The NPU operates at clock rates of up to 900 MHz, delivering computing performance of up to 4.5 TOPS (Trillion Operations Per Second). Optimized for AI models based on convolutional neural networks, it includes a Parallel Processing Unit (PPU) with 32-bit floating-point pipelining and threading.
Here are 30 typical models based on NPU on C3V platform, and some basic performance data have been run for your reference.