Today's sophisticated digital designs are rapidly evolving. Software-only simulation of such designs takes weeks or even months. Therefore a new generation of chip design requires a hardware-assisted solution. Hardware acceleration delivers a 10-1000 times performance boost. In the paper technologies of hardware simulation on selected examples are described.
Typically, hardware implemented neural networks are trained before implementation. Extreme learning machine (ELM) is a noniterative training method for single-layer feed-forward (SLFF) neural networks well suited for hardware implementation. It provides fixed-time learning and simplifies retraining of a neural network once implemented, which is very… (More)
Extreme Learning Machine (ELM) is a noniterative training method suited for Single Layer Feed Forward Neural Networks (SLFF-NN). Typically, a hardware neural network is trained before implementation in order to avoid additional on-chip occupation, delay and performance degradation. However, ELM provides fixed-time learning capability and simplifies the… (More)