新型FPGA架构和电路设计技术展望

范继聪; 于宗光; 谢达; 单悦尔; 徐仲延

doi:10.20193/j.ices2097-4191.2025.0016

PDF(18224 KB)

集成电路与嵌入式系统 ›› 2025, Vol. 25 ›› Issue (6) : 14-28. DOI: 10.20193/j.ices2097-4191.2025.0016

FPGA前沿技术与应用研究专刊

新型FPGA架构和电路设计技术展望

作者信息 +

Perspectives of novel FPGA architectures and circuit design technologies

Author information +

文章历史 +

摘要

与定制设计芯片相比,现场可编程门阵列(FPGA)支持硬件灵活重构,具有设计周期短和开发成本低等优势,广泛应用于通信、数据中心、人工智能、雷达和航空航天等领域。FPGA架构的设计目标是制造出高度可编程的FPGA芯片,同时最小化可重构性带来的面积和性能成本。随着应用需求和工艺技术能力的不断演变,正在迎来 FPGA 架构设计的新阶段。简述FPGA基本架构与FPGA架构评估,梳理新型FPGA架构和电路设计技术最新进展,探讨新型FPGA架构和电路设计的技术挑战和发展趋势。

Abstract

Compared to custom-designed chips, Field Programmable Gate Arrays (FPGAs) support flexible hardware reconfiguration and offer advantages such as shorter design cycles and lower development costs. They are widely used in fields such as communications, data centers, radar, and aerospace. The design of FPGA architectures aims to create highly programmable FPGA chips while minimizing the area and performance costs associated with reconfigurability. With the continuous evolution of application demands and process technology capabilities, FPGA architecture design is entering a new phase. This article briefly describes the basic architecture of FPGA with its evaluation, summarizes the latest developments in novel FPGA architectures and circuit design technologies, and discusses the technical challenges and development trends of novel FPGA architectures and circuit design.

导出引用

范继聪, 于宗光, 谢达, 等. 新型FPGA架构和电路设计技术展望[J]. 集成电路与嵌入式系统. 2025, 25(6): 14-28 https://doi.org/10.20193/j.ices2097-4191.2025.0016

FAN Jicong, YU Zongguang, XIE Da, et al. Perspectives of novel FPGA architectures and circuit design technologies[J]. Integrated Circuits and Embedded Systems. 2025, 25(6): 14-28 https://doi.org/10.20193/j.ices2097-4191.2025.0016

中图分类号： TN474

参考文献

列表( 原文顺序 | 文献年度倒序 | 文中引用次数倒序 ) 可视化分析

[1]	MURRAY K E, PETELIN O, ZHONG S, et al. VTR 8:High-performance CAD and customizable FPGA architecture modelling[J]. ACM Trans. Reconfigurable Technol. Syst., 2020, 13(2):1-55. 本文引用 [1]

[2]	BOUTROS A, GRADY B, ABBAS M, et al. Build fast, trade fast: FPGA-based high-frequency trading using high-level synthesis[C]// 2017 International Conference on ReConFigurable Computing and FPGAs (ReConFig),Cancun,Mexico, 2017:1-6. 本文引用 [1]

[3]	LEWIS D, CHIU G, CHROMCZAK J, et al. The Stratix10 highly pipelined FPGA architecture[C]// Proceedings of the 2016 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA '16).Association for Computing Machinery,New York,NY,USA, 2016:159-168. 本文引用 [1]

[4]	Intel. Intel Stratix 10 NX FPGA:AI-optimized FPGA for high-bandwidth,low-latency AI acceleration (SS-1121-1.0), 2020. 本文引用 [1]

[5]	KAPRE N, GRAY J. Hoplite:A deflection-routed directional torus NoC for FPGAs[J]. ACM Trans. Reconfigurable Technol. Syst. (TRETS), 2017, 10(2):1-24. 本文引用 [1]

