Large receive offload

Fujitsu Develops Virtual Router Acceleration Technology to Deliver Ultra-High-Speed Packet Processing Performance

Retrieved on: 
Friday, November 27, 2020
Computing, Computer networking, Telecommunications, Networking hardware, Computer science, Internet architecture, Router, Server appliance, Field-programmable gate array, Packet processing, Fujitsu, Large receive offload

As data volumes increase and systems become increasingly complex, however, the CPU resources required for packet processing in a virtual network increase.

Key Points: 
  • As data volumes increase and systems become increasingly complex, however, the CPU resources required for packet processing in a virtual network increase.
  • To resolve this issue, Fujitsu Laboratories has now developed technology to accelerate packet address control, which had been a performance bottleneck, while also offloading the processing of router functions in the virtual network to field programmable gate arrays (FPGAs)(2).
  • This speeds up packet processing performance eighteen-fold compared with existing virtual routers, while reducing the use of CPU resources to about one thirteenth that of existing technology.
  • Fujitsu Laboratories has now developed technology to offload the burden of virtual router functionality from the CPU to FPGAs, alongside technology to increase the speed of packet addressing control.

Intilop Delivers Their Enhanced One Thousand TCP/UDP Session Hardware Accelerator and Kernel Bypass Linux Driver for Hyper-Performance Networking Systems

Retrieved on: 
Thursday, April 25, 2019
Computing, Digital technology, Networking hardware, Telecommunications, TCP offload engine, Hardware acceleration, Xilinx, Field-programmable gate array, Transmission Control Protocol, Large receive offload

This 10G Hardware/Software subsystem with TCP Accelerator (TCP-Full-Offload-Engines) implements One Thousand Simultaneous TCP/UDP Connections and Bandwidth of more than 1 Gigabyte/sec per port regardless of number of simultaneous or active TCP Sessions with Kernel Bypass driver is unprecedented.

Key Points: 
  • This 10G Hardware/Software subsystem with TCP Accelerator (TCP-Full-Offload-Engines) implements One Thousand Simultaneous TCP/UDP Connections and Bandwidth of more than 1 Gigabyte/sec per port regardless of number of simultaneous or active TCP Sessions with Kernel Bypass driver is unprecedented.
  • The deployment-ready, sub-system solution provides networking OEMs an Ultra-low-latency and Hyper-performance for all networking equipment segments that have to process TCP/UDP Protocol.
  • Clients will be able to utilize FPGAs technology from Xilinx and Altera to get all of the benefits of TCP hardware acceleration.
  • As a pioneer, Intilop was the first company to deliver a series of Full TCP Offload Engines on FPGAs in 2009.