XSEDE16

The processing of XSEDE allocations awards and subsequent reporting of usage by XSEDE Service Providers (SPs) are two of the most critical integration points between service providers and XSEDE. Accurate and efficient processing of this information is the critical link in ensuring the integrity of the allocation process and provides the feedback mechanism whereby XSEDE can track both system and user usage, and plan for future allocations. 

This BOF seeks to share lessons learned, best practices, and new ideas for how current and future SPs address this important function. Topics the BOF will address: 

• Brief overview of the XSEDE data standards and API for processing awards and reporting usage 
• Structure and design of the XSEDE allocations database 
• Use cases from SPs who are currently integrating with XSEDE 
• Use cases from Level 3 SPs or other institutions, who are considering integration with XSEDE 
• Use cases from sites that are not XSEDE SPs but may have models of usage tracking of interest to others 
• Working with difference resource managers 
• Handing different resource types (processors, memory configurations, accelerators) 
• How data is reported to the XDMoD tool 

This BOF invites those who are involved with or interested in the allocations review and award process; systems administrators who are responsible to ingesting allocations award and reporting usage; system architects responsible for the design of development of systems to perform these functions; and managers and others involved in deploying new resources.

Ongoing outreach and education efforts are underway addressing several needs within the HPC community: user training, consultant training and best practices, software carpentry, etc. However, there is no systematic program of developing the technical specialists needed to design, debug, operate, and improve the current cyberinfrastructure of the nation, particularly in research computing. 

This BoF proposes to gather kindred spirits to discuss possible approaches to meeting that need, how best to leverage the best experiences/results of the other outreach and education efforts, and ways that the community can address the increasing shortage of cyberinfrastructure professionals.

This BoF will focus on a conversation about user needs in the XSEDE SP (Service Provider) community, and in the community of people who have implemented smaller scale XSEDE-like clusters via the XCBC (XSEDE-Compatible Basic Cluster) and XNIT (XSEDE National Integration Toolkit) programs. 

As we move into XSEDE2, the Community Resource Integration team (formerly Campus Bridging) would like to foster an ongoing conversation between users, user advocates, software providers, and SP's, in order to best provide toolkits that serve the XSEDE ecosystem. We hope to begin this conversation at XSEDE16, to help deepen the relationships between disparate parts of the XSEDE community from the very beginning of XSEDE2. An important part of the Community Resource Integration (CRI) mission is facilitating discussion around the tools currently in use and on the horizon. This BoF will be a first step in that direction, offering a chance for SP's (including XCBC/XNIT administrators), CRI staff and users to discuss current needs and future desire around the toolkits used in XSEDE level research. This session will include a panel of experts in Campus Bridging, with brief presentations and a 
focus on audience participation.

This session is intended to be a forum for open discussion on the topic of data analytics/data science and how it fits in a HPC environment (or how HPC fits into data analytics/data science). Topics that will be offered for discussion include: 

• What exactly IS "Big Data"? What constitutes inclusion in this category? 
• We've for a very long time been capable of GENERATING this data...have we been extremely negligent in not co-developing adequate methods to examine it all along? 
• Do the HPC communities, facilities and systems have a role in data analytics and data science? 
• What are the needs of our researchers in terms of data analytics or data science? 
• What resources are required in an HPC environment to meet these needs? 
• What are the implications of research data analytics in terms of the facilities and resources that we in the HPC community build and support? What new architectures and software will be needed? 
• What new skills are needed of campus champions and other research computing support personnel? Is training available to acquire these skills? 
• What new collaborations and partnerships might help to advance data analytics as a mode of research in a high performance research computing environment? 
• Should our community (research computing) have a leadership role in shaping and directing the state of tools for Data Analytics? 

The format of this BOF will be an open discussion and exchange of thoughts and ideas. Some issues (such as those presented above) will be presented to help frame the discussion.

In this session, we will bring together educators and scientists to solicit input on how to solve the similar problems and issues they face in the delivery of HPC training. Specifically, we will discuss three or more of the following topics: creating HPC Carpentry for complete novices who need to use HPC resources; creating inclusive training environments; online instructional innovations; developing courses and materials to prepare current and future HPC users; and, web accessibility. During the session, online polling software will be used to enhance engagement among attendees.

