An implementation method of heterogeneous many-core based on sparse matrix-vector multiplication based on Shenwei 26010 processor

Abstract

The invention discloses a method for realizing heterogeneous many-core of sparse matrix-vector multiplication based on domestic SW26010 processors. As the non-zero elements of a sparse matrix are distributed very irregularly, two different static and dynamic task partitioning methods are designed in the method, so as to adapt to different sparse matrices; a set of dynamic and static cache mechanism is provided, so as to promote the memory access hit rate of a vector x; a set of self-adapting optimization method is provided, specific to the sparse matrix, the optimal execution parameters can be dynamically selected, so as to promote the running performance. According to the method disclosed by the invention, 16 sparse matrices in a Matrix Market matrix set are adopted to conduct test, the running edition SpMV has about 10 times of acceleration to the utmost extent compared with the single main core of a domestic SW processor, and the average speed-up ratio is 6.51.

Description

technical field [0001] The invention relates to a method for realizing sparse matrix-vector multiplication SpMV (Sparse Matrix-Vector Multiplication), which is the core calculation of a sparse matrix, on a Shenwei many-core processor. In scientific computing and practical applications such as astrophysics and reservoir simulation. Background technique [0002] Sparse matrix-vector multiplication (SpMV) y=A*x is a very important computing kernel in scientific and engineering computing, and its performance often has a great impact on the overall performance of the application. SpMV is memory-intensive, the ratio of floating-point calculations to storage access in the algorithm is very low, and the distribution of non-zero elements in the sparse matrix is ​​very irregular. In the traditional SpMV implementation of CSR (Compressed Sparse Row) format, the vector x is accessed indirectly and irregularly, and the reusability is poor, which brings great challenges to the efficient ...

AI Technical Summary

Problems solved by technology

[0013] The technical problem solved by the present invention is: for the brand-new Shenwei processor with independent intellectual property rights, a kind of sparse matrix vector multiplication (SpMV) heterogeneous many-core implementation method based on Shenwei 26010 processor is proposed, which solves the problem of CSR format SpMV During calculation, problems such as load imbalance between tasks between cores, memory access bandwidth utilization, and adaptive performance optimization of different types of sparse matrices have been solved, thereby improving the performance of sparse matrix-vector multiplication as a whole.

Images