Loading…
Tuesday, August 7
 

10:30am MDT

Poster Judging Session
Tuesday August 7, 2018 10:30am - 1:00pm MDT
Wolf Law School

11:30am MDT

Registration
Tuesday August 7, 2018 11:30am - 1:00pm MDT
Wolf Law School

1:00pm MDT

Fundamentals of Accelerated Computing with OpenACC
In this this first session you will learn application profiling with the PGI PGProf profiler, building and running OpenACC code on multicore processors with the PGI compiler, before continuing in the second session to then move on to the GPU for maximum performance. No prior OpenACC and GPU Computing experience is required, but students are strongly encouraged to attend both sessions. Some experience with C/C++ or Fortran is required. Please bring your own computer for hands-on portions.

Speakers

Tuesday August 7, 2018 1:00pm - 2:30pm MDT
Room 205

1:00pm MDT

HPC Carpentry
This workshop is an introduction to using high-performance computing (HPC) systems, specifically the RMACC Summit compute resource, effectively. It is intended to give students an introduction to HPC and an overview of the tools needed to start making use of Summit for you research computing needs. If you do not already have a Summit account, we will have temporary account credentials available for use for the duration of the workshop.

By the end of this workshop, attendees will know how to:
  • Connect to a cluster
  • Use basic UNIX commands for managing files
  • Work with the Nano editor
  • Write simple shell scripts
  • Submit and manage jobs on Summit using the SLURM scheduler
  • Manage software through environment modules


Tuesday August 7, 2018 1:00pm - 2:30pm MDT
Courtroom

1:00pm MDT

Analyzing Structured Data with Python and Pandas
This workshop will give an overview about Pandas, an open source, BSD-licensed library providing high-performance, easy-to-use data structures and data analysis tools for the Python programming language. The workshop will focus on reading and writing structured data, like Excel or comma separated files. We will create descriptive statistics (describing individual variables, central tendency, shape and variation), sort, rank and group data. The different option of merging (joining) multiple files will be discussed. Finally, the techniques will be used to show the different options for cleaning data.
Please bring your own laptop with Python 3x and Pandas installed.

Speakers

Tuesday August 7, 2018 1:00pm - 2:30pm MDT
Room 207

1:00pm MDT

Introduction to Numpy/Scipy
The session will be a hands-on introduction.
We will discuss first of all why Numpy is important for scientific applications.
The following topics will be covered: creation of arrays, indexing and slicing, iteration over arrays, elementary operations with arrays, the concept of broadcasting, universal functions as well as masked arrays.
In the last part we will introduce Scipy, which is built on top of Numpy.

Speakers

Tuesday August 7, 2018 1:00pm - 2:30pm MDT
Room 204

1:00pm MDT

Real-time Rendering in VR with Unity3D
This hands-on workshop will cover the key steps to visualizing mesh data in Unity. We will begin by importing a model and its accompanying textures, followed by material creation/application, lighting, simple interactions and Virtual Reality support. Please bring a laptop with Unity 2017.3.1 installed, and feel free to bring a model in .obj or .fbx format to experiment with. Though it will be light on coding, there will be some C# scripting to handle interactions. You are welcome to ask any questions throughout the workshop, but there will be a Q&A session at the end as well.

Speakers

Tuesday August 7, 2018 1:00pm - 2:30pm MDT
Room 206

2:30pm MDT

Break- Sponsored by Lenovo
Tuesday August 7, 2018 2:30pm - 3:00pm MDT
Wolf Law School

3:00pm MDT

Fundamentals of Accelerated Computing with OpenACC (Cont’d) Accelerating Applications on GPU Devices for Maximum Performance
Continuing the work done in the previous session, participants will go deep on OpenACC Directives with hands-on instruction and labs. In this session you will move work on to the GPU for maximum performance. No prior OpenACC and GPU Computing experience is required, but students are strongly encouraged to have attended the first OpenACC session in the day. Some experience with C/C++ or Fortran is required. Please bring your own computer for hands-on portions.

Speakers

Tuesday August 7, 2018 3:00pm - 4:30pm MDT
Room 205

3:00pm MDT

CANCELLED- Introduction to Tensor Comprehension
This is a tutorial session on tensor comprehensions. Facebook AI Research (FAIR) released a new C++ library called tensor comprehensions that aims to bridge the gap between researchers who think regarding mathematical equations and engineers focusing on the practical needs of running large-scale models on various hardware backend. The main differentiating feature of Tensor Comprehensions is that it represents a unique take on Just-In-Time compilation to produce the high-performance codes that the machine learning community needs, automatically and on-demand. The aim of this tutorial is two-fold: (1) New HPC users will be able to appreciate the importance of HPC in machine learning (2) New HPC users will be able to appreciate the sophisticated tools that enable to them produce automatic code in relatively simple and straightforward manner.


Tuesday August 7, 2018 3:00pm - 4:30pm MDT
Room 206

3:00pm MDT

HPC Carpentry
This workshop is an introduction to using high-performance computing (HPC) systems, specifically the RMACC Summit compute resource, effectively. It is intended to give students an introduction to HPC and an overview of the tools needed to start making use of Summit for you research computing needs. If you do not already have a Summit account, we will have temporary account credentials available for use for the duration of the workshop.

By the end of this workshop, attendees will know how to:
  • Connect to a cluster
  • Use basic UNIX commands for managing files
  • Work with the Nano editor
  • Write simple shell scripts
  • Submit and manage jobs on Summit using the SLURM scheduler
  • Manage software through environment modules


Tuesday August 7, 2018 3:00pm - 4:30pm MDT
Courtroom

3:00pm MDT

Analyzing Structured Data with Python and Pandas
This workshop will give an overview about Pandas, an open source, BSD-licensed library providing high-performance, easy-to-use data structures and data analysis tools for the Python programming language. The workshop will focus on reading and writing structured data, like Excel or comma separated files. We will create descriptive statistics (describing individual variables, central tendency, shape and variation), sort, rank and group data. The different option of merging (joining) multiple files will be discussed. Finally, the techniques will be used to show the different options for cleaning data.
Please bring your own laptop with Python 3x and Pandas installed.

