CNP: An FPGA-based processor for Convolutional Networks
The DOI matches its Crossref record; 16 of the 17 references it cites were found in a registry or an index.
Abstract
Convolutional networks (ConvNets) are biologically inspired hierarchical architectures that can be trained to perform a variety of detection, recognition and segmentation tasks. ConvNets have a feed-forward architecture consisting of multiple linear convolution filters interspersed with pointwise non-linear squashing functions. This paper presents an efficient implementation of ConvNets on a low-end DSP-oriented field programmable gate array (FPGA). The implementation exploits the inherent parallelism of ConvNets and takes full advantage of multiple hardware multiply accumulate units on the FPGA. The entire system uses a single FPGA with an external memory module, and no extra parts. A network compiler software was implemented, which takes a description of a trained ConvNet and compiles it into a sequence of instructions for the ConvNet Processor (CNP). A ConvNet face detection system was implemented and tested. Face detection on a 512 times 384 frame takes 100 ms (10 frames per second), which corresponds to an average performance of 3.4 times 109connections per second for this 340 million connection network. The design can be used for low-power, lightweight embedded vision systems for micro-UAVs and other small robots.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Another option is to use field programable gate arrays (FPGAs), which consume much less energy than GPUs while providing an intermediate computing efficiency between CPUs and GPUs13–17.”
From Hardware implementation of memristor-based artificial neural networks (2024) · cites this paper as [13]
In the citing paper
“Also, CNN can be deployed in medical image classification [114], [115], traffic scenes related classification [116], [117], etc. [118], [119]”
From A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects (2022) · cites this paper as [116]
Citations
Cites
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 4×
“The design is specifically geared towards Convolutional Networks [1, 2], but can be used for many similar architectures based on local filter banks and classifiers, such as HMAX [3, 4], and HoG methods [5].”
BackgroundMethodInfluentialSelf-citationHistograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584 · cited 1×
“The design is specifically geared towards Convolutional Networks [1, 2], but can be used for many similar architectures based on local filter banks and classifiers, such as HMAX [3, 4], and HoG methods [5].”
MethodRapid object detection using a boosted cascade of simple features
Viola, P., & Jones, M. (2005) · Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 · doi:10.1109/cvpr.2001.990517 · Cited by 18,300
GradientBased Learning Applied to Document Recognition
(2009) · Intelligent Signal Processing · doi:10.1109/9780470544976.ch9 · Cited by 1,135 · cited 5×
“This paper presents a self-contained, high performance implementation of Convolutional Networks on a single FPGA.”
BackgroundMethodInfluentialUnsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition
Ranzato, M., Huang, F. J., Boureau, Y.-L., & LeCun, Y. (2007) · 2007 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2007.383157 · Cited by 1,086 · cited 1×
“ConvNets are used in several commercial and experimental applications, including video surveillance, OCR [2], face/person detection [6, 7], object recognition [8], and robot navigation [9, 10].”
MethodSelf-citationGeneralization and network design strategies
LeCun, Y. (1989) · Cited by 885
Self-citationObject Recognition with Features Inspired by Visual Cortex
Serre, T., Wolf, L., & Poggio, T. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.254 · Cited by 821 · cited 1×
“The design is specifically geared towards Convolutional Networks [1, 2], but can be used for many similar architectures based on local filter banks and classifiers, such as HMAX [3, 4], and HoG methods [5].”
MethodConvolutional face finder: a neural architecture for fast and robust face detection
Garcia, C., & Delakis, M. (2004) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2004.97 · Cited by 547 · cited 3×
“The architecture of the network is quite similar to those described in [6, 7].”
MethodMulticlass Object Recognition with Sparse, Localized Features
Mutch, J., & Lowe, D. G. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1 (CVPR'06) · doi:10.1109/cvpr.2006.200 · Cited by 453 · cited 1×
“The design is specifically geared towards Convolutional Networks [1, 2], but can be used for many similar architectures based on local filter banks and classifiers, such as HMAX [3, 4], and HoG methods [5].”
Method(2005) · neural information processing systems · Cited by 446
Self-citation
Research works printed but not linked: 1
- shoup, 1994, parameterized convolution filtering in a field programmable gate array, Selected papers from the Oxford 1993 international workshop on field programmable logic and applications on More FPGAs, 274
Cited by
Items 101–200 of 423
Srivastava, P., Kang, M., Gonugondla, S. K., Lim, S., Choi, J., Adve, V., Kim, N. S., & Shanbhag, N. (2018) · 2018 ACM/IEEE 45th Annual International Symposium on Computer Architecture (ISCA) · doi:10.1109/isca.2018.00015 · Cited by 55
“TH implements non-linear operations such as sigmoid via piece-wise linear approximation [27] not only to compute the decision functions f () in Table I but also to aggregate intermediate computed values when the vector length N is larger than 128.”
MethodFarrukh, F. U. D., Zhang, C., Jiang, Y., Zhang, Z., Wang, Z., Wang, Z., & Jiang, H. (2020) · IEEE Open Journal of Circuits and Systems · doi:10.1109/ojcas.2020.3007334 · Cited by 67
“These applications include autonomous vehicles, smart robots and camera technologies, and surveillance [7]–[10].”
