Quantifying the Performance Impact of Graph Structure on Neighbour Iteration Strategies for PageRank

Verstraaten, Merijn; Vărbănescu, Ana Lucia; Laat, Cees de

doi:10.1007/978-3-319-27308-2_43

Cited by 7 publications

(8 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the use of the static deployment model has negative consequences. Conceptually, graph applications are a poor fit for static, fixed-size infrastructure, as they have often iterative, but highly irregular workloads [3]. Previous techniques do not focus on a dynamic model of deployment, where infrastructure can grow and shrink to match the needs of the graph-processing application.…”

Section: Problem Statement and Conceptual Contributionmentioning

confidence: 99%

“…Typically, when making a case for elasticity [9] in graph processing, only graph-related metrics are considered, such as active vertices, or messages exchanged per super-step. Many complementary studies present an analysis on how the number of active vertices affects the algorithm efficiency: directionoptimizing BFS [10] is a technique entirely motivated by the variable number of active edges per iteration; Mizan [11] analyzes runtime per iteration and addresses the large imbalance; GraphReduce [12] leverages the observed variability in the number of active vertices (frontier size) for two datasets and three algorithms; high workload imbalance appears even between multiple designs and implementations of the same algorithm running the same workload [3]; etc. In contrast, we also analyze the impact of workload imbalance on the consumption of system-level resources.…”

Section: Problem Statement and Conceptual Contributionmentioning

confidence: 99%

See 1 more Smart Citation

An Elasticity Study of Distributed Graph Processing

Uta

Ilyushkin

et al. 2018

2018 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID)

View full text Add to dashboard Cite

Graphs are a natural fit for modeling concepts used in solving diverse problems in science, commerce, engineering, and governance. Responding to the variety of graph data and algorithms, many parallel and distributed graph-processing systems exist. However, until now these platforms use a static model of deployment: they only run on a pre-defined set of machines. This raises many conceptual and pragmatic issues, including misfit with the highly dynamic nature of graph processing, and could lead to resource waste and high operational costs. In contrast, in this work we explore a dynamic, elastic model of deployment. To conduct an in-depth elasticity study of distributed graph processing, we build a prototype, JoyGraph, which is the first such system that implements complex, policy-based, and finegrained elasticity. Using the state-of-the-art LDBC Graphalytics benchmark and the SPEC Cloud Group's elasticity metrics, we show the benefits of elasticity in graph processing: improved resource utilization, and aligned operation-workload dynamicity. Furthermore, we explore the cost of elasticity in graph processing. We identify a key drawback: although elasticity does not degrade application throughput, graph-processing workloads are sensitive to data movement while leasing or releasing resources.

show abstract

Section: Problem Statement and Conceptual Contributionmentioning

confidence: 99%

Section: Problem Statement and Conceptual Contributionmentioning

confidence: 99%

An Elasticity Study of Distributed Graph Processing

Uta

Ilyushkin

et al. 2018

2018 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID)

View full text Add to dashboard Cite

show abstract

“…GraphReduce [28] finds large variability in the number of active vertices (frontier size) for two datasets and three algorithms. High workload imbalance appears even between multiple designs and implementations of the same algorithm running the same workload [17]. In comparison, in this section we further analyze the impact of workload imbalance on the consumption of system-level resources.…”

Section: Variability In Graph Processingmentioning

confidence: 99%

“…The use of the static deployment model has negative consequences. Conceptually, graph applications are a poor fit for static, fixed-size infrastructure, because they have often iterative, but highly irregular workloads [5], [7], [17]. Pragmatically, even experts face difficult choices based on empirical approaches to estimate the size of the needed infrastructure; there are serious consequences when the choice is inaccurate, ranging from system-wide crashing when resources are underprovisioned [18], to possibly high resource waste and operational costs when the system is over-provisioned.…”

Section: Introductionmentioning

confidence: 99%

Elasticity in Graph Analytics? A Benchmarking Framework for Elastic Graph Processing

Uta

Ilyushkin

et al. 2018

2018 IEEE International Conference on Cluster Computing (CLUSTER)

View full text Add to dashboard Cite

Graphs are a natural fit for modeling concepts used in solving diverse problems in science, commerce, engineering, and governance. Responding to the diversity of graph data and algorithms, many parallel and distributed graph-processing systems exist. However, until now these platforms use a static model of deployment: they only run on a pre-defined set of machines. This raises many conceptual and pragmatic issues, including misfit with the highly dynamic nature of graph processing, and could lead to resource waste and high operational costs. In contrast, in this work we explore the benefits and drawbacks of the dynamic model of deployment. Building a threelayer benchmarking framework for assessing elasticity in graph analytics, we conduct an in-depth elasticity study of distributed graph processing. Our framework is composed of state-ofthe-art workloads, autoscalers, and metrics, derived from the LDBC Graphalytics benchmark and SPEC RG Cloud Group's elasticity metrics. We uncover the benefits and cost of elasticity in graph processing: while elasticity allows for fine-grained resource management, and does not degrade application performance, we find that graph workloads are sensitive to data migration while leasing or releasing resources. Moreover, we identify non-trivial interactions between scaling policies and graph workloads, which add an extra level of complexity to resource management and scheduling for graph processing.

show abstract

“…Although many works utilize GPU to accelerate the computations of PageRank, former study rarely focuses on speeding up local PageRank problem through GPU. Previous work utilizes GPU to speed up local PageRank computations in Lai et al However, it is still an issue that the dangling vertices restrict scope of usage.…”

Section: Introductionmentioning

confidence: 99%

Parallel computations of local PageRank problem based on Graphics Processing Unit

Lai

Shao

et al. 2017

Concurrency and Computation

View full text Add to dashboard Cite

Summary In this paper, we study the issue of improving the performance of Markov chain Monte Carlo method to solve local PageRank problem under General Purpose Graphics Processing Unit environment. As a large number of dangling vertices cause large storage space of dangling vertices and thus slow down the Markov chain procession, we propose a reordering strategy to compress the storage space and reduce the computational complexity of Markov chain procession. In our performance study, by parallelizing and optimizing the proposed algorithm based on GPU, the reordering strategy can be up 12× faster compared with basic method, where the graphs have high‐proportion dangling vertices. According to our investigation on this issue, the variance of random walks determines the number of random walks in the computation; we thus introduce low‐discrepancy sequences to enhance the performance. Moreover, the low‐discrepancy sequences are organized to load in the on‐chip shared memory to accelerate fetching with a wise warp scheduling for bank conflict schema. A series of experiments have been conducted to evaluate the optimization efficiency. Compared with fetching data from off‐chip global memory, the shared‐memory‐based strategy can have over 10× speedup ratio performance. The experiments indicate that the size of shared memory has a significant impact on the parallelism of the proposed method as well.

show abstract

Quantifying the Performance Impact of Graph Structure on Neighbour Iteration Strategies for PageRank

Cited by 7 publications

References 14 publications

An Elasticity Study of Distributed Graph Processing

An Elasticity Study of Distributed Graph Processing

Elasticity in Graph Analytics? A Benchmarking Framework for Elastic Graph Processing

Parallel computations of local PageRank problem based on Graphics Processing Unit

Contact Info

Product

Resources

About