Abstract: A system and method of performing sparse accumulation in column-wise sparse general matrix-matrix multiplication (SpGEMM) algorithms. The method includes receiving a request to perform SpGEMM based on a first matrix and a second matrix. The method includes accumulating, in a hardware buffer, a hash key and an intermediate multiplication result of the first matrix and the second matrix. The method includes performing a probe search of a hardware cache to identify a match between the hash key and a partial sum associated with the first matrix and the second matrix. The method includes generating, by a hardware adder, a multiplication result based on the partial sum and the intermediate multiplication result from the accumulation waiting buffer.

Abstract: A nonlinear equalizer for treating the nonlinear component of a distorted digital signal includes a first processing unit adapted to receive the distorted digital signal and yield an appropriate output signal in response thereto, a second processing unit adapted to receive the distorted digital signal and yield an appropriate output signal in response thereto, and a summation module for summing together the output signals from the first and second processing units so as to yield an equalized digital signal. In one embodiment, each of the first and second processing units comprises a linear filter, a partitioning filterbank for partitioning the distorted digital signal, and a multiplier for multiplying together the output of said linear filter with the output of said partitioning filterbank. In use, the nonlinear equalizer can be used to adaptively partition the distorted digital signal so as to allow for nonlinear equalization in a highly efficient manner.