Intilop's CTO, K. Masood to Present "How TCP Offload Engines scale up the TCP traffic bandwidth by up to 8x on existing Ethernet Networks", at the Ethernet Summit
Santa Clara, Calif, Feb. 09, 2012 -- Intilop, Inc. a pioneer and a recognized leader as developer and provider of complex Ultra-Low latency networking IPs, Products and Systems, today announced that Mr. Kelly Masood will be presenting a keynote titled: “How TCP Offload Engines scale up the TCP traffic bandwidth by up to 8x on existing 1G and 10G Ethernet Networks”, at the upcoming Ethernet Technology Summit, at the Hilton-Doubletree Hotel, San Jose, CA., on Wednesday, Feb. 22, 2012 at 9:50 AM. (PST).
Presentation Abstract:
“Phenomenal adaptation of 10G Ethernet ports is currently taking place, with more than 22 million ports projected by 2014 (source: The Linley Group). For the last 50 years, TCP/IP protocol software has been carrying the load for all network communications. Due to increase in traffic volume, a revolutionary approach to the problem by the way of; “1G and 10G TOE and Enhanced Ethernet MACs are needed to manage this explosive growth without deploying additional new pipes or equipment, which results in mega cost savings plus network life-extension.”
Moreover, beyond network life extension tremendous additional benefits are gained by deploying 1G or 10G TCP Offload Engines to make existing networks highly scalable. For example they can: i) Increase 1G-10G pipe bandwidth capacity to 95%, ii) Remove traffic queuing bottlenecks between CPU and TCP/UDP transactions, iii) Achieve Ultra-Low latency of 100 ns, iv) Drop TCP/UDP traffic related host CPU utilization below 5%, and v) Lower CPU related heat dissipation.
In contrast, networks still running on TCP/IP software are hard pressed to keep up with the mushrooming data on 1 G and 10G bps line rates. A typical TCP/IP stack has tens of thousands of lines of C code. Clearly this is large amount of code to be efficiently handled by any CPU/OS in software for real-time processing of multiple TCP sessions.
Therefore, by Full Offloading this critical yet time consuming function to an external and independent TCP Offload Engine that performs all TCP software functions in FPGA hardware is the most efficient way to go. Not only it frees up the host CPU, it increases the through put to near line rate and it decreases the latency to just a few hundred nanoseconds. Consequently, tremendous network scalability potential is available on the existing 1G & 10G pipes that can benefit the entire networking industry from aerospace/defense, financial services, cloud computing, and storage to telecomm etc.
Information on the Ethernet Technology Summit: www.ethernetsummit.com.
Intilop company and product information is available at: www.intilop.com.
Intilop Corporation is a developer and pioneer in advanced networking silicon IP and solutions, custom hardware solutions, SoC/ASIC/FPGA integrator and total solutions provider for Networking, Network Security, storage and Embedded Systems. They offer silicon proven semiconductor IPs and Products with various interfaces and comprehensive value add hardware and software solutions.
|
Related News
- Intilop Engineering Executive, K Masood to Present on 10G TCP Offload Engines at Ethernet Summit
- Intilop presents at Server Design Summit, how their ultra high performance 10G full TCP Offload Technology increases the network bandwidth by up to 6 times
- Intilop Corporation's Live Demo of its 3rd Generation Enhanced Ultralow latency 10G bit TCP Offload Engine and Total system solution for the Financial Markets received tremendous interest at the 'Low Latency Summit' in NYC.
- Enyx Premieres 25G TCP and UDP Offload Engines with Xilinx Virtex UltraScale+ 16nm FPGA on BittWare's XUPP3R PCIe Board
- Intilop releases Network Security TOE Module for Altera and Xilinx FPGAs for their 10G & 40G Full TCP & UDP Offload Engines
Breaking News
- Jury is out in the Arm vs Qualcomm trial
- Ceva Seeks To Exploit Synergies in Portfolio with Nano NPU
- Synopsys Responds to U.K. Competition and Markets Authority's Phase 1 Announcement Regarding Ansys Acquisition
- Alphawave Semi Scales UCIe™ to 64 Gbps Enabling >20 Tbps/mm Bandwidth Density for Die-to-Die Chiplet Connectivity
- RaiderChip Hardware NPU adds Falcon-3 LLM to its supported AI models
Most Popular
E-mail This Article | Printer-Friendly Page |