Today, Intel has built the world’s largest neuromorphic system. It is code-named Hala Point, this large-scale neuromorphic system, initially deployed at Sandia National Laboratories, utilizes Intel’s Loihi 2 processor. It is aimed at supporting research for future brain-inspired artificial intelligence (AI), and tackles challenges related to the efficiency and sustainability of today’s AI. Hala Point advances Intel’s first-generation large-scale research system, Pohoiki Springs, with architectural improvements to achieve over 10 times more neuron capacity and up to 12 times higher performance.
Hala Point supports up to 20 quadrillion operations per second, or 20 petaops, with an efficiency exceeding 15 trillion 8-bit operations per second per watt (TOPS/W) when executing conventional deep neural networks. This rivals and exceeds levels achieved by architectures built on graphics processing units (GPU) and central processing units (CPU). Hala Point’s unique capabilities could enable future real-time continuous learning for AI applications such as scientific and engineering problem-solving, logistics, smart city infrastructure management, large language models (LLMs) and AI agents.
Hala Point packages 1,152 Loihi 2 processors produced on Intel 3 process node in a six-rack-unit data center chassis the size of a microwave oven. The system supports up to 1.15 billion neurons and 128 billion synapses distributed over 140,544 neuromorphic processing cores, consuming a maximum of 2,600 watts of power. It also includes over 2,300 embedded x86 processors for ancillary computations.
Hala Point integrates processing, memory and communication channels in a massively parallelized fabric, providing a total of 16 petabytes per second (PB/s) of memory bandwidth, 3.5 PB/s of inter-core communication bandwidth, and 5 terabytes per second (TB/s) of inter-chip communication bandwidth.
Applied to bio-inspired spiking neural network models, the system can execute its full capacity of 1.15 billion neurons 20 times faster than a human brain and up to 200 times faster rates at lower capacity. While Hala Point is not intended for neuroscience modeling, its neuron capacity is roughly equivalent to that of an owl brain or the cortex of a capuchin monkey.
Loihi-based systems can perform AI inference and solve optimization problems using 100 times less energy at speeds as much as 50 times faster than conventional CPU and GPU architectures
Brian Wang is a Futurist Thought Leader and a popular Science blogger with 1 million readers per month. His blog Nextbigfuture.com is ranked #1 Science News Blog. It covers many disruptive technology and trends including Space, Robotics, Artificial Intelligence, Medicine, Anti-aging Biotechnology, and Nanotechnology.
Known for identifying cutting edge technologies, he is currently a Co-Founder of a startup and fundraiser for high potential early-stage companies. He is the Head of Research for Allocations for deep technology investments and an Angel Investor at Space Angels.
A frequent speaker at corporations, he has been a TEDx speaker, a Singularity University speaker and guest at numerous interviews for radio and podcasts. He is open to public speaking and advising engagements.
How much can an AI running with this much neuro compute power achieve? in other words, given that humans use a small fraction of brain power, wouldn’t an artificial human compute equivalent brain be able to do much more?
That’s not a given, it’s completely BS in fact. humans use their whole brain all the time. MRI / PET studies make that abundantly clear.
According to a search (nature.com), a human brain has 86 billions neurons. We are getting close in terms of pure computation power. It’s clearly that our topology and model is still lacking.
That’s said, I have the impression than the human brain active the neurons a lot less than our current hardware. That means that while it has more neurons, as they aren’t active at the same time, the consumption is a lot lower.
And one of the problems to escalate the model is the energy dissipation and cost. So I think the key are building neurons with little to no energy requirement to store their state (non-volatile memory or at least, long time retention without further energy feed at second frequency) plus circuits that turn off once the neuron ended their computation.
That way the energy requirements could being lowered by one or two orders of magnitude.
The key of the neuron model is the distributed memory close to the computer circuit, and we need that this neuron only uses energy when it’s active, or at least a minor fraction of energy between passive and active modes.
I have always believed a neuromorphic based system is the dark horse of AI development. It is still in its early developmental stages but has a definite edge in efficiency and adaptability.
So you are saying we have a new rival to Nvidia GPU’s…??
no it does rival Nvidia GPUs. It is a new niche chip.