Abstract: A system and method for accelerating multiply-accumulate (MAC) floating-point units during training of deep learning networks. The method including: receiving a first input data stream A and a second input data stream B; adding exponents of the first data stream A and the second data stream B in pairs to produce product exponents; determining a maximum exponent using a comparator; determining a number of bits by which each significand in the second data stream has to be shifted prior to accumulation by adding product exponent deltas to the corresponding term in the first data stream and using an adder tree to reduce the operands in the second data stream into a single partial sum; adding the partial sum to a corresponding aligned value using the maximum exponent to determine accumulated values; and outputting the accumulated values.

Abstract: A reference measurement system includes a rail vehicle configured to move along rails of a track. An imaging system is disposed on the rail vehicle and is configured to capture one or more images of a reference point. The system further includes a processor, which is configured to calculate a relative position between the rails and the reference point based on the image. Related methods for making reference measurements are described.