Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural Networks
The DOI matches its Crossref record; 38 of the 42 references it cites were found in a registry or an index.
Abstract
Eyeriss is an accelerator for state-of-the-art deep convolutional neural networks (CNNs). It optimizes for the energy efficiency of the entire system, including the accelerator chip and off-chip DRAM, for various CNN shapes by reconfiguring the architecture. CNNs are widely used in modern AI systems but also bring challenges on throughput and energy efficiency to the underlying hardware. This is because its computation requires a large amount of data, creating significant data movement from on-chip and off-chip that is more energy-consuming than computation. Minimizing data movement energy cost for any CNN shape, therefore, is the key to high throughput and energy efficiency. Eyeriss achieves these goals by using a proposed processing dataflow, called row stationary (RS), on a spatial architecture with 168 processing elements. RS dataflow reconfigures the computation mapping of a given shape, which optimizes energy efficiency by maximally reusing data locally to reduce expensive data movement, such as DRAM accesses. Compression and data gating are also applied to further improve energy efficiency. Eyeriss processes the convolutional layers at 35 frames/s and 0.0029 DRAM access/multiply and accumulation (MAC) for AlexNet at 278 mW (batch size N = 4), and 0.7 frames/s and 0.0035 DRAM access/MAC for VGG-16 at 236 mW (N = 3).
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
“such scaling will enable NeuRRAM to deliver higher energy and area efficiency than today’s state-of-the-art edge inference accelerators58–61.”
From A compute-in-memory chip based on resistive random-access memory (2022) · cites this paper as [58]
In the citing paper
“Some studies proposed to implement the argmax() function via hardware128–148, which could be beneficial to reduce the total transistor count and power consumption while at the same time increasing the throughput.”
From Hardware implementation of memristor-based artificial neural networks (2024) · cites this paper as [131]
In the citing paper
“Based on the analysis of the research, CoNNA is able to speed up at least 3.08 times and up to 14.1 times faster than the MIT Eyeriss Accelerator [20].”
From Embedded Intelligence on FPGA: Survey, Applications and Challenges (2021) · cites this paper as [20]
In the citing paper
“massively parallel processing architectures with distributed memory architectures, such as graphic processing units (GPUs) but also increasingly specialized chips for NN inference (e.g., [17]), have shown to be very energy efficient and capable of impressive computational throughput when fully utilized by concurrent algorithms [18].”
From An Introduction to Deep Learning for the Physical Layer (2017) · cites this paper as [17]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“Modern CNNs achieve their superior accuracy by building a very deep hierarchy of layers [2]–[5], [7], which transform the input image data into highly abstract representations called feature maps (fmaps).”
BackgroundVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 7×
“We benchmark the chip performance using two publicly available and widely used CNNs: AlexNet [2] and VGG-16 [3].”
MethodInfluentialImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
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 1×
“[25] demonstrate a CNN processor and only report the theoretical peak throughput along with the power measured on a CNN for the MNIST data set [26], which has storage and computation requirements that are orders of magnitude lower than the state-of-the-art CNNs.”
MethodGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 2×
“We have demonstrated an 1000-class image classification task [27] using this system, and a live demo can be found in [29].”
BackgroundMethodRich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612 · cited 1×
“D EEP learning using convolutional neural networks (CNNs) [1] has achieved unprecedented accuracy on many modern AI applications [2]–[9].”
Background(2010) · International Conference on Machine Learning · Cited by 13,995
Research works printed but not linked: 2
- han, 2015, Learning both weights and connections for efficient neural network, Proc Adv Neural Inf Process Syst, 28, 1135
- chen, 2016, An 1000-Class Image Classification Task Performed by the Eyeriss-Integrated Deep Learning System
Cited by
Items 201–300 of 1,001
HyPar: Towards Hybrid Parallelism for Deep Learning Accelerator Array
Song, L., Mao, J., Zhuo, Y., Qian, X., Li, H., & Chen, Y. (2019) · 2019 IEEE International Symposium on High Performance Computer Architecture (HPCA) · doi:10.1109/hpca.2019.00027 · Cited by 108
Self-citationA Survey of Convolutional Neural Networks on Edge with Reconfigurable Computing
Véstias, M. P. (2019) · Algorithms · doi:10.3390/a12080154 · Cited by 112
“Eyeriss [54] is a coarse-grain reconfigurable device that accelerates convolutional neural networks.”
BackgroundDave, S., Baghdadi, R., Nowatzki, T., Avancha, S., Shrivastava, A., & Li, B. (2021) · Proceedings of the IEEE · doi:10.1109/jproc.2021.3098483 · Cited by 111
A Review on the emerging technology of TinyML
Tsoukas, V., Gkogkidis, A., Boumpa, E., & Kakarountas, A. P. (2024) · ACM Computing Surveys · doi:10.1145/3661820 · Cited by 150
“The results revealed a better performance than other state-of-the-art approaches, such as Eyeriss [37], which is also an accelerator for CNNs and can optimize energy efficiency by including a hardware accelerator and a chip for Dynamic RAM (DRAM) .”
