Abstract
Field programmable gate array (FPGA) devices have become widespread in electronic systems due to their low design costs and reconfigurability. In battery-restricted applications such as handheld electronics systems, low-power FPGAs are in great demand. Leakage power almost equals dynamic power in modern integrated circuit technologies, so the reduction of leakage power leads to significant energy savings. We propose a power-efficient architecture for static random access memory (SRAM) based FPGAs, in which two modes (active mode and sleep mode) are defined for each module. In sleep mode, ultra-low leakage power is consumed by the module. The module mode changes dynamically from sleep mode to active mode when module outputs evaluate for new input vectors. After producing the correct outputs, the module returns to sleep mode. The proposed circuit design reduces the leakage power consumption in both active and sleep modes. The proposed low-leakage FPGA architecture is compared with state-of-the-art architectures by implementing Microelectronics Center of North Carolina (MCNC) benchmark circuits on FPGA-SPICE software. Simulation results show an approximately 95% reduction in leakage power consumption in sleep mode. Moreover, the total power consumption (leakage+dynamic power consumption) is reduced by more than 15% compared with that of the best previous design. The average area overhead (4.26%) is less than those of other power-gating designs.
摘要
现场可编程门阵列(FPGA)器件由于其低设计成本和可重构性, 在电子系统中得到广泛应用。在手持电子系统等电池受限的应用中, 低功耗FGPA的需求很大。在现代集成电路技术中, 泄漏功率几乎相当于动态功率, 因此降低泄漏功率可以显著节省能耗。我们提出一种基于静态随机存取存储器(SRAM)的FPGA高效架构, 其中每个模块定义了两种模式(活动模式和休眠模式)。在休眠模式下, 模块消耗超低泄漏功率。当模块输出对新输入向量的评估时, 模块模式由休眠模式动态改变为活动模式。在产生正确的输出后, 该模块返回到休眠模式。所提电路设计在活动模式和休眠模式下都降低了泄漏功耗。通过在FPGA-SPICE软件上实现北卡罗来纳州微电子中心(MCNC)基准电路, 将所提出的低泄漏FPGA体系结构与最先进的体系结构进行比较。仿真结果表明, 休眠模式下泄漏功耗降低约95%。此外, 与以往的最佳设计相比, 总功耗(泄漏功耗+动态功耗)降低15%以上。平均面积开销(4.26%)小于其他电源门控设计。
This is a preview of subscription content, log in via an institution to check access.
References
Ahmed I, Zhao SZ, Trescases O, et al., 2018. Automatic application-specific calibration to enable dynamic voltage scaling in FPGAs. IEEE Trans Comput-Aided Des Integr Circ Syst, 37(12):3095–3108. https://doi.org/10.1109/TCAD.2018.2801222
Ahmed I, Shen JL, Betz V, 2020. Optimizing FPGA logic circuitry for variable voltage supplies. IEEE Trans Very Large Scale Integr Syst, 28(4):890–903. https://doi.org/10.1109/TVLSI.2019.2962501
Ahmed R, Bsoul AAM, Wilton SJE, et al., 2014. High-level synthesis-based design methodology for dynamic power-gated FPGA. Proc 24th Int Conf on Field Programmable Logic and Applications, p.1–4. https://doi.org/10.1109/FPL.2014.6927433
Ahmed R, Wilton SJE, Hallschmid P, et al., 2015. Hierarchical dynamic power-gating in FPGAs. Proc 11th Int Symp on Applied Reconfigurable Computing, p.27–38. https://doi.org/10.1007/978-3-319-16214-0_3
Amara A, Amiel F, Ea T, 2006. FPGA vs. ASIC for low power applications. Microelectron J, 37(8):669–677. https://doi.org/10.1016/j.mejo.2005.11.003
Anderson JH, Najm FN, 2006. Active leakage power optimization for FPGAs. IEEE Trans Comput-Aided Des Integr Circ Syst, 25(3):423–437. https://doi.org/10.1109/TCAD.2005.853692
Anderson JH, Najm FN, 2009. Low-power programmable FPGA routing circuitry. IEEE Trans Very Large Scale Integr Syst, 17(8):1048–1060. https://doi.org/10.1109/TVLSI.2009.2017443
