Learn about offloading Open Virtual Network (OVN) pipelines to Intel Infrastructure Processing Units (IPU) in this technical conference talk from the 2024 OCP APAC Summit. Explore the implementation of P4OVN, a solution that leverages programmable network hardware to enhance network virtualization performance and efficiency. Discover how this offloading approach can optimize data center networking by moving virtual network processing from general-purpose CPUs to specialized IPU hardware.
Overview
Syllabus
P4OVN Offloading OVN Pipeline to Intel IPU
Taught by
Open Compute Project
Related Courses
-
Intel IPU and NVMe Initiator with SPDK - Introduction to Hardware Integration and Acceleration Framework
-
Running OVN at Scale - Performance Issues and Solutions in OpenStack Environments
-
OVN-Kubernetes: The New Default CNI of OpenShift
-
SIGCOMM 2020 - TEA - Enabling State Intensive Network Functions on Programmable Switches
-
Comparing TC-Flower and RTE_Flow Offloading in Open vSwitch
-
Empower Programmable Pipeline for Advanced Stateful Packet Processing
