A dynamically configurable coprocessor for convolutional neural networks
The DOI matches its Crossref record; 34 of the 36 references it cites were found in a registry or an index.
Abstract
Convolutional neural networks (CNN) applications range from recognition and reasoning (such as handwriting recognition, facial expression recognition and video surveillance) to intelligent text applications such as semantic text analysis and natural language processing applications. Two key observations drive the design of a new architecture for CNN. First, CNN workloads exhibit a widely varying mix of three types of parallelism: parallelism within a convolution operation, intra-output parallelism where multiple input sources (features) are combined to create a single output, and inter-output parallelism where multiple, independent outputs (features) are computed simultaneously. Workloads differ significantly across different CNN applications, and across different layers of a CNN. Second, the number of processing elements in an architecture continues to scale (as per Moore's law) much faster than off-chip memory bandwidth (or pin-count) of chips. Based on these two observations, we show that for a given number of processing elements and off-chip memory bandwidth, a new CNN hardware architecture that dynamically configures the hardware on-the-fly to match the specific mix of parallelism in a given workload gives the best throughput performance. Our CNN compiler automatically translates high abstraction network specification into a parallel microprogram (a sequence of low-level VLIW instructions) that is mapped, scheduled and executed by the coprocessor. Compared to a 2.3 GHz quad-core, dual socket Intel Xeon, 1.35 GHz C870 GPU, and a 200 MHz FPGA implementation, our 120 MHz dynamically configurable architecture is 4x to 8x faster. This is the first CNN architecture to achieve real-time video stream processing (25 to 30 frames per second) on a wide range of object detection and recognition tasks.
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 [16]
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
Histograms 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
Neural Networks And Learning Machines
Haykin, S. (2010) · Cited by 7,534
A unified architecture for natural language processing: deep neural networks with multitask learning
Collobert, R., & Weston, J. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390177 · Cited by 5,058 · cited 1×
“Feed-forward, multi-layer artificial neural networks like the Convolutional Neural Networks (CNN) [2][11][13][16][17][20][23] have found increasing use in several new applications because they have the potential to process vast amounts of labeled data to automatically learn and extract complex…”
BackgroundFace recognition: a convolutional neural-network approach
Lawrence, S., Giles, C. L., Tsoi, A. C., & Back, A. D. (1997) · IEEE Transactions on Neural Networks · doi:10.1109/72.554195 · Cited by 3,092
Lee, H., Grosse, R., Ranganath, R., & Ng, A. Y. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553453 · Cited by 2,412
Object 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
Large-scale deep unsupervised learning using graphics processors
Raina, R., Madhavan, A., & Ng, A. Y. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553486 · Cited by 742 · cited 2×
“…to match the exact computational workload of any layer of a CNN. Note that by replacing the convolver primitive with a different functional unit, we can easily implement different feed-forward neural networks and classifiers such as HMAX [17][27], Deep Belief Networks [29][30] and HoG methods [28].”
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
Fast support vector machine training and classification on graphics processors
Catanzaro, B., Sundaram, N., & Keutzer, K. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390170 · Cited by 372
Cited by
Items 301–350 of 350
An Efficient Dataflow Mapping Method for Convolutional Neural Networks
Liu, Z., Gu, H., Zhang, B., & Shi, C. (2021) · Neural Processing Letters · doi:10.1007/s11063-021-10670-z · Cited by 2
S-SIM: A Simulator for Systolic Array-based DNN Accelerators with Tile Access Awareness
Li, Y., Wen, M., Yang, R., Shen, J., Cao, Y., & Wang, J.-A. (2022) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas48785.2022.9937624 · Cited by 2
Architectures for Machine Learning
Yang, Y., Chen, C., & Wang, Z. (2024) · Springer eBooks · doi:10.1007/978-981-97-9314-3_12 · Cited by 2
Tuning Algorithms and Generators for Efficient Edge InferencePreprint
Naous, R., Supic, L., Kang, Y., Sredojević, R., Singhani, A., & Stojanovic, V. M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.02239 · Cited by 2
DATE: Defense Against TEmperature Side-Channel Attacks in DVFS Enabled MPSoCsPreprint
Dey, S., Singh, A. K., Wang, X., & McDonald-Maier, K. D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.01377 · Cited by 2
Tackling Variabilities in Autonomous DrivingPreprint
Qi, Y., Hu, Y., Wu, H., Li, S., Mao, H., Ye, X., Fan, D., & Sun, N. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.10415 · Cited by 3
Design and Implementation of UVM-based Verification Framework for Deep Learning Accelerators
Ragavi, D., Varni, S., Begum, M. M., Lavanya, M., & Divyadharshini, N. (2025) · International Conference on Smart Computing and Communications (ICSCC) · doi:10.1109/icscc66177.2025.11233731 · Cited by 1
Optimization of Convolution Neural Network Algorithm Based on FPGA
Tang, F., Zhang, W., Tian, X., Fan, X., & Cao, X. (2018) · Communications in computer and information science · doi:10.1007/978-981-13-1026-3_10 · Cited by 1
Elasto-Net: An HDL Conversion Framework For Convolutional Neural Networks
Ansari, A., & Ogunfunmi, T. (2018) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/acssc.2018.8645344 · Cited by 1
Ramadurgam, S. (2021) · Digital Collections of Colorado (Colorado State University) · Cited by 9
A Survey Paper on Acceleration of Convolutional Neural Network using Field Programmable Gate Arrays
Doifode, J., Sadakale, R., & Patil, R. A. (2021) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt51525.2021.9580053 · Cited by 1
Reconfigurable Architecture and Dataflow for Memory Traffic Minimization of CNNs Computation
Cheng, W., Liu, X., Wu, H.-T., Pai, H.-Y., & Chung, P.-Y. (2021) · Micromachines · doi:10.3390/mi12111365 · Cited by 1
Método para execução de redes neurais convolucionais em FPGA.
