Abstract: A scalar processor associated with a vector processor reduces the quantization error for blocked data with a relatively small register size by predicting adjustments for shared scalars used in runtime quantization. The scalar processor provides a recommended scale value to the vector processor for scaling a block of data from a wide data type format to a narrow data type format. The scalar processor and the vector processor share a register at which the scalar processor stores the recommended scale value and from which the vector processor accesses the recommended scale value. The vector processor performs an operation to quantize at least a portion of the block of data by applying a scale value that is based on the recommended scale value.

Abstract: Techniques are described for fine-tuning a neural network. A plurality of fine-tuning layers of a neural network are executed, each corresponding to a respective reference layer of a reference neural network. For each of the fine-tuning layers, a fine-tuning weight matrix is generated based on a reference weight matrix associated with the corresponding reference layer. One or more weights of the fine-tuning weight matrix are then iteratively adjusted based on a comparison of the output of the fine-tuning layer with the output of the corresponding reference layer.

Abstract: A device independent, frequency driven layout system and method for field programmable gate arrays ("FPGA") which allow for a circuit designer to specify the desired operating frequencies of clock signals in a given design to the automatic layout system to generate, if possible, a physical FPGA layout which will allow the targeted FPGA device to operate at the specified frequencies. Actual net, path and skew requirements are automatically generated and fed to the place and route tools. The system and method of the present invention evaluates the frequency constraints, determines what delay ranges are acceptable for each electrical connection and targets those ranges throughout the layout.

Abstract: A device independent, frequency driven layout system and method for field programmable gate arrays ("FPGA") which allow for a circuit designer to specify the desired operating frequencies of clock signals in a given design to the automatic layout system to generate, if possible, a physical FPGA layout which will allow the targeted FPGA device to operate at the specified frequencies. Actual net, path and skew requirements are automatically generated and fed to the place and route tools. The system and method of the present invention evaluates the frequency constraints, determines what delay ranges are acceptable for each electrical connection and targets those ranges throughout the layout.