52results about "Systolic arrays" patented technology

A data stream processing unit (DPU) and method for use are provided. A DPU includes a number of processing elements arranged in a sequence, and each datum in the data stream visits each processing element in sequence. Each processing element has a memory circuit, data and metadata input and output channels, and a computing circuit. The metadata input represents a partial computational state that is associated with each datum as it passes through the DPU. The computing circuit for each processing element operates on the data and metadata inputs as a function of its position in the sequence, producing an altered partial computational state that accompanies the datum. Each computing circuit may be modeled, for example, as a finite state machine, and the collection of processing elements cooperate to perform the computation. The computing circuits may be collectively programmed to perform any desired computation.

A general matrix-matrix multiplication (GEMM) dataflow accelerator circuit is disclosed that includes a smart 3D stacking DRAM architecture. The accelerator circuit includes a memory bank, a peripheral lookup table stored in the memory bank, and a first vector buffer to store a first vector that is used as a row address into the lookup table. The circuit includes a second vector buffer to store a second vector that is used as a column address into the lookup table, and lookup table buffers to receive and store lookup table entries from the lookup table. The circuit further includes adders to sum the first product and a second product, and an output buffer to store the sum. The lookup table buffers determine a product of the first vector and the second vector without performing a multiply operation. The embodiments include a hierarchical lookup architecture to reduce latency. Accumulation results are propagated in a systolic manner.

Systems and methods of propagating data within an integrated circuit includes: identifying a coarse data propagation path for distinct subsets of data of an input dataset that includes: setting inter-core data movements for the distinct subsets of data, the inter-core data movements defining a predetermined propagation of a given subset of data between two or more of a plurality of cores of an integrated circuit array of the integrated circuit; identifying a granular data propagation path for each distinct subset of data that includes: setting intra-core data movements for each distinct subset of data, the intra-core data movements defining a predetermined propagation of the given subset of data within one or more of the plurality of cores of the integrated circuit array of the integrated circuit; enabling a flow of the input dataset within the integrated circuit based on the coarse data propagation path and the granular propagation path.

A data stream processing unit (DPU) and methods for its use and programming are disclosed. A DPU includes a number of processing elements (PEs) arranged in a physical sequence. Each datum in the data stream visits each PE in sequence. Each PE has a memory circuit, data and metadata input and output channels, and a computing circuit. The metadata input represents a partial computational state that is associated with each datum as it passes through the DPU. Each computing circuit implements a finite state machine that operates on the data and metadata inputs as a function of its position in the sequence and a data context, producing an altered partial computational state that accompanies the datum. When the data context changes, the current state of the finite state machine is stored, and a new state is loaded. The processing elements may be collectively programmed to perform any desired computation.

A linear systolic array is added to the lower side of a trapezoid systolic array created by combining a triangular systolic array and a square systolic array. In order to make the connection among the cells fixed, the intermediate result output from each row of the trapezoid systolic array to a lower row is shifted in phase with respect to the intermediate result of the complex MFA algorithm, the phase shift is absorbed by the next row, and the phase shift in the intermediate result output from the last row of the trapezoid systolic array is corrected by the linear systolic array. Each cell is implemented by a CORDIC circuit that processes vector angle computation, vector rotation, division, and multiply-and-accumulate with a constant delay.

When a plurality of reference signal series are handled with the same input signal series during processing of an RLS algorithm based on QR decomposition, an object is to handle the plurality of reference signal series simultaneously. When performing processing of a sequential least-squares algorithm based on QR decomposition, to a configuration comprising a plurality of boundary cells (empty circles) which calculate appropriate rotation parameters for transformations based on Givens rotation, a plurality of internal cells (squares) which cause rotation of elements of a received data vector using the calculated values of the boundary cells (empty circles), and a final cell (double circles) which derives the a posteriori estimated error from the calculated values of the boundary cells (empty circles) and internal cells (squares), additional internal cells (squares) within 21 are connected so as to receive signals output from each of the internal cells (squares) arranged in the end cell column to which the signal series is input, and to the final cell (double circles) is connected an additional final cell (double circles) within 21, so as to receive the calculated values from the boundary cells (empty circles) and the calculated values from the additional internal cells (square) input to the additional final cell (double circles).