COE HPC

Bring High Performance Computing to Everyone in College of Engineering at Texas A&M University!

Call for Participation

Online Workshop: NVIDIA Deep Learning Institute for Computer Vision

Posted on by

The NVIDIA Deep Learning Institute (DLI), the Hewlett Packard Enterprise Data Science Institute at the University of Houston, the Texas A&M Institute of Data Science, Texas A&M High Performance Research Computing, and the Texas Engineering Experiment Station invite you to attend an online deep learning workshop on Aug 24, 2020 from 1:00PM to 5:00PM exclusively for verifiable academic students, staff, and researchers. NVIDIA DLI offers hands-on training for developers, data scientists, and researchers looking to solve challenging problems with deep learning and accelerated computing.

This workshop is hosted by Dr. Jian Tao through the NVIDIA University Ambassador Program at Texas A&M University.

See the workshop website for further details including how to register.

Exascale Computing Project (ECP) Sponsored Training Activities 

Posted on by

March 18 IDEAS-ECP Webinar: Testing Strategies

April 20-24 OpenMP Hackathon

April 21-24 Kokkos Bootcamp and Training

Other Training Activities of Interest 

March 9 NVIDIA Profiling Tools – Nsight Systems

March 10 NVIDIA Profiling Tools – Nsight Compute

March 25 DAOS: Next-Generation Data Management for Exascale

April/May/June OpenACC Series

May 5-7 2020 ALCF Computational Performance Workshop

2020 Monthly Series CUDA Training Series

2020 Series GPU Hackathon Series  

More Information about Upcoming ECP Training Activities

 

IDEAS ECP Webinar: Testing Strategies when Learning Programming Models and Using High-Performance Libraries

March 18, 2020

URL: https://exascaleproject.org/event/testingstrategies/

The next webinar in the series is titled, Testing: Strategies When Learning Programming Models and Using High-Performance Libraries, and will be presented by Balint Joo (Jefferson Laboratory). The webinar will take place on Wednesday, March 18, 2020 at 1:00 pm ET.

Software testing is an invaluable practice, albeit the level of testing in scientific applications can vary widely, from no testing at all to full continuous integration (as discussed in earlier webinars of the HPC-BP series). In this webinar I will consider a specific case: the use of unit-testing when developing a mini-app as an approach to learn about new programming models such as Kokkos and SYCL, or when using (or contributing to) high-performance libraries. I will illustrate with an example from Lattice QCD, focusing on the integration of the QUDA optimized library with the Chroma application. The webinar will focus on lessons learned and generally applicable strategies.

For more information or to register, please visit the URL above.

OpenMP Hackathon at Georgia Tech

April 20-24, 2020

URL: https://sites.google.com/view/omp-hack-atl/home

The Electrical Engineering and Computer Science Department at Georgia Institute of Technology in conjunction with Oak Ridge National Laboratory (ORNL) is organizing an ECP OpenMP Hackathon on April 20–April 24, 2020. This event is sponsored by the Exascale Computing Project (ECP), and driven by the ECP SOLLVE Project. We encourage participation of teams especially interested in porting and optimizing their applications by using the latest OpenMP features.

For more information or to register, please visit the URL above.

Kokkos Bootcamp and Training

April 21-24, 2020

URL: https://www.olcf.ornl.gov/calendar/kokkos-bootcamp-and-training/

The Oak Ridge Leadership Computing Facility (OLCF) will host a Kokkos training event organized by ECP on April 21-24, 2020. This workshop is intended to teach new Kokkos users how to get started and to help existing Kokkos users to further improve their codes. The training will cover the minimum required topics to get your application started on using Kokkos, and Kokkos experts will be on hand to help the more advanced users. For more information or to register, please visit the URL above.

Other Events that Might be of Interest to ECP Project Teams

 

NVIDIA Profiling Tools – Nsight Systems

March 9, 2020

URL: https://www.olcf.ornl.gov/calendar/nvidia-profiling-tools-nsight-systems/

 

On March 9, 2020, NVIDIA will present a webinar on how to use NVIDIA’s Nsight Systems – a statistical sampling profiler with tracing features – on Summit. Nsight Systems and Nsight Compute are NVIDIA’s next-generation profiling tools for understanding and optimizing the performance of CUDA, OpenACC, or OpenMP applications. NVIDIA recommends transitioning to these new tools since nvprof and Visual profiler will be deprecated in a future CUDA release. The presentation will be delivered remotely, but there will be an in-person viewing of the webinar for participants with current ORNL badges. For more information or to register, please visit the URL above.

