Difference between revisions of "ASIC Design of a Gaussian Message Passing Processor"
From iis-projects
Line 25: | Line 25: | ||
==Links== | ==Links== | ||
[1] [http://arxiv.org/abs/1404.3162 A Signal Processor for Gaussian Message Passing] | [1] [http://arxiv.org/abs/1404.3162 A Signal Processor for Gaussian Message Passing] | ||
+ | |||
+ | <!-- | ||
+ | |||
+ | COPY PASTE FROM THE LIST BELOW TO ADD TO CATEGORIES | ||
+ | |||
+ | GROUP | ||
+ | --->[[Category:Digital]]<!-- | ||
+ | [[Category:Analog]] | ||
+ | [[Category:Nano-TCAD]] | ||
+ | [[Category:Nano Electronics]] | ||
+ | |||
+ | STATUS | ||
+ | --->[[Category:Available]]<!-- | ||
+ | [[Category:In progress]] | ||
+ | [[Category:Completed]] | ||
+ | [[Category:Hot]] | ||
+ | |||
+ | TYPE OF WORK | ||
+ | --->[[Category:Semester Thesis]]<!-- | ||
+ | --->[[Category:Master Thesis]]<!-- | ||
+ | [[Category:PhD Thesis]] | ||
+ | [[Category:Research]] | ||
+ | |||
+ | NAMES OF EU/CTI/NT PROJECTS | ||
+ | [[Category:UltrasoundToGo]] | ||
+ | [[Category:IcySoC]] | ||
+ | [[Category:PSocrates]] | ||
+ | [[Category:UlpSoC]] | ||
+ | [[Category:Qcrypt]] | ||
+ | [[Category:PULP]] | ||
+ | [[Category:ArmaSuisse]] | ||
+ | |||
+ | YEAR (IF FINISHED) | ||
+ | [[Category:2010]] | ||
+ | [[Category:2011]] | ||
+ | [[Category:2012]] | ||
+ | [[Category:2013]] | ||
+ | [[Category:2014]] | ||
+ | |||
+ | ---> |
Revision as of 16:04, 15 April 2014
Contents
Short Description
Gaussian Message Passing can be used to formulate a wide range of real-world signal processing algorithms such as channel-estimation, equalization or time of arrival estimation. Recently we demonstrated, how a systolic array can be used to build a processor architecture to efficiently run such algorithms [1]. A specific processor of this type is usually attached as a fixed-function-unit to a heterogeneous multicore processor.
The goal of this project is to build an ASIC design of the processor architecture. You will start by optimizing the existing VHDL and Matlab model and extend it with a single instruction, multiple data (SIMD) operation mode. Then you will compare the performance speed-up for parallel execution against the existing architecture and start with the back-end design. After the back-end, the final ASIC will be fabricated in high-end CMOS technology.
Status: Available
- Looking for Interested Students
- Supervision: Harald Kroell, Lukas Bruderer
Character
- 20% Theory/Matlab
- 40% ASIC Design
- 40% EDA tools
Prerequisites
- VLSI I
- VLSI II (recommended)
- Matlab, VHDL
Professor