BackgroundAn FPGA-based stream processor for embedded real-time vision with Convolutional Networks
Farabet, C., Poulet, C., & LeCun, Y. (2009) · 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops · doi:10.1109/iccvw.2009.5457611 · Cited by 50
“Our system can also be implemented in a low-end FPGA (Xilinx Spartan-3A DSP, as first introduced in [5]) and still reach decent performances.”
MethodSelf-citationBridge the Gap between Neural Networks and Neuromorphic Hardware with a Neural Network Compiler
Ji, Y., Zhang, Y., Chen, W., & Xie, Y. (2018) · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · doi:10.1145/3173162.3173205 · Cited by 64
Energy-efficient and high-throughput FPGA-based accelerator for Convolutional Neural Networks
Feng, G., Hu, Z., Chen, S., & Wu, F. (2016) · IEEE International Conference on Solid-State and Integrated Circuit Technology · doi:10.1109/icsict.2016.7998996 · Cited by 63
“The bottlenecks of FPGA-based CNN can be eliminated by atom arithmetic level of legitimately planning operations like addition, multiplication [5][8], and advanced high-level optimization of parallelizing loops, increasing bandwidth with scheduled hardware resources [6][9].”
MethodCamuñas-Mesa, L. A., Acosta, A. J., Zamarreño-Ramos, C., Serrano‐Gotarredona, T., & Linares-Barranco, B. (2010) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2010.2078851 · Cited by 63
“Frame-based ConvNet Hardware Implementations are being developed by other groups [76]–[78].”
BackgroundFPGA‐accelerated deep convolutional neural networks for high throughput and energy efficiency
Qiao, Y., Shen, J., Xiao, T., Yang, Q., Wen, M., & Zhang, C. (2016) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.3850 · Cited by 62
“With respect to consistency, traditional works [4, 9, 10] design different accelerating units for different parts of CNNs.”
BackgroundA High Throughput Acceleration for Hybrid Neural Networks With Efficient Resource Management on FPGA
Yin, S., Tang, S., Lin, X., Ouyang, P., Tu, F., Liu, L., & Wei, S. (2018) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2018.2821561 · Cited by 60
Double MAC on a DSP: Boosting the Performance of Convolutional Neural Networks on FPGAs
Lee, S., Kim, D. W., Nguyen, D. T., & Lee, J. (2018) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2018.2824280 · Cited by 61
“If one chooses, for instance, R and C loops [34] instead of M and N, the first layer will scale much better.”
BackgroundDouble MAC: Doubling the performance of convolutional neural networks on modern FPGAs
Nguyen, D. T., Kim, D. W., & Lee, J. (2017) · Design, Automation, and Test in Europe · doi:10.23919/date.2017.7927113 · Cited by 58
“If one chooses, for instance, R and C loops [8], [9] instead of M and N , the first layer will scale much better.”
BackgroundEfficient Object Detection Framework and Hardware Architecture for Remote Sensing Images
Li, L., Zhang, S., & Wu, J. (2019) · Remote Sensing · doi:10.3390/rs11202376 · Cited by 58
“proposed CNP [35] with parallel vector computing architecture for low-power lightweight unmanned aircraft vehicles (UAVs) or robots, and a scalable dataflow 2-D grid hardware architecture Neuflow [36] optimized for the computation of general-purpose vision algorithms.”
Optimally Scheduling CNN Convolutions for Efficient Memory AccessPreprint
Stoutchinin, A., Conti, F., & Benini, L. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.01492 · Cited by 56
Real-Time Underwater Image Recognition with FPGA Embedded System for Convolutional Neural Network
Zhao, M., Hu, C., Wei, F., Wang, K., Wang, C., & Jiang, Y. (2019) · Sensors · doi:10.3390/s19020350 · Cited by 55
Memristor crossbar based multicore neuromorphic processors
Taha, T. M., Hasan, R., & Yakopcic, C. (2014) · IEEE International System-on-Chip Conference (SOCC) · doi:10.1109/socc.2014.6948959 · Cited by 54
Customizing Neural Networks for Efficient FPGA Implementation
Samragh, M., Ghasemzadeh, M., & Koushanfar, F. (2017) · IEEE International Symposium on Field-Programmable Custom Computing Machines (FCCM) · doi:10.1109/fccm.2017.43 · Cited by 54
“Since FPGAs are promising platforms for high-throughput and power efficient implementation of parallel algorithms, efficient FPGA realization of DNNs on single FPGA chips has attracted researchers’ attention [10], [11], [12].”
