The invention discloses a
hardware acceleration implementation
system and a method for an RNN
forward propagation model based on a transverse pulsation array. The method comprises the steps of firstly, configuring network parameters, initializing data, lateral
systolic array, wherein a blocking design is adopted in the weight in calculation; partitioning a weight matrix calculated by the
hidden layer according to rows; carrying out
matrix multiplication vector and vector summation operation and
activation function operation; calculating
hidden layer neurons, obtaining
hidden layer neurons according to the obtained hidden layer neurons; performing
matrix multiplication vector, vector summation operation and
activation function operation; generating an RNN output layer result; finally, generating an output result required by the RNN network according to
time sequence length configuration information; according to the method, a hidden layer and an output layer are parallel in a multi-dimensional mode, the pipelining performance of calculation is improved, meanwhile, the characteristic of weight matrix parameter sharing in the RNN is achieved, the partitioning design is adopted, the parallelism degree of calculation is further improved, the flexibility, expandability, the storage
resource utilization rate and the acceleration ratio are high, and calculation is greatly reduced.