Abstract | ||
---|---|---|
Recognizing speech, gestures, and visual features are im- portant interface capabilities for embedded mobile sys- tems. Perception algorithms have many traits in common with more conventional media processing applications. The primary motivation for this work is that applications such as real-time, speaker-independent, large-vocabulary, domain-independent continuous speech recognition sys- tems require more performance than is currently avail- able on embedded processors. Even on modern high- performance processors the performance is just barely able to keep up with real-time demands while consuming power at a rate that is well beyond what can be sustained on mobile systems. The solution to this dilemma has tra- ditionally been to design a special ASIC. ASIC design however is both expensive and lacks the generality needed to support dieren t phases of a complex algorithm or even evolutionary improvements to base method. This paper introduces an execution cluster based coprocessor archi- tecture and its CMOS implementation. This is compared against software implementations of algorithms running on a general purpose processor and also against custom ASICs. The cluster achieves an order of magnitude im- provement in energy consumption over a conventional processor while retaining a reasonable level of generality. The architecture is evaluated on several important per- ception applications where energy consumption is shown to improve by a factor of 12-55 times and energy-delay product improves by a factor of 3.8 - 40 times over con- ventional processor approaches. |
Year | Venue | Keywords |
---|---|---|
2003 | ESTIMedia | real time,embedded system,embedded processor |
Field | DocType | Citations |
Computer science,Real-time computing,Coprocessor,Perception,Embedded system | Conference | 4 |
PageRank | References | Authors |
0.91 | 18 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Binu K. Mathew | 1 | 166 | 12.25 |
Al Davis | 2 | 986 | 54.47 |
Ali Ibrahim | 3 | 58 | 5.87 |