BackgroundZeNA: Zero-Aware Neural Network Accelerator
Kim, D., Ahn, J., & Yoo, S. (2018) · IEEE Design & Test · doi:10.1109/mdat.2017.2741463 · Cited by 109
“Eyeriss [5] applies clock-gating for multiplications with zero activations, which saves energy consumption but cannot improve performance as it accumulates partial sums from neighbor processing elements (PEs) in a synchronous manner.”
BackgroundMethodLaconic deep learning inference acceleration
Sharify, S., Lascorz, A. D., Mahmoud, M., Nikolić, M., Siu, K., Stuart, D. M., Poulos, Z., & Moshovos, A. (2019) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1145/3307650.3322255 · Cited by 143
REQ-YOLO: A Resource-Aware, Efficient Quantization Framework for Object Detection on FPGAs
Ding, C., Wang, S., Liu, N., Xu, K., Wang, Y., & Liang, Y. E. (2019) · ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA) · doi:10.1145/3289602.3293904 · Cited by 126
“The second one is efficient hardware implementations, including FPGAs and ASICs [1, 7, 31, 32, 36, 49, 50, 53, 54].”
BackgroundMethodMachine Learning for Security in Vehicular Networks: A Comprehensive Survey
Talpur, A., & Gurusamy, M. (2022) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2021.3129079 · Cited by 107
Systolic Tensor Array: An Efficient Structured-Sparse GEMM Accelerator for Mobile CNN Inference
Liu, Z.-G., Whatmough, P. N., & Mattina, M. (2020) · IEEE Computer Architecture Letters · doi:10.1109/lca.2020.2979965 · Cited by 104
Sparsity-Aware and Re-configurable NPU Architecture for Samsung Flagship Mobile SoC
Jang, J.-W., Lee, S., Kim, D., Park, H., Ardestani, A. S., Choi, Y., Kim, C., Kim, Y., Yu, H., Abdel-Aziz, H. A., et al. (2021) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1109/isca52012.2021.00011 · Cited by 126
“Recently, a dedicated hardware accelerator for neural networks called neural processing unit (NPU), has been extensively studied for the efficient execution of neural networks [6, 7, 8, 9, 10].”
BackgroundMethodNeural Architecture Search Survey: A Hardware Perspective
Chitty-Venkata, K. T., & Somani, A. K. (2023) · ACM Computing Surveys · doi:10.1145/3524500 · Cited by 106
“The accelerator search includes resource allocation to the sub-accelerators and dataflow for each of the sub-accelerators from the following set of dataflows: Shidiannao [27], NVDLA [103], and row-stationary [12].”
MethodPeng, X., Liu, R., & Yu, S. (2019) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.2019.8702715 · Cited by 131
“at T=1, IMF[1][1] (a vector with length D) is assigned to PE[1][1], IMF[1][2] is assigned to PE[1][2], and so on, the partial sums in these 9 PEs will be summed up (by adder tree) to get OFM[2][2] (with size 1×1×N).”
BackgroundMethodInfluentialGAMMA: automating the HW mapping of DNN models on accelerators via genetic algorithm
Kao, S.-C., & Krishna, T. (2020) · doi:10.1145/3400302.3415639 · Cited by 212
“Thus GAMMA can work across both single-accelerator [11, 25] and multi-accelerator [46] systems.”
BackgroundSelf-citationEmbedded Intelligence on FPGA: Survey, Applications and Challenges
Seng, K. P., Lee, P. J., & Ang, L. M. (2021) · Electronics · doi:10.3390/electronics10080895 · Cited by 105
“Based on the analysis of the research, CoNNA is able to speed up at least 3.08 times and up to 14.1 times faster than the MIT Eyeriss Accelerator [20].”
BackgroundInfluentialAn Architecture to Accelerate Convolution in Deep Neural Networks
Ardakani, A., Condo, C., Ahmadi, M., & Gross, W. J. (2017) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2017.2757036 · Cited by 114
Koppula, S., Orosa, L., Yağlıkçı, A. G., Azizi, R., Shahroodi, T., Kanellopoulos, K., & Mutlu, O. (2019) · Proceedings of the 52nd Annual IEEE/ACM International Symposium on Microarchitecture · doi:10.1145/3352460.3358280 · Cited by 104
“We evaluate EDEN on three different accelerators: GPU [124], Eyeriss [26], and TPU [69].”
