How to achieve higher automotive MCU performance through interface IP

Artificial intelligence is making waves in many industries, and automotive is no exception. Today’s cars are smarter and more connected than ever before, and AI is at the heart of it all. Many new advanced driver assistance systems (ADAS) applications, such as automatic emergency braking, adaptive cruise control, and lane keeping assist, are built using the latest AI algorithms. In addition to ADAS, AI is increasingly being used in other applications such as battery management, domain/region control, and electric vehicle (EV) motor control.

Central to bringing AI to vehicle subsystems is a microcontroller with parallel processing capabilities to support AI workloads. This is where companies like Infineon come into play. The Infineon AURIX TC4x family of microcontrollers (MCUs) is Infineon's latest automotive MCU for next-generation electric vehicles, ADAS, automotive electrical/electronic (E/E) architectures, and affordable AI applications. To achieve the connectivity required to move data between on-board sensors and the automotive MCU for processing by AI algorithms, Infineon uses Synopsys interface IP. The two companies have a long history of collaboration in supporting high-performance automotive applications.

"Our increasingly AI-driven automotive landscape will help reduce system complexity, minimize potential points of failure, cut emissions through increased efficiency, and improve reliability while reducing costs," said Dr. Jörg Schepers, vice president of Automotive Microcontrollers at Infineon Technologies. "Through our long-standing collaboration with Synopsys and the integration of Synopsys controller and PHY IP, including PCIe, MIPI, and Ethernet, into our automotive SoCs, we are delivering the intelligence and connectivity that is defining the automotive world."

The impact of vehicle electrification and autonomous driving features

The automotive sector is constantly evolving, with vehicle electrification, autonomous driving capabilities, and changing automotive E/E architectures significantly shaping its future. The performance of applications such as object detection and autonomous steering depends on the ability of AI algorithms to provide real-time insights based on the vast amounts of data collected by onboard sensors. None of this is possible without high-speed, low-latency connectivity.

These capabilities bring to life a variety of AI-driven automotive applications, including:

Motor control: Instead of relying on expensive hardware sensors to monitor and control a vehicle’s electric motor, AI can use predictive analytics to control the rotation of the rotor inside the motor.

ADAS: AI algorithms can help identify what the radar or LiDAR in ADAS sees at the car’s approach and distance, enabling more accurate performance of systems such as autonomous driving, lane keeping, object detection, and automatic braking.

Battery management: Machine learning algorithms can help monitor battery health. And, based on this insight, along with driving profiles, AI can help accurately predict the remaining life of the battery. For fast charging, AI can control the state of charge of each individual battery and, combined with low-latency clustering, achieve optimized cell balancing of the entire battery pack in real time.

Navigation: AI can help guide drivers to the quickest or most efficient route to their destination, saving time as well as fuel/electricity.

Partnering for quality, reliability and safety

Infineon Technologies and Synopsys have joined forces to lay the technological foundation for today's and tomorrow's cars. The scalable, ASIL-D-compliant Infineon AURIX TC4x MCUs feature the company's triple-core 1.8 architecture and the AURIX Accelerator Suite, including a new parallel processing unit (PPU) and multiple intelligent accelerators.

To support 5Gbps Ethernet, 10BASE T1S Ethernet, PCI Express and MIPI D-PHY interfaces in its MCU families, Infineon relies on Synopsys interface IP to provide leading power, performance, area (PPA) and security for the most widely used protocols. The automotive-grade IP is designed and tested according to the AEC-Q100 quality standard to ensure additional reliability and complies with the ISO 26262 functional safety standard, which helps SoC-level evaluation and certification for the target ASIL. In addition, the PPU of its AURIX TC4x family is supported by Synopsys ARC EV processor IP to accelerate AI algorithms such as recurrent neural networks (RNN), radial basis function neural networks (RBF), convolutional neural networks (CNN) and multilayer perceptrons. Mutual customers can get a head start in software development by using the Synopsys ARC MetaWare Toolkit for AURIX TC4x, for virtually testing and evaluating automotive systems, and the Synopsys Virtualizer Development Kit, which provides a complete set of tools, runtime software and libraries for programming the PPU.

Synopsys and Infineon Technologies are both committed to enabling high-performance automotive systems. For Infineon, it is important to work with suppliers who can support its current and future automotive IP requirements, providing reliability, quality, and safety. In turn, Synopsys keeps pace with the evolution of automotive standards to ensure that our broad range of IP meets the latest requirements.

As AI algorithms become more sophisticated, automotive OEMs, Tier 1 suppliers, and semiconductor suppliers will need more processing power and ultra-fast connectivity to infuse greater intelligence into their vehicles. Fortunately, companies like Synopsys and Infineon are continuing to collaborate to define what’s possible for the next generation of automotive designs.