Level-Based Blocking for Sparse Matrices: Sparse Matrix-Power-Vector Multiplication

Abstract

The multiplication of a sparse matrix with a dense vector (SpMV) is a key component in many numerical schemes and its performance is known to be severely limited by main memory access. Several numerical schemes require the multiplication of a sparse matrix polynomial with a dense vector which is typically implemented as a sequence of SpMVs. This results in low performance and ignores the potential to increase the arithmetic intensity by reusing the matrix data from cache. In this work we use the recursive algebraic coloring engine (RACE) to enable blocking of sparse matrix data across the polynomial computations. In the graph representing the sparse matrix we form levels using a breadth-first search. Locality relations of these levels are then used to improve spatial and temporal locality when accessing the matrix data and to implement an efficient multithreaded parallelization. Our approach is independent of the matrix structure and avoids shortcomings of existing "blocking" strategies in terms of hardware efficiency and parallelization overhead. We quantify the quality of our implementation using performance modelling and demonstrate speedups of up to 3× and 5× compared to an optimal SpMV-based baseline on a single multicore chip of recent Intel and AMD architectures. Various numerical schemes like s-step Krylov solvers, polynomial preconditioners and power clustering algorithms will benefit from our development.

Efficient 2-Distance Coloring Method for Maximum and Average Sparse Graphs in Resource Allocation Optimization of Microgrids

“…For a sparse graph G , the maximum mean degree is denoted as () mad G and satisfies the condition that . In this article, there are other less common symbols that are consistent with the notation in Bondy and Murty's book [6][7][8][9][10].…”

On explicit exponential integrators in the solution of elastic wave propagation equations

“…Determining the exact number of computations performed by these methods is a complex task, further complicated by the fact that sparse matrix-vector multiplications are known to be bandwidth-limited in terms of performance Alappat et al [2022], Huber et al [2020]. Therefore, we adopt a simplified model that focuses exclusively on counting the loading and storing of elements.…”