BackgroundLaius: An 8-Bit Fixed-Point CNN Hardware Inference Engine
Li, Z., Wang, L., Guo, S., Deng, Y. L., Dou, Q., Zhou, H., & Lu, W. (2017) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa/iucc.2017.00030 · Cited by 54
Deep Learning Inferencing with High-performance Hardware Accelerators
Kljucaric, L., & George, A. D. (2023) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3594221 · Cited by 53
Neuromorphic computing's yesterday, today, and tomorrow – an evolutional view
Chen, Y., Li, H. H., Wu, C., Song, C., Li, S. K., Min, C., Cheng, H.-P., Wen, W., & Liu, X. (2017) · Integration · doi:10.1016/j.vlsi.2017.11.001 · Cited by 51
Zokaee, F., Lou, Q., Youngblood, N., Liu, W., Xie, Y., & Jiang, L. (2020) · Design, Automation, and Test in Europe · doi:10.23919/date48585.2020.9116494 · Cited by 51
“CNP [4] and SCNN [27] were trained with MNIST to recognize simple hand-written digits, while MobileNetV2 [24], Shuf-fleNetV2 [20] and ResNet-18 were trained with ImageNet to classify complex objects.”
MethodOvercoming resource underutilization in spatial CNN accelerators
Shen, Y., Ferdman, M., & Milder, P. A. (2016) · International Conference on Field Programmable Logic and Applications (FPL) · doi:10.1109/fpl.2016.7577315 · Cited by 48
“For example, the 2D-convolvers used in [6]– [9] must be as large as the largest filter in any of the CNN layers; they will necessarily be underutilized when used to compute any layer that has smaller filters.”
MethodAn efficient implementation of 2D convolution in CNN
Chang, J., & Sha, J. (2016) · IEICE Electronics Express · doi:10.1587/elex.13.20161134 · Cited by 48
“Among these approaches, the architecture which is inspired by [12], first introduced into CNN by [1], is commonly adopted.”
BenchIP: Benchmarking Intelligence Processors
Tao, J.-H., Du, Z., Guo, Q., Lan, H., Zhang, L., Zhou, S., Xu, L., Liu, C., Liu, H.-F., Tang, S., et al. (2018) · Journal of Computer Science and Technology · doi:10.1007/s11390-018-1805-8 · Cited by 49
“As an efficient alternative for deep learning, a large variety of customized hardware architectures, ranging from specialized GPUs (e.g., NVIDIA DGX-1 [7]) to FPGAs (e.g., CNP [8] and [9]) to ASICs (e.g., DianNao [10], NeuFlow [11], and EIE [12]) have emerged.”
BackgroundHardware-Software Co-Design for an Analog-Digital Accelerator for Machine Learning
Ambrosi, J., Ankit, A., Antunes, R., Chalamalasetti, S. R., Chatterjee, S., Hajj, I. E., Fachini, G. J. D. A., Faraboschi, P., Foltín, M., Huang, S., et al. (2018) · IEEE International Conference on Rebooting Computing (ICRC) · doi:10.1109/icrc.2018.8638612 · Cited by 48
“Some can be configured with FPGAs [72], [73], [63], [67], [74], [75], [76], [77].”
BackgroundHeterogeneous integration for artificial intelligence: Challenges and opportunities
Mukhopadhyay, S., Long, Y., Mudassar, B. A., Nair, C., DeProspo, B., Torun, H. M., Kathaperumal, M., Smet, V., Kim, D., Yalamanchili, S., et al. (2019) · IBM Journal of Research and Development · doi:10.1147/jrd.2019.2947373 · Cited by 47
An energy-efficient memory-based high-throughput VLSI architecture for convolutional networks
Kang, M., Gonugondla, S. K., Keel, M.-S., & Shanbhag, N. R. (2015) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2015.7178127 · Cited by 46
“Figure 1(b) shows the block diagram of a conventional C-Net system [4], where a conventional SRAM stores the weights wmn, and the input feature map xm is stored in a register bank.”
BackgroundMethodInfluentialService-Oriented Architecture on FPGA-Based MPSoC
Wang, C., Li, X., Chen, Y., Zhang, Y., Diessel, O., & Zhou, X. (2017) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2017.2701828 · Cited by 46
A survey of neural network accelerators
Li, Z., Wang, Y., Zhi, T., & Chen, T. (2017) · Frontiers of Computer Science · doi:10.1007/s11704-016-6159-1 · Cited by 46
“[49] implemented a RISC-like programmable ConvNet Processor which computes partial sums of different outputs with an identical input in parallel via multiple DSPs”
MethodHardware Trojan in FPGA CNN Accelerator
Ye, J., Hu, Y. H., & Li, X. (2018) · Proceedings - Asian Test Symposium/Proceedings · doi:10.1109/ats.2018.00024 · Cited by 46
İnce, T. (2019) · Electrical Engineering · doi:10.1007/s00202-019-00808-7 · Cited by 46
Wang, Y., Ding, C., Li, Z., Yuan, G., Liao, S., Ma, X., Yuan, B., Qian, X., Tang, J., Qiu, Q., et al. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11653 · Cited by 44
FPGA Implementation of CNN for Handwritten Digit Recognition
Xiao, R., Shi, J., & Zhang, C. (2020) · IEEE Information Technology, Networking, Electronic and Automation Control Conference (ITNEC) · doi:10.1109/itnec48623.2020.9085002 · Cited by 44
“For example, reference [11] is a classical convolution hardware implementation method, and the 3 × 3 convolution circuit shown in Fig.”
