Matches in SemOpenAlex for { <https://semopenalex.org/work/W1997614470> ?p ?o ?g. }
- W1997614470 abstract "Finite-difference, stencil-based discretization approaches are widely used in the solution of partial differential equations describing physical phenomena. Newton-Krylov iterative methods commonly used in stencil-based solutions generate matrices that exhibit diagonal sparsity patterns. To exploit these structures on modern GPUs, we extend the standard diagonal sparse matrix representation and define new matrix and vector data types in the PETSc parallel numerical toolkit. We create tunable CUDA implementations of the operations associated with these types after identifying a number of GPU-specific optimizations and tuning parameters for these operations. We discuss our implementation of GPU auto tuning capabilities in the Orio framework and present performance results for several kernels, comparing them with vendor-tuned library implementations." @default.
- W1997614470 created "2016-06-24" @default.
- W1997614470 creator A5022915639 @default.
- W1997614470 creator A5054205253 @default.
- W1997614470 creator A5074668365 @default.
- W1997614470 creator A5079346036 @default.
- W1997614470 date "2012-09-01" @default.
- W1997614470 modified "2023-09-23" @default.
- W1997614470 title "Autotuning Stencil-Based Computations on GPUs" @default.
- W1997614470 cites W1569090332 @default.
- W1997614470 cites W1876394617 @default.
- W1997614470 cites W2091908315 @default.
- W1997614470 cites W2099021415 @default.
- W1997614470 cites W2112391112 @default.
- W1997614470 cites W2141331848 @default.
- W1997614470 cites W2155503253 @default.
- W1997614470 cites W2162322364 @default.
- W1997614470 cites W3138798301 @default.
- W1997614470 doi "https://doi.org/10.1109/cluster.2012.46" @default.
- W1997614470 hasPublicationYear "2012" @default.
- W1997614470 type Work @default.
- W1997614470 sameAs 1997614470 @default.
- W1997614470 citedByCount "36" @default.
- W1997614470 countsByYear W19976144702013 @default.
- W1997614470 countsByYear W19976144702014 @default.
- W1997614470 countsByYear W19976144702015 @default.
- W1997614470 countsByYear W19976144702016 @default.
- W1997614470 countsByYear W19976144702017 @default.
- W1997614470 countsByYear W19976144702018 @default.
- W1997614470 countsByYear W19976144702019 @default.
- W1997614470 countsByYear W19976144702020 @default.
- W1997614470 countsByYear W19976144702022 @default.
- W1997614470 countsByYear W19976144702023 @default.
- W1997614470 crossrefType "proceedings-article" @default.
- W1997614470 hasAuthorship W1997614470A5022915639 @default.
- W1997614470 hasAuthorship W1997614470A5054205253 @default.
- W1997614470 hasAuthorship W1997614470A5074668365 @default.
- W1997614470 hasAuthorship W1997614470A5079346036 @default.
- W1997614470 hasBestOaLocation W19976144702 @default.
- W1997614470 hasConcept C11413529 @default.
- W1997614470 hasConcept C121332964 @default.
- W1997614470 hasConcept C130367717 @default.
- W1997614470 hasConcept C134306372 @default.
- W1997614470 hasConcept C139352143 @default.
- W1997614470 hasConcept C147060835 @default.
- W1997614470 hasConcept C159694833 @default.
- W1997614470 hasConcept C163716315 @default.
- W1997614470 hasConcept C173608175 @default.
- W1997614470 hasConcept C199360897 @default.
- W1997614470 hasConcept C2524010 @default.
- W1997614470 hasConcept C26713055 @default.
- W1997614470 hasConcept C2778119891 @default.
- W1997614470 hasConcept C33923547 @default.
- W1997614470 hasConcept C41008148 @default.
- W1997614470 hasConcept C41681595 @default.
- W1997614470 hasConcept C45374587 @default.
- W1997614470 hasConcept C459310 @default.
- W1997614470 hasConcept C56372850 @default.
- W1997614470 hasConcept C62520636 @default.
- W1997614470 hasConcept C73000952 @default.
- W1997614470 hasConcept C76752949 @default.
- W1997614470 hasConceptScore W1997614470C11413529 @default.
- W1997614470 hasConceptScore W1997614470C121332964 @default.
- W1997614470 hasConceptScore W1997614470C130367717 @default.
- W1997614470 hasConceptScore W1997614470C134306372 @default.
- W1997614470 hasConceptScore W1997614470C139352143 @default.
- W1997614470 hasConceptScore W1997614470C147060835 @default.
- W1997614470 hasConceptScore W1997614470C159694833 @default.
- W1997614470 hasConceptScore W1997614470C163716315 @default.
- W1997614470 hasConceptScore W1997614470C173608175 @default.
- W1997614470 hasConceptScore W1997614470C199360897 @default.
- W1997614470 hasConceptScore W1997614470C2524010 @default.
- W1997614470 hasConceptScore W1997614470C26713055 @default.
- W1997614470 hasConceptScore W1997614470C2778119891 @default.
- W1997614470 hasConceptScore W1997614470C33923547 @default.
- W1997614470 hasConceptScore W1997614470C41008148 @default.
- W1997614470 hasConceptScore W1997614470C41681595 @default.
- W1997614470 hasConceptScore W1997614470C45374587 @default.
- W1997614470 hasConceptScore W1997614470C459310 @default.
- W1997614470 hasConceptScore W1997614470C56372850 @default.
- W1997614470 hasConceptScore W1997614470C62520636 @default.
- W1997614470 hasConceptScore W1997614470C73000952 @default.
- W1997614470 hasConceptScore W1997614470C76752949 @default.
- W1997614470 hasLocation W19976144701 @default.
- W1997614470 hasLocation W19976144702 @default.
- W1997614470 hasOpenAccess W1997614470 @default.
- W1997614470 hasPrimaryLocation W19976144701 @default.
- W1997614470 hasRelatedWork W1936984751 @default.
- W1997614470 hasRelatedWork W2003264742 @default.
- W1997614470 hasRelatedWork W2020484966 @default.
- W1997614470 hasRelatedWork W2144511445 @default.
- W1997614470 hasRelatedWork W2529540995 @default.
- W1997614470 hasRelatedWork W2791204867 @default.
- W1997614470 hasRelatedWork W2804132206 @default.
- W1997614470 hasRelatedWork W2915788706 @default.
- W1997614470 hasRelatedWork W3122909934 @default.
- W1997614470 hasRelatedWork W4285033109 @default.
- W1997614470 isParatext "false" @default.
- W1997614470 isRetracted "false" @default.
- W1997614470 magId "1997614470" @default.