Delivering 60 TOPS with low power consumption for deep learning processing and up to 96K DMIPS, the R-Car V3U from Renesas Electronics is a new open, scalable ASIL D System on Chip (SoC) built to meet performance, safety, and scalability (up and down) demands of ADAS and automated driving (AD) systems. This new device achieves ASIL D metrics for the majority of the SoC processing chain besides reducing design complexity, time to market, and system cost.
Based on the R-Car Gen 4 architecture, the R-Car V3U SoC integrates sophisticated safety mechanisms to provide high coverage with fast detection and response for random hardware faults. It delivers highly flexible DNN (Deep Neural Network) and AI machine learning functions, and its flexible architecture can handle any state-of-the-art neural networks providing up to 60 TOPS with low power consumption and an air cooling system.
Moreover, the new device from Renesas also offers a wide range of programmable engines, including DSP for radar processing, multi-threading computer vision engine for traditional computer vision algorithms, image signal processing to enhance image quality, and additional hardware accelerators for key algorithms such as dense optical flow, stereo disparity, and object classification.
The R-Car V3U comes with an open and integrated development environment that enables customers to take advantage of the R-Car platform’s built-in hardware benefits, as well as low power consumption and deterministic real-time software to enable fast time-to-market for computer vision and deep learning-based solutions.
Combining R-Car V3U with Renesas’ high-performance, low-power RH850 microcontroller, integrated power management ICs, and power transistor devices, the customers can access all the key components required for their ADAS and AD ECUs. By doing so, the customers can efficiently develop their systems and speed up the time to market.
Key Features of R-Car V3U ASIL D System on Chip
- 8 Arm Cortex-A76 for application programming, configurable in LockStep Mode.
- Dual Cortex-R52 LockStep cores to run AUTOSAR.
- Dedicated CNN IP delivering 60 TOPS, capable of handling any state-of-the-art neural networks for automated driving.
- High-speed processing of algorithms like optical flow, object detection, and classification.
- Dual DSP for Radar processing.
- Integrated ISP enables a high level of integration for a reduced cost.
- Multiple communication interface such as Ethernet AVB, CAN, and FlexRay for in-vehicle communication.
- Multiple PCIe enabling easy scaling of V3U to increase overall system performance.
- Integrates multiple safety mechanisms that provide high coverage with fast detection and response for random hardware faults, achieving ASIL D metrics for the majority of the SoC processing chain.
- The open solution is supported by Renesas and R-Car Consortium partners.
The samples of the R-Car V3U SoC are available now and the mass production is scheduled for the second quarter of 2023.