Loading…
This event has ended. View the official site or create your own event → Check it out
This event has ended. Create your own
View analytic

Sign up or log in to bookmark your favorites and sync them to your phone or calendar.

Sunday, July 17
 

8:00am

Polar HPC Hackathon
Co-located workshop. Attendance is by invitation only.

Sunday July 17, 2016 8:00am - 5:00pm
Flagler InterContinental Miami

8:00am

Polar HPC Hackathon Breakout
Co-located workshop. Attendance is by invitation only.

Sunday July 17, 2016 8:00am - 5:00pm
Star/Palm Isle

3:00pm

Registration
Conference registration

Sunday July 17, 2016 3:00pm - 7:00pm
Registration

6:00pm

 
Monday, July 18
 

7:00am

Tutorial Breakfast - Sponsored by Cray and DDN
Monday July 18, 2016 7:00am - 8:00am
Mezzanine Mezzanine

7:00am

Registration
Monday July 18, 2016 7:00am - 8:00pm
Registration

8:00am

Student Tutorial: Supercomputing in Plain English
Prerequisites: One semester of programming in C, C++ or Fortran, recently, is encouraged but not required (a modest number of brief code examples will be examined). Basic experience with any Unix-like operating system (could be Linux but doesn’t have to be), recently, is encouraged but not required (an introductory Linux commands tutorial will be included). No previous HPC experience will be required.

Requirements: A laptop (Windows, MacOS or Linux) or a tablet (iOS, Android or Windows Mobile) is strongly recommended but not required.

Abstract:

* Lecture: Overview: What the Heck is Supercomputing?

This session provides a broad overview of High Performance Computing (HPC). Topics include: what is supercomputing?; the fundamental issues of HPC (storage hierarchy, parallelism); hardware primer; introduction to the storage hierarchy; introduction to parallelism via an analogy (multiple people working on a jigsaw puzzle); Moore's Law; the motivation for using HPC.

* Lab: Running A Job on a Supercomputer

In this hands-on lab session, you’ll get an account on one or more supercomputers, and you’ll get a chance to run a job. If you’re new to Unix-like operating systems, this will be a great introduction; if your Unix/Linux skills have gotten a little rusty, this will be a great refresher.

* Lecture: The Tyranny of the Storage Hierarchy

This session focuses on the implications of a fundamental reality: fast implies expensive implies small, and slow implies cheap implies large. Topics include: registers; cache, RAM, and the relationship between them; cache hits and misses; cache lines; cache mapping strategies (direct, fully associative, set associative); cache conflicts; write-through vs. write-back; locality; tiling; hard disk; virtual memory. A key point: Parallel performance can be hard to predict or achieve without understanding the storage hierarchy.

* Lab: Running Benchmarks on a Supercomputer

In this hands-on lab session, you’ll benchmark a matrix-matrix multiply code to discover the configuration that gets the best performance.

* Other topics may be introduced if time permits.

Content: Older versions of the lecture slides and exercise descriptions (which will be updated) may be found as follows:

* Lecture: Overview: What the Heck is Supercomputing?
http://www.oscer.ou.edu/ncsiworkshop2012intropar_sipe_overview_20120729.pdf

* Lab: Running A Job on a Supercomputer
http://www.oscer.ou.edu/ncsiworkshop2012intropar_exercise_learningbatch_boomer_20120729.pdf

* Lecture: The Tyranny of the Storage Hierarchy

http://www.oscer.ou.edu/ncsiworkshop2012intropar_sipe_storage_20120730.pdf

* Lab: Running Benchmarks on a Supercomputer
http://www.oscer.ou.edu/ncsiworkshop2012intropar_exercise_tiling_boomer_20120729.pdf


Monday July 18, 2016 8:00am - 12:00pm
Chopin Ballroom

8:00am

Tutorial: Building a Campus Cyberinfrastructure Hub on the Cloud with HUBzero
HUBzero is a powerful, open source software platform for creating dynamic web sites that support scientific research and educational activities (hubzero.org). Used by communities ranging from nanotechnology, earthquake engineering, earth sciences, data curation, and healthcare, it is a proven framework for building a science gateway, and a key part of many
organizations’ cyberinfrastructure.

The HUBzero platform provides an application framework for developing and deploying interactive computational tools. It has modules to aid in data sharing and publication as well as a complete user management system and robust group management system to facilitate collaboration across the entire site. The HUBzero Application also offers a comprehensive project management module.

HUBzero can serve as a complete cyberinfrastructure solution for an organization, managing tens of thousands of users, terabytes of data, and can be a onestop gateway to numerous, preconfigured grid computing resources. Its highly integrated services support collaborative research, data and results publication, and the platform can archive research and data for long term access and analysis.

Today, HUBzero is available as an cloud appliance (AMI) on Amazon Web Services’ Marketplace, so it is easier than ever to deploy and maintain a hub for your organization.

This tutorial will provide an overview of this integrated cyberinfrastructure, describe a selected set of of common usage patterns for HUBzero Hubs, and example Hubs of campus CI and science domains. The second portion of the tutorial will provide examples and handson exercises on how to use Amazon Web Services to deploy your own instance of the HUBzero platform and how to configure your AWS HUBzero instance to connect to XSEDE resources, building a web platform to support collaboration, data sharing, and computation at your own institution.


Monday July 18, 2016 8:00am - 12:00pm
Windsor InterContinental Miami

8:00am

Tutorial: High Performance Modeling and Simulation with Eclipse ICE
The Eclipse Integrated Computational Environment (ICE) is a scientific workbench and workflow environment designed to improve the user experience for modeling and simulation applications. ICE makes it possible for developers to deploy rich, graphical, interactive capabilities for their science codes, in a common, cross-platform user environment. This tutorial will teach attendees how to extend ICE to add custom plugins for tailoring the environment to their specific high-performance modeling and simulation applications.

The tutorial will begin with an overview of the architecture ICE uses for managing modeling and simulation workflows. Attendees will then:

- Learn how to create a simple, multicore/multithreaded high-performance simulator from scratch
- Learn how to extend the workbench to generate input files
- Learn the various ways that jobs can be launched in parallel from Eclipse
- Learn how to visualize data in 3D and analyze results locally or remotely
- Learn to generate custom UI widgets to make a unique domain-specific user focus
- Learn how to write run and execute scripts with EASE that modify the workbench
- Learn how to enhance the workbench to include links to source code repositories which developers can download and configure in ICE

This tutorial will include extensive documentation and exercises for attendees, and will focus on each attendee developing a custom high-performance modeling and simulation tool from scratch utilizing all the main features available in ICE. Attendees will be expected to have a least a moderate level of Java programming skills and some familiarity with Eclipse programming. Sample simulators will be available for those without an idea in mind and a science background is not required. Docker containers will be provided for Windows users.

Videos of applications similar to those that attendees will create are available on the Eclipse ICE YouTube Channel: https://www.youtube.com/channel/UCfmcuxKkDBPRmhbC5GoMwSw


Monday July 18, 2016 8:00am - 12:00pm
Gusman

8:00am

Tutorial: How to Boost the Performance of your MPI and PGAS Applications with MVAPICH2 Libraries?
MVAPICH2 software, supporting the latest MPI 3.1 standard, delivers best performance, scalability and fault tolerance for high-end computing systems and servers using InfiniBand, 10/40 GigE/iWARP and RoCE (V1 and V2) networking technologies. MVAPICH2-X software library provides support for hybrid MPI+PGAS (UPC, OpenSHMEM, CAF, and UPC++) programming models with unified communication runtime. MVAPICH2 and MVAPICH2-X software libraries (http://mvapich.cse.ohio-state.edu) are powering several supercomputers in the XSEDE program including Gordon, Comet, Lonestar4, and Stampede. These software libraries are being used by more than 2,550 organizations world-wide in 79 countries to extract the potential of these emerging networking technologies for modern systems. As of March '16, more than 358,000 downloads have taken place from this project's site. These software libraries are also powering several supercomputers in the TOP 500 list like Stampede, Tsubame 2.5 and Pleiades. A large number of XSEDE users are using these libraries on a daily-basis to run their MPI and PGAS applications. However, many of these users and the corresponding system administrators are not fully aware of all features, optimizations and tuning techniques associated with these libraries. This tutorial is aimed to address these concerns and provide a set of concrete guidelines to XSEDE users to boost performance of their applications. Further, as accelerators such as GPUs and MICs are commonly available on XSEDE resources, it is becoming an increasingly challenging task to extract best performance and scalability for user applications on such systems. We will also present tuning and optimization techniques for such systems. We will start with an overview of the MVAPICH2 libraries and their features. Next, we will focus on installation guidelines, runtime optimizations and tuning flexibility in-depth. An overview of configuration and debugging support in MVAPICH2 libraries will be presented. Support for GPUs and MIC enabled systems will be presented. The impact on performance of the various features and optimization techniques will be discussed in an integrated fashion. `Best Practices' for a set of common XSEDE applications will be presented. Advanced optimization and tuning of MPI applications using the new MPI-T feature (as defined by the MPI-3 standard) in MVAPICH2 will also be discussed. A set of case studies related to application redesign will be presented to take advantage of hybrid MPI+PGAS programming models. Finally, the use of MVAPICH2-EA library, aimed to reducing the energy footprint of HPC applications, will be explained.


Monday July 18, 2016 8:00am - 12:00pm
Escorial

8:00am

Tutorial: Introduction to CUDA Programming in C and Fortran
This tutorial is a beginning/intermediate course on programming NVIDIA GPUs with CUDA. After a short segment on why we are using accelerators in high performance computing and on accelerator hardware, we will describe all of the pieces necessary to write a CUDA program in C and Fortran. The example will be a stencil update, which is simple enough to be written in a few lines of code. The code design will be guided by the hardware; we will put emphasis on motivating common design principles by the desire to write fast code for GPU accelerators. In the second part of the presentation, we will focus on two common optimization strategies: using shared memory and overlapping computation with data transfer using CUDA streams. Experience with writing serial code in C or Fortran will be helpful to follow the examples.


Monday July 18, 2016 8:00am - 12:00pm
Michelangelo

8:00am

Tutorial: Introduction to Python Pandas for Data Analytics
This tutorial is a beginner level course on tackling data analytics using the Python pandas module. Python is a high-level object oriented language that has found wide acceptance in the scientific computing community. Ease of use and an abundance of software packages are some of the few reasons for this extensive adoption. Pandas is a high-level open-source library that provides data analysis tools for Python. We will also introduce necessary modules such as numpy for fast numeric computation and matplotlib/bokeh for plotting to supplement the data analysis process. Experience with a programming language such as Python, C, Java or R is recommended but not necessary.


Monday July 18, 2016 8:00am - 12:00pm
Brickell

8:00am

Tutorial: Introduction to Scientific Visualization and Data Sharing
Visualization is largely understood and used as an excellent communication tool by researchers. This narrow view often keeps scientists from fully using and developing their visualization skillset. This tutorial provides an understanding of visualization and its utility in error diagnostic and exploration of data for scientific insight. When used effectively visualization can provide a complementary and effective toolset for data analysis, which is one of the most challenging problems in computational domains. In this tutorial we plan to bridge these gaps by providing end users with fundamental visualization concepts, execution tools, customization and usage examples. Finally, short hands on tutorials on Data Sharing using SeedMe.org will be provided. The tutorial comprises of four closely related sessions as follows:
1 Visualization fundamentals: Lecture – Assay of standard techniques and their utility (45 min)
2 Hands on Visualization with VisIt software on your computer/laptop (80 mins)
3 Remote visualization with VisIt software on Comet/Gordon cluster at SDSC. We will provide training accounts. (30 mins)
4 VisIt software ships with SeedMe Python module for sharing visualizations rapidly. A swift introduction to using SeedMe.org will be provided (20 mins)


INSTRUCTOR: Amit Chourasia, San Diego Supercomputer Center, UCSD Duration: Half Day


PRE_REQUISITES: None


INTENDED AUDIENCE LEVEL: Beginner for visualization, Data sharing session will be useful for all attendees


TUTORIAL OUTCOME
The tutorial is aimed to jump start attendees with visualization, by providing them rapid background and how to use a tool. The attendees will gain understanding of standard visualization techniques, application scenarios and best practices. Attendees will get a hands on introduction to the VisIt visualization software and apply the standard techniques on sample data. By the end of the tutorial attendees will gain proficiency in creating sophisticated visualizations and pursue more advanced concept on their own. Attendees will also learn how to use HPC resources like Comet/Gordon and conduct remote visualization. Finally they will be introduced to SeedMe platform and how to use it for data and visualization sharing.


REQUIREMENTS
1. Computer + mouse with scroll wheel (laptop trackpads are very difficult to use for 3D navigation, so mouse is recommended)
2. VisIt software (version 2.9.2, yes please install this specific version, not the latest )
3. Download Sample Data https://wci.llnl.gov/content/assets/docs/simulation/computer-codes/visit/visit_data_files.tar.gz
4. Account on SeedMe.org (You may create an account during the tutorial)


SESSION DETAILS

Session 1 (Lecture): Visualization Fundamentals
----------------------------------------
In this session we will provide a rapid introduction to fundamental visualization concepts. We will provide an assay of visualization techniques available accompanied by example application scenarios. We will also discuss best practices and shortcomings of visualization techniques. These fundamentals will help attendees to apply and innovate existing techniques for their own research.
• Introduction to Visualization
• Perception overview with eye color sensitivity
• Visualization Techniques
• Application Examples
• Best Practices

Session 2 (Hands on): Visualization with VisIt
--------------------------------------
This session will provide a quick over view of VisIt and bulk of the session will be devoted to enable users to get a hands on experience with VisIt application. The attendees will create several visualizations on their laptops by following instructor’s guidance.
• VisIt Introduction
• VisIt basics (how VisIt works, one plot & 2 operators)
• Visit plot survey
• Expressions
• Commands and Scripting
• Moviemaking

Session 3 (Hands on): Remote Interactive Visualization
---------------------------------------------
This session will provide a instructions on how to create system host profile and connect to XSEDE host like Comet and perform remote interactive visualization.
• Remote Visualization (network permitting)

Session 4 (Hands on): Data Sharing using SeedMe.org
--------------------------------------------
This session will provide instructions on how leverage the SeedMe infrastructure to share visualizations within and outside your research group.
• SeedMe overview
• Command line interaction with SeedMe.org
• SeedMe integration with VisIt

Speakers

Monday July 18, 2016 8:00am - 12:00pm
Trade

8:00am

Tutorial: Secure Coding Practices & Automated Assessment Tools
This is a newly updated tutorial retaining key material from our previous tutorials at XSEDE (secure programming) with the addition of new material on the use of automated analysis tools. This tutorial would be a benefit not only to new attendees but also to attendees of the previous tutorials. Our tutorial focuses on the programming practices that can lead to security vulnerabilities, and on automated tools for finding security weaknesses.


Monday July 18, 2016 8:00am - 12:00pm
Balmoral

8:00am

Tutorial: Using Comet’s Virtual Clusters
Comet is an XSEDE HPC resource hosted and operated at SDSC. This tutorial introduces the virtual cluster capability of Comet, a unique feature that provides research groups, projects, and campuses with the ability to fully define their own software environment with a set of dynamically allocated virtual machines. This tutorial introduces Comet's virtual cluster capability, and has hands-on material to cover the different modes of usage anticipated for virtual clusters. We begin the tutorial with detailed information on the Comet system architecture, the design and architecture of the virtual cluster capability, and how it compares to other virtualized and cloud services. The high performance of the virtualized clusters combining the full AVX2 feature set of the Haswell processors and the InfiniBand HCAs using SR-IOV for MPI will be covered. We then follow with information on how to build, configure, and manage virtual clusters using the Cloudmesh client, a tool to easily interface with multiple clouds from the command line and a command shell. The hands-on section of the tutorial is divided into three sections: Installing and configuring a virtual cluster; Running MPI applications within the virtual cluster; Simple automation to start and stop virtual machines dynamically. SDSC and IU Staff will be available to meet with individual users, to further discuss usage of Comet, at the conclusion of the tutorial. INTENDED AUDIENCE LEVEL: Intermediate This tutorial is appropriate for people with some Linux system administration or management experience.

Speakers
avatar for Rick Wagner

Rick Wagner

HPC Systems Manager, San Diego Supercomputer Center


Monday July 18, 2016 8:00am - 12:00pm
Tuttle

8:00am

Tutorial: XSEDE New User Tutorial: Using Science Gateways
Overview: This tutorial will build upon the well-attended, well-reviewed XSEDE15 tutorial (http://sched.co/3YdG). The purpose of this tutorial is to supplement the standard XSEDE new user tutorial with overviews of how to use science gateways so that the new users can start using XSEDE for scientific research right away, at the conference, and continue at their home institution, without getting bogged down in the allocation process at the beginning. The tutorial is also appropriate for XSEDE Campus and Domain Champions who are interested in using science gateways to support their outreach and support work on their local campuses. The target audience members are scientists in particular domains (chemistry, neuroscience, atmospheric science) who are new to XSEDE and who optionally are familiar with common software packages in their field, but who do not have deep experience with using supercomputers and clusters. Campus Champions who work closely with new users are also encouraged to attend. The tutorial will provide a brief overview of XSEDE and the science gateway program, including a list of other available gateways not covered by the tutorial. The bulk of the tutorial will be a sequence of hands-on activities that introduce attendees to domain specific gateways. The tutorial organizers will work with XSEDE conference organizers and the outreach team to recruit new user attendees from the selected domains.

