IBM ready to commercialise light pulse technology
Big Blue claims data rates of 25Gbps have already been achieved.

IBM has developed a chip that can transmit data using light signals, and claims this will help firms deal with ever increasing volumes of data.
The "silicon nanophotonic" technology utilises light pulses alongside electric signals, which IBM claims allows more information to be carried between servers at a faster rate than traditional chips.
Big Blue has been working on the technology for 10 years and is ready to commercialise the concept as businesses enter the Big Data era.
IBM wants to commercialise the silicon nanophotonic technology using traditional manufacturing processes. The firm has taken a 90nm CMOS fabrication and integrated a number of modules to facilitate the light phase transfers. Additional components include wavelength division multiplexers (WDM), modulators and detectors.
IBM chip shows blue optical waveguides transmitting high-speed optical signals and yellow copper wires carrying high-speed electrical signals
So far nanophotonic technology has exceeded the data rates of 25Gbps per channel, IBM said.
The current method for increasing the performance in datacentres is to facilitate more parallel processes. This is done by packing more cores onto individuals processors and then loading more of these chips into racks and blades.
Get the ITPro daily newsletter
Sign up today and you will receive a free copy of our Future Focus 2025 report - the leading guidance on AI, cybersecurity and other IT challenges as per 700+ senior executives
IBM claims this type of scaling is unsustainable and not suitable for transferring ExaBytes of data.
The firm claims that optics are "destined" to be utilised in datacentres as it can meet the large bandwidth demands of high-performance computing.
"As it already happened in long-haul communications decades ago when optical fibers replaced copper cables, the copper cables that connect racks in the datacentres are now being replaced by optical fibers," the firm noted on its research page.
"Following the same trend optics can become competitive with copper at shorter and shorter distances eventually leading to optical on-board and may be even on-chip communications."
Dr. Solomon Assefa, research staff member at IBM will reveal further details at the IEEE International Electron Devices Meeting (IEDM) this week
-
RSAC Conference 2025: The front line of cyber innovation
ITPro Podcast Ransomware, quantum computing, and an unsurprising focus on AI were highlights of this year's event
-
Anthropic CEO Dario Amodei thinks we're burying our heads in the sand on AI job losses
News With AI set to hit entry-level jobs especially, some industry execs say clear warning signs are being ignored
-
Put AI to work for IT operations
whitepaper Reduce the cost and complexity of managing hybrid applications
-
AI in the retail industry is spreading beyond the IT department
News AI has become a strategic imperative for retailers, delivering marked productivity gains
-
Maximizing contact center operations with generative AI assistants backed by responsible AI principles
whitepaper Reduce the cost and complexity of managing hybrid applications
-
IBM just launched powerful new open source AI models – here’s what you need to know
News Available under the Apache 2.0 license, IBM's Granite 3.0 models are trained on enterprise data and can out-perform the competition
-
Achieving business outcomes with generative AI
Webinar Take your hybrid cloud journey to the next level with generative AI
-
Wimbledon’s new Catch Me Up AI feature promises to keep fans up to date at the tournament – after it irons out some of the wrinkles
News The latest feature to come out of IBM’s partnership with Wimbledon will keep fans engaged from the early stages right through to the final with dynamic player insights
-
AI demands new ways of data management
whitepaper The data leader’s guide for how to leverage the right databases for applications, analytics and generative AI
-
AI governance for responsible transparent and explainable AI workflows
whitepaper Build greater trust in your AI