Thermal field reconstruction based on weighted dictionary learning
Abstract Dynamic thermal management (DTM) is applied to address the thermal problem of high performance very‐large‐scale integrated chips. The false alarm rate (FAR) can be used to evaluate the impact of full‐chip thermal field reconstruction accuracy on DTM. A low FAR relies on the accurate reconst...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Hindawi-IET
2022-05-01
|
| Series: | IET Circuits, Devices and Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/cds2.12098 |
| _version_ | 1797426361692848128 |
|---|---|
| author | Tianyi Zhang Wenchang Li Jinyu Xiao Jian Liu |
| author_facet | Tianyi Zhang Wenchang Li Jinyu Xiao Jian Liu |
| author_sort | Tianyi Zhang |
| collection | DOAJ |
| description | Abstract Dynamic thermal management (DTM) is applied to address the thermal problem of high performance very‐large‐scale integrated chips. The false alarm rate (FAR) can be used to evaluate the impact of full‐chip thermal field reconstruction accuracy on DTM. A low FAR relies on the accurate reconstruction of the full thermal field, especially near the temperature triggering threshold of DTM. However, little attention is currently being paid to such temperature ranges. To reduce FAR, a new full‐chip thermal field reconstruction strategy is proposed. A low‐dimensional linear model is used to accurately represent the thermal fields. The dictionary learning technology is exploited to train the model and the minimum weighted mean square error evaluation method is incorporated to improve the reconstruction accuracy near the temperature triggering threshold. A temperature sensor placement algorithm using the heuristic algorithm to solve the NP‐hard problem is also proposed. The experimental results show that the proposed strategy can reconstruct the full thermal field with a more precise accuracy near the triggering threshold and achieve the lowest FAR compared to the state of the art. |
| first_indexed | 2024-03-09T08:29:08Z |
| format | Article |
| id | doaj.art-c4dad366204b495894498ac2ada28436 |
| institution | Directory Open Access Journal |
| issn | 1751-858X 1751-8598 |
| language | English |
| last_indexed | 2024-03-09T08:29:08Z |
| publishDate | 2022-05-01 |
| publisher | Hindawi-IET |
| record_format | Article |
| series | IET Circuits, Devices and Systems |
| spelling | doaj.art-c4dad366204b495894498ac2ada284362023-12-02T20:38:27ZengHindawi-IETIET Circuits, Devices and Systems1751-858X1751-85982022-05-0116322823910.1049/cds2.12098Thermal field reconstruction based on weighted dictionary learningTianyi Zhang0Wenchang Li1Jinyu Xiao2Jian Liu3Key Laboratory of Solid‐State Optoelectronics Information Technology Institute of Semiconductors Chinese Academy of Sciences Beijing ChinaKey Laboratory of Solid‐State Optoelectronics Information Technology Institute of Semiconductors Chinese Academy of Sciences Beijing ChinaCSMC Technologies Corporation Wuxi ChinaUniversity of Chinese Academy of Sciences Beijing ChinaAbstract Dynamic thermal management (DTM) is applied to address the thermal problem of high performance very‐large‐scale integrated chips. The false alarm rate (FAR) can be used to evaluate the impact of full‐chip thermal field reconstruction accuracy on DTM. A low FAR relies on the accurate reconstruction of the full thermal field, especially near the temperature triggering threshold of DTM. However, little attention is currently being paid to such temperature ranges. To reduce FAR, a new full‐chip thermal field reconstruction strategy is proposed. A low‐dimensional linear model is used to accurately represent the thermal fields. The dictionary learning technology is exploited to train the model and the minimum weighted mean square error evaluation method is incorporated to improve the reconstruction accuracy near the temperature triggering threshold. A temperature sensor placement algorithm using the heuristic algorithm to solve the NP‐hard problem is also proposed. The experimental results show that the proposed strategy can reconstruct the full thermal field with a more precise accuracy near the triggering threshold and achieve the lowest FAR compared to the state of the art.https://doi.org/10.1049/cds2.12098computational complexitymean square error methodstemperature sensorssensor placementthermal management (packaging)VLSI |
| spellingShingle | Tianyi Zhang Wenchang Li Jinyu Xiao Jian Liu Thermal field reconstruction based on weighted dictionary learning IET Circuits, Devices and Systems computational complexity mean square error methods temperature sensors sensor placement thermal management (packaging) VLSI |
| title | Thermal field reconstruction based on weighted dictionary learning |
| title_full | Thermal field reconstruction based on weighted dictionary learning |
| title_fullStr | Thermal field reconstruction based on weighted dictionary learning |
| title_full_unstemmed | Thermal field reconstruction based on weighted dictionary learning |
| title_short | Thermal field reconstruction based on weighted dictionary learning |
| title_sort | thermal field reconstruction based on weighted dictionary learning |
| topic | computational complexity mean square error methods temperature sensors sensor placement thermal management (packaging) VLSI |
| url | https://doi.org/10.1049/cds2.12098 |
| work_keys_str_mv | AT tianyizhang thermalfieldreconstructionbasedonweighteddictionarylearning AT wenchangli thermalfieldreconstructionbasedonweighteddictionarylearning AT jinyuxiao thermalfieldreconstructionbasedonweighteddictionarylearning AT jianliu thermalfieldreconstructionbasedonweighteddictionarylearning |