MethodBaptista, D., Mostafa, S. S., Pereira, L., Sousa, L. A., & Morgado‐Dias, F. (2018) · Energies · doi:10.3390/en11092460 · Cited by 43
“[38] propose a different implementation of a CNN on an FPGA.”
MethodImplementation of FPGA-based Accelerator for Deep Neural Networks
Tsai, T., Ho, Y.-C., & Sheu, M. (2019) · IEEE International Symposium on Design and Diagnostics of Electronic Circuits & Systems (DDECS) · doi:10.1109/ddecs.2019.8724665 · Cited by 43
Why TanH is a Hardware Friendly Activation Function for CNNs
Abdelouahab, K., Pelcat, M., & Berry, F. (2017) · International Conference on Distributed Smart Cameras · doi:10.1145/3131885.3131937 · Cited by 42
“As a result, CNNs implementations based on approximate computing resort to dynamic fixed point [3, 6], mini-float [6] ,or long word-length fixed point representation of data [7, 8].”
BackgroundDarbon, J., Dower, P. M., & Meng, T. (2022) · Mathematics of Control Signals and Systems · doi:10.1007/s00498-022-00333-2 · Cited by 41
Han, X., Zhou, D., Wang, S., & Kimura, S. (2016) · IEEE International Conference on Computer Design: VLSI in Computers and Processors (ICCD) · doi:10.1109/iccd.2016.7753296 · Cited by 39
“INTRODUCTION State-of-the-art CNNs are demonstrating high performance and flexibility in a wide range of applications including video surveillance, object recognition and mobile robot vision [1]–[3].”
BackgroundFPGA Implementation of Quantized Convolutional Neural Networks
Zhang, Q., Cao, J., Zhang, Y., Zhang, S., Zhang, Q., & Yu, D. (2019) · IEEE International Conference on Communication Technology (ICCT) · doi:10.1109/icct46805.2019.8947168 · Cited by 39
“[21][22][23] These articles focus on computational engine optimization.”
BackgroundA high-throughput reconfigurable processing array for neural networks
Wu, E., Zhang, X., Berman, D., & Cho, I. (2017) · International Conference on Field Programmable Logic and Applications (FPL) · doi:10.23919/fpl.2017.8056794 · Cited by 37
An OpenCL(TM) Deep Learning Accelerator on Arria 10Preprint
Aydonat, U., O’Connell, S., Capalija, D., Ling, A. C., & Chiu, G. R. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1701.03534 · Cited by 34
“More recently, FPGAs have shown promise in efficiently implementing CNNs [21, 16, 13, 20, 11, 2, 12, 14, 4].”
BackgroundMethodLow-Latency In Situ Image Analytics With FPGA-Based Quantized Convolutional Neural Network
Wang, M., Lee, K. C. M., Chung, B. M. F., Varma, B. S., Ng, H.-C., Wong, J. S. J., Shum, H. C., Tsia, K. K., & So, H. K. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3046452 · Cited by 33
“[12] presented a custom architecture for performing CNN inference on FPGA.”
MethodA memory-based realization of a binarized deep convolutional neural network
Nakahara, H., Yonekawa, H., Sasao, T., Iwamoto, H., & Motomura, M. (2016) · International Conference on Field-Programmable Technology (FPT) · doi:10.1109/fpt.2016.7929552 · Cited by 33
Perspective: Uniform switching of artificial synapses for large-scale neuromorphic arrays
Tan, S. H., Lin, P., Yeon, H., Choi, S., Park, Y., & Kim, J. (2018) · APL Materials · doi:10.1063/1.5049137 · Cited by 33
A design of license plate recognition system using convolutional neural network
Marzuki, P., Syafeeza, A. R., Wong, Y. C., Hamid, N. B. A., Alisa, A. N., & Ibrahim, M. M. (2019) · International Journal of Electrical and Computer Engineering (IJECE) · doi:10.11591/ijece.v9i3.pp2196-2204 · Cited by 33
Application of Event Cameras and Neuromorphic Computing to VSLAM: A Survey
Tenzin, S., Rassau, A., & Chai, D. (2024) · Biomimetics · doi:10.3390/biomimetics9070444 · Cited by 32
Design and Implementation of CNN Custom Processor Based on RISC-V Architecture
Li, Z., Hu, W., & Chen, S. (2019) · IEEE International Conference on High Performance Computing and Communications; IEEE International Conference on Smart City; IEEE International Conference on Data Science and Systems (HPCC/SmartCity/DSS) · doi:10.1109/hpcc/smartcity/dss.2019.00268 · Cited by 32
“[9] proposed an FPGA-based CNN.”
Li, N., Takaki, S., Yoichi, T., & Kitazawa, H. (2016) · IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI) · doi:10.1109/ssiai.2016.7459201 · Cited by 31
“Work [3] focused on hardware processing unit optimization.”
BackgroundMethodFast-BCNN: Massive Neuron Skipping in Bayesian Convolutional Neural Networks
Wan, Q., & Fu, X. (2020) · IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1109/micro50266.2020.00030 · Cited by 31
“Current parallelism strategies can be categorized into three types [20]: Synapse Parallelism [21], Neuron Parallelism [22] and Feature map Parallism [23].”
