Machine Learning with AMD GPUs and ROCm Software:
January 11: We are happy to inform that this course will be provided for those on waiting list on January 21, 2021
Dec. 17: This course will be provided as ONLINE course (using Microsoft Teams). Preliminary agenda for the ONLINE format.
Participants will be introduced to AMD's Instinct GPU portfolio and ROCm software ecosystem. The course will introduce the configuration of an AMD-based ML environment, along with the use of TensorFlow and PyTorch frameworks in conjunction with AMD GPUs. Exercises for participants will provide hands-on experience with the basics of using ROCm tools. The content will also include an introduction to performance profiling tools for AMD GPUs.
This course provides training in distributed Machine Learning.
Article about the course.
After this course, participants will
13:30 - 14:00 Login and Microsoft Teams setup
14:00 - 14:15 Welcome - HLRS, AMD
14:15 - 14:45 Instinct and ROCm product overview
14:45 - 15:30 ROCm basics
15:30 - 15:35 Pause
15:35 - 16:35 Machine learning with AMD GPUs
16:35 - 16:45 Pause
16:45 - 17:45 Additional ROCm topics
17:45 - 17:50 Pause
17:50 - 18:20 GPU performance profiling
18:20 - 18:30 Closing
Familiarity with TensorFlow and Pytorch will be a plus. Tutorial to explore prior to the course: "Learn and use ML" section: www.tensorflow.org/tutorials, a "Deep Learning with PyTorch" section: pytorch.org/tutorials, and a Python tutorial. In suggested prereading (see below) you will find more AMD material.
Please make sure to have a functioning working environment and remote access for interactive portions of the training prior to the course. In case of questions, please contact the course organizer (see below).
The course language is English.
Derek Bouius (AMD), Will Wang (AMD), and Pak Lui (AMD)
If the course is full, then please register to the waiting list, so that we can inform you when we can provide a second run of this course.
This course is free of charge.
HLRS is part of the Gauss Centre for Supercomputing (GCS), which is one of the six PRACE Advanced Training Centres (PATCs) that started in Feb. 2012.
HLRS is also member of the Baden-Württemberg initiative bwHPC-C5.
This course is provided within the framework of the bwHPC-C5 user Support.
This course is not part of the PATC curriculum and is not sponsored by the PATC program.
This workshop is part of the collaboration between AMD and the Horizon-2020 Centre of Excellence EXCELLERAT. AMD is an EXCELLERAT Interest Group. See also the EXCELLERAT Service Portal for more information.