A fully hardware-managed scheduling architecture for AI accelerators

Abstract The proliferation of AI applications across diverse domains has driven the evolution of AI accelerators toward higher performance and energy efficiency. This paper addresses the critical challenge of task scheduling in AI accelerators by introducing a fully hardware-managed scheduling syste...

Full description

Bibliographic Details
Published in:Journal of King Saud University: Computer and Information Sciences
Main Authors: Libo Cheng, Liang Yang, Jian Shao, Xinyi Gu, Rong Qian, Xinwei Zhang, Donghao Li, Hongbin Wang, Xiaoqi Xia
Format: Article
Language:English
Published: Springer 2026-02-01
Subjects:
AI accelerators
Hardware-managed scheduling
OCSR
Computation-scheduling instructions
Scheduling latency
Throughput optimization
Online Access:https://doi.org/10.1007/s44443-026-00513-z

Internet

https://doi.org/10.1007/s44443-026-00513-z

Similar Items