Attendees will not need to be researchers in a specific science domain to participate in a specific gateway exercise. The organizers will provide all required input files and data for the exercises. Attendees will be encouraged to work with gateway providers on their specific research problems. Each hands on session will demonstrate how to create an account on the science gateway; how to create, submit, and monitor a submission of a specific application code; and how to retrieve final results. Each session will also include a feedback opportunity to help new users understand the additional capabilities of each gateway and optionally try out attendee-provided input data. The following are participating gateways.

CIPRES (http://www.phylo.org/sub_sections/portal/) is a public resource for inference of large phylogenetic trees. It is designed to provide all researchers with access to large computational resources of XSEDE through a simple browser interface. The CIPRES Science Gateway provides access to a number of important parallel phylogenetics codes to insure the fastest possible run times for submitted jobs. Users configure job runs by completing a web form; on submission the user-entered information is used to configure the runs efficiently on XSEDE resources. CIPRES has supported 17,000+ users and 2,000+ publications in all areas of biology since 2009. Example tutorial material: http://www.phylo.org/tools/flash/cipresportal2_data_management.htm and http://www.phylo.org/tools/flash/cipresportal2_task_management.htm

SEAGrid (http://seagrid.org) enables researchers to run commonly used computational chemistry codes such as Gaussian, Lammps, Tinker and other applications on XSEDE resources. GridChem has been used by about 600 users since 2005, supporting more than 100 research papers, and more than 10 Graduate theses. The science gateway registered with XSEDE SEAGrid provides a Java desktop client called GridChem and manages user registration and jobs and related data through a virtual organization and transparently provided through the client. Example tutorial information: https://scigap.atlassian.net/wiki/display/SEAGrid/SEAGrid+Documentation

The Neuroscience Gateway (NSG - http://www.nsgportal.org) facilitates access and use of NSF’s High Performance Computing (HPC) resources by neuroscientists. NSG offers to computational neuroscientists free supercomputer time acquired using an NSG-managed allocation. Through a simple web-based portal, the NSG provides an administratively and technologically streamlined environment for uploading models, specifying HPC job parameters, querying running job status, receiving job completion notices, and storing and retrieving output data. Neuronal simulation tools provided by NSG includes NEURON, GENESIS, Brian, PyNN, NEST, and Freesurfer. More tools are added based on users’ requests. Example tutorial information: http://www.nsgportal.org/tutorial.html

The Apache Airavata Test Drive Gateway is a general purpose gateway that can be used to execute a wide range of codes, including computational chemistry, bioinformatics, computational fluid dynamics, and weather modeling applications. The Test Drive gateway can also be used to quickly enable new XSEDE applications to be available through a Web interface. This module of the tutorial will allow users to configure an advanced, non-hydrostatic numerical weather prediction model (WRF-ARW) through a graphical user interface, specifying physics and numerical techniques options, selecting analyses for initial/boundary conditions. The generated model outputs will be displayed as plots generated by the NCAR graphics library. Example tutorial information:(Walk through users to perform a generic WRF tutorial but utilizing XSEDE resources http://www2.mmm.ucar.edu/wrf/OnLineTutorial/)

Speakers
avatar for Suresh Marru

Suresh Marru

Member, Apache Software Foundation
Suresh Marru is a Member of the Apache Software Foundation and is the current PMC chair of the Apache Airavata project. He is a principal research systems architect at Indiana University. Suresh focuses on research topics at the intersection of distributed systems, application domain science; computational systems and has authored or co-authored over 75 peer-reviewed conference papers and journal articles in these areas. He gets his hands on... Read More →


Monday July 18, 2016 8:00am - 12:00pm
Bayfront B

8:00am

Tutorial: Building the Modern Research Data Portal Using the Globus Platform
New Globus REST APIs, combined with high-speed networks and Science DMZs, create a research data platform on which developers can create entirely new classes of scientific applications, portals, and gateways. Globus is an established service that is widely used for managing research data on XSEDE and campus computing resources, and it continues to evolve with the addition of data publication capabilities, and improvements to the core data transfer and sharing functions. Over the past year we have added new identity and access management functionality that will simplify access to Globus using campus logins, and facilitate the integration of Globus, XSEDE, and other research services into web and mobile applications.

In this tutorial, we use real-world examples to show how these new technologies can be applied to realize immediately useful capabilities. We explain how the Globus APIs provide intuitive access to authentication, authorization, sharing, transfer, and synchronization capabilities. Companion code (supplemented by iPython/Jupyter notebooks) will provide application skeletons that workshop participants can adapt to realize their own research data portals, science gateways, and other web applications that support research data workflows.


Monday July 18, 2016 8:00am - 5:00pm
Merrick I

8:00am

Tutorial: Introduction to Quantum Computing 2016
Introduction to Quantum Computing 2016, a full day tutorial, will review potential approaches to quantum computing and explore adiabatic quantum computing in particular.

Quantum computing has progressed from ideas and research to implementation and product development. The original gate or circuit model of quantum computing has now been supplemented with several novel architectures that promise a quicker path to implementation and scaling. Additionally, there are multiple physical devices capable of providing controllable evolution of a quantum wavefunction which could form the basis for a quantum computer.

Real quantum computers implement a specific architecture using a particular choice of underlying devices. The combination of architecture and device gives rise to the programming model and operating characteristics of the system. The programming model in turn determines what kinds of algorithms the system can execute.

This introductory course includes a hands-on laboratory in which students will formulate and execute programs on a live quantum computer in Canada.

The attendees should:
- gain a high level understanding of the different types of potential quantum computers
- become familiar with adiabatic quantum computing architecture and programming model
- be able to run quantum algorithms live on a D-Wave quantum computer.

The class will be a lecture /lab format, labs will have step by step instructions with support staff to guide attendees and answer questions as they develop their own quantum algorithms. Attendees will be exposed to the types of problems and applications suitable for today’s quantum technology. It is our hope that attendees will leave this tutorial inspired to create new algorithms and applications, and to explore the adiabatic or other paradigms of quantum computing. A class website will be created allowing attendees to access the presentation materials.

It is recommended attendees are working toward or have a degree in Computer Science, Math, and Physics, or have a degree of mathematical maturity and/or familiarity with algorithms and data structures.

Logistics & Requirements:
o Length of the tutorial (full-day (7 hours))
o Percentage of content split: beginner 30%, intermediate 50%, advanced 20%
o Requirements for attendees:
• Class size 20 -30 participants
Participants will need to provide their own laptop and be able to connect via RDP (Microsoft remote desktop client recommended for Windows and OSX devices) to individual AWS hosted VM instances running Windows 2012 R2 server which contain our software. Participants with non-Windows desktops should install one of the following clients:
- Mac OSX/iOS: https://itunes.apple.com/ca/app/microsoft-remote-desktop/id715768417?mt=12 may need upgrade of the OS to the latest patch level.
- Android: same as for OSX/iOS can be found on the Google Play store at https://play.google.com/store/apps/details?id=com.microsoft.rdc.android&hl=en may need OS upgrades to the latest patch levels.
- Linux: “RDesktop” found at the following location: http://www.rdesktop.org/ may require dependent packages to be installed and comes in a tar.gz format.


Monday July 18, 2016 8:00am - 5:00pm
Sandringham InterContinental Miami

8:00am

Tutorial: Programming Intel's 2nd Generation Xeon Phi (Knights Landing)
Intel's next generation Xeon Phi, Knights Landing (KNL), brings many changes from the first generation, Knights Corner (KNC). The new processor supports self-hosted nodes, connects cores via a mesh topology rather than a ring, and uses a new memory technology, MCDRAM. It is based on Intel’s x86 technology with wide vector units and hardware threads. Many of the lessons learned from using KNC do still apply, such as efficient multi-threading, optimized vectorization, and strided memory access.
This tutorial is designed for experienced programmers familiar with MPI and OpenMP. We’ll review the KNL architecture, and discuss the differences between KNC and KNL. We'll discuss the impact of the different MCDRAM memory configurations and the different modes of cluster configuration. Recommendations regarding MPI task layout when using KNL with the Intel OmniPath fabric will be provided.
As in past tutorials, we will focus on the use of reports and directives to improve vectorization and the implementation of proper memory access and alignment. We will also showcase new Intel VTune Amplifier XE capabilities that allow for in-depth memory access analysis and hybrid code profiling.


Monday July 18, 2016 8:00am - 5:00pm
Merrick II

8:00am

Tutorial: Using the novel features of Bridges and optimizing for its Intel processors
Pittsburgh Supercomputing Center (PSC)’s Bridges is a new XSEDE resource that will enable the convergence of HPC and Big Data within a highly flexible environment. This hands-on tutorial will demonstrate how to best leverage the unique features and capabilities of Bridges : extremely large shared memory (up to 12TB per node); virtual machines; GPU computing; Spark and Hadoop environments; interactivity; in-memory databases; rich data collections; graph analytics capabilities and powerful programming environment. The tutorial will also explain how to get a successful allocation for Bridges.


Monday July 18, 2016 8:00am - 5:00pm
Alahambra

8:00am

Tutorial: The many faces of data management, interaction, and analysis using Wrangler.
Link to slides
The goal of this tutorial is to provide guidance to participants on large-scale data services and analysis support with the newest XSEDE data research system, Wrangler. Being a mostly first of its kind XSEDE resource, both user and XSEDE staff training is needed to enable the novel research opportunities Wrangler presents. The tutorial consists of two major components. The morning sessions focus on helping user to familiar with the unique architecture and characteristics of Wrangler System and a set of data services the wrangler supports, including large scale file based data managements, database services, and data sharing services. The morning presentation includes introduction on the Wrangler system and its user environment, use of reservations for computing, data systems for structured and unstructured data, and data access layers using both Wranglers replicated long term storage system and high speed flash storage system. We will also introduce the Wrangler graphical interfaces, including the Wrangler Portal, Web based tools served by Wrangler including Jupyter notebooks and RStudio, and the iDrop web interface for iRODS. The afternoon session will focus on data driven analysis support on wrangler. The presentations are center around use of the dynamic provisioned of Hadoop ecosystem on Wrangler. The presentations include introduction on the core Hadoop cluster for big data analysis, using existing analysis routines through Hadoop Streaming, interactive analysis with Spark, using Hadoop/Spark with the often more familiar to researchers Python and R interfaces. 


Monday July 18, 2016 8:00am - 5:00pm
Dupont

8:00am

Wise2 Workshop
Co-located workshop. 
WISE is a global trust community where security experts share information and work together, creating collaboration among different e-infrastructures. Agenda of the event:https://wiki.geant.org/display/WISE/Upcoming+events 
All interested persons welcome to attend!
https://wise-community.org/ 

Monday July 18, 2016 8:00am - 5:00pm
Sevilla InterContinental Miami

10:00am

Morning break - Sponsored by Cray and DDN
Monday July 18, 2016 10:00am - 10:30am
Mezzanine Mezzanine

12:00pm

Lunch - Sponsored by Cray and DDN
Monday July 18, 2016 12:00pm - 1:00pm
Mezzanine Mezzanine

1:00pm

Tutorial: Hands on with Jetstream
Jetstream is the first of its kind production cloud resource intended to support science and engineering research. As part of XSEDE, the goal is to aid researchers across the United States that need modest amounts of interactive computing power. Part of the goal in implementing Jetstream is to increase the disciplinary diversity of the XD ecosystem as well as to reach non-traditional researchers that may have HPC needs but have not had adequate access or have faced other barriers to HPC usage. In our session, we would spend the first thirty minutes discussing the architecture and use of Jetstream followed by a short question and answer session, and then spend the remainder of the time showing Jetstream in use as well as allowing attendees to get on and try the system.

Intended Audience Level: All (especially for researchers, Champions, and any other interested users)
Prerequisites: Laptops, XSEDE Portal accounts, ssh keys

Monday July 18, 2016 1:00pm - 3:00pm
Windsor InterContinental Miami

1:00pm

Tutorial: Building Parallel Scientific Applications Using GenASiS
In this half-day tutorial, intermediate to advanced users will be exposed to GenASiS Basics, a collection of Fortran 2003 classes furnishing extensible object-oriented implementations of some rudimentary functionality common to many large-scale scientific applications. Use of these classes allows application scientists to focus more of their time and effort on numerical algorithms, problem setup and testing, shepherding production runs to completion, and data analysis and interpretation. By running fluid dynamics and molecular dynamics examples---fundamentally different models, requiring the solution of different equations, using different techniques and different parallelization strategies---participants will gain a top-down perspective and appreciation for how GenASiS Basics facilitates development of a variety of scientific applications. By running selected unit test programs that exercise and exemplify the usage of selected GenASiS Basics classes, participants will get a bottom-up overview of the range of functionality provided by GenASiS Basics.


Monday July 18, 2016 1:00pm - 5:00pm
Michelangelo

1:00pm

Tutorial: Deploying and Using JupyterHub in an HPC environment
JupyterHub, when properly configured and integrated with third-party code, can be used to support Jupyter Notebooks and parallel IPython clusters dispatched directly and automatically in HPC compute cluster environments. This access trivializes access to HPC resources while providing a common interface that can be deployed in any environment.

In this tutorial we will

- Introduce the concept of the Jupyter notebook
- Teach visualization and data analytics using the Jupyter notebook
- Demonstrate parallelization of Python code using ipyparallel and mpi4py
- Demonstrate using Spark from the CU-Boulder JupyterHub implementation
- Explain the implementation details of our JupyterHub HPC environment

Previous tutorials offered by Research Computing at the University of Colorado boulder are at:
https://github.com/ResearchComputing/Final_Tutorials

A few example tutorials that will provide the basis for this proposal are:
- Python_notebook
- Python_DataAnalysis
- Intro_Spark

We have also run successfully tutorials at XSEDE in 2014 and 2015.

INTENDED AUDIENCE LEVEL: Beginner-Intermediate


Monday July 18, 2016 1:00pm - 5:00pm
Trade

1:00pm

Tutorial: Introduction to Brown Dog: An Elastic Data Cyberinfrastructure for Autocuration and Digital Preservation
In modern-day “Big Data” science, the diversity of data (unstructured, uncurated, and of different formats) and software provides major challenges for scientific research, especially with the reproducibility of results. The NSF DIBBs Brown Dog Project[1] aims to build cyberinfrastructure to aid autocuration, indexing, and search of unstructured and uncurated digital data. It is focusing on an initial set of science use cases (green infrastructure, critical zone studies, ecology, social science) to guide the overarching design, with user-accessible extensibility as an important driving requirement for the project development. The Brown Dog is composed of two highly extensible services, Data Access Proxy (DAP) and Data Tilling Service (DTS). These services aim to leverage/reuse any existing pieces of code, libraries, services, or standalone software (past or present), accessible through an easy-to-use and programmable interface. DAP focuses on file format conversions; DTS does content based analysis/extraction on/from a file. These services wrap relevant conversion and extraction operations within arbitrary software with reusability purpose, manage their deployment in an elastic manner, and manage job execution from behind a deliberately compact REST API. Underpinning these core services are the foundational tools, which do the actual work of conversion or extraction. These tools are integrated into the Brown Dog services via a Brown Dog Tools Catalogue.

This tutorial aims to give the attendee the knowledge to be able to add a tool to the Brown Dog Tools Catalogue, and to be able to integrate Brown Dog capabilities into an application via the API.

Specifically, the two components to the tutorial will cover:

* Adding a conversion or extraction tool to Tools Catalogue - the user creates a Brown Dog wrapper script around a 3rd party tool exposing some data transformation functionality within that tool. We will walk attendees through the process of creating and adding the tool to the Tools Catalogue.

* Utilizing Brown Dog transformation services, through the brown dog API, through a new or pre-existing application.

We will provide attendees with stub code for integration of a tool into the Tools Catalogue, as well as a stub client application that will be used as an example of how to program against Brown Dog.

Speakers

Monday July 18, 2016 1:00pm - 5:00pm
Escorial

1:00pm

Tutorial: Introduction to Python
This tutorial covers the Python programming language including all the information needed to participate in the XSEDE16 Modeling Day event on Tuesday. Topics covered will be variables, types, operators, input/output, control structures, lists, functions, math libraries, and plotting libraries. To participate fully in the hands-on exercises, attendees should come with the Anaconda Python 2.7 package downloaded and installed on their computer. You can get Anaconda Python at https://www.continuum.io/downloads. The tutorial is intended for Python beginners.


Monday July 18, 2016 1:00pm - 5:00pm
Brickell

1:00pm

Tutorial: Introduction to Scientific Workflow Technologies on XSEDE
This is a proposal for a joint tutorial between the ECSS workflows team, and the teams from the following workflow technologies: Swift, Makeflow/Work Queue, RADICAL-Pilot, and Pegasus. The goal is that attendees will leave the tutorial with an understanding of the workflow related services and tools available, that they will understand how to use them on XSEDE through hands-on exercises, and that they will be able to apply this knowledge to their own workloads when using XSEDE and other computing resources. The tutorial will be based on the successful XSEDE15 tutorial (http://sched.co/3YdC). All tutorial material is available from https://sites.google.com/site/xsedeworkflows/. The tutorial format will be primarily hands on and interactive.

