Journal of Electrical and Computer Engineering Innovations (JECEI)
مقاله 4 ، دوره 10، شماره 2 ، مهر 2022، صفحه 299-310 اصل مقاله (774.5 K )
نوع مقاله: Original Research Paper
شناسه دیجیتال (DOI): 10.22061/jecei.2021.8253.499
نویسندگان
A. Teymouri 1 ؛ H. Dorosti* 2 ؛ M. Ersali Salehi Nasab 1 ؛ S.M. Fakhraie 1
1 Nano-Electronics Center of Excellence, School of Electrical and Computer Engineering, University of Tehran, Tehran, Iran.
2 Department of Computer Systems Architecture, Faculty of Computer Engineering, Shahid Rajaee Teacher Training University, Tehran, Iran.
تاریخ دریافت : 23 مرداد 1400 ،
تاریخ بازنگری : 29 آبان 1400 ،
تاریخ پذیرش : 30 آبان 1400
چکیده
Background and Objectives: The future demands of multimedia and signal processing applications forced the IC designers to utilize efficient high performance techniques in more complex SoCs to achieve higher computing throughput besides energy/power efficiency improvement. In recent technologies, variation effects and leakage power highly affect the design specifications and designers need to consider these parameters in design time. Considering both challenges as well as boosting the computation throughput makes the design more difficult.Methods: In this article, we propose a simple serial core for higher energy/power efficiency and also utilize data level parallel structures to achieve required computation throughput.Results: Using the proposed core we have 35% (75%) energy (power) improvement and also using parallel structure results in 8x higher throughput. The proposed architecture is able to provide 76 MIPS computation throughput by consuming only 2.7 pj per instruction. The outstanding feature of this processor is its resiliency against the variation effects.Conclusion: Simple serial architecture reduces the effect of variations on design paths, furthermore, the effect of process variation on throughput loss and energy dissipation is negligible and almost zero. Proposed processor architecture is proper for energy/power constrained applications such as internet of things (IoT) and mobile devices to enable easy energy harvesting for longer lifetime.
کلیدواژهها
Massive Parallel Processing ؛ SSTA ؛ Ultra-low-energy ؛ Variation-aware ؛ High-throughput
مراجع
[1] J.L. Hennessy, D.A. Patterson, Computer Architecture: A Quantitative Approach, 4th Edition, San Francisco: Morgan Kaufmann, 2006.
[2] B. Zhai, et al., "Energy-efficient subthreshold processor design," IEEE Trans. Very Large Scale Integr. VLSI Syst., 17: 1127-1137, 2009 .
[3] J.D. Owens, et al., "GPU computing," Proc. IEEE, 96(5): 879-899, 2008 .
[4] K.T. Johnson, et al., "General-purpose systolic arrays," Computer, 26: 20-31, 1993 .
[5] H. Esmaeilzadeh, et al., "Dark silicon and the end of multicore scaling," in Proc. 2011 38th Annual International Symposium on Computer Architecture (ISCA): 365-376, 2011.
[6] M.B. Taylor, "A landscape of the new dark silicon design regime," IEEE Micro, 33(5): 8-19, 2013 .
[7] S.R. Sarangi, et al., "VARIUS: A model of process variation and resulting timing errors for microarchitects," IEEE Trans. Semicond. Manuf., 21: 3-13, 2008 .
[8] J. Crop, et al., "Design automation methodology for improving the variability of synthesized digital circuits operating in the sub/near-threshold regime," in Proc. 2011 International Green Computing Conference and Workshops (IGCC): 1-6, 2011.
[9] L. Nazhandali, et al., "Energy optimization of subthreshold-voltage sensor network processors," in Proc. 32nd International Symposium on Computer Architecture (ISCA'05): 197-207, 2005.
[10] J. Constantin, et al., "TamaRISC-CS: An ultra-low-power application-specific processor for compressed sensing," in Proc. 2012 IEEE/IFIP 20th International Conference on VLSI and System-on-Chip (VLSI-SoC): 159-164, 2012.
[11] J.H.F. Constantin, "Application-specific processor design for low-complexity & low-power embedded systems," in Winter School on Design Technologies for Heterogeneous Embedded Systems (FETCH), 2013.
[12] R. Pawlowski, et al., "A 530mV 10-lane SIMD processor with variation resiliency in 45nm SOI," in Proc. 2012 IEEE International Solid-State Circuits Conference (ISSCC), 2012 .
