A 0.13mJ/Prediction CIFAR-100 Raster-Scan- Based Wired-Logic Processor Using Non-Linear Neural Network
Authors:
- 21 May 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
A 0.13mJ/prediction with 68.6% accuracy single- chip wired-logic artificial intelligence (AI) processor is developed in a 16nm field-programmable gate array (FPGA). Compared with conventional von-Neumann architecture-based AI processors, the energy efficiency is greatly improved by eliminating the DRAM/BRAM access. A technical challenge of the conventional wired-logic processor is the large amount of hardware resources required. To implement a large convolutional neural network (CNN) into a single FPGA chip, two techniques are used: (1) a sparse neural network which is called non-linear neural network (NNN), and (2) a newly developed raster-scan-based wired-logic architecture. The amount of hardware resources required is reduced by a factor of 5.4. Compared with the state-of-the-art FPGA-based processor, 238 times better energy efficiency is achieved with the same accuracy on the CIFAR-I00 task. In addition, 7 times better energy efficiency is achieved compared with the state-of- the-art application-specific integrated circuit (ASIC) processor.Keywords
This publication has 8 references indexed in Scilit:
- A 13.7μJ/prediction 88% Accuracy CIFAR-10 Single-Chip Wired-logic Processor in 16-nm FPGA using Non-Linear Neural Network2022
- Hiddenite: 4K-PE Hidden Network Inference 4D-Tensor Engine Exploiting On-Chip Model Construction Achieving 34.8-to-16.0TOPS/W for CIFAR-100 and ImageNet2022
- A 0.61-μJ/Frame Pipelined Wired-logic DNN Processor in 16-nm FPGA Using Convolutional Non-Linear Neural NetworkIEEE Open Journal of Circuits and Systems, 2021
- NC-Net: Efficient Neuromorphic Computing Using Aggregated Subnets on a Crossbar-Based Architecture With Nonvolatile MemoryIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2021
- FPGA-Based Sparsity-Aware CNN Accelerator for Noise-Resilient Edge-Level Image Recognition2019
- Accelerating Binarized Convolutional Neural Networks with Software-Programmable FPGAs2017
- Convolutional networks for fast, energy-efficient neuromorphic computingProceedings of the National Academy of Sciences of the United States of America, 2016
- 1.1 Computing's energy problem (and what we can do about it)2014