Parallel Programming for Efficiency
5 credits
Syllabus, Master's level, 1DL560
A revised version of the syllabus is available.
- Code
- 1DL560
- Education cycle
- Second cycle
- Main field(s) of study and in-depth level
- Computer Science A1F, Technology A1F
- Grading system
- Fail (U), Pass (3), Pass with credit (4), Pass with distinction (5)
- Finalised by
- The Faculty Board of Science and Technology, 13 March 2014
- Responsible department
- Department of Information Technology
Entry requirements
120 credits including 60 credits in computer science, including Advanced Computer Architecture and Low-level Parallel Programming.
Learning outcomes
To pass the course the students should be able to
- analyse programs for efficient use of computational resources, including cache, memory bandwidth, CPUs, and energy
- use profiling tools for energy and performance
- apply profiling and optimisation techniques to a program to improve its efficiency
- determine achieved efficiency as a fraction of the system's and application's potential
Content
Introduction to one or more complex, computationally intensive applications. Introduction to profiling and measurement techniques for performance and energy. Optimisation techniques.
Instruction
Online lectures, seminars, project.
Assessment
Oral and written presentation of assignments and project.
Reading list
No reading list found.