A compare unit includes an array including a plurality of buffer pairs to receive records on one level of a plurality of levels of a hierarchical structure. A comparator is coupled to the array, and the comparator includes one input to receive one beat of one record from one buffer of a selected buffer pair of the plurality of buffer pairs coupled to the comparator. The comparator further includes another input to receive another beat of another record from another buffer of the selected buffer pair, and logic coupled to the one input and the other input to compare the one beat and the other beat to obtain a winner beat of the compare.

An accelerator for bitonic sorting includes a plurality of compare-exchange circuits and a first-in, first-out (FIFO) buffer associated with each of the compare-exchange circuits. An output of each FIFO buffer is a FIFO value. The compare-exchange circuits are configured to, in a first mode, store a previous value from a previous compare-exchange circuit or a memory to its associated FIFO buffer and pass a FIFO value from its associated FIFO buffer to a subsequent compare-exchange circuit or the memory; in a second mode, compare the previous value to the FIFO value, store the greater value to its associated FIFO buffer, and pass the lesser value to the subsequent compare-exchange circuit or the memory; and in a third mode, compare the previous value to the FIFO value, store the lesser value to its associated FIFO buffer, and pass the greater value to the subsequent compare-exchange circuit or the memory.

A computational memory for a computer. The memory includes a memory bank having a selected-row buffer and being configured to store records up to a number, K. The memory also includes an accumulator connected to the memory bank, the accumulator configured to store up to K records. The memory also includes an arithmetic and logic unit (ALU) connected to the accumulator and to the selected row buffer of the memory bank, the ALU having an indirect network of 2K ports for reading and writing records in the memory bank and the accumulator, and the ALU further physically configured to operate as a sorting network. The memory also includes a controller connected to the memory bank, the ALU, and the accumulator, the controller being hardware configured to direct operation of the ALU.

A method for finding a best matching string among a set of strings for a reference string includes representing, for each of the set of strings paired with the reference string, a dynamic programming problem for calculating a final alignment score as a matrix of cells, and calculating a current optimal alignment boundary threshold. The method also includes executing, for each string of the set of strings, a calculation of a prospective final alignment score of a candidate alignment of the each of the set of strings and the reference string for each cell. Based on determining, that prospective final alignment score improves the current optimal alignment boundary threshold, the method includes calculating a final alignment score for the string of the set of strings associated with the cell. Otherwise, the method includes aborting the calculation of a candidate alignment covering the string associated with the cell.

A compare unit includes an array including a plurality of buffer pairs to receive records on one level of a plurality of levels of a hierarchical structure. A comparator is coupled to the array, and the comparator includes one input to receive one beat of one record from one buffer of a selected buffer pair of the plurality of buffer pairs coupled to the comparator. The comparator further includes another input to receive another beat of another record from another buffer of the selected buffer pair, and logic coupled to the one input and the other input to compare the one beat and the other beat to obtain a winner beat of the compare.

Disclosed is a calculation device. The present calculation device includes: a memory for storing a plurality of homomorphic ciphertexts for an approximate message including an error; and a processor for sorting the plurality of homomorphic ciphertexts by using a 5-way sorter which can sort five homomorphic ciphertexts in a single stage.

An accelerator for bitonic sorting includes a plurality of compare-exchange circuits and a first-in, first-out (FIFO) buffer associated with each of the compare-exchange circuits. An output of each FIFO buffer is a FIFO value. The compare-exchange circuits are configured to, in a first mode, store a previous value from a previous compare-exchange circuit or a memory to its associated FIFO buffer and pass a FIFO value from its associated FIFO buffer to a subsequent compare-exchange circuit or the memory; in a second mode, compare the previous value to the FIFO value, store the greater value to its associated FIFO buffer, and pass the lesser value to the subsequent compare-exchange circuit or the memory; and in a third mode, compare the previous value to the FIFO value, store the lesser value to its associated FIFO buffer, and pass the greater value to the subsequent compare-exchange circuit or the memory.

A method for finding a best matching string among a set of strings for a reference string includes representing, for each of the set of strings paired with the reference string, a dynamic programming problem for calculating a final alignment score as a matrix of cells, and calculating a current optimal alignment boundary threshold. The method also includes executing, for each string of the set of strings, a calculation of a prospective final alignment score of a candidate alignment of the each of the set of strings and the reference string for each cell. Based on determining, that prospective final alignment score improves the current optimal alignment boundary threshold, the method includes calculating a final alignment score for the string of the set of strings associated with the cell. Otherwise, the method includes aborting the calculation of a candidate alignment covering the string associated with the cell.

A method for finding a best matching string among a set of strings for a reference string includes representing, for each of the set of strings paired with the reference string, a dynamic programming problem for calculating a final alignment score as a matrix of cells, and calculating a current optimal alignment boundary threshold. The method also includes executing, for each string of the set of strings, a calculation of a prospective final alignment score of a candidate alignment of the each of the set of strings and the reference string for each cell. Based on determining, that prospective final alignment score improves the current optimal alignment boundary threshold, the method includes calculating a final alignment score for the string of the set of strings associated with the cell. Otherwise, the method includes aborting the calculation of a candidate alignment covering the string associated with the cell.

A shuffle exchange network includes a first circuit that includes a first stage having a first set of elements storing a first set of sequences of length N, and multiple exchange units each receiving input from a first pair of the elements. Each exchange unit selectively couples the first pair of elements in the first stage to a second pair of elements that is fed back to the first stage. The exchange units receive input from each pair of elements based on a perfect shuffle operation. A second circuit outputs to the first circuit and includes a second stage preceding the first stage. The second circuit operates based on an inverse perfect shuffle operation.