latest interconnect advancements that maximize application performance and scalability through the concept of co-design, an industry driven concept that accelerates the path to Exascale.

Biography

Mr. Kashif Chauhan currently holds a Senior Systems Engineer position at Mellanox Corporation. He is responsible for delivering engineering and expertise in areas of High Performance Computing, Big Data, and Cloud Computing. He has 15+ years in the technology business, covering pre-sales, consulting and engineering. His consulting experience entails engagement with global customers in various verticals, including Oil & Gas, Financial, and Retail. Prior to Mellanox, Mr. Chauhan had an extensive tenure at Cisco Systems consulting with Enterprise customers. He is a graduate of the University of Houston.

Bob Collins
Bob Collins

Regional Account Manager
Qumulo

Topic: "Using Real-Time Analytics to Better Manage Your Data with Qumulo Core Software"

Slides: available after the Symposium

Abstract

Join us for a 30-minute seminar with Bob Collins (Regional Account Manager at Qumulo) to learn how Qumulo's next generation data-aware scale-out NAS leverages its real-time analytics to help you better manage your data. In this seminar you will learn how to:

  • Understand your data repository at the file level using Qumulo Core's real-time file system analytics.
  • Eliminate silos of storage using a single storage namespace for all data.
  • Achieve transparent capacity and IO expansion with a linear scale-out storage architecture
  • Customize your environment via programmable REST API
  • Optimize your storage infrastructure for both sequential write index, random search as well as hot, warm and cold data.

Biography

A seasoned IT veteran with 19+ years of highly successful sales and systems engineering leadership in the storage industry, Bob's credentials were built around designing advanced and complex IT datacenter architectures, spanning a wide set of software and hardware technologies from storage and networking companies such as EMC, NetApp, Brocade, Cisco and Isilon, among many others. As the Regional Account Manager for the Texas-Oklahoma-Louisiana-Arkansas area, he is evangelizing the second generation of scale-out high performance NAS that leverages data awareness capability for his company, Qumulo.

Eduardo Colmenares
Eduardo Colmenares

Assistant Professor
Computer Science Department
Midwestern State University

Topic: "A Data Communication Reliability and Trustability Study for Cluster Computing"

Slides:   PowerPoint   PDF

Abstract

In High Performance Computing (HPC), most of the problems under study will be either embarrassingly parallel or data dependent. Beyond the nature of the problem, scientists will be interested in either one or two additional characteristics. The first, performance, focuses in achieving an accurate solution in a fraction of the time of a sequential approach. The second is consecutive, accurate and steady time readings. In their quest for performance, some scientists forget not only that the chosen tool, in many cases a distributed-memory system, is a multi-user system, but also that its components are interconnected through a high-speed communications network to facilitate the interaction among processors. In this talk, we show why a cluster characterization is relevant, particularly for scientific kernels where multiple accurate and consecutive time readings are necessary to statistically validate a behavior. We present the characterization of two clusters by using two variants of the ping pong test. One of the clusters is a multi-user research oriented cluster, while the second is a one-user cluster with older technology.

Biography

Dr. Eduardo Colmenares is an Assistant Professor of Computer Science at Midwestern State University. He received his BS in Electronics Engineering from the Industrial University of Santander, Colombia, his Master of Science and PhD in Computer Science from Texas Tech University, both with Focus in High Performance Computing and Scientific Computing. For his doctoral work at Texas Tech University, Dr. Colmenares studied a kernel of scientific relevance in multiple fields of science, the All-Pairs Shortest Path (APSP) problem. He developed an algorithmically restructured solution for the APSP that makes use of non-blocking features supported by a heterogeneous multi-core architecture, in order to minimize the effects of the intense data sharing among processors and to target better performance than the traditional and pipelined approaches.

Bob Crovella
Bob Crovella

Solutions Architect
Tesla Sales
NVIDIA

Topic: "NVIDIA Accelerated Computing Frontiers in HPC, Scientific Computing and Deep Learning"

Slides: available after the Symposium

Abstract

NVIDIA Graphics Processing Units (GPUs) are the world's fastest and most power efficient accelerators, delivering world record scientific application performance. Learn how recent advances in NVIDIA Tesla solutions are enabling software developers and end users to obtain maximum performance and power efficiency for their workloads. Topics to be covered will include a brief Tesla High Performance Computing (HPC) roadmap, CUDA and OpenACC updates, a brief review of GPU enabled applications, and an update on why GPUs are driving innovations in Deep Learning.