MethodFast Algorithms for Quaternion-Valued Convolutional Neural Networks
Cariow, A., & Cariowa, G. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2979682 · Cited by 30
On the AER convolution processors for FPGA
Linares-Barranco, A., Paz-Vicente, R., Gómez-Rodríguez, F., Jimenez, A., Rivas, M., Jiménez, G., & Civit, A. (2010) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.2010.5537577 · Cited by 30
“Another approach for solving frame-based convolutions with higher performances are the ConvNets [17][18], based on cellular neural networks, that are able to achieve a theoretical sustained 4 GOPS for 7x7 kernel sizes.”
BackgroundA reconfigurable accelerator for neuromorphic object recognition
Sabarad, J., Kestur, S., Park, M. S., Dantara, D., Narayanan, V., Chen, Y., & Khosla, D. (2012) · Asia and South Pacific Design Automation Conference (ASP-DAC) · doi:10.1109/aspdac.2012.6165067 · Cited by 30
“This image pyramid is successively feed-forward to obtain responses from the alternating higher S(simple) and C(complex) layers.”
BackgroundImplementation of Data-optimized FPGA-based Accelerator for Convolutional Neural Network
Cho, M., & Kim, Y. (2020) · International Conference on Electronics, Information, and Communication (ICEIC) · doi:10.1109/iceic49074.2020.9050993 · Cited by 29
“Many researches have been conducted to implement more efficient high-performance CNN accelerators on FPGA platforms [2][3].”
MethodScheduling Computation Graphs of Deep Learning Models on Manycore CPUsPreprint
Tang, L., Wang, Y., Willke, T. L., & Li, K. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.09667 · Cited by 29
“periments runs as an independent host. However, a manycore CPU can be viewed as an accelerator. Related work on optimizations for deep learning computations on the accelerators include GPU [11], FPGA [18, 26, 66, 67] and the rst generation Intel Xeon Phi coprocessor 14 (Knights Corner) [68]. Their focus was on the opt…”
BackgroundTwo sparsities are better than one: unlocking the performance benefits of sparse–sparse networks
Hunter, K., Spracklen, L., & Ahmad, S. (2022) · Neuromorphic Computing and Engineering · doi:10.1088/2634-4386/ac7c8a · Cited by 28
“Over the last decade there has been significant attention focused on accelerating DNNs using FPGAs and other architectures, including convolutional networks [18].”
BackgroundVarGNet: Variable Group Convolutional Neural Network for Efficient Embedded ComputingPreprint
Zhang, Q., Li, J., Meng, Y., Song, L., Zhou, H., Li, Z., Meng, W., Zhang, X., & Wang, G. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.05653 · Cited by 28
“To accelerate neural networks, FPGAs [13, 50, 17, 31] and ASIC designs [7, 36, 23, 29, 19] have been widely studied.”
BackgroundMethodA Threshold Neuron Pruning for a Binarized Deep Neural Network on an FPGA
Fujii, T., Sato, S., & Nakahara, H. (2018) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2017rcp0013 · Cited by 27
“Figure 9 shows the serial-input parallel-output (SIPO) fully connected layer [11].”
BackgroundStochastic-Based Deep Convolutional Networks with Reconfigurable Logic Fabric
Alawad, M., & Lin, M. (2016) · IEEE Transactions on Multi-Scale Computing Systems · doi:10.1109/tmscs.2016.2601326 · Cited by 26
Customizable Computing—From Single Chip to Datacenters
Cong, J., Fang, Z., Huang, M., Wei, P., Wu, D., & Yu, C. H. (2018) · Proceedings of the IEEE · doi:10.1109/jproc.2018.2876372 · Cited by 26
“[81] C.”
FPGA-based architecture for the real-time computation of 2-D convolution with large kernel size
Toledo, F. J., Martínez-Álvarez, J. J., Garrigós, J., & Vicente, J. M. F. (2012) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2012.06.002 · Cited by 25
A pipelined and scalable dataflow implementation of convolutional neural networks on FPGA
Bacis, M., Natale, G., Sozzo, E. D., & Santambrogio, M. D. (2017) · IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum · doi:10.1109/ipdpsw.2017.44 · Cited by 25
“In particular, FPGA-based accelerators recently gained substantial attention due to their advantages of performance and high energy-efficiency, as well as a lower power consumption compared to GPUs, and a higher flexibility than ASICs, thanks to their reconfigurability [11, 12, 13, 14].”
BackgroundRoofline-Model-Based Design Space Exploration for Dataflow Techniques of CNN Accelerators
Park, C., Park, S., & Park, C. S. (2020) · IEEE Access · doi:10.1109/access.2020.3025550 · Cited by 25
“Field-programmable gate array (FPGA) based accelerators for reconfigurable systems can be a cost-effective and viable solution to achieve both high energy efficiency and large throughput in CNN implementations [3], [6], [7], [24].”
