Presentation + Paper
4 October 2023 Custom ASICs for data center video processing: advancements in AI-ML integrated, high-performance VPUs for hyper-scaled platforms
E. Andrade, A. Ndachena, B. Macz, C. Tang, M. Wang, S. Yen, P. Mohammadi, L. Xu, J. Lou
Author Affiliations +
Abstract
Purpose-built silicon for hyper-scaled video platforms is becoming mainstream as developers move beyond common video IP cores and commodity chip designs. A new generation of video processing units (VPUs) powered by Application Specific Integrated Circuits (ASICs) combine the essential encoding, decoding, and transcoding functionality with an on-chip deep neural network engine for AI and ML framework integration. This paper explores the transformative impact of custom ASICs on data center video processing, exploring their pivotal role in meeting the ever-evolving demands of this dynamic landscape. We will discuss design trade-offs for data center workloads using VPUs that involve multiple priorities, such as improving video quality while maintaining low bitrates using AI and ML applications enabled by silicon-powered video encoding and processing stacks. The paper will also showcase practical applications of AI and ML that are currently infeasible using software alone.
Conference Presentation
(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.
E. Andrade, A. Ndachena, B. Macz, C. Tang, M. Wang, S. Yen, P. Mohammadi, L. Xu, and J. Lou "Custom ASICs for data center video processing: advancements in AI-ML integrated, high-performance VPUs for hyper-scaled platforms", Proc. SPIE 12674, Applications of Digital Image Processing XLVI, 1267412 (4 October 2023); https://doi.org/10.1117/12.2685872
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Video

Video processing

Video acceleration

Video coding

Video compression

Artificial intelligence

Video surveillance

Back to Top