Biography

Bob Crovella leads a technical team at NVIDIA that is responsible for supporting the sales of our GPU Computing products through our Original Equipment Manufacturer (OEM) partners and systems. Bob joined NVIDIA in 1998. Previous to his current role at NVIDIA, he led a technical team that was responsible for the design-in support of our GPU products into OEM systems, working directly with the OEM engineering and technical staffs responsible for their respective products. Prior to joining NVIDIA, Bob held various engineering positions at Chromatic Research, Honeywell, Cincinnati Milacron, and Eastman Kodak. Bob holds degrees from Rensselaer Polytechnic Institute (M. Eng., Communications and Signal Processing) and The State University of NY at Buffalo (BSEE). He resides with his family in the Dallas TX area.

Nicholas A. Davis
Nicholas A. Davis

Assistant Professor of Research
Department of Medical Informatics
School of Community Medicine
University of Oklahoma - Tulsa

Topic: "Exploring Adverse Drug Effect Data Using Apache Spark, Hadoop, and Docker"

Slides:   PDF

Abstract

Adverse drug reactions (ADRs), a subset of the broader adverse events (AEs), have been shown in several studies to have a considerable burden on healthcare costs and patient outcomes. ADRs account for a significant increase in patient morbidity, mortality, and additional healthcare costs. In this presentation, we explore ADRs and AEs from the U.S. Food and Drug Administration's Adverse Event Reporting System (FAERS) data set. Using big data analysis tools from the Hadoop ecosystem, including Apache Spark, we analyze the FAERS data and discuss interesting trends and observations in the 10+ year historical data set.

Biography

Dr. Nicholas Davis is Assistant Professor of Research in Medical Informatics at the University of Oklahoma-Tulsa School of Community Medicine. He received his BS in Computer Science with a minor in Mathematics, his MS in Computer Science with a focus in Information Security, and his PhD in Computer Science, all from the University of Tulsa (TU). For his doctoral work at TU, Dr. Davis performed research in bioinformatics, focusing on genomic analysis of immune response data sets and analysis of fMRI brain imaging data to identify regions of interest. In addition to his academic experience, Dr. Davis has accumulated over a decade of industry experience in a variety of technology roles, such as software development and architecture, network and system administration, and information security, including being a Certified Information Systems Security Professional (CISSP). He is inventor on a patent for Methods and Systems for Graphical Image Authentication.

His current projects include analysis of type 1 diabetes mellitus data to determine insulin pump settings correlated to improved glycemic outcomes, as well as data mining of clinical and claims data sets to understand and create predictive models of medication adherence across multiple dimensions. Dr. Davis's research interests include analysis of electronic health record and claims data, data science algorithms and tools, machine learning/statistical inference, diabetes, medication adherence, integrative analysis of heterogeneous biological data sets, and high performance computing.

Dan DeBacker
Dan DeBacker

Principal Systems Engineer
Americas Sales
Brocade Communications Systems, Inc.

Topic: "Software Defined Networking – That's the answer, What's the question?"

Slides:   PowerPoint   PDF

Abstract

Oh no, not another SDN presentation talking about a bunch of new techie acronyms that mean nothing to me. Well, there will be some of that here, however in this presentation you'll also get a perspective on SDN in regard to the reality of its use. There is no doubt that SDN will touch every network in some shape, form or fashion in the future. How and to what extent will vary greatly. This presentation will focus on the technologies of SDN and real life use case implementations to solve real life issues.

Biography

Dan DeBacker, Principal Systems Engineer, Americas, provides subject matter expertise in all aspects of Brocade's Ethernet and Software Defined Networking solutions. He is engaged in large, strategic account opportunities offering insight to address customer business requirements and providing Brocade's long term vision for data networking.

A tech veteran for more than 25 years, Dan is valued for his communication skills, customer-first mentality and transparency. His vast industry experience in dealing with large customers worldwide enables him to help solve complex customer needs, create new business opportunities and utilize skills in strategic planning, team building and business development.

