Abstract
JPEG compression based on the discrete cosine transform (DCT) is a key building block in low-power multimedia applications. We use approximate computing to exploit the error tolerance of JPEG and formulate a novel optimization problem that maximizes power savings under an error budget. We analyze the error propagation sensitivity in the DCT network and use this information to model the impact of introduced errors on the output quality. Simulations show up to 15% reduction in area and delay which corresponds to 40% power savings at iso-delay.
Original language | English (US) |
---|---|
Title of host publication | Proceedings of the 53rd Annual Design Automation Conference, DAC 2016 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
ISBN (Electronic) | 9781450342360 |
DOIs | |
State | Published - Jun 5 2016 |
Event | 53rd Annual ACM IEEE Design Automation Conference, DAC 2016 - Austin, United States Duration: Jun 5 2016 → Jun 9 2016 |
Publication series
Name | Proceedings - Design Automation Conference |
---|---|
Volume | 05-09-June-2016 |
ISSN (Print) | 0738-100X |
Other
Other | 53rd Annual ACM IEEE Design Automation Conference, DAC 2016 |
---|---|
Country/Territory | United States |
City | Austin |
Period | 6/5/16 → 6/9/16 |
Bibliographical note
Publisher Copyright:© 2016 ACM.
Keywords
- Approximate computing
- Image compression
- JPEG
- Low-power design
- Nonlinear optimization