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-GPU Graph Analytics
We present a single-node, multi-GPU programmable graph processing library that allows programmers to easily extend single-GPU graph algorithms to achieve scalable performance on large graphs with billions of edges. Directly using the single-GPU implementations, our design only requires programmers to specify a few algorithm-dependent concerns, hiding most multi-GPU related implementation details. We analyze the theoretical and practical limits to scalability in the context of varying graph primitives and datasets. We describe several optimizations, such as direction optimizing traversal, and a just-enough memory allocation scheme, for better performance and smaller memory consumption. Compared to previous work, we achieve best-of-class performance across operations and datasets, including excellent strong and weak scalability on most primitives as we increase the number of GPUs in the system.
more »
« less
- PAR ID:
- 10026456
- Date Published:
- Journal Name:
- Proceedings of the 31st IEEE International Parallel and Distributed Processing Symposium
- Page Range / eLocation ID:
- 479–490
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Constructing k-nearest neighbor (kNN) graphs is a fundamental component in many machine learning and scientific computing applications. Despite its prevalence, efficiently building all-nearest-neighbor graphs at scale on distributed heterogeneous HPC systems remains challenging, especially for large sparse non-integer datasets. We introduce optimizations for algorithms based on forests of random projection trees. Our novel GPU kernels for batched, within leaf, exact searches achieve 1.18× speedup over sparse reference kernels with less peak memory, and up to 19× speedup over CPU for memory-intensive problems. Our library,PyRKNN, implements distributed randomized projection forests for approximate kNN search. Optimizations to reduce and hide communication overhead allow us to achieve 5× speedup, in per iteration performance, relative to GOFMM (another projection tree, MPI-based kNN library), for a 64M 128d dataset on 1,024 processes. On a single-node we achieve speedup over FAISS-GPU for dense datasets and up to 10× speedup over CPU-only libraries.PyRKNNuniquely supports distributed memory kNN graph construction for both dense and sparse coordinates on CPU and GPU accelerators.more » « less
-
null (Ed.)High-performance implementations of graph algorithms are challenging to implement on new parallel hardware such as GPUs because of three challenges: (1) the difficulty of coming up with graph building blocks, (2) load imbalance on parallel hardware, and (3) graph problems having low arithmetic intensity. To address some of these challenges, GraphBLAS is an innovative, on-going effort by the graph analytics community to propose building blocks based on sparse linear algebra, which allow graph algorithms to be expressed in a performant, succinct, composable, and portable manner. In this paper, we examine the performance challenges of a linear-algebra-based approach to building graph frameworks and describe new design principles for overcoming these bottlenecks. Among the new design principles is exploiting input sparsity, which allows users to write graph algorithms without specifying push and pull direction.Exploiting output sparsityallows users to tell the backend which values of the output in a single vectorized computation they do not want computed. Load-balancing is an important feature for balancing work amongst parallel workers. We describe the important load-balancing features for handling graphs with different characteristics. The design principles described in this paper have been implemented in “GraphBLAST”, the first high-performance linear algebra-based graph framework on NVIDIA GPUs that is open-source. The results show that on a single GPU, GraphBLAST has on average at least an order of magnitude speedup over previous GraphBLAS implementations SuiteSparse andGBTL, comparable performance to the fastest GPU hardwired primitives and shared-memory graph frameworks Ligra and Gunrock, and better performance than any other GPU graph framework ,while offering a simpler and more concise programming model.more » « less
-
Finding from a big graph those subgraphs that satisfy certain conditions (aka. subgraph search) is useful in many applications such as community detection and subgraph matching. These problems often generate a search-space tree with size exponential to the size of the input graph. GPUs with thousands of cores are a natural choice to speed up subgraph search, but existing GPU solutions either conduct BFS on the search-space tree which leads to memory overflow due to intermediate subgraph-size explosion, or they conduct DFS on the search-space tree which is memory-efficient but can be 2 orders of magnitude slower than a BFS solution. In this paper, we present G2-AIMD, a subgraph-centric framework for efficient subGraph Search on GPUs, which enjoys the efficiency of BFS on the search-space tree, while avoids intermediate subgraph-size explosion with novel system designs such as adaptive chunk-size adjustment and host-memory subgraph buffering, inspired by the additive-increase/multiplicative-decrease (AIMD) algorithm in TCP congestion control. G2-AIMD provides a convenient subgraph-centric programming interface to facilitate the implementation of subgraph search algorithms on top, so as to enjoy the above performance merits. G2-AIMD also supports multi-GPU execution where each GPU only needs to load a fraction of the input graph. To demonstrate the efficiency and scalability of G2-AIMD, two algorithms were implemented on top with additional optimization techniques, and they significantly outperform the existing GPU solutions.more » « less
-
Programming to achieve high performance for NVIDIA GPUs using CUDA has been known to be challenging. A GPU has hundreds or thousands of cores that a program must exhibit sufficient parallelism to achieve maximum GPU utilization. A system with GPU accelerators has a heterogeneous and deep memory system that programmers must effectively and correctly use to fully take advantage of the GPU's parallelism capability. In this paper, we present CUDAMicroBench, a collection of fourteen microbenchmarks that demonstrate performance challenges in CUDA programming and techniques to optimize the CUDA programs to address these challenges. It also includes examples and techniques for using advanced CUDA features such as data shuffling between threads, dynamic parallelism, etc that can help users optimize the CUDA program for performance. The microbenchmark can be used for evaluating the performance of GPU architectures, the memory systems of GPU itself and of the whole system architectures, and for evaluating the effectiveness of compiler and performance tools for performance analysis. It can be used to help users understand the complexity of heterogeneous GPU-accelerator systems through examples and guide users for performance optimization. It is released as BSD-licensed open-source from https://github.com/passlab/CUDAMicroBench.git.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/IPDPS.2017.117
