Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312608710> ?p ?o ?g. }
- W4312608710 abstract "Linear algebra kernels such as linear solvers, eigen-solvers are the actual working engine underneath many scientific applications. The growing scale of these applications has led researchers to rely on high-precision computing for improving their efficiency and their stability. In this work, we investigate the impact of arbitrary extended precision on multiple variants of the Conjugate Gradient method (CG). We show how our VRP processor improves the convergence and the efficiency of these kernels. We also illustrate how our set of tools (library, software environment) enables to migrate legacy applications in a fast and intuitive way while preserving high-performance. We observe up to an 8X improvements on kernel iteration count, and up to a 40 % improvement on latency. Nevertheless, the main benefit is the stability gained with the precision. It makes it possible to resolve larger and ill-conditioned systems without costly compensating techniques." @default.
- W4312608710 created "2023-01-05" @default.
- W4312608710 creator A5015505681 @default.
- W4312608710 creator A5032264534 @default.
- W4312608710 creator A5032792210 @default.
- W4312608710 creator A5048568686 @default.
- W4312608710 creator A5057876068 @default.
- W4312608710 creator A5087197771 @default.
- W4312608710 date "2022-09-01" @default.
- W4312608710 modified "2023-09-25" @default.
- W4312608710 title "Accelerating Variants of the Conjugate Gradient with the Variable Precision Processor" @default.
- W4312608710 cites W1506342804 @default.
- W4312608710 cites W1575701986 @default.
- W4312608710 cites W1969213662 @default.
- W4312608710 cites W1977146902 @default.
- W4312608710 cites W1981220107 @default.
- W4312608710 cites W1983325766 @default.
- W4312608710 cites W2030995892 @default.
- W4312608710 cites W2055529081 @default.
- W4312608710 cites W2082479178 @default.
- W4312608710 cites W2104281151 @default.
- W4312608710 cites W2106191211 @default.
- W4312608710 cites W2125426869 @default.
- W4312608710 cites W2480266340 @default.
- W4312608710 cites W2752588380 @default.
- W4312608710 cites W2752879223 @default.
- W4312608710 cites W2770593197 @default.
- W4312608710 cites W2897248362 @default.
- W4312608710 cites W2936567838 @default.
- W4312608710 cites W2944490985 @default.
- W4312608710 cites W2962775754 @default.
- W4312608710 cites W3123063474 @default.
- W4312608710 cites W4230094279 @default.
- W4312608710 cites W4248206987 @default.
- W4312608710 doi "https://doi.org/10.1109/arith54963.2022.00017" @default.
- W4312608710 hasPublicationYear "2022" @default.
- W4312608710 type Work @default.
- W4312608710 citedByCount "0" @default.
- W4312608710 crossrefType "proceedings-article" @default.
- W4312608710 hasAuthorship W4312608710A5015505681 @default.
- W4312608710 hasAuthorship W4312608710A5032264534 @default.
- W4312608710 hasAuthorship W4312608710A5032792210 @default.
- W4312608710 hasAuthorship W4312608710A5048568686 @default.
- W4312608710 hasAuthorship W4312608710A5057876068 @default.
- W4312608710 hasAuthorship W4312608710A5087197771 @default.
- W4312608710 hasConcept C111919701 @default.
- W4312608710 hasConcept C112972136 @default.
- W4312608710 hasConcept C113775141 @default.
- W4312608710 hasConcept C11413529 @default.
- W4312608710 hasConcept C114614502 @default.
- W4312608710 hasConcept C119857082 @default.
- W4312608710 hasConcept C134306372 @default.
- W4312608710 hasConcept C139352143 @default.
- W4312608710 hasConcept C162324750 @default.
- W4312608710 hasConcept C173608175 @default.
- W4312608710 hasConcept C177264268 @default.
- W4312608710 hasConcept C182365436 @default.
- W4312608710 hasConcept C199360897 @default.
- W4312608710 hasConcept C2524010 @default.
- W4312608710 hasConcept C2777303404 @default.
- W4312608710 hasConcept C2777904410 @default.
- W4312608710 hasConcept C33923547 @default.
- W4312608710 hasConcept C41008148 @default.
- W4312608710 hasConcept C459310 @default.
- W4312608710 hasConcept C50522688 @default.
- W4312608710 hasConcept C6802819 @default.
- W4312608710 hasConcept C74193536 @default.
- W4312608710 hasConcept C76155785 @default.
- W4312608710 hasConcept C81184566 @default.
- W4312608710 hasConcept C82876162 @default.
- W4312608710 hasConceptScore W4312608710C111919701 @default.
- W4312608710 hasConceptScore W4312608710C112972136 @default.
- W4312608710 hasConceptScore W4312608710C113775141 @default.
- W4312608710 hasConceptScore W4312608710C11413529 @default.
- W4312608710 hasConceptScore W4312608710C114614502 @default.
- W4312608710 hasConceptScore W4312608710C119857082 @default.
- W4312608710 hasConceptScore W4312608710C134306372 @default.
- W4312608710 hasConceptScore W4312608710C139352143 @default.
- W4312608710 hasConceptScore W4312608710C162324750 @default.
- W4312608710 hasConceptScore W4312608710C173608175 @default.
- W4312608710 hasConceptScore W4312608710C177264268 @default.
- W4312608710 hasConceptScore W4312608710C182365436 @default.
- W4312608710 hasConceptScore W4312608710C199360897 @default.
- W4312608710 hasConceptScore W4312608710C2524010 @default.
- W4312608710 hasConceptScore W4312608710C2777303404 @default.
- W4312608710 hasConceptScore W4312608710C2777904410 @default.
- W4312608710 hasConceptScore W4312608710C33923547 @default.
- W4312608710 hasConceptScore W4312608710C41008148 @default.
- W4312608710 hasConceptScore W4312608710C459310 @default.
- W4312608710 hasConceptScore W4312608710C50522688 @default.
- W4312608710 hasConceptScore W4312608710C6802819 @default.
- W4312608710 hasConceptScore W4312608710C74193536 @default.
- W4312608710 hasConceptScore W4312608710C76155785 @default.
- W4312608710 hasConceptScore W4312608710C81184566 @default.
- W4312608710 hasConceptScore W4312608710C82876162 @default.
- W4312608710 hasLocation W43126087101 @default.
- W4312608710 hasOpenAccess W4312608710 @default.
- W4312608710 hasPrimaryLocation W43126087101 @default.
- W4312608710 hasRelatedWork W2118233105 @default.
- W4312608710 hasRelatedWork W2411976577 @default.