Method and apparatus for neural network optimized matrix-matrix multiplication (nnmm)
AssigneeTencent America LLC
InventorsWei WANG, Wei JIANG, Shan LIU
Life of this patent
Estimating the term…
Abstract
According to embodiments, a method of neural network optimized matrix-matrix multiplication (NNMM) is performed by at least one processor and includes determining a first matrix of input coefficients, and determining a second matrix of weight coefficients of a neural network that is trained so that the second matrix has a predetermined uniform pattern, the predetermined uniform pattern having at least two of the weight coefficients that have a same value. The method further includes performing multiplication of the determined first matrix and the determined second matrix to determine output coefficients.
Claims20
A method of neural network optimized matrix-matrix multiplication (NNMM), the method being performed by at least one processor, and the method comprising:
- determining a first matrix of input coefficients;
- determining a second matrix of weight coefficients of a neural network that is trained so that the second matrix has a predetermined uniform pattern, the predetermined uniform pattern having at least two of the weight coefficients that have a same value;
- and
- performing multiplication of the determined first matrix and the determined second matrix to determine output coefficients.
An apparatus for neural network optimized matrix-matrix multiplication (NNMM), the apparatus comprising:
- at least one memory configured to store program code;
- and
- at least one processor configured to read the program code and operate as instructed by the program code, the program code comprising:
- first determining code configured to cause the at least one processor to determine a first matrix of input coefficients;
- second determining code configured to cause the at least one processor to determine a second matrix of weight coefficients of a neural network that is trained so that the second matrix has a predetermined uniform pattern, the predetermined uniform pattern having at least two of the weight coefficients that have a same value;
- and
- performing code configured to cause the at least one processor to perform multiplication of the determined first matrix and the determined second matrix to determine output coefficients.
A non-transitory computer-readable medium storing instructions that, when executed by at least one processor for neural network optimized matrix-matrix multiplication (NNMM), cause the at least one processor to:
- determine a first matrix of input coefficients;
- determine a second matrix of weight coefficients of a neural network that is trained so that the second matrix has a predetermined uniform pattern, the predetermined uniform pattern having at least two of the weight coefficients that have a same value;
- and
- perform multiplication of the determined first matrix and the determined second matrix to determine output coefficients.
Dependencies are inferred from the claim text.