A Multi-Neural Network Acceleration Architecture
The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
A cost-effective multi-tenant neural network execution is becoming one of the most important design goals for modern neural network accelerators. For example, as emerging AI services consist of many heterogeneous neural network executions, a cloud provider wants to serve a large number of clients using a single AI accelerator for improving its cost effectiveness. Therefore, an ideal next-generation neural network accelerator should support a simultaneous multi-neural network execution, while fully utilizing its hardware resources. However, existing accelerators which are optimized for a single neural network execution can suffer from severe resource underutilization when running multiple neural networks, mainly due to the load imbalance between computation and memory-access tasks from different neural networks.In this paper, we propose AI-MultiTasking (AI-MT), a novel accelerator architecture which enables a cost-effective, high-performance multi-neural network execution. The key idea of AI-MT is to fully utilize the accelerator’s computation resources and memory bandwidth by matching compute- and memory-intensive tasks from different networks and executing them in parallel. However, it is highly challenging to find and schedule the best load-matching tasks from different neural networks during runtime, without significantly increasing the size of on-chip memory. To overcome the challenges, AI-MT first creates fine-grain tasks at compile time by dividing each layer into multiple identical sub-layers. During runtime, AI-MT dynamically applies three sub-layer scheduling methods: memory block prefetching and compute block merging for the best resource load matching, and memory block eviction for the minimum on-chip memory footprint. Our evaluations using MLPerf benchmarks show that AI-MT achieves up to 1.57x speedup over the baseline scheduling method.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
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
ImageNet 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
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
Google'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 · cited 2×
“Neural networks (NNs) have been applied to a wide range of applications thanks to their high accuracy and performance (e.g., image classification [30], [32], [35], [50], [56] and speech recognition [55]).”
BackgroundIn-Datacenter Performance Analysis of a Tensor Processing Unit
Jouppi, N. P., Young, C., Patil, N., Patterson, D., Agrawal, G., Bajwa, R., Bates, S., Bhatia, S., Boden, N., Borchers, A., et al. (2017) · Proceedings of the 44th Annual International Symposium on Computer Architecture · doi:10.1145/3079856.3080246 · Cited by 4,537 · cited 9×
“For example, to efficiently support the basic operations of modern neural networks (e.g., ‡ Corresponding author. matrix and vector operations), those accelerators often adopt two-dimensional processing element (PE) arrays [14], [15], [33].”
BackgroundMethodInfluentialOptimizing 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 · cited 1×
“For example, weight-stationary [7], [13], [16], [33], [43], [46], [47], [51], [52], [59], output-stationary [22], [51], row-stationary [14], [15], [26] dataflows determine spatial and temporal data mappings to PEs differently.”
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 · cited 5×
“Similarly, Eyeriss [14] utilizes a systolic array to exploit the data reuse characteristics of modern CNNs, but leverages the rowstationary dataflow to maximize data reuse and accumulation at the RF level.”
BackgroundInfluentialEIE: 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
Alwani, M., Chen, H., Ferdman, M., & Milder, P. (2016) · 2016 49th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1109/micro.2016.7783725 · Cited by 662 · cited 1×
“For example, weight-stationary [7], [13], [16], [33], [43], [46], [47], [51], [52], [59], output-stationary [22], [51], row-stationary [14], [15], [26] dataflows determine spatial and temporal data mappings to PEs differently.”
Applied Machine Learning at Facebook: A Datacenter Infrastructure Perspective
Hazelwood, K., Bird, S., Brooks, D., Chintala, S., Diril, U., Dzhulgakov, D., Fawzy, M., Jia, B., Jia, Y., Kalro, A., et al. (2018) · 2018 IEEE International Symposium on High Performance Computer Architecture (HPCA) · doi:10.1109/hpca.2018.00059 · Cited by 590
Cited by
SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning
Wang, H., Zhang, Z., & Han, S. (2021) · 2021 IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca51647.2021.00018 · Cited by 427
Heterogeneous Dataflow Accelerators for Multi-DNN Workloads
Kwon, H., Lai, L., Pellauer, M., Krishna, T., Chen, Y.-H., & Chandra, V. (2021) · 2021 IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca51647.2021.00016 · Cited by 144
“When we combine the same dataflow, we construct scaled-out multi-FDAs [24], which we also evaluate in Subsection V-B.”
BackgroundMethodInfluentialMAGMA: An Optimization Framework for Mapping Multiple DNNs on Multiple Accelerator Cores
Kao, S.-C., & Krishna, T. (2022) · 2022 IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca53966.2022.00065 · Cited by 58
“…tasks also has much less layer dependency issue than single-tenant single-job tasks for following reasons. i) As shown by the observation in AI-MT [3], multi-tenancy, running multiple neural networks together, can largely alleviate the layer dependency problem as layers from different neural…”
BackgroundMethodInfluential
Metadata
- Authors
- Baek, E., Kwon, D., & Kim, J.
- Venue
- 2020 ACM/IEEE 47th Annual International Symposium on Computer Architecture (ISCA)
- Publisher
- IEEE
- Published
- 2020-05
- Pages
- 940-953
- OpenAlex
- W3043406639
- Cited by
- 107
- References
- 10
- FWCI
- 11.60
- Type
- conference paper
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: A Multi-Neural Network Acceleration Architecture. https://app.cochat.ai/papers/10.1109/isca45697.2020.00081
- The paper
- Baek, E., Kwon, D., & Kim, J. (2020). A Multi-Neural Network Acceleration Architecture. 2020 ACM/IEEE 47th Annual International Symposium on Computer Architecture (ISCA). https://doi.org/10.1109/isca45697.2020.00081
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.