Title | ||
---|---|---|
A machine learning-based approach for power and thermal management of next-generation video coding on MPSoCs: work-in-progress |
Abstract | ||
---|---|---|
High Efficiency Video Coding (HEVC) provides high efficiency at the cost of increased computational complexity followed by increased power consumption and temperature of current Multi-Processor Systems-on-Chip (MPSoCs). In this paper, we propose a machine learning-based power and thermal management approach that dynamically learns the best encoder configuration and core frequency for each of the several video streams running in an MPSoC, using information from frame compression, quality performance, total power and temperature. We implement our approach in an enterprise multicore server and compare it against state-of-the-art techniques. Our approach improves video quality and performance by 17% and 11%, respectively, while reducing average temperature by 12%, without degrading compression or increasing power.
|
Year | DOI | Venue |
---|---|---|
2017 | 10.1145/3125502.3125533 | CODES+ISSS |
Keywords | Field | DocType |
HEVC,power/thermal management,machine learning,MPSoC | Computer science,Real-time computing,Coding (social sciences),Artificial intelligence,MPSoC,Video quality,Multi-core processor,Work in process,Parallel computing,Thermal management of electronic devices and systems,Encoder,Machine learning,Computational complexity theory,Embedded system | Conference |
ISBN | Citations | PageRank |
978-1-4503-5185-0 | 1 | 0.43 |
References | Authors | |
7 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Arman Iranfar | 1 | 28 | 4.48 |
marina zapater | 2 | 54 | 10.70 |
D. Atienza | 3 | 182 | 24.26 |