Speakers

Tuesday August 7, 2018 3:00pm - 4:30pm MDT
Room 207

3:00pm MDT

Introduction to Numpy/Scipy
The session will be a hands-on introduction.
We will discuss first of all why Numpy is important for scientific applications.
The following topics will be covered: creation of arrays, indexing and slicing, iteration over arrays, elementary operations with arrays, the concept of broadcasting, universal functions as well as masked arrays.
In the last part we will introduce Scipy, which is built on top of Numpy.

Speakers

Tuesday August 7, 2018 3:00pm - 4:30pm MDT
Room 204

3:00pm MDT

RMACC SysAdmins Round Up/ HTTP Needs for HPC: Improving Access
Open discussion between RMACC system administrators on topics that need moving forward. Ask questions and help answer questions on storage, compute, software, configurations. This is the time to meet new administrators in the RMACC region as well. We’ll also target discussion of SC events and the next RMACC SysAdmin Meet-up.

Understanding the ecosystem of HTTP needs for science gateways, web access to clusters and storage portals, self-service data sharing models, and building software services to enhance access. Overview of products like Open OnDemand, FastX, Globus, JupyterHub, RStudio and understand strengths and weaknesses. What is needed to help make these packages easier to configure and deploy?

Speakers

Tuesday August 7, 2018 3:00pm - 4:30pm MDT
Room 301
 
Wednesday, August 8
 

7:30am MDT

8:30am MDT

Welcome and Poster Presentations
Wednesday August 8, 2018 8:30am - 9:00am MDT
Courtroom

9:00am MDT

Architecting Science Application for Exascale
Exascale systems are coming soon. At the same time the demands of science for supercomputing are changing. Rates of data generation and complexity of science require new approaches. I will discuss the current exascale system plans and some of the challenges expected. The primary focus of the talk will be on how we get science applications ready for exascale through both the DOE computing facilities and the Exascale Computing Project. The result of this process is expected to bring in a new way for science to use HPC systems.

Speakers
KR

Katherine Riley

Katherine is the Director of Science of the Argonne Leadership Computing Facility overseeing the scientific and technical direction for the facility. She has worked at the ALCF for over 10 years focusing on application readiness for supercomputing and co-designing supercomputers for... Read More →


Wednesday August 8, 2018 9:00am - 10:15am MDT
Courtroom

10:15am MDT

Networking Break
Wednesday August 8, 2018 10:15am - 10:30am MDT
Wolf Law School

10:30am MDT

"AIRI" - The industry's First Complete AI-Ready Infrastructure (Pure Storage sponsored session)
​​​​This summer is a fantastic milestone for Pure as we recently announced
"AIRI" - The industry's First Complete AI-Ready Infrastructure.



AIRI is a first in the industry across multiple fronts, but two specifically:
-1st storage platform to be on the main stage of AI (as referenced by
several Analysts and Press over the past several weeks of public-facing briefings) -1st time that NVIDIA has teamed with another company in this fashion within AI.



The promise of the adoption of AI is vast. It's easy to talk about self-driving cars, but AI will touch everything from the Grocery
industry to Healthcare to Transportation through autonomous vehicles ranging from cars to trucks, to planes, and boats. At the NVIDIA GTC conference, NVIDIA CEO Jensen Huang talked about a 25X increase in GPU (the technology that is increasingly driving the performance and scalability of AI through Deep Learning) performance over the last 5 years. But AI has largely been the domain of science fiction and large research institutions and labs.



The Enterprise has largely been on the outside looking in with AI due
to infrastructure complexity and cost. With AIRI, AI is far more accessible to those Enterprise Customers in every industry that will literally change the world. That accessibility to the Enterprise with
AIRI will allow the vast potential of AI's computational capabilities for mass consumption.



Please join Keith Ober, FlashBlade Systems Engineer, for an AIRI architectural overview.

Speakers

Wednesday August 8, 2018 10:30am - 11:30am MDT
Courtroom

10:30am MDT

The Convergence of HPC and AI (Intel Sponsored Session)



Speakers

Wednesday August 8, 2018 10:30am - 11:30am MDT
Room 304

10:30am MDT

Visualization Paper Session
Designing in the Dark – guiding research-driven software design with visualization:
I will be presenting a real-time, interactive visualization project created with Unity to supplement an upcoming research paper about the projected outcomes of chemical reactions. The paper deals with overly optimistic projections of reaction rates, and the likelihood of defects resulting in imperfect outcomes. I will be covering the process of creating the software both for its technical considerations (efficient rendering in real-time) and its scientific validity, mentioning where applicable steps taken for optimization of the underlying algorithms and graphical rendering in addition to remaining possibilities for increasing performance and the potential for better implementations. Additionally, I will address the degree to which the development of this software influenced the direction of the research informing it and helped to highlight areas of incomplete understanding of the mechanisms proposed therein.

Interactive visualizations for multiobjective optimization problems:
In environmental planning problems, decision makers are faced with multiple competing objectives. Multiobjective optimization is a promising method for identifying solutions for these complex systems. However, the datasets that result from these optimizations are large and multi-dimensional, making them difficult to interpret. Interactive visualizations allow users to more easily explore these data and make better decisions. In this presentation, we highlight the features of parasol.js, our new interactive visualization library for exploring multiobjective optimization datasets.


