AI/ML and AR/VR applications at Edge

AI/ML and AR/VR applications at Edge

@Sukhdev Kapur

@Vikram Siwach

 

 

Project Technical Lead:               Vikram Siwach



Project Committers detail:

Committer

Committer

Company

Committer

Contact Info

Committer Bio 

Committer Picture 

Self Nominate for PTL (Y/N)

Committer

Committer

Company

Committer

Contact Info

Committer Bio 

Committer Picture 

Self Nominate for PTL (Y/N)

 

 

 

 

 

 

Sukhdev Kapur

Juniper Networks

@Sukhdev Kapur

 

 

 

Vikram Siwach

MobiledgeX

@Vikram Siwach

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Presentation:

 

 

Blueprint species:

Attributes

Description

Informational

Attributes

Description

Informational

Type

New Blueprint for enabling AI/ML and low latency AR/VR capabilities at the Edge

New submission for integrating Tungsten Fabric for Edge Cloud for AI/VR applications for developers in a distributed environment

Industry Sector

Edge Cloud, Enterprise, 5G, and IoT

The blueprint empowers Integrated Edge Cloud architecture to use single SDN Controller (Tungsten Fabric) for all type of Containers, Virtual Machines, and Bare Metal Servers.

Blueprint Family - Proposed   Name

Integrated Edge Cloud

 

Use Case

Programmability on switches and I/O Accelerations on programmable NICs & embedded FPGAs to deliver AI/ML workload placement and low latency demands of AR/VR applications onboarding edge stack

 

Blueprint proposed Name

AI/ML and AR/VR applications at Edge

 

Initial POD Cost (capex)

Leverage white boxes, standard NICs:  The cost of POD will depend upon the hardware profiles and peripherals desired

 

Scale & Type

The deployment will employ baremetal as well virtual machines and containers. The smallest footprint for minimal Cloudlet is 9VMs to a large Cloudlet could span to 8-Cluster Cloudlets

 

Applications

AI/ML streaming workloads and AR/VR applications

 

Power Restrictions

Less than 10Kw

 

Infrastructure orchestration

OpenStack Queens or above

Docker 1.13.1 or above

Container Orchestration –K8s 1.10.2 or above

OS - Ubuntu 16.x, CentOS

 

SDN

Tungsten Fabric Kernel vRouter, DPDK vRouter, SR-IOV and SmartNIC

 

Workload Type

Containers over VM or baremetal

 

Additional Details

● Runs on Commodity HW
● x86, ARM, SoC, ...
● Multiple options for partial or full NIC offloads (Intel, Netronome, Mellanox)
● Future Supports:
● eBPF/XDP offload