The DOI matches its Crossref record; 40 of the 40 references it cites were found in a registry or an index.
In-Datacenter Performance Analysis of a Tensor Processing Unit
Abstract
Many architects believe that major improvements in cost-energy-performance must now come from domain-specific hardware. This paper evaluates a custom ASIC---called a Tensor Processing Unit (TPU) --- deployed in datacenters since 2015 that accelerates the inference phase of neural networks (NN). The heart of the TPU is a 65,536 8-bit MAC matrix multiply unit that offers a peak throughput of 92 TeraOps/second (TOPS) and a large (28 MiB) software-managed on-chip memory. The TPU's deterministic execution model is a better match to the 99th-percentile response-time requirement of our NN applications than are the time-varying optimizations of CPUs and GPUs that help average throughput more than guaranteed latency. The lack of such features helps explain why, despite having myriad MACs and a big memory, the TPU is relatively small and low power. We compare the TPU to a server-class Intel Haswell CPU and an Nvidia K80 GPU, which are contemporaries deployed in the same datacenters. Our workload, written in the high-level TensorFlow framework, uses production NN applications (MLPs, CNNs, and LSTMs) that represent 95% of our datacenters' NN inference demand. Despite low utilization for some applications, the TPU is on average about 15X -- 30X faster than its contemporary GPU or CPU, with TOPS/Watt about 30X -- 80X higher. Moreover, using the CPU's GDDR5 memory in the TPU would triple achieved TOPS and raise TOPS/Watt to nearly 70X the GPU and 200X the CPU.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
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
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
Identity mappings in deep residual networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_38 · Cited by 10,741
Identity Mappings in Deep Residual Networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · arXiv · doi:10.48550/arxiv.1603.05027 · Cited by 10,665
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., et al. (2016) · arXiv · doi:10.48550/arxiv.1603.04467 · Cited by 9,408
Self-citationGoogle's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
Wu, Y., Schuster, M., Chen, Z., Le, Q. V., Norouzi, M., Macherey, W., Krikun, M., Cao, Y., Gao, Q., Macherey, K., et al. (2016) · arXiv · doi:10.48550/arxiv.1609.08144 · Cited by 5,319
Self-citationWilliams, S., Waterman, A., & Patterson, D. A. (2009) · Communications of the ACM · doi:10.1145/1498765.1498785 · Cited by 2,798
Self-citationThe Case for Energy-Proportional Computing
Barroso, L. A., & Hölzle, U. (2007) · Computer · doi:10.1109/mc.2007.443 · Cited by 2,491
Optimizing FPGA-based Accelerator Design for Deep Convolutional Neural Networks
Zhang, C., Li, P., Sun, G., Guan, Y., Xiao, B., & Cong, J. (2015) · Proceedings of the 2015 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays · doi:10.1145/2684746.2689060 · Cited by 2,158
Dean, J., & Barroso, L. A. (2013) · Communications of the ACM · doi:10.1145/2408776.2408794 · Cited by 1,852
Self-citationThe Handbook of brain theory and neural networks
(2003) · Choice Reviews Online · doi:10.5860/choice.41-0300 · Cited by 1,524
DianNao: a small-footprint high-throughput accelerator for ubiquitous machine-learning
Chen, T., Du, Z., Sun, N., Wang, J., Wu, C., Chen, Y., & Temam, O. (2014) · Proceedings of the 19th international conference on Architectural support for programming languages and operating systems · doi:10.1145/2541940.2541967 · Cited by 1,297
Eyeriss: a spatial architecture for energy-efficient dataflow for convolutional neural networks
Chen, Y.-H., Emer, J., & Sze, V. (2016) · ACM SIGARCH Computer Architecture News · doi:10.1145/3007787.3001177 · Cited by 1,182