Wednesday August 8, 2018 10:30am - 11:30am MDT
Room 204

10:30am MDT

Cradle to Grave: Planning your data life cycle
This session provides a brief overview of the data lifecycle -- including planning, writing proposals with data management plans, approvals, data collection/creation, analysis, visualization, sharing and preservation -- followed by group discussion of the challenges, uncertainties and lessons learned.

Speakers

Wednesday August 8, 2018 10:30am - 11:30am MDT
Room 205

10:30am MDT

Resume and Interview Tips and Tricks
Join an interactive discussion about how to prepare and conquer job interviews.

Bring your resume and/or cover letter for review by our moderators and other attendees. Get help to improve the layout, flow, and content.


Wednesday August 8, 2018 10:30am - 11:30am MDT
Room 305

10:30am MDT

Red Hat: Linux Container Security
Linux container technology allows a customer to carve a system out into isolated containers and run applications securely within the confines of the containers. It facilitates multi-tenancy, which allows IT organizations to take better advantage of the large servers available in their datacenters. While multitenancy provides flexibility for server resource management, especially for service providers, it introduces additional complexity, especially related to the security of applications and data that reside on the same server. Daniel will discuss resource management, namespacing, and the use of SELinux to tighten the security of Linux containers.

Speakers

Wednesday August 8, 2018 10:30am - 11:30am MDT
Room 301

10:30am MDT

Best practices for writing an RFP for HPC Hardware Purchases
This panel will discuss some of the best practices for writing an RFP and share experiences from the vendor and university perspectives.


Wednesday August 8, 2018 10:30am - 11:30am MDT
Room 207

10:30am MDT

RMACC User Support Meetup
Do you work in User Support? Would you like to connect with user support teams at other RMACC partner institutions? Join us for a Informal Meet and Greet!

Speakers

Wednesday August 8, 2018 10:30am - 11:30am MDT
Room 206

11:30am MDT

Lunch- Sponsored by Pure Storage
Wednesday August 8, 2018 11:30am - 12:45pm MDT
Wolf Law School

12:45pm MDT

Breaking the Glass Ceiling: Successfully Identifying and Addressing Selection Bias in a Student Program
This work presents program evaluation findings affiliated with gender-based selection bias in an international high performance computing (HPC) student program. The research demonstrates application reviewers from all countries are unconsciously biased against female applicants resulting in significantly lower applicant scores. Additional data that contradicts reviewer bias and supports gender parity among participants in HPC knowledge level and academic achievement are presented. Suggestions for reducing selection bias in light of our findings are discussed. This talk also includes preliminary findings from the expansion of this study to members of underrepresented minorities in HPC.


Speakers

Wednesday August 8, 2018 12:45pm - 2:00pm MDT
Courtroom

2:00pm MDT

Break- Sponsored by Mark III Systems
Wednesday August 8, 2018 2:00pm - 2:30pm MDT
Wolf Law School

2:30pm MDT

Research Computing and Networking with Cisco Solutions (Cisco Vendor Session 30 minutes)
The session will go over high level architecture of Cisco UCS server platforms for CPU/GPU computing and Software Defined Storage relevant to research computing and networking. The session will discuss the low latency fabric options along with unified server management approach. And lastly the session will discuss recent ScienceDMZ architecture for research computing.

Speakers

Wednesday August 8, 2018 2:30pm - 3:00pm MDT
Room 304

2:30pm MDT

AI from Concept to Realization (HPE Sponsored Sessions)
A.I. has been the hot trend of the last two years with roots stemming from the 1950s and further back. Today we are finally seeing the fruit of computational & mathematical excellence lending to an industry explosion in autonomous everything. We will cover how HPE is driving the market by helping customer in their AI journey but also how Hewlett Packard Labs is driving innovation.

Speakers

Wednesday August 8, 2018 2:30pm - 3:30pm MDT
Courtroom

2:30pm MDT

Globus: Beyond File Transfer
Globus is a research data management service for easily and securely moving, sharing, and publishing data. This presentation will provide a brief overview of Globus, review notable events in the evolution of the Globus service over the past year, and provide an update on future product direction.

Speakers

Wednesday August 8, 2018 2:30pm - 3:30pm MDT
Room 305

2:30pm MDT

HPC in Data Science and Machine Learning
High Performance Computing (HPC) has an integral role to play in Data Science and Machine Learning.  The combination of software tools, computational resources, networking, and data storage has allowed large scale prediction and inference to be applied in a myriad of domains including image processing, voice recognition, and anomaly detection, to name but a few.   In this talk we will highlight some current connections between HPC and Data Science, including large scale dimension reduction and deep learning.  In particular, we will illustrate how combinations of fast CPUs and high-performance Graphical Processing Units (GPU) have enabled new approaches and products.

Speakers
RP

Randy Paffenroth

Dr. Paffenroth graduated from Boston University with degrees in both mathematics and computer science and he was awarded his Ph.D. in Applied Mathematics from the University of Maryland in June of 1999. After attaining his Ph.D., Dr. Paffenroth spent seven years as a Staff Scientist... Read More →


Wednesday August 8, 2018 2:30pm - 3:30pm MDT
Room 204

2:30pm MDT

Research reincarnation: steps to improve the reproducibility of your research
The research reproducibility movement aims to improve the transparency and robustness of published research findings. In this birds of a feather discussion we will discuss tools, techniques, and practices that collectively improve the reproducibility of our research, and will share our experiences, both positive and negative, with these tools.


Wednesday August 8, 2018 2:30pm - 3:30pm MDT
Room 205

2:30pm MDT

Cloud use in academia- Successes and Hurdles
Adoption of cloud resources in academia as been slow compared to the commercial sector. There are significant financial hurdles that have slowed the adoption of cloud resources by researchers in academia. This panel will first discuss the success stories using cloud resources in academia. Next the financial hurdles driven by the cycle of external funding and potential solutions to accelerate the adoption of cloud resources are discussed. The panel will consist of participants from academia and industry.


