Unleash AI Performance

Origin Evolution™ is a radical advancement in neural engine IP for AI inference that delivers optimal performance in applications as varied as smartphones, automobiles, and data centers. With built-in support for popular LLM and CNN networks, it builds on the success of Origin NPU IP using Expedera's unique packet-based architecture, which reduces memory requirements to the bare minimum and dramatically slashes processing overhead. The architecture is far more efficient than the common layer-based architectures underlying other NPU implementations. By subdividing each layer into self-contained fragments that are independently executable, it enables parallel execution across multiple layers, better resource utilization, and deterministic performance. It also eliminates the need for hardware-specific optimizations, allowing customers to run their trained neural networks unchanged without reducing model accuracy.