Prior to Brocade, Dan held positions within systems engineering, office of the Chief Technology Officer and product/solution management at Bay Networks / Nortel / Avaya. Dan also held various positions within the IT organizations of Ford Motor Company.

Dan holds a Bachelor of Science degree in Computer and Information Systems as well as an MBA from the University of Michigan.

Kendra Dresback
Kendra Dresback

Research Assistant Professor
School of Civil Engineering & Environmental Science
University of Oklahoma

Topic: "Initial Steps to Optimizing a Shallow-Water Model, ADCIRC, for the Intel(R) Xeon Phi Co-processors"

Slides: available after the Symposium

Abstract

Coming soon

Biography

Dr. Kendra M. Dresback is a Research Assistant Professor in the School of Civil Engineering & Environmental Science at the University of Oklahoma. She received her PhD in Civil Engineering at the University of Oklahoma. Her MS thesis investigated a predictor-corrector time-marching algorithm to achieve accurate results in less time using a finite element-based shallow water model; her dissertation focused on several algorithmic improvements to the same finite element-based shallow water model, ADCIRC. She has published papers in the area of computational fluid dynamics. Dr. Dresback's research includes the use of computational models to help in the prediction of hurricane storm surge and flooding in coastal areas and the incorporation of transport effects in coastal seas and oceans in ADCIRC. Her research has been supported with funding from the National Science Foundation, the US Department of Education, the Office of Naval Research, the US Department of Defense EPSCoR, the US Department of Homeland Security, NOAA and the US Army Corp of Engineers.

James W. Ferguson
James Ferguson

Education, Outreach, and Training Director
National Institute for Computational Sciences
University of Tennessee Knoxville

Topic: "XSEDE and its Campus Bridging Project"

Slides:   PowerPoint   PDF

Talk Abstract

We will give a brief overview of the NSF-funded Extreme Science and Education Discovery Environment (XSEDE) project and then detail its Campus Bridging effort. Within XSEDE, Campus Bridging is a combination of tools, people, and technical expertise, striving to bring resources in data, storage, and compute power close enough to the user so as to appear to be peripheral devices on their own desktop machine. The tools and other features of this effort do not require a connection to XSEDE; they can be used to increase productivity independently.

Biography

Jim Ferguson is the Director of Education, Outreach & Training for the National Institute for Computational Sciences (NICS) at the University of Tennessee Knoxville. His responsibilities include coordinating a wide range of outreach and education related activities associated with NICS, as well as varied responsibilities in the XSEDE project in the Training and Campus Bridging efforts. Jim has served on many workshop and conference organizing committees, with current efforts including the upcoming SCxy Conferences and the International HPC Summer School series.

Before joining NICS, Jim's focus was programming for, training, and educating users of high performance computers and networks. Jim's previous experience includes positions at Pratt & Whitney Aircraft and the National Center for Supercomputing Applications, including significant roles in NSF-funded projects like the National Laboratory for Applied Network Research and Web100. Jim is an alumnus of Rose-Hulman Institute of Technology.

Karl Frinkle
Karl Frinkle and Mike Morris

Professor
Department of Mathematics
Southeastern Oklahoma State University

Topic: "Parallel Programming in the Classroom - Analysis of Genome Data"
(with Mike Morris)

Slides: available after the Symposium

Abstract

Over the course of a semester, students enrolled in an HPC seminar class created a suite of human genome analysis tools on the Beowulf clusters that they and other students built. The analysis tools were written with C and MPI and subsequently interfaced with a LAMP (Linux, Apache, MySQL, and PHP) website through the use of scripts. The output was visualized with the help of Google Charts. We will discuss the technical details of this project and demonstrate how these tools can be used to analyze multiple human genomes simultaneously.

Biography

Karl Frinkle is an applied mathematician who earned his PhD from the University of New Mexico. He is deeply interested in numerical simulations, and most recently in parallel programming. Karl joined the SE Mathematics department in 2005, and thoroughly enjoys teaching parallel programming courses with Mike Morris through the CS department.

