Low-power, highly reliable dynamic thermal management by exploiting approximate computing
With the continuous downscaling of semiconductor processes, the growing power density and thermal issues in multicore processors become more and more challenging, thus reliable dynamic thermal management (DTM) is required to prevent severe challenges in system performance. The accuracy of the therma...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Institute of Electrical and Electronics Engineers
2020
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/86605/ http://psasir.upm.edu.my/id/eprint/86605/1/Low-power.pdf |
| _version_ | 1848860243273973760 |
|---|---|
| author | Rahimipour, Somayeh Flayyih, Wameedh Nazar Kamsani, Noor Ain Hashim, Shaiful Jahari Stan, Mircea R. Rokhani, Fakhrul Zaman |
| author_facet | Rahimipour, Somayeh Flayyih, Wameedh Nazar Kamsani, Noor Ain Hashim, Shaiful Jahari Stan, Mircea R. Rokhani, Fakhrul Zaman |
| author_sort | Rahimipour, Somayeh |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | With the continuous downscaling of semiconductor processes, the growing power density and thermal issues in multicore processors become more and more challenging, thus reliable dynamic thermal management (DTM) is required to prevent severe challenges in system performance. The accuracy of the thermal profile, delivered to the DTM manager, plays a critical role in the efficiency and reliability of DTM, different sources of noise and variations in deep submicron (DSM) technologies severely affecting the thermal data that can lead to significant degradation of DTM performance. In this article, we propose a novel fault-tolerance scheme exploiting approximate computing to mitigate the DSM effects on DTM efficiency. Approximate computing in hardware design can lead to significant gains in energy efficiency, area, and performance. To exploit this opportunity, there is a need for design abstractions that can systematically incorporate approximation in hardware design which is the main contribution of our work. Our proposed scheme achieves 11.20% lower power consumption, 6.59% smaller area, and 12% reduction in the number of wires, while increasing DTM efficiency by 5.24%. |
| first_indexed | 2025-11-15T12:42:08Z |
| format | Article |
| id | upm-86605 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T12:42:08Z |
| publishDate | 2020 |
| publisher | Institute of Electrical and Electronics Engineers |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-866052021-10-07T20:11:43Z http://psasir.upm.edu.my/id/eprint/86605/ Low-power, highly reliable dynamic thermal management by exploiting approximate computing Rahimipour, Somayeh Flayyih, Wameedh Nazar Kamsani, Noor Ain Hashim, Shaiful Jahari Stan, Mircea R. Rokhani, Fakhrul Zaman With the continuous downscaling of semiconductor processes, the growing power density and thermal issues in multicore processors become more and more challenging, thus reliable dynamic thermal management (DTM) is required to prevent severe challenges in system performance. The accuracy of the thermal profile, delivered to the DTM manager, plays a critical role in the efficiency and reliability of DTM, different sources of noise and variations in deep submicron (DSM) technologies severely affecting the thermal data that can lead to significant degradation of DTM performance. In this article, we propose a novel fault-tolerance scheme exploiting approximate computing to mitigate the DSM effects on DTM efficiency. Approximate computing in hardware design can lead to significant gains in energy efficiency, area, and performance. To exploit this opportunity, there is a need for design abstractions that can systematically incorporate approximation in hardware design which is the main contribution of our work. Our proposed scheme achieves 11.20% lower power consumption, 6.59% smaller area, and 12% reduction in the number of wires, while increasing DTM efficiency by 5.24%. Institute of Electrical and Electronics Engineers 2020-08-12 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/86605/1/Low-power.pdf Rahimipour, Somayeh and Flayyih, Wameedh Nazar and Kamsani, Noor Ain and Hashim, Shaiful Jahari and Stan, Mircea R. and Rokhani, Fakhrul Zaman (2020) Low-power, highly reliable dynamic thermal management by exploiting approximate computing. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 28 (10). 2210 - 2222. ISSN 1063-8210; ESSN: 1557-9999 https://ieeexplore.ieee.org/document/9165819 10.1109/TVLSI.2020.3012626 |
| spellingShingle | Rahimipour, Somayeh Flayyih, Wameedh Nazar Kamsani, Noor Ain Hashim, Shaiful Jahari Stan, Mircea R. Rokhani, Fakhrul Zaman Low-power, highly reliable dynamic thermal management by exploiting approximate computing |
| title | Low-power, highly reliable dynamic thermal management by exploiting approximate computing |
| title_full | Low-power, highly reliable dynamic thermal management by exploiting approximate computing |
| title_fullStr | Low-power, highly reliable dynamic thermal management by exploiting approximate computing |
| title_full_unstemmed | Low-power, highly reliable dynamic thermal management by exploiting approximate computing |
| title_short | Low-power, highly reliable dynamic thermal management by exploiting approximate computing |
| title_sort | low-power, highly reliable dynamic thermal management by exploiting approximate computing |
| url | http://psasir.upm.edu.my/id/eprint/86605/ http://psasir.upm.edu.my/id/eprint/86605/ http://psasir.upm.edu.my/id/eprint/86605/ http://psasir.upm.edu.my/id/eprint/86605/1/Low-power.pdf |