Scalable automated driving technologies supplier AImotive and Nextchip, a dedicated automotive vision technology company, have announced that AImotive has successfully demonstrated automotive NN (neural network) vision applications executing at up to 98% efficiency on the aiWare3P NPU (Neural Network Processor Unit) used on Nextchip’s latest Apache5 IEP (Imaging Edge Processor).
Also featuring an advanced ISP supporting imaging sensors up to 5.7MP resolution, quad-core Arm A53 CPU, and small package size of 9 x 9mm, the Apache5 is designed for demanding automotive edge-vision applications to full AEC-Q100 Grade 2.
Thanks to rapid bring-up of all key functions on Apache5, complemented by aiWare Studio’s unique offline NN optimization tools, AImotive and Nextchip were able to demonstrate to customers the Apache5 IEP executing demanding automotive AI applications using the aiWare NPU within weeks of receiving first samples. This, the companies say, confirms that Apache5’s aiWare3P 1.6 TOPS NPU can deliver up to 98% sustained real-time efficiency for a wide range of NN workloads. Only minimal optimization effort was required, which was completed prior to receipt of the first devices.
“We are excited that thanks to the close collaboration between Nextchip and AImotive, we have been able to demonstrate Apache5 executing compelling automotive AI applications with exceptional efficiency within weeks of receiving first samples,” said Young Jun Yoo, CMO at Nextchip.
“With Apache5 we have demonstrated that we can deliver two to three times higher CNN performance for the same claimed TOPS of other NPUs,” added Márton Fehér, senior vice-president, hardware engineering, AImotive. “Furthermore, our aiWare Studio SDK enabled our aiDrive team to bring up multiple well-optimized NNs within days of receiving Apache5 silicon.”