Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384807671> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4384807671 abstract "We propose an algorithm that aims at minimizing the inter-node communication volume for distributed and memory-efficient tensor contraction schemes on modern multi-core compute nodes. The key idea is to define processor grids that optimize intra-/inter-node communication volume in the employed contraction algorithms. We present an implementation of the proposed node-aware communication algorithm into the Cyclops Tensor Framework (CTF). We demonstrate that this implementation achieves a significantly improved performance for matrix-matrix-multiplication and tensor-contractions on up to several hundreds modern compute nodes compared to conventional implementations without using node-aware processor grids. Our implementation shows good performance when compared with existing state-of-the-art parallel matrix multiplication libraries (COSMA and ScaLAPACK). In addition to the discussion of the performance for matrix-matrix-multiplication, we also investigate the performance of our node-aware communication algorithm for tensor contractions as they occur in quantum chemical coupled-cluster methods. To this end we employ a modified version of CTF in combination with a coupled-cluster code (Cc4s). Our findings show that the node-aware communication algorithm is also able to improve the performance of coupled-cluster theory calculations for real-world problems running on tens to hundreds of compute nodes." @default.
- W4384807671 created "2023-07-20" @default.
- W4384807671 creator A5022838370 @default.
- W4384807671 creator A5040432851 @default.
- W4384807671 creator A5044984265 @default.
- W4384807671 creator A5085152691 @default.
- W4384807671 creator A5085234799 @default.
- W4384807671 date "2023-07-17" @default.
- W4384807671 modified "2023-09-26" @default.
- W4384807671 title "Optimizing Distributed Tensor Contractions using Node-Aware Processor Grids" @default.
- W4384807671 doi "https://doi.org/10.48550/arxiv.2307.08829" @default.
- W4384807671 hasPublicationYear "2023" @default.
- W4384807671 type Work @default.
- W4384807671 citedByCount "0" @default.
- W4384807671 crossrefType "posted-content" @default.
- W4384807671 hasAuthorship W4384807671A5022838370 @default.
- W4384807671 hasAuthorship W4384807671A5040432851 @default.
- W4384807671 hasAuthorship W4384807671A5044984265 @default.
- W4384807671 hasAuthorship W4384807671A5085152691 @default.
- W4384807671 hasAuthorship W4384807671A5085234799 @default.
- W4384807671 hasBestOaLocation W43848076711 @default.
- W4384807671 hasConcept C11413529 @default.
- W4384807671 hasConcept C114614502 @default.
- W4384807671 hasConcept C120314980 @default.
- W4384807671 hasConcept C121332964 @default.
- W4384807671 hasConcept C127413603 @default.
- W4384807671 hasConcept C155281189 @default.
- W4384807671 hasConcept C17349429 @default.
- W4384807671 hasConcept C173608175 @default.
- W4384807671 hasConcept C199360897 @default.
- W4384807671 hasConcept C202444582 @default.
- W4384807671 hasConcept C26713055 @default.
- W4384807671 hasConcept C2780595030 @default.
- W4384807671 hasConcept C33923547 @default.
- W4384807671 hasConcept C41008148 @default.
- W4384807671 hasConcept C62520636 @default.
- W4384807671 hasConcept C62611344 @default.
- W4384807671 hasConcept C66938386 @default.
- W4384807671 hasConcept C84114770 @default.
- W4384807671 hasConceptScore W4384807671C11413529 @default.
- W4384807671 hasConceptScore W4384807671C114614502 @default.
- W4384807671 hasConceptScore W4384807671C120314980 @default.
- W4384807671 hasConceptScore W4384807671C121332964 @default.
- W4384807671 hasConceptScore W4384807671C127413603 @default.
- W4384807671 hasConceptScore W4384807671C155281189 @default.
- W4384807671 hasConceptScore W4384807671C17349429 @default.
- W4384807671 hasConceptScore W4384807671C173608175 @default.
- W4384807671 hasConceptScore W4384807671C199360897 @default.
- W4384807671 hasConceptScore W4384807671C202444582 @default.
- W4384807671 hasConceptScore W4384807671C26713055 @default.
- W4384807671 hasConceptScore W4384807671C2780595030 @default.
- W4384807671 hasConceptScore W4384807671C33923547 @default.
- W4384807671 hasConceptScore W4384807671C41008148 @default.
- W4384807671 hasConceptScore W4384807671C62520636 @default.
- W4384807671 hasConceptScore W4384807671C62611344 @default.
- W4384807671 hasConceptScore W4384807671C66938386 @default.
- W4384807671 hasConceptScore W4384807671C84114770 @default.
- W4384807671 hasLocation W43848076711 @default.
- W4384807671 hasOpenAccess W4384807671 @default.
- W4384807671 hasPrimaryLocation W43848076711 @default.
- W4384807671 hasRelatedWork W1485627940 @default.
- W4384807671 hasRelatedWork W1513409726 @default.
- W4384807671 hasRelatedWork W1543798151 @default.
- W4384807671 hasRelatedWork W1577331154 @default.
- W4384807671 hasRelatedWork W1969934278 @default.
- W4384807671 hasRelatedWork W2104779926 @default.
- W4384807671 hasRelatedWork W4312354936 @default.
- W4384807671 hasRelatedWork W2622518229 @default.
- W4384807671 hasRelatedWork W2964144940 @default.
- W4384807671 hasRelatedWork W3119075280 @default.
- W4384807671 isParatext "false" @default.
- W4384807671 isRetracted "false" @default.
- W4384807671 workType "article" @default.