A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Filters
How Well Do Graph-Processing Platforms Perform? An Empirical Performance Evaluation and Analysis
2014
2014 IEEE 28th International Parallel and Distributed Processing Symposium
Preserved Fulltext
To alleviate this challenge, we propose an empirical method for benchmarking graph-processing platforms. ...
Thus, users face the daunting challenge of selecting an appropriate platform for their specific application. ...
GraphLab stores the entire graph and all program state in memory. ...
doi:10.1109/ipdps.2014.49
dblp:conf/ipps/GuoBVIMW14
fatcat:rqes3axydvdl7cejaek72dzjem
Pregelix: Big(ger) Graph Analytics on A Dataflow Engine
[article]
2014
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
There is a growing need for distributed graph processing systems that are capable of gracefully scaling to very large graph datasets. ...
., we have seen up to 15x speedup compared to Apache Giraph and up to 35x speedup compared to distributed GraphLab), and makes more effective use of available machine resources to support Big(ger) Graph ...
Finally, we thank Raghu Ramakrishnan for the early discussion of this work as well as the sponsorship for our access to the Yahoo! cluster for scale-testing early versions of the system. ...
arXiv:1407.0455v1
fatcat:gq6jqcmptbejjfslnee5wdaouu
Pregelix
2014
Proceedings of the VLDB Endowment
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit the original URL.
The file type is application/pdf.
There is a growing need for distributed graph processing systems that are capable of gracefully scaling to very large graph datasets. ...
., we have seen up to 15× speedup compared to Apache Giraph and up to 35× speedup compared to distributed GraphLab), and more effective use of available machine resources to support Big(ger) Graph Analytics ...
Finally, we thank Raghu Ramakrishnan for discussing this work with us and sponsoring our access to a Yahoo! cluster for scale-testing early versions of the system. ...
doi:10.14778/2735471.2735477
fatcat:bx5bfbo24fhdnnxnpvyfnkn2ci
LFGraph
2013
Proceedings of the First ACM SIGOPS Conference on Timely Results in Operating Systems - TRIOS '13
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
We present LFGraph, a fast, scalable, distributed, in-memory graph analytics engine intended primarily for directed graphs. LFGraph is the first system to satisfy all of the above requirements. ...
Distributed graph analytics frameworks must offer low and balanced communication and computation, low preprocessing overhead, low memory footprint, and scalability. ...
Acknowledgements: We thank our shepherd Benjamin Wester and anonymous reviewers for their insightful comments and suggestions. ...
doi:10.1145/2524211.2524218
dblp:conf/sosp/HoqueG13
fatcat:nrls3wmvkbhglddqzsyetom44u
From "think like a vertex" to "think like a graph"
2013
Proceedings of the VLDB Endowment
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
This vertex-centric model is easy to program and has been proved useful for many graph algorithms. ...
To meet the challenge of processing rapidly growing graph and network data created by modern applications, a number of distributed graph processing systems have emerged, such as Pregel and GraphLab. ...
Giraph++ uses Netty or Hadoop RPC for communication, whereas GraphLab uses MPI) and the use of different programming languages (Giraph++ in Java and GraphLab in C++) contribute a great deal to the difference ...
doi:10.14778/2732232.2732238
fatcat:6xnz5bqxcvcu7o3rpbiw5qfq4i
BigSparse: High-performance external graph analytics
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
for terabyte-size graphs with billions of vertices. ...
In our experiments on a server with 32GB to 64GB of DRAM, BigSparse outperforms other in-memory and semi-external graph analytics systems for algorithms such as PageRank, BreadthFirst Search, and Betweenness-Centrality ...
Many prominent graph analytics platforms, including Pregel [13] and GraphLab [11] , expose a vertex-centric programming model because of its ease of distributed execution. ...
arXiv:1710.07736v1
fatcat:3rlvy45dtzazjecsqiilg2vgeu
Beyond Triangles: A Distributed Framework for Estimating 3-profiles of Large Graphs
[article]
2015
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Our algorithm is distributed and operates as a vertex program over the GraphLab PowerGraph framework. ...
Our algorithm uses the novel concept of 3-profile sparsifiers: sparse graphs that can be used to approximate the full 3-profile counts for a given large graph. ...
Pregel, GraphLab, Galois, GraphX, see [30] for a comparison) are frameworks for expressing distributed computation on graphs in the language of vertex programs. ...
arXiv:1506.06671v1
fatcat:hr4pbfp6ezffjiwz7sfkz6xmzq
Beyond Triangles
2015
Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '15
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit the original URL.
The file type is application/pdf.
Our algorithm is distributed and operates as a vertex program over the GraphLab framework. ...
Our algorithm uses the novel concept of 3-profile sparsifiers: sparse graphs that can be used to approximate the full 3-profile counts for a given large graph. ...
