CoChat

Efficient and Effective Sparse LSTM on FPGA with Bank-Balanced Sparsity

Cao, Shijie, Zhang, Chen, Yao, Zhuliang, Xiao, Wencong, Nie, Lanshun, Zhan, Dechen, Liu, Yunxin, Wu, Ming, Zhang, Lintao · 2019 · Proceedings of the 2019 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays
Cited by 178

The DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.

Abstract

Neural networks based on Long Short-Term Memory (LSTM) are widely deployed in latency-sensitive language and speech applications. To speed up LSTM inference, previous research proposes weight pruning techniques to reduce computational cost. Unfortunately, irregular computation and memory accesses in unrestricted sparse LSTM limit the realizable parallelism, especially when implemented on FPGA. To address this issue, some researchers propose block-based sparsity patterns to increase the regularity of sparse weight matrices, but these approaches suffer from deteriorated prediction accuracy. This work presents Bank-Balanced Sparsity (BBS), a novel sparsity pattern that can maintain model accuracy at a high sparsity level while still enable an efficient FPGA implementation. BBS partitions each weight matrix row into banks for parallel computing, while adopts fine-grained pruning inside each bank to maintain model accuracy. We develop a 3-step software-hardware co-optimization approach to apply BBS in real FPGA hardware. First, we propose a bank-balanced pruning method to induce the BBS pattern on weight matrices. Then we introduce a decoding-free sparse matrix format, Compressed Sparse Banks (CSB), that transparently exposes inter-bank parallelism in BBS to hardware. Finally, we design an FPGA accelerator that takes advantage of BBS to eliminate irregular computation and memory accesses. Implemented on Intel Arria-10 FPGA, the BBS accelerator can achieve 750.9 GOPs on sparse LSTM networks with a batch size of 1. Compared to state-of-the-art FPGA accelerators for LSTM with different compression techniques, the BBS accelerator achieves 2.3 ~ 3.7x improvement on energy efficiency and 7.0 ~ 34.4x reduction on latency with negligible loss of model accuracy.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3289602.3293898

Cites

8 of 8 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Show all 8 references

Cited by

See all 178

Metadata

Authors
Cao, S., Zhang, C., Yao, Z., Xiao, W., Nie, L., Zhan, D., Liu, Y., Wu, M., & Zhang, L.
Venue
Proceedings of the 2019 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays
Publisher
ACM
Published
2019-02-20
Pages
63-72
OpenAlex
W2915106038
Cited by
178
References
8
FWCI
9.78
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: Efficient and Effective Sparse LSTM on FPGA with Bank-Balanced Sparsity. https://app.cochat.ai/papers/10.1145/3289602.3293898
The paper
Cao, S., Zhang, C., Yao, Z., Xiao, W., Nie, L., Zhan, D., Liu, Y., Wu, M., & Zhang, L. (2019). Efficient and Effective Sparse LSTM on FPGA with Bank-Balanced Sparsity. Proceedings of the 2019 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays. https://doi.org/10.1145/3289602.3293898

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.