Single-accuracy matrix multiplication optimization method based on loongson chip 3A

Abstract

The invention discloses a single-accuracy matrix multiplication optimization method based on a loongson chip 3A. The method is characterized by comprising the following steps of: dividing two single-accuracy source matrixes of the loongson chip 3A into two sub matrixes according to a principle that the two single-accuracy source matrixes are less than or equal to a half of a one-level cache and less than or equal to a half of a second-level cache; and pre-fetching data by using a 128-bit access instruction and a concurrent single-accuracy floating point instruction of the loongson chip 3A in a matrix multiplication core computation code of a 32-bit access instruction, a single-accuracy floating point multiplication-addition instruction and a pre-fetching instruction of the loongson chip 3A and using a pre-fetching address calculation mode of subtracting the size of an operation data CDS from the first address CACAS of an operation data set, so that a floating point operation part can basically operate at full load. By the method, the problem of invalid pre-fetching of address-non-aligned data is solved, and the executive efficiency of an address-non-aligned single-accuracy matrix multiplication is approximate to that of an address-aligned single-accuracy matrix multiplication. Compared with a basic linear algebra subprogram library (GotoBLAS) version 2-1.07, the single-accuracy matrix multiplication which is optimized by the method provided by the invention has the advantage that: an operation speed is averagely improved by above 90 percent.

Description

technical field [0001] The invention belongs to the technical field of electrical digital data processing, and in particular relates to an optimization method for single-precision matrix multiplication based on Loongson 3A. Background technique [0002] Loongson 3A is China's first quad-core central processing unit (CPU) with completely independent intellectual property rights. In the field of high-performance computing, Godson 3A needs the support of the basic linear algebra subroutine library. The better basic linear algebra subroutine library that can be used on Godson 3A is the basic linear algebra subroutine library (GotoBLAS) developed by the High Performance Computing Group of the Supercomputing Center of the University of Texas at Austin. The basic linear algebra subroutine library (GotoBLAS) developed by the High Performance Computing Group of the University of Texas at Austin Supercomputing Center achieves efficient single-precision matrix by using optimization te...

AI Technical Summary

Problems solved by technology

Loongson 3A has unique instructions such as 128-bit memory access and parallel single-precision floating point. However, the basic linear algebra subroutine library (GotoBLAS) developed by the High Performance Computing Group of the Supercompu