SuperLectures.com

DATA-PATH AND MEMORY ERROR COMPENSATION TECHNIQUE FOR LOW POWER JPEG IMPLEMENTATION

DSP Algorithm and Architecture Optimization for Hardware Implementation

Full Paper at IEEE Xplore

Přednášející: Chaitali Chakrabarti, Autoři: Yunus Emre, Chaitali Chakrabarti, Arizona State University, United States

The paper presents a novel technique to mitigate effects of data-path and memory errors in JPEG implementations. These errors are mainly caused by voltage scaling and process variation in scaled technologies. We characterize the data-path and memory errors and derive a probability distribution of the total number of errors. We propose an algorithm-specific technique that corrects most errors after the quantization step in JPEG encoder by exploiting the characteristics of the quantized coefficients. Simulation results show that the proposed technique has a PSNR performance degradation of around 1.5 dB compared to the error-free case and 4 dB improvement compared to the no correction case at 0.75 bpp when BER=10^(-4). This is achieved with small circuitry overhead and no memory overhead.


  Přepis řeči

|

  Slajdy

Zvětšit slajd | Zobrazit všechny slajdy

0:00:16

  1. slajd

0:01:10

  2. slajd

0:01:34

  3. slajd

0:03:00

  4. slajd

0:04:39

  5. slajd

0:05:39

  6. slajd

0:06:11

  7. slajd

0:07:39

  8. slajd

0:09:30

  9. slajd

0:09:58

 10. slajd

0:10:37

 11. slajd

0:11:26

 12. slajd

0:13:26

 13. slajd

0:13:49

 14. slajd

0:14:19

 15. slajd

  Komentáře

Please sign in to post your comment!

  Informace o přednášce

Nahráno: 2011-05-26 14:45 - 15:05, Club H
Přidáno: 9. 6. 2011 23:29
Počet zhlédnutí: 24
Rozlišení videa: 1024x576 px, 512x288 px
Délka videa: 0:16:30
Audio stopa: MP3 [5.63 MB], 0:16:30