[6]	WANG Z Y, SUN J B, GOKSOY A, et al. Exploiting 2.5D/3D heterogeneous integration for AI computing[C]// Proceedings of the 29th Asia and South Pacific Design Automation Conference. New York: IEEE, 2024:758-764. 本文引用 [1]

[7]	PUTNAM A, CAULFIELD A M, CHUNG E S, et al. A reconfigurable fabric for accelerating large-scale datacenter services[C]// Proc. ACM/IEEE Int. Symp. Comput. Architecture (ISCA), 2014:13-24. 本文引用 [1]

[8]	FOWERS J, OVTCHAROV K, PAPAMICHAEL M, et al. A Configurable Cloud-Scale DNN Processor for Real-Time AI[C]// 2018 ACM/IEEE 45th Annual International Symposium on Computer Architecture (ISCA),Los Angeles,CA,USA, 2018:1-14. 本文引用 [1]

[9]	BOUTROS A, YAZDANSHENAS S, BETZ V. You Cannot Improve What You Do not Measure: FPGA vs. ASIC Efficiency Gaps for Convolutional Neural Network Inference[J]. ACM Trans. Reconfigurable Technol. Syst. (TRETS), 2018, 11(3):1-23. 本文引用 [2]

[10]	TESSIER R, BETZ V, NETO D, et al. Power-efficient RAM mapping algorithms for FPGA embedded memory blocks[J]. IEEE Trans. Computer-Aided Design Integrated Circuits Syst., 2007, 26(2):278-290. 本文引用 [1]

[11]	BOUTROS A, BETZ V. FPGA Architecture: Principles and Progression[M]. IEEE Circuits and Systems Magazine, 2021, 21(2):4-29. 本文引用 [7]

[12]	LI F, LIN Y, HE L, et al. Power modeling and characteristics of field programmable gate arrays[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2005, 24(11):1712-1724. 本文引用 [1]

[13]	蔡宏瑞, 范继聪, 徐彦峰, 等. 一种改进型可配置逻辑块的结构设计[J]. 电子与封装, 2022, 22(11):110308. CAI H R, FAN J C, XU Y F, et al. Structural design of an imprived configurable logic block[J]. Electronics & Packaging, 2022, 22(11):110308. (in Chinese) 本文引用 [1]

[14]	YANG S. Logic Synthesis and Optimization Benchmarks User Guide:Version 3.0. Microelectronics Center of North Carolina, 1991. 本文引用 [1]

[15]	MURRAY K E, ELGAMMAL A, BETZ V, et al. SymbiFlow and VPR: An Open-Source Design Flow for Commercial and Novel FPGAs[J]. IEEE Micro, 2020, 40(4):49-57. 本文引用 [1]

[16]	MURRAY K E, WHITTY S, LIU S, et al. Titan: enabling large and complex benchmarks in academic CAD[C]// 2013 23rd International Conference on Field programmable Logic and Applications,Porto,Portugal, 2013:1-8. 本文引用 [1]

[17]	WONG H Y, CHENG L R, LIN Y, et al. FPGA device and architecture evaluation considering process variations[C]// ICCAD-2005. IEEE/ACM International Conference on Computer-Aided Design,San Jose,CA,USA, 2005:19-24. 本文引用 [1]

[18]	CARTER W, DUONG I, FREMAN R, et al. A user programmable reconfiguration gate array[C]// Proceedings of the IEEE Custom Integrated Circuits Conference, 1986:233-235. 本文引用 [2]

[19]	Xilinx. Ultrascale architecture configurable logic block user guide. UG574 (v1.5), 2017. 本文引用 [1]

[20]	Xilinx. Zynq-7000 all programmable soc technical reference manual. UG585(v1.21.1), 2017. 本文引用 [1]

[21]	GAIDE B, GAITONDE D, RAVISHANKAR C, et al. Xilinx Adaptive Compute Acceleration Platform: Versal Architecture[J]. Proc. ACM/SIGDA Int. Symp. Field-Programmable Gate Arrays (FPGA), 2019:84-93. 本文引用 [3]

