In-Person Workshops

In-person workshops on Thursday, March 3 are an additional $75. When registering for the conference, select the registration option that includes Thursday Workshop. If you decide to add-on a Thursday workshop after you have already registered, please reach out to conference staff (kenkennedy@rice.edu) to update your registration.

The $75 workshop registration includes access to one of the workshops on Thursday (details below). You will be asked to specify your choice during registration.

Thursday, March 3 (8:30 AM – 3:00 PM)

Workshop 1: Best Practices in Supercomputing Systems Management

Speakers: Practitioners and Experts from Industry, Academia, and National Labs

Location: Room 280 (BioScience Research Collaborative)

Schedule:

  • 8:30 AM |  Breakfast
  • 9:00 AM | Introduction – Keith Gray, TGS; Tommy Minyard, TACC
  • 9:05 AM | TACC Update – Tommy Minyard, TACC
  • 10:00 AM | Automation Best Practices – Todd Sayers, Shell
  • 10:30 AM | Break
  • 10:45 AM | DAOS Use at Argonne – Kevin Harms, Argonne; Johann Lombardi, Intel; Mohamad Chaarawi, Intel
  • 11:15 AM | Benchmarking Best Practices – Adam Hough, Shell
  • 11:45 AM | Open Discussion – Organizing Group
  • 12:15 PM | Lunch
  • 1:00 PM | Facilities Best Practices – Kent Blancett, BP; Tommy Minyard, TACC; Ron Cogswell, Shell; David Baldwin, Shell
  • 1:30 PM | Job Scheduler Management – Ron Cogswell, Shell; Guillaume Mangeot, AWS
  • 2:00 PM | Lustre Update – Peter Jones; Andreas Dilger
  • 2:30 PM | Management Toolkits – Luke Wilson, Dell
  • 3:00 PM | Wrap-up

Thursday, March 3 (8:00 AM – 4:15 PM)

Workshop 2: Devito Training and Hackathon

Speakers:

  • Luke Decker, Chevron
  • Pavel Dimitrov, NVIDIA
  • Gerard Gorman, Imperial College London, Devito Codes Ltd
  • Ken Hester, NVIDIA
  • Paul Holzhauer, Devito Codes Ltd
  • Fatmir Hoxha, NVIDIA
  • Chris Leader, Schlumberger
  • Alexander Loddoch, Chevron
  • Fabio Luporini, Devito Codes Ltd
  • Pedro Mario Cruz e Silva, NVIDIA
  • Rhodri Nelson, Imperial College London
  • Osama Qazi, NVIDIA
  • Igor Terentyev, NVIDIA
  • Guillaume Thomas-Collignon, NVIDIA
  • John Washbourne, Chevron
  • Philipp Witte, Microsoft

Location: Auditorium (BioScience Research Collaborative)

Description:

Devito is a domain-specific Language (DSL) and code generation framework for the design of highly optimised finite difference kernels for use in simulation, inversion methods, FWI and RTM. Devito utilises SymPy to allow the definition of operators from high-level symbolic equations and generates optimised software for a wide range of CPU and GPU processors.

The Devito hackathon will consist of two tracks.

  • The training stream will lead participants new to Devito from the development of finite-difference solvers within Devito through to the development of a basic FWI framework that can run on the Cloud.
  • The second track, led by a team from NVidia, will show how to leverage the Devito JIT-backdoor to enable developers to build, debug, profile, and develop class-leading and cutting-edge software that utilizes the latest visual computing hardware from Nvidia. This session profiles the OpenACC code generated by Devito using Nvidia Nsight Compute. It provides detailed performance metrics and API debugging via a command-line tool that is used to target, create, and optimize CUDA kernels for Devito.

The training track will use Jupyter notebook, which can be either installed on the participants’ laptops or run directly on the Azure Cloud instances provided for the workshop. Hackathon participants will have access to a range of Azure CPU and GPU instances for benchmarking and technical support from the Devito team.

To fully engage with the workshop, we recommend:

  • Bring a laptop with a browser.
  • Experience in Python programming.
  • Basic knowledge of Git and a GitHub account.
  • Knowledge of finite differences.

We also encourage participants to join our slack channel to make it easier to respond to individual questions. You can join using the following link https://join.slack.com/t/devitocodes/shared_invite/zt-gtd2yxj9-Y31YKk_7lr9AwfXeL2iMFg

Schedule:

  • 8:00 AM | Check-in and Breakfast
  • 8:30 AM | Welcome and Introductions
  • 9:00 AM -12:00 PM | Parallel sessions:
    • Zero-to-Devito – Developing solvers and imaging with Devito
    • NVidia deep dive into performance benchmarking and optimization
  • 12:00-1:00 PM | Lunch
  • 1:00-2:20 PM | Invited talks from industry
    • Chevron
    • Schlumberger
    • Microsoft
    • NVIDIA
  • 2:20-2:40 PM | Devito Roadmap
  • 2:40-3:00 PM | Break
  • 3:00-4:00 PM | Panel discussion: GSD Panel – comprised of Devito, technology, and Cloud
  • 4:00-4:15 PM | Closing remarks

Fostering relationships and highlighting trends in HPC for the energy industry. #energyhpc