 

NVIDIA Profiling Tools – Nsight Compute

March 10, 2020

URL: https://www.olcf.ornl.gov/calendar/nvidia-profiling-tools-nsight-compute/

 

On March 10, 2020, NVIDIA will present a webinar on how to use NVIDIA’s Nsight Compute – a kernel-level analysis and performance metric tool – on Summit. Nsight Systems and Nsight Compute are NVIDIA’s next-generation profiling tools for understanding and optimizing the performance of CUDA, OpenACC, or OpenMP applications. NVIDIA recommends transitioning to these new tools since nvprof and Visual profiler will be deprecated in a future CUDA release. The presentation will be delivered remotely, but there will be an in-person viewing of the webinar for participants with current ORNL badges.

For more information or to register, please visit the URL above.

DAOS: Next Generation Data Management for Exascale

March 25, 2020

URL: https://www.alcf.anl.gov/events/daos-next-generation-data-management-exascale

The Argonne Leadership Computing Facility (ALCF) is presenting the next Aurora Early Adopter Series webinar on March 25, 2020. The Distributed Asynchronous Object Storage (DAOS) is an open-source, scale-out object store designed from the ground up for massively distributed Non-Volatile Memory (NVM). DAOS takes advantage of next-generation NVM technology, like Storage Class Memory (SCM) and NVM express (NVMe), and is extremely lightweight since it operates end-to-end in user space with full OS bypass. DAOS offers a shift away from an I/O model designed for block-based and high-latency storage to one that inherently supports fine-grained data access and unlocks the performance of the next-generation storage technologies. This presentation will introduce the key concepts behind DAOS and the software ecosystem enabling this technology. We will then provide more details on the DAOS deployment on Aurora and how applications will benefit from this new storage tier.

For more information or to register, please visit the URL above.

OpenACC Training Series

April 17, May 28, and June 23

URL: https://www.olcf.ornl.gov/openacc-training-series/

OpenACC is a directive-based approach to parallel programming for heterogeneous architectures, where developers specify regions of code (written in C, C++, and Fortran) to be offloaded from a host CPU to a GPU. This approach is meant to reduce the amount of programming effort required of developers relative to low-level models, such as CUDA.

NVIDIA will present a 3-part OpenACC training series intended to help new and existing GPU programmers learn to use the OpenACC API. Each part will include a 1-hour presentation and example exercises. The exercises are meant to reinforce the material from the presentation and can be completed during a 1-hour hands-on session following each lecture (for in-person participants) or on your own (for remote participants).

For more information or to register, please visit the URL above.

2020 ALCF Computational Performance Workshop

May 5-7, 2020

URL: https://www.alcf.anl.gov/events/2020-alcf-computational-performance-workshop

From May 5–7, 2020, the ALCF will host the annual ALCF Computational Performance Workshop to help researchers achieve computational readiness on ALCF computing resources. Workshop participants will have the opportunity to:

  • Work directly with ALCF and industry professionals during the workshop and dedicated hands-on sessions

  • Explore advanced techniques and tools to enhance code performance and expand your data science skills

  • Benchmark and debug your code with exclusive reservations on ALCF computing systems

  • Prepare for a major allocation award (e.g., INCITE, ALCC, ALCF Data Science Program)

For more information or to register, please visit the URL above.

CUDA Training Series

Monthly in 2020

URL: https://www.olcf.ornl.gov/cuda-training-series/

NVIDIA will present a 9-part CUDA training series intended to help new and existing GPU programmers understand the main concepts of the CUDA platform and its programming model. Each part will include a 1-hour presentation and example exercises. The exercises are meant to reinforce the material from the presentation and can be completed during a 1-hour hands-on session following each lecture (for in-person participants) or on your own (for remote participants).  OLCF and NERSC will both be holding in-person events for each part of the series, where participants can watch the presentations and get help from experts during the hands-on sessions. In-person participants without current Summit or Cori-GPU access will be given temporary accounts to work on the examples.

