Software for "Bringing Order to Sparsity: A Sparse Matrix Reordering Study on Multicore CPUs"

The paper "Bringing Order to Sparsity: A Sparse Matrix Reordering Study on Multicore CPUs" compares various strategies for reordering sparse matrices. The purpose of reordering is to improve performance of sparse matrix operations, for example, by reducing fill-in resulting from sparse Cholesky factorisation or improving data locality in sparse matrix-vector multiplication (SpMV). Many reordering strategies have been proposed in the literature and the current paper provides a thorough comparison of several of the most popular methods. This comparison is based on performance measurements that were collected on the eX3 cluster, a Norwegian, experimental research infrastructure for exploration of exascale computing. The code that was used to perform matrix reordering and collect performance measurements is provided here. This archive contains the following: * libmtx-0.4.0.zip: Source code for Libmtx 0.4.0, which was used to perform matrix reordering with Reverse Cuthill-McKee, Nested Dissection and Graph Partitioning based on METIS. * Matrix-Partitioning-Utility-1.0.zip: Source code for a utility that was used to perform matrix reordering with Hypergraph Partitioning based on PaToH. * sparsebase-0.3.1.zip: Source code for SparseBase 0.3.1, which was used to perform matrix reordering with Approximate Minimum Degree and Gray order. Documentation for SparseBase is included in sparsebase-0.3.1-docs.pdf. * spmv-1.5.zip: Source code for Sparse Matrix-Vector Multiplication (SpMV) with two different kernels for matrices in compressed sparse row (CSR) format. * upchol-1.0.zip: Source code for sparse Cholesky factorization and for counting fill-in. * mtxfeatures-1.0.zip: Source code for computing matrix features