XCelHD: An Efficient GPU-Powered Hyperdimensional Computing with Parallelized Training
Authors:
- 17 January 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 220-225
Abstract
Hyperdimensional Computing (HDC) is an emerging lightweight machine learning method alternative to deep learning. One of its key strengths is the ability to accelerate it in hardware, as it offers massive parallelisms. Prior work primarily focused on FPGA and ASIC, which do not provide the seamless flexibility required for HDC applications. Few studies that attempted GPU designs are inefficient, partly due to the complexity of accelerating HDC on GPUs because of the bit-level operations of HDC. Besides, HDC training exhibited low hardware utilization due to sequential operations. In this paper, we present XCelHD, a high-performance GPU-powered framework for HDC. XCelHD uses a novel training method to maximize the training speed of the HDC model while fully utilizing hardware. We propose memory optimization strategies specialized for GPU-based HDC, minimizing the access time to different memory subsystems and redundant operations. We show that the proposed training method reduces the required number of training epochs by four-fold to achieve comparable accuracy. Our evaluation results on NVIDIA Jetson TX2 show that XCelHD is up to $35\times$ faster than the state-of-the-art TensorFlow-based HDC implementation.
Keywords
Funding Information
- DARPA
- NSF (2100237,1730158,1826967,1911095)
This publication has 14 references indexed in Scilit:
- F5-HD2019
- FELIX2018
- Hierarchical hyperdimensional computing for energy efficient classification2018
- Brain-inspired computing exploiting carbon nanotube FETs and resistive RAM: Hyperdimensional computing case study2018
- VoiceHD: Hyperdimensional Computing for Efficient Speech Recognition2017
- Exploring Hyperdimensional Associative Memory2017
- Hyperdimensional computing with 3D VRRAM in-memory kernels: Device-architecture co-design for energy-efficient, error-resilient language recognition2016
- A Robust and Energy-Efficient Classifier Using Brain-Inspired Hyperdimensional Computing2016
- Modeling Dependencies in Multiple Parallel Data Streams with Hyperdimensional ComputingIEEE Signal Processing Letters, 2014
- Introducing a New Benchmarked Dataset for Activity Monitoring2012