Toward Auto-tuned Krylov Basis Computation for Different Sparse Matrix Formats and Interconnects on GPU Clusters
Langshi Chen, Serge G. Petition · 2015
Krylov subspace methods (KSMs) are widely used insolving large-scale sparse linear problems. The orthogonalizationprocess in methods like GMRES would consume a majorityof the time. Since modern manycore architecture based acceleratorshave provided great horsepowers for computations,communication overheads remain a bottleneck, especially inclusters with a great number of nodes. The HA-PACS/TCA ofTsukuba University is a CPU-GPU hybrid cluster equipped withdifferent interconnects for communications among GPUs. We testa group of Krylov basis computation methods with differentsparse matrices and interconnects on HA-PACS/TCA. Resultsshow that an auto-tuning scheme is required to deal with varioustypes of matrices.