Modern recommendation systems integrate graph convolution neural networks(GCN)for enhancing embedding representation.Compared with widely deployed neural network-based models,the extra message propagation layer of GCN...Modern recommendation systems integrate graph convolution neural networks(GCN)for enhancing embedding representation.Compared with widely deployed neural network-based models,the extra message propagation layer of GCN-based recommendation is featured with extensive computations and irregular memory access.However,architecture designs for prevailing deep neural network recommendation models assume simple pooling in the embedding layer.ReRAM-based GCN accelerators are specialized for graph-related operations.However,they are designed for general graphs,while GCN-based recommendation models mainly operate on the user-item graph.In this paper,we proposed a resistive random accessed memory(ReRAM)based processing-in-memory(PIM)accelerator,ReGCNR,for GCN-based recommendation.ReGCNR is featured with three key innovations.First,we exploit the 3-dimensional(3-D)stacked heterogeneous ReRAM to fit with the large-size embedding table and user-item graph.Then,we propose a joint degree mapping schema that maximizes the efficiency of the execution pipeline.After that,ReGCNR assembles a well-coordinated pipeline and hardware scheduling design to boost overall system performance.Results show that ReGCNR outperforms GPU by 69.83×and 56.67×in terms of average speedup and energy saving,respectively.In addition,ReGCNR outperforms state-of-the-art ReRAM-based solutions by 11.13×speedups and 7.22×energy savings on average.展开更多
基金supported by the National Key Research and Development Program of China under Grant No.2023YFB4503400the National Natural Science Foundation of China under Grant No.62322205,62072195,and 61825202supported by Zhejiang Lab(Grant No.2022P10AC02).
文摘Modern recommendation systems integrate graph convolution neural networks(GCN)for enhancing embedding representation.Compared with widely deployed neural network-based models,the extra message propagation layer of GCN-based recommendation is featured with extensive computations and irregular memory access.However,architecture designs for prevailing deep neural network recommendation models assume simple pooling in the embedding layer.ReRAM-based GCN accelerators are specialized for graph-related operations.However,they are designed for general graphs,while GCN-based recommendation models mainly operate on the user-item graph.In this paper,we proposed a resistive random accessed memory(ReRAM)based processing-in-memory(PIM)accelerator,ReGCNR,for GCN-based recommendation.ReGCNR is featured with three key innovations.First,we exploit the 3-dimensional(3-D)stacked heterogeneous ReRAM to fit with the large-size embedding table and user-item graph.Then,we propose a joint degree mapping schema that maximizes the efficiency of the execution pipeline.After that,ReGCNR assembles a well-coordinated pipeline and hardware scheduling design to boost overall system performance.Results show that ReGCNR outperforms GPU by 69.83×and 56.67×in terms of average speedup and energy saving,respectively.In addition,ReGCNR outperforms state-of-the-art ReRAM-based solutions by 11.13×speedups and 7.22×energy savings on average.
