NEREN SEMINAR Bridging the Gap: Research Facilitation

PRESENTING SPONSOR: RED RIVER

TECHNOLOGY SPONSORS: PENGUIN COMPUTING & IGNEOUS SYSTEMS

FRIDAY, MARCH 31, 2017 8:30AM – 3:00PM

Hyatt Regency Cambridge 575 Memorial Drive Cambridge, Massachusetts

Register at redriver.com/neren-seminar In collaboration with UMass Amherst and the Massachusetts Green High Performance Computing Center (MGHPCC), NEREN presents the second in a series of day long seminars devoted to REGIONAL COLLABORATION AND RESEARCH COMPUTING. 1 // NEREN SEMINAR

AGENDA

8:30AM – 9:00AM Registration/Continental Breakfast/Networking

9:30AM – 9:40AM Welcoming/Opening Remarks (NEREN)

9:40AM – 10:00AM Trends Enabling Analytics, Data and Collaboration Presenter: Paul Krein, Vice President of Digital and Cloud Solutions, Red River Advances in technology, new computing models, and industry investments are making collaboration, advanced analytics, and large scale data sharing more accessible than ever before. These trends and advancements have the ability to bridge the gaps and reshape the pace of innovation.

10:00AM – 10:40AM New and Existing Infrastructure Presenter: James A. Cuff, Assistant Dean for Research and Computing, and Co-Principal Investigator – ACI-REF More and more our national computational infrastructure continues to grow in size, scale and complexity. Our researchers rather than finding easy and seamless access to boundless resource are actually finding increasing friction between them and the resources they desperately need in a world driven by Big Data. ACI-REF was designed as a 2 year pilot to investigate if direct application of human capital through facilitation would remove this friction. One of the critical work products of this activity was to develop a best practices handbook. James will discuss the evolution of the project and next steps for campuses as they continue to design their cyberinfrastructure strategies from lessons learned from this activity. Following on, James will describe the North East Storage Exchange, a 5 year funded effort just starting to develop a low cost, secure and highly performant object store for science and research. NESE builds on prior success with the MGHPCC data center for research and their shared operating model, and features investigators from each of , , MIT, Harvard and the University of Massachusetts. Their aim as like the “wetware” example of the ACI-REF program is to build frictionless access to large scale storage for science.

10:40AM – 11:20AM Bridging the Gap - Facilitating Collaborative Life Science Research in Commercial & Enterprise Environments Presenter: Chris Dagdigian, Co-Founder and Senior Director of Infrastructure BioTeam The future of pharmaceutical drug development increasingly requires complex multi-party collaboration (and high-scale data exchange) among public, private, academic and non-profit organizations. While collaborating in one area, some parties may be fierce competitors in other areas. Using recent work with Biotechnology and Pharmaceutical clients, Chris will candidly discuss current and emerging challenges, trends and requirements for facilitating collaborative research across, with and among commercial entities. 2 // NEREN SEMINAR

11:20AM – Noon Research Computing Facilitators – A Collaborative Approach

Presenter: John Goodhue, Executive Director, MGHPCC

Research Computing Facilitators combine technical knowledge and strong interpersonal skills with a service mindset, and use their connections with cyberinfrastructure providers to ensure that researchers and educators have access to the best available resources. It is widely recognized that Research Computing Facilitators are critical to successful use of research computing resources, but in very short supply. This talk will discuss two ideas, developed by several NEREN members, that could make it easier for small and medium sized-institutions to fill their need for Research Computing Facilitators: (1) Build a shared regional pool of experts who can work across institutions. This can both increase the range of available knowledge and skills, and provide “bench depth” that makes it easier to manage turnover and handle bursts of activity. (2) Work with this pool of experts to create mentoring and work assignment opportunities that give students greater exposure to the Research Computing Facilitator role.

