Convolutional neural network hardware computing device and method

The invention relates to a convolutional neural network hardware computing device and a convolutional neural network hardware computing method, which are used for realizing efficient convolutional computing. The device comprises a convolution window extraction circuit used for loading input feature map data and extracting a convolution window; and the processing element array is used for performing multiply-accumulate operation on the convolution window received from the convolution window extraction circuit and the corresponding weight kernel. The convolution window extraction circuit comprises C extraction units and is used for loading and extracting C input channels in parallel. The processing element array has M rows * N columns of processing elements. Each column of the processing element array processes one output channel. M processing elements in the same column of the processing element array process M C-channel K * K convolution windows in parallel. 本发明涉及一种卷积神经网络硬件计算装置及方法，用于实现高效的卷积计算。所述装置包括：卷积窗提取电路，用