One major obstacle when running workflows on XSEDE is where to run the workflow engine. Larger project and groups might have their own submit hosts, but it is common that users struggle finding a home for their workflow runs. For this reason, one effort that the ECSS workflows team have set up, based on feedback from the XSEDE14 workflow birds-of-a-feather session, is an IU Quarry hosted submit host. The host is based on as a clone of the login.xsede.org single sign on host. Thus, just like login.xsede.org, any XSEDE user with an active allocation will automatically have access. For the tutorial, we will also provide Jetstream-packaged VMs of the workflow software, as appropriate. With the host, we are also assembling content for a website highlighting tested workflow systems with XSEDE specific examples that users could use for trying out the different tools. These examples will be used as a basis for the examples in the proposed tutorial’s hands-on exercises.

Swift is a simple language for writing parallel scripts that run many copies of ordinary programs concurrently as soon as their inputs are available, reducing the need for complex parallel programming. The same script runs on multi-core computers, clusters, clouds, grids and supercomputers, and is thus a useful tool for moving your computations from laptop or workstation to any XSEDE resource. Swift can run a million programs, thousands at a time, launching hundreds per second. This hands-on tutorial will give participants a taste of running simple parallel scripts on XSEDE systems and provide pointers for applying it to your own scientific work.

Makeflow is a workflow engine for executing large complex workflows, with workflows up to thousands of tasks and hundreds of gigabytes. In this section of the tutorial, users will learn the basics of writing a Makeflow, which is based on the traditional Make construct. In the hands-on example, the users will learn to write Makeflow rules, run a makeflow locally, as well as running the tasks on XSEDE resources. The users will be introduced to Work Queue, a scalable master/worker framework, and create workers on XSEDE resources and connect them to the makeflow. The users will learn to use Work Queue to monitor workflows and the basics of debugging makeflows.

The Pegasus Workflow Management System sits on top of HTCondor DAGMan. In this section of the tutorial, users will learn how to create abstract workflows, and plan, execute, and monitor the resulting executable workflow. The first workflow will be run locally on the submit host, while the two other hands-on examples will be about running workflows on XSEDE resources. One workflow will include running jobs across resources, and highlights the workflow system’s data management capability in such setups. Another workflow will be about about using the pegasus-mpi-cluster tool to execute a high-throughput workload in an efficient and well-behaved manner on one of the XSEDE high performance computing resources.

RADICAL-Pilot allows a user to run large numbers of tasks concurrently on a multitude of distributed computing resources. A task can be a large-parallel simulation or a single-core analysis routine. RADICAL-Pilot is a “programmable” Pilot-Job system developed in Python. After discussing the concept of “Pilot Jobs”, we introduce how to use RADICAL-Pilot to support task-level parallelism. We then demonstrate how to write simple Python applications that use RADICAL-Pilot to execute coupled tasks on distributed computing resources. Additionally, the user can specify input and output data on the tasks that will be handled transparently by the system.

Attendee prerequisites: The participants will be expected to bring in their own laptops with the following software installed: SSH client, Web Browser, PDF reader. We assume basic familiarity with working in a Linux environment.

Special Needs: Even though the submit host enables users with existing allocations to use their own accounts, we would like to have access to a set of XSEDE training accounts for users who currently do not have active allocations.


Monday July 18, 2016 1:00pm - 5:00pm
Balmoral

1:00pm

Tutorial: Parallel I/O - for Reading and Writing Large Files in Parallel
Link for Presentation
This half-day tutorial will provide an overview of the practices and strategies for the efficient utilization of parallel file systems through parallel I/O. The target audience of this tutorial is analysts and application developers who do not have prior experience with MPI I/O, HDF5, and T3PIO. However, they should be familiar with C/C++/Fortran programming and basic MPI. A brief overview of the related basic concepts will be included in the tutorial where needed. All the concepts related to the tutorial will be explained with examples and there will be a hands-on session. By the end of the tutorial, the audience will have learnt to implement parallel I/O (through MPI I/O and the high-level libraries discussed in this tutorial) and will be motivated to apply the knowledge gained to improve the I/O performance of their applications.


Monday July 18, 2016 1:00pm - 5:00pm
Gusman

1:00pm

Tutorial: Scientific Computing without the Command-line: An Intro to the Agave API
High performance computing has become a critical resource in an increasing number of scientific disciplines. For many of these “nontraditional” computing communities, the learning curve to become proficient at the command-line is a burden, but it also constrains the computational side of that scientific domain to a subset of specialists. Conversely, bringing computationally demanding apps upon which a scientific community relies to a more accessible interface can provide a platform for broader adoption, collaboration, and ultimately accelerated discovery.
This workshop demonstrates how to use the Agave API to run complete scientific workflows using XSEDE high performance computing resources without touching the command-line. Through hands-on sessions, participants will look at managing and sharing data across XSEDE resources, and we will tackle how to orchestrate job execution across systems and capture metadata on the results (and the process) so that parameters and methodologies are not lost. We will guide users on how to leverage software modules on the system as well as custom code installed in user space. Finally, we will discuss examples how both individual labs as well as large projects are using XSEDE and Agave to provide web interfaces for everything from crop modeling to molecular simulations. The Agave API and all the tools used are open-source software.


Monday July 18, 2016 1:00pm - 5:00pm
Raphel

1:00pm

Tutorial: SciGaP Tutorial: Developing Science Gateways using Apache Airavata
Science gateways, or Web portals, are an important mechanism for broadening and simplifying access to computational grids, clouds, and campus resources. Gateways provide science-specific user interfaces to end users who are unfamiliar with or need more capabilities than provided by command-line interfaces. In this tutorial, we present SciGaP, which includes participation from the CIPRES, UltraScan, Neuroscience, and SEAGrid Gateways combined with the Apache Airavata middleware for managing jobs and data. Our goal is to show participants how to build and run gateways using both software and collected experience from some of the most heavily used XSEDE science gateways. This tutorial will build on the well attended and well reviewed XSEDE14 and XSEDE15 tutorials. Extensive tutorial material is available from https://s.apache.org/scigap-xsede14 and https://s.apache.org/scigap-xsede15.

Speakers
avatar for Suresh Marru

Suresh Marru

Member, Apache Software Foundation
Suresh Marru is a Member of the Apache Software Foundation and is the current PMC chair of the Apache Airavata project. He is a principal research systems architect at Indiana University. Suresh focuses on research topics at the intersection of distributed systems, application domain science; computational systems and has authored or co-authored over 75 peer-reviewed conference papers and journal articles in these areas. He gets his hands on... Read More →


Monday July 18, 2016 1:00pm - 5:00pm
Tuttle

1:00pm

Tutorial: Using the XDMoD Job Viewer to Improve Job Performance
XDMoD has recently been enhanced with a Job Viewer feature that provides users, HPC support specialists, and others with access to detailed job level information. This information includes: accounting data, details about the application being run, summary and detailed job performance metrics, and time series plots describing CPU user, memory usage, memory bandwidth, network interconnect, parallel file system and flops for individual jobs. Virtually all XSEDE affiliated resources have been instrumented with TACC_stats, and as a result are now supplying job level performance data directly to XDMoD. Users and support personnel can use this information to determine the efficiency of a given job, and to guide the improvement of job efficiency for subsequent jobs. This tutorial will instruct the user in how to use the XDMoD Job Viewer, describe the type of job-level information that it includes, and guide participants in the use of the Job Viewer as a user support and analysis tool. This tutorial will be beneficial to all levels of users from beginners looking to understand how to launch parallel HPC jobs properly to advanced users trying to optimize job performance.


Tentative Outline for XSEDE16 Job Viewer Tutorial:

1. Overview of XDMoD (Thomas Furlani)
a. Focus on impact to improve code efficiency/Performance
b. Examples
c. Introduce Job Viewer as a tool

2. Brief Demo of XDMoD (Matthew Jones or Robert DeLeon)
a. Overview
b. Application Kernels
c. Job level monitoring (SUPReMM)
d. Job Viewer Introduction

3. Detailed Demo of XDMoD Job Viewer (Joseph White or Matthew Jones)
a. How to use the Job Viewer
b. Information provided by the Job Viewer
c. How to use the Job Viewer as a user support tool

4. Hands-on use of XDMoD and the Job Viewer (CCR personnel)
a. Pick a few example cases to show in greater detail
b. Emphasis on Job Viewer workflow
c. Secondary emphasis on using XDMoD for efficiency and quality of service

5. Summary presentation—Take home lessons (All)


Monday July 18, 2016 1:00pm - 5:00pm
Chopin Ballroom

1:00pm

Tutorial: XSEDE New User Tutorial
This tutorial will provide training and hands-on activities to help new users learn and become comfortable with the basic steps necessary to first obtain, and then successfully employ an XSEDE allocation to accomplish their research or educational goals. The tutorial will consist of three sections: The first part of the tutorial will explain the XSEDE allocations process and how to write and submit successful allocation proposals. The instructor will describe the contents of an outstanding proposal and the process for generating each part. Topics covered will include the scientific justification, the justification of the request for resources, techniques for producing meaningful performance and scaling benchmarks, and navigating the XRAS system through the XSEDE Portal for electronic submission of proposals. The second section, "Information Security Training for XSEDE Researchers," will review basic information security principles for XSEDE users including: how to protect yourself from on-line threats and risks, how to secure your desktop/laptop, safe practices for social networking, email and instant messaging, how to choose a secure password and what to do if your account or machine have been compromised. The third part of the tutorial will cover the New User Training material that is been delivered remotely quarterly, but will delve deeper into these topics. New topics will be covered, including how to troubleshoot a job that has not run, and how to improve job turnaround by understanding differences in batch job schedulers on different platforms. We anticipate significant interest from Campus Champions, and therefore we will explain how attendees can assist others, as well as briefly describe projects that are being currently carried out in non-traditional HPC disciplines.


Monday July 18, 2016 1:00pm - 5:00pm
Bayfront B

3:00pm

Afternoon Break - Sponsored by Cray and DDN
Monday July 18, 2016 3:00pm - 3:30pm
Mezzanine Mezzanine

3:00pm

Tutorial: Teach GPU Accelerating Computing - Hands-on with NVIDIA Teaching Kit for University Educators
As performance and functionality requirements of interdisciplinary computing applications rise, industry demand for new graduates familiar with accelerated computing with GPUs grows. In the future, many mass-market applications will be what are considered "supercomputing applications" as per today's standards. This hands-on tutorial introduces a comprehensive set of academic labs and university teaching material for use in introductory and advanced parallel programming courses. The teaching materials start with the basics and focus on programming GPUs, and include advanced topics such as optimization, advanced architectural enhancements, and integration of a variety of programming languages.

INTENDED AUDIENCE LEVEL: Intermediate
PRE-REQUISITES: Laptop to participate in hands-on aspect


Monday July 18, 2016 3:00pm - 5:00pm
Windsor InterContinental Miami

3:00pm

ACI-REF All-hands
Co-located workshop. Attendance by invitation only.

Monday July 18, 2016 3:00pm - 5:00pm
Godfrey

5:15pm

BOF: Coin of the Realm: Current practices and future opportunities in processing of XSEDE allocations awards and usage data
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.


Monday July 18, 2016 5:15pm - 6:15pm
Tuttle

5:15pm

BOF: Developing a System for HPC Administrators Professional Development
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.


Monday July 18, 2016 5:15pm - 6:15pm
Balmoral

5:15pm

BOF: Enriching the XSEDE Ecosystem with Software Toolkits
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.


Monday July 18, 2016 5:15pm - 6:15pm
Bayfront B

5:15pm

BOF: HPC and Data Analytics: High Performance Research Computing in the world of Data Science
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.


Monday July 18, 2016 5:15pm - 6:15pm
Sandringham InterContinental Miami

5:15pm

BOF: Shared Solutions in HPC Training
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.

Speakers
avatar for Dana Brunson

Dana Brunson

Asst. VP Research CI/Director, High Performance Computing Center, Oklahoma State University


Monday July 18, 2016 5:15pm - 6:15pm
Trade

5:15pm

BOF: Value Analytics - a New Module for XDMoD
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.


Monday July 18, 2016 5:15pm - 6:15pm
Windsor InterContinental Miami

6:30pm

Campus Champions Networking Event
Champions Meet, Greet, and Network with Champion Community --BY INVITATION ONLY

Monday July 18, 2016 6:30pm - 8:00pm
Bayfront InterContinental Miami
 
Tuesday, July 19
 

7:00am

Breakfast
Tuesday July 19, 2016 7:00am - 8:00am
Mezzanine Mezzanine

7:00am

Registration
Tuesday July 19, 2016 7:00am - 4:30pm
Registration

8:00am

Plenary - Opening Session. DR. PAMELA MCCAULEY Innovation Nation: The Critical Impact of Innovation
Welcome from Conference Chair
Plenary - Pamela McCauley 
In this dynamic keynote address, Dr. Pamela McCauley discusses the impact of innovation on individuals, nations, and the global society. She highlights her State Department HIV/AIDS Health Care Service Delivery work as an application example of the critical impact of science and technology innovation. Intertwined in her talk, Dr. McCauley highlights the crucial component of diversity and why successful innovation is dependent on all-inclusive collaboration. She shares high and lows of her own career as well as research-based practical strategies for individuals and organizations to propel their actions into useful products and services, both globally and collaboratively. 

Dr. Pamela McCauley is an ergonomics and biomechanics expert, a dynamic keynote speaker, a popular author, and an award-winning professor in the Department of Industrial Engineering and Management Systems at the University of Central Florida where she serves as Director of the Ergonomics Laboratory.

Dr. McCauley is currently on assignment with the U.S. Department of State in her role as a Jefferson Science Fellow. The Jefferson Science Fellowship program serves as an innovative model for engaging the American academic science and engineering communities in U.S. foreign policy. Dr. McCauley is involved in technology assessment and policy, researching the globally critical Ergonomics of Ebola, HIV and Other Infectious Diseases for Healthcare Workers.

She is the author of over 80 technical papers, book chapters, conference proceedings and the internationally best-selling ergonomics textbook; Ergonomics: Foundational Principles, Applications, and Technologies. Many of her leadership, diversity, innovation and STEM education related talks draw from her research-based book Transforming Your STEM Career Through Leadership and Innovation: Inspiration and Strategies for Women as well as her personal story; Winners Don't Quit . . . Today They Call Me Doctor.

 

Tuesday July 19, 2016 8:00am - 10:00am
Grand Ballroom InterContinental Miami

8:00am

Jetstream All-hands
Co-located workshop. Attendance by invitation only.

Tuesday July 19, 2016 8:00am - 10:00am
Tuttle

8:00am

Polar HPC Hackathon
Co-located workshop. Attendance is by invitation only.

Tuesday July 19, 2016 8:00am - 5:00pm
Flagler InterContinental Miami

8:00am

Polar HPC Hackathon Breakout
Co-located workshop. Attendance is by invitation only.

Tuesday July 19, 2016 8:00am - 5:00pm
Star/Palm Isle

9:30am

Student Modeling Day
Modeling Day- undergraduates and graduates will work in teams to understand an underlying model and its behavior, simulate a range of conditions, write and test the computer codes (using Python programming language) that are needed to solve real-world problems, improve the user interface to the code, and validate code against real data or more sophisticated models.

Maximum capacity: 45. Sign-ups are strongly encouraged

Tuesday July 19, 2016 9:30am - 5:00pm
Merrick II

10:00am

Morning Break - Sponsored by SDSC
Tuesday July 19, 2016 10:00am - 10:30am
Biscayne Ballroom

10:30am

AD: Image Analysis and Infrastructure Support for Data Mining the Farm Security Administration – Office of War Information Photography Collection
This paper reports on the initial work and future trajectory of the Image Analysis of the Farm Security Administration – Office of War Information Photography Collection team, supported through an XSEDE startup grant and Extended Collaborative Support Service (ECSS). The team is developing and utilizing existing algorithms and running them on Comet to analyze the Farm Security Administration - Office of War Information image corpus from 1935-1944, held by the Library of Congress (LOC) and accessible online to the public. The project serves many fields within the humanities, including photography, art, visual rhetoric, linguistics, American history, anthropology, and geography, as well as the general public. Through robust image, metadata, and lexical semantics analysis, researchers will gain deeper insight into photographic techniques and aesthetics employed by FSA photographers, editorial decisions, and overall collection content. By pairing image analysis with metadata analysis, including lexiosemantic extraction, the opportunities for deep data mining of this collection expand even further.


Tuesday July 19, 2016 10:30am - 11:00am
Chopin Ballroom

10:30am

SW: A Virtual Filesystem for On-demand Processing of Multi-dimensional Datasets
Diverse areas of science and engineering are increasingly driven by high-throughput automated data capture and analysis. Modern acquisition technologies, used in many scientific applications (e.g., astronomy, physics, materials science, geology, biology, and engineering) and often running at gigabyte per second data rates, quickly generate terabyte to petabyte datasets that must be stored, shared, processed and analyzed at similar rates. The largest datasets are often multidimensional, such as volumetric and time series data derived from various types of image capture. Cost-effective and timely processing of these data requires system and software architectures that incorporate on-the-fly processing to minimize I/O traffic and avoid latency limitations. In this paper we present the Virtual Volume File System, a new approach to on-demand processing with file system semantics, combining these principles into a versatile and powerful data pipeline for dealing with some of the largest 3D volumetric datasets. We give an example of how we have started to use this approach in our work with massive electron microscopy image stacks. We end with a short discussion of current and future challenges.


