Deep Graph Library Optimizations for Intel(R) x86 Architecture
This work provides incremental optimizations for researchers and practitioners using DGL on Intel x86 CPUs to improve computational efficiency in graph learning tasks.
The paper tackled performance bottlenecks in CPU implementations of the Deep Graph Library for graph neural networks, achieving speed-ups of 1.5x to 13x across 7 applications compared to baseline implementations.
The Deep Graph Library (DGL) was designed as a tool to enable structure learning from graphs, by supporting a core abstraction for graphs, including the popular Graph Neural Networks (GNN). DGL contains implementations of all core graph operations for both the CPU and GPU. In this paper, we focus specifically on CPU implementations and present performance analysis, optimizations and results across a set of GNN applications using the latest version of DGL(0.4.3). Across 7 applications, we achieve speed-ups ranging from1 1.5x-13x over the baseline CPU implementations.