BackgroundBriefly Analysis about CNN Accelerator based on FPGA
Wang, Z., Li, H., Yue, X., & Meng, L. (2022) · Procedia Computer Science · doi:10.1016/j.procs.2022.04.036 · Cited by 25
ESSA: An energy-Aware bit-Serial streaming deep convolutional neural network accelerator
Hsu, L.-C., Chiu, C., Lin, K.-T., Chou, H.-H., & Pu, Y.-Y. (2020) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2020.101831 · Cited by 24
A Holistic Approach for Optimizing DSP Block Utilization of a CNN implementation on FPGA
Abdelouahab, K., Bourrasset, C., Pelcat, M., Berry, F., Quinton, J., & Sérot, J. (2016) · ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC) · doi:10.1145/2967413.2967430 · Cited by 24
Parana: A Parallel Neural Architecture Considering Thermal Problem of 3D Stacked Memory
Yin, S., Tang, S., Lin, X., Ouyang, P., Tu, F., Liu, L., Zhao, J., Xu, C., Li, S., Xie, Y., et al. (2018) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2018.2858230 · Cited by 24
“Many prior work [7], [8], [25], [26], [27], [28], [29], [30], [31], [32], [33], [34], [35], [36], [37], [38], [39], [40], [41], [42], [43], [44], [45], [46], [47], [48], [49] have used spatial architectures to accelerate neural networks in ASIC and FPGA implementations.”
BackgroundPYNQ FPGA Hardware implementation of LeNet-5-Based Traffic Sign Recognition Application
Maraoui, A., Messaoud, S., Bouaafia, S., Ammari, A. C., Khriji, L., & Machhout, M. (2021) · International Multi-Conference on Systems, Signals & Devices (SSD) · doi:10.1109/ssd52085.2021.9429480 · Cited by 24
“Indeed, in many works of CNN accelerators implementation in [6] [7] [8] [9] [10] which have been suggested for different purposes and with various techniques and methodologies.”
BackgroundOptimizing CNNs on Multicores for Scalability, Performance and Goodput
Rajbhandari, S., He, Y., Ruwase, O., Carbin, M., & Chilimbi, T. M. (2017) · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · doi:10.1145/3037697.3037745 · Cited by 23
“GPUs [27], FPGAs [23, 45, 55] and ASICs [9, 10] have being used to accelerate CNN inference, which is a subset (i.e., forward propagation phase only) of CNN training.”
MethodInfluentialA High-efficiency FPGA-based Accelerator for Convolutional Neural Networks using Winograd Algorithm
Huang, Y., Shen, J., Wang, Z., Wen, M., & Zhang, C. (2018) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1026/1/012019 · Cited by 23
“Since CPUs can hardly provide the massive parallelism required by CNNs, many hardware accelerators, such as GPU, FPGA [2-12], and ASIC [13], have been developed to improve the performance of CNNs.”
BackgroundAll binarized convolutional neural network and its implementation on an FPGA
Shimoda, M., Sato, S., & Nakahara, H. (2017) · International Conference on Field-Programmable Technology (FPT) · doi:10.1109/fpt.2017.8280163 · Cited by 23
“Therefore, a circuit which accesses the values efficiently by preparing long buffers and offers it to the multiply-accumulation (MAC) each clock is proposed [4].”
BackgroundHardware Compilation of Deep Neural Networks: An Overview
Zhao, R., Liu, S., Ng, H.-C., Wang, E., Davis, J. J., Niu, X., Wang, X., Shi, H.-F., Constantinides, G. A., Cheung, P. Y. K., et al. (2018) · IEEE International Conference on Application-specific Systems, Architectures and Processors (ASAP) · doi:10.1109/asap.2018.8445088 · Cited by 23
“’s paper was particularly significant since it explored more opportunities for parallelism than existing works, which only exploited parallelism at the operator level through systolic arrays [47]–[49].”
BackgroundKelp: QoS for Accelerated Machine Learning Systems
Zhu, H., Lo, D., Cheng, L., Govindaraju, R., Ranganathan, P., & Erez, M. (2019) · IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca.2019.00036 · Cited by 22
Enhancing the Scalability of Multi-FPGA Stencil Computations via Highly Optimized HDL Components
Reggiani, E., Sozzo, E. D., Conficconi, D., Natale, G., Moroni, C., & Santambrogio, M. D. (2021) · ACM Transactions on Reconfigurable Technology and Systems · doi:10.1145/3461478 · Cited by 22
Nekooei, A., & Safari, S. (2022) · Neural Networks · doi:10.1016/j.neunet.2022.02.024 · Cited by 22
Addressing Sparsity in Deep Neural Networks
Zhou, X., Chen, Y., Du, Z., Zhang, S., Zhang, L., Lan, H., Liu, S., Li, L., Guo, Q., & Chen, T. (2018) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2018.2864289 · Cited by 21
Convolutional neural network acceleration with hardware/software co-design
Chen, A. T.-Y., Biglari-Abhari, M., Wang, K. I., Bouzerdoum, A., & Tivive, F. H. C. (2017) · Applied Intelligence · doi:10.1007/s10489-017-1007-z · Cited by 20
Limonova, E. E., Sheshkus, A. V., Ivanova, A. A., & Nikolaev, D. (2018) · Pattern Recognition and Image Analysis · doi:10.1134/s105466181801011x · Cited by 20
“Despite the fact that FPGA implementations of neural networks are efficient and characterized by low power consumption [22, 23], they can be used only when working on hardware platforms.”