Noon – 12:30PM Lunch break

12:30PM – 12:45PM Case Study – Penguin Computing, Brian Hammond Ph.D

12:45PM – 1:00PM Case Study – Igneous Systems, Stephen Pao, CMO

1:10PM – 2:10PM Breakout sessions  Presented by: Christopher Misra, Chief Technology Officer, UMass Amherst and James A. Cuff, Assistant Dean for Research and Computing, Harvard University and Co-Principal Investigator – ACI-REF and Chris Hill, Principal Research Engineer, Massachusetts Institute of Technology, Earth, Atmospheric and Planetary Sciences

2:20 PM – 3:00PM Closing remarks  Christopher Misra, UMass Amherst, Chief Technology Officer and Paul Krein, Vice President of Digital and Cloud Solutions, Red River ABOUT OUR SPEAKERS

Paul Krein Paul Krein is the Vice President of Cloud and Digital Solutions, and the Office of the CTO at Red River. He leads the technology strategy Vice President of for Red River, leads the solutions and technology engineering teams, Digital and Cloud Solutions, and works with executives and technology leaders to understand the Red River art of the possible, assess impacts of leading trends, and evaluate the economic changes in delivering data and computational capacity at scale. His teams design and architect, build and run solutions for Healthcare/Lifesciences, Retail, Education and Government missions and infrastructure enabling greater efficiency and higher scale. He is a change agent, has opened new markets throughout his career, and has lead sales, management and business operations functions. Paul holds an M.B.A from the Simon School in Finance and Organizational Strategy, and a B.S. in Electrical Engineering from the University of Rochester.

James A. Cuff James Cuff is the Assistant Dean for Research Computing in the Division of Science in the Faculty of Arts and Sciences. James also performs Assistant Dean for the role of Distinguished Engineer for Research Computing in HUIT Research and Computing, at Harvard University. His group supports advanced high performance Harvard University and technical computing (in excess of 60,000 processors), 2+PF of GPGPU, Co-Principal Investigator – and large scale storage systems for data science at over 20+PB. The ACI-REF group was involved in the initial design, build and eventual support of the MGHPCC project where they now run scientific computing and academic research systems supporting multiple schools at Harvard University.

Prior to working at Harvard, James managed the Applied Production Systems Group at the of Harvard and MIT. Before moving to the US, James created the high performance computing infrastructure for the Ensembl project at the Wellcome Trust Sanger Institute. While completing his D. Phil. in protein secondary structure prediction, James worked at the European Institute in Cambridge.

James holds a D. Phil. in Molecular from Oxford University and a B.Sc. (Hons) in Chemistry with Industrial Experience from Manchester University.

Chris Dagdigian Accidental entrepreneur, cloud nerd and bioinformaticist-gone-bad Chris Dagdigian has spent much of the last 18 years designing, building, Co-Founder and Senior fixing and improving research-focused IT infrastructures used in Director of Infrastructure demanding production computing environments. Chris is the co-founder of the BioTeam Inc. (https://bioteam.net) - a specialist independent consultancy built around scientists and engineers who “bridge the research/IT gap” every day. He occasionally is known to blog, tweet and speak about industry trends and best practices. 4 // NEREN SEMINAR

John Goodhue John Goodhue is the Executive Director of the Massachusetts Green High Performance Computing Center (MGHPCC). The MGHPCC is dedicated Executive Director, to supporting the growing scientific computing needs of faculty-driven MGHPCC research at MIT, University of Massachusetts, Boston University, Northeastern University, and Harvard University. John is a business and technical leader with 30 years of experience in networking and high performance computing. John has held senior engineering management, general management, and technology leadership positions at Cisco Systems, where he led the development and marketing of Internet routers for service providers, and BBN Technologies, where he led projects to develop Internet routing and High Performance Computing technologies. He has also been on the early management teams for several Boston-area startup companies. John holds a B.S. in Computer Engineering from the Massachusetts Institute of Technology.

Christopher Misra Christopher Misra is the Chief Technology Officer with the University of Massachusetts Amherst where he has worked for many years. His Chief Technology Officer, responsibilities include management of overall campus technology UMass Amherst coordination, networking, data centers, information security program, identity management, and enterprise architecture. Chris has been active for many years with various regional and national information security organizations including the Security Task Force, Internet2 Salsa, and REN-ISAC, serving on program committees, chairing working groups, and presenting at conferences. Chris is also an instructor at UMass where he has taught undergraduate courses on Network Security for many years.