Speakers
BJ

Brian Johnson

University of Colorado Boulder


Wednesday August 8, 2018 2:30pm - 3:30pm MDT
Room 206

2:30pm MDT

Kubernetes and Developing a Highly Available Application Portfolio
More and more organizations are adopting Kubernetes as a means of achieving high availability and flexible cluster computing. We’ll demonstrate to users how we’re leveraging Kubernetes for our mission in SLATE and improving our application portfolio in CHPC. The presentation will include technical overview of the Kubernetes, interfacing in various methods to Kubernetes, and showing the use cases within the SLATE project and within CHPC.

Speakers

Wednesday August 8, 2018 2:30pm - 3:30pm MDT
Room 301

2:30pm MDT

Best practices for running a student employee program
Join us for a session about how to run an effective student employee program at your institution. Hear from professionals who are in charge of these programs and those who have been students in these programs about how to create a great working environment and program that's beneficial to all.


Wednesday August 8, 2018 2:30pm - 3:30pm MDT
Room 207

3:30pm MDT

Networking Break
Wednesday August 8, 2018 3:30pm - 3:45pm MDT
Wolf Law School

3:45pm MDT

Altair Cloud - Engineered for Simplicity and Performance (Altair sponsored session, 30 minutes)
Altair’s High-Performance Computing (HPC) appliance creation and management software solutions provide engineers, scientists and administrators access to superior cloud computing technology. Users can cost effectively support, run, monitor and manage their simulation needs in the cloud to create robust product designs.
With Altair’s cloud technology, you can…
  • Avoid cloud provider lock-in by choosing between major global and local cloud providers and can easily change from one to the other.
  • Create your own HPC appliance by designing your HPC infrastructure with a simple and intuitive interface.
  • Integrate your application with PBS Works, our world-leading workload scheduling management suite.
  • Deploy your HPC stack in minutes with just a few clicks anytime, anywhere.
  • Control your cloud consumption with user quotas and alerting.
Altair’s HPC cloud management platform puts cloud infrastructures under your control.

Speakers

Wednesday August 8, 2018 3:45pm - 4:15pm MDT
Room 304

3:45pm MDT

Extending On-premise HPC to the Cloud (Rescale Sponsored Session)
Customers have made significant investments in on-premise HPC facilities. Meanwhile, the cloud has emerged as a new way to deliver HPC. Rescale offers a non-disruptive, unified platform approach to HPC in the cloud. In this talk, Gabriel Broner will discuss the use cases, challenges, and benefits for extending HPC to the cloud. A live demonstration will also be given.

Speakers

Wednesday August 8, 2018 3:45pm - 4:45pm MDT
Courtroom

3:45pm MDT

Toward data immortality: preserving your research legacy by publishing research data
Funders and publishers have accelerated the process of making raw research data open and accessible. This session will demystify the process of data publishing. Topics will include picking the right (meta)data standards for your field, finding an appropriate repository and how to submit data to the RMACC data repository, which is open to all RMACC members.


Wednesday August 8, 2018 3:45pm - 4:45pm MDT
Room 205

3:45pm MDT

Marketing yourself to Employers
Everyone has skills. They get you in the door, but not necessarily get you the job. There can be 100 or more applicants per job posting, and they all have the same or better skills as you.  It’s not just about the skills, it’s how to put your best foot forward to stand out as "the one.”   In today’s extremely competitive job environment it is increasingly important for each person to create a clear, concise statement on who you are, what professional skills you offer, and why you are the best candidate for the position.    Hear from marketing and industry professionals on what employers want to know and how to prepare for the questions employers are going to ask.


Wednesday August 8, 2018 3:45pm - 4:45pm MDT
Room 305

3:45pm MDT

National Compute resources for your research
DO you need access to additional computing time to complete your research? In this session we will provide information about national computing resources that are available for research, including information about where to go for more information as well as how to get started and applying for access. In addition, we will present information about HPC educational opportunities.


Wednesday August 8, 2018 3:45pm - 4:45pm MDT
Room 204

3:45pm MDT

On-premise Secure Environments and Data Classifications
Most high-performance computing system in academic settings do not provide support for data with privacy and regulatory constraints on sensitive data. This session will first provide an overview over the main categories of regulated and sensitive data. Then use cases from different RMACC partners are presented. Each panelist will describe how they address these issues in their local compute and data environment, and how they educate their users about how to these environments for sensitive and regulated data.  

Speakers
WB

Wayne Bradford

University of Utah
BJ

Brad Judy

University of Colorado Boulder
SM

Scott Maize

University of Colorado Boulder


Wednesday August 8, 2018 3:45pm - 4:45pm MDT
Room 206

3:45pm MDT

Red Hat: New Container Technologies and Security
Red Hat and the open source community have been working on new tools for using OCI containers. The goal of these tools is to break down the concepts of defining, pulling, storing and running containers into their base components. Then we build tools to run these containers with as much security as possible. This talk will explain the process and the tools and how they can be used more securely then current technologies.
In this session, we'll demonstrate some of those new tools, including:
* CRI-O for supporting Kubernetes workloads.
* Buildah for building container images.
* Skopeo for moving container images between container registries and stores.
* Podman for running traditional command line containers.

