"Running on around 20 watts, the human brain is able to process vast quantities of sensory information from our environment without interrupting consciousness. For decades, researchers have been trying to replicate these processes in silicon, in what is commonly referred to as neuromorphic computing. Sandia has been at the center of much of this research. The lab has deployed numerous neuromorphic systems from the likes of Intel, SpiNNaker, and IBM over the past several years."
"In a paper recently published in the journal Nature Machine Intelligence, the boffins at Sandia demonstrated a novel algorithm for efficiently running a class of problems called partial differential equations (PDEs) on neuromorphic computers, including Intel's Loihi 2 neurochips. PDEs are at the heart of some of the most complex scientific computing workloads today. They're used to model all manner of phenomena including electrostatic forces between molecules, the flow of water through a turbine, and the way radio frequencies propagate through buildings, the researchers explain."
Neuromorphic computing replicates brainlike processes in silicon and delivers high-efficiency, low-power computation similar to the human brain's ~20-watt operation. Multiple neuromorphic systems from Intel, SpiNNaker, and IBM have been deployed and used to test algorithms that run partial differential equations (PDEs) on neuromorphic chips including Intel's Loihi 2. PDEs underpin many complex scientific workloads such as molecular electrostatics, fluid flow through turbines, and radio-frequency propagation through buildings. Brain motor-control tasks demonstrate exascale-level computations performed cheaply, suggesting neuromorphic architectures can address both AI acceleration and large-scale numerical problems and may enable ultra-efficient supercomputers.
Read at Theregister
Unable to calculate read time
Collection
[
|
...
]