Chris Hill Chris Hill specializes in Earth and planetary computational science. He is interested in the application of large-scale computation to all aspects Principal Research of understanding Earth and planetary systems. He was a founding Engineer, Massachusetts developer of the M.I.T. General Circulation Model (MITgcm), a numerical Institute of Technology simulation tool used for a wide range of basic science and applied Earth, Atmospheric and studies in planetary fluid dynamics. He also helped launch the Earth Planetary Sciences System Modeling Framework (ESMF), a major open standard for creating multicomponent models of Earth system processes. In both activities he has been active in developing prognostic model and model-data synthesis tools. Recent work has included multi-physics, multi-scale models of fluid problems that have relevance to improved modeling of flows in inhomogeneous porous media. The approaches combine algorithmic ideas, with evolving designs in massively parallel computer systems to allow more accurate fluid simulation at a lower computational cost. The work exploits the ESMF multi-component coupling system to provide a general framework for modeling, in which a hierarchy of models is mapped to a hierarchy of hardware.

Hill co-leads the research, education and outreach committee of the Massachusetts Green High Performance Computing Center (MGHPCC). The MGHPCC is a multi-university enterprise in Massachusetts, dedicated to enhancing large-scale computing infrastructure in the area. Hill has worked at MIT since 1993. ABOUT OUR SPONSORS

PRESENTING SPONSOR:

Red River Red River brings together the ideal combination of talent, partners and products to disrupt the status quo in technology and drive success for business and government in ways previously unattainable. Red River serves organizations well beyond traditional technology integration, bringing more than 20 years of experience and mission-critical expertise in security, networking, analytics, collaboration, mobility and cloud solutions.

Red River delivers ongoing IT consulting, maintenance and support to ensure optimal success through an array of unique service offerings, including integrated Managed, Professional, Technical and Support Services. Whether you need help answering simple end-user inquiries with our 24x7x365 Network Operations Center, need to develop a path to the cloud, or implement new network security protocols, our certified experts are available to help.

Learn more at redriver.com 6 // NEREN SEMINAR

TECHNOLOGY SPONSORS:

Penguin Computing For almost two decades Penguin Computing has been the leader in development open, Linux-based cloud and HPC solutions. With their unmatched Linux expertise, Penguin Computing offers a comprehensive portfolio of products, ranging from Linux servers and workstations to integrated, turn-key HPC clusters and cluster management software. Penguin Computing provides customized build-order server solutions for enterprises and institutions with special hardware requirements. They complement their hardware and software solutions with Penguin Computing on Demand (POD)—a public HPC cloud that provides supercomputing capabilities on-demand on a pay-as-you-go basis.

Penguin is a one-stop shop for HPC and enterprise customers, providing solutions for a wide array of computing needs and user profiles: • HPC and cloud solutions optimized for industry-specific uses • High-powered workstations for individual power users • Highly power-efficient server platforms for enterprise computing

Private and public cloud solutions, including hybrid options.

Learn more at penguincomputing.com

Igneous Systems Igneous is an onsite Storage as-a-Service and Data Management Software as-a-Service offering to store and manage your unstructured data. Compatible with cloud-native APIs, Igneous Data Service provides object storage as-a-Service in the enterprise data center. Igneous also integrates Igneous Insights and a suite of data management tools (backup, archive, and replication) to ensure that content can be shared, migrated, and protected in any environment.

Unlike traditional on-premises storage solutions, Igneous users don’t have to buy hardware, install software, or manage systems. Applications and users simply interact with Igneous Data Service through industry-standard object protocols, such as Amazon S3 API or file protocols such as FTP. Through Igneous Insights, Igneous Backup, Igneous Archive, and Igneous Replication, Igneous Data Service also interacts with your existing file servers via NFS to provide a rich set of data management solutions to securely automate your handling of data throughout its lifecycle.

Igneous is ideal both for organizations who want to keep their data strictly on-premises or for those taking advantage of Amazon Web Services, Microsoft Azure, or Google Cloud Platform.

Learn more at igneous.io PRESENTING SPONSOR:

TECHNOLOGY SPONSORS: