Bit-Width-Aware Design Environment for Few-Shot Learning on Edge AI Hardware
Research Institute of Electrical Communication, Tohoku University(东北大学电气通信研究所);Graduate School of Engineering, Tohoku University(东北大学工学研究科);IMT Atlantique, Lab-STICC, UMR CNRS 6285(大西洋高等理工学院,Lab-STICC,CNRS联合研究实验室6285)
R. Kanda, H. L. Blevec, N. Onizawa, M. Leonardon, V. Gripon, T. Hanyu
In this study, we propose an implementation methodology of real-time few-shot learning on tiny FPGA SoCs such as the PYNQ-Z1 board with arbitrary fixed-point bit-widths. Tensil-based conventional design environments limited hardware implementations to fixed-point bit-widths of 16 or 32 bits. To address this, we adopt the FINN framework, enabling implementations with arbitrary bit-widths. Several customizations and minor adjustments are made, including: 1.Optimization of Transpose nodes to resolve data format mismatches, 2.Addition of handling for converting the final reduce mean operation to Global Average Pooling (GAP). These adjustments allow us to reduce the bit-width while maintaining the same accuracy as the conventional realization, and achieve approximately twice the throughput in evaluations using CIFAR-10 dataset.
Design Environment of Quantization-Aware Edge AI Hardware for Few-Shot Learning
Research Institute of Electrical Communication, Tohoku University(东北大学电气通信研究所);Graduate School of Engineering, Tohoku University(东北大学工学院);IMT Atlantique, Lab-STICC, UMR CNRS 6285(大西洋高等矿业学院,实验室-STICC,法国国家科学研究中心联合研究单位6285)
Trinity College Dublin, The University of Dublin(都柏林大学圣三一学院);The School of Computer Science and Statistics(计算机科学与统计学院);Institute of Technology Carlow(卡洛理工学院)
Computer Systems Lab, Cornell University(康奈尔大学计算机系统实验室);Systems and Networking Research Group, Microsoft Research(微软研究院系统与网络研究组);Department of Electrical and Electronic Engineering, Imperial College London(伦敦帝国理工学院电子与电气工程系)
Bitwise Systolic Array Architecture for Runtime-Reconfigurable Multi-precision Quantized Multiplication on Hardware Accelerators
Dresden University of Technology, Germany(德累斯顿理工大学);Ruhr University Bochum, Germany(博德大学);Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI Dresden/Leipzig), Germany(可扩展数据与人工智能研究中心(ScaDS.AI 德累斯顿/莱比锡))
LUT Tensor Core: A Software-Hardware Co-Design for LUT-Based Low-Bit LLM Inference
Imperial College London(帝国理工学院伦敦分校);Microsoft Research London, UK(微软研究院伦敦, UK);Peking University(北京大学);Microsoft Research Beijing, China(微软研究院北京, China);University of Science(科学大学);University of Washington(华盛顿大学);Microsoft Research Seattle, USA(微软研究院西雅图, USA);Shanghai Jiao Tong University Shanghai, China(上海交通大学上海, China);Microsoft Research(微软研究院);Shanghai Jiao Tong University(上海交通大学)
High-Speed Area-Efficient Hardware Architecture for the Efficient Detection of Faults in a Bit-Parallel Multiplier Utilizing the Polynomial Basis of GF(2m)
Hardware-Compatible Single-Shot Feasible-Space Heuristics for Solving the Quadratic Assignment Problem
QB Information Technologies (1QBit)(1QB信息技术公司);Institute for Neuromorphic Compute Nodes (PGI-14), Peter Grünberg Institute, Forschungszentrum Jülich GmbH(于利希研究中心彼得·格林贝格研究所神经形态计算节点研究所);RWTH Aachen University(亚琛工业大学);HPE Labs, Hewlett Packard Enterprise(惠普企业实验室);University of California, Santa Barbara(加州大学圣塔芭芭拉分校)
GRAU: A Generic Runtime-Reconfigurable Activation-Requantization Unit for Quantized Neural Network Accelerators
Ruhr University Bochum, Germany(博德姆鲁尔大学);Dresden University of Technology, Germany(德累斯顿技术大学);Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI Dresden/Leipzig), Germany(可扩展数据与人工智能中心(ScaDS.AI 德累斯顿/莱比锡))