GPU implementation of SpMV

You are allowed to download the code designed for a GPU implementation of the SpMV product based on a Sliced ELLR-T format which requires storing significant fewer redundant elements than previously proposed schemes in order to achieve high throughput.

| Read the license | GET CODE |

Test matrices

A test matrix used in papers [2][4] may be downloaded from UF Sparse Matrix Market collection.

[2] Dziekonski, A.; Lamecki, A.; Mrozowski, M.; , "GPU Acceleration of Multilevel Solvers for Analysis of Microwave Components With Finite Element Method," Microwave and Wireless Components Letters, IEEE , vol.21, no.1, pp.1-3, Jan. 2011
doi: 10.1109/LMWC.2010.2089974 getPDF

[4] Dziekonski A.; Lamecki A.; Mrozowski M.; , "Tuning a Hybrid GPU-CPU V-Cycle Multilevel Preconditioner for Solving Large Real and Complex Systems of FEM Equations", Antennas and Wireless Propagation Letters, IEEE , vol.10, pp.619-622, July 2011 getPDF