For more information or to register, please visit the URL above.

2020 GPU Hackathon Series

URL: https://gpuhackathons.org/events

These GPU hackathons are 5-day coding events in which teams of developers prepare their own applications(s) to run on GPUs or focus on optimizing their application(s) that currently run on GPUs. Teams should consist of three or more developers who are intimately familiar with (some part of) their application, and they will work alongside two mentors with GPU programming expertise. If you want/need to get your code running (or optimized) on a GPU-accelerated system, these hackathons offer a unique opportunity to set aside 5 days, surround yourself with experts in the field, and push toward your goals.

TAMIDS Data Science Trainee Program

Posted on by

Overview

Though its Data Science Trainee Program, TAMIDS helps faculty and researchers develop Data Science projects, match interested students to work on them, and provide technical guidance and mentorship during the project.

With the rapid development of information technologies, the applications of data science has dramatically changed various aspects of our society and economy. In responding to this emerging trend,  the Texas A&M Institute of Data Science (TAMIDS) was established to pursue new approaches to data science research, education, operations and partnership at Texas A&M University.

Among all the objectives of TAMIDS, the education of the new generation of researchers that combine their disciplinary competences with data science expertise is of paramount importance. Through collaboration with A&M colleges, research agencies, and industrial partners, the TAMIDS Data Science Trainee Program breaks college boundaries to bring together the expertise and skills from science, engineering, operations, business, health, education, etc. to solve challenging problems while preparing our students for their future career success.

Roles and Registration

We identify three roles – Project Leader, Trainee, and Consultant – in which people can be involved in the program with TAMIDS.

Project Leaders: 

  • Propose Data Science projects by submission here; the proposals are posted online
  • Select and supervise one or more interested trainees to participate in the project
  • Help trainee to acquire domain knowledge needed to conduct the project
  • TAMU Role for Project Leaders: faculty, research staff, post-doc or operations staff

Trainees:

  • Register to participate in the program here and indicate their interest in specific project proposals
  • Participate in proposed project(s)
  • Attend TAMIDS and HPRC training events on Data Science and computing if needed
  • Learn background domain knowledge needed to conduct their project(s)
  • TAMU Role for Trainees: undergraduate or graduate students

Consultants: 

  • Assist Project Leaders with development of project proposals and trainee selection if requested
  • Provide trainee mentorship, project consultancy, and helps with evaluation
  • Consultants can register here
  • TAMU Role for Consultants: faculty, research staff, post-doc, operations staff or graduate students

TAMIDS will support and sustain the Data Science Traineeship Program by (1) managing the program organization; (2) assisting in matching leaders, projects and trainees; (3) organizing Data Science workshops and training programs; (4) helping with project computing and storage resources, and (5) helping develop Data Science courses and curriculum with domain emphases.

We invite A&M faculty, researchers, staff, and students to join this program to promote research, education, service, operations, and outreach in Data Science across Texas A&M. With your involvement and contribution, we will build a vibrant research and education environment for data science at Texas A&M.

Contact Information

For questions about the TAMIDS Data Science Traineeship Program, please contact Dr. Jian Tao, jtao@tamu.edu

TAMIDS Data Science Webinar Series

Posted on by

The Texas A&M Institute of Data Science invites you to attend the TAMIDS Data Science Webinars from Oct 15 to Oct 29, 2019. This webinar series is to introduce the fundamentals of data science (with python) to students and researchers from the Texas A&M University system.

Registration: FREE

More information of the webinars can be found at

https://tinyurl.com/yyxwbzy6

FPGAs in the Era of AI and Big Data

Posted on by

FPGAs in the Era of AI and Big Data

Register

by Lawrence Landis <lawrence.landis@intel.com>

102.B Student Computing Center, Texas A&M University
8:45AM – 5:00PM September 27th, 2019

Description:
Intel Programmable Logic Devices (FPGA) are used in a wide range of applications from industrial electronics, networking and AI acceleration. FPGAs are a staple of Electronic Engineering Curriculums due to their flexibility in describing electronic circuitry without requiring any semiconductor manufacturing tooling costs. Intel’s Programmable Solutions Group FPGA University Program engages with worldwide universities to promote FPGA education and research.

Learning Objectives:

  • At the conclusion of this workshop, you’ll have an understanding of how FPGAs function and common programming models used to implement a variety of FPGA based applications.
  • Register Transfer Language use model using the Verilog Hardware Description Language
  • Network on Chip and IP integration using the Platform Designer Integration tool
  • High Level Language Description through the use of C++ derivative languages like HLS and OpenCL
  • Overlay use models (OpenVino)
  • The student will gain the necessary skills to understand which applications should utilize which programming model to most efficiently balance development time, performance and cost.

Workshop Syllabus:

8:45 Registration
9:00: Lecture: FPGA applications and architecture, Quartus overview
10:00: Lab 1: Introduction to the Quartus Development Tool Suite using Verilog programming
11:15: Lecture: Embedded NIOS and Platform Designer
12:00: Lunch
1:00: Lab2: Embedded NIOS and Platform Designer
2:00: Lecture: High Level Design Usage Model for FPGAs – OpenCL and HLS
2:45: Lab3: High Level Design
3:30: Lecture: OpenVino overlay usage model
4:15: Lab4: OpenVino Vision and Neural Network Heterogeneous Computing
5:00 Conclude Workshop

Workshop Instructions:
The Quartus Lite free tool suite will be required for Labs 1 and 2. Please visit this site: http://fpgasoftware.intel.com/18.1/?edition=lite and install Quartus Prime and MAX 10 libraries.

COE-HPC Offers Special Topic Course on Data Science for Undergraduate Students

Posted on by

With the support from the Texas A&M Institute of Data Science, the Texas Engineering Experiment Station, the Texas A&M High Performance Research Computing, and the Department of Electrical & Computer Engineering, Dr. Jian Tao at COE-HPC will teach a special topic course – ECEN 489 section 504 (CRN 40958) to undergraduate students on various subjects in Data Science in Fall 2019.

The course introduces students to the computational practice of Data Science through a sequence of interactive modules that provide an integrated hands-on approach to its methods, tools, and applications, and supporting technologies including high performance and cloud computing platforms. These modules prepare students for a concurrent semester-long project involving real-world applications of Data Science. The course is aimed both at students who wish to acquire knowledge of Data Science by developing fluency in its applications, and also students with previous exposure to Data Science foundations who wish to develop complementary skills in the use of state of the art systems and tools.

More about the course can be found here.

NVIDIA DLI Deep Learning for Computer Vision Workshop @ Texas A&M University

Posted on by

Description
The NVIDIA Deep Learning Institute (DLI), the Texas A&M Institute of Data Science, the Texas A&M High Performance Research Computing, and the Texas Engineering Experiment Station invite you to attend a hands-on deep learning workshop on September 7th, 2019 from 8:30AM to 5:00PM at the ILSB Auditorium exclusively for verifiable academic students, staff, and researchers. NVIDIA DLI offers hands-on training for developers, data scientists, and researchers looking to solve challenging problems with deep learning and accelerated computing.

Learning Objectives

At the conclusion of the workshop, you’ll have an understanding of the fundamentals of deep learning and be able to:

Implement common deep learning workflows, such as image classification and object detection

Experiment with data, training parameters, network structure, and other strategies to increase performance and capability of neural networks

Integrate and deploy neural networks in your own applications to start solving sophisticated real-world problems

Upon completion of this Lab, you will be able to implement deep learning to solve problems in the real world.

Workshop Outline

08:30 — Registration (refreshments & soft drinks)

09:00 — Introduction

Meet the instructor.

Create an account at courses.nvidia.com/join

09:15 — Unlocking New Capabilities

Learn the biological inspiration behind deep neural networks (DNNs).

Explore training DNNs with big data.

Train neural networks to perform image classification by harnessing the three main ingredients of deep learning: deep neural networks, big data, and the GPU.

10:00 — Break (refreshments & soft drinks)

10:15 — Unlocking New Capabilities and Measuring and Improving Performance

Deploy trained neural networks from their training environment into real applications.

Optimize DNN performance.

Incorporate object detection into your DNNs.

12:00 — Lunch (provided)

13:00 — Final Project

Validate learnings by applying the deep learning application development workflow (load dataset, train, and deploy model) to a new problem.

