Introduction to GPU programming: When and how to use GPU-acceleration?

Introduction to GPU programming: When and how to use GPU-acceleration?

ATTENTION: If are you looking for the course organized at C3SE, Chalmers, Göteborg in the spring of 2020, then the correct registration page is: https://www.hpc2n.umu.se/events/courses/c3se2020-when-and-how-to-use-gpu-acceleration.

GPU-acceleration has been shown to provide significant performance benefits in many different applications. However, for a novice, or even for a moderately experienced scientist or programmer, it is not always clear which applications could potentially benefit from GPU-acceleration and which do not. For example, a Nvidia V100 GPU can perform artificial intelligence (AI) related computations in a fraction of the time it takes a regular CPU to perform the same computations but ill-informed OpenACC compiler pragma can actually make a code run slower. Why is this? When should one invest time in GPU-acceleration? How much speedup can be expected with a given application?

Purpose: The main goal of this one day course is to start answering these questions. The course also covers the basics of GPU programming and aims to provide the necessary information for avoiding the most common pitfalls.

Requirements: The course does not require any existing GPU programming knowledge but basic understanding of the C language is required for the hands-ons.

Date: 2019-11-05
Time: 9:00-17:00
Location: MC313
Instructors: Mirko Myllykoski
Deadline for registration: 2019-10-29

NOTE This is an old course with some outdated scripts specific to HPC2N. You can find material (including links to recordings of lectures) from a newer, very similar course here: Heterogeneous computing with performance modelling

Schedule

Coffee and tea will be provided. Please bring a laptop for the hands-on. 

Materials

• Example codes: https://git.cs.umu.se/mirkom/gpu_course
• Introduction to the course
• Introduction to HPC2N and Kebnekaise
• GPU hardware and CUDA basics
• Where is my performance?

Registration

Please fill in the below form to sign up. All fields marked with * are required. REGISTRATION CLOSED! Please email bbrydsoe@cs.umu.se or mirkom@cs.umu.se to check if it is still possible to participate.