Speakers

Wednesday August 8, 2018 3:45pm - 4:45pm MDT
Room 301

3:45pm MDT

Towards Shared Cyberinfrastructure in the RMACC region
In this session we will present an overview over recent projects that have in impact on the RMACC region. The first project is the NSF funded RMACC Summit supercomputer where 10% of the CPU cycles are allocated for schools in the region. The other project is the Cyberteam project centered around improving the efficiency of data related workflows. During the remainder of the session we will discuss a strategy for improving the regional CI by exploring a regional CI plan and how seed funding from federal agencies could lead to shared distributed CI in the region operated by a key institutions in each state of the region but shared and governed by all RMACC members 


Wednesday August 8, 2018 3:45pm - 4:45pm MDT
Room 207

4:45pm MDT

Networking Break
Wednesday August 8, 2018 4:45pm - 5:00pm MDT
Wolf Law School

5:00pm MDT

5:15pm MDT

Reception- Sponsored by HPE
Wednesday August 8, 2018 5:15pm - 6:30pm MDT
Wolf Law School
 
Thursday, August 9
 

7:30am MDT

Breakfast and Registration
Thursday August 9, 2018 7:30am - 8:30am MDT
Wolf Law School

8:30am MDT

Achieving High Performance Python in Modern HPC Workflow
The evolution in usage of popular scripting languages such as Python has led to the language's growing popularity in HPC work. With more and more numerical workloads being written in Python, getting the most out of one's mixed C and Python code becomes challenging with the intricacies and restrictions normally present in the Python language. However, recent advancements in Python tools has allowed for additional options for mixed codebases–with the proper knowledge of how to design, measure, and publish such Python packages in a compute center, a high-productivity Python compute environment can easily coexist with existing HPC code and workflows.
 This presentation will cover the theory behind Python HPC performance, the tools used to convert portions of the code back and forth between Python and C code, determining and profiling the performance of a mixed application, and finally building and deploying applications within a compute center. Examples will be shown of each of the critical methods above will provide reinforcement of the concepts, followed afterwards with a Q&A session.

Speakers
DL

David Liu

David is a Technical Consultant Engineer at Intel Corporation in Austin, Texas, where he represents Intel's Python products and projects. He is focused on solving customer problems in Python while simultaneously developing and shaping Intel's software products to match customer needs... Read More →


Thursday August 9, 2018 8:30am - 10:00am MDT
Room 207

8:30am MDT

PySpark XSEDE- Part One
We will cover the defining characteristics of "Big Data" and typical ways of interacting with it before we dive into a detailed, and exercise-driven, exploration of Spark, the preeminent big data framework. We will use Spark to investigate data mining at scale and also its more sophisticated machine learning capabilities.

Speakers

Thursday August 9, 2018 8:30am - 10:00am MDT
Room 204

8:30am MDT

Introduction to Jetstream- Part One
Prerequisites:
Basic Linux command line knowledge a plus (but not required)
 Required: Laptop, modern web browser(Chrome,Firefox, Safari)

This tutorial will first give an overview of Jetstream and various aspects of the system. Then we will take attendees through the basics of using Jetstream via the Atmosphere web interface. This will include a guided walk-through of the interface itself, the features provided, the image catalog, launching and using virtual machines on Jetstream, using volume-based storage, and best practices. We are targeting users of every experience level. Atmosphere is well-suited to both HPC novices and advanced users. This tutorial is generally aimed at those unfamiliar with cloud computing and generally doing computation on laptops or departmental server resources. While we will not cover advanced topics in this particular tutorial, we will touch on the available advanced capabilities during the initial overview.

Speakers

Thursday August 9, 2018 8:30am - 10:00am MDT
Courtroom

8:30am MDT

Integrating Globus Into Your Applications and Workflows
During this hands-on tutorial, students will learn how to integrate Globus data management capabilities into their own applications and workflows, using the Globus REST APIs and Python SDK.

Speakers

Thursday August 9, 2018 8:30am - 10:00am MDT
Room 205

8:30am MDT

HPC Carpentry
This workshop is an introduction to using high-performance computing (HPC) systems, specifically the RMACC Summit compute resource, effectively. It is intended to give students an introduction to HPC and an overview of the tools needed to start making use of Summit for you research computing needs. If you do not already have a Summit account, we will have temporary account credentials available for use for the duration of the workshop.

By the end of this workshop, attendees will know how to:
  • Connect to a cluster
  • Use basic UNIX commands for managing files
  • Work with the Nano editor
  • Write simple shell scripts
  • Submit and manage jobs on Summit using the SLURM scheduler
  • Manage software through environment modules


Thursday August 9, 2018 8:30am - 10:00am MDT
Room 305

8:30am MDT

Building interactive web applications using Shiny
When you have a lot of excellent data, you want to show it off! Shiny makes it easy to build interactive web applications straight from R. This session will cover creating a basic shiny app, customizing the user interface with formatted text, panels and reactive output, and share your apps on the web on github and as a web page.

Speakers

Thursday August 9, 2018 8:30am - 10:00am MDT
Room 304

8:30am MDT

Lessons learned building and operating Jetstream
Consisting of two 320 node clouds operated by Indiana University and the Texas Advanced Computing Center at University of Texas Austin, Jetstream is a first of kind system funded by the National Science Foundation. Jetstream was conceived four years ago, and early operations started two and a half years ago. In this time there have been a number of mistakes made as well as pitfalls avoided in both the construction and operation of this distributed cloud resource. Causes of major outages, design choices, pain points, as well as comparisons to traditional HPC systems will be covered.

Speakers
ML

Mike Lowe

Jetstream


Thursday August 9, 2018 8:30am - 10:00am MDT
Room 301

8:30am MDT

Your Next Generation of Scientific Visualization with Paraview 5.5.0
ParaView is an open-source, cross-platform application used to exploration, analyze and visualization scientific data. These processing capabilities can be done either with the real time interactive gui or using python scripts.
In this hands on workshop we will take a productive look at some of the many new and a few of the more advanced features of Paraview 5.5. This includes new filters, plugins and the beautiful new NVidia renderer IndeX. In addition, we will look at creating our visualizations, including animations, using python scripting, showing you how to quickly and efficiently become proficient at this powerful way of visualizing your data.
Skill Level: This is an intermediate level overview of using the new features of Paraview as well as development with python to explore and visualize large scientific data sets.
Requirements: This is a hands on tutorial. If you wish to follow along please already have Paraview version 5.5.0 installed on your laptop which can be freely downloaded from; https://www.paraview.org/download/. We will not take time to deal with installation issues once the workshop starts. If you have problems with your setup please contact me at tdunn@colorado.edu.