John Hale
John Hale

Professor of Computer Science
Tandy Professor of Bioinformatics and Computational Biology
Tandy School of Computer Science
University of Tulsa

Topic: "Building an Exotic HPC Ecosystem at The University of Tulsa"
(with Andrew Kongs and Peter J. Hawrylak)

Slides: available after the Symposium

Talk Abstract

This talk covers the in-progress journey of the Tandy School of Computer Science at The University of Tulsa to build a unique high performance computing (HPC) ecosystem for researchers and students. The presenters motivate and describe the launch of TU's initial HPC point of presence — a traditional CPU cluster — along with lessons learned from that process. They also discuss ongoing work to stand up two distinct heterogeneous compute node clusters and the challenging research problems they will be used to address. Objectives and developments in leveraging these HPC resources in the classroom will be presented. In addition to passing along some wisdom picked up along the way, the presenters will reveal their plans for the future of TU's evolving HPC ecosystem.

Biography

Dr. John Hale is a Professor of Computer Science and holds the Tandy Endowed Chair in Bioinformatics and Computational Biology at the University of Tulsa. He is a founding member of the TU Institute of Bioinformatics and Computational Biology (IBCB), and a faculty research scholar in the Institute for Information Security (iSec). His research has been funded by the US Air Force, the National Science Foundation (NSF), the Defense Advanced Research Projects Agency (DARPA), the National Security Agency (NSA), and the National Institute of Justice (NIJ). These projects include research on neuroinformatics, cyber trust, information privacy, attack modeling, secure software development, and cyber-physical system security. He has testified before Congress on three separate occasions as an information security expert, and in 2004 he was awarded a patent on technology he co-developed to thwart digital piracy on file sharing networks. In 2000, Professor Hale earned a prestigious NSF CAREER award for his educational and research contributions to the field of information assurance.

Peter J. Hawrylak
Peter Hawrylak

Assistant Professor
Tandy School of Computer Science
Assistant Professor
Department of Electrical and Computer Engineering
The University of Tulsa

Topic: "Building an Exotic HPC Ecosystem at The University of Tulsa"
(with Andrew Kongs and John Hale)

Slides: available after the Symposium

Talk Abstract

This talk covers the in-progress journey of the Tandy School of Computer Science at The University of Tulsa to build a unique high performance computing (HPC) ecosystem for researchers and students. The presenters motivate and describe the launch of TU's initial HPC point of presence — a traditional CPU cluster — along with lessons learned from that process. They also discuss ongoing work to stand up two distinct heterogeneous compute node clusters and the challenging research problems they will be used to address. Objectives and developments in leveraging these HPC resources in the classroom will be presented. In addition to passing along some wisdom picked up along the way, the presenters will reveal their plans for the future of TU's evolving HPC ecosystem.

Biography

Peter J. Hawrylak, Ph.D. (M'05) received the B.S. degree in Computer Engineering, the M.S. degree in Electrical Engineering, and the Ph.D. in Electrical Engineering from the University of Pittsburgh, in 2002, 2004, and 2006, respectively. He is an Assistant Professor in the Department of Electrical and Computer Engineering, with a joint appointment in the Tandy School of Computer Science, at The University of Tulsa. He has published more than 40 publications and holds 12 patents in the radio frequency identification (RFID) and energy harvesting areas. His research interests include RFID, security for low-power wireless devices, Internet of Things applications, and digital design. Dr. Hawrylak is a member of the IEEE and IEEE Computer Society, and is currently the Secretary of the Tulsa Section of the IEEE. He served as chair of the RFID Experts Group (REG) of the Association for Automatic Identification and Mobility (AIM) in 2012-2013. Peter received AIM Inc.'s Ted Williams Award in 2015 for his contributions to the RFID industry. Dr. Hawrylak is the Publication Co-Chair of the International IEEE RFID Conference, and is the Editor-in-Chief of the International Journal of Radio Frequency Identification Technology and Applications (IJRFITA) journal published by InderScience Publishers, which focuses on the application and development of RFID technology.

