Abstract: A 3D device includes a first semiconductor chip and a second semiconductor chip stacked vertically. The first semiconductor chip includes a first plurality of tiles. The second semiconductor chip includes a second plurality of tiles. A bus electrically couples each of the first plurality of tiles to a corresponding one of the second plurality of tiles based on assignments of the first plurality of tiles and the second plurality of tiles to tile-to-tile pairs that define a minimized sum of bus delays among each possible tile-to-tile pairs. In each tile-to-tile pair, a net electrically couples each of a first plurality of pins to a corresponding one of a second plurality of pins based on assignments of the first plurality of pins to the second plurality of pins that define a minimized sum of net delays among each possible pin-to-pin pairs.

Abstract: A method includes receiving a value and an identifier from a first memory and hashing the identifier to produce a memory block identifier. The method also includes routing, based on the memory block identifier, a read request to a memory block of a plurality of memory blocks and updating the value received from the first memory based on a property received from the memory block in response to the read request. The memory further includes storing the updated value in the first memory.

Abstract: Partition-level compression of an m×n sparse matrix includes determining in each partition, row and column indices of elements having non-zero values. Each partition has s rows and t columns and s<m and t<n. A group of ordered sets of tuples is generated from the elements and row and column indices in each partition that has at least one non-zero element. Each ordered set includes s tuples, and positions of the s tuples in the ordered set correspond to the s rows of the partition, each tuple includes a value of an element of the partition and an associated column index, and the associated column index indicates, for an element of the partition having a non-zero value, a column index in the partition. A compression processor indicates for each group, a count of the one or more ordered sets, a partition row number, and a partition column number.

Abstract: A method includes receiving a value and an identifier from a first memory and hashing the identifier to produce a memory block identifier. The method also includes routing, based on the memory block identifier, a read request to a memory block of a plurality of memory blocks and updating the value received from the first memory based on a property received from the memory block in response to the read request. The memory further includes storing the updated value in the first memory.

Abstract: Circuitry for multiplying a sparse matrix by a dense vector includes a first switching circuit (302) for routing input triplets from N input ports to N output ports based on column indices of the triplets. Each triplet includes a non-zero value, a row index, and a column index. N first memory banks (303) store subsets of vector elements and are addressed by the column indices of the triplets. N multipliers (305) multiply the non-zero values of the triplets by the vector element read from the respective memory bank. A second switching circuit (304) routes tuples based on row indices of the tuples. Each tuple includes a product output by the one of the N multipliers and a row index output by an output port of the first switching circuit. N accumulator circuits (307) sum products of tuples having equal row indices.

Abstract: A method includes receiving a value and an identifier from a first memory and hashing the identifier to produce a memory block identifier. The method also includes routing, based on the memory block identifier, a read request to a memory block of a plurality of memory blocks and updating the value received from the first memory based on a property received from the memory block in response to the read request. The memory further includes storing the updated value in the first memory.