Presentation + Paper
30 September 2024 Scheduling algorithms on heterogeneous architecture for efficient vision systems
Author Affiliations +
Abstract
Deep Neural Network (DNN) algorithms have become ubiquitous within the vision domain, encompassing various tasks, including object detection, segmentation, and classification. However, executing complex DNNs in realtime systems demands improved energy efficiency, runtime, and accuracy. Traditional embedded imaging designs, typically implemented on homogeneous architectures, face hardware limitations, prompting the need for heterogeneous computing architectures. These architectures combine CPUs, GPUs, FPGAs, and other accelerators, enabling applications to use the most efficient architecture for a given algorithm. The challenge lies in scheduling and partitioning algorithms across accelerators with different computing paradigms and tool-sets. This requires balancing computational power, memory bandwidth, and communication overhead. Effective scheduling involves considering task dependencies, resource availability, and synchronisation. Current deep learning libraries often target single architectures and lack mechanisms to intelligently partition sub-operations across the most suitable processors.

This paper introduces a scheduler for heterogeneous vision systems that finely partitions and maps suboperations of convolutional neural networks and image processing algorithms. Leveraging state-of-the-art compiler frameworks such as PyTorch, TVM, and ONNX, the proposed scheduler optimally distributes tasks across heterogeneous components. Experimental results show that the heterogeneous platform achieves on average 1.12× and 1.08× improvements in kernel runtime and energy consumption, compared to the best-performing discrete hardware counterparts, GPU and FPGA. The study demonstrates that partitioning algorithms based on their runtime and energy properties and optimally scheduling them improves energy and runtime efficiency compared to homogeneous components executing the complete algorithm.
Conference Presentation
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Teymoor Ali, George Paul, Robert Nicol, and Deepayan Bhowmik "Scheduling algorithms on heterogeneous architecture for efficient vision systems", Proc. SPIE 13137, Applications of Digital Image Processing XLVII, 131370F (30 September 2024); https://doi.org/10.1117/12.3031278
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Field programmable gate arrays

Image processing

Computer hardware

Computer architecture

Energy efficiency

Computer vision technology

Power consumption

RELATED CONTENT

Real-time FPGA architectures for computer vision
Proceedings of SPIE (March 21 2000)
Remote hardware-reconfigurable robotic camera
Proceedings of SPIE (October 05 2001)
FPGA-based architecture for motion recovering in real-time
Proceedings of SPIE (February 27 2002)
Reconfigurable vision system for real-time applications
Proceedings of SPIE (February 27 2002)

Back to Top