IBM Readies Silicon Nanophotonics to Tackle Big Data

After releasing an initial proof of concept in 2010, IBM Research has announced a breakthrough in the manufacturing process for its silicon nanophotonics chips, which combine silicon and lasers on optical-electrical circuits, VentureBeat reports.

IBM Silicon Nanophotonics 1.jpg

“This technology breakthrough is a result of more than a decade of pioneering research at IBM,” said Dr. John E. Kelly, Senior Vice President and Director of IBM Research. “This allows us to move silicon nanophotonics technology into a real-world manufacturing environment that will have impact across a range of applications.”

Silicon nanophotonics will directly target the challenges created by the era of big data, as rising congestion among remote data storage, locations coupled with a boom in services and applications, has become a growing risk for enterprise networks. 

Current optical components, expensive and separately deployed, use lasers to guide light and convert it into electrical signals processed on silicon chips. IBM's solution will enable optical components to be embedded inside a standard 90 nanometer chip at low cost while still meeting performance requirements for big data. The goal is to usher in a faster, more powerful computing standard to drive information through high-speed servers and supercomputers. 

Whether transferring data a few centimeters or many kilometers, IBM's small scale optical components can move terabytes of data with light pulses through optical firers, as fast as 25 gigabits per second, VentureBeat reports. 

The previous obstacle to deployment of silicon nanophotonics has been high production costs, however IBM has developed a factory line that incorporates the optical components -- such as wavelength division multiplexers (WDM), modulators, and detectors -- alongside the CMOS electrical circuitry on a normal silicon chip. 

According to the VentureBeat report, IBM nanophotonics scientist Solomon Assefa will deliver a presentation on the technology at the IEEE International Electron Devices Meeting, which starts today in San Francisco. 

Build smarter apps with Machine Learning, Bots, Cognitive Services - Start free.

Start Learning Now