Tuesday July 19, 2016 10:30am - 11:00am
Brickell

10:30am

TECH: Jetstream - performance, early experience, and early results
Jetstream is undergoing its acceptance review by the National Science Foundation (NSF) at the beginning of May. We expect the system to be accepted by the NSF in short order and this abstract is written with the assumption that acceptance will be complete by the time final versions of papers are due. Here, we present the acceptance test criteria and results that define the key performance characteristics of Jetstream, describe the experiences of the Jetstream team in standing up and operating an OpenStack-based cloud environment, and describe some of the early scientific results that have been obtained by researchers and students using this system. Jetstream is a distributed production cloud resource and, as such, is a first-of-a-kind system for the NSF; it is scaled at an investment and computational capability – 0.5 PetaFLOPS peak – that is consistent with this status. While the computational capability does not stand out within the spectrum of resources funded by the NSF and supported by XSEDE, the functionality does. Jetstream offers interactive virtual machines (VMs) provided through the user-friendly Atmosphere interface. The software stack consisting of Globus for authentication and data transfer, OpenStack as the basic cloud environment, and Atmosphere as the user interface has proved very effective although the OpenStack change cycle and intentional lack of backwards compatibility creates certain implementation challenges. Jetstream is a multi-region deployment that operates as a single integrated system and is proving effective in supporting modes and subdisciplines of research traditionally underrepresented on larger XSEDE-supported clusters and supercomputers. Already researchers in biology, network science, economics, earth science, and computer science have used it to perform research – much of it research in the “long tail of science.”


Tuesday July 19, 2016 10:30am - 11:00am
Sevilla InterContinental Miami

10:30am

WDD: Challenges and Accomplishments of the Computational Science Undergraduate Research Experiences (CSURE) REU Program
The Computational Science for Undergraduate Research Experiences (CSURE) is an NSF funded Research Experiences for Undergraduates (REU) program organized by the Joint Institute for Computational Sciences (JICS), www.jics.utk.edu/csure-reu. The main goal of the CSURE project is to direct a group of ten undergraduate students to explore the emergent computational science models and techniques proven to work on the supercomputers at the National Institute for Computational Sciences (NICS). In addition, a number of summer interns from Hong Kong also participated in the program. The CSURE program focuses on five different scientific domains: chemistry and material sciences, systems biology, engineering mechanics, atmospheric sciences, and parallel solvers on emergent platforms. The program also enjoys the joint relationship with researchers at the Oak Ridge National Laboratory. Because of these diverse topics of research area and backgrounds of participant, we will in this paper entail the challenges and resolutions in managing and coordinating the program, delivering cohesive tutorial materials, directing mentorship of individual projects, and a few good lessons learned in the duration of the program since it started in 2013.


Tuesday July 19, 2016 10:30am - 11:00am
Trade

11:00am

AD/VIS: UrbanFlow: Large-scale Framework to Integrate Social Media and Authoritative Landuse Maps
Users of micro-blogging services and content sharing platforms are generating massive amount of Geotagged information on a daily basis. Although these big data streams are not intended as a source of Geospatial information, researchers have found that ambient geographic information (AGI) complements authoritative sources. In this regard, the digital footprints of users provides a real time monitoring of people activities and their spatial interaction, while more traditional sources such as remote sensing and land use maps provide a synoptic view of the physical infrastructure of the urban environment. Traditionally trained scientists in social science and geography usually face great challenges when experimenting with new methods to synthesize big data sources because of the data volume and its lack of a structure. In order to overcome these challenges we developed UrbanFlow, a platform that allows scientists to synthesize massive Geolocated Twitter data with detailed land use maps. This platform would allow scientists to gather observations to better understand human mobility patterns in relation to urban land use, study cities’ spatial networks based on identifying common frequent visitors between different urban neighborhoods and monitoring the patterns of urban land use change. A key aspect of UrbanFlow is utilizing the power of distributed computing (using Apache Hadoop and cloud-based services) to process massive number of tweets and integrate them with authoritative datasets, as well as efficiently store them in a database cluster to facilitate fast interaction with users.


Tuesday July 19, 2016 11:00am - 11:30am
Chopin Ballroom

11:00am

SW: An Architecture for Automatic Deployment of Brown Dog Services At Scale into Diverse Computing Infrastructures
Brown Dog is an extensible data cyberinfrastructure, that provides a set of extensible and distributed data conversion and metadata extraction services to enable access and search within unstructured, un-curated and inaccessible research data across different domains of sciences and social science, which ultimately aids in supporting reproducibility of results. We envision that Brown Dog, as a data cyberinfrastructure, is an essential service in a comprehensive cyberinfrastructure which includes data services, high performance computing services and more that would enable scholarly research in a variety of disciplines that today is not yet possible. Brown Dog focuses on four initial use cases, specifically, addressing the conversion and extraction needs in the research areas of ecology, civil and environmental engineering, library and information science, and use by the general public. In this paper, we describe an architecture that supports contribution of data transformation tools from users, and automatic deployment of the tools as Brown Dog services in diverse infrastructures such as cloud or high performance computing (HPC) based on user demands and load on the system. We also present results validating the performance of the initial implementation of Brown Dog.


Tuesday July 19, 2016 11:00am - 11:30am
Brickell

11:00am

TECH: User Managed Virtual Clusters in Comet
Hardware virtualization has been gaining a significant share of computing timein the last years. Using virtual machines (VMs) for parallel computing is anattractive option for many users. A VM gives users a freedom of choosing anoperating system, software stack and security policies, leaving the physicalhardware, OS management, and billing to physical cluster administrators. Thewell-known solutions for cloud computing, both commercial (Amazon Cloud, GoogleCloud, Yahoo Cloud, etc.) and open-source (OpenStack, Eucalyptus) provideplatforms for running a single VM or a group of VMs. With all the benefits,there are also some drawbacks, which include reduced performance when runningcode inside of a VM, increased complexity of cluster management, as well as theneed to learn new tools and protocols to manage the clusters.
At SDSC, we have created a novel framework and infrastructure by providing virtualHPC clusters to projects using the NSF sponsored Comet supercomputer.Managing virtual clusters on Comet is similar to managing a bare-metal cluster in terms of processes and tools that are employed. This is beneficial becausesuch processes and tools are familiar to cluster administrators. Unlikeplatforms like AWS, Comet's virtualization capability supportsinstalling VMs from ISOs (i.e., a CD-ROM or DVD image) or via an isolatedmanagement VLAN (PXE). At the same time, we're helping projects take advantageof VMs by providing an enhanced client tool for interaction with our managementsystem called Cloudmesh client. Cloudmesh client can also be used to managevirtual machines on OpenStack, AWS, and Azure.


Tuesday July 19, 2016 11:00am - 11:30am
Sevilla InterContinental Miami

11:00am

WDD: Assisting Bioinformatics Programs at Minority Institutions: Needs Assessment, and Lessons Learned -A Look at an Internship Program
PURPOSE: We present work in assisting Bioinformatics efforts at minority institutions in the USA funded through an NIH grant over the last 15 years. The primary aim was to create a program for assisting minority institutions in building multidisciplinary bioinformatics training programs. DESIGN: The program involves four components for immediate and long-term increases in research opportunities at minority institutions. Component 1: A two-week Summer Institute in Bioinformatics introducing the breadth of bioinformatics while discussing open research problems. Component 2: Strengthening or establishing bioinformatics programs at minority serving campuses by teaching bioinformatics in collaboration with local faculty. Component 3: A five to eight-week research internship at the PSC for students that completed bioinformatics courses on their campuses. Component 4: Development of a model curriculum for a concentration in bioinformatics in biology, computer science, or mathematics. In this paper we will report on the results of the internship program. 
METHODS: In compliance with federal regulations (45 CFR 46) concerning Human Subjects Research, the survey materials and procedures used and discussed in this paper were approved by Carnegie Mellon University’s Institutional Review Board (IRB No. HS-13-099 on 3/15/13, IRB No HS-14-141 on 3/18/14, and IRB No HS-15-178 on 3/12/15). Under these approved procedures, we began to conduct voluntary pre and post surveys of interns and summer institute participants. These surveys were completed at the very beginning of their summer experience at the PSC (pre-survey) and again at the end of their summer experience at the PSC (post-survey). This paper reports on a subset of the questions asked in the pre and post surveys, mainly on the demographic and skill sets of the participants that are most relevant to computation and high performance computing. 
DEMOGRAPHICS: 21 minority institutions have benefited the grant. Of the thirty-six student surveys completed, 36% were completed by undergraduate students, 36% by master’s students and 25% by doctoral students. 96% of total participants identified that they were attending a minority serving institution (MSI) with 47% indicating that they were attending a Hispanic serving institution, 44% indicating that they were attending a historically black college/university while 5% indicated that they were attending an “other” minority serving institution. 82% of participants self-identified as belonging to racial and ethnic groups that have been shown by the National Science Foundation to be underrepresented in health-related sciences on a national basis, which includes African Americans, Hispanic Americans, Native Americans, Alaskan Natives, Hawaiian Natives, and Natives of the U.S. Pacific Islands. 
NEEDS ASSESSMENT: The MARC pre-survey also included questions asking the participant to identify their prior bioinformatics knowledge. Few student participants self-identified as having intermediate bioinformatics knowledge. The majority of participants in the pre-surveys identified themselves as being able to run bioinformatics programs, but being uncomfortable changing the program parameters. One-third have not done basic bioinformatics analysis (such as database search and multiple alignment). About one-half had not done more advanced bioinformatics analysis and greater than one-half had not worked with structural data. About three-quarters or greater of the participants had not been exposed to common NGS analyses. The number of participants that reported Basic or Advanced skills with programming, databases, or the UNIX operating system was 30% or less. When asked through an open text unstructured question to list the basic steps and tools needed for these analyses, before the workshop the answers to this type of questions was typically “I do not know”. In the post-survey, the majority of the participants expressed that they could run basic bioinformatics analyses at an intermediate or advanced level. For NGS tasks done during the training less than one-third expressed that they could perform these analyses at an advanced level. The participants reported improvements in their programming, databases, or UNIX skills but 30-50% indicated low-level skills in these areas. 
LESSONS LEARNED: A strong team effort at the teaching level is needed to help improve the skill set of interns. Follow-up is key in order to help student maintain or improve the skills gained and carry out research successfully. It is very difficult to add courses or degrees in many state Minority Serving Institutions. Variability in traditional Biology Curricula make adapting the courses and modules required for broader improvement of computational skills a challenge. Math requirements at the bachelor’s degree level and “introductory computing” courses can be substantial barriers to success for biology students. Finally, better bioinformatics and computational textbooks for biologists at the undergraduate level are needed. 
CONCLUSIONS: This program has been a highly successful outreach effort and a very sound and cost-effective use of the MARC funding program from NIH. Important lessons have been learned about bioinformatics education that should be implemented at the policy level in order to ensure that educators, students and researchers at minority serving institutions can address science problems using state-of-the-art computational methods, computational genomics and Big Data. 

GRANT SUPPORT: This work was supported by National Institutes of Health Minority Access to Research Careers (MARC) grant T36-GM-095335 to the Pittsburgh Supercomputing Center. It also used the BioU computing cluster, which was made available by National Institutes of Health grant T36-GM-008789 to the Pittsburgh Supercomputing Center. This work used the Extreme Science and Engineering Discovery Environment (XSEDE), which is supported by the National Science Foundation grant OCI-1053575. Specifically, it used the Blacklight supercomputer system at the Pittsburgh Supercomputing Center (PSC).


Tuesday July 19, 2016 11:00am - 11:30am
Trade

11:30am

AD: Accelerating TauDEM for Extracting Hydrology Information from National-Scale High Resolution Topographic Dataset
With the advent of DEMs with finer resolution and higher accuracy to represent surface elevation, we face an enormous need to have optimized parallel hydrology algorithms that are imminent to be able to process big DEM data efficiently. TauDEM (Terrain Analysis Using Digital Elevation Models) is a suite of Digital Elevation Model (DEM) tools for the extraction and analysis of hydrologic information from topography. We present performance improvements on parallel hydrology algorithms in TauDEM suite that allowed us to process very big DEM data. The parallel algorithms are improved by applying block-wise data decomposition technique, improving communication model and parallel I/O enhancements to obtain maximum performance from available computational and storage resources at supercomputer systems. After the improvements, as a case study, we successfully filled the depressions of entire US 10-meter DEM data (667GB, 180 billion raster cells) within 2 hours that shows a significant improvement compared to the previous parallel algorithm that was unable to do the same task within 2 days using 4,096 processor cores on Stampede supercomputer. We report the methodology and make the performance analysis of the algorithm improvements.


Tuesday July 19, 2016 11:30am - 12:00pm
Chopin Ballroom

11:30am

SW: In-memory Integration of Existing Software Components for Parallel Adaptive Unstructured Mesh Workflows
Reliable mesh-based PDE simulations are needed to solve complex engineering problems. Mesh adaptivity can increase reliability by reducing discretization errors, but requires two or more software components to exchange information. Often, components exchange information by reading and writing a common file format. 
On massively parallel computers filesystem bandwidth is a critical performance bottleneck. Our data stream and component interface approaches avoid the filesystem bottleneck. In this paper we present the approaches and discuss their use within the PHASTA computational fluid dynamics solver and Albany Multiphysics framework. Information exchange performance results are reported on up to 2048 cores of a BlueGene/Q system.


Tuesday July 19, 2016 11:30am - 12:00pm
Brickell

11:30am

TECH: Experiences and Benefits of Running RDMA Hadoop and Spark on SDSC Comet
Big Data problems dealing with a variety of large data sets are now common in a wide range of domain science research areas such as bioinformatics, social science, astronomical image processing, weather and climate dynamics, and economics. In some cases, the data generation and computation is done on high performance computing (HPC) resources, thus presenting an incentive for developing/optimizing big data middleware and tools to take advantage of the existing HPC infrastructures. Data-intensive computing middleware (such as Hadoop, Spark) can potentially benefit greatly from the hardware already designed for high performance and scalability with advanced processor technology, large memory/core, and storage/filesystems. SDSC Comet represents such a resource with large numbers of compute nodes with fast node local SSD storage, and high performance Lustre filesystems. This paper discusses experiences and benefits of using optimized Remote Direct Memory Access (RDMA) Hadoop and Spark middleware on the XSEDE Comet HPC resource, including some performance results of Big Data benchmarks and applications. Comet is a general purpose HPC resource so some work is needed to integrate the middleware to run within the HPC scheduling framework. This aspect of the implementation is also discussed in detail.


Tuesday July 19, 2016 11:30am - 12:00pm
Sevilla InterContinental Miami

11:30am

WDD: An Agile Approach for Engaging Students in Research and Development
Opportunities to solve real-world problems - collaboratively or individually – can create significant impact on the education and career goals of students. By providing such opportunities to students, research groups and businesses can also benefit significantly. However, several factors and strategies play a role in developing a mutually beneficial synergy between the students and research groups (or businesses). Adopting a disciplined agile approach for student engagement and retention is one such strategy. In this paper we discuss our experiences in engaging students in research and development through the aforementioned approach. Some lessons learnt and recommendations are also included in the paper.


Tuesday July 19, 2016 11:30am - 12:00pm
Trade

12:00pm

Lunch - Sponsored by Dell
Tuesday July 19, 2016 12:00pm - 1:00pm
Mezzanine Mezzanine

12:00pm

Open SP Forum Meeting
Tuesday July 19, 2016 12:00pm - 1:00pm
Windsor InterContinental Miami

1:00pm

Plenary - Meredith Drosback - White House Office of Science and Technology Policy - "The National Strategic Computing Initiative"
The National Strategic Computing Initiative was launched one year ago asan all-of-government effort to maximize the benefits of high-performancecomputing research, development, and deployment to advance scientificdiscovery and ensure economic competitiveness.  The Initiative includesparticipation from the National Science Foundation, Department of Energy,Department of Defense, and eight other Federal departments and agencies.In this presentation, I will share an overview of the Initiative as wellas an update on Federal efforts over the last year and opportunities forengagement with academia and industry.

Speakers
avatar for Meredith Drosback

Meredith Drosback

Dr. Meredith Drosback serves as the Assistant Director for Education andPhysical Sciences and the Science Division Staff Director at the WhiteHouse Office of Science and Technology Policy (OSTP).  Her work focuseson improving learning outcomes and opportunities in science, technology,engineering, and mathematics (STEM) education, as well as a variety oftopics across the broader science portfolio, including space science,physical science... Read More →


Tuesday July 19, 2016 1:00pm - 3:00pm
Grand Ballroom InterContinental Miami

3:00pm

3:30pm

AD: Optimization of non-linear image registration in AFNI
The Analysis of Functional Neuroimaging (AFNI) is a widely adopted software package in the fMRI data analysis community. For many types of analysis pipelines, one important step is to register a subject's image to a pre-defined template so different images can be compared within a normalized coordination system. Although a 12-point affine transformation works fine for some standard cases, it is usually found insufficient for voxelwise types of analyses. This is especially challenging if the subject has brain atrophy due to some kinds of neurological condition such as Parkinson's disease. The 3dQwarp code in AFNI is a non-linear image registration procedure that overcomes the drawbacks of a canonic affine transformation. However, the existing OpenMP instrumentation in 3dQwarp is not efficient for warping at an ultra fine level, and the constant trip counts of the iterative algorithm also hurts the accuracy. Based on the profiling and benchmark analysis, we improve the parallel efficiency by the optimization of its OpenMP structure and obtain about 2x speedup for normalized workload. With the incorporation of a convergence criteria, we are able to perform warping at a much finer level beyond the default threshold and achieve about 20% improvement in term of Pearson correlation.


