An official website of the United States government
IntroductionReconstructing low-level particle tracks in neutrino physics can address some of the most fundamental questions about the universe. However, processing petabytes of raw data using deep learning techniques poses a challenging problem in the field of High Energy Physics (HEP). In the Exa.TrkX Project, an illustrative HEP application, preprocessed simulation data is fed into a state-of-art Graph Neural Network (GNN) model, accelerated by GPUs. However, limited GPU memory often leads to Out-of-Memory (OOM) exceptions during training, due to the large size of models and datasets. This problem is exacerbated when deploying models on High-Performance Computing (HPC) systems designed for large-scale applications. MethodsWe observe a high workload imbalance issue during GNN model training caused by the irregular sizes of input graph samples in HEP datasets, contributing to OOM exceptions. We aim to scale GNNs on HPC systems, by prioritizing workload balance in graph inputs while maintaining model accuracy. Our paper introduces diverse balancing strategies aimed at decreasing the maximum GPU memory footprint and avoiding the OOM exception, across various datasets. ResultsOur experiments showcase memory reduction of up to 32.14% compared to the baseline. We also demonstrate the proposed strategies can avoid OOM in application. Additionally, we create a distributed multi-GPU implementation using these samplers to demonstrate the scalability of these techniques on the HEP dataset. DiscussionBy assessing the performance of these strategies as data loading samplers across multiple datasets, we can gauge their effectiveness in both single-GPU and distributed environments. Our experiments, conducted on datasets of varying sizes and across multiple GPUs, broaden the applicability of our work to various GNN applications that handle input datasets with irregular graph sizes.
more »
« less
Multi-dimensional balanced graph partitioning via projected gradient descent
Motivated by performance optimization of large-scale graph processing systems that distribute the graph across multiple machines, we consider the balanced graph partitioning problem. Compared to most of the previous work, we study the multi-dimensional variant in which balance according to multiple weight functions is required. As we demonstrate by experimental evaluation, such multi-dimensional balance is essential for achieving performance improvements for typical distributed graph processing workloads. We propose a new scalable technique for the multidimensional balanced graph partitioning problem. It is based on applying randomized projected gradient descent to a non-convex continuous relaxation of the objective. We show how to implement the new algorithm efficiently in both theory and practice utilizing various approaches for the projection step. Experiments with large-scale graphs containing up to hundreds of billions of edges indicate that our algorithm has superior performance compared to the state of the art.
more »
« less
- Award ID(s):
- 1657477
- PAR ID:
- 10303543
- Date Published:
- Journal Name:
- Proceedings of the VLDB Endowment
- Volume:
- 12
- Issue:
- 8
- ISSN:
- 2150-8097
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Balanced graph partitioning is a critical step for many large-scale distributed computations with relational data. As graph datasets have grown in size and density, a range of highly-scalable balanced partitioning algorithms have appeared to meet varied demands across different domains. As the starting point for the present work, we observe that two recently introduced families of iterative partitioners---those based on restreaming and those based on balanced label propagation (including Facebook's Social Hash Partitioner)---can be viewed through a common modular framework of design decisions. With the help of this modular perspective, we find that a key combination of design decisions leads to a novel family of algorithms with notably better empirical performance than any existing highly-scalable algorithm on a broad range of real-world graphs. The resulting prioritized restreaming algorithms employ a constraint management strategy based on multiplicative weights, borrowed from the restreaming literature, while adopting notions of priority from balanced label propagation to optimize the ordering of the streaming process. Our experimental results consider a range of stream orders, where a dynamic ordering based on what we call ambivalence is broadly the most performative in terms of the cut quality of the resulting balanced partitions, with a static ordering based on degree being nearly as good.more » « less
-
Large-scale graph analytics has become increasingly common in areas like social networks, physical sciences, transportation networks, and recommendation systems. Since many such practical graphs do not fit in main memory, graph analytics performance depends on efficiently utilizing underlying storage devices. These out-of-core graph processing systems employ sharding and sub-graph partitioning to optimize for storage while relying on efficient sequential access of traditional hard disks. However, today's storage is increasingly based on solid-state drives (SSDs) that exhibit high internal parallelism and efficient random accesses. Yet, state-of-the-art graph processing systems do not explicitly exploit those properties, resulting in subpar performance. In this paper, we develop CAVE, the first graph processing engine that optimally exploits underlying SSD-based storage by harnessing the available storage device parallelism via carefully selecting which I/Os to graph data can be issued concurrently. Thus, CAVE traverses multiple paths and processes multiple nodes and edges concurrently, achieving parallelization at a granular level. We identify two key ways to parallelize graph traversal algorithms based on the graph structure and algorithm: intra-subgraph and inter-subgraph parallelization. The first identifies subgraphs that contain vertices that can be accessed in parallel, while the latter identifies subgraphs that can be processed in their entirety in parallel. To showcase the benefit of our approach, we build within CAVE parallelized versions of five popular graph algorithms (Breadth-First Search, Depth-First Search, Weakly Connected Components, PageRank, Random Walk) that exploit the full bandwidth of the underlying device. CAVE uses a blocked file format based on adjacency lists and employs a concurrent cache pool that is essential to the parallelization of graph algorithms. By experimenting with different types of graphs on three SSD devices, we demonstrate that CAVE utilizes the available parallelism, and scales to diverse real-world graph datasets. CAVE achieves up to one order of magnitude speedup compared to the popular out-of-core systems Mosaic and GridGraph, and up to three orders of magnitude speedup in runtime compared to GraphChi.more » « less
-
null (Ed.)We develop GeoMatch as a novel, scalable, and efficient big-data pipeline for large-scale map matching on Apache Spark. GeoMatch improves existing spatial big-data solutions by utilizing a novel spatial partitioning scheme inspired by Hilbert space-filling curves. Thanks to its partitioning scheme, GeoMatch can effectively balance operations across different processing units and achieve significant performance gains. GeoMatch also incorporates a dynamically adjustable error-correction technique that provides robustness against positioning errors. We demonstrate the effectiveness of GeoMatch through rigorous and extensive empirical benchmarks that consider large-scale urban spatial datasets ranging from 166,253 to 3.78B location measurements. We separately assess execution performance and accuracy of map matching and develop a benchmark framework for evaluating large-scale map matching. Results of our evaluation show up to 27.25-fold performance improvements compared to previous works while achieving better processing accuracy than current solutions. We also showcase the practical potential of GeoMatch with two urban management applications. GeoMatch and our benchmark framework are open-source.more » « less
-
A skyline query searches the data points that are not dominated by others in the dataset. It is widely adopted for many applications which require multi-criteria decision making. However, skyline query processing is considerably time-consuming for a high-dimensional large scale dataset. Parallel computing techniques are therefore needed to address this challenge, among which MapReduce is one of the most popular frameworks to process big data. A great number of efficient MapReduce skyline algorithms have been proposed in the literature and most of their designs focus on partitioning and pruning the given dataset. However, there are still opportunities for further parallelism. In this study, we propose two parallel skyline processing algorithms using a novel LShape partitioning strategy and an effective Propagation Filtering method. These two algorithms are 2Phase LShape and 1Phase LShape, used for multiple reducers and single reducer, respectively. By extensive experiments, we verify that our algorithms outperformed the state-of-the-art approaches, especially for high-dimensional large scale datasets.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.14778/3324301.3324307
