因應嵌入式系統的應用程式日漸複雜，三維可重組態可程式邏輯閘陣列逐漸被應用至嵌入式系統以增加運算能力。然而，三維堆疊的架構造成熱能管理難以解決。本論文提出熱感知任務放置法，透過任務功率及完成時間分類來降低系統溫度進而維持系統穩定性；並提出執行時期對調高功率任務與低功率任務來冷卻系統，以提供系統執行更多任務。經過一連串實驗分析，發現提出的演算法能有效降低系統溫度。

Partial reconfigurable three-dimensional field programmable gate arrays are promising innovations for meeting the demand of implementing embedded systems demonstrating high area efficiency and excellent performance. However, thermal management has become a critical concern in three-dimensional integrated systems; this is because high system temperatures degrade system performance. This study proposes online thermal-aware task allocation algorithms for minimizing the system temperature under area constraints for both column-based and CLB-based three-dimensional field programmable gate array. In addition, an online thermal-aware swap algorithm is proposed for cooling the system through task reconfiguration for improving the system utilization. The thermal efficiency and run-time overhead of the proposed methodology was evaluated using a series of workloads, and impressive results were obtained.

[1] XILINX, http://www.xilinx.com/, 7 Series FPGAs Packaging and Pinout,
2012.
[2] XILINX, http://www.xilinx.com/, Partial Reconfiguration of Xilinx FPGAs
Using ISE Design Suite, 2012.
[3] XILINX, http://www.xilinx.com/, Virtex-6 FPGA Packagingand Pinout
Specifications, 2011.
[4] XILINX, http://www.xilinx.com/, Lowering Power at 28 nm with Xilinx 7
Series Devices, 2012.
[5] XILINX, http://www.xilinx.com/, Xilinx Stacked Silicon Interconnect Technology
Delivers Breakthrough FPGA Capacity, Bandwidth, and Power Efficiency,
2012.
[6] C. Hong, K. Benkrid, X. Iturbe, A. Ebrahim, and T. Arslan, “Efficient onchip
task scheduler and allocator for reconfigurable operating systems,” Embedded
Systems Letters, IEEE, vol. 3, no. 3, pp. 85–88, 2011.
[7] C. Hong, K. Benkrid, X. Iturbe, A. T. Erdogan, and T. Arslan, “An fpga
task allocator with preliminary first-fit 2d packing algorithms,” in Adaptive
Hardware and Systems (AHS), 2011 NASA/ESA Conference on, pp. 264–
270, IEEE, 2011.
[8] W. Hu, C. Wang, J. Ma, T. Chen, and D. Chen, “A novel approach for finding
candidate locations for online fpga placement,” in Computer and Information
Technology (CIT), 2010 IEEE 10th International Conference on,
pp. 2509–2515, IEEE, 2010.
[9] T. Marconi, Y. Lu, K. Bertels, and G. Gaydadjiev, “Online hardware task
scheduling and placement algorithm on partially reconfigurable devices,” in
Reconfigurable Computing: Architectures, Tools and Applications, pp. 306–
311, Springer, 2008.
[10] P.-H. Yuh, C.-L. Yang, and Y.-W. Chang, “T-trees: A tree-based representation
for temporal and three-dimensional floorplanning,” ACM Transactions
on Design Automation of Electronic Systems (TODAES), vol. 14, no. 4, p. 51,
2009.
27
[11] T. Marconi, Y. Lu, K. Bertels, and G. Gaydadjiev, “3d compaction: A novel
blocking-aware algorithm for online hardware task scheduling and placement
on 2d partially reconfigurable devices,” in Reconfigurable Computing:
Architectures, Tools and Applications, pp. 194–206, Springer, 2010.
[12] T.-H. Lin, P. Banerjee, and Y.-W. Chang, “An efficient and effective analytical
placer for fpgas,” in Proceedings of the 50th Annual Design Automation
Conference, p. 10, ACM, 2013.
[13] T.-Y. Lee, N.-Y. Lin, W.-C. Chen, and H. Wu, “An efficient task placement
method for reconfigurable fpga systems,” in Complex, Intelligent, and Software
Intensive Systems (CISIS), 2013 Seventh International Conference on,
pp. 451–455, IEEE, 2013.
