AT&T Is Giving the P4 Language a Whirl
A mere 78 lines of code that even a manager can understand.
A mere 78 lines of code that even a manager can understand.
The post Worth Reading: Rolling the root appeared first on 'net work.
There are few international supercomputing hubs sporting the systems and software prowess of the Swiss National Supercomputing Center (CSCS), which started with large-scale vector machines in 1992 and moved through a series of other architectures and vendors; from NEC at the beginning, to IBM, and most recently, Cray. In fact, the center has had an ongoing preference for Cray supercomputers, with an unbroken stretch of machines beginning in 2007.
In addition to choosing Cray as the system vendor, CSCS has been an early adopter and long-term user of GPU acceleration. According to the center’s director, Thomas Schulthess, teams there firmed …
First Wave of Pascal GPUs Coming to European Supercomputer was written by Nicole Hemsoth at The Next Platform.
Telcos looking at virtualization can look to where it's been done before.
While we normally think of RFCs as standards, there is actually a lot of useful information published through the IETF process that relates to basic network engineering concepts. Since this information is specifically and intentionally vendor independent, it often goes back to the theoretical basis of a line of thinking, or explains things in a way that’s free of vendor implementation jargon. From time to time, I like to highlight these sorts of drafts, to bring them to the notice of the wider networking community.
A lot of basic research has gone into quality of service from the perspective of queuing, marking, and dropping mechanisms. The result of this research is a wide array of quality of service mechanisms, which tend to be explained either using deep math, or in terms of “look what feature we’ve implemented, and here’s how to configure it.” RFC7806, published this month, is a useful intermediary between the high math and vendor implementation styles of presentation. This RFC describes a model often used for understanding quality of service, the Generalized Processor Sharing model, and how it applies to a few packet queuing, marking, and drop strategies.
Benchmarking routing protocols might not be something you Continue reading