Bsoul AAM, Wilton SJE, 2010. An FPGA architecture supporting dynamically controlled power gating. Int Conf on Field-Programmable Technology, p.1–8. https://doi.org/10.1109/FPT.2010.5681533
Bsoul AAM, Wilton SJE, Tsoi KH, et al., 2016. An FPGA architecture and CAD flow supporting dynamically controlled power gating. IEEE Trans Very Large Scale Integr Syst, 24(1):178–191. https://doi.org/10.1109/TVLSI.2015.2393914
Chen DM, Cong J, Dong C, et al., 2010. Technology mapping and clustering for FPGA architectures with dual supply voltages. IEEE Trans Comput-Aided Des Integr Circ Syst, 29(11):1709–1722. https://doi.org/10.1109/TCAD.2010.2061770
Chen WT, Li L, Lu P, et al., 2016. Design of FPGA’s highspeed and low-power programmable interconnect. Proc 13th IEEE Int Conf on Solid-State and Integrated Circuit Technology, p.707–709. https://doi.org/10.1109/ICSICT.2016.7999018
Colleman S, Verhelst M, 2021. High-utilization, high-flexibility depth-first CNN coprocessor for image pixel processing on FPGA. IEEE Trans Very Large Scale Integr Syst, 29(3):461–471. https://doi.org/10.1109/TVLSI.2020.3046125
Ebrahimi Z, Khaleghi B, Asadi H, 2017. PEAF: a power-efficient architecture for SRAM-based FPGAs using reconfigurable hard logic design in dark silicon era. IEEE Trans Comput, 66(6):982–995. https://doi.org/10.1109/TC.2016.2636141
Hassan H, Anis M, Elmasry M, 2008. Input vector reordering for leakage power reduction in FPGAs. IEEE Trans Comput-Aided Des Integr Circ Syst, 27(9):1555–1564. https://doi.org/10.1109/TCAD.2008.927673
Herath K, Prakash A, Fahmy SA, et al., 2021. Power-efficient mapping of large applications on modern heterogeneous FPGAs. IEEE Trans Comput-Aided Des Integr Circ Syst, 40(12):2508–2521. https://doi.org/10.1109/TCAD.2020.3047722
Huda S, Anderson JH, 2017. Leveraging unused resources for energy optimization of FPGA interconnect. IEEE Trans Very Large Scale Integr Syst, 25(8):2307–2320. https://doi.org/10.1109/TVLSI.2017.2691409
Ishihara S, Hariyama M, Kameyama M, 2011. A low-power FPGA based on autonomous fine-grain power gating. IEEE Trans Very Large Scale Integr Syst, 19(8):1394–1406. https://doi.org/10.1109/TVLSI.2010.2050500
Jahanirad H, 2019. CC-SPRA: correlation coefficients approach for signal probability-based reliability analysis. IEEE Trans Very Large Scale Integr Syst, 27(4):927–939. https://doi.org/10.1109/TVLSI.2018.2886027
Kaur I, Rohilla L, Nagpal A, et al., 2018. Different configuration of low-power memory design using capacitance scaling on 28-nm field-programmable gate array. In: Muttoo SK (Ed.), System and Architecture. Springer, Singapore, p.151–161. https://doi.org/10.1007/978-981-10-8533-8_15
Khaleghi B, Asadi H, 2018. A resistive RAM-based FPGA architecture equipped with efficient programming circuitry. IEEE Trans Circ Syst I Regul Pap, 65(7):2196–2209. https://doi.org/10.1109/TCSI.2017.2778113
Kim S, Na S, Kong BY, et al., 2021. Real-time SSDLite object detection on FPGA. IEEE Trans Very Large Scale Integr Syst, 29(6):1192–1205. https://doi.org/10.1109/TVLSI.2021.3064639
Koppa S, John E, 2018. Performance tradeoffs in the design of low-power SRAM arrays for implantable devices. J Low Power Electron, 14(1):18–27. https://doi.org/10.1166/jolpe.2018.1528
Kumar A, Anis M, 2007. Dual-threshold CAD framework for subthreshold leakage power aware FPGAs. IEEE Trans Comput-Aided Des Integr Circ Syst, 26(1):53–66. https://doi.org/10.1109/TCAD.2006.882595
