OCTEON® 10 Machine Learning Industry’s First Integrated Inferencing Platform White Paper

PublishTime：2022-03-18

● OCTEON DPUs have traditionally been used extensively as integrated network and security processors in enterprise networking equipment. This equipment was largely built to support a hierarchical network topology of core, distribution and access with firewalls protecting the entry and exit at the perimeters. Most enterprises owned and maintained networking hardware on premise. Over the last decade, enterprises have started moving workloads and access outside of this controlled environment and into public, private and hybrid networks accessed through both wired and, increasingly, wireless communications networks.
● The combination of remote access, the drive to reduce costs and upgrade services, and the expansion of cloud network capabilities has led to a borderless (or perimeter-less) digital workplace and significantly changed the dynamics of building and managing connectivity and access. This disaggregation of data center resources has opened possibilities to add accelerators for these workloads into the cloud, so called Workload Accelerators. In addition to networking and security, new storage, video, and 5G workloads have been added to the list of infrastructure use cases, each needing workload acceleration. As a final kicker, machine learning inferencing capability can augment these workloads with anomalous fault detection, security and quality improvements, and deep application insight. These capabilities must be delivered with a comprehensive, optimized, open-sourced software framework.

Brand of Product：	MARVELL
Part#：
Product Category：	enterprise networking equipment More
Application：	[ integrated network ][ security processors ] More
Data Type：	White Paper More
Safety & Environment Standards：	More
Operating Temperature：	Please see the document for details
Qualification Grade：	More
Qualification Approval：	More
Package：
Language：	English Chinese Chinese and English Japanese
Date of Creation：	June 2021
Version Number：
Data Encoding：
Data Size：	318 KB

Data section preview(2pages)

- The full preview is over. If you want to read the whole 5 page document,please Sign in/Register -

Download

+1 Like
Add to Favorites

Recommend

Technical Resources

More>

All reproduced articles on this site are for the purpose of conveying more information and clearly indicate the source. If media or individuals who do not want to be reproduced can contact us, which will be deleted.

Integrated Circuits