August 11, 2014
IBM recently unveiled the second generation of a new type of computer chip that consumes less power and performs faster than traditional chips based on Von Neumann architecture. The SyNAPSE chip, which is still in development, was designed to function like the human brain, using more than a million “neurons” communicating through electrical spikes. This new technology requires a new type of programming language as well, but the performance gains are massive.
Because of its unique structure of “neurons,” the SyNAPSE chip is better suited for analyzing and discerning patterns in data. Some potential applications for the chip include image pattern recognition in self-driving cars, powering small search-and-rescue robots, and transcribing meetings. The chip can perform parallel processing much faster and accurately than any other chip.
IBM put its chip to the test by running an image recognition program. The chip was supposed to recognize cars, people, and bicycles in a video from a street intersection. According to MIT Technology Review, “A nearby laptop that had been programmed to do the same task processed the footage 100 times slower than real time, and it consumed 100,000 times as much power as the IBM chip.”
The SyNAPSE chip consumes just about the same amount of power as a hearing aid, about 70 milliwatts. To improve performance, the chip can be connected to several other chips, making a larger neural network.
The SyNAPSE project is now eight years in the making. After $53.5 million in funding from the U.S. Defense Advanced Research Projects Agency (DARPA), IBM has introduced two generations of the chip. The first generation chip was unveiled in 2013. Last year, IBM also created a new programming language, and SyNAPSE University, to support the new technology, according to Engadget.