[13] K. Ma, et al., "Architecture exploration for ambient energy harvesting nonvolatile processors," in Proc. IEEE 21st International symposium on High Performance Computer Architecture (HPCA), 2015 .
[14] Z. Wang, et al., "An energy-efficient heterogeneous dual-core processor for internet of things," in Proc. IEEE International Symposium on Circuits and Systems (ISCAS), 2015 .
[15] Y. Kim, D. Shin, J. Lee, Y. Lee, H. J. Yoo, "14.3 A 0.55V 1.1mW artificial intelligence processor with PVT compensation for micro robots," in proc. IEEE International Solid-State Circuits Conference (ISSCC), 2016 .
[16] H. Cherupalli, R. Kumar, J. Sartori, "Exploiting dynamic timing slack for energy efficiency in ultra-low-power embedded systems," in Proc. IEEE International Symposium on Computrer Architecture, 2016 .
[17] G.K. konstadinidis, et al., "SPARC M7: A 20nm 32-Core 64MB L3 Cache Processor," IEEE J. Solid-State Circuits, 51(1): 79-91, 2016 .
[18] M. Tomei, H. Duwe, N.S. Kim, R. Kumar, "Bit serializing a microprocessor for ultra-low-power," in Proc. ISLPED 2016: 200–205, 2016.
[19] C. Kelly, V. Ekanayake, R. Manohar, "SNAP: A sensor-network asynchronous processor," in Proc. Ninth International Symposium on Asynchronous Circuits and Systems: 24-33, 2013.
[20] R. Uytterhoeven, W. Dehaene, "A Sub 10 pJ/Cycle Over a 2 to 200 MHz Performance Range RISC-V Microprocessor in 28nm FDSOI," in Proc. IEEE 44thEuropean Solid-State Circuits Conference (ESSCIRC), 2018 .
[21] V. Kartsch, M. Guermandi, S. Benatti, F. Montagna, L. Benini, "An Energy-Efficient IoT node for HMI applications based on an ultra-low power multicore processor," in Proc. IEEE Sensors Applications Symposium (SAS), 2019 .
[22] M. Eggimann, S. Mach, M. Magno, L. Benini, "A risc-v based open hardware platform for always-on wearable smart sensing," in Proc. IEEE 8thInternational Workshop Advances in Sensors and Interfaces (IWASI), 2019 .
[23] B. Soltani, H. Dorosti, M.E. Salehi, S.M. Fakhraie., "Ultra-low-energy DSP processor design for many-core parallel applications," J. Electr. Comput. Eng. Innovations, 8 (1): 71-84, 2019 .
[24] H. Dorosti, et al., "Ultralow-energy variation-aware design: adder architecture study," IEEE Trans. Very Large Scale Integr. VLSI Syst. (TVLSI), 24(3): 1165-1168, 2016 .
[25] M. Wang, N. Yu, W. Ma, Q. Sheng, W. Zhang, Z. Huang, " An ultra low-power processor with dynamic regfile configuration," in Proc. 2018 IEEE International Conference on Solid-State and Integrated Circuits Technology (ICSICT): 1-3, 2018.
[26] P. Meinerzhagen, S.M. Sherazi, A. Burg, J.N. Rodrigues, “Benchmarking of standard-cell based memories in the sub-vt domain in 65-nm CMOS technology,” IEEE J. Emerging Sel. Top. Circuits Syst., 1(2): 173-182, 2011.
[27] L. Nazhandali, M. Minuth, T. Austin, "Sensebench: toward an accurate evaluation of sensor network processors," in Proc. 2005 IEEE Workload Characterization Symposium: 197-203, 2005.
[28] S. Yin, P. Ouyang, J. Yang, T. Lu, X. Li, L. Liu, S. Wei, "An ultra-high energy-efficient reconfigurable processor for deep neural networks with binary/ternary weights in 28nm CMOS," in Proc. IEEE Symposium on VLSI Circuits: 37-38, 2018.
[29] A. Wang, B.H. Calhoun, A.P. Chandrakasan, Design for Ultra Low-Power Systems, New York: Springer, 2006.
[30] B. Zhai, S. Pant, L. Nazhandali, S. Hanson, J. Olson, A. Reeves, M. Minuth, R. Helfand, T. Austin, D. Sylvester, D. Blaauw, “Energy-efficient subthreshold processor design,” IEEE Trans. Very Large Scale Integr. VLSI Syst., 17 (8): 1127-1137, 2009.
آمار
تعداد مشاهده مقاله: 355
تعداد دریافت فایل اصل مقاله: 266