EIE: Efficient Inference Engine on Compressed Deep Neural Network
Han, S., Liu, X., Mao, H., Pu, J., Pedram, A., Horowitz, M. A., & Dally, W. J. (2016) · 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA) · doi:10.1109/isca.2016.30 · Cited by 1,077
ISAAC: A Convolutional Neural Network Accelerator with In-Situ Analog Arithmetic in Crossbars
Shafiee, A., Nag, A., Muralimanohar, N., Balasubramonian, R., Strachan, J. P., Hu, M., Williams, R. S., & Srikumar, V. (2016) · 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA) · doi:10.1109/isca.2016.12 · Cited by 775
Chi, P., Li, S., Xu, C., Zhang, T., Zhao, J., Liu, Y., Wang, Y., & Xie, Y. (2016) · 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA) · doi:10.1109/isca.2016.13 · Cited by 573
Eyeriss: A Spatial Architecture for Energy-Efficient Dataflow for Convolutional Neural Networks
Chen, Y.-H., Emer, J., & Sze, V. (2016) · 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA) · doi:10.1109/isca.2016.40 · Cited by 534
A dynamically configurable coprocessor for convolutional neural networks
Chakradhar, S., Sankaradas, M., Jakkula, V., & Cadambi, S. (2010) · Proceedings of the 37th annual international symposium on Computer architecture · doi:10.1145/1815961.1815993 · Cited by 343
Memory-centric accelerator design for Convolutional Neural Networks
Peemen, M., Setio, A. A. A., Mesman, B., & Corporaal, H. (2013) · 2013 IEEE 31st International Conference on Computer Design (ICCD) · doi:10.1109/iccd.2013.6657019 · Cited by 332
Accelerating Deep Convolutional Neural Networks Using Specialized Hardware
Ovtcharov, K., Ruwase, O., Kim, J.-Y., Fowers, J., Strauß, K., & Chung, E. S. (2015) · Cited by 310
Minerva: Enabling Low-Power, Highly-Accurate Deep Neural Network Accelerators
Reagen, B., Whatmough, P., Adolf, R., Rama, S., Lee, H., Lee, S. K., Hernandez-Lobato, J. M., Wei, G.-Y., & Brooks, D. (2016) · 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA) · doi:10.1109/isca.2016.32 · Cited by 246
Cnvlutin: Ineffectual-Neuron-Free Deep Neural Network Computing
Albericio, J., Judd, P., Hetherington, T., Aamodt, T., Jerger, N. E., & Moshovos, A. (2016) · 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA) · doi:10.1109/isca.2016.11 · Cited by 226
The case for the reduced instruction set computer
Patterson, D. A., & Ditzel, D. R. (1980) · ACM SIGARCH Computer Architecture News · doi:10.1145/641914.641917 · Cited by 211
Self-citationA VLSI architecture for high-performance, low-cost, on-chip learning
Hammerstrom, D. (1990) · 1990 IJCNN International Joint Conference on Neural Networks · doi:10.1109/ijcnn.1990.137621 · Cited by 209
DianNao family: energy-efficient hardware accelerators for machine learning
Chen, Y., Chen, T., Xu, Z., Sun, N., & Temam, O. (2016) · Communications of the ACM · doi:10.1145/2996864 · Cited by 205
The Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines
Barroso, L. A., & Hölzle, U. (2009) · Synthesis Lectures on Computer Architecture · doi:10.1007/978-3-031-01722-3 · Cited by 197
Neurocube: A Programmable Digital Neuromorphic Architecture with High-Density 3D Memory
Kim, D., Kung, J., Chai, S., Yalamanchili, S., & Mukhopadhyay, S. (2016) · 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA) · doi:10.1109/isca.2016.41 · Cited by 171
Fathom: reference workloads for modern deep learning methods
Adolf, R., Rama, S., Reagen, B., Wei, G.-Y., & Brooks, D. (2016) · 2016 IEEE International Symposium on Workload Characterization (IISWC) · doi:10.1109/iiswc.2016.7581275 · Cited by 169
Convolution engine: balancing efficiency & flexibility in specialized computing
Qadeer, W., Hameed, R., Shacham, O., Venkatesan, P., Kozyrakis, C., & Horowitz, M. A. (2013) · Proceedings of the 40th Annual International Symposium on Computer Architecture · doi:10.1145/2485922.2485925 · Cited by 168