[14] J.-W. Hsieh, Y.-H. Chang, and W.-L. Lee, “An enhanced leakage-aware
scheduler for dynamically reconfigurable fpgas,” in Proceedings of the 16th
Asia and South Pacific Design Automation Conference, pp. 661–667, IEEE
Press, 2011.
[15] A. Al-Wattar, S. Areibi, and F. Saffih, “Efficient on-line hardware/software
task scheduling for dynamic run-time reconfigurable systems,” in Parallel
and Distributed Processing Symposium Workshops & PhD Forum
(IPDPSW), 2012 IEEE 26th International, pp. 401–406, IEEE, 2012.
[16] Y. Lu, T. Marconi, K. Bertels, and G. Gaydadjiev, “A communication aware
online task scheduling algorithm for fpga-based partially reconfigurable systems,”
in Field-Programmable Custom Computing Machines (FCCM), 2010
18th IEEE Annual International Symposium on, pp. 65–68, IEEE, 2010.
[17] X. Iturbe, K. Benkrid, T. Arslan, I. Martinez, and M. Azkarate, “Atb: Areatime
response balancing algorithm for scheduling real-time hardware tasks,”
in Field-Programmable Technology (FPT), 2010 International Conference
on, pp. 224–232, IEEE, 2010.
[18] K. Siozios and D. Soudris, “A novel algorithm for temperature-aware placement
and routing on 3d fpgas,” in International Conference on VLSI and
System-on-Chip, 2008.
[19] A. Gayasen, V. Narayanan, M. Kandemir, and A. Rahman, “Designing a
3-d fpga: Switch box architecture and thermal issues,” Very Large Scale
Integration (VLSI) Systems, IEEE, vol. 16, pp. 882–893, July 2008.
28
[20] H. A. Clarke and K. Murakami, “Thermal effect of tsvs in 3d die-stacked
integrated circuits,” in Digital System Design (DSD), 2011 14th Euromicro
Conference on, pp. 503–508, IEEE, 2011.
[21] S. Pasricha, “A framework for tsv serialization-aware synthesis of application
specific 3d networks-on-chip,” in VLSI Design (VLSID), 2012 25th International
Conference on, pp. 268–273, IEEE, 2012.
[22] K. Wang, S. Dong, Y. Ma, G. Satoshi, and J. Cong, “Leakage-aware
performance-driven tsv-planning based on network flow algorithmin 3d ics,”
in Quality Electronic Design (ISQED), 2012 13th International Symposium
on, pp. 129–136, IEEE, 2012.
[23] B. Shi, C. Serafy, and A. Srivastava, “Co-optimization of tsv assignment
and micro-channel placement for 3d-ics,” in Proceedings of the 23rd ACM
international conference on Great lakes symposium on VLSI, pp. 337–338,
ACM, 2013.
[24] B. Shi, A. Srivastava, and P. Wang, “Non-uniform micro-channel design for
stacked 3d-ics,” in Proceedings of the 48th Design Automation Conference,
pp. 658–663, ACM, 2011.
[25] Y.-W. Wang and Y.-S. Chen, “On-line thermal-aware task management for
three-dimensional dynamically partially reconfigurable systems,” in Embedded
and Real-Time Computing Systems and Applications (RTCSA), 2013
IEEE 19th International Conference on, pp. 111–120, IEEE, 2013.
[26] J. Li, M. Qiu, J. Hu, and E. H.-M. Sha, “Thermal-aware rotation scheduling
for 3d multi-core with timing constraint,” in Signal Processing Systems
(SIPS), 2010 IEEE Workshop on, pp. 323–326, IEEE, 2010.
[27] E. McDonald, “Runtime fpga partial reconfiguration,” in IEEE Aerospace
Conference, pp. 1–7, March 2008.
[28] XILINX, “Kintex-7 fpgas data sheet.” http://www.xilinx.com/,
February 2015.
[29] XILINX, “Power methodology guide.” http://www.xilinx.com/,
April 2013.
[30] S. Jang, D.Wu,M. Jarvin, B. Chan, K. Chung, A.Mishchenko, and R. Brayton,
“Smartopt: an industrial strength framework for logic synthesis,” in
Proceedings of the ACM/SIGDA international symposium on Field programmable
gate arrays, pp. 237–240, ACM, 2009.