.png){kind=icon}
返回
Reduced precision floating-point optimization for Deep Neural Network On-Device Learning on microcontrollers
.png){kind=icon}
OA
AI
DOI：10.1016/j.future.2023.07.020.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Enabling On-Device Learning (ODL) for Ultra-Low-Power Micro-Controller Units (MCUs) is a key step for post-deployment adaptation and fine-tuning of Deep Neural Network (DNN) models in future TinyML applications. This paper tackles this challenge by introducing a novel reduced precision optimization technique for ODL primitives on MCU-class devices, leveraging the State-of-Art advancements in RISC-V RV32 architectures with support for vectorized 16-bit floating-point (FP16) Single-Instruction Multiple-Data (SIMD) operations. Our approach for the Forward and Backward steps of the Back Propagation training algorithm is composed of specialized shape transform operators and Matrix Multiplication (MM) kernels, accelerated with parallelization and loop unrolling. When evaluated on a single training step of a 2D Convolution layer, the SIMD-optimized FP16 primitives result up to 1.72x faster than the FP32 baseline on a RISC-V-based 8+1-core MCU. An average computing efficiency of 3.11 Multiply and Accumulate operations per clock cycle (MAC/clk) and 0.81 MAC/clk is measured for the end-to-end training tasks of a ResNet8 and a DS-CNN for Image Classification and Keyword Spotting, respectively - requiring 17.1 ms and 6.4 ms on the target platform to compute a training step on a single sample. Overall, our approach results more than two orders of magnitude faster than existing ODL software frameworks for single-core MCUs and outperforms by 1.6x previous FP32 parallel implementations on a Continual Learning setup.& COPY; 2023 Elsevier B.V. All rights reserved.
Keyword:
Parallel computing
Computer architecture
Open source software
Open architecture platforms
Deep learning
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
F
IF:
6.1
论文数:
6.9K
被引数:
2.3W
机构
引用论文
.png){kind=icon}
A Low-Power Transprecision Floating-Point Cluster for Efficient Near-Sensor Data Analytics用于高效近传感器数据分析的低功耗Transprecision浮点集群
OAAI
OAAI分享收藏
查看更多内容