BackgroundMethodInfluentialA Systematic Survey of General Sparse Matrix-matrix Multiplication
Gao, J., Ji, W., Chang, F., Shi-yu, H., Wei, B., Liu, Z., & Wang, Y. (2022) · ACM Computing Surveys · doi:10.1145/3571157 · Cited by 129
“[63][27] use a CSR variation, run-length encoding (RLE), to store a sparse weight matrix in deep neural network (DNN).”
MethodNeurostream: Scalable and Energy Efficient Deep Learning with Smart Memory Cubes
Azarkhish, E., Rossi, D., Loi, I., & Benini, L. (2017) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2017.2752706 · Cited by 129
“A glance at the SoA highlights two main directions: (I) Application-specific architectures based on ASIC/FPGAs [13], [15], [16], [17], [18], [34], [38]; (II) Software implementations on programmable general-purpose platforms such as CPUs and GPUs [13], [30], [39], [40].”
BackgroundKim, Y., Choi, J.-S., & Kim, M. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2864321 · Cited by 107
Jie-Fang, Z., Lee, C., Liu, C., Shao, Y. S., Keckler, S. W., & Zhang, Z. (2020) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2020.3043870 · Cited by 123
Soft errors in DNN accelerators: A comprehensive review
Ibrahim, Y., Wang, H., Liu, J., Wei, J., Chen, L., Rech, P., Adam, K., & Guo, G. (2020) · Microelectronics Reliability · doi:10.1016/j.microrel.2020.113969 · Cited by 102
Blanco‐Filgueira, B., García-Lesta, D., Fernández-Sanjurjo, M., Brea, V. M., & Lopez, P. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2019.2902141 · Cited by 112
Kim, Y., Park, H., Moitra, A., Bhattacharjee, A., Venkatesha, Y., & Panda, P. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9747906 · Cited by 113
DHP19: Dynamic Vision Sensor 3D Human Pose Dataset
Calabrese, E., Taverni, G., Easthope, C. A., Skriabine, S., Corradi, F., Longinotti, L., Eng, K., & Delbruck, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00217 · Cited by 99
“Several hardware accelerators [3, 10] have been developed to take advantage of the activation sparsity by skipping over the zero activations.”
BackgroundSmartShuttle: Optimizing off-chip memory accesses for deep learning accelerators
Li, J., Yan, G., Lü, W., Jiang, S., Gong, S., Wu, J., & Li, X. (2018) · Design, Automation, and Test in Europe · doi:10.23919/date.2018.8342033 · Cited by 115
Jafari, A., Ganesan, A., Thalisetty, C. S. K., Sivasubramanian, V., Oates, T., & Mohsenin, T. (2018) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2018.2848647 · Cited by 103
Nguyen, D. T., Kim, H., & Lee, H.-J. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3020569 · Cited by 97
“le a 32-bit data word access from DRAM (45nm CMOS technology) requires 640pJ [25]. There are a number of previous works designing a single layer accelerator for CNNs [13]-[15], [16], [18], [26]-[29], [31]. These works optimize the processing of a single CNN layer through loop optimization to increase hardware utilizat…”
MethodSiP-ML: high-bandwidth optical network interconnects for machine learning training
Khani, M., Ghobadi, M., Alizadeh, M., Zhu, Z., Glick, M. S., Bergman, K., Vahdat, A. M., Klenk, B., & Ebrahimi, E. (2021) · ACM SIGCOMM Conference (SIGCOMM) · doi:10.1145/3452296.3472900 · Cited by 169
Taurus: a data plane architecture for per-packet ML
Swamy, T., Rucker, A., Shahbaz, M., Gaur, I., & Olukotun, K. (2022) · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · doi:10.1145/3503222.3507726 · Cited by 162
“Other architectures, like Eyeriss [26], Brainwave [49], and EIE [68], achieve high efficiency by focusing on specific algorithms.”
Brain-Inspired Computing: A Systematic Survey and Future Trends
Li, G., Deng, L., Tang, H., Pan, G., Tian, Y., Roy, K., & Maass, W. (2024) · Proceedings of the IEEE · doi:10.1109/jproc.2024.3429360 · Cited by 155
“Deep learning accelerators mainly refer to ANN accelerators [43], [171], [172], [173], [174], [175], [176], [177], [178], [179], [180], [181], [182], which use specific chips to accelerate the execution of ANNs.”
