Technology company Intel has introduced its first discrete graphics processing unit (dGPU), tailored specifically for the automotive industry. The Intel Arc Graphics for Automotive, revealed at Intel’s AI Cockpit Innovation Experience event, will be deployed in vehicles by 2025 and will “elevate in-vehicle AI capabilities”, the company says.
The new dGPU is designed to address the increasing need for advanced computing power in modern vehicle cockpits. By integrating Intel Arc graphics into its existing portfolio of AI-enhanced, software-defined vehicle (SDV) system-on-chips (SoCs), Intel is providing auto makers with a scalable platform.
The platform is designed for a unified development process, enabling a single vehicle platform to be designed across various trim levels. Auto makers can start with the Intel SDV SoC and later integrate the discrete GPU to handle more complex computing tasks and expand AI capabilities.
Intel says its technologies enable advanced voice, camera and gesture recognition, with support for high-definition screens, 3D graphics, and multiple in-vehicle cameras.
AI algorithms that learn driver preferences aim to provide a highly personalized in-car experience, adjusting settings without the need for voice commands. Demonstrations at the event showcased the capabilities of local large language models (LLMs) for vehicle control and interaction.
The dGPU can also support immersive 4K displays, multiscreen setups and advanced interfaces.
“Intel’s strategy is to bring the power of AI into devices of every size and shape, and we’re thrilled to bring that expertise and our vast open AI ecosystem to the automotive industry,” said Jack Weast, vice president and general manager of Intel Automotive.
“China’s rapid electric vehicle development cycles and advanced technological adoption make it an ideal testing ground for our next-generation technologies.”