MethodA scalable architecture for multi-class visual object detection
Advani, S., Tanabe, Y., Irick, K. M., Sampson, J., & Narayanan, V. (2015) · International Conference on Field Programmable Logic and Applications (FPL) · doi:10.1109/fpl.2015.7293961 · Cited by 19
“Figure 3 highlights the fundamental bottlenecks and shows that the algorithm is almost equally compute-bound as is memorybound across various image sizes.”
BackgroundA CNN Accelerator on FPGA with a Flexible Structure
Shan, D., Cong, G., & Lu, W. D. (2020) · International Conference on Computational Intelligence and Applications (ICCIA) · doi:10.1109/iccia49625.2020.00047 · Cited by 19
The Implementation of CNN-Based Object Detector on ARM Embedded Platforms
Zhang, Y., Bi, S., Dong, M., & Liu, Y. (2018) · IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) · doi:10.1109/dasc/picom/datacom/cyberscitec.2018.00074 · Cited by 19
A Multithreaded CGRA for Convolutional Neural Network Processing
Ando, K., Takamaeda-Yamazaki, S., Ikebe, M., Asai, T., & Motomura, M. (2017) · Circuits and Systems · doi:10.4236/cs.2017.86010 · Cited by 18
“FPGA implementations of CNN coprocessors using DSP blocks were also proposed [11] [12].”
MethodScalable FPGA Accelerator for Deep Convolutional Neural Networks with Stochastic Streaming
Alawad, M., & Lin, M. (2018) · IEEE Transactions on Multi-Scale Computing Systems · doi:10.1109/tmscs.2018.2886266 · Cited by 18
“Their proposed structure can significantly improve the performance and energy consumption of simple task CNNs [35], [36].”
An Efficient Hardware Implementation of Artificial Neural Network based on Stochastic Computing
Nguyen, D.-A., Ho, H.-H., Bui, D.-H., & Tran, X. (2018) · NAFOSTED Conference on Information and Computer Science (NICS) · doi:10.1109/nics.2018.8606843 · Cited by 18
“To enable real-time, in-field processing of ANN in such platforms, developing dedicated hardware architectures has attracted growing interest [5][6][7].”
MethodAn FPGA Realization of a Deep Convolutional Neural Network Using a Threshold Neuron Pruning
Fujii, T., Sato, S., Nakahara, H., & Motomura, M. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-56258-2_23 · Cited by 17
VHDL generator for a high performance convolutional neural network FPGA-based accelerator
Hamdan, M. K. A., & Rover, D. T. (2017) · International Conference on ReConFigurable Computing and FPGAs (ReConFig) · doi:10.1109/reconfig.2017.8279827 · Cited by 17
Efficiency Optimization of Trainable Feature Extractors for a Consumer Platform
Peemen, M., Mesman, B., & Corporaal, H. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-23687-7_27 · Cited by 17
One-Dimensional Binary Convolutional Neural Network Accelerator Design for Bearing Fault Diagnosis
Syu, Z.-S., & Lee, C. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3340715 · Cited by 16
“Herein, two potential approaches are adopted to address the expensive computing and storage devices required using deep learning approach [20], [21], [22], [23], [24], [25], [26], [27], [28], [29].”
MethodDesign and implementation of deep learning-based object detection and tracking system
Tsai, T., & Wu, P. (2024) · Integration · doi:10.1016/j.vlsi.2024.102240 · Cited by 16
Using Data Compression for Optimizing FPGA-Based Convolutional Neural Network Accelerators
Guan, Y., Xu, N., Zhang, C., Yuan, Z., & Cong, J. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-67952-5_2 · Cited by 16
“Previous works on FPGA-based CNN accelerator aim at optimizing computation throughput [1,5,11] and I/O bandwidth [10] to achieve the best performance.”
BackgroundA Real-time Online Aircraft Neural Network System
Zhang, Y., Zhao, Q., Tao, L., Cao, J., Wei, M., & Zhang, X. (2019) · doi:10.1109/iwofc48002.2019.9078469 · Cited by 16
“Paper [2][17] Paper [3][9] This article Performance (GMACs) IV.”
BackgroundLiu, X., Kim, D. H., Wu, C., & Chen, D. (2018) · doi:10.1145/3225209.3225214 · Cited by 16
“With such advantages, recently several research works have used FPGAs to accelerate CNN computations [10, 11, 12, 13, 14, 15].”
MethodReview of prominent strategies for mapping CNNs onto embedded systems
Arredondo-Velázquez, M., Díaz-Carmona, J., Gutiérrez, A. I. B., & Torres-Huitzil, C. (2020) · IEEE Latin America Transactions · doi:10.1109/tla.2020.9082927 · Cited by 16
“Las propuestas [101], [102], [94], [103], [104] hacen uso de dicho método convencional inspirándose en [105], siendo en [101] donde se utilizó por primera vez en una RNC.”
