Data processing method, apparatus and system

By optimizing the shape and computation process of sparse matrix blocks, the problems of slow computation speed and resource waste in large-scale matrix multiplication are solved, and more efficient matrix multiplication is achieved.

WO2026114175A1 Publication Date: 2026-06-04HUAWEI TECH CO LTD
4 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2025/137177
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2024-11-27
Filing Date
2025-11-24
Publication Date
2026-06-04

AI Technical Summary

Technical Problem

Existing technologies are unable to effectively accelerate the matrix multiplication process performed by processing devices and reduce computational resource consumption, especially when processing large-scale sparse matrix data, where the calculation speed is slow and resources are wasted.

Method used

By reading non-zero vectors and the target vector from the sparse matrix to form multiple matrix blocks, performing matrix multiplication and transposing and merging, the shape of the matrix blocks is optimized to adapt to processor capabilities and reduce computational redundancy.

Benefits of technology

It enables a more flexible computation process in sparse matrix computation, reduces the number of computations and data loading, improves processor speed, and reduces memory access costs.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present application relates to the technical field of computers, and provides a data processing method, an apparatus and a system. The method comprises: reading non-zero vectors in a first matrix to obtain a plurality of first matrix blocks, and reading target vectors in a second matrix to obtain a plurality of second matrix blocks, the vector positions of the target vectors being associated with the vector positions of the non-zero vectors. Then, the method further comprises: performing matrix multiplication computation on a plurality of transposed first matrix blocks and a plurality of transposed second matrix blocks, so as to obtain a plurality of result matrix blocks; and further obtaining a target matrix on the basis of a plurality of transposed result matrix blocks. Thus, sparse computation of matrix multiplication can be successfully implemented. In addition, sparse computation of matrix multiplication can be implemented more flexibly, so as to better satisfy requirements of different services, thus accelerating the computation process during which processing devices execute matrix multiplication computation, and reducing computing resources consumed by processing devices in executing matrix multiplication computation.
Need to check novelty before this filing date? Find Prior Art