Learn how to set up your GPU-enabled environment to begin work on your own projects.

Explore additional project ideas and resources to get started with NVIDIA AMI in the cloud, nvidia-docker, and the NVIDIA DIGITS container.

15:00 — Break (refreshments & soft drinks)

15:15 — Final Review

Review key learnings and wrap up questions.

Complete the assessment to earn a certificate.

Take the workshop survey.

16:45 — Wrap-up

Prerequisites:

Familiarity with the basic programming, fundamentals such as functions and variables.

NVIDIA DLI Certification:

Through built-in assessments, participants can earn certification to prove subject matter competency and support professional career growth.

Workshop Setup Instructions:

1. Create an NVIDIA Developer account at http://courses.nvidia.com/join.

2. Make sure that WebSockets works for you:

Test your laptop at http://websocketstest.com

Under ENVIRONMENT, confirm that “WebSockets” is checked yes.

Under WEBSOCKETS (PORT 80), confirm that “Data Receive”, “Data Send”, and “Echo Test” are checked yes.

3. If there are issues with WebSockets, try updating your browser. We recommend Chrome, Firefox, or Safari for an optimal performance.

4. Once onsite, visit http://courses.nvidia.com/dli-event and enter the event code provided by the instructor.

Parking:

If you have a valid A&M parking permit, you can park in the “night and weekend authorized” lots.

http://transportmap.tamu.edu/parkingmap/tsmap.htm?map=naw

COE-HPC Offers Special Topic Course on HPC for Undergraduate Students

Posted on by

With the support from Texas A&M Institute of Data Science, Texas Engineering Experiment Station, and Texas A&M High Performance Research Computing, Dr. Jian Tao at COE-HPC will teach a special topic course – ENGR 489 section 504 (CRN 36736) to undergraduate students on various subjects in High Performance Computing (HPC) and Big Data analytics in Spring 2019.

In this course, students will learn the fundamentals of HPC and parallel programming in a hands-on and project-based manner. In addition, they will build a functional HPC system with Raspberry Pi’s and run some benchmarks and real world applications. Each student will have access to one Raspberry Pi. After spending a week or two to get familiar with the Linux operating system and network management, students will form teams and start building smaller clusters and run some simple benchmarks. An introduction to Python programing language will be given to the students with a focus on its applications in scientific and engineering research. Students will be encouraged to practice computational thinking throughout the course. Two more weeks will be dedicated to introductory level Message Passing Interface (MPI) programming. Students shall then be able to write, compile, and test their MPI programs on their team clusters. By the end of the middle term, students will build a big cluster by linking all the Raspberry Pi’s together. In the next two weeks, students will carry out benchmark runs, discuss scheduling mechanisms to share such a cluster and learn to submit jobs managed by a queuing system. By the end of the semester, students will run some scientific and engineering applications on the cluster and carry out some performance analysis and tuning.

More about the course can be found here.

CALL FOR MATERIALS FOR THE SUPERCOMPUTING CONFERENCE (SC17)

Posted on by

We would like to showcase your HPRC supported computational research at the TAMU HPRC booth during the Supercomputing Conference (SC17) in Denver, Colorado, on Nov 13-16, 2017.

This will be a great opportunity to promote your research to a large audience. SC is the premier conference for high performance computing for academia and industry and attracts engineers and computational scientists from all over the world. In addition, many representatives from funding agencies such as NSF, DOE, and NIH also attend SC. We encourage you to participate in this conference.

Exhibitors include leading companies, national and international research labs, and many top research universities. For reference, there were 349 exhibitors and 11,000+ registered attendees at SC16.

We will use posters and 2 42+” TV displays as medium for showcasing your works. You can contribute in the form of posters, slides/videos, or both.

Submission deadline: Monday, October 2nd, 2017
For submitting slides or videos, wide screen format (16:9) and up to 10 slides are preferred. Please include author/title as a footnote in the slides and caption in the video.
If you would like to submit your work to be presented in poster format:
Submit only an electronic copy of your work to HPRC and we will print all posters.
If the poster file size is less than 5 MB, please email your posters to help@hprc.tamu.edu
For file sizes larger than 5 MB, please upload your file to filex.tamu.edu or place files in your scratch directory on Ada/Terra and then email us the location of your poster files.
Size of poster: 32 inches (wide) x 48 inches (tall)
File format: PDF (preferred) or PowerPoint; please contact us if other format is used
Please use highest image resolution whenever possible
Most conference attendees work in high performance computing fields and/or utilize computing clusters for their research. For the interest of the audience, please include which HPRC cluster you used, software used and typical job size (#cores, memory, and run time).
We will do our best to present your research if we can.