Two-Dimensional Materials for Brain-Inspired Computing Hardware
Hadke, S. S., Kang, M., Sangwan, V. K., & Hersam, M. C. (2025) · Chemical Reviews · doi:10.1021/acs.chemrev.4c00631 · Cited by 112
Hardware for machine learning: Challenges and opportunities
Sze, V., Chen, Y.-H., Emer, J., Suleiman, A., & Zhang, Z. (2018) · 2018 IEEE Custom Integrated Circuits Conference (CICC) · doi:10.1109/cicc.2018.8357072 · Cited by 97
Self-citationLee, Y.-L., Tsung, P.-K., & Wu, M. (2018) · 2018 International Symposium on VLSI Design, Automation and Test (VLSI-DAT) · doi:10.1109/vlsi-dat.2018.8373244 · Cited by 88
“7024 [5] Y.”
BackgroundEdge and Fog Computing Enabled AI for IoT-An Overview
Zou, Z., Jin, Y., Nevalainen, P., Huan, Y., Heikkonen, J., & Westerlund, T. (2019) · IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS) · doi:10.1109/aicas.2019.8771621 · Cited by 116
“CNN processor (Eyeriss) [36] DNN/CNN Accelerator (Imagenet with Row Stationary) 278mW, 7.”
MethodCamus, V., Mei, L., Enz, C., & Verhelst, M. (2019) · IEEE Journal on Emerging and Selected Topics in Circuits and Systems · doi:10.1109/jetcas.2019.2950386 · Cited by 110
“SA-ST arrays contain a 1D vector of PEs per accumulation island whose results are added together, either in a systolic way [24], [25] or through a single-cycle accumulator [26], [27].”
BackgroundComprehensive SNN Compression Using ADMM Optimization and Activity Regularization
Deng, L., Wu, Y., Hu, Y., Liang, L., Li, G., Hu, X., Ding, Y., Li, P., & Xie, Y. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3109064 · Cited by 134
Multiply accumulate operations in memristor crossbar arrays for analog computing
Chen, J., Li, J., Li, Y., & Miao, X. (2021) · Journal of Semiconductors · doi:10.1088/1674-4926/42/1/013104 · Cited by 109
AI Accelerator Survey and Trends
Reuther, A., Michaleas, P. W., Jones, M. P., Gadepally, V. N., Samsi, S., & Kepner, J. (2021) · IEEE High Performance Extreme Computing Conference · doi:10.1109/hpec49654.2021.9622867 · Cited by 124
“Research chips including Eyeriss [16], [126], [127], EIE [128], Tetris [129], Tianjic [130], the DianNao family [131], Adapteva [132], [133],”
BackgroundDNN Engine: A 28-nm Timing-Error Tolerant Sparse Deep Neural Network Processor for IoT Applications
Whatmough, P. N., Lee, S. K., Brooks, D., & Wei, G.-Y. (2018) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2018.2841824 · Cited by 96
“Several works have previously described specialized architectures in silicon for CNNs, often focusing on computer vision tasks [2]–[7], such as classifying the ImageNet data set.”
BackgroundSupporting peripherals in intermittent systems with just-in-time checkpoints
Maeng, K., & Lucia, B. (2019) · ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI) · doi:10.1145/3314221.3314613 · Cited by 124
“Then, we multiply the DRAM access numbers given by the paper [11] with an FRAM access energy of 0.”
MethodTowards Real-Time Object Detection on Embedded Systems
Mao, H., Yao, S., Tang, T., Li, B., Yao, J., & Wang, Y. (2018) · IEEE Transactions on Emerging Topics in Computing · doi:10.1109/tetc.2016.2593643 · Cited by 94
Parallelizing SRAM Arrays with Customized Bit-Cell for Binary Neural Networks
Liu, R., Peng, X., Sun, X., Khwa, W.-S., Si, X., Chen, J., Li, J., Chang, M., & Yu, S. (2018) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1145/3195970.3196089 · Cited by 107
“In BNNs proposed in [4,5], both the weights and activations are generally constrained to +1/-1.”
BackgroundSilicon Photonics Codesign for Deep Learning
Cheng, Q., Kwon, J., Glick, M. S., Bahadori, M., Carloni, L. P., & Bergman, K. (2020) · Proceedings of the IEEE · doi:10.1109/jproc.2020.2968184 · Cited by 108
“Although GPUs, FPGAs, and application-specific integrated circuits (ASICs) have received extensive interest for developing dedicated hardware accelerators in deeplearning calculations [22]–[24], photonics has long been recognized as a promising alternative to address the fanin and fan-out problems for linear algebra p…”
BackgroundToward Functional Safety of Systolic Array-Based Deep Learning Hardware Accelerators
Kundu, S., Banerjee, S., Raha, A., Natarajan, S., & Basu, K. (2021) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2020.3048829 · Cited by 107
ALAMO: FPGA acceleration of deep learning algorithms with a modularized RTL compiler
Ma, Y., Suda, N., Cao, Y., Vrudhula, S., & Seo, J.-S. (2018) · Integration · doi:10.1016/j.vlsi.2017.12.009 · Cited by 93
On the Resilience of RTL NN Accelerators: Fault Characterization and Mitigation
Salami, B., Ünsal, O., & Kestelman, A. C. (2018) · International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD) · doi:10.1109/cahpc.2018.8645906 · Cited by 114
Zhao, T., Xie, Y., Wang, Y., Cheng, J., Guo, X., Hu, B., & Chen, Y. (2022) · Proceedings of the IEEE · doi:10.1109/jproc.2022.3153408 · Cited by 92
Self-citationAre SNNs Really More Energy-Efficient Than ANNs? an In-Depth Hardware-Aware Study
Dampfhoffer, M., Mesquida, T., Valentian, A., & Anghel, L. (2022) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2022.3214509 · Cited by 113
“The results are shown for the AlexNet, VGG16 and MobileNet topologies, having Nsyn/Nneur = 2.9 × 103, 1.7 × 103, 9.4 × 102, respectively.”
