Morpho, Inc. has provided deep learning inference engine SoftNeuro to a project promoted by the University of Tokyo, Tohoku University, and Kobe University to accelerate high-resolution galaxy formation simulations using deep learning on the supercomputer Fugaku. The result is approx. 19.2 times faster inference time and approx.

93% reduction in power consumption. About Conditions and Measured Values: SoftNeuro is used for 3D-Unet inference on Fugaku. Comparison of inference speed using TensorFlow (available as standard on Fugaku) and using SoftNeuro optimized for Fugaku.

Each Fugaku uses 1 node (48 cores). Morpho will support further acceleration of 3D simulations (galaxy formation simulations) using deep learning on Fugaku through the project and collaboration. In addition, Morpho will continue to further improve the convenience and technical capabilities of “SoftNeuro” and develop technology on a global level to realize a fruitful culture through the provision of various services and solutions.