Mo Zou

Mo Zou

Auto-generated profile, based on publicly available information

Mo Zou

State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
11 August 2022 in IEEE Computer Architecture Letters
Verified
Journal Article
Closed access
MYMingyu Yan
Mingyu Yan
MZMo Zou
Mo Zou
XYXiaocheng Yang
Xiaocheng Yang
WLWenming Li
Wenming Li
XYXiaochun Ye
Xiaochun Ye
YXYuan Xie
Yuan Xie
Heterogeneous graph neural networks (HGNNs) deliver powerful capacity in heterogeneous graph representation learning. The execution of HGNNs is usually accelerated by GPUs. Therefore, characterizing and understanding the execution pattern of HGNNs on GPUs is important for both software and hardware optimizations. Unfortunately, there is no detailed characterization effort of HGNN workloads on GPUs. In this paper, we characterize HGNN workloads at inference phase and explore the execution of HGNNs on GPU, to disclose the execution semantic and execution pattern of HGNNs. Given the characterization and exploration, we propose several useful guidelines for both software and hardware optimizations for the efficient execution of HGNNs on GPUs.

19 April 2022 in IEEE Computer Architecture Letters
Verified
Journal Article
Closed access
HLHaiyang Lin
Haiyang Lin
MYMingyu Yan
Mingyu Yan
XYXiaocheng Yang
Xiaocheng Yang
MZMo Zou
Mo Zou
WLWenming Li
Wenming Li
DFDongrui Fan
Dongrui Fan
Graph neural network (GNN) has been demonstrated to be a powerful model in many domains for its effectiveness in learning over graphs. To scale GNN training for large graphs, a widely adopted approach is distributed training which accelerates training using multiple computing nodes. Maximizing the performance is essential, but the execution of distributed GNN training remains preliminarily understood. In this work, we provide an in-depth analysis of distributed GNN training on GPUs, revealing several significant observations and providing useful guidelines for both software optimization and hardware optimization.

30 April 2024 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
RXRunzhen Xue
Runzhen Xue
DHDengke Han
Dengke Han
MYMingyu Yan
Mingyu Yan
MZMo Zou
Mo Zou
XYXiaocheng Yang
Xiaocheng Yang
DFDongrui Fan
Dongrui Fan
Heterogeneous graph neural networks (HGNNs) have emerged as powerful algorithms for processing heterogeneous graphs (HetGs), widely used in many critical fields. To capture both structural and semantic information in HetGs, HGNNs first aggregate the neighboring feature vectors for each vertex in each semantic graph and then fuse the aggregated results across all semantic graphs for each vertex. Unfortunately, existing graph neural network accelerators are ill-suited to accelerate HGNNs. This is because they fail to efficiently tackle the specific execution patterns and exploit the high-degree parallelism as well as data reusability inside and across the processing of semantic graphs in HGNNs. In this work, we first quantitatively characterize a set of representative HGNN models on GPU to disclose the execution bound of each stage, inter-semantic-graph parallelism, and inter-semantic-graph data reusability in HGNNs. Guided by our findings, we propose a high-performance HGNN accelerator, HiHGNN, to alleviate the execution bound and exploit the newfound parallelism and data reusability in HGNNs. Specifically, we first propose a bound-aware stage-fusion methodology that tailors to HGNN acceleration, to fuse and pipeline the execution stages being aware of their execution bounds. Second, we design an independency-aware parallel execution design to exploit the inter-semantic-graph parallelism. Finally, we present a similarity-aware execution scheduling to exploit the inter-semantic-graph data reusability. Compared to the state-of-the-art software framework running on NVIDIA GPU T4 and GPU A100, HiHGNN respectively achieves an average 40.0× and 8.3× speedup as well as 99.59% and 99.74% energy reduction with quintile the memory bandwidth of GPU A100.

14 February 2022 in IEEE Computer Architecture Letters
Verified
Journal Article
Closed access
MZMo Zou
Mo Zou
MZMingzhe Zhang
Mingzhe Zhang
RWRujia Wang
Rujia Wang
XSXian-He Sun
Xian-He Sun
XYXiaochun Ye
Xiaochun Ye
ZTZhimin Tang
Zhimin Tang
Graph processing is a vital component in various application domains. However, a good graph processing performance is hard to achieve due to its intensive irregular data accesses. Noticing that in real-world graphs, a small portion of vertices occupy most connections, several techniques are proposed to reorder vertices based on their access frequency for better data access locality. However, these approaches can be further improved by identifying reordered data more effectively, which will reduce reordering overhead and improve overall performance. In this letter, we propose Learning-Based Reordering (LBR) , a novel lightweight framework that identifies and reorders hot data adaptively for given graphs, algorithms, and threads. Our experimental evaluation indicates that LBR decreases reordering overhead by 24.7% while improves performance by 9.9% compared to the best-performing existing scheme.

11 January 2023
Verified
Book Chapter
Closed access
PDF file
MZMo Zou
Mo Zou
MYMingyu Yan
Mingyu Yan
WLWenming Li
Wenming Li
ZTZhimin Tang
Zhimin Tang
XYXiaochun Ye
Xiaochun Ye
DFDongrui Fan
Dongrui Fan

9 May 2025 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
XLXiming Liu
Ximing Liu
YZYongwei Zhao
Yongwei Zhao
MZMo Zou
Mo Zou
YLYang Liu
Yang Liu
YHYifan Hao
Yifan Hao
TCTianshi Chen
Tianshi Chen
Chiplet-based DNN accelerators have been extensively explored to save design and manufacturing costs. Previous works regard all chiplets as identical and employ uniform workload partitioning strategies. These workload partitioning strategies overlook various real-world factors that contribute to remarkable performance variations among chiplets, including manufacturing process variation, thermal condition, physical placement, and power supply condition. When considering these performance variations, a variation-aware workload partitioning can achieve superior performance. This article introduces VariPar, a systematic framework to employ variation-aware partitioning strategy in chiplet-based DNN accelerators. VariPar models performance variations for each chiplet and partition workloads accordingly. VariPar includes a simulator with multifactor variation modeling and a heuristic search engine to generate near-optimal partitioning within a reasonable time. Experiment results show that VariPar achieves $1.45{\times }$ performance and $1.82{\times }$ energy efficiency improvement on average when compared to uniform partitioning (UP) strategy.