ACES: AI/ML on Intel PVC GPUs

Overview

Instructor: Zhenhua He, Richard Lawrence

Time: Tuesday, March 19, 2024 — 1:30PM-4:00PM CT

Location: online using Zoom

Prerequisites: Current ACCESS ID; basic Linux/Unix skills; basic understanding of machine learning concepts, neural networks, and deep learning; familiarity with deep learning frameworks TensorFlow and/or PyTorch

This course provides an overview of Intel PVC GPUs, guidance on accessing these GPUs on the ACES cluster at Texas A&M High Performance Research Computing, and demonstrations of running AI/ML models with the GPUs using PyTorch and Tensorflow.

Course Materials

Presentation slides

The presentation slides will be available when the course starts.

ACES: Introducing Intel PVC GPUs (Spring 2024) PDF

ACES: Introducing Intel PVC GPUs (Fall 2023) PDF

Participation

Attendees will log in to the cluster during the training session in order to follow examples and complete exercises with the instructor's guidance.

Agenda

Topics covered include:

Intro to Intel PVC
We will introduce Intel's PVC, its architecture, and the PVC GPUs on the TAMU ACES platform.
Demo on ACES
Students will learn how to run models of different frameworks with PVC GPUs on the ACES system.
TensorFlow on PVC
Students will learn how to convert a TensorFlow image classification model to run on a PVC GPU.
PyTorch on PVC
Students will learn how to convert a PyTorch image classification model to run on a PVC GPU.