You are here:

AI processor (NPU) IP

・High-Performance:
Featuring a scalable architecture with over 40 TOPS computing power,
capable of handling a wide range of inference tasks.
・Multicore Parallel Processing:
A multicore design that can concurrently process multiple diverse models.
・Mixed Precision Computation:
Adopts a mixed precision computation approach to balance inference
performance and accuracy.
・Extensive Data Format Support:
Supports a broad range of data formats including INT4/8, FP4/FP8/FP16.
・Comprehensive Model Support:
ONNX support, enabling a diverse set of AI models.
・Edge Computing Optimization:
Optimized for edge computing with high PPA efficiency.