BackgroundMethodInfluentialGANAX: A Unified MIMD-SIMD Acceleration for Generative Adversarial Networks
Yazdanbakhsh, A., Falahati, H., Wolfe, P. J., Esmaeilzadeh, H., & Samadi, K. (2018) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1109/isca.2018.00060 · Cited by 109
“zero-insertion and variable number of operations per each convolution window) in GANs poses unique architectural challenges that the traditional convolution accelerators [16]–[18], [20], [22] can not adequately address.”
BackgroundMethodInfluentialA TinyML Platform for On-Device Continual Learning With Quantized Latent Replays
Ravaglia, L., Rusci, M., Nadalini, D., Capotondi, A., Conti, F., & Benini, L. (2021) · IEEE Journal on Emerging and Selected Topics in Circuits and Systems · doi:10.1109/jetcas.2021.3121554 · Cited by 132
“Most efforts in this direction employ a variety of inferenceonly acceleration techniques such as pruning [33] and byte and sub-byte integer quantization [4]; the use of large arrays of simple MAC units [34] or even mixed-signal techniques such as in-memory computing [35].”
MethodBoroumand, A., Ghose, S., Akin, B., Narayanaswami, R., Junior, G. F. D. O., Ma, X., Shiu, E., & Mutlu, O. (2021) · International Conference on Parallel Architectures and Compilation Techniques (PACT) · doi:10.1109/pact52795.2021.00019 · Cited by 153
Edge Intelligence: A Review of Deep Neural Network Inference in Resource-Limited Environments
Ngo, D., Park, H.-C., & Kang, B. (2025) · Electronics · doi:10.3390/electronics14122495 · Cited by 154
Snowflake: An efficient hardware accelerator for convolutional neural networks
Gokhale, V., Zaidy, A., Chang, A. X. M., & Culurciello, E. (2017) · 2017 IEEE International Symposium on Circuits and Systems (ISCAS) · doi:10.1109/iscas.2017.8050809 · Cited by 90
Accelerating CNN Inference on ASICs: A Survey
Moolchandani, D., Kumar, A., & Sarangi, S. R. (2020) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2020.101887 · Cited by 108
“Finally, the all-in-one reuse architecture called the Row stationary (RS) dataflow [26] (see Figure 13(d)) reuses all the types of data – weights, activations and partial sums – at the register file.”
MethodHigh Performance CNN Accelerators Based on Hardware and Algorithm Co-Optimization
Yuan, T., Liu, W., Han, J., & Lombardi, F. (2020) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2020.3030663 · Cited by 102
“A tiling technique [16], [5] has widely been used to address insufficient memory in embedded architectures.”
MethodInfluentialSextans: A Streaming Accelerator for General-Purpose Sparse-Matrix Dense-Matrix Multiplication
Song, L., Chi, Y., Sohrabizadeh, A., Choi, Y., Lau, J., & Cong, J. (2022) · ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA) · doi:10.1145/3490422.3502357 · Cited by 121
Reconfigurable Compute-In-Memory on Field-Programmable Ferroelectric Diodes
Liu, X., Ting, J., He, Y., Fiagbenu, M. M. A., Zheng, J. X., Wang, D., Frost, J., Musavigharavi, P., Esteves, G., Kisslinger, K., et al. (2022) · Nano Letters · doi:10.1021/acs.nanolett.2c03169 · Cited by 100
“The increasingly ubiquitous presence of sensors and edge/IoT devices has created a flood of data, which has exposed a wide efficiency gap in computing hardware, ranging from mobile and edge devices to data centers and cloud computing hardware [4-5].”
BackgroundEVA²: Exploiting Temporal Redundancy in Live Computer Vision
Buckler, M., Bedoukian, P., Jayasuriya, S., & Sampson, A. (2018) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1109/isca.2018.00051 · Cited by 115
“Eyeriss’s use of off-chip DRAM is representative of other CNN ASIC designs [3].”