Tuesday July 19, 2016 3:30pm - 4:00pm
Chopin Ballroom

3:30pm

SW: CloudBridge: a Simple Cross-Cloud Python Library
With clouds becoming a standard target for deploying applications, it is more important than ever to be able to seamlessly utilize resources and services from multiple providers. Proprietary vendor APIs make this challenging and lead to conditional code being written to accommodate various API differences, requiring application authors to deal with these complexities and to test their applications against each supported cloud. In this paper, we describe an open source Python library called CloudBridge that provides a simple, uniform, and extensible API for multiple clouds. The library defines a standard ‘contract’ that all supported providers must implement, and an extensive suite of conformance tests to ensure that any exposed behavior is uniform across cloud providers, thus allowing applications to confidently utilize any of the supported clouds without any cloud-specific code or testing.


Tuesday July 19, 2016 3:30pm - 4:00pm
Brickell

3:30pm

3:30pm

WDD: XSEDE Scholars Tutorial: The Things I Wish I Had Known When I Started in HPC
High Performance Computing (HPC) clusters have been essential in the simulation of physical systems due to their large computing power and storage capabilities. However, new users, the majority who are in non-computing fields, face several challenges when working with these supercomputers because the information found online can be overwhelming and no practical guides are readily available. The panel will cover challenges and answers to several topics ranging from: getting access to a supercomputer, logging in to the system, submitting jobs, and future needs of non-traditional users.


Tuesday July 19, 2016 3:30pm - 4:15pm
Trade

4:00pm

AD: Optimization and parallel load balancing of the MPAS Atmosphere weather and climate code
MPAS (Model for Prediction Across Scales) Atmosphere is a highly scalable application for global weather and climate simulations. It uses an unstructured Voronoi mesh in the horizontal dimensions, thereby avoiding problems associated with traditional rectilinear grids, and deploys a subset of the atmospheric physics used in WRF. In this paper, we describe work that was done to improve the overall performance of the software: serial optimization of the dynamical core and thread-level load balancing of the atmospheric physics. While the overall reductions were modest for standard benchmarks, we expect that the contributions will become more important with the eventual addition of atmospheric chemistry or when running at larger scale.


Tuesday July 19, 2016 4:00pm - 4:30pm
Chopin Ballroom

4:00pm

SW: Optimization of 3D Fusion Devices
Optimization and design of nuclear fusion devices is a complex task with large computational requirements. The complexity is defined by the number of parameters involved in every single possible optimization function that focuses on the different aspects of plasma confinement. This paper presents a possible optimization of an existing nuclear fusion device. The optimization process is carried out by a parallel algorithm specifically designed to work with large scale problems. While the focus of the paper is fusion, the approach used can be applied to any other large scale problem. We have run our experiments on an HPC cluster. The results show the validity of our approach and how complex scientific problems can benefit from the outcomes of this work.


Tuesday July 19, 2016 4:00pm - 4:30pm
Brickell

4:00pm

TECH: Containers in Research: Initial Experiences with Lightweight Infrastructure
Linux containers have garnered a considerable amount of interest in a very short amount of time. Docker, in par- ticular, has captured a lot of this momentum – and is of- ten viewed as the de-facto standard for lightweight software deployment. Containerized applications can be quickly deployed, providing a virtual software environment (as op- posed to a more traditional virtual machine) with little to no performance overhead. 
We believe Docker, and the modern trend toward containers and microservices it epitomizes, can provide a significant technological advantage for service deployment in an HPC environment. We present several use cases for containers, ranging from simple web application delivery to prototype compute cluster environments. Finally, we share our initial performance results, and our upcoming plans for container development at our site.


Tuesday July 19, 2016 4:00pm - 4:30pm
Sevilla InterContinental Miami

4:15pm

WDD: Orion: Discovery Environment for HPC Research and Bridging XSEDE Resources
We present a case study on how Georgia State University (GSU) has grown its active High Performance Computing (HPC) research community by 80% in 2015 over previous year, and how GSU is projected to double its active HPC research community for 2016 over 2015. In October 2015, GSU launched an institutional HPC resource, Orion, which provides batch and interactive compute environment. Currently, Orion supports both the traditional and non-traditional research communities on our campus as well as our affiliates from Qatar University, University of Toronto, and Georgia Tech. At GSU, Research Solutions’ HPC facilitators are responsible for facilitating the HPC research, which is done in a form of providing technical support in developing pipelines and automating job submission process for various applications researchers need to use for their research. This approach has resulted in nearly 80% growth in our active HPC users from 2014 to 2015, and currently we are tracking at doubling our active HPC user community in 2016. XSEDE remains a backbone of our ambitious goals, as we rely on XSEDE for providing us the necessary resources for select users whose research quickly exceeds our local infrastructure.


Tuesday July 19, 2016 4:15pm - 5:00pm
Trade

4:15pm

4:30pm

AD: Time Propagation of Partial Differential Equations Using the Short Iterative Lanczos Method and Finite-Element Discrete Variable Representation
The short iterative Lanczos method has been combined with the finite-element discrete variable representation to yield a powerful approach to solving the time-dependent Schroedinger equation. It has been applied to the interaction of short, intense laser radiation(attosecond pulses) to describe the single and double ionization of atoms and molecules, but the approach is not limited to this particular application. The algorithm will be described in some detail and how it been successfully ported to the Intel Phi coprocessors. While further experimentation is needed, the current results provide reasonable evidence that by suitably modifying the code to combine MPI, OpenMP, and compiler offload directives, one can achieve significant improvement in performance from these coprocessors for problems such as the above.


Tuesday July 19, 2016 4:30pm - 5:00pm
Chopin Ballroom

4:30pm

SW: Introducing a New Client/Server Framework for Big Data Analytics with the R Language
Historically, large scale computing and interactivity have been at odds. This is a particularly sore spot for data analytics applications, which are typically interactive in nature. To help address this problem, we introduce a new client/server framework for the R language. This framework allows the R programmer to remotely control anywhere from one to thousands of batch servers running as cooperating instances of R. And all of this is done from the user's local R session. Additionally, no specialized software environment is needed; the framework is a series of R packages, available from CRAN. The communication between client and server(s) is handled by the well-known ZeroMQ library. To handle computations, we use the established pbdR packages for large scale distributed computing. These packages utilize HPC standards like MPI and ScaLAPACK to handle complex, tightly-coupled computations on large datasets. In this paper, we outline the client/server architecture, discuss the pros and cons to this approach, and provide several example workflows which bring

interactivity to terabyte size computations.


Tuesday July 19, 2016 4:30pm - 5:00pm
Brickell

4:30pm

TECH: An Overview of the Implementation of CILogon at NICS
Authentication for HPC resources has always been a double edged issue. On one hand, HPC facilities would like users to login as easily as possible, but with the increase and complexity of system exploits, HPC centers would like to protect their systems to the highest degree possible, which often leads to complicated login mechanisms. While solutions like Two Factor authentication are optimal from a system administration view point, user buy in hasn't been as vociferous as one would hope. In this paper we discuss the implementation of an alternate solution, CILogon, at NICS. We start with a brief overview of CILogon and then delve into the implementation details. We discuss how we incorporated CILogon to enable users to use their campus credentials to login to the NICS user portal as well our compute resource Darter. We discuss the issues we faced during implementation and the strategies we implemented to overcome them.


Tuesday July 19, 2016 4:30pm - 5:00pm
Sevilla InterContinental Miami

5:15pm

BOF: High Performance Computing for Humanities, Arts, and Social Science
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.

Speakers

Tuesday July 19, 2016 5:15pm - 6:15pm
Sevilla InterContinental Miami

5:15pm

BOF: Persistent Community of Cyberinfrastructure Professionals: Challenges and Next Steps
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.

Moderators
Speakers
avatar for Dana Brunson

Dana Brunson

Asst. VP Research CI/Director, High Performance Computing Center, Oklahoma State University


Tuesday July 19, 2016 5:15pm - 6:15pm
Trade

5:15pm

BOF: Topics on Cloud and Virtualization in XSEDE
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 


Tuesday July 19, 2016 5:15pm - 6:15pm
Brickell

5:15pm

BOF: XSEDE, the Science Gateways Community Institute and You
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. 

Speakers
avatar for Suresh Marru

Suresh Marru

Member, Apache Software Foundation
Suresh Marru is a Member of the Apache Software Foundation and is the current PMC chair of the Apache Airavata project. He is a principal research systems architect at Indiana University. Suresh focuses on research topics at the intersection of distributed systems, application domain science; computational systems and has authored or co-authored over 75 peer-reviewed conference papers and journal articles in these areas. He gets his hands on... Read More →


Tuesday July 19, 2016 5:15pm - 6:15pm
Chopin Ballroom

5:15pm

7:00pm

Welcome Networking - Sponsored by Intel
Tuesday July 19, 2016 7:00pm - 9:00pm
Bayfront InterContinental Miami
 
Wednesday, July 20
 

7:00am

Breakfast
Wednesday July 20, 2016 7:00am - 8:00am
Mezzanine Mezzanine

7:00am

Registration
Wednesday July 20, 2016 7:00am - 4:30pm
Registration

8:30am

AD: A Parallel Evolutionary Algorithm for Subset Selection in Causal Inference Models
Science is concerned with identifying causal inferences. To move beyond simple observed relationships and associational inferences, researchers may employ randomized experimental designs to isolate a treatment effect, which then permits causal inferences. When experiments are not practical, a researcher is relegated to analyzing observational data. To make causal inferences from observational data, one must adjust the data so that they resemble data that might have emerged from an experiment. Traditionally, this has occurred through statistical models identified as matching methods. We claim that matching methods are unnecessarily constraining and propose, instead, that the goal is better achieved via a subset selection procedure that is able to identify statistically indistinguishable treatment and control groups. This reformulation to identifying optimal subsets leads to a model that is computationally complex. We develop an evolutionary algorithm that is more efficient and identifies empirically more optimal solutions than any other causal inference method. To gain greater efficiency, we also develop a scalable algorithm for a parallel computing environment by enlisting additional processors to search a greater range of the solution space and to aid other processors at particularly difficult peaks.


Wednesday July 20, 2016 8:30am - 9:00am
Chopin Ballroom

8:30am

SW: The XSEDE BLAST Gateway: Leveraging Campus Development for the XSEDE Gateway
This paper describes an XSEDE Extended Collaboration Support Service (ECSS) effort on scaling a campus developed online BLAST service (BLASTer) into an XSEDE gateway bridging the gap between genomic researchers and advanced computing and data environments like those found in the Extreme Science and Engineering Discovery Environment (XSEDE) network. Biologists and geneticists all over the world use the suite of Basic Local Alignment Search Tools (BLAST) developed by the National Center for Biotechnology Information (NCBI) throughout the full spectrum of genomic research. It has become one of the defacto bioinformatics applications used in all variety of computing environments. BLASTer allows researchers to achieve those tasks faster and without expert computing knowledge by converting BLAST jobs to a parallel model. It handles all of the details of computation submission, execution, and database access for users through an intuitive web-based interface provided by the unique features of the HUBzero gateway platform. This paper details the core development of BLASTer for campus computing resources at Purdue University, some of its successes among the user community, and the current efforts by an ECSS scientific gateways project from XSEDE to include data-intensive use of resources like Wrangler at the Texas Advanced Computing Center (TACC) within the XSEDE network. The lessons learned from this project will be used to bring other XSEDE computing resources to BLASTer in the future and other programs like BLASTer to XSEDE users.


Wednesday July 20, 2016 8:30am - 9:00am
Brickell

8:30am

TECH: Globus: Recent Enhancements and Future Plans
Globus offers a broad suite of research data management cappabilities to the research community as web-accessible services. The initial service, launched in 2010, focused on reliable, high-performance, secure data transfer; since thattime, Globus capabilities have been progressively enhancedin response to user demand. In 2015, secure data sharing and publication services were introduced. Other recent enhancements include support for secure HTTP data access, new storage system types (e.g., Amazon S3, HDFS, Ceph), endpoint search, and administrator management. A powerful new authentication and authorization platform service,Globus Auth, addresses identity, credential, and delegation management needs encountered in research environments.New REST APIs allow external and third-party services to leverage Globus data management, authentication, and authorization capabilities as a platform, for example when building research data portals. We describe these and other recent enhancements to Globus, review adoption trends (to date, 38,000 registered users have operated on more than 150PB and 25B les), and present future plans.


Wednesday July 20, 2016 8:30am - 9:00am
Sevilla InterContinental Miami

8:30am

WDD: The Advanced Cyberinfrastructure Research and Education Facilitators Virtual Residency: Toward a National Cyberinfrastructure Workforce
An Advanced Cyberinfrastructure Research and Education Facilitator (ACI-REF) works directly with researchers to advance the computing- and data-intensive aspects of their research, helping them to make effective use of Cyberinfrastructure (CI). The University of Oklahoma (OU) is leading a national "virtual residency" program to prepare ACI-REFs to provide CI facilitation to the diverse populations of Science, Technology, Engineering and Mathematics (STEM) researchers that they serve. Until recently, CI facilitators have had no education or training program; the Virtual Residency program addresses this national need by providing: (1) training, specifically (a) summer workshops and (b) third party training opportunity alerts; (2) a community of facilitators, enabled by (c) a biweekly conference call and (d) a mailing list.


Wednesday July 20, 2016 8:30am - 9:00am
Trade

9:00am

WDD: Access and Inclusion in XSEDE Training
Computing in science and engineering is now ubiquitous: digital technologies underpin, accelerate, and enable new, even transformational, research in all domains. Access to an array of integrated and well-supported high-end digital services is critical for the advancement of knowledge. Driven by community needs, XSEDE (the Extreme Science and Engineering Discovery Environment) substantially enhances the productivity of a growing community of scholars, researchers, and engineers through access to advanced digital services that support open research. 
An XSEDE strategic goal is to extend use of high-end digital services to new communities by preparing current and next generation of scholars, researchers, and engineers in the use of advanced digital technologies via training, education, and outreach. The mission of XSEDE’s Under-Represented Community Engagement (URCE) program is to raise awareness of the value of advanced digital research services and recruit users from new communities. In collaboration with XSEDE training and education programs, the URCE program works with the faculty and students that are non-traditional users of XSEDE resources and helps them in utilizing XSEDE's advanced digital research services and ecosystem. 
The focus of this work are individual researchers, research teams, faculty, staff, and students who have limited or no exposure. These are first time users. The institutions that the URCE program works with are small, minority, and resource limited; and the individuals are under-represented minorities and women. In order for first time users to be successful, they need training, practice, user support, extended collaborative support, and software tools and environments including gateways to allow them to rapidly join the community and become productive. 
Over the past four years, the URCE program has organized and facilitated training across the country at a variety of institutions ranging from small private Historically Black Colleges and Universities (HBCUs) such as Philander Smith to the University of Texas at El Paso which is a large public Hispanic Serving Institution and in collaboration with research intuitions that have significant diversity initiatives on their campuses. Every URCE training workshop has included extensive post workshop evaluation and the participants progress in engaging with XSEDE services is tracked so we can identify deepening engagement and persistence. 
This type of success has been achieved because training has evolved due to our reflection on the post workshop feedback and data. The practices that have been incorporated include providing the motivation for using these types of services, promoting the simplest access through gateways, careful tailoring of the content to the audience, and developing persistence after the event.

Speakers
avatar for Lorna Rivera

Lorna Rivera

Senior Research Specialist, I-STEM, University of Illinois at Urbana-Champaign


Wednesday July 20, 2016 9:00am - 9:20am
Trade

9:00am

AD: Three Dimensional Simulations of Fluid Flow and Heat Transfer with Spectral Element Method
This paper presents a computational approach for simulating three dimensional fluid flow and convective heat transfer involving viscous heating and Boussinesq approximation for buoyancy term. The algorithm was implemented with a modal spectral element method for accurate resolutions to coupled nonlinear partial differential equations. High order time integration schemes were used for time derivatives. Simulation results were analyzed and verified. They indicate that this approach is viable for investigating convective heat transfer subject to complex thermal and flow boundary conditions in three dimensional irregular domains.


Wednesday July 20, 2016 9:00am - 9:30am
Chopin Ballroom

9:00am

SW: TopoLens: Building A CyberGIS Community Data Service for Enhancing the Usability of High-resolution National Topographic Datasets
Geospatial data, also known as spatial data or geographic information, is data or information representing physical objects with an explicit geographic component on the surface or near-surface of the Earth. The increased volume and diversity of geospatial data have caused serious usability challenges to researchers in various scientific domains, which calls for a cyberGIS solution. To address these issues, this paper presents a cyberGIS community data service framework to facilitate big geospatial data access, processing, and sharing based on a hybrid supercomputer architecture. Through the collaboration between the CyberGIS Center at the University of Illinois at Urbana-Champaign (UIUC) and the U.S. Geological Survey (USGS), a community data service for accessing, customizing, and sharing digital elevation model (DEM) and its derived datasets from the 10m national elevation dataset, namely TopoLens, is developed to demonstrate the pipelined integration of big geospatial data sources, computation needed for customizing the original dataset for end user needs, and a highly usable online user environment. TopoLens provides online access to precomputed and on-demand computed high-resolution elevation data by leveraging the ROGER supercomputer. The need for building such services for GIScientists and the usability of this prototype service have been acknowledged in community evaluation.