Speakers

Thursday August 9, 2018 8:30am - 10:00am MDT
Room 206

10:00am MDT

Networking Break
Thursday August 9, 2018 10:00am - 10:30am MDT
Wolf Law School

10:30am MDT

Achieving High Performance Python in Modern HPC Workflow
The evolution in usage of popular scripting languages such as Python has led to the language's growing popularity in HPC work. With more and more numerical workloads being written in Python, getting the most out of one's mixed C and Python code becomes challenging with the intricacies and restrictions normally present in the Python language. However, recent advancements in Python tools has allowed for additional options for mixed codebases–with the proper knowledge of how to design, measure, and publish such Python packages in a compute center, a high-productivity Python compute environment can easily coexist with existing HPC code and workflows.
 This presentation will cover the theory behind Python HPC performance, the tools used to convert portions of the code back and forth between Python and C code, determining and profiling the performance of a mixed application, and finally building and deploying applications within a compute center. Examples will be shown of each of the critical methods above will provide reinforcement of the concepts, followed afterwards with a Q&A session.

Speakers
DL

David Liu

David is a Technical Consultant Engineer at Intel Corporation in Austin, Texas, where he represents Intel's Python products and projects. He is focused on solving customer problems in Python while simultaneously developing and shaping Intel's software products to match customer needs... Read More →


Thursday August 9, 2018 10:30am - 12:00pm MDT
Room 207

10:30am MDT

PySpark XSEDE- Part Two
We will cover the defining characteristics of "Big Data" and typical ways of interacting with it before we dive into a detailed, and exercise-driven, exploration of Spark, the preeminent big data framework. We will use Spark to investigate data mining at scale and also its more sophisticated machine learning capabilities.

Speakers

Thursday August 9, 2018 10:30am - 12:00pm MDT
Room 204

10:30am MDT

Introduction to Jetstream- Part Two
Prerequisites:
Basic Linux command line knowledge a plus (but not required)
 Required: Laptop, modern web browser(Chrome,Firefox, Safari)

This tutorial will first give an overview of Jetstream and various aspects of the system. Then we will take attendees through the basics of using Jetstream via the Atmosphere web interface. This will include a guided walk-through of the interface itself, the features provided, the image catalog, launching and using virtual machines on Jetstream, using volume-based storage, and best practices. We are targeting users of every experience level. Atmosphere is well-suited to both HPC novices and advanced users. This tutorial is generally aimed at those unfamiliar with cloud computing and generally doing computation on laptops or departmental server resources. While we will not cover advanced topics in this particular tutorial, we will touch on the available advanced capabilities during the initial overview.

Speakers

Thursday August 9, 2018 10:30am - 12:00pm MDT
Courtroom

10:30am MDT

Workflow Tools
Workflow tools help to shape complex analyses into efficient, reproducible programs that can be run on your local machine, on a cluster such as RMACC Summit, or even on national computing resources like the Open Science Grid (OSG). Some of these tools are container-friendly, and provide a great way to improve the reproducibility of your research. During this hands-on session we will use RMACC Summit to build workflows with two workflow tools: Snakemake and Nextflow.

Speakers

Thursday August 9, 2018 10:30am - 12:00pm MDT
Room 205

10:30am MDT

HPC Carpentry
This workshop is an introduction to using high-performance computing (HPC) systems, specifically the RMACC Summit compute resource, effectively. It is intended to give students an introduction to HPC and an overview of the tools needed to start making use of Summit for you research computing needs. If you do not already have a Summit account, we will have temporary account credentials available for use for the duration of the workshop.

By the end of this workshop, attendees will know how to:
  • Connect to a cluster
  • Use basic UNIX commands for managing files
  • Work with the Nano editor
  • Write simple shell scripts
  • Submit and manage jobs on Summit using the SLURM scheduler
  • Manage software through environment modules


Thursday August 9, 2018 10:30am - 12:00pm MDT
Room 305

10:30am MDT

Tidyverse: Doing neat data science in R
Tidyverse is a collection of R packages for end-to-end data science. Tidyverse enables users to read, organize, manipulate and visualize numeric and text data. This tutorial will provide a hands-on introduction to the basics of Tidyverse.

Speakers

Thursday August 9, 2018 10:30am - 12:00pm MDT
Room 304

10:30am MDT

Congratulations – your new Data Center has been value-engineered!
HPC systems are so strongly dependent on facility power and cooling that the building essentially becomes part of the computer. This marriage between computer and facility has moments of happiness as well as relationship storms. The first problem in the relationship starts with the requirements and design phase where experienced HPC staff and architects must come together with crystal balls and magic to design a facility to support systems that have yet to be invented. How much power do we really need? How are we going to cool these systems? What about building controls and monitoring? Next comes the happy day of value-engineering. ☹ This presentation will share lessons learned through this phase. Stay tuned next year for the update on construction and commissioning. All of this effort is hopefully leading to a happy marriage between machine and facility.