de Sousa, M. C. F. (2019) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.3.2019.tde-14082019-110912 · Cited by 1
Securing edge deep neural network against input evasion and IP theft
Wang, S. (2021) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/152267 · Cited by 1
Dey, S., Saha, S., Singh, A. K., & McDonald-Maier, K. D. (2020) · doi:10.36227/techrxiv.12686051.v1 · Cited by 3
Hardware accelerated simulation and automatic design of heterogeneous architecture
Cong, T. (2023) · theses.fr (ABES) · doi:10.70675/2095a8aaz6695z4be9za7d6ze515295f5eaf · Cited by 1
Intelligent Vision Systems: Exploring the State-of-the-Art and Opportunities for the Future
Advani, S., Kestur, S., & Narayanan, V. (2015) · IEEE International Symposium on Nanoelectronic and Information Systems (iNIS) · doi:10.1109/inis.2015.69
The Human Body Edge Detection of Infrared Image with IGA_CNN Algorithm
Hu, G., & Yuenyong, S. (2016) · Science & Technology Asia · doi:10.14456/tijsat.2016.6
Automating the generation of hardware accelerators from custom arithmetic functions
Petrousov, I., & Dasygenis, M. (2017) · Panhellenic Conference on Informatics · doi:10.1145/3139367.3139421
Exploring Convolutional Neural Networks on the ρ-VEX architecture
Tetteroo, J. (2018) · Research Repository (Delft University of Technology)
Li, Z., Li, J., Ren, A., Ding, C., Draper, J. T., Qiu, Q., Yuan, B., & Wang, Y. (2018) · IEEE Computer Society Annual Symposium on VLSI · doi:10.1109/isvlsi.2018.00016 · Cited by 3
Hardware Development for Non-Hardware Engineers
Richmond, D. A. (2018) · eScholarship (California Digital Library)
DeCoILFNet: Depth Concatenation and Inter-Layer Fusion based ConvNet AcceleratorPreprint
Baranwal, A., Bansal, I., Nahar, R., & Krishna, K. M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.02774
Accelerating Backward Convolution of Convolutional Neural Networks on BWDSP
Yang, J., Zheng, Q., Gai, W., & Maohui, L. (2018) · International Symposium on Parallel Architectures, Algorithms and Programming · doi:10.1109/paap.2018.00036
Many Universal Convolution Cores for Ensemble Sparse Convolutional Neural Networks
Kuramochi, R., Sada, Y., Shimoda, M., Sato, S., & Nakahara, H. (2019) · IEEE International Symposium on Embedded Multicore/Many-core Systems-on-Chip (MCSoC) · doi:10.1109/mcsoc.2019.00021
A Convolutional Neural Networks Accelerator Based on Parallel Memory
Tan, H., Liu, S., Chen, H., Sun, H., & Li, H. (2019) · Communications in computer and information science · doi:10.1007/978-981-15-1850-8_15
Programmable Address Generation Unit for Deep Neural Network Accelerators
Khan, M. J. (2020) · KTH Publication Database DiVA (KTH Royal Institute of Technology)
A Power-Efficient Programmable DCNN Processor for Intelligent Sensing
Wang, B., Gan, J., Xie, Y., Wang, Y., Xiao, Z., & Zhou, J. (2019) · IEEE International System-on-Chip Conference (SOCC) · doi:10.1109/socc46988.2019.1570553982
TMAV: Temporal Motionless Analysis of Video using CNN in MPSoCPreprint
Dey, S., Singh, A. K., Prasad, D. K., & McDonald-Maier, K. D. (2019) · doi:10.36227/techrxiv.10128359
Design Space Exploration Scheme for Mapping Convolutional Neural Network on Zynq Zedboard
Hassan, M. S. U., Khan, U. S., & Khawaja, S. G. (2020) · International Conference on Electronics, Computers and Artificial Intelligence (ECAI) · doi:10.1109/ecai50035.2020.9223137
Accelerating two dimensional FFT and convolutional neural networks on FPGA