Wednesday July 20, 2016 9:00am - 9:30am
Brickell

9:00am

TECH: Developing Applications with Networking Capabilities via End-to-End SDN (DANCES)
The Developing Applications with Networking Capabilities via End-to-End SDN (DANCES) project was a collaboration between The University of Tennessee’s National Institute for Computational Sciences (UT-NICS), Pittsburgh Supercomputing Center (PSC), Pennsylvania State University (Penn State), the National Center for Supercomputing Applications (NCSA), Texas Advanced Computing Center (TACC), Georgia Institute of Technology (Georgia Tech), the Extreme Science and Engineering Discovery Environment (XSEDE), and Internet2 to investigate and develop a capability to add network bandwidth scheduling capability via software-defined networking (SDN) programmability to selected cyberinfrastructure services and applications. DANCES, funded by the National Science Foundation’s Campus Cyberinfrastructure – Network Infrastructure and Engineering (CC-NIE) program award numbers 1341005, 1340953, and1340981, has investigated three vendor network devices in order to determine which implements the OpenFlow 1.3 standard with DANCES requirements of meters and per-port queueing in order to provide a network reservation and rate-limiting capability desired to implement the goals of DANCES. Of the devices tested the DANCES project determined that the Corsa DP6410 met the requirements of OpenFlow 1.3 especially the implementation of features of metering and per port queueing which allow complex quality of service configuration for network flows. After selection of the network device a test environment was setup between the University of Tennessee and PSC to simulate a supercomputer center compute and data transfer resource environment. This paper described the DANCES project, the DANCES OpenFlow 1.3 specification requirements, the determination and acquiring of a sufficient OpenFlow 1.3 network device, the provisioning of a test environment, the UT-NICS test plan and the exciting and successful results of the tests.


Wednesday July 20, 2016 9:00am - 9:30am
Sevilla InterContinental Miami

9:20am

WDD: Rescuing Lost History: Using Big Data to Recover Black Women’s Lived Experiences
This study employs latent Dirichlet allocation (LDA) algorithms and comparative text mining to search 800,000 periodicals in JSTOR (Journal Storage) and HathiTrust from 1746 to 2014 identify the types of conversations that emerge about Black women's shared experience over time and the resulting knowledge that developed. We used MALLET to interrogate various genres of text (poetry, science, psychology, sociology, African American Studies, policy, etc.). We also used comparative text mining (CTM) to explore latent themes across collections written in different time periods by analyzing the common and expert models. We used data visualization techniques, such as tree maps, to identify spikes in certain topics during various historical contexts such as slavery, reconstruction, Jim Crow, etc. We identified a subset of our corpus (20,000) comprised of known Black or Black women authors and compared patterns of words in the subset against the larger 8000,000 corpus. Preliminary findings indicate that when we pulled 300,000 volumes, about 80,000 (~25%) do not have subject metadata. This appears to suggest that if a researcher searched for volumes about Black women, they may not have access to a significant amount of data on the topic. When volumes are not tagged properly, researchers would have to know that it exists when they do their searches. The recovery nature of this project involves identifying these untagged volumes and making the corpus publicly available to librarians and others with copyright considerations.


Wednesday July 20, 2016 9:20am - 9:40am
Trade

9:30am

AD: Performance and Scalability Analysis for Parallel Reservoir Simulations on Three Supercomputer Architectures
In this work, we tested the performance and scalability on three supercomputers of different architectures including SDSC’s Comet, SciNet’s GPC and IBM’s Blue Gene/Q systems, through benchmarking parallel reservoir simulations. The Comet and GPC systems adopt a fat-tree network and they are connected with InfiniBand interconnects technology. The Blue Gene/Q uses a 5-dimensional toroidal network and it is connected with custom interconnects. In terms of supercomputer architectures, these systems represent two main interconnect families: fat-tree and torus. To demonstrate the application scalability for supercomputers with today’s diversified architectures, we benchmark a parallel black oil simulator that is extensively used in the petroleum industry. Our implementation for this simulator is coded in C and MPI, and it offers grids, data, linear solvers, preconditioners, distributed matrices and vectors and modeling modules. Load balancing is based on the Hilbert space-filling curve (HSFC) method. Krylov subspace and AMG solvers are implemented, including restarted GMRES, BiCGSTAB, and AMG solvers from Hypre. The results show that the Comet is the fastest supercomputer among tested systems and the Blue Gene/Q has the best parallel efficiency. The scalability analysis helps to identify the performance barriers for different supercomputer architectures. The study of testing the application performance serves to provide the insights for carrying out parallel reservoir simulations on large-scale computers of different architectures.


Wednesday July 20, 2016 9:30am - 10:00am
Chopin Ballroom

9:30am

SW: Anatomy of SEAGrid Science Gateway
The SEAGrid Science Gateway provides researchers and educators a unified access to computational resources in a seamless fashion. SEAGrid has evolved from Computational Chemistry Grid infrastructure and is celebrating 10 years of service to the community that initially provided computational chemistry tools. This scope has since broadened to encompass other areas of Science and Engineering. SEAGrid is built on the Apache Airavata science gateway framework. This paper describes the technical architecture and internal underpinnings of the SEAGrid Science Gateway.

Speakers
avatar for Suresh Marru

Suresh Marru

Member, Apache Software Foundation
Suresh Marru is a Member of the Apache Software Foundation and is the current PMC chair of the Apache Airavata project. He is a principal research systems architect at Indiana University. Suresh focuses on research topics at the intersection of distributed systems, application domain science; computational systems and has authored or co-authored over 75 peer-reviewed conference papers and journal articles in these areas. He gets his hands on... Read More →


Wednesday July 20, 2016 9:30am - 10:00am
Brickell

9:30am

TECH: BIC-LSU: Big Data Research Integration with Cyber-infrastructure for LSU
In recent years, big data analysis has been widely applied to many research fields including biology, physics, transportation, and material science. Even though the demands for big data migration and big data analysis are dramatically increasing in campus IT infrastructures, there are several technical challenges that need to be addressed. First of all, frequent big data transmission between storage systems in different research groups imposes heavy burdens on regular campus network. Second, the current campus IT infrastructure is not designed to fully utilize the hardware capacity for big data migration and analysis. Last but not the least, running big data applications on top of large-scale high-performance computing facilities is not straightforward, especially for researchers and engineers in non-IT disciplines.
We develop a campus IT infrastructure for big data migration and analysis, called BIC-LSU, which consists of a task-aware Clos OpenFlow network, high-performance cache storage servers, customized high-performance transfer applications, a light-weight control framework to manipulate existing big data storage systems and job scheduling systems, and a comprehensive social networking-enabled web portal. BIC-LSU achieves 40Gb/s disk-to-disk big data transmission, maintains short average transmission task completion time, enables the convergence of control on commonly deployed storage and job scheduling systems, and enhances easiness of big data analysis with a universal user-friendly interface. BIC-LSU software requires minimum dependencies and has high extensibility. Other research institutes can easily customize and deploy BIC-LSU as an augmented service on their existing IT infrastructures.


Wednesday July 20, 2016 9:30am - 10:00am
Sevilla InterContinental Miami

9:40am

WDD: Advanced Research Network Infrastructure Enables Research Opportunities in the DC Area

Abstract: This paper reports on the development of the Capital Area Advanced Research and Education Network (CAAREN), which provides an advanced research and education network infrastructure for the D.C. metro region. Working in partnership with the D.C. Office of the Chief Technology Officer’s program, DC-Net, the George Washington University Division of Information Technology (IT) developed CAAREN out of a need for advanced research infrastructure for the D.C. area, and a need for collaboration among D.C. area universities. CAAREN’s objective is to provide an advanced research network infrastructure, as well as outreach and services for K-12 schools, museums, libraries and similar organizations within the D.C. metro region. A number of initiatives have been completed or are underway to help advance research and education for current and future generations to advance scientific discovery through the use of this cyberinfrastructure.



Wednesday July 20, 2016 9:40am - 10:00am
Trade

10:00am

10:30am

AD: A Scalable High-performance Topographic Flow Direction Algorithm for Hydrological Information Analysis
Hydrological information analysis based on Digital Elevation Models (DEM) provide hydrological properties derived from high-resolution topographic data represented as elevation grid. Flow direction detection is one of the most computationally intensive functions. As the resolution of DEM becomes higher, the computational bottleneck of this function hinders the use of these DEM data in large-scale studies. As the computation of flow directions for the study extent needs global information, the parallelization involves iterative communications. This paper presents an efficient parallel flow direction detection algorithm that identifies spatial features (e.g., flats) that can or cannot be computed locally. An efficient sequential algorithm is then applied to resolve those local features, while communication is applied to compute non-local features. This strategy significantly reduces the number of iterations needed in the parallel algorithm. Experiments show that our algorithm outperformed the best existing parallel (i.e., the d8 algorithm in TauDEM) by two orders of magnitude. The parallel algorithm exhibited desirable scalability on Stampede and ROGER supercomputer.


Wednesday July 20, 2016 10:30am - 11:00am
Chopin Ballroom

10:30am

SW: From OpenACC to OpenMP 4: Toward Automatic Translation
For the past few years, OpenACC has been the primary directive-based API for programming accelerator devices like GPUs. OpenMP 4.0 is now a competitor in this space, with support from different vendors. In this paper, we describe an algorithm to convert (a subset of) OpenACC to OpenMP 4; we implemented this algorithm in a prototype tool and evaluated it by translating the EPCC Level 1 OpenACC benchmarks. We discuss some of the challenges in the conversion process and propose what parts of the process should be automated, what should be done manually by the programmer, and what future research and development is necessary in this area.


Wednesday July 20, 2016 10:30am - 11:00am
Brickell

10:30am

TECH: Not just HPC: XSEDE's Computing Resource Diversity

  • Panel featuring XSEDE’s newest resource providers and systems

  • Sergiu Sanielevici to moderate


Wednesday July 20, 2016 10:30am - 12:00pm
Sevilla InterContinental Miami

10:30am

WDD: Preparing Tomorrow¹s Cyberinfrastructure Leaders Today
This panel session will gather community recommendations on strategies for preparing the workforce to advance the capabilities, capacities and utilization of cyberinfrastructure with an emphasis on Computational and Data-enabled Science and Engineering (CDS&E), Data Science and related areas. The panel members will pose challenges and controversial ideas to stimulate audience participation to identify methods and approaches the community should pursue in support of advancing research, discovery, and scholarly studies through the usage of computational and data-enabled tools, resources, and methods. The XSEDE16 audience will be challenged to contribute their suggestions both during and after the session via social media and discussion forums. The audience suggestions will be incorporated into a report that will be publicly disseminated by the middle of 2017.

 

There are many reports that have documented the need to prepare a diverse workforce able to advance research, discovery, scholarly studies and economic competitiveness via CI. The White House issued an Executive Order establishing the National Strategic Computing Initiative (NSCI) to coordinate research, development, and deployment strategies, to draw on the strengths of departments and agencies to move the US federal government into a position that sharpens, develops, and streamlines a wide range of new 21st century applications. The NSCI goals include (a) advancing core technologies to solve difficult computational problems and (b) fostering increased use of the new capabilities in the public and private sectors. Workforce development is a key element of this initiative.

 

XSEDE and the NSF funded Blue Waters project, along with other projects and organizations are working to advance workforce development. They place an emphasis on:

* increasing formal and informal education and training opportunities in Cyberinfrastructure (CI), Computational and Data-enabled Science and Engineering (CDS&E), Data Science and related capabilities;

* expanding the workforce in these areas by fostering the identification, recruitment and cultivation of CI, CDS&E and Data Science practitioners, and of faculty who educate these practitioners;

* developing approaches to increase the diversity of the CI, CDS&E and Data Science workforce.

 

The goal of the panel discussions is to identify recommendations that will help advance discovery and scholarly studies via the applications of computational and data-enabled tools, resources, and methods.

 

This panel is intended to spark dialogue among the XSEDE16 participants on strategies that have potential to enhance the preparation of the workforce. The panel members will have 10 minutes each to present diverse viewpoints from a variety of community perspectives.

Following the panel presentations, a series of challenging questions will be posed to the audience to promote discussions to identify possible solutions. The moderator will foster discussions among the audience and will be proactive in ensuring that the audience is as engaged as the panel in the discussions. The moderator will guide the group towards making recommendations for enhancing workforce development.

 

The audience will be encouraged to provide oral comments and to provide written comments using polling software that everyone will be able to observe in real time, thus giving all attendees a voice in the discussion and a chance to explore topics not previously raised by the panel. The audience members will also be encouraged to submit written suggestions after the conference.

 

The panel organizers will provide a forum for open discussion and contributions of ideas during and after the Conference. The organizers will post drafts of recommendations throughout the development process, and the final set of recommendations will be posted by the middle of 2017.

Emcee - Henry Neeman, University of Oklahoma

Panel Members:

* Linda Akli, Southeastern Universities Research Association (SURA) will represent the needs of the Diversity Forum

* John Towns, NCSA, University of Illinois will provide a CIO’s perspective

* John Mosher, Oklahoma Innovation Institute will provide a Champion’s perspective

* Thomas Hauser, University of Colorado, Boulder

* Nathan Weeks, USDA-ARS Corn Insects and Crop Genetics Research Unit, Iowa State University

Moderators
Wednesday July 20, 2016 10:30am - 12:00pm
Trade

11:00am

AD: Implementation of Simple XSEDE-Like Clusters: Science Enabled and Lessons Learned
The Extreme Science and Engineering Discovery Environment (XSEDE) has created a suite of software that is collectively known as the XSEDE-Compatible Basic Cluster (XCBC). It is designed to enable smaller, resource-constrained research groups or universities to quickly and easily implement a computing environment similar to XSEDE computing resources.The XCBC acts as both an enabler of local research and as a springboard for seamlessly moving researchers onto XSEDE resources when the time comes to scale up their efforts to larger hardware. The XCBC system consists of the Rocks Cluster Manager, developed at the San Diego Supercomputer Center for use on Gordon and Comet, and an XSEDE-specific “Rocks Roll'', containing a selection of libraries, compilers, and scientific software curated by the Campus Bridging (CB) group. The versions of software included in the roll are kept up to date with those implemented on XSEDE resources.
The Campus Bridging team has helped several universities implement the XCBC, and finds the design to be extremelyuseful for resource-limited (in time, administrator knowledge, ormoney) research groups or institutions. Here, we detail our recentexperiences in implementing the XCBC design at university campuses across the country. These XCBC implementations were carried out with Campus Bridging staff traveling on-site to the partner institutions to directly assist with the cluster build. Results from a site visits at partner institutions show how the Campus Bridging team helped accelerate cluster implementation and research by providing expertise and hands-on assistance during cluster building. We also describe how, following a visit from Campus Bridging staff, the XCBC has accelerated research and discovery at our partner institutions.


Wednesday July 20, 2016 11:00am - 11:30am
Chopin Ballroom

11:00am

SW: Open OnDemand – Transforming Computational Science Through Omnidisciplinary Software Cyberinfrastructure
The Open OnDemand Project is an open-source software project, based on the proven OSC OnDemand platform, to allow HPC centers to install and deploy advanced web and graphical interfaces for their users. The Open OnDemand team is completing the first year of the project and releasing its first version this summer. In this paper, we describe the user experience and design of Open OnDemand and discuss next steps for the open source project.


Wednesday July 20, 2016 11:00am - 11:30am
Brickell

11:30am

AD: Using High Performance Computing To Model Cellular Embryogenesis
C. Elegans is a primitive multicellular organism (worm) that shares many important biological characteristics that arise as complications within human beings. It begins as a single cell and then undergoes a complex embryogenesis to form a complete animal. Using experimental data, the early stages of life of the cells are simulated by computers. The goal of this project is to use this simulation to compare the embryogenesis stage of C. Elegans cells with that of human cells. Since the simulation involves the manipulation of many files and large amounts of data, the power provided by supercomputers and parallel programming is required. The serial agent based simulation program NetLogo completed the simulation in roughly six minutes. By comparison, using the parallel agent based simulation toolkit RepastHPC, the simulation completed in under a minute when executing on four processors of a small cluster. Unlike NetLogo, RepastHPC does not contain a visual element. Therefore, a visualization program, VisIt, was used to graphically show the data produced by the RepastHPC simulation.


Wednesday July 20, 2016 11:30am - 12:00pm
Chopin Ballroom

11:30am

SW: Extended Batch Sessions and Three-Phase Debugging: Using DMTCP to Enhance the Batch Environment
Batch environments are notoriously unfriendly because it's not easy to interactively diagnose the health of a job. A job may be terminated without warning when it reaches the end of an allotted runtime slot, or it may terminate even sooner due to an unsuspected bug that occurs only at large scale.
Two strategies are proposed that take advantage of DMTCP for system-level checkpointing. First, we describe how to easily implement extended batch sessions that overcome the typical limitation of 24 hours maximum for a single batch job on large HPC resources. This removes the necessity for the application-specificcheckpointing found in many long-running codes. Second, we describe a three-phase debugging strategy that permits one to interactively debug long-running MPI applications that were developed for non-interactive batch environments.


Wednesday July 20, 2016 11:30am - 12:00pm
Brickell

12:00pm

Lunch - Sponsored by HPE
Wednesday July 20, 2016 12:00pm - 1:00pm
Mezzanine Mezzanine

12:00pm

Student and Mentor Lunch
By invitation only

Wednesday July 20, 2016 12:00pm - 1:00pm
Bayfront A

12:00pm

XDMoD Advisory Committee Meeting
Attendance by invitation only.

