Accelerating Graph Convolutional Networks Using Crossbar-based Processing-In-Memory Architectures
Authors:
Top Cited Papers
- 1 April 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1029-1042
Abstract
Graph convolutional networks (GCNs) are promising to enable machine learning on graphs. GCNs exhibit mixed computational kernels, involving regular neural-network-like computing and irregular graph-analytics-like processing. Existing GCN accelerators obey a divide-and-conquer philosophy to architect two separate types of hardware to accelerate these two types of GCN kernels, respectively. This hybrid architecture improves intra-kernel efficiency but considers little inter-kernel interactions in a holistic view for improving overall efficiency.In this paper, we present a new GCN accelerator, RE-FLIP, with three key innovations in terms of architecture design, algorithm mappings, and practical implementations. First, ReFlip leverages PIM-featured crossbar architectures to build a unified architecture for supporting the two types of GCN kernels simultaneously. Second, ReFlip adopts novel algorithm mappings that can maximize potential performance gains reaped from the unified architecture by exploiting the massive crossbar-structured parallelism. Third, ReFlip assembles software/hardware co-optimizations to process real-world graphs efficiently. Compared to the state-of-the-art software frameworks running on Intel Xeon E5-2680v4 CPU and NVIDIA Tesla V100 GPU, ReFlip achieves the average speedups of 6,432× and 86.32× and the average energy savings of 9,817× and 302.44×, respectively. In addition, ReFlip also outperforms a state-of-the-art GCN hardware accelerator, AWB-GCN, by achieving an average speedup of 5.06× and an average energy saving of 15.63×.Keywords
Funding Information
- National Natural Science Foundation of China
This publication has 31 references indexed in Scilit:
- Leveraging Hardware Caches for MemoizationIEEE Computer Architecture Letters, 2017
- PipeLayer: A Pipelined ReRAM-Based Accelerator for Deep Learning2017
- GraphPIM: Enabling Instruction-Level PIM Offloading in Graph Computing Frameworks2017
- ISAACACM SIGARCH Computer Architecture News, 2016
- PRIMEACM SIGARCH Computer Architecture News, 2016
- Dot-product engine for neuromorphic computing2016
- Memristor load current mirror circuit2015
- GraphMatProceedings of the VLDB Endowment, 2015
- Ramulator: A Fast and Extensible DRAM SimulatorIEEE Computer Architecture Letters, 2015
- Design of cross-point metal-oxide ReRAM emphasizing reliability and cost2013