Learn how to write a portable parallel program that can run on multicore CPUs and accelerators like GPUs, and how to apply incremental parallelization strategies using the OpenACC programming model to accelerate an example application that simulates heat distribution across a 2-dimensional metal plate and applying this knowledge to accelerate a mini-application.
This event is open to all students and is an opportunity to explore SFU’s Supercomputer Cedar infrastructure. Learn how SFU’s world leading experts can help guide you on your big data journey and harness Cedar for your own research breakthroughs.
Supercomputer Cedar is Canada’s greenest supercomputer for its power efficiency and is in the top 100 in the world for the most powerful GPUs. Cedar is one of five national systems Compute Canada has deployed as part of one of the biggest advanced research computing renewals in Canada’s history.
Simon Fraser University is Canada’s top comprehensive university according to Maclean’s Magazine’s 2021 university rankings. This distinction reflects SFU’s commitment to innovative education, world class research, and deep engagement with our communities, locally and internationally. As Canada’s engaged university, SFU invites international collaboration to address global problems using advances in big data and AI to create innovative and equitable solutions.
The bootcamp will be hosted online in the pacific time zone. All communication will be done through Zoom, Slack and email.
Basic experience with C/C++ or Fortran. No GPU programming knowledge is required.
This event has limited capacity, so please make sure that prerequisites are met before applying. You will be receiving an acceptance email with details on how to participate by November 26, 2020.
Day 1: December 2, 2020
- Welcome: 9:00 AM PDT
- Connecting to a cluster: 9:00 AM - 09:15 AM PDT
- Introduction to GPU programming: 9:15 AM - 9:30 AM PDT (Lecture)
- What is a GPU and Why Should You care?
- What is GPU Programming?
- Available Libraries, Programming Models, Platforms.
- Introduction to OpenACC: 9:15 AM - 10:00 AM PDT (Lecture + Lab)
- What is OpenACC and Why Should You Care?
- Profile-driven Development.
- First Steps with OpenACC.
- Lab 1.
- OpenACC Data Management: 10:00 AM - 10:45 AM PDT (Lecture + Lab)
- CPU and GPU Memories.
- CUDA Unified (Managed) Memory.
- OpenACC Data Management.
- Lab 2.
- Break 11:00 AM - 11:30 AM PDT
- Gangs, Workers, and Vectors Demystified: 11:30 AM - 12:30 PM (Lecture + Lab)
- GPU Profiling.
- Loop Optimizations.
- Lab 3.
Day 2: December 3, 2020
- Mini-application challenge: 9:00 AM - 12PM PDT
- Overview of the mini-application
- Review steps to acceleration
- Application challenge (work in teams of individually)
- Mini-application Solution: 12:00 PM - 1:00 PM PDT
- Walk-through using NVIDIA ® Nsight ™ Tools
- Winner announcement
- Profiling Lab: offline with instructor support through Slack until the end of day December 3rd.
Participants will have access to Simon Fraser University's Supercomputer Cedar is one of the most powerful academic supercomputers in Canada. Cedar provides the scale and capacity that is paving the way for new research breakthroughs.
Cedar provides the computing power Canadian researchers need to achieve transformational innovations that directly benefit Canadians. Just some of these include personalized medicine for better patient care, green technologies to help fight climate change and artificial intelligence research that will contribute to the Canadian economy.
Cedar is one of five national systems Compute Canada has deployed as part of one of the biggest advanced research computing renewals in Canada’s history. https://www.sfu.ca/research/supercomputer-cedar
Important Event Dates
Simon Fraser University’s HPC OpenACC Bootcamp Day 1
Simon Fraser University’s HPC OpenACC Bootcamp Day 2