# Energy-efficient Dense DNN Acceleration with Signed Bit-slice Architecture

arXiv: https://arxiv.org/abs/2203.07679 · HTML: https://mlsanity.com/paper/2203.07679/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 29 references that are in the map.
- First posted on arXiv 15 Mar 2022.

## Builds on (most cited first, 14 of 14)

- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [Accelerating the Super-Resolution Convolutional Neural Network](https://mlsanity.com/paper/1608.00367/) (2016)
- [EIE: Efficient Inference Engine on Compressed Deep Neural Network](https://mlsanity.com/paper/1602.01528/) (2016)
- [Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing](https://mlsanity.com/paper/1905.10083/) (2019)
- [ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votes](https://mlsanity.com/paper/2001.10692/) (2020)
- [Bit Fusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Networks](https://mlsanity.com/paper/1712.01507/) (2017)
- [Embodied Question Answering in Photorealistic Environments with Point Cloud Perception](https://mlsanity.com/paper/1904.03461/) (2019)
- [Rendering Natural Camera Bokeh Effect with Deep Learning](https://mlsanity.com/paper/2006.05698/) (2020)

## Abstract (arXiv)

As the number of deep neural networks (DNNs) to be executed on a mobile system-on-chip (SoC) increases, the mobile SoC suffers from the real-time DNN acceleration within its limited hardware resources and power budget. Although the previous mobile neural processing units (NPUs) take advantage of low-bit computing and exploitation of the sparsity, it is incapable of accelerating high-precision and dense DNNs. This paper proposes energy-efficient signed bit-slice architecture which accelerates both high-precision and dense DNNs by exploiting a large number of zero values of signed bit-slices. Proposed signed bit-slice representation (SBR) changes signed 11112 bit-slice to 00002 by borrowing a 1 value from its lower order of bit-slice. As a result, it generates a large number of zero bit-slices even in dense DNNs. Moreover, it balances the positive and negative values of 2's complement data, allowing bit-slice based output speculation which pre-computes high order of bit-slices and skips the remaining dense low order of bit-slices. The signed bit-slice architecture compresses and skips the zero input signed bit-slices, and the zero skipping unit also supports the output skipping by masking the speculated inputs as zero. Additionally, the heterogeneous network-on-chip (NoC) benefits the exploitation of data reusability and reduction of transmission bandwidth. The paper introduces a specialized instruction set architecture (ISA) and a hierarchical instruction decoder for the control of the signed bit-slice architecture. Finally, the signed bit-slice architecture outperforms the previous bit-slice accelerator, Bit-fusion, over ×3.65 higher area-efficiency, ×3.88 higher energy-efficiency, and ×5.35 higher throughput.