GraphScale: Scalable Processing on FPGAs for HBM and Large GraphsJust Accepted
ACM Transactions on Reconfigurable Technology and Systems(2023)
摘要
Recent advances in graph processing on FPGAs promise to alleviate performance bottlenecks with irregular memory access patterns. Such bottlenecks challenge performance for a growing number of important application areas like machine learning and data analytics. While FPGAs denote a promising solution through flexible memory hierarchies and massive parallelism, we argue that current graph processing accelerators either use the off-chip memory bandwidth inefficiently or do not scale well across memory channels. In this work, we propose GraphScale, a scalable graph processing framework for FPGAs. GraphScale combines multi-channel memory with asynchronous graph processing (i. e., for fast convergence on results) and a compressed graph representation (i. e., for efficient usage of memory bandwidth and reduced memory footprint). GraphScale solves common graph problems like breadth-first search, PageRank, and weakly-connected components through modular user-defined functions, a novel two-dimensional partitioning scheme, and a high-performance two-level crossbar design. Additionally, we extend GraphScale to scale to modern high-bandwidth memory (HBM) and reduce partitioning overhead of large graphs with binary packing.
更多查看译文
关键词
FPGA,Graph processing,HBM
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要