[22]	BETZ V, ROSE J, MARQUARDT A. Architecture and CAD for Deep-Submicron FPGAs[M]. Springer Science & Business Media, 1999. 本文引用 [1]

[23]	AHMED E, ROSE J. The effect of LUT and cluster size on deep submicron FPGA performance and density[J]. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2004, 12(3):288-298. 本文引用 [2]

[24]	Altera Corp. Stratix II Device Handbook,Volume 1 (SII5V1-4.5)[Z], 2007. 本文引用 [1]

[25]	LEWIS D, AHMED E, BAECKLER G, et al. The Stratix II logic and routing architecture[C]// Proc. ACM/SIGDA Int. Symp. Field-Programmable Gate Arrays (FPGA), 2005:14-20. 本文引用 [2]

[26]	Xilinx Inc. Versal ACAP Configurable Logic Block Architecture Manual (AM005 v1.0), 2020. 本文引用 [1]

[27]	CHIASSON C, BETZ V. Should FPGAs abandon the pass gate?[C]// Proc. Int. Conf. Field-Programmable Logic Appl., 2013:1-8. 本文引用 [1]

[28]	FlexLogix. FlexLogix eFPGA[EB/OL].[2025-04]. https://flex-logix.com/efpga/. https://flex-logix.com/efpga/ 本文引用 [1]

[29]	WILTON S J E. Architectures and Algorithms for Field-Programmable Gate Arrays with Embedded Memories[D]. University of Toronto, 1997. 本文引用 [1]

[30]	SADOWSKA M M, WU Y L. Orthogonal greedy coupling—anew optimization approach for 2-D field-programmable gate arrays[C]// 32nd Design Automation Conference, San Francisco,CA,USA, 1995:568-573. 本文引用 [1]

[31]	LONGA P, MIRI A. Area-efficient FIR filter design on FPGAs using distributed arithmetic[C]// 2006 IEEE International Symposium on Signal Processing and Information Technology,Vancouver,BC,Canada, 2006:248-252. 本文引用 [1]

[32]	MEHER P K, CHANDRASEKARAN S, AMIRA A. FPGA realization of FIR Filters by efficient and flexible systolization using distributed arithmetic[J]. IEEE Trans. Signal Process., 2008, 56(7):3009-3017. 本文引用 [1]

[33]	Xilinx Inc. Virtex-5 FPGA XtremeDSP Design Considerations (UG193 v3.6), 2017. 本文引用 [1]

[34]	Xilinx Inc. Virtex-6 FPGA DSP48E1 Slice (UG369 v1.3), 2011. 本文引用 [1]

[35]	Xilinx Inc. UltraScale Architecture DSP Slice (UG579 v1.9), 2019. 本文引用 [1]

[36]	AFSHAR H P, LENNE P. Highly versatile DSP blocks for improved FPGA arithmetic performance[C]// Proc. IEEE Int. Symp. Field Programmable Custom Computing Mach.(FCCM), 2010:229-236. 本文引用 [1]

[37]	CEVRERO A, ATHANASOPOULOS P, AFSHAR H P, et al. Field programmable compressor trees:Acceleration of multi-input addition on FPGAs[J]. ACM Trans. Reconfigurable Technol. Syst. (TRETS), 2009, 2(2):1-36. 本文引用 [1]

[38]	LANGHAMMER M, PASCA B. Floating-point DSP block architecture for FPGAs[C]// Proc. ACM/SIGDA Int. Symp. Field-Programmable Gate Arrays (FPGA), 2015:117-125. 本文引用 [1]

[39]	AHMAD S, SUBRAMANIAN S, BOPPANA V, et al. Xilinx First 7nm device:Versal AI core (VC1902)[C]// 2019 IEEE Hot Chips 31 Symposium (HCS),Cupertino,CA,USA, 2019:1-28. 本文引用 [1]

