How did Intel Scales Neuromorphic Research System to 100 Million Neurons!!!!? check it now

Post date:

Author:

Category:

Today, Intel announced the readiness of Pohoiki Springs, its latest and most potent neuromorphic research system. It provides the computational capacity of 100 million neurons. The cloud-based system will be made available to members of the Intel Neuromorphic Research Community (INRC), extending their neuromorphic work to solve more significant, more complex problems.

According to Mike Davies, director of Intel’s Neuromorphic Computing Lab: “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.”

Pohoiki Springs, a data center rack-mounted system unveiled in March 2020, is Intel’s most extensive neuromorphic computing system developed to date. It integrates 768 Loihi neuromorphic research chips inside a chassis, the size of five standard servers. (Credit: Intel Corporation)

 

What is it?

Pohoiki Springs is a data center rack-mounted system and is Intel’s most extensive neuromorphic computing system developed to date. It integrates 768 Loihi neuromorphic research chips inside a chassis, the size of five standard servers. The human brain acts as the main inspiration for Loihi processors. Loihi is so efficient that it can process specific workloads 1,000 times faster and 10,000 times more efficiently than most other processors.

Intel researchers believe the extreme parallelism and asynchronous signaling of neuromorphic systems may provide significant performance gains at dramatically reduced power levels compared with the most advanced conventional computers available today.

What the Opportunity for Scale is

In nature, some of the smallest living creatures perform millions of computational problems that go unnoticed. For example, ants can visualize or track objects so that they can avoid them on their path. In the same way,  Intel’s smallest neuromorphic system, Kapoho Bay, comprises two Loihi chips with 262,000 neurons and supports a variety of real-time edge workloads. Intel and INRC researchers have demonstrated the ability for Loihi to recognize gestures in real-time, read braille using novel artificial skin, orient direction using learned visual landmarks, and discover new odor patterns.