Kuon I, Rose J, 2007. Measuring the gap between FPGAs and ASICs. IEEE Trans Comput-Aided Des Integr Circ Syst, 26(2):203–215. https://doi.org/10.1109/TCAD.2006.884574
Li F, Lin Y, He L, 2004. Vdd programmability to reduce FPGA interconnect power. IEEE/ACM Int Conf on Computer Aided Design, p.760–765. https://doi.org/10.1109/ICCAD.2004.1382678
Li F, Lin Y, He L, 2007. Field programmability of supply voltages for FPGA power reduction. IEEE Trans Comput-Aided Des Integr Circ Syst, 26(4):752–764. https://doi.org/10.1109/TCAD.2006.884848
Li J, Chow P, Peng YX, et al., 2021. FPGA implementation of an improved OMP for compressive sensing reconstruction. IEEE Trans Very Large Scale Integr Syst, 29(2):259–272. https://doi.org/10.1109/TVLSI.2020.3030906
Lin MJ, El Gamal A, 2009. A low-power field-programmable gate array routing fabric. IEEE Trans Very Large Scale Integr Syst, 17(10):1481–1494. https://doi.org/10.1109/TVLSI.2008.2005098
Lin Y, He L, 2006. Dual-Vdd interconnect with chip-level time slack allocation for FPGA power reduction. IEEE Trans Comput-Aided Des Integr Circ Syst, 25(10):2023–2034. https://doi.org/10.1109/TCAD.2006.870858
Luu J, Goeders J, Wainberg M, et al., 2014. VTR 7.0: next generation architecture and CAD system for FPGAs. ACM Trans Reconfig Technol Syst, 7(2):6. https://doi.org/10.1145/2617593
Ma YF, Cao Y, Vrudhula S, et al., 2018. Optimizing the convolution operation to accelerate deep neural networks on FPGA. IEEE Trans Very Large Scale Integr Syst, 26(7):1354–1367. https://doi.org/10.1109/TVLSI.2018.2815603
Mitra J, Nayak TK, 2018. An FPGA-based phase measurement system. IEEE Trans Very Large Scale Integr Syst, 26(1):133–142. https://doi.org/10.1109/TVLSI.2017.2758807
Nguyen DT, Nguyen TN, Kim H, et al., 2019. A high-throughput and power-efficient FPGA implementation of YOLO CNN for object detection. IEEE Trans Very Large Scale Integr Syst, 27(8):1861–1873. https://doi.org/10.1109/TVLSI.2019.2905242
Nunez-Yanez JL, Hosseinabady M, Beldachi A, 2016. Energy optimization in commercial FPGAs with voltage, frequency and logic scaling. IEEE Trans Comput, 65(5):1484–1493. https://doi.org/10.1109/TC.2015.2435771
Qi H, Ayorinde O, Calhoun BH, 2017. An ultra-low-power FPGA for IoT applications. IEEE SOI-3D-Subthreshold Microelectronics Technology Unified Conf, p. 1–3. https://doi.org/10.1109/S3S.2017.8308753
Rahimi H, Jahanirad H, 2021. An evolutionary approach to implement logic circuits on three dimensional FPGAs. Expert Syst Appl, 174:114780. https://doi.org/10.1016/j.eswa.2021.114780
Ramesh NVK, Uday Kiran K, Reshma NKSVS, et al., 2021. An efficient way to optimize the FPGA routing architecture. Proc 6th Int Conf on Communication and Electronics Systems, p.209–211. https://doi.org/10.1109/ICCES51350.2021.9489142
Ravishankar C, Anderson JH, Kennings A, 2012. FPGA power reduction by guarded evaluation considering logic architecture. IEEE Trans Comput-Aided Des Integr Circ Syst, 31(9):1305–1318. https://doi.org/10.1109/TCAD.2012.2192478
Savari MA, Jahanirad H, 2020. NN-SSTA: a deep neural network approach for statistical static timing analysis. Expert Syst Appl, 149:113309. https://doi.org/10.1016/j.eswa.2020.113309
Seifoori Z, Khaleghi B, Asadi H, 2017. A power gating switch box architecture in routing network of SRAM-based FPGAs in dark silicon era. Design, Automation & Test in Europe Conf & Exhibition, p.1342–1347. https://doi.org/10.23919/DATE.2017.7927201
