Netronome just introduced its Agilio CX 50GbE SmartNICs in OCP Mezzanine 2.0 form factor with line-rate advanced cryptography and 2GB onboard DDR memory to the market. The new SmartNIC cuts down on tail latency significantly and this allows for a reasonable level of enabling high-performance 2.0 applications to be used to advantage in cost and energy-efficient servers.
With advanced Transport Layer Security (TLS/SSL)-based cryptography support as well as a line-rate of as high as two million stateful sessions for each SmartNIC, web and data storage servers in hyperscale environments, a chance now exists for being secured far better than ever before. This consequently prevents the hacking of networks and important user data.
Quite useful in OCP Yosemite servers, the Agilio CX 50GbE SmartNICs puts a standards-based and open advanced buffer scheme to work. It is enabled by the peculiar several-core multithread processing memory-based architecture of the Netronome Network Flow Processor (NFP) silicon. This enhances the performance of applications and also allows hyperscale operators to maintain great levels of service level agreements (SLAs).
Dynamic and creative eBPF-based hardware acceleration and programming allows intelligent scaling of networking workloads through a variety of host CPU cores, improving the efficiency of servers.
The solution also optimizes security and data center efficiencies simply by offloading TLS, a widely deployed protocol that is usually put to use for encryption and authentication of application that needs data to be exchanged in a secure manner, over a network. In the words of Sujal Das, Chief marketing and strategy officer at Netronome, “Securing user data in Web 2.0 applications and preventing malicious attacks as those involving BGP hijacking as experienced quite recently in hyperscale operator infrastructures are critical needs that have exacerbated significantly in recent years. Netronome developed the Agilico CX 500GbE SmartNIC solution to address these vital industry requirements by meticulously optimizing the hardware with open source and hyperscale operator applications and infrastructures.”