Designing RISC-V Instruction Set Extensions for Artificial Neural Networks: An LLVM Compiler-Driven Perspective

The demand for Artificial Intelligence (AI) based solutions is exponentially increasing in all application fields, including low-power devices on the edge. However, due to their limited computational capabilities, these devices, which run Central Processing Units (CPUs) tailored to embedded applicat...

Full description

Bibliographic Details

Published in:	IEEE Access
Main Authors:	Karthikeyan Kalyanasundaram Balasubramanian, Mirco Di Salvo, Walter Rocchia, Sergio Decherchi, Marco Crepaldi
Format:	Article
Language:	English
Published:	IEEE 2024-01-01
Subjects:	RISC-V AI RISC-V custom instructions extensions LLVM instruction set architecture hardware-software co-design
Online Access:	https://ieeexplore.ieee.org/document/10501937/