[40]	GYSEL P, MOTAMEDI M, GHIASI S. Hardware-oriented approximation of convolutional neural networks[OL]. 2016,arXiv:1604.03168. 本文引用 [1]

[41]	MELLEMPUDI N, KUNDU A, DAS D, et al. Mixed low-precision deep learning inference using dynamic fixed point[OL]. 2017,arXiv:1701.08978. 本文引用 [1]

[42]	MISHRA A, NURVITADHI E, COOK J J, et al. WRPN:Wide reduced-precision networks[OL]. 2017, arXiv:1709.01134. 本文引用 [1]

[43]	RASOULINEZHAD S R, ZHOU H, WANG L L, et al. PIR-DSP: An FPGA DSP block architecture for multi-precision deep neural networks[C]// 2019 IEEE 27th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM),San Diego,CA,USA, 2019:35-44. 本文引用 [1]

[44]	Intel Corp. Intel Agilex variable precision DSP blocks user guide (UG 20213), 2020. 本文引用 [1]

[45]

TYHACH

, WANG

, SUNG

, et al. A 90 nm FPGA I/O buffer design with 1.6 Gbps data rate for source-synchronous system and 300 MHz clock rate for external memory interface[C]// Proceedings of the IEEE 2004 Custom Integrated Circuits Conference (IEEE Cat. No.04CH37571),Orlando,FL,USA, 2004,:431-434.

本文引用 [1]

[46]	ZHANG N, WANG X, TANG H, et al. Low-voltage and high-speed FPGA I/O cell design in 90nm CMOS[C]// 2009 IEEE 8th International Conference on ASIC,Changsha, China, 2009:533-536. 本文引用 [1]

[47]	QIAN T T, CHEN L, LI X W, et al. A 1.25 Gbps programmable FPGA I/O buffer with multi standard support[C]// 2018 IEEE 3rd International Conference on Integrated Circuits and Microsystems (ICICM),Shanghai,China, 2018:362-365. 本文引用 [1]

[48]	Ultrascale architecture clocking resources (UG572 v1.7)[Z]. Xilinx Inc, 2018. 本文引用 [1]

[49]	NASIRI E, SHAIKH J, PEREIRA A H, et al. Multiple dice working as one: CAD flows and routing architectures for silicon interposer FPGAs[J]. IEEE Trans. Very Large Scale Integr. (VLSI) Syst., 2015, 24(5):1821-1834. 本文引用 [1]

[50]	CHAWARE R, NAGARAJAN K, RAMALINGAM S. Assembly and reliability challenges in 3D integration of 28nm FPGA die on a large high density 65nm passive interposer[C]// 2012 IEEE 62nd Electronic Components and Technology Conference, San Diego,CA,USA, 2012:279-283. 本文引用 [1]

[51]	NURVITADHI E, COOK J, MISHRA A, et al. In-package domain-specific ASICs for intel Stratix 10 FPGAs: A case study of accelerating deep learning using tensortile ASIC[C]// 2018 28th International Conference on Field Programmable Logic and Applications (FPL),Dublin,Ireland, 2018:106-1064. 本文引用 [1]

[52]	NURVITADHI E, KWON D, LAFARI A, et al. Evaluating and Enhancing Intel Stratix 10 FPGAs for persistent real-time AI[C]// Proc. ACM/SIGDA Int. Symp. Field-Programmable Gate Arrays (FPGA), 2019:119. 本文引用 [1]

[53]	NURVITADHI E, KWON D, LAFARI A, et al. Why compete when you can work together: FPGA ASIC integration for persistent RNNs[C]// 2019 IEEE 27th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), San Diego,CA,USA, 2019:199-207. 本文引用 [1]

