Accel-GCN: High-Performance GPU Accelerator Design for Graph Convolution Networks

Graph Convolutional Networks (GCNs) are pivotal in extracting latent information from graph data across various domains, yet their acceleration on mainstream GPUs is challenged by workload imbalance and memory access irregularity. To address these challenges, we present Accel-GCN, a GPU accelerator...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Digest of technical papers - IEEE/ACM International Conference on Computer-Aided Design s. 01 - 09
Hlavní autori: Xie, Xi, Peng, Hongwu, Hasan, Amit, Huang, Shaoyi, Zhao, Jiahui, Fang, Haowen, Zhang, Wei, Geng, Tong, Khan, Omer, Ding, Caiwen
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 28.10.2023
Predmet:
Accelerator architectures
Bandwidth
Benchmark testing
Convolution
GPUs
Graph Convolution Network
Graphics processing units
Memory management
parallel computing
Parallel processing
sparse matrix multiplication (SpMM)
ISSN:1558-2434
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Graph Convolutional Networks (GCNs) are pivotal in extracting latent information from graph data across various domains, yet their acceleration on mainstream GPUs is challenged by workload imbalance and memory access irregularity. To address these challenges, we present Accel-GCN, a GPU accelerator architecture for GCNs. The design of Accel-GCN encompasses: (i) a lightweight degree sorting stage to group nodes with similar degree; (ii) a block-level partition strategy that dynamically adjusts warp workload sizes, enhancing shared memory locality and workload balance, and reducing metadata overhead compared to designs like GNNAdvisor; (iii) a combined warp strategy that improves memory coalescing and computational parallelism in the column dimension of dense matrices. Utilizing these principles, we formulate a kernel for SpMM in GCNs that employs block-level partitioning and combined warp strategy. This approach augments performance and multi-level memory efficiency and optimizes memory bandwidth by exploiting memory coalescing and alignment. Evaluation of Accel-GCN across 18 benchmark graphs reveals that it outperforms cuSPARSE, GNNAdvisor, and graph-BLAST by factors of 1.17×, 1.86×, and 2.94× respectively. The results underscore Accel-GCN as an effective solution for enhancing GCN computational efficiency. The implementation can be found on Github*.
ISSN:1558-2434
DOI:10.1109/ICCAD57390.2023.10323722