Understanding the value of campus-based cyberinfrastructure (CI) to the institutions that invest in such CI is intrinsically difficult. It is often challenging to demonstrate the relative contribution of CI and associated expertise to any new discovery, and there is often little indication of how important campus-based CI was in reviews of grant proposals that were funded. The NSF funded Value Analytics (VA) module for Open XDMoD will help address this challenge by extending Open XDMoD with grant funding and publication metrics. In this BoF we will outline the current state of Open XDMoD-VA and show first results of our work. We invite members of the community to join a discussion about how the new metrics can be used at different institutions and we invite feedback on the proposed features of Open XDMoD-VA.

This Birds of a Feather session is for those interested in Humanities, Arts, and Social Science with HPC. Alan Craig will lead the session. The anticipated audience includes scholars from fields of humanities, arts, and social science as well as people who support computing for scholars from those areas, and anyone else who is interested. 

It will offer the opportunity to discuss and learn about how others are using HPC in their research, especially with respect to text analytics, video analytics, and image analytics, but the floor is open for topics of participant interest. Additionally, this BOF will provide an update on the XSEDE science gateways that are being developed and being made available for text analysis and video analysis.

BoF Discussion Panel:  Jim Bottum (Clemson University), Melissa Cragin (Midwest BDHub), Dave Lifka (Cornell University), John Towns (XSEDE).  Moderator: Phil Blood (Pittsburgh Supercomputing Center).

Over the past few years, we have witnessed the emergence of numerous active efforts that have been established with the goal of preparing and supporting cyberinfrastructure professionals encompassing campuses, nonprofits and government agencies across the nation. These professionals are essential for raising awareness of and access to advanced digital resources among faculty, researchers, students, and staff within their organizations. Examples of these types of organizations include the Campus Champions, Advanced Cyberinfrastructure Research and Education Facilitator (ACI-REF), the Great Plains Network, Software (and Data and HPC) Carpentry, as well as professional societies including SIGHPC. One of the most prevalent recurring questions among these and other efforts, including the agencies and projects funding these efforts, is “What does it take to build a persistent community of cyberinfrastructure professionals?”

While there is tremendous support for these professional support organizations, there are also a number of challenges they face. These include reliable long-term funding that is not tied to a specific project and the difficulty in structuring an organization to meet the needs of a wide range of CI professionals, among diverse environments ranging from small campuses to large research universities, and national labs, as well as organizations that span geographic regions and time zones. 

The goal of this BoF is to identify the above mentioned challenges, seek potential solutions, and establish collaborative efforts for instituting the groundwork to persistently support fostering of communities comprising CI professionals. The objective is to bring together a variety of projects and organizations working together to serve the unique needs of CI professionals.

XSEDE is seeing a growing portfolio of cloud and virtualization resources being added to the diverse set of resources that XSEDE allocates and uses as part of the XSEDE Federation. With these new resources come new challenges and opportunities for effective use of these resources for furthering scientific research. The “Topics on Cloud and Virtualization in XSEDE” BOF will provide a short overview of the cloud and virtualization capabilities available in XSEDE (including IU’s Jetstream, PSC’s Bridges, SDSC’s Comet and Cornell’s Aristotle, the DIBBs cloud federation) and NSF’s cloud projects. Additionally, the BOF will initiate and foster discussion on the challenges and opportunities for collaboration and coordination for this growing community. The organizers will provide a collected set of topics and challenges from the SPs and user community to foster discussion. Prior to the BOF, the organizers will solicit questions, comments and references regarding key topic and challenge areas to be presented to spur discussion including but not limited to: 

• Shared image and container repositories 
• Image security vetting best practices 
• Cloud and virtualization standard adoption (or not!) 
• AAA 
• Security (including how to provide bare metal access), identity management and authentication 
• Use cases and software needs & requirements (leading to image development) 
• Staff skills and training needed 
• What is new with clouds and virtualization that is needed by our XSEDE user community 

Science gateways, also known as web portals or virtual research environments are a fundamental part of today’s research landscape. Beginning in 2013, more users accessed XSEDE resources via gateways than they did from the command line. However, despite the presence of gateways for many years, development of these environments is often done with an ad hoc process, limiting success, resource efficiency, and long-term impact. Developers are often unaware that others have solved similar challenges before, and they do not know where to turn for advice or expertise. Without knowledge of what's possible, projects waste money and time implementing the most basic functions rather than the value-added features for their unique audience. Critically also many gateway efforts fail. Some fail early by not understanding how to build communities of users; others fail later by not developing plans for sustainability. 

