Lightator: An Optical Near-Sensor Accelerator with Compressive Acquisition Enabling Versatile Image Processing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Morsali, Mehrdad, Reidy, Brendan, Najafi, Deniz, Tabrizchi, Sepehr, Imani, Mohsen, Nikdast, Mahdi, Roohi, Arman, Zand, Ramtin, Angizi, Shaahin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909132126158848
author Morsali, Mehrdad
Reidy, Brendan
Najafi, Deniz
Tabrizchi, Sepehr
Imani, Mohsen
Nikdast, Mahdi
Roohi, Arman
Zand, Ramtin
Angizi, Shaahin
author_facet Morsali, Mehrdad
Reidy, Brendan
Najafi, Deniz
Tabrizchi, Sepehr
Imani, Mohsen
Nikdast, Mahdi
Roohi, Arman
Zand, Ramtin
Angizi, Shaahin
contents This paper proposes a high-performance and energy-efficient optical near-sensor accelerator for vision applications, called Lightator. Harnessing the promising efficiency offered by photonic devices, Lightator features innovative compressive acquisition of input frames and fine-grained convolution operations for low-power and versatile image processing at the edge for the first time. This will substantially diminish the energy consumption and latency of conversion, transmission, and processing within the established cloud-centric architecture as well as recently designed edge accelerators. Our device-to-architecture simulation results show that with favorable accuracy, Lightator achieves 84.4 Kilo FPS/W and reduces power consumption by a factor of ~24x and 73x on average compared with existing photonic accelerators and GPU baseline.
format Preprint
id arxiv_https___arxiv_org_abs_2403_05037
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Lightator: An Optical Near-Sensor Accelerator with Compressive Acquisition Enabling Versatile Image Processing
Morsali, Mehrdad
Reidy, Brendan
Najafi, Deniz
Tabrizchi, Sepehr
Imani, Mohsen
Nikdast, Mahdi
Roohi, Arman
Zand, Ramtin
Angizi, Shaahin
Hardware Architecture
Signal Processing
This paper proposes a high-performance and energy-efficient optical near-sensor accelerator for vision applications, called Lightator. Harnessing the promising efficiency offered by photonic devices, Lightator features innovative compressive acquisition of input frames and fine-grained convolution operations for low-power and versatile image processing at the edge for the first time. This will substantially diminish the energy consumption and latency of conversion, transmission, and processing within the established cloud-centric architecture as well as recently designed edge accelerators. Our device-to-architecture simulation results show that with favorable accuracy, Lightator achieves 84.4 Kilo FPS/W and reduces power consumption by a factor of ~24x and 73x on average compared with existing photonic accelerators and GPU baseline.
title Lightator: An Optical Near-Sensor Accelerator with Compressive Acquisition Enabling Versatile Image Processing
topic Hardware Architecture
Signal Processing
url https://arxiv.org/abs/2403.05037