In keeping with IBM’s old motto, the IT giant hopes to lay the groundwork for an Internet of Things (IoT) that “thinks.” On Aug. 7, the company unveiled its largest chip ever, which contains 5.4 billion transistors and features an architecture that is inspired by the way the human brain processes information.
A product of the DARPA-funded Systems of Neuromorphic Adaptive Plastic Scalable Electronics (SyNAPSE) project, the “fully functional and production-scale chip” features 256 million programmable synapses, 1 million programmable neurons and 4,096 neurosynaptic cores. It is capable of performing 46 billion synaptic operations per second per watt.
By comparison, the single-core prototype developed in 2011 had just 262,144 programmable synapses and 256 programmable neurons.
Despite its capabilities and size — IBM describes the second-generation SyNAPSE chip “as one of the largest CMOS chips ever built” — it sips power. According to the company, “it consumes a minuscule 70mW—orders of magnitude less power than a modern microprocessor.”
The brain-like chip as built using Samsung’s 28nm chip making process, which incorporates dense on-chip memory and low-leakage transistors. Power savings are achieved, in part, by the chip’s event-driven architectures, which draws power only when it needs to, unlike traditional chips which consume electricity even at idle.
Shawn Han, vice president of Foundry Marketing for Samsung Electronics, said in a statement the project leveraged “a process traditionally used for commercially available, low-power mobile devices to deliver a chip that emulates the human brain by processing extreme amounts of sensory information with very little power.” He called the chip a “huge architectural breakthrough that is essential as the industry moves toward the next-generation cloud and big-data processing.”
According to Dr. Dharmendra S. Modha, Chief Scientist of IBM Research’s Brain-Inspired Computing unit, his company “has broken new ground in the field of brain-inspired computers, in terms of a radically new architecture, unprecedented scale, unparalleled power/area/speed efficiency, boundless scalability.”
The innovation could help pave the way for smarter, more aware IoT systems and mobile devices. “These brain-inspired chips could transform mobility, via sensory and intelligent applications that can fit in the palm of your hand but without the need for Wi-Fi,” added Dr. Modha.
Pedro Hernandez is a contributing editor at Datamation. Follow him on Twitter @ecoINSITE.
Photo courtesy of Shutterstock.