A few years ago, Intel came out with a neuromorphic (self-learning) research chip called Loihi, which mimics the brain’s basic mechanics. It makes machine learning faster, more efficient, and requires less power to compute. The neuromorphic chip draws inspiration from how neurons in a brain communicate and learn – but use spikes and plastic synapses that can be modulated based on timing. Machines with Loihi processors can adapt in real-time instead of waiting for the next update from the cloud. And, Loihi can process information up to 1,000 times faster and 10,000 times more efficiently than conventional processors.
Now, Intel announced it completed a data center rack-mounted system using Loihi processors. Pohoili Springs, as it is called, is the company’s most extensive neuromorphic computing system developed to date – integrating 768 Loihi neuromorphic research chips inside a chassis the size of five standard servers. It provides the computational capacity of 100 million neurons, which puts it to par with the computing power of the brain of a small mammal.
Mike Davies, director of Intel’s Neuromorphic Computing Lab, said:
Pohoiki Springs scales up our Loihi neuromorphic research chip by more than 750 times while operating at a power level of under 500 watts. The system enables our research partners to explore ways to accelerate workloads that run slowly today on conventional architectures, including high-performance computing (HPC) systems.
This new system will be accessible to members of the Intel Neuromorphic Research Community (INRC) via the cloud, allowing them to tap into it to tackle more complex problems.
Loihi processors have already been put to use before the making of Pohoiki Springs, however. Intel’s neuromorphic computing research team recently used Loihi in identifying and categorizing smells in a new form of an electronic nose.
Systems, like Pohoiki Springs, are the future of automation to AI and beyond. There is a growing need for computers to be able to solve abstract problems in real-time while adapting to change, seemingly without thinking, as we can do. This system lays the foundation for an autonomous, interconnected future where computers will be able to do things like identifying optimal paths for driving directions, minimize risk in stock portfolio returns, schedule airline flights, monitor traffic lights, and so much more.
