Skip to content
Technische Universität Berlin Deutsch
Course catalog and module transfer system

GPU ComputingModule description #41201 / Version 3

← Module page Deutsche Fassung
Module / Version#41201 / #3
ValiditySince Winter semester 2026/27
Available language(s)English, German
Credit points6
Person responsible for the moduleSteuwer, Michel
GradingGraded
Exam formatPortfolio examination
Language(s) of instructionEnglish

Affiliation

FacultyFakultät IV
InstituteInstitut für Softwaretechnik und Theoretische Informatik
Academic chair34353200 FG Programmiersprachen

Contact

OfficeEN 21
Contact personSteuwer, Michel
E-mail addresslehre@compl.tu-berlin.de
Websitehttps://www.tu.berlin/compl/studium-lehre

Learning outcomes

On completion of this course, the student will be able to:
* understand the architecture of modern GPUs
* write error-free software for GPUs performing data-parallel computations
* reason about the performance of GPU software
* applying optimizations to improve the performance of GPU software

Content

In this course, students learn about modern GPU computing, with an emphasis on using GPUs for computational-intensive and data-parallel problems. Students will gain theoretical knowledge about GPU hardware as well as practical skills in writing high-performance GPU software.

* Modern GPU hardware
* Throughput oriented computing vs. latency oriented computing
* Data-parallel computational problems
* GPU programming model
* GPU programming with mainstream GPU programming languages
* Common Bugs in GPU computing
* Reasoning about performance of GPU software
* Performance optimizations
* GPU programming with domain-specific approaches

Module components

Compulsory area

The following courses are mandatory for this module:

CoursesTypeNumberFrequencyLanguageHours per weekCourse catalog
GPU ComputingLecture Winter and summer semester[en]2 ISIS
GPU ComputingInternship Winter and summer semester[en]4 ISIS

Workload and credit points

GPU Computing (Lecture)

Workload descriptionMultiplierHoursTotal
Attendance152 h30 h
Pre/post processing152 h30 h
60 h

GPU Computing (Internship)

Workload descriptionMultiplierHoursTotal
Attendance154 h60 h
Pre/post processing154 h60 h
120 h

The workload of the module adds up to 180 hours. The module therefore comprises 6 credit points.

Description of teaching and learning methods

This module consists of a weekly lecture that teaches the foundations of GPU computing. The main components of this module are practical courseworks in which the students will work under supervision in a lab to practice their GPU computing skills, as well as a final practical project where each student implements and optimizes a full GPU application.

Requirements for participation and examination

Desirable prerequisites for participation in the courses:

Solid programming skills in a language with explicit memory management (e.g., C/C++ or Rust), as well as a good understanding of computer architecture are required.

Mandatory requirements for the module examination registration:

This module has no examination requirements.

Completion of the module

GradingGraded
Exam formatPortfolio examination
Type of portfolio examination100 points in total
LanguageEnglish, German

Test elements

NamePoints/WeightCategoryDuration/Extent
(Learning process review) Courseworks30practical40 hours
(Deliverable assessment) Practical Project60practical75 hours
(Examination) Practical Project Presentation10oral10 minutes

Exam description

During the first part of the semester, students will work in the Lab on courseworks exercising their GPU computing skills.
These weekly courseworks will be graded.
For the last 4 weeks, the students will be working individually on implementing and optimizing a full GPU application.
Finally, the students present their projects in the form of a poster and a 10-minute oral presentation.

Duration of the module

The following number of semesters is estimated for taking and completing the module: 1 semester(s).

This module can be started in the following semesters: Winter and summer semester.

Maximum number of participants

The maximum capacity of participants is 30.

Registration procedures

See https://www.tu.berlin/compl/studium-lehre as well as the information given in the first lecture.

Recommended reading, lecture notes

Lecture notes

unavailable

Electronic lecture notes

unavailable

Recommended literature

No recommended literature given

Assigned programs

This module version is used in the following programs:

Program / program versionSemester(s)Curriculum component
Computer Engineering
Computer Engineering (M. Sc.) - StuPO 2015
WS 2026/27Wahlpflichtbereich › Studiengebiet A › Eingebettete Systeme und Rechnerarchitekturen / Embedded Systems and Computer Architectures
Computer Science
Computer Science (B. Sc.) - StuPO 2025
WS 2026/27Wahlpflichtbereich › Studiengebiete › Rechensysteme › Weitere Module
Computer Science (Informatik)
Computer Science (Informatik) (M. Sc.) - StuPO 2015
WS 2026/27Wahlpflichtbereich › Studiengebiet › Eingebettete Systeme und Rechnerarchitekturen / Embedded Systems and Computer Architectures
Electrical Engineering
Electrical Engineering (M. Sc.) - StuPO 2015
WS 2026/27Wahlpflichtbereich › Studiengebiete Fak. IV › Eingebettete Systeme und Rechnerarchitekturen / Embedded Systems and Computer Architectures

Miscellaneous

Not specified