Neuromorphic computing: Energy footprint
Energy in use
The energy it uses or converts while it works, and how efficiently
- Consumption
- Electricity, in small amounts: IBM's million-neuron TrueNorth chip used 63 mW [4]
- Conversion
- Turns electrical energy into spiking computation; energy is used mainly when neurons fire
- Unit
- mW
- Note
- Intel says Loihi can be up to 10,000 times more efficient than CPUs for specialised applications [2]; this is a maker's claim for chosen tasks. The whole Hala Point system draws at most 2,600 W [9].
as of 2026-11-11
Energy links
The energy sources and technologies it uses, holds, converts, loses or gets back
Consumes- El Electricity Neuromorphic chips run on electricity but draw little when idle; TrueNorth used 63 mW [4].
as of 2026-11-11
Sources
- Intel's Pohoiki Beach, a 64-Chip Neuromorphic System, Delivers Breakthrough Results in Research Tests Edge AI and Vision Alliance (Intel announcement), 2019
- A Million Spiking-Neuron Integrated Circuit with a Scalable Communication Network and Interface Merolla et al., Science 345 (abstract at Yale University)
- Intel Builds World's Largest Neuromorphic System to Enable More Sustainable AI Intel (newsroom), 2024