Wednesday July 20, 2016 12:00pm - 1:00pm
Windsor InterContinental Miami

1:30pm

Plenary Session - DR. HELEN TURNER 'A'ohe pau ka 'ike i ka hālau ho'okahi: education at the interface of science, culture and privilege in Hawai'i

Pacific islands offer the world stunning biodiversity, millennia-old models for sustainability, and uniquely rich indigenous cultures. These ‘paradoxical paradises’ are also globally-relevant sentinel locations for the ravages of climate change, food insecurity, health inequity, wealth gaps, migration and erosion of indigenous culture. Science and technology offer important components of the solutions to these problems, particularly as the era of ‘big data’ arrives. However, data science has the potential to become the latest in a series of colonizing Western scientific paradigms from which Pacific indigenous peoples are largely disenfranchised. Tensions between science and culture are an emerging threat to health, sustainability and prosperity in the Pacific. This presentation discusses innovative data science research projects and educational approaches that embody principles of democratization (an inclusive STEM pipeline that transcends barriers of privilege),  decolonization (inculturation of indigenous knowledge within a Western scientific paradigm), and (re)-discovery (export of Pacific-based models to address global challenges). Theolelo no’eau of the title tells us  that ‘not all knowledge is learned in the same school’. A discussion will be offered of gaps in the Pacific educational ecosystem for science and technology, and the necessary fusion of science and culture in STEM educational approaches.


Speakers
DH

Dr. Helen Turner

Dr. Helen Turner is Chaminade University's Dean of Natural Sciences and a tenured Professor of Biology. Dr. Helen Turner, a leading STEM advocate, has agreed to give a plenary presentation at XSEDE16 in Miami. Her talk title is: " 'A'ohe pau ka 'ike i ka hālau ho'okahi: education at the interface of science, culture and privilege in Hawai'i." | | Turner resides as the Dean of Natural Sciences and is a tenured Professor of Biology at Chaminade... Read More →


Wednesday July 20, 2016 1:30pm - 3:00pm
Grand Ballroom InterContinental Miami

3:00pm

3:30pm

AD: Tools for studying populations and timeseries of neuroanatomy enabled though GPU acceleration in the Computational Anatomy Gateway
The Computational Anatomy Gateway is a software as a service tool for medical imaging researchers to quantify changes in anatomical structures over time, and through the progression of disease. GPU acceleration on the Stampede cluster has enabled the development of new tools, combining advantages of grid based and particle based methods for describing fluid flows, and scaling up analysis from single scans to populations and time series. We describe algorithms for estimating average anatomies, and for quantifying atrophy rate over time. We report code performance on different sized datasets, revealing that the number vertices in a triangulated surface presents a bottleneck to our computation. We show results on an example dataset, quantifying atrophy in the entorhinal cortex, a medial temporal lobe brain region whose structure is sensitive changes in early Alzheimer's disease.


Wednesday July 20, 2016 3:30pm - 4:00pm
Chopin Ballroom

3:30pm

SW: Case Study: Microservice Evolution and Software Lifecycle of the XSEDE User Portal API
The XSEDE User Portal (XUP) is a web interface providing a set of user specific XSEDE services and documentation to a diverse audience. The XUP architecture started out depending on monolithic services provided by large Java libraries, but continues to evolve to use an application programming interface (API) powered by a set of microservices. The goal is to have the XUP API provide development and deployment environments that are agile, sustainable, and capable of handling feature changes. In making this transition, we have developed guidelines for API services that balance complexity and reuse needs with flexibility requirements. In doing so, we have also created our own set of best practices on how to convert to using microservices. In this paper we will use the XSEDE User Portal API development as a case study to explain our rationale, approach, and experiences in working with microservices in a real production environment to provide better and more reliable science services for end users.


Wednesday July 20, 2016 3:30pm - 4:00pm
Brickell

3:30pm

TECH: A Quantitative Analysis of Node Sharing on HPC Clusters Using XDMoD Application Kernels
In this investigation, we study how application performance is affected when jobs are permitted to share compute nodes. A series of application kernels consisting of a diverse set of benchmark calculations were run in both exclusive and node-sharing modes on the Center for Computational Research’s high-performance computing (HPC) cluster. Very little increase in runtime was observed due to job contention among application kernel jobs run on shared nodes. The small differences in runtime were quantitatively modeled in order to characterize the resource contention and attempt to determine the circumstances under which it would or would not be important. A machine learning regression model applied to the runtime data successfully fitted the small differences between the exclusive and shared node runtime data; it also provided insight into the contention for node resources that occurs when jobs are allowed to share nodes. Analysis of a representative job mix shows that runtime of shared jobs is affected primarily by the memory subsystem, in particular by the reduction in the effective cache size due to sharing; this leads to higher utilization of DRAM. Insights such as these are crucial when formulating policies proposing node sharing as a mechanism for improving HPC utilization.


Wednesday July 20, 2016 3:30pm - 4:00pm
Sevilla InterContinental Miami

3:30pm

VIS: Visualization Showcase Panel I
The panelists' Scientific Visualization Showcase submissions will be shown with each panelist providing insights into the process of creating cutting edge outreach visualizations.  The remainder of the session will be an open floor for discussion giving audience members the opportunity to engage panelists.

Visualization of Geodynamo Simulations

Panelist: Amit Chourasia

Earth’s magnetic field undergoes striking variations in direction and strength on a vast spectrum of time scales. Complex motions of the liquid iron core maintain the magnetic field, but the inner workings of this so-called dynamo process are obscured from direct observation and pose significant challenges for theoretical and computational modeling. This study aims to simulate the dynamo and determine which parameters can be associated with common features that are observed in the incomplete geological record of the magnetic field. The simulation produces an output comprised of magnetic field, the fluid flow, and temperature in the Earth’s core. Visualization results based on the output data are compared with observations projected down to the core surface, and to link those features with model behavior deep within the core. The visualization aspect of this study is enabling the scientists to identify interesting physical phenomena in the models that may be related to observation, including fluid up and down welling throughout the liquid core.

Insights into Alzheimer's Disease: Molecular Dynamics (MD) Simulations of Peptide-Membrane Interactions

Panelist: Ayat Mohammed

High performance computing (HPC) is essential in order to perform detailed MD simulations that allow for mechanistic insight into many diseases. Alzheimer’s disease (AD) pathology is primarily caused by the Aβ(42) peptide. MD simulations of a toxic (human Aβ(42) ) and non-toxic (rat Aβ(42) ) were performed in physiologically-relevant membrane environment conditions (310 K, 150 mM NaCl, pH 7) to assess differences in toxicity to membranes relevant to AD. The simulation results were processed with open tools and the results rendered with a raytracer. This paper describes the background science and the visualization techniques used to produce the accompanying video and compare the mechanisms of amyloid activity.

Interactive high quality visualization of long track EF5 Tornado with NVIDIA IndeX

Panelist: Mahendra Roopa

It is planned to show a 1+ TB of time-varying simulation data of an EF5 tornado within NVIDIA IndeX at interavtive frame rates. NVIDIA IndeX is an SDK that leverages GPU clusters for scalable, real-time, visualization and computing of multi-valued volumetric data together with embedded geometry data. See the following video: 
https://drive.google.com/file/d/0B8v1f5iVVCWpX3NmVzJSandPYVk/view?usp=sharing 
Different attributes of the tornado are shown within NVIDIA IndeX. 

MPAS-Ocean, Accelerated Climate Model for Energy

Panelist: Greg Abram

Climate change research relies on models to better understand and predict the complex, interdependant processes that affect the atmosphere, ocean, and land. These models are computationally intensive and produce terabytes to petabytes of data. Visualization and analysis is increasingly difficult, yet is critical to gain scientific insights from large simulations. The recently-developed Model for Prediction Across Scales-Ocean (MPAS-Ocean) is designed to investigate climate change at global high-resolution (5 to 10 km gridcells) on high performance computing platforms. In the accompanying video, we use state-of-the-art visualization techniques to explore the physical processes in the ocean relevant to climate change. These include heat transport, turbulence and eddies, weakening of the meridional overturning circulation, and interaction between a warming ocean and Antarctic ice shelves. The project exemplifies the benefits of tight collaboration among scientists, artists, computer scientists, and visualization specialists. 

An Extreme-Scale Implicit Solver for Complex PDEs: Highly Heterogeneous Flow in Earth's Mantle

Panelist: Greg Abram

This visualization shows the result of the Gordon Bell Award-winning simulation of mantle convection done by scientists from the University of Texas, IBM and Cal Tech. The flow is illustrated by the advection of particles positioned hear one face of the Marianas Trench, showing the cyclic flow down, eastward, up and westward. 

Potential Connectivity in the Coral Triangle

Panelist: Scott Pearse

Rising ocean temperatures have given rise to coral bleaching events at higher rates than have been seen in observed history. Researchers at the National Center for Atmospheric Research are studying how effectively coral reef ecosystems can repopulate each other after bleaching events through a metric called Potential Connectivity. In this visualization, we observe a state of the art flow simulation called CT-ROMS. This simulation replicates the nature of the Coral Triangle, recognized as the world center for marine biodiversity.

Video can be found here:http://www.vis.ucar.edu/~pearse/fullSequence_5.mp4 


Wednesday July 20, 2016 3:30pm - 5:30pm
Trade

4:00pm

AD: Delayed Update Algorithms for Quantum Monte Carlo Simulation on GPU
QMCPACK is open source scientific software designed to perform Quantum Monte Carlo simulation, a first-principles method for describing many-fermion systems. The evaluation of each Monte Carlo move requires finding the determinant of a dense matrix of wave functions. This calculation forms a key computational kernel in QMCPACK. After each accepted event, the wave function matrix undergoes a rank-one update to represent a single particle move within the system. The Sherman-Morrison formula is used to update the matrix inverse. Occasionally, the explicit inverse must be recomputed to maintain numerical stability. An alternate approach to this kernel utilizes QR factorization to maintain stability without re-factorization.

 

Algorithms based on a novel delayed update scheme are explored in this effort. This strategy involves calculating probabilities for multiple successive Monte Carlo moves and delaying their application to the matrix of wave functions until an event is denied or a predetermined limit of acceptances is reached. Updates grouped in this manner are then applied to the matrix en bloc to achieve enhanced computational intensity.

 

GPU-accelerated delayed update algorithms are tested and profiled for both Sherman-Morrison and QR based probability evaluation kernels. Results are evaluated against existing methods for numerical stability and efficiency; emphasis is placed on large systems, where acceleration is critical.


Wednesday July 20, 2016 4:00pm - 4:30pm
Chopin Ballroom

4:00pm

SW/VIS: User, data, and job submission patterns for a highly accessed science gateway
The CIPRES Science Gateway (CSG) is a public resource created to provide access to community phylogenetics codes on high performance computing resources. The CSG has been in operation since 2009, and has a large and growing user base. As a popular resource, the CSG provides an opportunity to study user behavior and job submissions in a Gateway environment. Here we examine CSG user and data turnover, jobs submissions success rates, and causes for job failures. The results of our investigation provide a better understanding of the populations that use the CSG, and point to areas where improvements can be made in meeting user needs and using resources more efficiently.


Wednesday July 20, 2016 4:00pm - 4:30pm
Brickell

4:00pm

TECH: Libraries Functions Tracking with XALT
XALT is a tracking tool that collects accurate, detailed, and continuous job-level and link-time data. XALT stores that data in a database and ensures that all the data collection is transparent to the users. XALT tracks libraries and object files linked by the application. A recent feature improvement in XALT allows it to also tracks external subroutines and functions called by an application. This paper describes this function-tracking implementation in XALT and showcases the kind of data and analysis that becomes available from this new feature. A recently developed web-based interface to XALT database is also described, allowing center's staffs to more easily understand software usage on their compute resources.


Wednesday July 20, 2016 4:00pm - 4:30pm
Sevilla InterContinental Miami

4:00pm

4:30pm

AD: Efficient Primitives for Standard Tensor Linear Algebra
This paper presents the design and implementation of low-levellibrary to compute general sums and products over multi-dimensional arrays (tensors). Using only 3 low-level functions, the API at once generalizes core BLAS1-3 as well as eliminates the need for most tensor transpositions. Despite their relatively low operation count, we show that these transposition steps can become performance limiting in typical use cases for BLAS on tensors. The execution of the present API achieves peak performance on the same order of magnitude (teraflops) as for vendor-optimized GEMM by utilizing a code generator to output CUDA source code for all computational kernels. The outline for these kernels is a multi-dimensional generalization of the MAGMA BLAS matrix multiplication on GPUs. Separate transpositions steps can be skipped because every kernel allows arbitrary multi-dimensional transpositions of the arguments. The library, including its methodology and programming techniques, are made available in SLACK. Future improvements to the library include a high-level interface to translate directly from a \LaTeX{}-like equation syntax to a data-parallel computation.

Speakers

Wednesday July 20, 2016 4:30pm - 5:00pm
Chopin Ballroom

4:30pm

SW: Understanding the Evolving Cyberinfrastructure Needs of the Neuroscience Community
In this paper, we first present a brief summary of the Neuroscience Gateway (NSG) which has been in operation since 2013. NSG is providing computational neuroscientists access to Extreme Science and Engineering Discovery Environment (XSEDE) high performance computing (HPC) resources. As a part of running the NSG we have interacted closely with the neuroscience community. This has given us the opportunity to receive input and feedback from the neuroscience researchers regarding their cyberinfrastructure needs. This is now more important given the context of the BRAIN (Brain Research through Advancing Innovative Neurotechnologies) Initiative which is a national initiative announced in 2013. Based on this interaction with the neuroscience community and the input we have received for the last three years, we analyze the comprehensive cyberinfrastructure needs of the neuroscience community in the second part of the paper.


Wednesday July 20, 2016 4:30pm - 5:00pm
Brickell

4:30pm

TECH: A web interface for XALT log data analysis
XALT is a job-monitoring tool to collect accurate, detailed, and continuous job level and link-time data on all MPI jobs running on the computing cluster. Due to its usefulness and complementariness to existing logs and databases, XALT has been deployed on Stampede at Texas Advanced Computing Center and other high performance computing resources around the world. The data collected by XALT can be extremely valuable to help resource providers understanding resources usages and identify patterns and insights for future improvements. However, the volume of data collected by XALT grows quickly over time on large system and presents challenges for access and analysis. In this paper, we describe development of a prototype tool for analyze and visualize XALT data. The application utilizes Spark for processing the large volume of log data and Shiny for visualizing the results over the web. The application provides an easy to use interface for users to conveniently share and communicate executable usage and patterns without prerequisite knowledge on big data technology.


Wednesday July 20, 2016 4:30pm - 5:00pm
Sevilla InterContinental Miami

5:15pm

BOF: Future of XSEDE User Portal Services
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?


Wednesday July 20, 2016 5:15pm - 6:15pm
Chopin Ballroom

5:15pm

BOF: Understanding User-Level Activity on Today's Supercomputers with XALT
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.


Wednesday July 20, 2016 5:15pm - 6:15pm
Sevilla InterContinental Miami

5:15pm

BOF: XSEDE Resource Allocation Service (XRAS)
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. 

Speakers
avatar for David Hart

David Hart

User Services Section Manager, National Center for Atmospheric Research


Wednesday July 20, 2016 5:15pm - 6:15pm
Brickell

6:15pm

Speed Networking
Students! Come meet our great XSEDE16 sponsors one-on-one, and share your enthusiasm for advanced computing, visualization, data analysis and research!

We will do a round robin-style event where each of the sponsors will be sitting at a table, and you’ll move around to meet them in 2-minute rounds. Don’t forget to bring your resume and your “personal elevator pitch” – we want you to make a good impression!

Participating Sponsors include: Intel, Dell, Hewlett Packard Enterprise, Cray, DataDirect Networks, NVIDIA, Aeon Computing, Allinea Software, Omnibond, San Diego Supercomputer Center, Internet2, D-Wave, Indiana University and iRODS (RENCI).

There will be 2 time slots for Speed Networking – 6:15pm and 7:15pm. Snacks and refreshments will be served.

To sign up, send an email to mfratkin@tacc.utexas.edu with “XSEDE16 STUDENT” in the subject line, and specify your preferred time. We will do our best to accommodate everyone.

Wednesday July 20, 2016 6:15pm - 7:15pm
Bayfront A

6:30pm

ECSS Training
Co-located workshop. Attendance by invitation only.

Wednesday July 20, 2016 6:30pm - 8:30pm
Chopin Ballroom

7:15pm

Speed Networking
Students! Come meet our great XSEDE16 sponsors one-on-one, and share your enthusiasm for advanced computing, visualization, data analysis and research!

We will do a round robin-style event where each of the sponsors will be sitting at a table, and you’ll move around to meet them in 2-minute rounds. Don’t forget to bring your resume and your “personal elevator pitch” – we want you to make a good impression!

Participating Sponsors include: Intel, Dell, Hewlett Packard Enterprise, Cray, DataDirect Networks, NVIDIA, Aeon Computing, Allinea Software, Omnibond, San Diego Supercomputer Center, Internet2, D-Wave, Indiana University and iRODS (RENCI).

There will be 2 time slots for Speed Networking – 6:15pm and 7:15pm. Snacks and refreshments will be served.

To sign up, send an email to mfratkin@tacc.utexas.edu with “XSEDE16 STUDENT” in the subject line, and specify your preferred time. We will do our best to accommodate everyone.

