Proposal of an open-source accelerators library for inference of transformer networks in edge devices based on Linux

 

שמור ב:
מידע ביבליוגרפי
Autores: Araya-Núñez, Alejandro, Fernández-Badilla, Justin, González-Vargas, Daniel González-Vargas, León-Huertas, Jimena, Obregón-Fonseca, Erick-Andrés, Xie-Li, Danny
פורמט: artículo original
סטטוס:Versión publicada
Fecha de Publicación:2024
תיאור:Transformers networks have been a great milestone in the natural language processing field, and have powered technologies like ChatGPT, which are undeniably changing people’s lives. This article discusses the characteristics and computational complexity of Transformers networks, as well as, the potential for improving its performance in low-resource environments through the use of hardware accelerators. This research has the potential to significantly improve the performance of Transformers in edge and low-end devices. In addition, Edge Artificial Intelligence, Hardware Acceleration, and Tiny Machine Learning algorithms are explored. The proposed methodology includes a software and hardware layer, with a Linux-based minimal image built on top of a synthesized RTL. The proposal also includes a library of hardware accelerators that can be customized to select the desired accelerators based on the device’s resources and operations to be accelerated.
País:Portal de Revistas TEC
מוסד:Instituto Tecnológico de Costa Rica
Repositorio:Portal de Revistas TEC
שפה:Inglés
OAI Identifier:oai:ojs.pkp.sfu.ca:article/7225
גישה מקוונת:https://revistas.tec.ac.cr/index.php/tec_marcha/article/view/7225
מילת מפתח:Artificial intelligence
driver
FPGA
hardware accelerator
Linux
transformers
Inteligencia artificial
acelerador por hardware