IMG Series4 is a range of multi-cores with a new architecture and advanced features that are ideal for Automotive needs for autonomous vehicles and ADAS.
It is designed to conform to ISO 26262 processes they enable the safe inference of neural networks without performance degradation. Featuring ultra-low latency, low bandwidth thanks to Imagination Tensor Tiling; and with sophisticated workload management, these designs meet the needs of R&D teams as well as SoC designers. The Series4 NNA range can be used for multiple use cases from embedded on-vehicle to cloud and hits the sweet spot for self-driving due to its energy-efficiency, low silicon area, and offline/online mature software tools.
For more information on IMG Series4 NNA, please visit our product page.
Speaker: Andrew Grant, Senior Director of AI, Imagination Technologies
Duration: 25 minutes
Available on Demand