IBM said this evening that its scientists have developed a computer chip that can move a trillion bits of information a second.
Known as the "Holey Optochip," the prototype optical chipset can transfer the equivalent of 500 high-definition movies a second, or the entire U.S. Library of Congress Web archive in an hour, Big Blue said. The innovation is possible because IBM's scientists figured out that, by drilling 48 minuscule holes in a standard quarter-inch silicon CMOS chip, they were able to ramp up data transfer rates from what was possible.
And by breaking through the terabyte-per-second barrier, the Holey Optochip is capable of data transfer at up to eight times the speed of today's parallel optical components,said. The company plans to show off its research on the new chip at the Optical Fiber Communication Conference in Los Angeles tomorrow.
IBM said the Holey Optochip module "is constructed with components that are commercially available today, providing the possibility to manufacture at economies of scale."
And that's important, the company said, because major advances in data transfer rates are being driven by a vast increase in the number of applications and services that send large amounts of data over consumer and enterprise networks. And by moving to an optical networking architecture, IBM said, networks benefit from the speeds offered by using light pulses rather than electrons being sent over wires.
In addition, the new chip offers computer makers energy efficiencies previously unavailable to them, IBM said. "Consistent with green computing initiatives, the Holey Optochip achieves record speed at a power efficiency...that is among the best ever reported," the company said in a release. "The transceiver consumes less than five watts; the power consumed by a 100 watt light bulb could power 20 transceivers. This progress in power efficient interconnects is necessary to allow companies that adopt high-performance computing to manage their energy load while performing powerful applications such as analytics, data modeling, and forecasting."