BackgroundInfluentialZhang, J., Rangineni, K., Ghodsi, Z., & Garg, S. (2018) · Proceedings of the 55th Annual Design Automation Conference · doi:10.1145/3195970.3196129 · Cited by 87
“In Figure 7, we use the test dataset to compare the energy consumption of ThVolt-Dynamic with (a) the baseline TPU (base); (b) Zero-Skip [1, 7, 22, 29, 32], that saves energy at run-time by skipping over all MAC operations with zero weights and/or activations, and (c) Zero-Skip+ThVolt-Dynamic, that applies ThVolt-Dyna…”
BackgroundMethodInfluentialHW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmark
Li, C., Yu, Z., Fu, Y., Zhang, Y., Zhao, Y., You, H., Yu, Q., Wang, Y., & Lin, Y. C. (2021) · arXiv · doi:10.48550/arxiv.2103.10584 · Cited by 88
Shan, W., Yang, M., Wang, T., Lu, Y., Cai, H., Zhu, L., Xu, J., Wu, C., Shi, L., & Yang, J. (2020) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2020.3029097 · Cited by 94
SkyNet: a Hardware-Efficient Method for Object Detection and Tracking on Embedded SystemsPreprint
Zhang, X., Lu, H., Hao, C., Li, J., Cheng, B., Li, Y., Rupnow, K., Xiong, J., Huang, T. S., Shi, H., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.09709 · Cited by 111
“Recently, we have seen intensive studies on DNN accelerators in hardware, which attempt to take advantage of different hardware design styles, such as GPUs, FPGAs and ASICs, to improve the speed and efficiency of DNN inference and training processes (Qiu et al., 2016; Chen et al., 2016; Zhang et al., 2017a; Jouppi et…”
BackgroundModels of Learning to Classify X-ray Images for the Detection of Pneumonia using Neural Networks
Saraiva, A. A., dos Santos, D. A. M., da Costa, N. J. C., Sousa, J., Ferreira, N. M. F., Valente, A. L. G., & Soares, S. (2019) · International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC) · doi:10.5220/0007346600760083 · Cited by 87
“Each neuron receives some inputs, applies the scalar product of inputs and weights in addition to a non-linear function (Chen et al., 2017).”
BackgroundNeuromorphic-enabled video-activated cell sorting
He, W., Zhu, J., Feng, Y., Liang, F., You, K., Chai, H., Sui, Z., Hao, H., Li, G., Zhao, J., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-55094-0 · Cited by 95
dMazeRunner: Executing Perfectly Nested Loops on Dataflow Accelerators
Dave, S., Kim, Y., Avancha, S., Lee, K., & Shrivastava, A. (2019) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3358198 · Cited by 106
“For example, [3, 12] offered specific ways of spatiotemporal execution of convolutions, which are not always very efficient.”
BackgroundMethodInfluentialAn Overview of Efficient Interconnection Networks for Deep Neural Network Accelerators
Nabavinejad, S. M., Baharloo, M. M., Chen, K.-C. J., Palesi, M., Kogel, T., & Ebrahimi, M. (2020) · IEEE Journal on Emerging and Selected Topics in Circuits and Systems · doi:10.1109/jetcas.2020.3022920 · Cited by 95
Custom Hardware Architectures for Deep Learning on Portable Devices: A Review
Zaman, K. S., Reaz, M. B. I., Ali, S. H. M., Bakar, A. A. A., & Chowdhury, M. E. H. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3082304 · Cited by 102
An Electro-Photonic System for Accelerating Deep Neural Networks
Demirkiran, C., Eris, F., Wang, G., Elmhurst, J., Moore, N., Harris, N. C., Basumallik, A., Reddi, V. J., Joshi, A., & Bunandar, D. (2023) · ACM Journal on Emerging Technologies in Computing Systems · doi:10.1145/3606949 · Cited by 104
“For completeness, in this section, we compare the full ADEPT system against state-of-the-art electronic [15,18,42, 46] and photonic [49,54,69] accelerators.”
MethodDual Dynamic Inference: Enabling More Efficient, Adaptive, and Controllable Deep Inference
Wang, Y., Shen, J., Hu, T.-K., Xu, P., Nguyen, T. M., Baraniuk, R. G., Wang, Z., & Lin, Y. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.2979669 · Cited by 108
Bio‐Inspired 3D Artificial Neuromorphic Circuits
Liu, X., Wang, F., Su, J., Zhou, Y., & Ramakrishna, S. (2022) · Advanced Functional Materials · doi:10.1002/adfm.202113050 · Cited by 91
Meta-optic accelerators for object classifiers
Zheng, H., Liu, Q., Zhou, Y., Kravchenko, I. I., Huo, Y., & Valentine, J. (2022) · Science Advances · doi:10.1126/sciadv.abo6410 · Cited by 98
“…impactful when used for the linear matrix-vector multiplications 10, 11 that comprise the convolution operations in DNNs as these are often the most computationally burdensome components typically comprising more than 90% of the required floating-point operations (FLOPs) in popular CNNs 12, 13 .”
