de | en

Parallelisation of Physics Calculations on GPUs with CUDA

Module PH1351

This module handbook serves to describe contents, learning outcome, methods and examination type as well as linking to current dates for courses and module examination in the respective sections.

Module version of SS 2017 (current)

There are historic module descriptions of this module. A module description is valid until replaced by a newer one.

available module versions
SS 2017SS 2011

Basic Information

PH1351 is a semester module in German or English language at Master’s level which is offered in summer semester.

This Module is included in the following catalogues within the study programs in physics.

  • Catalogue of student seminars for condensed matter physics
  • Catalogue of student seminars for nuclear, particle, and astrophysics
  • Catalogue of student seminars for Biophysics
  • Catalogue of student seminars for Applied and Engineering Physics

If not stated otherwise for export to a non-physics program the student workload is given in the following table.

Total workloadContact hoursCredits (ECTS)
120 h 30 h 4 CP

Responsible coordinator of the module PH1351 is Stefan Recksiegel.

Content, Learning Outcome and Preconditions

Content

Seminar talks and programming projects by students on parallelisation methods on GPUs in computational physics

Learning Outcome

After successful participation in the module the student can implement algorithms from computaional physics on highly parallel processors like GPUs. He/she understands how various parallelisation parameters influence the speed of execution.

Preconditions

Algorithms from Computational Physics (e.g. by simultaneous participation in the lecture Computational Physics II), C programming.

Courses, Learning and Teaching Methods and Literature

Courses and Schedule

TypeSWSTitleLecturer(s)Dates
PS 2 Parallelisation of physics calculations on GPUs with CUDA Recksiegel, S. Thu, 16:00–18:00, PH 1161
and singular or moved dates

Learning and Teaching Methods

The learning outcomes of this module will be developed through the literature search, the study of literature, the programming, the preparation of the presentation, the discussion with the teacher, the talk itself and answering questions about it.

Media

Presentation materials, complementary literature, Computer with CUDA enabled GPU (available in the CIP pool).

Literature

CUDA programming guide by NVIDIA (more info), part 5 and part 6 of GPU Gems 3.

http://users.ph.tum.de/srecksie/lehre/cuda.html

Module Exam

Description of exams and course work

In the course of the seminar each student individually prepares a talk on a topic of current research. Based on this talk the learning outcome is tested.

Current exam dates

Currently TUMonline lists the following exam dates. In addition to the general information above please refer to the current information given during the course.

Title
TimeLocationInfoRegistration
Seminar Talk in Parallelisation of physics calculations on GPUs with CUDA for M.Sc. Students
Mon, 2019-07-22 Dummy-Termin, Leistung wird im Rahmen der Veranstaltung erbracht. // Dummy date. Course work during the semester. till 2019-07-21
Top of page