Wednesday July 20, 2016 7:15pm - 8:15pm
Bayfront A
 
Thursday, July 21
 

7:00am

Breakfast
Thursday July 21, 2016 7:00am - 8:00am
Mezzanine Mezzanine

8:00am

Plenary Champion Fellow Lightning Talks
Champion Fellow Speakers: Kevin Abbey (Rutgers University), Erin Hodgess (University of Houston Downtown), Don McLaughlin (West Virginia University),Nitin Sukhija (Mississippi State University), Craig Tanis (University of Tennessee Chattanooga).

Fellows will present their final report of their year-long ECSS project collaboration.

Thursday July 21, 2016 8:00am - 8:45am
Grand Ballroom InterContinental Miami

8:45am

Plenary Champion Panel
"Campus Engagement: Helping You with Resources from Local to International"

Panel Participants: XSEDE Campus Champions
Panel Moderator: Dana Brunson, Oklahoma State University

As the Campus Champions program has matured and grown, the Champion mission has rapidly expanded beyond the originally conceived purpose. Champions now focus on finding the best solution for their constituents, at any level, including workgroup, institution, state, region, domain, national and even international. In addition, the impact of the Champions now includes sharing of Cyberinfrastructure challenges and solutions, leading to professional development that is improving research and education outcomes.
In this panel, we will discuss the emerging mandate of the XSEDE Campus Engagement program, especially but not only the Champions, and how this transformation will affect computing- and data-intensive research and education nationwide.

Thursday July 21, 2016 8:45am - 10:00am
Grand Ballroom InterContinental Miami

10:00am

Morning Break - Sponsored by Omnibond
Thursday July 21, 2016 10:00am - 10:30am
Biscayne Ballroom

10:30am

AD: Computational Considerations in Transcriptome Assemblies and Their Evaluation, using High Quality Human RNA-Seq Data
It is crucial to understand the performance of transcriptome assemblies to improve current practices. Investigating the factors that affect a transcriptome assembly is very important and is the primary goal of our project. To that end, we designed a multi-step pipeline consisting of variety of pre-processing and quality control steps. XSEDE allocations enabled us to achieve the computational demands of the project. The high memory Blacklight and Greenfield systems at Pittsburgh Supercomputing Center were essential to accomplish multiple steps of this project. This paper presents the computational aspects of our comprehensive transcriptome assembly and validation study.


Thursday July 21, 2016 10:30am - 11:00am
Chopin Ballroom

10:30am

AD: Towards a Methodology for Cross-Accelerator Performance Profiling
The computing requirements of scientific applications have influenced processor design, and have motivated the introduction and use of accelerator architectures for high performance computing (HPC). Consequently, it is now common for the compute nodes of HPC clusters to be comprised of multiple processing elements, including accelerators. Although execution time can be used to compare the performance of different processing elements, there exists no standard way to analyze application performance across processing elements with very different architectural designs and, thus, understand why one outperforms another. Without this knowledge, a developer is handicapped when attempting to effectively tune application performance as is a hardware designer when trying to understand how best to improve the design of processing elements. In this paper, we use the LULESH 1.0 proxy application to compare and analyze the performance of three different accelerators: the Intel Xeon Phi and the NVIDIA Kepler and Fermi GPUs. Our study shows that LULESH 1.0 exhibits similar runtime behavior across the three accelerators, but runs up to 7x faster on the Kepler. Despite the significant architectural differences between the Xeon Phi and the GPUs, and the differences in the metrics used to characterize the performance of these architectures, we were able to quantify why the Kepler outperforms both the Fermi and the Xeon Phi. To do this, we compared their achieved instructions per cycle and vectorization efficiency, as well as their memory behavior and power and energy consumption.


Thursday July 21, 2016 10:30am - 11:00am
Sevilla InterContinental Miami

10:30am

SW: SeedMe: A scientific data sharing and collaboration platform.
Rapid secure data sharing and private online discussion are requirements for coordinating today’s distributed science teams using High Performance Computing (HPC), visualization, and complex workflows. Modern HPC infrastructures do a good job of enabling fast computation, but the data produced remains within a site’s storage and network environment tuned for performance rather than broad easy access. To share data and visualizations among distributed collaborators, manual efforts are required to move data out of HPC environments, stage data locally, bundle data with metadata and descriptions, manage versions, build animations, encode videos, and finally post it all online somewhere for secure access and discussion among project colleagues. While some of these tasks can be scripted, the effort remains cumbersome, time-consuming, and error prone. A more streamlined approach is needed.
In this paper we describe SeedMe – the Stream Encode Explore and Disseminate My Experiments platform for web-based scientific data sharing and discussion. SeedMe provides streamlined and application-controlled automatic data movement from HPC and desktop environments, metadata management, data descriptions, video encoding, secure data sharing, threaded discussion, and, optionally, public access for education and outreach.


Thursday July 21, 2016 10:30am - 11:00am
Brickell

10:30am

VIS: Visualization Showcase Panel II
The panelists' Visualization Showcase submissions will be shown with each panelist providing insights into the process of creating cutting edge outreach visualizations.  The remainder of the session will be an open floor for discussion giving audience members the opportunity to engage panelists.

Hurricane Odile HWRF Simulation

Panelist: Matt Rehme

When Hurricane Odile made landfall on the Baja California Peninsula in September 2014 as a category 3 storm, it inflicted widespread damage, flooding and power outages in Mexico and the Southwestern United States. Researchers at the National Center for Atmospheric Research (NCAR) in Boulder, CO, created this simulation using the Hurricane Weather Research Forecast, an advanced hurricane prediction system developed by the National Oceanic and Atmospheric Administration (NOAA).

Using advanced computing and storage resources at NCAR and NOAA, the simulation combines dropsonde data, conventional observations and satellite data into a 3-D grid with 3KM horizontal resolution and 61 vertical levels providing a highly detailed glimpse into the processes and evolution of this hurricane over a 6-day period. The system, now deployed for real-time storm tracking, fills gaps in previous weather simulations to provide a more accurate assessment of intensity, structure and expected rainfall for severe storms.

Viewing Link (YouTube): https://youtu.be/NYWgCuaeXrw

Download Link (DropBox): https://dl.dropboxusercontent.com/u/97834010/odile1920x1080_01.mp4

El Niño: 1997 Compared with 2015

Panelist: Matt Rehme

This visualization was created using advanced computing resources at NCAR, including the NCAR Command Language (NCL), a programming language designed specifically for scientific data processing and visualization; and Geyser, a large-memory node system used for large-scale analysis and post-processing tasks, operated by NCAR’s Computational & Information Systems laboratory. The animation depicts a comparison of changes in sea surface temperature (SST) anomalies between the major El Niño event of 1997-98 and the El Niño event which emerged in 2015.

The data visualized are from the NOAA 1/4° daily Optimum Interpolation Sea Surface Temperature (OISST) database. These data sets are combined from sources such as satellites, buoy networks, and ships. They are named for the key satellite sensor used: in this case, the Advanced Very High Resolution Radiometer (AVHRR).

Viewing link: https://www.youtube.com/watch?v=whsQbIwWjBo

Download Link: https://www.dropbox.com/s/09yklospylcj4g9/elnino1997v2015_to1231_titles.mov?dl0 


Visualization of Storm Simulations for Data Mining Tornadogenesis Precursors

Panelist: Greg Foss

This video is a sample of animations resulting from an in-progress XSEDE ECSS project investigating the use of 3D visualization techniques as a possible data mining method exploring large (approximately 5TB) and complex supercell thunderstorm simulation data. The goal is finding factors (referred to as objects) that distinguish tornadogenesis (tornado formation) from "tornado failure" (failure of a storm containing strong low-level rotation to produce a tornado) in a series of simulated storms.The animations will be used to help develop the object definitions for the data mining, to ensure automatically extracted objects match subjectively (visually) identified ones,and to develop definitions for new objects. This submission's material results from the project's first dataset and visualizes hook echoes, BWERs, updrafts, cold pools, vertical pressure perturbation gradients, and helicity/vorticity properties. In addition to consultants from TACC's visualization staff, XSEDE resources include HPC systems Maverick (TACC), and Stampede (TACC)for the visualizations, and Darter (NICS) for the storm simulations.

Visualization of simulated white dwarf collisions as a primary channel for type Ia supernovae

Panelist: David Bock

Type Ia supernovae are an important and significant class of supernovae. While it is known that these events result from thermonuclear explosions of white dwarfs, there is currently no satisfactory scenario to achieve such explosions. Direct collisions of white dwarfs are simulated to study the possibility that the resulting explosions are the main source of type Ia supernovae. An adaptive mesh refinement grid simulates the varying levels of detail and a custom volume renderer is used to visualize density, temperature, and the resulting nickel production during the collision. 

Link: http://lantern.ncsa.illinois.edu/~dbock/Vis/XSEDE/XSEDE16/Bock_Kushnir.mov 
Visualization: David Bock, National Center for Supercomputing Applications 
Principal Investigator: Doron Kushnir, Institute for Advanced Study


Orbiting Black Holes Magnetohydrodynamics

Panelist: Mark Van Moer

This visualization shows a simulation of two orbiting black holes generated by the HARM3d magnetohydrodynamics package. The focus will be on showing the behavior of magnetic field lines emanating from just above the black holes, perpendicular to the orbital plane. The completed video will highlight the field line entrainment and encirclement of the orbital axis along with volume rendering of the particle density in order to show their correspondence.

The rough cut of the video can be downloaded from:

https://www.dropbox.com/s/qt36oz07xj4xef3/noble_vanmoer_sisneros_draft.mov?dl=0

We anticipate having more timesteps available by the time of the conference with correspondingly longer sequences.

ParaView + OSPRay: High-Fidelity Ray Tracing for Scientific Visualization

Panelist: Paul Navratil

This visualization demonstrates an integration of the Intel OSPRay ray tracing engine with ParaView, a VTK-based visualization toolkit. By using ray tracing, researchers can produce visualizations with photorealistic shading more easily than with rasterization-based methods. In addition, ray tracing is more efficient than rasterization when rendering many views of high-resolution geometry. This video demonstrates the capabilities of the current pvOSPRay implementation and compares the visualization results against standard ParaView rendering. pvOSPRay is available on TACC high-performance computing systems and available for download at https://tacc.github.io/pvOSPRay/ . 

The movie is available for download at https://utexas.box.com/v/XSEDE16Vis 



Thursday July 21, 2016 10:30am - 12:00pm
Trade

11:00am

AD: Estimating the Accuracy of User Surveys for Assessing the Impact of HPC Systems
Each year, the Computational & Information Systems Laboratory (CISL) conducts a survey of its current and recent user community to gather a number of metrics about the scientific impact and outcomes from the use of CISL’s high-performance computing systems, particularly peer-reviewed publications. However, with a modest response rate and reliance on self-reporting by users, the accuracy of the survey is uncertain as is the degree of that uncertainty. To quantify this uncertainty, CISL undertook a project that attempted to provide statistically supported limits on the accuracy and precision of the survey approach. We discovered limitations related to the range of users’ HPC usage in our modeling phase, and several methods were attempted to adjust the model to fit the usage data. The resulting statistical models leverage data about the HPC usage associated with survey invitees to quantify the degree to which the survey undercounts the relevant publications. A qualitative assessment of the collected publications aligns with the statistical models, reiterates the challenges associated with acknowledgment for use of HPC resources, and suggests ways to improve the survey results further.

Speakers
avatar for David Hart

David Hart

User Services Section Manager, National Center for Atmospheric Research


Thursday July 21, 2016 11:00am - 11:30am
Sevilla InterContinental Miami

11:00am

AD: Improving the Scalability of a Charge Detection Mass Spectrometry Workflow
The Indiana University (IU) Department of Chemistry’s Martin F. Jarrold (MFJ) Research Group studies a specialized technique of mass spectrometry called Charge Detection Mass Spectrometry (CDMS). The goal of mass spectrometry is to determine the mass of chemical and biological compounds, and with CDMS, the MFJ Research Group is extending the upper limit of mass detection. These researchers have developed a scientific application, which accurately analyzes raw CDMS data generated from their mass spectrometer. This paper explains the comprehensive process of optimizing the group’s workflow by improving both the latency and throughput of their CDMS application. These significant performance improvements enabled high efficiency and scalability across IU’s Advanced Cyberinfrastructure; overall, this analysis and development resulted in a 25x speedup of the application.


Thursday July 21, 2016 11:00am - 11:30am
Chopin Ballroom

11:00am

SW: The 10 Attributes that Drive Adoption and Diffusion of Computational Tools in e-Science
As the computational movement gains more traction in the scientific community, there is an increasing need to understand what drives adoption and diffusion of tools. This investigation reveals what makes a computational tool more easily adopted by users within the e-science community. Guided by Rogers’s [1] Diffusion of Innovations theory, we set out to identify the innovation attributes of a range of computational tools across domains. Based on 135 interviews with domain scientists, computational technologists, and supercomputer center administrators across the U.S. and a small portion from Europe, systematic analysis revealed 10 key attributes. They are: driven by needs, organized access, trialability, observability, relative advantage, simplicity, compatibility, community-driven, well-documented, and adaptability. We discuss the attributes in the form of questions stakeholders should keep in mind while designing and promoting the tools. We also present strategies associated with each attribute. The 10 attributes and associated questions can serve as a checklist for e-science projects that aim to promote their computation tools beyond the incubators. This paper is submitted to the "Software and Software Environments" track because it has implications for engagement of user communities.

Speakers
MW

Michelle Williams

 Michelle Williams is an MS candidate in health & strategic communication at Chapman University in Orange, California. She is also a graduate research assistant in the Chapman's OCT (Organizing, Communication, & Technology) Research Group. Besides this paper, Michelle researches communication strategies for agile software development in e-science projects.


Thursday July 21, 2016 11:00am - 11:30am
Brickell

11:30am

AD: Minimization of Xeon Phi Core Use with Negligible Execution Time Impact
For many years GPUs have been components of HPC clusters (Titan and Piz Daint), while only in recent years has the Intel Xeon Phi been included (Tianhe-2 and Stampede). For example, GPUs are in 14% of systems in the November 2015 Top500 list, while the Xeon Phi is in 6%. Intel came out with Xeon Phi to compete with NVIDIA GPUs by offering a unified environment that supports OpenMP and MPI, and by providing competitive and easier-to-utilize processing power with less power consumption. The best Xeon Phi execution-time performance requires high data parallelism, good scalability, and the use of parallel algorithms. In addition, efficient power performance and application concurrency can be achieved by decreasing the number of cores employed for application execution. Accordingly, the objectives of this paper are to: (1) Demonstrate that some applications can be executed with fewer cores than are available to the user with a negligible impact on execution time: For 59.3% of the 27 application instances studied, doing this resulted in better performance and for 37% using less than half resulted in performance degradation of not more than 10% in the worst case. (2) Develop a tool that provides the user with the "best" number of cores to employ: We designed an algorithm and developed a plugin for the Periscope Tuning Framework, an automatic performance tuner, that for a given application provide the user with an estimation of this number. (3) Understand if performance metrics can be used to identify applications that can be executed with fewer cores with a negligible impact on execution time: We identified, via statistical analyses, the following three metrics that are indicative of this, at least for the application instances studied: low L1 Compute to Data Access ratio, i.e., the average number of computations that are performed per byte of data loaded/stored in the L1 cache, a high use of data bandwidth, and, to a lesser extent, a low vectorization intensity.


Thursday July 21, 2016 11:30am - 12:00pm
Sevilla InterContinental Miami

11:30am

AD: Scaling GIS analysis tasks from the desktop to the cloud utilizing contemporary distributed computing and data management approaches: A case study of project-based learning and cyberinfrastructure concepts
In this paper we present the experience of scaling in parallel a geographic information system modeling framework to hundreds of processors. The project began in an active learning cyberinfrastructure course which was followed by an XSEDE ECSS effort in collaboration across multiple-institutions.


Thursday July 21, 2016 11:30am - 12:00pm
Chopin Ballroom

11:30am

SW: Practical Realtime Monitoring of Resource Utilization for HPC Applications
HPC centers run a diverse set of applications from a variety of scientific domains. Every application has different resource requirements, but it is difficult for domain experts to find out what these requirements are and how they impact performance. In particular, the utilization of shared resources such as parallel file systems may influence application performance in significant ways that are not always obvious to the user. We present a tool, REMORA, that is designed to provide the information that is most critical for running efficiently an application in HPC systems. REMORA collects runtime resource utilization data for a particular job execution and presents a user-friendly summary on completion. The information provided forms a complete view of the application interaction with the system resources, which is typically missing from other profiling and analysis tools. Setting up and running REMORA requires trivial effort, and can be done as a regular user with no special permissions. This enables both users and administrators to download the tool and identify a particular application’s resource requirements within minutes, helping in the diagnosis of errors and performance issues. REMORA is designed to be scalable and have minimal impact on application performance, and includes support for NVIDIA GPUs and Intel Xeon Phi coprocessors. It is open source, modular, and easy to modify to target a large number of HPC resources.


Thursday July 21, 2016 11:30am - 12:00pm
Brickell

12:00pm

1:30pm

XSEDE All-Hands
Thursday July 21, 2016 1:30pm - 3:00pm
Chopin Ballroom

3:00pm

ECSS Training
Co-located workshop. Attendance by invitation only.

Thursday July 21, 2016 3:00pm - 5:00pm
Chopin Ballroom