[54]	WU S Y, LIN C Y, CHIANG M C, et al. A 7 nm CMOS platform technology featuring 4th generation FinFET transistors with a 0.027 um² high density 6-T SRAM cell for mobile SoC applications[C]// 2016 IEEE International Electron Devices Meeting (IEDM),San Francisco,CA,USA, 2016:2.6.1-2.6.4. 本文引用 [1]

[55]

YEAP

, LIN

S S

, CHEN

Y M

, et al. 5 nm CMOS production technology platform featuring full-fledged EUV,and high mobility channel FinFETs with densest 0.021 μm² SRAM cells for mobile SoC and high performance computing applications[C]// 2019 IEEE International Electron Devices Meeting (IEDM),San Francisco,CA,USA, 2019:36.7.1-36.7.4.

本文引用 [1]

[56]	NIKOLIC S, CATTHOOR F, TOKEI Z, et al. Global Is the New Local: FPGA Architecture at 5nm and Beyond[C]// The 2021 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA '21).Association for Computing Machinery,New York,NY,USA, 34-44. 本文引用 [3]

[57]	GARROU P, BOWER C, RAMM P. Handbook of 3-D Integration: Technology and Applications of 3-D Integrated Circuits[M]. 1st ed. Hoboken,NJ: Wiley, 2008. 本文引用 [1]

[58]	FENG J, LIU Y, GRIFFIN P B, et al. Integration of germanium-on-insulator and silicon MOSFETs on a silicon substrate[J]. IEEE Electron Device Letters, 2006, 27(11):911-913. 本文引用 [1]

[59]	BATUDE P, ERNST T, ARCAMONE J, et al. 3-D Sequential Integration:A Key Enabling Technology for Heterogeneous Co-Integration of New Function With CMOS[J]. IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 2012, 2(4):714-722. 本文引用 [5]

[60]	SZE V, CHEN Y H, YANG T J, et al. Efficient processing of deep neural networks: A tutorial and survey[J]. Proceedings of the IEEE, 2017, 105(12):2295-2329. 本文引用 [1]

[61]

BOUTROS

, ELDAFRAWY

, YAZDANSHENAS

, et al. Math Doesn’t Have to be Hard: Logic Block Architectures to Enhance Low-Precision Multiply-Accumulate on FPGAs[C]// Proceedings of the 2019 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA '19).Association for Computing Machinery,New York,NY,USA, 2029:94-103.

本文引用 [3]

[62]	LI Y G, LI X, SHEN H B, et al. An All-digital Compute-in-memory FPGA Architecture for Deep Learning Acceleration[J]. ACM Trans. Reconfigurable Technol. Syst. 204, 17(18):1-27. 本文引用 [1]

[63]

GUO

L C

, CHI

Y Z

, WANG

, et al. Autobridge: Coupling coarse-grained floorplanning and pipelining for high-frequency HLS design on multi-die fpgas[C]// The 2021 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays(FPGA '21).Association for Computing Machinery,New York,NY,USA, 2021:81-92.

本文引用 [1]

[64]	YE H C, HAO C, CHENG J Y, et al. ScaleHLS: Scalable High-Level Synthesis through MLIR[OL]. arXiv preprint arXiv:2107.11673(2021). 本文引用 [1]

[65]	GUO L C, LAU J, CHI Y Z, et al. Analysis and Optimization of the Implicit Broadcasts in FPGA HLS to Improve Maximum Frequency[C]// 2020 57th ACM/IEEE Design Automation Conference (DAC),San Francisco,CA,USA, 2020:1-6. 本文引用 [1]

[66]	TANG X F, GIACOMIN E, CHAUVIERE B, et al. OpenFPGA:An Open-Source Framework for Agile Prototyping Customizable FPGAs[J]. IEEE Micro, 2020, 40(4):41-48. 本文引用 [1]

[67]	TANG X F, GORE G, GIACOMIN E, et al. Openfpga:towards automated prototyping for versatile fpgas,Workshop on Open-Source EDA Technology, 2020. 本文引用 [1]