Wind River unlocks multi-core scalability for advanced networking apps

IDF 2011 SAN FRANCISCO, USA: Wind River has introduced the latest version of its Wind River Network Acceleration Platform, a multi-core acceleration solution delivering ultra-fast networking performance for network infrastructure equipment.

The solution enables greater performance with the addition of packet acceleration for higher-level protocols including Layer 4 transport protocols such as UDP and TCP. This release expands hardware support for Freescale QorIQ and Intel Xeon next-generation multi-core processors. Optimized for multi-core silicon, Wind River Network Acceleration Platform allows network performance to scale efficiently with the number of cores in a processor.

“Network equipment providers are racing to tackle the growing challenges of delivering high-performance network products that scale to meet the exploding traffic on 3G, 4G and wireline networks,” said Mike Langlois, GM of networking and telecommunications at Wind River. “Wind River Network Acceleration Platform allows project teams to spend their time developing high value, intelligent networking applications while easing migration to cutting-edge silicon. Wind River delivers a comprehensive network acceleration solution that fully leverages the benefits of multi-core technology for breakthrough networking performance.”

Using a multi-core asymmetric multiprocessing (AMP) approach, Wind River Network Acceleration Platform enhances the standard Linux networking stack to support high-performance network acceleration capabilities far exceeding what is possible using symmetric multiprocessing (SMP) mode alone.

Wind River’s unique AMP approach enables packet acceleration that provides as much as 10 times the performance of standard Linux configurations. Unlike point solution software packages that can only remedy a single bottleneck to partially address performance issues, Wind River Network Acceleration Platform is an integrated solution to help eliminate bottlenecks not only in moving packets through the silicon itself, but throughout the entire networking platform.