Speakers

Thursday August 9, 2018 10:30am - 12:00pm MDT
Room 301

10:30am MDT

Scientific Visualization with Bokeh
Most all Python coders are familiar with matplotlib and/or Seaborn but morn at the lack of interactivity with their graphical exploration of their data. Bokeh is an answer to this problem and so much more as not only does it provide interactivity, quick and easily, to your visual needs but it also targets web browsers for presentation.
In this hands on workshop we will work in Jupyter Lab (the next generation of Jupyter Notebooks) to create many different types of interactive plots. As we work through these visualizations we will work towards building an advanced, multi-plot, fully interactive, scientific visualization dashboard which we will display live in a browser.
Skill Level: While this is a productive introduction to Bokeh I recommend that you are comfortable with the basics of Python including writing and calling functions as I will assume you are comfortable enough with the concepts of Python to just concentrate on using Bokeh.
Requirements:  This is a hands on tutorial. If you wish to follow along you should have a python distribution (its HIGHLY recommended to use Python 3.v as Python2 will no longer be maintained after 2020) installed on your laptop. If you do not have Python installed I recommend looking at Anaconda (https://anaconda.org/anaconda/python). Make sure you have access to Jupyter Lab (the next generation of Jupyter Notebooks) and that you have installed the Bokeh package (https://bokeh.pydata.org/en/latest/docs/installation.html). We will not take time to deal with installation issues once the workshop starts. If you have problems with your setup please contact me at tdunn@colorado.edu.

Speakers

Thursday August 9, 2018 10:30am - 12:00pm MDT
Room 206

12:00pm MDT

Lunch- Sponsored by Rescale
Thursday August 9, 2018 12:00pm - 1:00pm MDT
Wolf Law School

1:00pm MDT

PySpark XSEDE- Part Three
We will cover the defining characteristics of "Big Data" and typical ways of interacting with it before we dive into a detailed, and exercise-driven, exploration of Spark, the preeminent big data framework. We will use Spark to investigate data mining at scale and also its more sophisticated machine learning capabilities.

Speakers

Thursday August 9, 2018 1:00pm - 2:30pm MDT
Room 204

1:00pm MDT

High Throughput Computation on the Open Science Grid
Would you like to use distributed resources of the Open Science Grid, or just want to learn how to do large-scale high throughput computing?  The format of this tutorial is a mix of lecture and hands-on exercises, so please bring your laptop and make sure you have an SSH client installed.

 You will be provided with a training account on OSG Connect which, during the tutorial, will be upgraded to a full user account. After the session, you will have full access to the OSG, know how to run and scale up workloads, and manage your data. If time permits, the OSG User Support team will also help get your own workload set up for execution on OSG.

Topics to include:
    Introduction to OSG Connect
    Job Scheduling with HTCondor
    Scaling Up Workloads
    Managing data


Thursday August 9, 2018 1:00pm - 2:30pm MDT
Courtroom

1:00pm MDT

Using containers on RMACC Summit- Part One
A container is an image that includes everything needed to run one or more pieces of software: the code itself, an operating system environment and its associated tools and libraries, and other desired customizations. Containers are “stand-alone”, enabling workflows to be easily packaged and shared across platforms. This hands-on tutorial will provide an introduction to containers, the basics of running Docker and Singularity containers on RMACC Summit, and examples of building Singularity containers from recipe files.


Thursday August 9, 2018 1:00pm - 2:30pm MDT
Room 205

1:00pm MDT

HPC Carpentry
This workshop is an introduction to using high-performance computing (HPC) systems, specifically the RMACC Summit compute resource, effectively. It is intended to give students an introduction to HPC and an overview of the tools needed to start making use of Summit for you research computing needs. If you do not already have a Summit account, we will have temporary account credentials available for use for the duration of the workshop.

By the end of this workshop, attendees will know how to:
  • Connect to a cluster
  • Use basic UNIX commands for managing files
  • Work with the Nano editor
  • Write simple shell scripts
  • Submit and manage jobs on Summit using the SLURM scheduler
  • Manage software through environment modules


Thursday August 9, 2018 1:00pm - 2:30pm MDT
Room 305

1:00pm MDT

Parallel data analysis and machine learning using the Python package ipyparallel
In this tutorial, the Python package ipyparallel is introduced together with Jupyterhub notebooks. The ipyparallel package enables the development, debugging and interactive monitoring of parallel applications. It allows the quick parallelization of embarrassing parallel algorithms with just a few lines of code.  In our tutorial we will focus on two use cases: The first use case demonstrates how to parallelize the analysis of a large dataset and significantly reduce the time to process the data. The second use case will explain how to speed up machine learning algorithms from scikit-learn  using ipyparallel.

The materials can be download from https://github.com/ResearchComputing/RMACC-2018-ipyparallel.git

Speakers

Thursday August 9, 2018 1:00pm - 2:30pm MDT
Room 207

1:00pm MDT

Creating reproducible reports using R markdown
Documenting your analysis in a way that is understandable to a colleague (or yourself 3 months later) can be challenging. One way to make reports more readable, even by people who don’t code, is to alternate human readable text with machine readable code. This session will cover creating reproducible reports of this type using R Markdown. After this session, you will be able to create R markdown documents, add formatted text and executable code blocks, and render the R markdown document into a final report.

Speakers

Thursday August 9, 2018 1:00pm - 2:30pm MDT
Room 304

1:00pm MDT

Containers: What, How, Why, Security and Scientific Workloads?
Containers have recently become a hot topic in high-performance and scientific computing. While containers can provide significant advantages, they don't always live up to the hype. In order to help cut through the marketing, we explain what containers are, how they work, and survey some of the popular implementations with an eye toward supporting scientific workloads. Security and other operational concerns will also be covered for cluster administrators considering supporting containerized workloads on their systems.