Kyle Hutson
Kyle Hutson

System Administrator
Department of Computing & Information Sciences
Kansas State University

Topic: "Big Storage, Little Budget" (with Dan Andresen and Adam Tygart)

Slides: available after the Symposium

Abstract

Kansas State University's HPC cluster was running out of storage space last year. Vendors of traditional HPC storage solutions were either too expensive to be feasible or too little capacity to be of long-term use.  The system that ended up providing the best storage capacity for the available budget was Ceph, an open-source project that provides storage striped across many commodity servers. This session is a case study of the pros and cons of our implementation of a 1.5 PB Ceph-based storage cluster, discussing the history of network-based filesystems, including why our previous Gluster-based was no longer suitable.  Questions and discussion are encouraged.

Biography

Kyle Hutson has been involved with Linux system administration since 1994. He received his bachelor's degree from Kansas State University in computer engineering in 1995. He has worked in non-profit, public sector, and public sector IT services, including several years as a small business IT consultant. Kyle joined Kansas State University's HPC team in 2012.

Utkarsh Kapoor
Utkarsh Kapoor

PhD Graduate Student
School of Chemical Engineering
Oklahoma State University

Topic: "Thermo-physical and Structural Properties of Imidazolium Based Binary Ionic Liquid Mixtures from Molecular Simulation"

Slides: available after the Symposium

Talk Abstract

Ionic liquids (ILs) are novel chemical substances composed entirely of ions. Unlike common salts, ILs can be synthesized to exist as liquid under ambient conditions. Many ILs do not evaporate and hence are dubbed as "environmentally friendly," making them attractive candidates for replacement of volatile organic compounds used in chemical industry. ILs are also known as "designer solvents," as their properties can be fine-tuned by varying the cations and anions independently. The number of such possible combinations can be increased dramatically by forming mixtures of ILs. In this presentation, we report the predictions of structural and thermo-physical properties, obtained by Molecular dynamics atomistic simulations of two binary ILs over a range of temperature. One of the binary mixtures contained the cation 1-n-butyl-3-methylimidazolium [C4mim]+ while different mole fractions of chloride [Cl]- and methyl sulfate [MeSO4]- were investigated. Another binary IL mixture was composed of [C4mim]+ in combination with different mole fractions of [Cl]- and bis(trifluoromethanesulfonyl)imide [NTf2]- anions. The mixture behavior was quantified in terms of thermodynamic properties such as excess molar volume and excess residual enthalpy. The observed non-ideal behavior of IL mixtures will be explained in terms of three-dimensional probability plots of anion distributions around the cation [C4mim]+ and enhancement of local mole fraction suggesting the manner vicinity of cation and anion changes by change in composition. Also, transport properties like self-diffusion coefficients and ionic conductivity were predicted and reasoned based on ion pair correlated motion.

Biography

Utkarsh Kapoor received his Bachelor's degree in Chemical Engineering from Birla Institute of Technology and Science (BITS) – Pilani, Rajasthan, India in 2012. Thereafter, he worked as Process Engineer in Grasim Industries Ltd. (chemical division), Aditya Birla Group (ABG) for a year and a half with focus on manufacturing caustic soda solution. He was also part of the plant commissioning team when initially he was stationed at ABG, sulphites division, Thailand. He has been pursuing Ph.D. program in School of Chemical Engineering at Oklahoma State University since fall 2014, with a special focus on predicting various properties of solvents such as ionic liquids using the power of computational simulations. He is a recipient of Halliburton Graduate Fellowship from OSU's College of Engineering, Architecture and Technology (CEAT), and is working as Creativity, Innovation and Entrepreneurship Scholar, having received a scholarship from OSU's Spears School of Business for academic year 2015-16. He also received the Graduate College top-tier fellowship for academic year 2014-15. He is also involved as Vice President of OSU Automation Society (OSUAS) and General Secretary of OSU's Chemical Engineering Graduate Student Association (ChEGSA), where he helps the team in planning and organizing various technical and social events.


Andrew Kongs

Research Staff
Tandy School of Computer Science
University of Tulsa

Topic: "Building an Exotic HPC Ecosystem at The University of Tulsa"
(with John Hale and Peter J. Hawrylak)

Slides: available after the Symposium

Talk Abstract

This talk covers the in-progress journey of the Tandy School of Computer Science at The University of Tulsa to build a unique high performance computing (HPC) ecosystem for researchers and students. The presenters motivate and describe the launch of TU's initial HPC point of presence — a traditional CPU cluster — along with lessons learned from that process. They also discuss ongoing work to stand up two distinct heterogeneous compute node clusters and the challenging research problems they will be used to address. Objectives and developments in leveraging these HPC resources in the classroom will be presented. In addition to passing along some wisdom picked up along the way, the presenters will reveal their plans for the future of TU's evolving HPC ecosystem.