BackgroundA Survey on Deep-Learning-Based Real-Time SAR Ship Detection
Li, J., Chen, J., Cheng, P., Yu, Z., Yu, L., & Chi, C. (2023) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2023.3244616 · Cited by 98
Hardware Trojan Design on Neural Networks
Clements, J., & Lao, Y. (2019) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.2019.8702493 · Cited by 100
Emerging memory technologies for neuromorphic computing
Kim, C.-H., Lim, S., Woo, S. Y., Kang, W.-M., Seo, Y.-T., Lee, S., Lee, S., Kwon, D., Oh, S., Noh, Y., et al. (2018) · Nanotechnology · doi:10.1088/1361-6528/aae975 · Cited by 91
Review of ASIC accelerators for deep neural network
Machupalli, R., Hossain, M., & Mandal, M. K. (2022) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2022.104441 · Cited by 108
Euphrates: Algorithm-SoC Co-Design for Low-Power Mobile Continuous Vision
Zhu, Y., Samajdar, A., Mattina, M., & Whatmough, P. N. (2018) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1109/isca.2018.00052 · Cited by 106
Ibrahum, A. D. M., Hussain, M., & Hong, J. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-11014-8 · Cited by 131
AtomLayer: A Universal ReRAM-Based CNN Accelerator with Atomic Layer Computation
Qiao, X., Cao, X., Yang, H., Song, L., & Li, H. H. (2018) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1145/3195970.3195998 · Cited by 122
“Custom DNN accelerators such as Google TPU [7] and Eyeriss [8] have been proposed.”
MethodFreely scalable and reconfigurable optical hardware for deep learning
Bernstein, L., Sludds, A., Hamerly, R., Sze, V., Emer, J., & Englund, D. R. (2021) · Scientific Reports · doi:10.1038/s41598-021-82543-3 · Cited by 107
Self-citationHow to Evaluate Deep Neural Network Processors: TOPS/W (Alone) Considered Harmful
Sze, V., Chen, Y.-H., Yang, T.-J., & Emer, J. S. (2020) · IEEE Solid-State Circuits Magazine · doi:10.1109/mssc.2020.3002140 · Cited by 80
“The mapping process, on a layer-by-layer basis, is explored in detail in [12]–[14].”
Self-citationRaPiD: AI Accelerator for Ultra-low Precision Training and Inference
Venkataramani, S., Srinivasan, V., Wang, W., Sen, S., Zhang, J., Agrawal, A., Kar, M., Jain, S., Mannari, A., Tran, H., et al. (2021) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1109/isca52012.2021.00021 · Cited by 120
“This has led to many academic demonstrations and commercial AI cores exploiting systolic dataflow architectures [23, 25, 26, 30, 47, 48, 49].”
BackgroundDeng, C., Sui, Y., Liao, S., Qian, X., & Yuan, B. (2021) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1109/isca52012.2021.00090 · Cited by 97
Drawing Early-Bird Tickets: Toward More Efficient Training of Deep NetworksPreprint
You, H., Li, C., Xu, P., Fu, Y., Wang, Y., Chen, X., Lin, Y., Wang, Z., & Baraniuk, R. G. (2020) · arXiv (Cornell University) · Cited by 94
Liu, X., Yang, J., Zou, C., Chen, Q., Yan, X., Chen, Y., & Cai, C. (2022) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2021.3059318 · Cited by 79
Self-citationAccelerating Neural Network Inference on FPGA-Based Platforms—A Survey
Wu, R., Guo, X., Du, J., & Li, J. (2021) · Electronics · doi:10.3390/electronics10091025 · Cited by 79
“Eyeriss v2 [96] integrates a new PE architecture that enables sparse weights and input activations to be handled directly in the compressed domain, resulting in not only energy efficiency but also throughput improvement.”
BackgroundLearning-Based Frequency Estimation Algorithms.
Hsu, C.-Y., Indyk, P., Katabi, D., & Vakilian, A. (2018) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 116
TensorDash: Exploiting Sparsity to Accelerate Deep Neural Network Training
Mahmoud, M., Edo, I., Zadeh, A. H., Awad, O. M., Pekhimenko, G. G., Albericio, J., & Moshovos, A. (2020) · IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1109/micro50266.2020.00069 · Cited by 91
“which is referred to as sparsity [5], [11], [18], [25], [27], [40], [48], [60], [79], [82].”
