Performance Optimization and Modeling of Blocked Sparse Kernels

We present a method for automatically selecting optimal implementations of sparse matrixvector operations. Our software ‘AcCELS’ (Accelerated Compress-storage Elements for Linear Solvers) involves a setup phase that probes machine characteristics, and a run-time phase where stored characteristics are combined with a measure of the actual sparse matrix to find the optimal kernel implementation. We present a performance model that is shown to be accurate over a large range of matrices.

• Type: Journal
• Year: 2007
• Where: IJHPCA
• Authors: Alfredo Buttari, Victor Eijkhout, Julien Langou, Salvatore Filippone
• Keywords: Actual Sparse Matrix, IJHPCA 2007, Optimal Kernel Implementation, Sparse Matrixvector Operations