Software-defined vehicles and in-vehicle AI are reshaping automotive compute from dozens of distributed ECUs to centralized and zonal architectures—fundamentally changing how data movement, power delivery, safety and cost are engineered. This talk compares decentralized, centralized and zonal compute approaches and maps each to vehicle designs, highlighting what’s changing fastest in autonomous driving (sensor fusion, perception, planning) and infotainment (graphics, multimodal UX, connectivity). We’ll discuss how to future-proof compute decisions considering performance alongside bandwidth, latency and thermal constraints, and take a brief look at geopolitical factors affecting supply chains and platform choices. Attendees will leave with a practical understanding of architecture framework and implementation options, including chiplet-based designs and scalable core strategies.