Thursday August 9, 2018 1:00pm - 2:30pm MDT
Room 301

1:00pm MDT

Interactive Global Visualizations with CesiumJS
CesiumJS is the exciting open-source library for creating high quality global visualizations for the Earth or any spherical celestial body you desire, using static and/or dynamic data. CesiumJS is the leading solution replacement for the now discontinued Google Earth providing, even greater functionality and quality then previously seen.
In this hands on workshop we will setup a fully working CesiumJS work environment and explore Cesium’s javascripting capabilities to create interactive maps including 3D terrain. We will then prepare data to be used for mapping onto our 3D terrains, add 3D objects, explore environmental (atmospheric) controls and a whole lot more. We will do all of this in Cesium’s wonderful development/test environment ‘Sandcastle’. We will conclude by moving our work to a full-fledged web served interactive webpage complete with html, css and JavaScript codes.
Skill Level: A bare bones understanding off what Javascript is and are comfortable with some coding language. For the purposes of this tutorial we will work directly in Cesium’s wonderful development/test environment ‘Sandcastle’
Requirements: This is a hands on tutorial. If you wish to follow along, please make sure you have a machine that’s capable of running CesiumJS. To test this please visit this page; https://cesiumjs.org/Cesium/Apps/HelloWorld.html. If the page loads and you see a pretty image of the Earth, then congratulations you’re ready to go.

Speakers

Thursday August 9, 2018 1:00pm - 2:30pm MDT
Room 206

2:30pm MDT

Break- Sponsored by Dell
Thursday August 9, 2018 2:30pm - 3:00pm MDT
Wolf Law School

3:00pm MDT

PySpark XSEDE- Part Four
We will cover the defining characteristics of "Big Data" and typical ways of interacting with it before we dive into a detailed, and exercise-driven, exploration of Spark, the preeminent big data framework. We will use Spark to investigate data mining at scale and also its more sophisticated machine learning capabilities.

Speakers

Thursday August 9, 2018 3:00pm - 4:30pm MDT
Room 204

3:00pm MDT

High Throughput Computation on the Open Science Grid
Would you like to use distributed resources of the Open Science Grid, or just want to learn how to do large-scale high throughput computing?  The format of this tutorial is a mix of lecture and hands-on exercises, so please bring your laptop and make sure you have an SSH client installed.

 You will be provided with a training account on OSG Connect which, during the tutorial, will be upgraded to a full user account. After the session, you will have full access to the OSG, know how to run and scale up workloads, and manage your data. If time permits, the OSG User Support team will also help get your own workload set up for execution on OSG.

Topics to include:
    Introduction to OSG Connect
    Job Scheduling with HTCondor
    Scaling Up Workloads
    Managing data


Thursday August 9, 2018 3:00pm - 4:30pm MDT
Courtroom

3:00pm MDT

Using containers on RMACC Summit- Part Two
A container is an image that includes everything needed to run one or more pieces of software: the code itself, an operating system environment and its associated tools and libraries, and other desired customizations. Containers are “stand-alone”, enabling workflows to be easily packaged and shared across platforms. This hands-on tutorial will provide an introduction to containers, the basics of running Docker and Singularity containers on RMACC Summit, and examples of building Singularity containers from recipe files.


Thursday August 9, 2018 3:00pm - 4:30pm MDT
Room 205

3:00pm MDT

HPC Carpentry
This workshop is an introduction to using high-performance computing (HPC) systems, specifically the RMACC Summit compute resource, effectively. It is intended to give students an introduction to HPC and an overview of the tools needed to start making use of Summit for you research computing needs. If you do not already have a Summit account, we will have temporary account credentials available for use for the duration of the workshop.

By the end of this workshop, attendees will know how to:
  • Connect to a cluster
  • Use basic UNIX commands for managing files
  • Work with the Nano editor
  • Write simple shell scripts
  • Submit and manage jobs on Summit using the SLURM scheduler
  • Manage software through environment modules


Thursday August 9, 2018 3:00pm - 4:30pm MDT
Room 305

3:00pm MDT

Mpi4Py
MPI Message Passing Interface, is a standardized message-passing system for writing parallel applications. The official standard defines the syntax and semantics of a library for writing in Fortran and C. However, there are unofficial implementations for MPI for Python. This tutorial will cover the mpi4py module for writing Python MPI programs. We will give an overview of MPI with the examples in python. We will discuss the differences between mpi4py and “normal” MPI. We will compare mpi4py’s Object oriented and nonOO methodologies, giving advantages for each. We will continue with numerous examples showing the more common MPI calls. We also discuss extended examples including solving a partial differential equation on a grid and doing Bag of Task parallelism to solve many related problems. Links: http://mpi4py.scipy.org, http://mpi-forum.org,https://www.python.org
http://geco.mines.edu/prototype/Show_me_some_local_HPC_tutorials/mpi4py/

Speakers

Thursday August 9, 2018 3:00pm - 4:30pm MDT
Room 207

3:00pm MDT

Parallel R
Learn how to use R utilizing all cores of your or a supercomputer. You will learn how to prepare your serial R code so that it will be easier to run it in parallel. The parallel package will be introduced and you will be able to run some simple examples in parallel. Next, you will install the pbdMPI package in your project directory on our RMACC Summit supercomputer so that you can run R programs that utilize more than one compute node. You will then run some simple examples, including parallel random number generation, to get started and to familiarize yourself with running parallel R programs

The materials can be downloaded from https://github.com/ResearchComputing/RMACC-2018-parallel-R.git

Speakers

Thursday August 9, 2018 3:00pm - 4:30pm MDT
Room 304

3:00pm MDT

Data Visualization in Web Browsers with JavaScript APIs
Browser-embedded visualizations have become a ubiquitous tool for sharing and exploring data. This presentation will provide an entry point to help developers choose the right tools and techniques for creating effective web-based visualizations using JavaScript APIs. We will discuss the capabilities, limitations, drawbacks, and benefits of web-based visualizations and several specific APIs (Plotly.js, d3, HTML5-Canvas, ESRI JS-API). Several use-cases will be demonstrated and the underlying code will be discussed. All code/resources will be made available for download. Attendees will leave with an understanding of how web technology can be used to visualize data, a familiarity with some popular JS-APIs, and a clear path forward to start visualizing their data in the web browser.


Thursday August 9, 2018 3:00pm - 4:30pm MDT
Room 206
 
Filter sessions
Apply filters to sessions.