Learn More
Sparse matrix-vector multiplication (SpMxV) is a kernel operation widely used in iterative linear solvers. The same sparse matrix is multiplied by a dense vector repeatedly in these solvers. Matrices with irregular sparsity patterns make it difficult to utilize cache locality effectively in SpMxV computations. In this work, we investigate single-and(More)
For outer-product–parallel sparse matrix-matrix multiplication (SpGEMM) of the form C=A×B, we propose three hypergraph models that achieve simultaneous partitioning of input and output matrices without any replication of input data. All three hypergraph models perform conformable one-dimensional (1D) columnwise and 1D rowwise partitioning of the input(More)
Sparse matrix-vector and matrix-transpose-vector multiplication (SpMM<sup>T</sup>V) repeatedly performed as z&#x2190;A<sup>T</sup><sub>x</sub> and y&#x2190; A z (or y A w) for the same sparse matrix A is a kernel operation widely used in various iterative solvers. One important optimization for serial SpMM<sup>T</sup>V is reusing A-matrix nonzeros, which(More)
Exploiting spatial and temporal localities is investigated for efficient row-by-row parallelization of general sparse matrix-matrix multiplication (SpGEMM) operation of the form <inline-formula><tex-math notation="LaTeX">$C=A\,B$ </tex-math><alternatives><inline-graphic xlink:href="aykanat-ieq1-2656893.gif"/></alternatives></inline-formula> on many-core(More)
The sparse matrix-vector multiplication (SpMxV) is a kernel operation widely used in iterative linear solvers. The same sparse matrix is multiplied by a dense vector repeatedly in these solvers. Matrices with irregular sparsity patterns make it difficult to utilize cache locality effectively in SpMxV computations. In this work, we investigate single-and(More)
The sparse matrix-vector multiplication (SpMxV) is a kernel operation widely used in iterative linear solvers. The same sparse matrix is multiplied by a dense vector repeatedly in these solvers. Matrices with irregular sparsity patterns make it difficult to utilize cache locality effectively in SpMxV computations. In this work, we investigate single-and(More)