Origami: A Convolutional Network Accelerator
Cavigelli, L., Gschwend, D., Mayer, C., Willi, S., Muheim, B., & Benini, L. (2015) · ACM Great Lakes Symposium on VLSI (GLSVLSI) · doi:10.1145/2742060.2743766 · Cited by 157
Cambricon: An Instruction Set Architecture for Neural Networks
Liu, S., Du, Z., Tao, J., Han, D. S., Luo, T., Xie, Y., Chen, Y., & Chen, T. (2016) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1109/isca.2016.42 · Cited by 146
Identifying Shades of Green: The SPECpower Benchmarks
Lange, K.-D. (2009) · Computer · doi:10.1109/mc.2009.84 · Cited by 111
RedEye: Analog ConvNet Image Sensor Architecture for Continuous Mobile Vision
LiKamWa, R., Hou, Y., Gao, Y., Polansky, M. G., & Zhong, L. (2016) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1109/isca.2016.31 · Cited by 76
Toward accelerating deep learning at scale using specialized hardware in the datacenter
Ovtcharov, K., Ruwase, O., Kim, J.-Y., Fowers, J., Strauß, K., & Chung, E. S. (2015) · IEEE Hot Chips Symposium · doi:10.1109/hotchips.2015.7477459 · Cited by 50
Design of a 1st Generation Neurocomputer
Ramacher, U., Beichter, J., Raab, W., Anlauf, J. K., Brüls, N., Hachmann, U., & Wesseling, M. (1991) · Springer eBooks · doi:10.1007/978-1-4615-3994-0_14 · Cited by 49
A reconfigurable fabric for accelerating large-scale datacenter services
Putnam, A. R., Caulfield, A. M., Chung, E. S., Chiou, D., Constantinides, K., Demme, J., Esmaeilzadeh, H., Fowers, J., Gopal, G. P., Gray, J., et al. (2016) · Communications of the ACM · doi:10.1145/2996868 · Cited by 46
Special-purpose digital hardware for neural networks: An architectural survey
Ienne, P., Cornu, T., & Kuhn, G. M. (1996) · The Journal of VLSI Signal Processing Systems for Signal Image and Video Technology · doi:10.1007/bf00930664 · Cited by 37
Large-Scale Deep Learning For Building Intelligent Computer Systems
Dean, J. (2016) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/2835776.2835844 · Cited by 26
Self-citationBanish, M. R., Chenault, D. B., & Harchanko, J. S. (2004) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.560815 · Cited by 8
Technical Perspective: If I could only design one circuit …
Keutzer, K. (2016) · Communications of the ACM · doi:10.1145/2996862 · Cited by 5
Research works printed but not linked: 15
- Asanović, K. 1998. Asanović, K., Beck, Johnson, J., Wawrzynek, J., Kingsbury, B. and Morgan, N., November 1998. Training Neural Networks with Spert-II. Chapter 11 in Parallel Architectures for Artificial Networks: Paradigms and Implementations, N. Sundararajan and P. Saratchandran (Eds.), IEEE Computer Society Press, ISBN 0-8186-8399-6. https://people.eecs.berkeley.edu/~krste/papers/annbook.pdf
- Caulfield, A.M., Chung, E.S., Putnam, A., Angepat, H., Fowers, J., Haselman, M., Heil, S., Humphrey, M., Kaur, P., Kim, J.Y. and Lo, D.2016. A Cloud-Scale Acceleration Architecture. MICRO-49 conference.
- Gupta S. Agrawal A. Gopalakrishnan K. and Narayanan P. 2015 July. Deep Learning with Limited Numerical Precision. ICML. · doi:10.5555/3045118.3045303
- Han S.; Pool J.; Tran J.; and Dally W. 2015. Learning both weights and connections for efficient neural networks. In Advances in Neural Information Processing Systems. · doi:10.5555/2969239.2969366
- Hennessy J.L. and Patterson D.A. 2018. Computer architecture: a quantitative approach 6th edition Elsevier.
- Krizhevsky A. Sutskever I. and Hinton G. 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems. · doi:10.5555/2999134.2999257
- Ross, J., Phelps, A., 2015. Computing Convolutions Using a Neural Network Processor, Patent Application No. 62/164,902.
- Ross, J., 2015. Prefetching Weights for a Neural Network Processor, Patent Application No. 62/164,981.
