A method of performing matrix computations includes receiving a compression-encoded matrix including a plurality of rows. Each row of the compression-encoded matrix has a plurality of defined element values and, for each such defined element value, a schedule tag indicating a schedule for using the defined element value in a scheduled matrix computation. The method further includes loading the plurality of rows of the compression-encoded matrix into a corresponding plurality of work memory banks, and providing decoded input data to a matrix computation module configured for performing the scheduled matrix computation. For each work memory bank, a next defined element value and a corresponding schedule tag are read. If the schedule tag meets a scheduling condition, the next defined element value is provided to the matrix computation module. Otherwise, a default element value is provided to the matrix computation module.

An embodiment of an apparatus comprises one or more fractional width fused multiply-accumulate (FMA) circuits configured as a shared Wallace tree, and circuitry coupled to the one or more fractional width FMA circuits to provide one or more fractional width FMA operations through the one or more fractional width FMA circuits. Other embodiments are disclosed and claimed.

Matrix multiplication systolic array feed methods and related processing element (PE) microarchitectures for efficiently implementing systolic array generic matrix multiplier (SGEMM) in integrated circuits is provided. A systolic array architecture may include a processing element array, a column feeder array, and a row feeder array. A bandwidth of external memory may be reduced by a factor of reduction based on interleaving of the matrix data via a feeding pattern of the column feeder array and the row feeder array.

Systems and methods are provided to perform multiply-accumulate operations of normalized numbers in a systolic array to enable greater computational density, reduce the size of systolic arrays required to perform multiply-accumulate operations of normalized numbers, and/or enable higher throughput operation. The systolic array can be provided normalized numbers by a column of normalizers and can lack support for denormal numbers. Each normalizer can normalize the inputs to each processing element in the systolic array. The systolic array can include a multiplier and an adder. The multiplier can have multiple data paths that correspond to the data type of the input. The multiplier and adder can employ expanded exponent range to operate on normalized floating-point numbers and can lack support for denormal numbers.

Circuitry operating under a floating-point mode or a fixed-point mode includes a first circuit accepting a first data input and generating a first data output. The first circuit includes a first arithmetic element accepting the first data input, a plurality of pipeline registers disposed in connection with the first arithmetic element, and a cascade register that outputs the first data output. The circuitry further includes a second circuit accepting a second data input and generating a second data output. The second circuit is cascaded to the first circuit such that the first data output is connected to the second data input via the cascade register. The cascade register is selectively bypassed when the first circuit is operated under the fixed-point mode.

An apparatus to facilitate acceleration of matrix multiplication operations. The apparatus comprises a systolic array including matrix multiplication hardware to perform multiply-add operations on received matrix data comprising data from a plurality of input matrices and sparse matrix acceleration hardware to detect zero values in the matrix data and perform one or more optimizations on the matrix data to reduce multiply-add operations to be performed by the matrix multiplication hardware.

This specification describes systolic arrays of hardware processing units. In one aspect, a matrix computation unit includes multiple cells arranged in a systolic array. Each cell includes multiplication circuitry configured to determine a product of elements or submatrices of input matrices, summation circuitry configured to determine a sum of an input accumulated value and the product output by the multiplication circuitry, multiple accumulators connected to an output of the summation circuitry, and a controller circuit configured to select, from the accumulators, a given accumulator to receive the sum output by the summation circuitry.

Matrix multiplication systolic array feed methods and related processing element (PE) microarchitectures for efficiently implementing systolic array generic matrix multiplier (SGEMM) in integrated circuits is provided. A systolic array architecture may include a processing element array, a column feeder array, and a row feeder array. A bandwidth of external memory may be reduced by a factor of reduction based on interleaving of the matrix data via a feeding pattern of the column feeder array and the row feeder array.

An apparatus to facilitate acceleration of matrix multiplication operations. The apparatus comprises a systolic array including matrix multiplication hardware to perform multiply-add operations on received matrix data comprising data from a plurality of input matrices and sparse matrix acceleration hardware to detect zero values in the matrix data and perform one or more optimizations on the matrix data to reduce multiply-add operations to be performed by the matrix multiplication hardware.

Systems and methods are provided to perform multiply-accumulate operations of at least one normalized number in a systolic array. The systolic array can obtain a first input and detect that the first input is denormal. Based on determining the first input is denormal, the systolic array can generate a first normalized number by normalizing the first input. Processing elements of the systolic array can include a multiplier and an adder. The multiplier can multiply the first normalized number by a second normal or normalized number to generate a multiplier product and the adder can add an input partial sum to the multiplier product to generate an addition result.