Optimization and performance evaluation of the IDR iterative Krylov solver on GPUs
| Autor: | Jack Dongarra, Gregory D. Peterson, Gerhard Wellein, Moritz Kreutzer, Hartwig Anzt, Eduardo Ponce |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Co-design
020203 distributed computing Computer science Dimensionality reduction Computation Locality 010103 numerical & computational mathematics 02 engineering and technology Parallel computing Solver Sparse matrix vector 01 natural sciences Theoretical Computer Science Kernel (image processing) Hardware and Architecture ddc:000 0202 electrical engineering electronic engineering information engineering 0101 mathematics Performance model Software |
| Zdroj: | The International Journal of High Performance Computing Applications. 32:220-230 |
| ISSN: | 1741-2846 1094-3420 |
| DOI: | 10.1177/1094342016646844 |
| Popis: | In this paper, we present an optimized GPU implementation for the induced dimension reduction algorithm. We improve data locality, combine it with an efficient sparse matrix vector kernel, and investigate the potential of overlapping computation with communication as well as the possibility of concurrent kernel execution. A comprehensive performance evaluation is conducted using a suitable performance model. The analysis reveals efficiency of up to 90%, which indicates that the implementation achieves performance close to the theoretically attainable bound. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|