- Ross, J., Thorson, G., 2015. Rotating Data for Neural Network Computations, Patent Application No. 62/164,908.
- Schurman, E. and Brutlag, J., 2009, June. The user and business impact of server delays, additional bytes, and HTTP chunking in web search. In Velocity Web Performance and Operations Conference.
- 10.5555/800048.801719 · doi:10.5555/800048.801719
- Steinberg, D., 2015. Full-Chip Simulations, Keys to Success. Proc. Synopsys Users Group (SNUG) Silicon Valley 2015.
- Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V. and Rabinovich, A., 2015. Going deeper with convolutions. Proc. IEEE Conference on Computer Vision and Pattern Recognition.
- Thorson, G., Clark, C., Luu, D., 2015. Vector Computation Unit in a Neural Network Processor, Patent Application No. 62/165,022.
- Young, C., 2015. Batch Processing in a Neural Network Processor, Patent Application No. 62/165,020.
Cited by
Howard, A., Sandler, M., Chen, B., Wang, W., Chen, L.-C., Tan, M., Chu, G., Vasudevan, V., Zhu, Y., Pang, R., et al. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00140 · Cited by 9,708
Self-citationOpportunities and obstacles for deep learning in biology and medicine
Ching, T., Himmelstein, D. S., Beaulieu-Jones, B. K., Kalinin, A. A., Do, B. T., Way, G. P., Ferrero, E., Agapow, P.-M., Zietz, M., Hoffman, M. M., et al. (2018) · Journal of The Royal Society Interface · doi:10.1098/rsif.2017.0387 · Cited by 2,310
Memory devices and applications for in-memory computing
Sebastian, A., Le Gallo, M., Khaddam-Aljameh, R., & Eleftheriou, E. (2020) · Nature Nanotechnology · doi:10.1038/s41565-020-0655-z · Cited by 2,289
In-memory computing with resistive switching devices
Ielmini, D., & Wong, H.-S. P. (2018) · Nature Electronics · doi:10.1038/s41928-018-0092-2 · Cited by 2,298
Fully hardware-implemented memristor convolutional neural network
Yao, P., Wu, H., Gao, B., Tang, J., Zhang, Q., Zhang, W., Yang, J. J., & Qian, H. (2020) · Nature · doi:10.1038/s41586-020-1942-4 · Cited by 2,179
Metadata
- Authors
- Jouppi, N. P., Young, C., Patil, N., Patterson, D., Agrawal, G., Bajwa, R., Bates, S., Bhatia, S., Boden, N., Borchers, A., Boyle, R., Cantin, P.-L., Chao, C., Clark, C., Coriell, J., Daley, M., Dau, M., Dean, J., Gelb, B., Ghaemmaghami, T. V., Gottipati, R., Gulland, W., Hagmann, R., Ho, C. R., Hogberg, D., Hu, J., Hundt, R., Hurt, D., Ibarz, J., Jaffey, A., Jaworski, A., Kaplan, A., Khaitan, H., Killebrew, D., Koch, A., Kumar, N., Lacy, S., Laudon, J., Law, J., Le, D., Leary, C., Liu, Z., Lucke, K., Lundin, A., MacKean, G., Maggiore, A., Mahony, M., Miller, K., Nagarajan, R., Narayanaswami, R., Ni, R., Nix, K., Norrie, T., Omernick, M., Penukonda, N., Phelps, A., Ross, J., Ross, M., Salek, A., Samadiani, E., Severn, C., Sizikov, G., Snelham, M., Souter, J., Steinberg, D., Swing, A., Tan, M., Thorson, G., Tian, B., Toma, H., Tuttle, E., Vasudevan, V., Walter, R., Wang, W., Wilcox, E., & Yoon, D. H.
- Venue
- ACM SIGARCH Computer Architecture News
- Published
- 2017-06-24
- Volume
- 45
- Issue
- 2
- Pages
- 1-12
- ISSN
- 0163-5964 (ISSN-L)
- OpenAlex
- W2953212265
- Cited by
- 1,240
- References
- 40
- FWCI
- 187.99
- Type
- journal article
- Language
- en
- Open access
- closed
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.