FlexLogix introduces inference engine

FlexLogix has announced inference-optimized nnMAX clusters to develop the InferX X1 edge inference co-processor for incorporation in SoCs as IP, and in chip form, in Q3. Its performance advantage is claimed to be strong at low batch sizes which are required in edge applications where there is typically only one camera/sensor. InferX X1's performance at small batch sizes is close to data center inference boards and is optimized for large models which need 100s of billions of operations per image. For example, for YOLOv3 real time object recognition, InferX X1 processes 12.7 frames/second of 2 megapixel images at batch size 1. Performance is roughly linear with image size: so frame rate approximately doubles for a 1 megapixel image.