Computing the Sparse Matrix Vector Product using Block-Based Kernels Without Zero Padding on Processors with AVX-512 Instructions

The sparse matrix-vector product (SpMV) is a fundamental operation in many scientific applications from various fields. The High Performance Computing (HPC) community has therefore continuously invested a lot of effort to provide an efficient SpMV kernel on modern CPU architectures. It has been shown that block-based kernels are helpful to achieve high performance, but also that they are difficult to use in practice because of the important zero padding they imply. In the current paper, we propose new kernels using the AVX-512 instruction set, which makes it possible to use a blocking scheme without any zero padding in the matrix memory storage. We describe mask-based sparse matrix formats and their corresponding SpMV kernels highly optimized in assembly language. Considering that the optimal blocking size depends on the matrix, we also provide a method to predict the best kernel to be used utilizing a simple interpolation of the results from the previous executions. We compare the performance of our approach against the Intel MKL CSR kernel and the CSR5 open-source package on a set of standard benchmark matrices. We show that we can achieve significant improvements in many cases, both for sequential and for parallel execution. Finally, we provide the corresponding code in an open source library, called SPC5.