Biography

Andrew Kongs is Research Staff at The University of Tulsa. His specialties include prototyping, enterprise networking, embedded systems, printed circuit board design and digital forensics. He designed, built and manages Anvil, a general purpose cluster at the University of Tulsa. He has designed electronics and instrumentation for research and teaching purposes.

Scott Lathrop
Scott Lathrop

XSEDE Director for Education and Outreach
Shodor Education Foundation, Inc.
Blue Waters Technical Program Manager for Education
National Center for Supercomputing Applications

Topic: "Expanding Campus Engagement with XSEDE"

Slides: available after the Symposium

Talk Abstract

A key objective of XSEDE is to increase research productivity and the preparation of the workforce via access to advanced digital resources and services. Campuses are a critical component of XSEDE's efforts to engage and support the user community. Through cooperation and coordination with campuses, the resources and services being offered on campuses can directly complement those offered by XSEDE; from deploying advanced digital resources to providing support services such as consulting and training.

The session will begin with a discussion of the range of XSEDE's resources and services. This will be followed by an open discussion of the needs and requirements of campuses, which XSEDE can help to address.

Biography

Through his position with the Shodor Education Foundation, Inc., Scott Lathrop splits his time between being the XSEDE Director of Education and Outreach, and being the Blue Waters Technical Program Manager for Education. Lathrop has been involved in high performance computing and communications activities since 1986.

Lathrop is currently coordinating education and outreach activities among the XSEDE Service Providers involved in the NSF-funded XSEDE project. He coordinates the community engagement activities for the Blue Waters project. He helps ensure that Blue Waters and XSEDE education and outreach activities are coordinated and complementary. Lathrop has been involved in the SC Conference series since 1989, served as a member of the SC Steering Committee for six years. He was the XSEDE14 Conference General Chair.

David R. Monismith Jr.
David Monismith

Independent Researcher

Topic: "Computing Hydrogen Ion Survival Probability: Academy Student, Graduate Student, and Faculty Experiences"

Slides: available after the Symposium

Abstract

This presentation covers the experiences of a Missouri Academy student, a Graduate Directed Project team, and Computer Science and Physics Faculty at Northwest Missouri State University in data management, computational science and physics while simulating firing a Hydrogen Ion at a metal surface.  Faculty involved in the project, Drs. Chakraborty, Monismith, and Shaw, were awarded XSEDE startup and XRAC allocations to perform over 20,000 2D simulations of firing a hydrogen ion at various metallic surfaces at a scale of hundreths of atomic units.  Simulations in this project allowed for variations in the trajectory model used, distance of closest approach, normal velocity, parallel velocity, height of the potentials, width of each potential, and distance between adjacent steps.  Academy student experiences included learning about directive based parallelism and updating a Fortran IV/77 code to Fortran 90 and to include OpenMP parallelism.  Graduate students involved in a graduate directed project developed two codes as part of a data management plan for the project.  The first was to upload simulation results from the TACC Stampede supercomputer to a server at Northwest Missouri State University to retain results in a MySQL database.  The second was to retrieve data from this MySQL database and present it in a graphical format using a Java Swing GUI tool that produced graphical reports using the JasperReports API.  Faculty have performed significant optimizations to the code to allow for single parameter set executions that make use of all compute resources on a Stampede node - asynchronous OpenMP/Xeon Phi OpenMP with 16 and 240 cores, respectively. So far results in this project have been produced for two metals and Drs. Chakraborty and Shaw have over 30 graphs on which they are performing analysis.  Dr. Monismith is currently performing optimizations on a 3D version of this code on PSC Greenfield.

