Blog

Netronome_Web_Logo_UPE9ULO.original.png

Optimizing BPF: Smaller Programs for Greater Performance

By Quentin Monnet | Jan 14, 2020

For decades, the evolution of computing performance has been governed by Moore’s law, which stated that every two years, the size of transistors would decrease and their numbers in dense integrated circuits would double. Then physics caught up, and the industry started to add processing cores to compensate the slow down of that curve (or to be more accurate, the end of frequency scaling)

Netronome_Web_Logo_UPE9ULO.original.png

Open-Sourcing the CoreNIC Firmware

By Quentin Monnet | Sep 05, 2019

Programmability is everywhere! Gone are the days when hardware components would be entrusted with a single task. Nowadays, even network cards run low-level software, also known as “firmware,” usually distributed as binary images by vendors. But what if we were to open these programs to the users? Since we love to create new opportunities, Netronome just published the source code for the CoreNIC firmware, used with the Agilio SmartNICs.

Netronome_Web_Logo_UPE9ULO.original.png

Libkefir: All Your Rules in One Bottle

By Quentin Monnet | Jul 25, 2019

Netronome is releasing libkefir, a library for converting network filtering rules into BPF programs, in a simple and efficient way! But how does it work? What is it for? Fear not, for all your questions will [hopefully!] be addressed in this blog.

Netronome_Web_Logo_UPE9ULO.original.png

Overcoming Tail Latency with Netronome SmartNICs

By Netronome | Jul 11, 2019

Netronome explains why tail latency can have a crippling effect in data center infrastructures, why it is important for hyperscalers to overcome its challenges, and how Netronome SmartNICs can solve the problem of high tail latency.

Netronome_Web_Logo_UPE9ULO.original.png

The $200M Funding Endorsement: SmartNICs are Rock Stars in Modern Data Centers

By Netronome | Jun 28, 2019

An announcement yesterday about a $200M investment in a data center silicon startup in Silicon Valley was a momentous revival of the glorious past. This has not happened in while, in such a mammoth scale. Even on a smaller scale, the focus lately has been on silicon related to machine learning and inferencing.