Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200014673> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4200014673 abstract "Graph data structures are central to many applications such as social networks, citation networks, molecular interactions, and navigation systems. Graph Convolutional Networks (GCNs) are used to process and learn insights from the graph data for tasks such as link prediction, node classification, and learning node embeddings. The compute and memory access characteristics of GCNs differ, both from conventional graph analytics algorithms and from convolutional neural networks, rendering the existing accelerators for graph analytics as well as deep learning, inefficient. In this work, we propose PIM-GCN, a crossbar-based processing-in-memory (PIM) accelerator architecture for GCNs. PIM-GCN incorporates a node-stationary dataflow with support for both Compressed Sparse Row (CSR) and Compressed Sparse Column (CSC) graph data representations. We propose techniques for graph traversal in the compressed sparse domain, feature aggregation, and feature transformation operations in GCNs mapped to in-situ analog compute functions of crossbar memory, and present the trade-offs in performance, energy, and scalability aspects of the PIM-GCN architecture for CSR, and CSC graph data representations. PIM-GCN shows an average speedup of over <tex xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>$3-16times$</tex> and an average energy reduction of <tex xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>$4-12times$</tex> compared to the existing accelerator architectures." @default.
- W4200014673 created "2021-12-31" @default.
- W4200014673 creator A5008340979 @default.
- W4200014673 creator A5030751472 @default.
- W4200014673 creator A5076019669 @default.
- W4200014673 creator A5088745992 @default.
- W4200014673 date "2021-11-01" @default.
- W4200014673 modified "2023-09-24" @default.
- W4200014673 title "Crossbar based Processing in Memory Accelerator Architecture for Graph Convolutional Networks" @default.
- W4200014673 cites W2108880814 @default.
- W4200014673 cites W2516141709 @default.
- W4200014673 cites W2613989746 @default.
- W4200014673 cites W2625457103 @default.
- W4200014673 cites W2725159389 @default.
- W4200014673 cites W2794243109 @default.
- W4200014673 cites W2909331201 @default.
- W4200014673 cites W2913104037 @default.
- W4200014673 cites W2931118404 @default.
- W4200014673 cites W2945146780 @default.
- W4200014673 cites W2949674408 @default.
- W4200014673 cites W2949989598 @default.
- W4200014673 cites W2962903741 @default.
- W4200014673 cites W2965744772 @default.
- W4200014673 cites W2980039165 @default.
- W4200014673 cites W2980104813 @default.
- W4200014673 cites W2982164923 @default.
- W4200014673 cites W2998332152 @default.
- W4200014673 cites W3005901860 @default.
- W4200014673 cites W3017228913 @default.
- W4200014673 cites W3043072009 @default.
- W4200014673 cites W3048881102 @default.
- W4200014673 cites W3091862797 @default.
- W4200014673 cites W3093516620 @default.
- W4200014673 cites W3102587717 @default.
- W4200014673 cites W3105753905 @default.
- W4200014673 cites W3111375540 @default.
- W4200014673 cites W3157609068 @default.
- W4200014673 cites W4243519499 @default.
- W4200014673 cites W4254672563 @default.
- W4200014673 doi "https://doi.org/10.1109/iccad51958.2021.9643465" @default.
- W4200014673 hasPublicationYear "2021" @default.
- W4200014673 type Work @default.
- W4200014673 citedByCount "6" @default.
- W4200014673 countsByYear W42000146732022 @default.
- W4200014673 countsByYear W42000146732023 @default.
- W4200014673 crossrefType "proceedings-article" @default.
- W4200014673 hasAuthorship W4200014673A5008340979 @default.
- W4200014673 hasAuthorship W4200014673A5030751472 @default.
- W4200014673 hasAuthorship W4200014673A5076019669 @default.
- W4200014673 hasAuthorship W4200014673A5088745992 @default.
- W4200014673 hasConcept C108583219 @default.
- W4200014673 hasConcept C132525143 @default.
- W4200014673 hasConcept C154945302 @default.
- W4200014673 hasConcept C173608175 @default.
- W4200014673 hasConcept C29984679 @default.
- W4200014673 hasConcept C41008148 @default.
- W4200014673 hasConcept C48044578 @default.
- W4200014673 hasConcept C68339613 @default.
- W4200014673 hasConcept C76155785 @default.
- W4200014673 hasConcept C77088390 @default.
- W4200014673 hasConcept C80444323 @default.
- W4200014673 hasConcept C81363708 @default.
- W4200014673 hasConceptScore W4200014673C108583219 @default.
- W4200014673 hasConceptScore W4200014673C132525143 @default.
- W4200014673 hasConceptScore W4200014673C154945302 @default.
- W4200014673 hasConceptScore W4200014673C173608175 @default.
- W4200014673 hasConceptScore W4200014673C29984679 @default.
- W4200014673 hasConceptScore W4200014673C41008148 @default.
- W4200014673 hasConceptScore W4200014673C48044578 @default.
- W4200014673 hasConceptScore W4200014673C68339613 @default.
- W4200014673 hasConceptScore W4200014673C76155785 @default.
- W4200014673 hasConceptScore W4200014673C77088390 @default.
- W4200014673 hasConceptScore W4200014673C80444323 @default.
- W4200014673 hasConceptScore W4200014673C81363708 @default.
- W4200014673 hasLocation W42000146731 @default.
- W4200014673 hasOpenAccess W4200014673 @default.
- W4200014673 hasPrimaryLocation W42000146731 @default.
- W4200014673 hasRelatedWork W1800827217 @default.
- W4200014673 hasRelatedWork W1967627035 @default.
- W4200014673 hasRelatedWork W2370911386 @default.
- W4200014673 hasRelatedWork W2499279132 @default.
- W4200014673 hasRelatedWork W2731899572 @default.
- W4200014673 hasRelatedWork W3116150086 @default.
- W4200014673 hasRelatedWork W3133861977 @default.
- W4200014673 hasRelatedWork W4200173597 @default.
- W4200014673 hasRelatedWork W4312417841 @default.
- W4200014673 hasRelatedWork W4321369474 @default.
- W4200014673 isParatext "false" @default.
- W4200014673 isRetracted "false" @default.
- W4200014673 workType "article" @default.