IBM’s Digital Chip Cracks the Brain’s Code

Friday - October 27 2023, 07:17 UTC - 1 year ago

IBM recently released NorthPole, a fully digital chip that mimics the brain’s structure and efficiency. It can run AI programs using up to 96 percent less energy than GPUs. NorthPole rounds out IBM’s decade-long research into brain-inspired chips, as the company attempts to create faster and more energy efficient chips for AI computing at the edge. This chip creates an open source platform, which allows for more efficient development of AI models that can operate with a lower carbon footprint.

The brain is an exceptionally powerful computing machine. Scientists have long tried to recreate its inner workings in mechanical minds. A team from IBM may have cracked the code with NorthPole, a fully digital chip that mimics the brain’s structure and efficiency. When pitted against state-of-the-art graphics processing units (GPUs)—the chips most commonly used to run AI programs—IBM’s brain-like chip triumphed in several standard tests, while using up to 96 percent less energy.

IBM is no stranger to brain-inspired chips. From TrueNorth to SpiNNaker, they’ve spent a decade tapping into the brain’s architecture to better run AI algorithms. Project to project, the goal has been the same: How can we build faster, more energy efficient chips that allow smaller devices—like our phones or computers in self-driving cars—to run AI on the "edge." Edge computing can monitor and respond to problems in real-time without needing to send requests to remote server farms in the cloud. Like switching from dial-up modems to fiber-optic internet, these chips could also speed up large AI models with minimal energy costs.

The problem? The brain is analog. Traditional computer chips, in contrast, use digital processing—0s and 1s. If you’ve ever tried to convert an old VHS tape into a digital file, you’ll know it’s not a straightforward process. So far, most chips that mimic the brain use analog computing. Unfortunately, these systems are noisy and errors can easily slip through.

With NorthPole, IBM went completely digital. Tightly packing 22 billion transistors onto 256 cores, the chip takes its cues from the brain by placing computing and memory modules next to each other. Faced with a task, each core takes on a part of a problem. However, like nerve fibers in the brain, long-range connections link modules, so they can exchange information too. This sharing is an "innovation," said Drs. Subramanian Iyer and Vwani Roychowdhury at the University of California, Los Angeles (UCLA), who were not involved in the study.

The chip is especially relevant in light of increasingly costly, power-hungry AI models. Because NorthPole is fully digital, it also dovetails with existing manufacturing processes—the packaging of transistors and wired connections—potentially making it easier to produce at scale.

The chip represents "neural inference at the frontier of energy, space and time," the authors wrote in their paper, published in Science.

Mind Versus Machine .

From DALL-E to ChatGTP, generative AI has taken the world by storm with its shockingly human-like text-based responses and images. But to study author Dr. Dharmendra S. Modha, generative AI is on an unsustainable path. The software is trained on billions of examples—often scraped from the web—to generate responses. Both creating the algorithms and running them requires massive amounts of computing power, resulting in high costs, processing delays, and a large carbon footprint.

These popular AI models are loosely inspired by the brain’s inner workings. But they don’t mesh well with our current computers. The brain processes and stores memories in the same location. Computers, in contrast, must break a problem into smaller components, offloading the data to different places nearby. Even then, AI algorithms run too slowly and use up too much energy, quashing hopes of creating a powerful AI computer the size of a cellphone.

NorthPole may have changed that. In the near future, the chip could be connected to several other NorthPole chips, creating a parallel computing architecture known as a cluster. While GPUs sport better raw computing power, their enclosed hierarchies force models to run step by step—a process known as serial processing. With a cluster of NorthPoles linked together, serial processing could become obsolete, as machines can work on different elements of a problem at the same time—an approach known as distributed computing. NorthPole chips could progress AI technologies through distributed computing while using less energy than the current solutions.

NorthPole is not yet ready for commercial use. Its creators are open-sourcing the design, however, so research centers and universities can help further this line of work. “If you open your problem to the outside world, then many people can work on it and that actually creates an ecosystem which can innovate faster,” said Modha. Eventually, chips like NorthPole can help us “innovate self-modifying AI systems at the edge,” with all the safety and efficiency they confer.