Sparseloop: An Analytical Approach To Sparse Tensor Accelerator Modeling
Wu, Y. N., Tsai, P.-A., Parashar, A., Sze, V., & Emer, J. (2022) · IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1109/micro56248.2022.00096 · Cited by 113
“For example, Eyeriss [8] uses a row-stationary dataflow, a RLC encoding for data stored in DRAM, and storage and compute units that stay idle for IneffOps.”
BackgroundMethodInfluentialSelf-citationPIMCA: A Programmable In-Memory Computing Accelerator for Energy-Efficient DNN Inference
Zhang, B., Yin, S., Kim, M., Saikia, J., Kwon, S., Myung, S., Kim, H., Kim, S. J., Seo, J.-S., & Seok, M. (2022) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2022.3211290 · Cited by 80
Testability and Dependability of AI Hardware: Survey, Trends, Challenges, and Perspectives
Su, F., Liu, C., & Stratigopoulos, H. (2023) · IEEE Design and Test · doi:10.1109/mdat.2023.3241116 · Cited by 97
RANA: Towards Efficient Neural Acceleration with Refresh-Optimized Embedded DRAM
Tu, F., Wu, W., Yin, S., Liu, L., & Wei, S. (2018) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1109/isca.2018.00037 · Cited by 91
Transform Quantization for CNN Compression
Young, S. I., Wang, Z., Taubman, D., & Girod, B. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3084839 · Cited by 110
“We measure speed up from transform quantization on high-performance DNN-targeted hardware accelerators Google TPU [82] and MIT Eyeriss [83], adopting SCALE-sim [84] to simulate the time cycles of MobileNet-v2 quantized using our approach or using HAQ [46].”
MethodLi, W., Sun, X., Huang, S., Jiang, H., & Yu, S. (2022) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2022.3163197 · Cited by 77
Rapuano, E., Meoni, G., Pacini, T., Dinelli, G., Furano, G., Giuffrida, G., & Fanucci, L. (2021) · Remote Sensing · doi:10.3390/rs13081518 · Cited by 96
Applications and Techniques for Fast Machine Learning in Science
Deiana, A. M., Tran, N. V., Agar, J., Blott, M., Guglielmo, G. D., Duarte, J. M., Harris, P. C., Hauck, S., Liu, M., Neubauer, M. S., et al. (2022) · Frontiers in Big Data · doi:10.3389/fdata.2022.787421 · Cited by 126
Designing Novel AAD Pooling in Hardware for a Convolutional Neural Network Accelerator
Khalil, K., Eldash, O., Kumar, A., & Bayoumi, M. (2022) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2021.3139904 · Cited by 83
Yue, J., Liu, Y., Yuan, Z., Feng, X., He, Y., Sun, W., Zhang, Z., Si, X., Liu, R., Wang, Z., et al. (2022) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2022.3148273 · Cited by 83
Li, J., Shen, G., Zhao, D., Zhang, Q., & Zeng, Y. (2023) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2023.3279349 · Cited by 77
Jain, S., Tsai, H., Chen, C.-T., Muralidhar, R., Boybat, I., Frank, M. M., Woźniak, S., Stanisavljevic, M., Adusumilli, P., Narayanan, P., et al. (2023) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2022.3221390 · Cited by 76
Analytical guarantees on numerical precision of deep neural networks
Sakr, C., Kim, Y., & Shanbhag, N. R. (2017) · Open Access System for Information Sharing (Pohang University of Science and Technology) · Cited by 104
Metadata
- Authors
- Chen, Y.-H., Krishna, T., Emer, J. S., & Sze, V.
- Affiliations
- Massachusetts Institute of Technology (US)
- Georgia Institute of Technology (US)
- Nvidia (United States) (US)
- Venue
- IEEE Journal of Solid-State Circuits
- Published
- 2017-01
- Volume
- 52
- Issue
- 1
- Pages
- 127-138
- ISSN
- 0018-9200 (ISSN-L)
- 1558-173X
- OpenAlex
- W2289252105
- Semantic Scholar
- ffdaa12ef011de9dbf43be46d45a3abcc8288965
- Cited by
- 3,247
- References
- 42
- Citations by year
- 2026: 218 · 2025: 313 · 2024: 294 · 2023: 373 · 2022: 365 · 2021: 450 · 2020: 427 · 2019: 354 · 2018: 302 · 2017: 118
- FWCI
- 182.12
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Journal of Solid-State Circuits (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
- Keywords
- reconfigurable accelerators, deep convolutional neural networks, energy efficiency, spatial architecture, data movement reduction, data compression, processing elements, AlexNet, VGG16, convolutional layers
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.