GPGPU Scheduling Schemes to Improve Latency and Resource Utilization

View Full Paper

Ask AI

Bookmark

Authors

Discussion

New scheduling method improves task acceptance and energy efficiency in embedded systems, highlighting its flexibility and performance.

The Hybrid GPGPU Scheduler improves task scheduling by 11% at high usage and demonstrates real-time adaptability and efficiency.
Testing showed an 85% task acceptance rate with 12 concurrent tasks and a significant 40% reduction in scheduling delay.
Utilizing machine learning methods like Gradient Boosting Decision Trees, the scheduler caters to memory limitations effectively.
This solution highlights the importance of balancing performance and energy efficiency in real-time embedded system scheduling.

Murty et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark