AImotive, a leading supplier of scalable automated driving technologies, and Nextchip Co., Ltd., 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 latest Apache5 IEP (Imaging Edge Processor) from Nextchip. Also featuring an advanced ISP supporting imaging sensors up to 5.7 Mpixel resolution, quad-core Arm A53 CPU and small package size of only 9- by 9-mm, 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 lead customers the Apache5 IEP executing demanding automotive AI applications using the aiWare NPU within weeks of receiving first samples. These confirm 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.
"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 2x to 3x higher CNN performance for the same claimed TOPS of other NPUs," said Márton Fehér, senior vice-president hardware engineering for AImotive. "Furthermore, our aiWare Studio SDK enabled our aiDrive team to bring up multiple well-optimized NNs within days of receiving Apache5 silicon."
Nextchip has commenced shipping samples of Apache5 to lead customers, and is now accepting production enquiries.
AEC Q100 qualified magnetic encoder ICs
Battery technology using silicon nanofibers validated
New type of battery charges ten times faster than lithium-ion
Embedded vision optimized FPGA targets vehicle applications