Biography

Dr. David Monismith is an independent researcher in the Oklahoma City Area.  He was an Assistant Professor at Northwest Missouri State University from 2012 to 2015 where he served as XSEDE Campus Champion, Graduate Directed Projects Coordinator, and PI on two US Army Subcontracts.  He is currently working as a Co-PI with Drs. John Shaw and Himadri Chakraborty on an XSEDE Allocation entitled "Computational Simulations of Electronic Motions and Excitations in Nanostructured Surfaces by Ion-Surface and Adsorbate-Surface Charge-Transfer Interactions".  While working on this project, Dr. Monismith wrote code that generates scripts to perform parameter sweeps on the Texas Advanced Computing Center (TACC) Stampede Supercomputer using the TACC Launcher. He also worked with Yixiao (Icy) Zhang, a Northwest Academy student, to help her parallelize the code using OpenMP.  Dr. Monismith later updated the code to make use of Xeon Phi Accelerators, and worked with a graduate student team to develop tools to save results to a database and generate graphs from those results.  Dr. Monismith is currently performing reviews, parallelization, and optimization on the code for this project.  Additionally, Dr. Monismith is performing pro bono work on the Scholar-Link project with the Community Foundation of Northwest Missouri.  Scholar-Link has been a graduate directed project at NWMSU since 2012.  It enables students in Northwest Missouri to easily access and apply for hundreds of scholarships offered through the Community Foundation using a single scholarship application.

Mike Morris
Karl Frinkle and Mike Morris

Assistant Professor
Department of Chemistry, Computer and Physical Sciences
Southeastern Oklahoma State U

Topic: "Parallel Programming in the Classroom - Analysis of Genome Data"
(with Karl Frinkle)

Slides: available after the Symposium

Abstract

Over the course of a semester, students enrolled in an HPC seminar class created a suite of human genome analysis tools on the Beowulf clusters that they and other students built. The analysis tools were written with C and MPI and subsequently interfaced with a LAMP (Linux, Apache, MySQL, and PHP) website through the use of scripts. The output was visualized with the help of Google Charts. We will discuss the technical details of this project and demonstrate how these tools can be used to analyze multiple human genomes simultaneously.

Biography

Mike Morris' degrees are in math, but he has always said he wound up on the business end of a computer. He taught Computer Science (CS) in the early 80s after working as an Operations Research Analyst for Conoco in Ponca City OK. Mike left teaching and spent 15 years doing various things in the CS industry before returning to Southeastern Oklahoma State to once again teach CS, where he remains today.

Mukundhan Selvam
Mukundhan Selvam

Research Assistant
Aerospace Engineering
Computational Fluid Dynamics Laboratory
Wichita State University

Topic: "Peformance Tuning and Optimization of a Hybrid MPI+OpenMP Higher Order Computational Fluid Dynamics Solver"

Slides: available after the Symposium

Talk Abstract

An in-house Computational Fluid Dynamics (CFD) numerical solver with a higher order Weighted Essentially Non-Oscillatory (WENO) Scheme for the incompressible Navier-Stokes equations are developed and hybrid parallel implementations utilizing MPI and OpenMP are implemented. Here, we focus on the approaches for performance analysis, enhancements of the above solver and evaluate their results. By careful implementation of offloading the OpenMP constructs to Intel Xeon Phi co-processors, non-blocking MPI communications calls to overcome the communication overhead and constructing advanced derived data types for non-contiguous data, we have achieved a strong scaling of 75x speed-up in 64 cores. We also highlight the other key improvements and optimizations utilized to achieve these results. Performance tuning is approached on four fronts: MPI routines, OpenMP offloading, cache optimizations and Intel Math Kernel Libraries (MKL) high performance libraries. Though it is tedious to refactor the tightly coupled algorithms, these improvements enable us to execute larger and accurate simulations to take advantage of the Many Integrated Core (MIC) architectures of modern HPC as well as large scale distributed memory computing.

Biography

Mukundhan Selvam holds a M.S. degree in Aerospace Engineering from Wichita State University, and earned his B.E. degree in Aeronautical Engineering from Anna University, Chennai, India. Mr. Selvam's research interests are computational fluid dynamics, high performance computing, distributed computing, scientific computation, numerical turbulence modeling and performance tuning for massively parallel scientific software. Mr. Selvam also holds a Research position at the National Institute for Aviation Research (NIAR) in Wichita KS, where he has lead teams and projects in developing automated systems software in python, data analysis, testing/certification of advanced aircraft materials and tweaking finite element numerical analysis to adapt it to our simulations. Recent work has been focused on performance approaches for improving speedup and efficiency of a hybrid CFD solver in HPC clusters. He has been recognized for his excellence and research contributions in the Aerospace field by the American honor society in Aerospace Engineering - Sigma Gamma Tau in 2015. Through his persistent passion towards HPC and fluid dynamics, he has published and presented technical papers at conferences like AIAA. He is currently seeking to continue his career/research in scientific simulation's software development and HPC.

