Ryft Systems Puts Real-Time Analytics of Big Data an API Call Away

Mike Vizard
Slide Show

Capitalizing on Big Data: Analytics with a Purpose

Accessing analytics of any type has always been a complex endeavor. But starting this week, Ryft Systems wants to make real-time analytics running on a 1u server built using field programmable gate arrays (FPGAs) a single application programming interface (API) call away.

Pat McGarry, vice president of engineering for Ryft Systems, says that by deploying a dedicated Ryft ONE server that runs a “Linux-like” operating system to process analytics IT organizations can once and for all eliminate I/O bottlenecks.

The biggest challenge with Big Data, says McGarry, is not so much the size of that data that needs to processed at any given time, but rather the velocity at which that data needs to be processed. Rather than relying on a general-purpose processor, McGarry says that Ryft has combined FPGAs with up to 40 solid-state disk drives that can process up to 48TB of data at a rate of 10 gigabytes per second.


In addition, McGarry notes that the Ryft ONE not only reduces the complexity of invoking analytics using an open API, it significantly reduces the size of the data center footprint to process those applications at a rate that is 200 times faster than systems based on general-purpose processors.

Obviously, not every analytics application needs to be processed in real time. But at a time when organizations are investing in Big Data to help them make better decisions, the less historical the data being used to make those decisions, the sounder they are likely to be.



Add Comment      Leave a comment on this blog post
Mar 24, 2015 8:39 AM Ilya Geller Ilya Geller  says:
Language has its own Internal parsing and statistics. For instance, there are two sentences: a) ‘Fire!’ b) ‘In this amazing city of Rome some people sometimes may cry in agony: ‘Fire!’’ Evidently, that the phrase ‘Fire!’ has different importance into both sentences, in regard to extra information in both. This distinction is reflected as the phrase weights: the first has 1, the second – 0.12; the greater weight signifies stronger emotional ‘acuteness’. First you need to parse obtaining phrases from clauses, for sentences and paragraphs. Next, you calculate Internal statistics, weights; where the weight refers to the frequency that a phrase occurs in relation to other phrases. That's it - there is no Big Data and its problem. Reply

Post a comment

 

 

 

 


(Maximum characters: 1200). You have 1200 characters left.

 

null
null

 

Subscribe to our Newsletters

Sign up now and get the best business technology insights direct to your inbox.