GraphR: Accelerating Graph Processing Using ReRAM
- GNN

This paper presents GRAPHR, the first ReRAM-based graph processing accelerator. GRAPHR follows the principle of near-data processing but explores the opportunity of per-forming massive parallel operations with low hardware and energy cost. Compared to recent works in applying ReRAM to more regular neural computations, we are faced with several challenges: 1) The graph data are stored in the com-pressed format, instead of matrix forms, making it impossible to perform direct in-situ computations in memory; 2) It is less intuitive to map various graph algorithms to ReRAM with hardware constrains; 3) Coordinating data movements among ReRAM crossbars and memory to achieve high throughput. GRAPHR is a novel accelerator architecture consisting of two major components: memory ReRAM and graph engine (GE). The core graph computations are performed in sparse matrix format in GEs (ReRAM crossbars), which perform efficient matrix-vector multiplications. The vector/matrix-based graph computation is not new, but ReRAM offers the unique opportunity to realize the massive parallelism with unprecedented energy efficiency and low hardware cost. Due to the same cost/performance tradeoff, with ReRAM, the gain of performing parallel operations overshadows the wastes due to sparsity in matrix view within a small subgraph. Moreover, it naturally enables near data processing with reduced data movements. The experiment results show that GRAPHR achieves a16.01x (up to132.67x) speedup and an33.82x energy saving on geometric mean compared to a CPU baseline system.
View on arXiv