Intel Labs unveiled its largest neuromorphic computer on Wednesday, a 1.15 billion neuron system believed to be roughly analogous to an owl's brain.
How neuromorphic computing will change our world in wonderful ways | Intel
But don't worry, Intel hasn't recreated Fallout's Robobrain. Instead of a network of organic neurons and synapses, Intel's Hala Point emulates them all in silicon.
At about 20 W, our brains are surprisingly efficient at processing the vast amounts of information pouring in from each of the senses at any given moment. The field of neuromorphics, which Intel and IBM have spent the last few years exploring, aims to mimic the brain's network of neurons and synapses to build computers that can process information more efficiently than traditional accelerators.
How effective? According to Intel, its latest system – delivered to Sandia National Labs in the US – is a 6U box about the size of a microwave oven that consumes 2,600W and can reportedly achieve deep neural network efficiencies as high as 15 TOPS/W at 8- little precision. To put that into perspective, Nvidia's most powerful system, the Blackwell-based GB200 NVL72, which hasn't even shipped yet, only manages 6 TOPS/W at INT8, while its current DGX H100 system can handle around 3.1 TOPS/W .
