FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1998894100> ?p ?o ?g. }

• W1998894100 endingPage "1150" @default.
• W1998894100 startingPage "1140" @default.
• W1998894100 abstract "Lower upper (LU) factorization for sparse matrices is the most important computing step for circuit simulation problems. However, parallelizing LU factorization on the graphic processing units (GPUs) turns out to be a difficult problem due to intrinsic data dependence and irregular memory access, which diminish GPU computing power. In this paper, we propose a new sparse LU solver on GPUs for circuit simulation and more general scientific computing. The new method, which is called GPU accelerated LU factorization (GLU) solver (for GPU LU), is based on a hybrid right-looking LU factorization algorithm for sparse matrices. We show that more concurrency can be exploited in the right-looking method than the left-looking method, which is more popular for circuit analysis, on GPU platforms. At the same time, the GLU also preserves the benefit of column-based left-looking LU method, such as symbolic analysis and column-level concurrency. We show that the resulting new parallel GPU LU solver allows the parallelization of all three loops in the LU factorization on GPUs. While in contrast, the existing GPU-based left-looking LU factorization approach can only allow parallelization of two loops. Experimental results show that the proposed GLU solver can deliver $5.71times $ and $1.46times $ speedup over the single-threaded and the 16-threaded PARDISO solvers, respectively, $19.56times $ speedup over the KLU solver, $47.13times $ over the UMFPACK solver, and $1.47times $ speedup over a recently proposed GPU-based left-looking LU solver on the set of typical circuit matrices from the University of Florida (UFL) sparse matrix collection. Furthermore, we also compare the proposed GLU solver on a set of general matrices from the UFL, GLU achieves $6.38times $ and $1.12times $ speedup over the single-threaded and the 16-threaded PARDISO solvers, respectively, $39.39times $ speedup over the KLU solver, $24.04times $ over the UMFPACK solver, and $2.35times $ speedup over the same GPU-based left-looking LU solver. In addition, comparison on self-generated $RLC$ mesh networks shows a similar trend, which further validates the advantage of the proposed method over the existing sparse LU solvers." @default.
• W1998894100 created "2016-06-24" @default.
• W1998894100 creator A5001610191 @default.
• W1998894100 creator A5058844682 @default.
• W1998894100 creator A5072810436 @default.
• W1998894100 creator A5084762460 @default.
• W1998894100 date "2016-03-01" @default.
• W1998894100 modified "2023-10-03" @default.
• W1998894100 title "GPU-Accelerated Parallel Sparse LU Factorization Method for Fast Circuit Analysis" @default.
• W1998894100 cites W1520511539 @default.
• W1998894100 cites W2017431061 @default.
• W1998894100 cites W2020561008 @default.
• W1998894100 cites W2022038016 @default.
• W1998894100 cites W2041999884 @default.
• W1998894100 cites W2055094346 @default.
• W1998894100 cites W2063748721 @default.
• W1998894100 cites W2067795769 @default.
• W1998894100 cites W2074093855 @default.
• W1998894100 cites W2106969188 @default.
• W1998894100 cites W2118076222 @default.
• W1998894100 cites W2123097484 @default.
• W1998894100 cites W2130886743 @default.
• W1998894100 cites W2132450860 @default.
• W1998894100 cites W2136834900 @default.
• W1998894100 cites W2162322364 @default.
• W1998894100 cites W2169150754 @default.
• W1998894100 doi "https://doi.org/10.1109/tvlsi.2015.2421287" @default.
• W1998894100 hasPublicationYear "2016" @default.
• W1998894100 type Work @default.
• W1998894100 sameAs 1998894100 @default.
• W1998894100 citedByCount "46" @default.
• W1998894100 countsByYear W19988941002016 @default.
• W1998894100 countsByYear W19988941002017 @default.
• W1998894100 countsByYear W19988941002018 @default.
• W1998894100 countsByYear W19988941002019 @default.
• W1998894100 countsByYear W19988941002020 @default.
• W1998894100 countsByYear W19988941002021 @default.
• W1998894100 countsByYear W19988941002022 @default.
• W1998894100 countsByYear W19988941002023 @default.
• W1998894100 crossrefType "journal-article" @default.
• W1998894100 hasAuthorship W1998894100A5001610191 @default.
• W1998894100 hasAuthorship W1998894100A5058844682 @default.
• W1998894100 hasAuthorship W1998894100A5072810436 @default.
• W1998894100 hasAuthorship W1998894100A5084762460 @default.
• W1998894100 hasConcept C11413529 @default.
• W1998894100 hasConcept C14580979 @default.
• W1998894100 hasConcept C149635348 @default.
• W1998894100 hasConcept C173608175 @default.
• W1998894100 hasConcept C187834632 @default.
• W1998894100 hasConcept C41008148 @default.
• W1998894100 hasConcept C459310 @default.
• W1998894100 hasConceptScore W1998894100C11413529 @default.
• W1998894100 hasConceptScore W1998894100C14580979 @default.
• W1998894100 hasConceptScore W1998894100C149635348 @default.
• W1998894100 hasConceptScore W1998894100C173608175 @default.
• W1998894100 hasConceptScore W1998894100C187834632 @default.
• W1998894100 hasConceptScore W1998894100C41008148 @default.
• W1998894100 hasConceptScore W1998894100C459310 @default.
• W1998894100 hasIssue "3" @default.
• W1998894100 hasLocation W19988941001 @default.
• W1998894100 hasOpenAccess W1998894100 @default.
• W1998894100 hasPrimaryLocation W19988941001 @default.
• W1998894100 hasRelatedWork W1519244489 @default.
• W1998894100 hasRelatedWork W1605239144 @default.
• W1998894100 hasRelatedWork W1995349980 @default.
• W1998894100 hasRelatedWork W2073045545 @default.
• W1998894100 hasRelatedWork W2115695914 @default.
• W1998894100 hasRelatedWork W2158964476 @default.
• W1998894100 hasRelatedWork W2385361820 @default.
• W1998894100 hasRelatedWork W2523376728 @default.
• W1998894100 hasRelatedWork W2965967938 @default.
• W1998894100 hasRelatedWork W3007849603 @default.
• W1998894100 hasVolume "24" @default.
• W1998894100 isParatext "false" @default.
• W1998894100 isRetracted "false" @default.
• W1998894100 magId "1998894100" @default.
• W1998894100 workType "article" @default.