D. Kent Snider
D. Kent Snider

Regional Sales Director
Mellanox Technologies

Topic: "New Era of Performance through Co-Design"
(with Kashif Chauhan)

Slides:   PDF

Abstract

Mellanox InfiniBand technology is the foundation for scalable and performance demanding computing infrastructures. Delivering more than 100Gb/s throughput, sub 700ns application to application latency and message rates of 150 million messages per second has already placed ConnectX-4 EDR 100Gb/s technology in the Top500 list of the world's most powerful and efficient supercomputers. We will discuss the latest interconnect advancements that maximize application performance and scalability through the concept of co-design, an industry driven concept that accelerates the path to Exascale.

Biography

Mr. D. Kent Snider currently holds the position of Director, Central US Sales for Mellanox Corporation. His responsibilities include direction of all sales, engineering, support and demand generation activities for the Central US Region. Mr. Snider has over 15 years in the high technology industry in various sales, sales management and consulting roles. Mr. Snider has broad experience in the IT industry including networking, HPC, storage infrastructure, managed services and IT contract consulting. His assignments have covered many vertical markets (Oil & Gas, Media, Entertainment, Engineering, Manufacturing and Health Services), working for NetApp, Gartner Consulting and EMC. He hold a BS degree in Business from Ball State University and is a graduate of the University of Pennsylvania Wharton School of Executive Education.

DJ Spry
DJ Spry

Principal Engineer
Open Networking Product Group
Dell Inc.

Topic: "Open Networking and HPC"

Slides: available after the Symposium

Abstract

The new style of Web-scale IT that is run in hyperscale organizations like Google, Facebook and Amazon has changed the paradigm for delivery of IT services. Mainstream enterprise organizations are now attempting to deliver increased agility, improved management and/or reduced cost for their constituents. Over the past 12 months, vendors have continued to leverage merchant-based silicon within their switching portfolios. Thus, differentiation between vendor solutions continues to shift toward software (including management, provisioning, automation and orchestration), with hardware capabilities (such as bandwidth, capacity and scalability) becoming more standardized.

We will cover what Dell doing to lead the way in Open Networking and how HPC customers can take advantage and leverage Open Networking in their deployments.

Biography

DJ Spry is a Network Engineer with over 18 years experience designing and operating secure large-scale campus, data center, and service provider networks. Most recently he is concentrating on cloud, Software Defined Networking (SDN), and evangelizing the value of Open Networking for data center, big data, and cloud deployments. Prior to joining Dell, DJ was a Consulting Engineer for Juniper Networks focusing on Federal, Department of Defense, and Intelligence Community customers. In addition, he is a United States Air Force veteran.

Dan Stanzione
Dan Stanzione

Executive Director
Texas Advanced Computing Center
The University of Texas

Topic: "Data in a Flash: Next Generation Architectures for Big Data in Supercomputing — the Wrangler project and what comes next"

Slides: available after the Symposium

Talk Abstract

Coming soon

Biography

Dan Stanzione is the Executive Director of the Texas Advanced Computing Center (TACC) at The University of Texas at Austin and the Principal Investigator for Wrangler. He is also the PI for TACC's 10 PetaFlop Stampede supercomputer, and has previously been involved in the deployment and operation of the Ranger and Lonestar supercomputers at TACC. He served as the Co-Director of The iPlant Collaborative, an ambitious endeavor to build cyberinfrastructure to address the grand challenges of plant science. Prior to joining TACC, Dr. Stanzione was the founding director of the Ira A. Fulton High Performance Computing Institute (HPCI) at Arizona State University (ASU). Before ASU, he served as an AAAS Science Policy Fellow in the National Science Foundation and as a research professor at Clemson University, his alma mater.