FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3008821662> ?p ?o ?g. }

• W3008821662 abstract "Deep learning systems have been successfully applied to Euclidean data such as images, video, and audio. In many applications, however, information and their relationships are better expressed with graphs. Graph Convolutional Networks (GCNs) appear to be a promising approach to efficiently learn from graph data structures, having shown advantages in many critical applications. As with other deep learning modalities, hardware acceleration is critical. The challenge is that real-world graphs are often extremely large and unbalanced; this poses significant performance demands and design challenges. In this paper, we propose Autotuning-Workload-Balancing GCN (AWB-GCN) to accelerate GCN inference. To address the issue of workload imbalance in processing real-world graphs, three hardware-based autotuning techniques are proposed: dynamic distribution smoothing, remote switching, and row remapping. In particular, AWB-GCN continuously monitors the sparse graph pattern, dynamically adjusts the workload distribution among a large number of processing elements (up to 4K PEs), and, after converging, reuses the ideal configuration. Evaluation is performed using an Intel D5005 FPGA with five commonly-used datasets. Results show that 4K-PE AWB-GCN can significantly elevate PE utilization by 7.7x on average and demonstrate considerable performance speedups over CPUs (3255x), GPUs (80.3x), and a prior GCN accelerator (5.1x)." @default.
• W3008821662 created "2020-03-06" @default.
• W3008821662 creator A5009432979 @default.
• W3008821662 creator A5018230223 @default.
• W3008821662 creator A5018356320 @default.
• W3008821662 creator A5021051610 @default.
• W3008821662 creator A5027887058 @default.
• W3008821662 creator A5041853964 @default.
• W3008821662 creator A5059605240 @default.
• W3008821662 creator A5060138777 @default.
• W3008821662 creator A5066226919 @default.
• W3008821662 creator A5067209238 @default.
• W3008821662 creator A5078443672 @default.
• W3008821662 date "2019-08-23" @default.
• W3008821662 modified "2023-10-16" @default.
• W3008821662 title "AWB-GCN: A Graph Convolutional Network Accelerator with Runtime Workload Rebalancing" @default.
• W3008821662 cites W1501856433 @default.
• W3008821662 cites W1527463082 @default.
• W3008821662 cites W179875071 @default.
• W3008821662 cites W1977850862 @default.
• W3008821662 cites W1981252059 @default.
• W3008821662 cites W2016311778 @default.
• W3008821662 cites W2067247412 @default.
• W3008821662 cites W2087507944 @default.
• W3008821662 cites W2095249664 @default.
• W3008821662 cites W2112643910 @default.
• W3008821662 cites W2116341502 @default.
• W3008821662 cites W2124007994 @default.
• W3008821662 cites W2128853364 @default.
• W3008821662 cites W2131183411 @default.
• W3008821662 cites W2139906443 @default.
• W3008821662 cites W2150117348 @default.
• W3008821662 cites W2163605009 @default.
• W3008821662 cites W2285660444 @default.
• W3008821662 cites W2289252105 @default.
• W3008821662 cites W2515673159 @default.
• W3008821662 cites W2516141709 @default.
• W3008821662 cites W2519887557 @default.
• W3008821662 cites W2565851976 @default.
• W3008821662 cites W2566870951 @default.
• W3008821662 cites W2613119772 @default.
• W3008821662 cites W2625457103 @default.
• W3008821662 cites W2727953781 @default.
• W3008821662 cites W2766856748 @default.
• W3008821662 cites W2786016794 @default.
• W3008821662 cites W2788962621 @default.
• W3008821662 cites W2794952988 @default.
• W3008821662 cites W2795118915 @default.
• W3008821662 cites W2890068895 @default.
• W3008821662 cites W2890855364 @default.
• W3008821662 cites W2891325938 @default.
• W3008821662 cites W2900228909 @default.
• W3008821662 cites W2902209387 @default.
• W3008821662 cites W2903262661 @default.
• W3008821662 cites W2918342466 @default.
• W3008821662 cites W2949744956 @default.
• W3008821662 cites W2950898568 @default.
• W3008821662 cites W2962711740 @default.
• W3008821662 cites W2962767366 @default.
• W3008821662 cites W2962903741 @default.
• W3008821662 cites W2963581908 @default.
• W3008821662 cites W2964311892 @default.
• W3008821662 cites W2964321699 @default.
• W3008821662 cites W2964571482 @default.
• W3008821662 cites W2970066309 @default.
• W3008821662 cites W2980200167 @default.
• W3008821662 cites W2984035546 @default.
• W3008821662 cites W3003537320 @default.
• W3008821662 cites W3008522202 @default.
• W3008821662 cites W3016542674 @default.
• W3008821662 cites W3016904661 @default.
• W3008821662 cites W3017228913 @default.
• W3008821662 cites W3017521908 @default.
• W3008821662 cites W3047345547 @default.
• W3008821662 cites W3101861725 @default.
• W3008821662 cites W3104393472 @default.
• W3008821662 cites W637153065 @default.
• W3008821662 cites W78077100 @default.
• W3008821662 doi "https://doi.org/10.48550/arxiv.1908.10834" @default.
• W3008821662 hasPublicationYear "2019" @default.
• W3008821662 type Work @default.
• W3008821662 sameAs 3008821662 @default.
• W3008821662 citedByCount "3" @default.
• W3008821662 countsByYear W30088216622021 @default.
• W3008821662 crossrefType "posted-content" @default.
• W3008821662 hasAuthorship W3008821662A5009432979 @default.
• W3008821662 hasAuthorship W3008821662A5018230223 @default.
• W3008821662 hasAuthorship W3008821662A5018356320 @default.
• W3008821662 hasAuthorship W3008821662A5021051610 @default.
• W3008821662 hasAuthorship W3008821662A5027887058 @default.
• W3008821662 hasAuthorship W3008821662A5041853964 @default.
• W3008821662 hasAuthorship W3008821662A5059605240 @default.
• W3008821662 hasAuthorship W3008821662A5060138777 @default.
• W3008821662 hasAuthorship W3008821662A5066226919 @default.
• W3008821662 hasAuthorship W3008821662A5067209238 @default.
• W3008821662 hasAuthorship W3008821662A5078443672 @default.
• W3008821662 hasBestOaLocation W30088216621 @default.
• W3008821662 hasConcept C111919701 @default.
• W3008821662 hasConcept C13164978 @default.
• W3008821662 hasConcept C132525143 @default.

• next