Presentation
CDA-GNN: A Chain-driven Accelerator for Efficient Asynchronous Graph Neural Network
DescriptionAsynchronous Graph Neural Network (AGNN) has attracted much research attention because it enables faster convergence speed than the synchronous GNN. However, existing software/hardware solutions suffer from redundant computation overhead and excessive off-chip communications
for AGNN due to irregular state propagations along the dependency chains between vertices. This paper proposes a chain-driven asynchronous accelerator, CDA-GNN, for efficient AGNN inference. Specifically, CDA-GNN proposes a chain-driven asynchronous execution approach into novel
accelerator design to regularize the vertex state propagations for fewer redundant computations and off-chip communications, and also designs a chain-aware data caching method to improve data locality for AGNN. We have implemented and evaluated CDA-GNN on a Xilinx Alveo U280 FPGA card.
Compared with the state-of-the-art software solutions (i.e., Dorylus and AMP) and hardware solutions (i.e., BlockGNN and FlowGNN), CDA-GNN improves the performance of AGNN inference by an average of 1,173x, 182.4x, 10.2x, and 7.9x and saves energy by 2,241x, 242.2x, 12.4x, and 8.9x, respectively.
for AGNN due to irregular state propagations along the dependency chains between vertices. This paper proposes a chain-driven asynchronous accelerator, CDA-GNN, for efficient AGNN inference. Specifically, CDA-GNN proposes a chain-driven asynchronous execution approach into novel
accelerator design to regularize the vertex state propagations for fewer redundant computations and off-chip communications, and also designs a chain-aware data caching method to improve data locality for AGNN. We have implemented and evaluated CDA-GNN on a Xilinx Alveo U280 FPGA card.
Compared with the state-of-the-art software solutions (i.e., Dorylus and AMP) and hardware solutions (i.e., BlockGNN and FlowGNN), CDA-GNN improves the performance of AGNN inference by an average of 1,173x, 182.4x, 10.2x, and 7.9x and saves energy by 2,241x, 242.2x, 12.4x, and 8.9x, respectively.
Event Type
Research Manuscript
TimeTuesday, June 2511:30am - 11:45am PDT
Location3003, 3rd Floor
AI
Design
AI/ML Architecture Design