The Science Gateways Community Institute (SGCI, http://www.sciencegateways.org) is the first implementation-phase software institute to be awarded through NSF’s Software Infrastructure for Sustained Innovation (SI2) program. SGCI has been designed as a service organization to address challenges by offering services to and building community among the research communities developing gateways. The Institute’s five-component design is the result of several years of studies, including many focus groups and a 5,000-person survey of the research community. This BOF will provide an overview of SGCI’s offerings and solicit feedback on additional services the community would like to see. 

The XSEDE User Portal (XUP) provides an integrated interface for XSEDE users to submit an allocation request, manage an allocation, and access the information and services available to them through the XSEDE project. XUP has become a main source for users to access XSEDE services and features. The XUP allows users to accomplish many things, including:

* Request allocations, and view and manage project allocation usage
* Manage user profile and publications
* Submit and Track XSEDE publications
* Monitor the status of HPC, storage, and visualization resources
* View system account information
* Register for training and view online training courses
* Access documentation and user news
* Receive consulting support and chat with other users on user forums

XUP also includes an additional interface for mobile devices including mobile web, iOS and Android apps to fulfill the need for users to access XSEDE on the go.

The XUP team will lead a discussion designed to enhance the capabilities of XSEDE User Portal and XUP Mobile Services. The purpose of this BoF is to collect user feedback about the current XSEDE User Portal and Mobile services and find out what users would love to see. We plan to have this BOF be an open and engaging discussion to find out what YOU the users would like to see on the user portal. What would make your life easier on XSEDE? What ideas and capabilities would you like to see?

Let's talk real, no-kiddin' supercomputer analytics, aimed at moving beyond monitoring the machine as a whole or even its individual hardware components. We're interested in drilling down to the level of individual tasks, users, and binaries. We’re after ready answers to the "what, where, how, when and why" that stakeholders are clamoring for: everything from which libraries (or individual functions!) are in demand, to preventing the problems that get in the way of successful science. This talk will show how XALT can provide this type of job-level insight. 
We will show how this tool provides high value to centers and their users as it can provide documentation on how an application was built to provide reproducibility by reporting the exact environment in which jobs were run. 

We have been running XALT at the Texas Advanced Computing Center, one of the largest supercomputing centers in the U.S. and it has become mission critical for us to know what programs to benchmark for new systems. It has also told us what programs shouldn't be running on the large memory nodes. We will also describe using analytics on the big data generated through XALT.  XALT has a small but growing community. It is also tracking usage at major sites around the world: NICS, University of Utah, KAUST.

The eXtreme Science and Engineering Discovery Environment (XSEDE) developed Resource Allocation Service (XRAS) is a software as a service solution for managing allocation requests for resources, instruments and collaborations. The XRAS service is offered to interested clients outside of XSEDE as a way to manage their allocation needs. This BOF session will include demonstrations of the XRAS system in place for XSEDE, The National Center for Atmospheric Research (NCAR) and Blue Waters, as well as showcase the features of XRAS and explain interactions with potential client organizations. 

XRAS provides data storage as well as interfaces for the submission, review and awarding of these allocation requests. Because the allocation processes for most shared resource providers are typically variations on a common high-level approach, XRAS can deliver allocations software as a service through a set of common tools and interfaces enhanced by flexible mechanisms that allow resource providers to tailor the environment to meet the needs of their process. Through this service, campuses can leverage the expertise of XSEDE (and prior programs) in managing national HPC allocations processes over more than 20 years with a minimum investment of local effort and establish integration with the national NSF-supported HPC cyberinfrastructure. By offering this service to the eScience community, XSEDE intends to expand opportunities for open science by sharing the interfaces needed to manage resource allocations for both large and small institutions.