Kala, S., & Jose, B. R. (2020) · Dyuthi Digital Repository (Cochin University of Science and Technology)
From Compute to Data: Across-the-Stack System Design for Intelligent Applications
Kang, Y. (2018) · Deep Blue (University of Michigan)
Computing Framework for Autonomous Driving
Shi, W., & Liu, L. (2021) · Springer eBooks · doi:10.1007/978-3-030-81564-6_2
Master-slave based test cost reduction method for DNN accelerators
Solangi, U. S., Ibtesam, M., & Park, S. (2021) · IEICE Electronics Express · doi:10.1587/elex.18.20210425
Knee Lift Detection using Convolutional Neural Network Method with FPGA Hardware Design
Chen, T.-C., Luo, Y.-J., Wan, W.-C., & Tsai, T. (2021) · IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) · doi:10.1109/icce-tw52618.2021.9603148
Dey, S., Saha, S., Singh, A. K., & McDonald-Maier, K. D. (2020) · doi:10.36227/techrxiv.12686051
Lee, J., Han, S., Choi, S., & Choi, J. (2022) · Electronics · doi:10.3390/electronics11131996
TMAV: Temporal Motionless Analysis of Video using CNN in MPSoCPreprint
Dey, S., Singh, A. K., Prasad, D. K., & McDonald-Maier, K. D. (2019) · doi:10.36227/techrxiv.10128359.v2
A Compressed Data Partition and Loop Scheduling Scheme for Neural Networks
Li, D., Fang, R., Wang, J., Zhao, D., Chong, T., Ren, Z., & Ma, J. (2022) · IEEE Access · doi:10.1109/access.2022.3204038
Convolution tensor slicing optimization for multicore NPUs
Sousa, R. C. F. (2023) · doi:10.47749/t/unicamp.2023.1374643
A real-time demonstrator for image classification using FPGA-based logic neural networks
Concha, D., García-Espinosa, F. J., Ramírez, I., & Aranda, L. A. (2024) · Real-time Processing of Image, Depth, and Video Information · doi:10.1117/12.3017459
Deep Learning Optimization and Acceleration
Jiang, B. (2022) · University of North Texas Digital Library (University of North Texas) · doi:10.12794/metadc1986716
Zhang, M., Liu, R., Li, P., & Han, J. (2025) · International Symposium on New Energy Technologies and Power Systems (NETPS) · doi:10.1109/netps65392.2025.11101990
Energy Analysis of Row-Stationary Dataflow in CNN Computation on Microcontrollers
Koppala, M. R. (2024) · Qucosa - Monarch (Chemnitz University of Technology) · doi:10.60687/2025-0048
Hardware Accelerators for Machine Learning Applications. Case Study : Autonomous Vehicles
Neggaz, M. A. (2020) · theses.fr (ABES) · doi:10.70675/09cf40c0z17a0z4efbz8c0fzb956e149d59c · Cited by 1
Oudrhiri, A. (2023) · theses.fr (ABES) · doi:10.70675/2609bad0z35acz4e0dz9fa3zd4505963159d
Metadata
- Authors
- Chakradhar, S., Sankaradas, M., Jakkula, V., & Cadambi, S.
- Affiliations
- NEC Laboratories America, Inc., Princeton, NJ, USA
- Venue
- Proceedings of the 37th annual international symposium on Computer architecture
- Publisher
- ACM
- Published
- 2010-06-19
- Pages
- 247-257
- ISSN
- 1063-6897 (ISSN-L)
- OpenAlex
- W2009832130
- Cited by
- 343
- References
- 36
- Citations by year
- 2025: 3 · 2024: 8 · 2023: 11 · 2022: 17 · 2021: 25 · 2020: 46 · 2019: 49 · 2018: 51 · 2017: 56 · 2016: 42 · 2015: 14 · 2014: 9 · 2013: 2 · 2012: 7
- FWCI
- 2.33
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Proceedings - International Symposium on Computer Architecture/Proceedings (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Hardware and Architecture › Embedded Systems Design Techniques
- Keywords
- convolutional neural networks, coprocessor architecture, parallelism, off-chip memory bandwidth, object detection, image recognition
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.