ECE 69500 - Inference Methods for Codes on Graphs

Note:

Fall 2009 CRN 17907

Course Details

Lecture Hours: 3 Credits: 3

Counts as:

Experimental Course Offered:

Fall 2009

Catalog Description:

We will focus on the recent development for codes on graph, including the encoder/decoder structures, analysis and design tools for the graph-based error correcting codes, and the emerging techniques of network coding for network communications. It will be explored step-by-step the frontier knowledge about achieving the channel/network capacity with efficient implementation. Many applications of the underlying principles will be discussed, including the LDPC source codes, the linear system detectors, and the turbo systems, and intra-session and intersession network coding.

Required Text(s):

  1. General Purpose Graphics Processor Architecture , Aamodt, T.M., Fung, W.L., & Rogers, T.G, , 2018

Recommended Text(s):

  1. Computer Architecture: A Quantitative Approach , 5th Edition , Hennessey and Patterson
  2. Programming Massively Parallel Processors: A Hands-on Approach , 3rd Edition , Kirk, D.B., & Hwu, W.M.W. , Elsevier, Inc. , 2016

Lecture Outline:

Hours Major Topics
1 week General purpose architecture background and the evolution to accelerators Entropy and channel capacity from the detection perspective
2 weeks Programming massively parallel accelerators
1 week Advances in the GPU programming model
3 weeks GPU core design
2 weeks GPU memory system and interconnect
2 weeks CPU/GPU systems and AMD Fusion architecture
1 week Intel Xeon Phi design
1 week Custom and reconfigurable accelerators
2 weeks Case studies on architectures for machine learning

Assessment Method:

none