Accelerator-Based Programming, 7.5 credits
Academic year 2023/2024
Autumn 2023, 50%, Campus
Start date: 28 August 2023
End date: 30 October 2023
Application deadline: 17 April 2023
Application code: UU-12020 Application
Language of instruction: English
Selection: Higher education credits in science and engineering (maximum 240 credits)
Registration: 28 July 2023 – 4 September 2023
Entry requirements: 120 credits. High Performance and Parallel Computing 7.5 credits or High Performance Programming 10 credits. Proficiency in English equivalent to the Swedish upper secondary course English 6.
If you are not a citizen of a European Union (EU) or European Economic Area (EEA) country, or Switzerland, you are required to pay application or tuition fees. Formal exchange students will be exempted from tuition fees, as well as the application fee. Read more about fees.
Application fee: SEK 900
Tuition fee, first semester: SEK 18,125
Tuition fee, total: SEK 18,125
About the course
Historically, data analysis and computing-related tasks have been executed on the CPU. With increasing data volumes, the interest in using various other computational platforms has increased. One important example of this is the use of GPUs, originally graphics processing units, for machine learning (GPU stands for Graphics Processing Unit).
Sometimes, one can get adequate or even great performance for a specific task by using an existing framework that supports an accelerator, such as a GPU. However, frequently it can be beneficial to write customised accelerator code. In this course, we review various accelerator types and compare them to traditional CPUs. We also explore the CPU/accelerator interface, and how we can program and profile performance on accelerators. Profiling is of uttermost importance in an accelerator context, since it is frequently a great challenge to actually unlock the theoretical gains in efficiency promised by the accelerators.
Department of Information Technology
hus 10, Lägerhyddsvägen 1
Box 337, 751 05 UPPSALA