Please contact us at help@hprc.tamu.edu if you have questions.

HPRC

The HeroX Fortran Storytelling Competition

Posted on by

After launching the High Performance Fast Computing Challenge, it came to our attention that the mere mention of the Fortran programming language really resonated with the challenge community! A lot of you started out with Fortran, back when it was still one of the go-to programming languages for calculation-intensive applications like weather prediction, fluid dynamics, and even computational chemistry.

Even though NASA had to reconsider their approach for improving the access-restricted software in the High Performance Fast Computing Challenge, we thought we could still have some fun with this and crowdsource the best stories about our innovators and Fortran. For the sake of history, appreciating our community’s expertise, and just hearing a good story, this challenge will offer a total of up to $1750 split amongst the top three “Fortran” reminiscers!
How to Get Involved

What we’re asking is simple: just turn on your phone camera and start talking!
We’d suggest you structure your 1 to 3 minute video to include:

  • An introduction to yourself and your participation in the “The HeroX Fortran Storytelling Competition”
  • Introduce your background with Fortran:
    • When did you first learn it, and what was the application?
    • How are you using it now? (if at all)
    • How is it a different experience than it was in the beginning?
  • Encourage voters to vote for your video

Prize

The HeroX Fortran Storytelling Competition offers a total prize pool of up to $1,750.  The prizes will be awarded as follows:

  • First Place – $1,000
  • Second Place – $500
  • Third Place – $250

Additionally, winners will be featured in a HeroX blog post and across our social media channels.

How do I win?

To be eligible for an award, your entry must:

  • Include a link to a YouTube or Vimeo video of yourself that is no longer than 3 minutes long.
  • Be in the top 3 at the end of crowd voting!

Voting Scorecard

When voting for your favorite video keep the following guidelines in mind:

Section Description Overall Weight
Unique Story Lot’s of people learned Fortran in a computer science class in college, how is your story different? 25
Original approach Creativity and your unique perspective/approach. 25
Tone A strong, captivating and/or funny voice with lots of personality will get full points. 25
Effort A commitment to quality on behalf of the competitor, such as high production value. 25

Rules

Participation Eligibility:

The challenge is open to all adults (18 years and older, or age of majority), private teams, public teams, and collegiate teams. Teams may originate from any country. Submissions must be made in English. All challenge-related communication will be in English.

To be eligible to compete, you must comply with all the terms of the challenge as defined in the Challenge-Specific Agreement.  Submissions that contain inappropriate or offensive material will be disqualified.

 

Registration and Submissions:

Submissions must be made online (only), via upload to the HeroX.com website, on or before 5:00 pm EDT on June 28, 2017. All submissions will be public on the challenge page once submitted. No late submissions will be accepted.

 

Intellectual Property Rights:

It is not anticipated that participation in this competition will require the sharing of any intellectual property. As detailed in the Challenge-Specific Agreement – Competitors will retain all intellectual property rights to their technology. HeroX may use submissions in future promotional materials.

 

Selection of Winners:

Selected submissions will be made publicly visible for the voting stage. Prizes will be awarded to the submitters who have the top 3 vote totals at the close of the voting period.  All votes are subject to review. Any competitor using unfair methods to solicit votes will be automatically disqualified from the challenge. In the case of a tie, the winner(s) will be selected based on selection by HeroX Judges.

 

Additional Information

  • By participating in the Challenge, each competitor agrees to submit only their original idea. Any indication of “copying” amongst competitors is grounds for disqualification.
  • All applications will go through a process of due diligence; any application found to be misrepresentative, plagiarized, or sharing an idea that is not their own will be automatically disqualified.
  • All ineligible applicants will be automatically removed from the competition with no recourse or reimbursement.
  • No purchase or payment of any kind is necessary to enter or win the competition.
  • Void wherever restricted or prohibited by law.
View legal agreement