Pregel, GraphLab, Galois, GraphX, see [30] for a comparison) are frameworks for expressing distributed computation on graphs in the language of vertex programs. ...
doi:10.1145/2783258.2783413
dblp:conf/kdd/ElenbergSBD15
fatcat:ccyhwydbebe5jbifh3juuo5fjq
Distributed Programming over Time-Series Graphs
2015
2015 IEEE International Parallel and Distributed Processing Symposium
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2014 pre-print arXiv:1406.5975v1 fatcat:e23bx7zv5nbdbks55m43iywhci
We examine storage optimizations for GoFS, design patterns in Gopher to leverage the distributed data layout, and evaluate the GoFFish platform using time-series graph data and applications on a commodity ...
Gopher is co-designed with GoFS, a distributed storage specialized for time-series graphs, as part of the GoFFish distributed analytics platform. ...
Google recently proposed the Pregel model [8] of vertex centric programming for large scale graph processing, which also has similarities with GraphLab [18] . ...
doi:10.1109/ipdps.2015.66
dblp:conf/ipps/SimmhanCWKFRP15
fatcat:3kvc46tdbjftjohwyxmy2cptea
Big Graph Analytics Platforms
2017
Foundations and Trends in Databases
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
First, there is often interest in doing temporal analysis over historical traces of graphs, often called time-evolving graphs or historical graphs; examples of such analysis tasks include network evolution ...
GraphChi GraphChi was proposed as a single-PC counterpart to distributed GraphLab, which keeps the GAS programming model but eliminates the requirement of a cluster of machines with large cumulative main ...
Two thread pools are maintained in TurboGraph, one for the execution threads, and the other for the asynchronous I/O callback threads. ...
doi:10.1561/1900000056
fatcat:ucqrtzo4q5g2lpj6dmp7jv3e5m
Intel "big data" science and technology center vision and execution plan
2013
SIGMOD record
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2014; you can also visit the original URL.
The file type is application/pdf.
This paper presents the big data vision of this technology center and the execution plan for the first few years. ...
Intel held a national competition for a 5th Science and Technology center in 2012 and selected a proposal from M.I.T. with a theme of "Big Data". ...
We are also exploring visualization of large data sets and efficient algorithms for complex analysis. ...
doi:10.1145/2481528.2481537
fatcat:cfufdakydbfkfdjk2yftm572la
Characterizing Application Memory Error Vulnerability to Optimize Datacenter Cost via Heterogeneous-Reliability Memory
2014
2014 44th Annual IEEE/IFIP International Conference on Dependable Systems and Networks
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2015; you can also visit the original URL.
The file type is application/pdf.
Existing approaches to providing reliability for memory devices pessimistically treat all data as equally vulnerable to memory errors. ...
This presents an opportunity to greatly reduce server hardware cost by provisioning the right amount of memory reliability for different applications. ...
We thank the anonymous reviewers and the members of SAFARI research group for feedback. We acknowledge the support of Microsoft and Samsung. ...
doi:10.1109/dsn.2014.50
dblp:conf/dsn/LuoGSSMKLKVM14
fatcat:57c4bkj3brha7jbzxosrrfwucu
Toward Scalable Systems for Big Data Analytics: A Technology Tutorial
2014
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
More complex analysis for production workload traces can be found in the authors' subsequent research [289] . Ghazal et al. ...
GraphLab proposes three consistency models, full, edge, and vertex consistency, to allow for different levels of parallelism. • Stream Processing Model: S4 [36] and Storm [35] are two distributed stream ...
doi:10.1109/access.2014.2332453
fatcat:6unxlocbmnhs7mfctlvphdyqtu
Systems and Algorithms for Large-scale Graph Analytics (Dagstuhl Seminar 14462)
2015
Dagstuhl Reports
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
This report documents the program and the outcomes of Dagstuhl Seminar 14462 "Systems and Algorithms for Large-scale Graph Analytics". ...
We also thank Karthik Nilakant and Valentin Dalibard for their help with editing the report. ...
We thank Derek Murray for his great contribution to the organization of the workshop and participation via Skype as he could not travel because of the sudden set down of Microsoft Research Silicon Valley ...
doi:10.4230/dagrep.4.11.59
dblp:journals/dagstuhl-reports/Yoneki0M14
fatcat:dilicps65jgipetfid3udj2q4i
Views and Transactional Storage for Large Graphs
[chapter]
2013
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
We present Concerto, a graph store based on distributed, in-memory data structures. ...
Using graph views, programmers can perform event-driven analysis and dynamically optimize application performance. ...
We thank the anonymous reviewers for their valuable feedback. Part of this research was sponsored by the DARPA GRAPHS program (BAA-12-01). ...
doi:10.1007/978-3-642-45065-5_15
fatcat:vvzx3ptnnje5xivuzpmwgfxyze
« Previous
Showing results 1 — 15 out of 99 results