DeltaRNN: A Power-efficient Recurrent Neural Network Accelerator
Open accessThe DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
Recurrent Neural Networks (RNNs) are widely used in speech recognition and natural language processing applications because of their capability to process temporal sequences. Because RNNs are fully connected, they require a large number of weight memory accesses, leading to high power consumption. Recent theory has shown that an RNN delta network update approach can reduce memory access and computes with negligible accuracy loss. This paper describes the implementation of this theoretical approach in a hardware accelerator called "DeltaRNN" (DRNN). The DRNN updates the output of a neuron only when the neuron»s activation changes by more than a delta threshold. It was implemented on a Xilinx Zynq-7100 FPGA. FPGA measurement results from a single-layer RNN of 256 Gated Recurrent Unit (GRU) neurons show that the DRNN achieves 1.2 TOp/s effective throughput and 164 GOp/s/W power efficiency. The delta update leads to a 5.7x speedup compared to a conventional RNN update because of the sparsity created by the DN algorithm and the zero-skipping ability of DRNN.
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Speech recognition with deep recurrent neural networks
Graves, A., Mohamed, A.-R., & Hinton, G. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638947 · Cited by 8,893 · cited 1×
“Recurrent Neural Networks (RNNs) are fully-connected single- or multi-layered networks with complex neurons that have multiple memory states and enabled state-of-art accuracies in tasks involving temporal sequences [27] such as automatic speech recognition [2, 9] and natural language processing [23].”
BackgroundRecurrent neural network based language model
Mikolov, T., Karafiát, M., Burget, L., Černocký, J., & Khudanpur, S. (2010) · Interspeech 2010 · doi:10.21437/interspeech.2010-343 · Cited by 5,390 · cited 1×
“Recurrent Neural Networks (RNNs) are fully-connected single- or multi-layered networks with complex neurons that have multiple memory states and enabled state-of-art accuracies in tasks involving temporal sequences [27] such as automatic speech recognition [2, 9] and natural language processing [23].”
BackgroundLearning both Weights and Connections for Efficient Neural Networks
Han, S., Pool, J., Tran, J., & Dally, W. J. (2015) · arXiv · doi:10.48550/arxiv.1506.02626 · Cited by 1,481 · cited 1×
“[13] employs a load-balance-aware pruning scheme, including both pruning [15] and quantization.”
MethodESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA
Han, S., Kang, J., Mao, H., Hu, Y., Li, X., Li, Y., Xie, D., Luo, H., Yao, S., Wang, Y., et al. (2017) · Proceedings of the 2017 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays · doi:10.1145/3020078.3021745 · Cited by 591 · cited 2×
“[13] employs a load-balance-aware pruning scheme, including both pruning [15] and quantization.”
MethodSoftware-Hardware Codesign for Efficient Neural Network Acceleration
Guo, K., Han, S., Yao, S., Wang, Y., Xie, Y., & Yang, H. (2017) · IEEE Micro · doi:10.1109/mm.2017.39 · Cited by 78 · cited 1×
“The server- or desktop-targeted Titan X consumes about 200 W and achieves a power efficiency around 5GOp/s/W in inference of an LSTM layer with 1024 neurons [12].”
Background
Cited by
Long short-term memory networks in memristor crossbar arrays
Li, C., Wang, Z., Rao, M., Belkin, D., Song, W., Jiang, H., Yan, P., Li, Y., Lin, P., Hu, M., et al. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-018-0001-4 · Cited by 429
Efficient Acceleration of Deep Learning Inference on Resource-Constrained Edge Devices: A Review
Shuvo, M. M. H., Islam, S. K., Cheng, J., & Morshed, B. I. (2023) · Proceedings of the IEEE · doi:10.1109/jproc.2022.3226481 · Cited by 436
A Survey of Accelerator Architectures for Deep Neural Networks
Chen, Y., Xie, Y., Song, L., Chen, F., & Tang, T. (2020) · Engineering · doi:10.1016/j.eng.2020.01.007 · Cited by 370
Aimar, A., Mostafa, H., Calabrese, E., Rios-Navarro, A., Tapiador-Morales, R., Lungu, I.-A., Milde, M. B., Corradi, F., Linares-Barranco, A., Liu, S.-C., et al. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2852335 · Cited by 292
Self-citation 3: Accelerating attention mechanisms in neural networks with approximation
Ham, T. J., Jung, S. J., Kim, S., Oh, Y. H., Park, Y., Song, Y., Park, J.-H., Lee, S., Park, K., Lee, J. W., et al. (2020) · 2020 IEEE International Symposium on High Performance Computer Architecture (HPCA) · doi:10.1109/hpca47549.2020.00035 · Cited by 242
Metadata
- Authors
- Gao, C., Neil, D., Ceolini, E., Liu, S.-C., & Delbruck, T.
- Venue
- Proceedings of the 2018 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays
- Publisher
- ACM
- Published
- 2018-02-15
- Pages
- 21-30
- OpenAlex
- W2788838111
- Cited by
- 133
- References
- 6
- FWCI
- 6.38
- Type
- conference paper
- Language
- en
- Open access
- bronze
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: DeltaRNN: A Power-efficient Recurrent Neural Network Accelerator. https://app.cochat.ai/papers/10.1145/3174243.3174261
- The paper
- Gao, C., Neil, D., Ceolini, E., Liu, S.-C., & Delbruck, T. (2018). DeltaRNN: A Power-efficient Recurrent Neural Network Accelerator. Proceedings of the 2018 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays. https://doi.org/10.1145/3174243.3174261
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.