Difference between revisions of "ASIC Design of a Sigma Point Processor"
From iis-projects
(Created page with "thumb|240px ==Short Description== Numerous applications from the area of wireless communications, robotics or navigation require computationally demanding s...") |
|||
Line 35: | Line 35: | ||
[[Category:Semester Thesis]] | [[Category:Semester Thesis]] | ||
[[Category:Available]] | [[Category:Available]] | ||
− | |||
[[#top|↑ top]] | [[#top|↑ top]] |
Revision as of 15:45, 1 October 2014
Contents
Short Description
Numerous applications from the area of wireless communications, robotics or navigation require computationally demanding signal-processing algorithms, which have to be executed in real-time. Examples include robot positioning or estimation of time-varying radio channels.
Sigma point belief propagation [1] lets one describe these algorithms in a common way. While in a recent master project [2] we demonstrated, how a more restrictive type of belief propagation can be used to build a dedicated processor architecture, the goal of this project is to build a processor for sigma point belief propagation. Application specific processors of this type are serve as an signal-processing accelerator in heterogeneous multicore processors. They offer a unique blend of flexibility and computational performance compared to dedicated hardware implementations or general purpose processors.
You will start by implementing a sigma point processor in Matlab, then implementing and verifying the processor in VHDL. Afterwards you will compare the performance speed-up of your processor against existing designs and start with back-end design. After the back-end, your signal processor ASIC will be fabricated in high-end 65nm CMOS technology.
Status: Available
- Looking for Interested Students
- Supervision: Harald Kröll, Lukas Bruderer
Character
- 20% Theory/Matlab
- 40% ASIC Design
- 40% EDA tools
Prerequisites
- VLSI I
- VLSI II (recommended)
- Matlab, VHDL
Professor