TY - GEN
T1 - Understanding the thermal challenges of high-performance mobile devices with a detailed platform temperature model
AU - Yu, Ying Ju
AU - Wu, Carole-Jean
N1 - Funding Information:
The authors would like to thank the anonymous reviewers for their useful feedback. This work is supported in part by the National Science Foundation (under grants for the I/UCRC Center for Embedded Systems #1361926, CNS #1358805, CCF #1525462, and CCF #1652132).
Funding Information:
VI. SUMMARY In this paper, we characterized the thermal response of real-world, representative mobile workloads and then used the response to calibrate the temperature prediction model. The thermal model offers accurate prediction accuracies of 90% for hot spots at the processor die and at the platform surface. Also, we used the thermal model to explore alternative construction choices. As the air gap increases, the processor temperature rises significantly. We hope the work presented in this paper can motivate advanced thermal management for high-performance embedded platforms. ACKNOWLEDGMENT The authors would like to thank the anonymous reviewers for their useful feedback. This work is supported in part by the National Science Foundation (under grants for the I/UCRC Center for Embedded Systems #1361926, CNS #1358805, CCF #1525462, and CCF #1652132).
Publisher Copyright:
© 2017 IEEE.
PY - 2017/12/5
Y1 - 2017/12/5
N2 - Modern high-performance electronics are embedded in smartphones, self-driving automobiles, and augmented reality wearable. These computing platforms are high performance and multifunctional. One of the major performance limiting factors in these platforms is the poorly designed thermal solution that is triggered to prevent overheating at the processor transistor junction and at the platform surface. Even though the dynamic voltage and frequency scaling (DVFS) feature widely available in modern processors can be used as a control knob in processor temperature management, its associated performance cost is tremendous and the response time for temperature control is significant.
AB - Modern high-performance electronics are embedded in smartphones, self-driving automobiles, and augmented reality wearable. These computing platforms are high performance and multifunctional. One of the major performance limiting factors in these platforms is the poorly designed thermal solution that is triggered to prevent overheating at the processor transistor junction and at the platform surface. Even though the dynamic voltage and frequency scaling (DVFS) feature widely available in modern processors can be used as a control knob in processor temperature management, its associated performance cost is tremendous and the response time for temperature control is significant.
UR - http://www.scopus.com/inward/record.url?scp=85046530377&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85046530377&partnerID=8YFLogxK
U2 - 10.1109/IISWC.2017.8167768
DO - 10.1109/IISWC.2017.8167768
M3 - Conference contribution
AN - SCOPUS:85046530377
T3 - Proceedings of the 2017 IEEE International Symposium on Workload Characterization, IISWC 2017
SP - 122
EP - 123
BT - Proceedings of the 2017 IEEE International Symposium on Workload Characterization, IISWC 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 IEEE International Symposium on Workload Characterization, IISWC 2017
Y2 - 1 October 2017 through 3 October 2017
ER -