摘要
AnewGraphicsProcessingUnit(GPU)parallelizationstrategyisproposedtoacceleratesparsefiniteelementcomputationforthreedimensionalelectromagneticanalysis.TheparallelizationstrategyisemployedbasedonanewcompressionformatcalledslicedELLFour(slicedELL-F).TheslicedELL-Fformat-basedparallelizationstrategyisdesignedforhasteningmanyaddition,dotproduct,andSparseMatrixVectorProduct(SMVP)operationsintheConjugateGradientNorm(CGN)calculationoffiniteelementequations.ThenewimplementationofSMVPonGPUsisevaluated.TheproposedstrategyexecutedonaGPUcanefficientlysolvesparsefiniteelementequations,espe-ciallywhentheequationsarehugesparse(sizeofmostrowsinacoefficientmatrixislessthan8).NumericalresultsshowtheslicedELL-Fformat-basedparallelizationstrategycanreachsigni?cantspeedupscomparedtoCompressedSparseRow(CSR)format.
出版日期
2011年04月14日（中国期刊网平台首次上网日期，不代表论文的发表时间）