BackgroundMOCHA: Morphable Locality and Compression Aware Architecture for Convolutional Neural Networks
Jafri, S. M. A. H., Hemani, A., Paul, K., & Abbas, N. (2017) · IEEE International Parallel and Distributed Processing Symposium (IPDPS) · doi:10.1109/ipdps.2017.59 · Cited by 15
“While performance, to some extent, can be achieved by FPGAs [2], [3], [4] and GPUS [1], [5], [6], [7], the low power demands to enable deployment in field cannot be met by them.”
BackgroundMethodA hardware architecture for accelerating neuromorphic vision algorithms
Maashri, A. A., DeBole, M., Yu, C.-L., Narayanan, V., & Chakrabarti, C. (2011) · SiPS ... design and implementation - IEEE Workshop on Signal Processing Systems · doi:10.1109/sips.2011.6089002 · Cited by 15
Huan, Y., Qin, Y., You, Y., Zheng, L., & Zou, Z. (2016) · IEEE International System-on-Chip Conference (SOCC) · doi:10.1109/socc.2016.7905445 · Cited by 15
“Exploration has been taken in GPU [2, 3], FPGA [4, 5, 6], and specialized hardware [7, 8].”
An Instruction Set Architecture for Machine Learning
Chen, Y., Lan, H., Du, Z., Liu, S., Tao, J., Han, D., Luo, T., Guo, Q., Li, L., Xie, Y., et al. (2018) · ACM Transactions on Computer Systems · doi:10.1145/3331469 · Cited by 14
“Over the past decade, there have been many hardware accelerators customized to NNs, implemented on FPGAs [18, 51, 57, 59] or as ASICs [5, 17, 20, 62].”
Bridge the Gap between Neural Networks and Neuromorphic Hardware with a Neural Network Compiler
Ji, Y., Zhang, Y., Chen, W., & Xie, Y. (2018) · ACM SIGPLAN Notices · doi:10.1145/3296957.3173205 · Cited by 14
SHARC: A streaming model for FPGA accelerators and its application to Saliency
Kestur, S., Dantara, D., & Narayanan, V. (2011) · Design, Automation, and Test in Europe · doi:10.1109/date.2011.5763198 · Cited by 14
“This model is very well suited for compute-intensive applications in areas such as real-time vision and signal processing, where stream processing provides enormous performance benefits.”
BackgroundChen, J.-L., Ai, P., Wang, D., Wang, H., Fang, N., Xu, D., Gong, Q., & Yang, Y.-K. (2020) · Nuclear Science and Techniques · doi:10.1007/s41365-020-00756-z · Cited by 14
“As a programmable device, an FPGA has reconfigurable logic resources based on a look-up-table (LUT) [20].”
MethodEfficient Network Construction Through Structural Plasticity
Du, X., Li, Z., Ma, Y., & Cao, Y. K. (2019) · IEEE Journal on Emerging and Selected Topics in Circuits and Systems · doi:10.1109/jetcas.2019.2933233 · Cited by 14
“Some other works focus on data reuse of convolutional layers and demonstrate the results on specific hardware [7], [12]–[14].”
BackgroundWan, Q., Xia, H., Zhang, X., Wang, L., Song, S. L., & Fu, X. (2021) · IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1145/3466752.3480120 · Cited by 13
“, systolic array [21], input channel and output channel (MN-dimension) ma ping, e.”
BackgroundInfluentialFPGA-Based Accelerator for Deep Convolutional Neural Networks for the SPARK Environment
Morcel, R., Ezzeddine, M., & Akkary, H. H. (2016) · IEEE International Conference on Smart Cloud (SmartCloud) · doi:10.1109/smartcloud.2016.31 · Cited by 13
“We propose a custom-designed FPGA-based 2D convolution filter that can be used to accelerate the computation of the multi-layer convolution operator used in the distributed training of convolutional neural networks.”
Method
Metadata
- Authors
- Farabet, C., Poulet, C., Han, J. Y., & LeCun, Y.
- Affiliations
- Courant Institute of Mathematical Sciences (US)
- ORCID
- LeCun, Yann
- Venue
- 2009 International Conference on Field Programmable Logic and Applications
- Publisher
- IEEE
- Published
- 2009-08
- Pages
- 32-37
- OpenAlex
- W1990315422
- Cited by
- 367
- References
- 17
- Citations by year
- 2026: 6 · 2025: 8 · 2024: 12 · 2023: 13 · 2022: 19 · 2021: 23 · 2020: 36 · 2019: 46 · 2018: 55 · 2017: 54 · 2016: 51 · 2015: 15 · 2014: 2 · 2013: 4 · 2012: 3
- FWCI
- 6.26
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on Field Programmable Logic and Applications (FPL) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Hardware and Architecture › Embedded Systems Design Techniques
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Embedded Systems and FPGA Applications
- Keywords
- convolutional neural networks, FPGA implementation, multiply-accumulate unit, face detection, embedded vision, low-power electronics, micro UAV, hardware acceleration
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.