Seifoori Z, Asadi H, Stojilović M, 2019. A machine learning approach for power gating the FPGA routing network. Int Conf on Field-Programmable Technology, p.10–18. https://doi.org/10.1109/ICFPT47387.2019.00010
Seifoori Z, Asadi H, Stojilović M, 2021. Shrinking FPGA static power via machine learning-based power gating and enhanced routing. IEEE Access, 9:115599–115619. https://doi.org/10.1109/ACCESS.2021.3085005
Seomun J, Shin Y, 2011. Design and optimization of power-gated circuits with autonomous data retention. IEEE Trans Very Large Scale Integr Syst, 19(2):227–236. https://doi.org/10.1109/TVLSI.2009.2033356
Singh P, Reniwal BS, Vijayvargiya V, et al., 2018. Ultra low power-high stability, positive feedback controlled (PFC) 10T SRAM cell for look up table (LUT) design. Integration, 62:1–13. https://doi.org/10.1016/j.vlsi.2018.03.006
Tan BL, Lee WK, Mok KM, et al., 2018. Clock gating implementation on commercial field programmable gate array (FPGA). Proc 4th Int Conf on Electrical, Electronics and System Engineering, p.102–106. https://doi.org/10.1109/ICEESE.2018.8703530
Tang XF, Giacomin E, De Micheli G, et al., 2018. Post-P&R performance and power analysis for RRAM-based FPGAs. IEEE J Emerg Sel Top Circ Syst, 8(3):639–650. https://doi.org/10.1109/JETCAS.2018.2847600
Tang XF, Giacomin E, De Micheli G, et al., 2019. FPGA-SPICE: a simulation-based architecture evaluation framework for FPGAs. IEEE Trans Very Large Scale Integr Syst, 27(3):637–650. https://doi.org/10.1109/TVLSI.2018.2883923
Tatsumura K, Yazdanshenas S, Betz V, 2018. Enhancing FPGAs with magnetic tunnel junction-based block RAMs. ACM Trans Reconfig Technol Syst, 11(1):6. https://doi.org/10.1145/3154425
Tuan T, Rahman A, Das S, et al., 2007. A 90-nm low-power FPGA for battery-powered applications. IEEE Trans Comput-Aided Des Integr Circ Syst, 26(2):296–300. https://doi.org/10.1109/TCAD.2006.885731
Vo MH, 2018. The merged clock gating architecture for low power digital clock application on FPGA. Int Conf on Advanced Technologies for Communications, p.282–286. https://doi.org/10.1109/ATC.2018.8587596
Wagle A, Vrudhula S, 2022. Heterogeneous FPGA architecture using threshold logic gates for improved area, power, and performance. IEEE Trans Comput-Aided Des Integr Circ Syst, 41(6):1855–1867. https://doi.org/10.1109/TCAD.2021.3099780
Zhu JF, Pan LY, Yan YR, et al., 2014. A fast application-based supply voltage optimization method for dual voltage FPGA. IEEE Trans Very Large Scale Integr Syst, 22(12):2629–2634. https://doi.org/10.1109/TVLSI.2013.2296791
Author information
Authors and Affiliations
Corresponding author
Additional information
Compliance with ethics guidelines
Hadi JAHANIRAD declares that he has no conflict of interest.
Data availability
The data that support the findings of this study are available from the author upon reasonable request.
List of supplementary materials
1 Effects of power-domain granularity on energy saving
2 Leakage mechanisms in FPGA
Fig. S1 Internal circuitry of a tile
Fig. S2 A circuit placement and two different granularities
Fig. S3 A typical basic logic element architecture
Table S1 Synthetic circuit properties
Electronic Supplementary Material
Rights and permissions
About this article
Cite this article
Jahanirad, H. Dynamic power-gating for leakage power reduction in FPGAs. Front Inform Technol Electron Eng 24, 582–598 (2023). https://doi.org/10.1631/FITEE.2200084
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1631/FITEE.2200084