English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep learning systems have been successfully applied to Euclidean data suchas images, video, and audio. In many applications, however, information andtheir relationships are better expressed with graphs. Graph ConvolutionalNetworks (GCNs) appear to be a promising approach to efficiently learn fromgraph data structures, having shown advantages in many critical applications.As with other deep learning modalities, hardware acceleration is critical. Thechallenge 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) toaccelerate GCN inference. To address the issue of workload imbalance inprocessing real-world graphs, three hardware-based autotuning techniques areproposed: 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 ofprocessing elements (up to 4K PEs), and, after converging, reuses the idealconfiguration. Evaluation is performed using an Intel D5005 FPGA with fivecommonly-used datasets. Results show that 4K-PE AWB-GCN can significantlyelevate PE utilization by 7.7x on average and demonstrate considerableperformance speedups over CPUs (3255x), GPUs (80.3x), and a prior GCNaccelerator (5.1x).

AWB-GCN: A Graph Convolutional Network Accelerator with Runtime Workload Rebalancing