Haobin Tan

Haobin Tan

Auto-generated profile, based on publicly available information

Haobin Tan

College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 June 2024
Verified
Conference Paper
Open access
SCSitian Chen
Sitian Chen
HTHaobin Tan
Haobin Tan
AZAmelie Chi Zhou
Amelie Chi Zhou
YLYusen Li
Yusen Li
PBPavan Balaji
Pavan Balaji
Deep Learning Recommendation Models (DLRMs) have gained popularity in recommendation systems due to their effectiveness in handling large-scale recommendation tasks. The embedding layers of DLRMs have become the performance bottleneck due to their intensive needs on memory capacity and memory bandwidth. In this paper, we propose UpDLRM, which utilizes real-world processing-in-memory (PIM) hardware, UPMEM DPU, to boost the memory bandwidth and reduce recommendation latency. The parallel nature of the DPU memory can provide high aggregated bandwidth for the large number of irregular memory accesses in embedding lookups, thus offering great potential to reduce the inference latency. To fully utilize the DPU memory bandwidth, we further studied the embedding table partitioning problem to achieve good workload-balance and efficient data caching. Evaluations using real-world datasets show that, UpDLRM achieves much lower inference time for DLRM compared to both CPU-only and CPU-GPU hybrid counterparts.

3 April 2025 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
HTHaobin Tan
Haobin Tan
YXYao Xiao
Yao Xiao
AZAmelie Chi Zhou
Amelie Chi Zhou
KLKezhong Lu
Kezhong Lu
XYXuan Yang
Xuan Yang
Graph partitioning is of great importance to optimizing the performance and cost of geo-distributed graph analytics applications. However, it is non-trivial to obtain efficient and effective partitioning due to the challenges brought by the large graph scales, dynamic graph changes and the network heterogeneity in geo-distributed data centers (DCs). Existing studies usually adopt heuristic-based methods to achieve fast and balanced partitioning for large graphs, which are not powerful enough to address the complexity in our problem. Further, graph structures of many applications can change at various frequencies. Dynamic partitioning methods usually focus on achieving low latency to quickly adapt to changes, which unfortunately sacrifices partitioning effectiveness. Also, such methods are not aware of the dynamicity of graphs and can over sacrifice effectiveness for unnecessarily low latency. To address the limitations of existing studies, we propose DistRLCut, a novel graph partitioner which leverages Multi-Agent Reinforcement Learning (MARL) to solve the complexity of the partitioning problem. To achieve fast partitioning for large graphs, DistRLCut adapts MARL to a distributed implementation which significantly accelerates the learning process. Further, DistRLCut incorporates two techniques to trade-off between partitioning effectiveness and efficiency, including local training and agent sampling. By adaptively tuning the number of local training iterations and the agent sampling rate, DistRLCut is able to achieve good partitioning results within an overhead constraint required by graph dynamicity. Experiments using real cloud DCs and real-world graphs show that, compared to state-of-the-art static partitioning methods, DistRLCut improves the performance of geo-distributed graph analytics by 11%-95%. DistRLCut can partition over 28 million edges per second, showcasing its scalability for large graphs. With varying graph changing frequencies, DistRLCut can improve the performance by up to 71% compared to state-of-the-art dynamic partitioning.