- 10 Gigabit Ethernet MAC with IEEE 1588 PTP Support and AVB for Auto
- 10G PHY for PCIe 3.0 in TSMC (16nm) for Automotive
- 128-bit vector word length ARC VPX2 DSP IP
- 24 Ghz / 77 Ghz Automotive Radar Transceivers IP
- 256-bit vector word length, dual-core ARC VPX3 DSP IP with integrated hardware safety features for automotive
- 512-bit dual-core vector DSP IP
- More Products...
IP-SOC DAYS 2025 IP-SOC DAYS 2024 IP-SOC DAYS 2023 IP-SOC DAYS 2022 IP-SOC DAYS 2021 IP-SOC 2024 IP-SOC 2023 IP-SOC 2022 IP-SOC 2021
|
|||||||
![]() |
|

SDV Safety Calls for Partnerships, Open Source
- Automotive Industry Charts New Course with RISC-V
- Arteris Q1 2025 presentation highlights 28% revenue growth, strategic automotive wins
- Samsung's 12nm-class Automotive LPDDR5X: DRAM for safety-critical centralized automotive systems
- Xylon at ADAS&AVT Expo Europe 2025
- Cadence and AVCC to Advance Physical AI Innovations for Autonomous Vehicles
- NVIDIA Unveils NVLink Fusion for Industry to Build Semi-Custom AI Infrastructure With NVIDIA Partner Ecosystem (May. 20, 2025)
- sureCore extends its sureFIT design service to include custom memory solutions for AI applications (May. 20, 2025)
- Versatile Whitebox 1G Ethernet PHY IP Core with BroadR-Reach™ for Connected Automotive and Industrial Systems (May. 19, 2025)
- Codasip: Toward Custom, Safe, Secure RISC-V Compute Cores (May. 19, 2025)
- Semidynamics: From RISC-V with AI to AI with RISC-V (May. 19, 2025)
- See Latest News>>
Industry experts from Codasip, Elektrobit, TTTech Auto and the Eclipse Foundation discuss safety and security of self-driving software-defined vehicles as well as challenges that this concept represents for automakers.
www.eetimes.eu/, May. 30, 2023 –
As cars swap internal combustion engines for electric motors and become increasingly autonomous and connected, they are transforming from a collection of various electromechanical parts to highly integrated software-defined platforms that can add features and capabilities over time. At EE Times' Advanced Automotive Tech Forum 2023, industry experts from Codasip, Elektrobit, TTTech Auto and the Eclipse Foundation discussed safety and security of self-driving software-defined vehicles (SDVs) as well as challenges that this concept represents for automakers.
A strategic inflection point
The increasing number of electronically controlled components in modern vehicles need to work in concert with each other. Traditionally, those mechanical components were controlled by electronic control units (ECUs) operated by the on-board computer. But when a vehicle must perform hundreds of operations while considering data from dozens of sensors every second, it becomes inefficient to map all the ECUs and sensors together manually. Instead, it makes sense to logically disaggregate software layer from physical layer.
"[One Level 3 autonomous driving project that we have is running] about 400 different tasks, performing 100 applications, and then we have like 100 constraints; [for example,] if a pedestrian walks in front of your sensor set, then you need to react in a matter of milliseconds to engage on the actuation and braking side," said Stefan Poledna, CTO at TTTech Auto. "You need to map that onto the ECUs; we have about 50 CPU cores running there, we have four different hardware accelerators there, two TSN switches, 1,000 virtual links. Basically, you need to make this mapping from your logical software function, in terms of execution communication, to these hardware resources to meet all the constraints. As those applications get so complex, this goes beyond what you can do in a manual fashion. This is where we are linking up this logical software layer to the physical hardware."