https://kalper.net/kp/tag/graph-generation/ Graph Generation Wowchemy (https://wowchemy.com)en-usFri, 01 Jul 2022 00:00:00 +0000 https://kalper.net/kp/media/logo_hu7c4e9283a16f91dce013794dd725bda5_36458_300x300_fit_lanczos_3.png https://kalper.net/kp/tag/graph-generation/ https://kalper.net/kp/items/research/graphs/ Fri, 01 Jul 2022 00:00:00 +0000 https://kalper.net/kp/items/research/graphs/ <p>Parallel/Distributed implementation (1000s of GPUs), Graph algorithms, Graph Generation on multiple GPUs, Community detection-based solutions</p> <h2 id="overview">Overview</h2> <p>See <a href="../../../tag/graph">all items tagged <strong>Graph</strong></a></p> <ul> <li>Very large network generation (trillion-edge)</li> <li>Very fast network generation <ul> <li>GPU-based scalable algorithms</li> <li>Billion of edges per second</li> </ul> </li> <li>Scale-free and distribution-conformant networks</li> <li>Community detection-based applications <ul> <li>Electric grid distribution network inference</li> </ul> </li> </ul> <div class="gallery" style="text-align: center;"> <a data-fancybox="gallery-graphs" href="https://kalper.net/kp/kp/items/research/graphs/images/grid-community-detection-12.png" > <img src="https://kalper.net/kp/kp/items/research/graphs/images/grid-community-detection-12_huc48cb079c45c67c4edabc788eb577aaa_3408691_500x0_resize_q90_lanczos_3.png" loading="lazy" alt="grid-community-detection-12.png" width="500" height="297"> </a> <a data-fancybox="gallery-graphs" href="https://kalper.net/kp/kp/items/research/graphs/images/trillion-edge.png" > <img src="https://kalper.net/kp/kp/items/research/graphs/images/trillion-edge_hu2673e3bfde490bc506a90053934099ab_180871_500x0_resize_q90_lanczos_3.png" loading="lazy" alt="trillion-edge.png" width="500" height="300"> </a> </div> <h2 id="related-publications">Related Publications</h2> <p> <div class="media stream-item"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> <a href="https://kalper.net/kp/kp/publication/2021-11-01-frontiers-netgen/" >Fast GPU-Based Generation of Large Graph Networks From Degree Distributions</a> </div> <a href="https://kalper.net/kp/kp/publication/2021-11-01-frontiers-netgen/" class="summary-link"> <div class="article-style"> A novel algorithm has been designed, developed, and implemented on modern GPU accelerators, and benchmarked on networks with billions of edges, including Facebook and Twitter networks. Rates of generation exceed 50 billion edges per second. </div> </a> <div class="stream-meta article-metadata"> <div> <span > <a href="https://kalper.net/kp/kp/author/maksudul-alam/">Maksudul Alam</a></span>, <span class="author-highlighted"> <a href="https://kalper.net/kp/kp/author/kalyan-perumalla/">Kalyan Perumalla</a></span><i class="author-notes fas fa-info-circle" data-toggle="tooltip" title="Corresponding Author"></i> </div> </div> <div class="btn-links"> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://kalper.net/kp/kp/publication/2021-11-01-frontiers-netgen/2021-11-01-Frontiers-Netgen.pdf" target="_blank" rel="noopener"> PDF </a> <a href="#" class="btn btn-outline-primary btn-page-header btn-sm js-cite-modal" data-filename="/kp/publication/2021-11-01-frontiers-netgen/cite.bib"> Cite </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://doi.org/10.3389/fdata.2021.737963" target="_blank" rel="noopener"> DOI </a> </div> </div> <div class="ml-3"> <a href="https://kalper.net/kp/kp/publication/2021-11-01-frontiers-netgen/" > <img src="https://kalper.net/kp/kp/publication/2021-11-01-frontiers-netgen/featured_hu161706106d37a15beb50728bd4a69633_115864_150x0_resize_lanczos_3.png" alt="Fast GPU-Based Generation of Large Graph Networks From Degree Distributions" loading="lazy"> </a> </div> </div> <div class="media stream-item"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> <a href="https://kalper.net/kp/kp/publication/2020-11-01-cuppa/" >Scale-Free Graph Networks with Trillions of Edges: Rapid Generation using 1000 GPUs</a> </div> <a href="https://kalper.net/kp/kp/publication/2020-11-01-cuppa/" class="summary-link"> <div class="article-style"> Our algorithm <strong>cuPPA</strong> generates scale-free networks using the preferential-attachment model, custom-designed to exploit multiple GPUs. We generate extremely large scale-free networks of <strong>4 trillion edges</strong> in less than 8 minutes using 1,008 NVIDIA Volta GPUs of the Summit supercomputer. This represents the first ever graph network generation at this scale of parallel execution with over thousand GPUs. Moreover, our algorithm is uniquely suitable for generating networks in a <em>streaming mode</em> without the need for explicitly storing (writing to disk) the entire network, and is suitable for targeting even larger scales with quadrillions of edges. </div> </a> <div class="stream-meta article-metadata"> <div> <span > <a href="https://kalper.net/kp/kp/author/maksudul-alam/">Maksudul Alam</a></span>, <span class="author-highlighted"> <a href="https://kalper.net/kp/kp/author/kalyan-perumalla/">Kalyan Perumalla</a></span> </div> </div> <div class="btn-links"> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://kalper.net/kp/kp/publication/2020-11-01-cuppa/2020-11-01-cuPPA.pdf" target="_blank" rel="noopener"> PDF </a> </div> </div> <div class="ml-3"> <a href="https://kalper.net/kp/kp/publication/2020-11-01-cuppa/" > <img src="https://kalper.net/kp/kp/publication/2020-11-01-cuppa/featured_hu2673e3bfde490bc506a90053934099ab_180871_150x0_resize_lanczos_3.png" alt="Scale-Free Graph Networks with Trillions of Edges: Rapid Generation using 1000 GPUs" loading="lazy"> </a> </div> </div> <div class="media stream-item"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> <a href="https://kalper.net/kp/kp/publication/2020-09-01-ornl-network/" >On the Robustness of Network Community Structure Under Addition of Edges</a> </div> <a href="https://kalper.net/kp/kp/publication/2020-09-01-ornl-network/" class="summary-link"> <div class="article-style"> We study the impact of edge additions on the community structure using Lancichinetti-Fortunato-Radicchi (LFR) benchmark networks. We show that, for a fixed network size, the impact of edge additions is greater on networks with initially weak community structure than on networks with strongly clustered structures. Also, we find that the perception of the impact is also dependent on the community detection algorithm used to uncover communities. </div> </a> <div class="stream-meta article-metadata"> <div> <span > <a href="https://kalper.net/kp/kp/author/pablo-moriano/">Pablo Moriano</a></span>, <span class="author-highlighted"> <a href="https://kalper.net/kp/kp/author/kalyan-perumalla/">Kalyan Perumalla</a></span> </div> </div> <div class="btn-links"> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://kalper.net/kp/kp/publication/2020-09-01-ornl-network/2020-09-01-ornl-network.pdf" target="_blank" rel="noopener"> PDF </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://doi.org/10.2172/1661212" target="_blank" rel="noopener"> DOI </a> </div> </div> <div class="ml-3"> <a href="https://kalper.net/kp/kp/publication/2020-09-01-ornl-network/" > <img src="https://kalper.net/kp/kp/publication/2020-09-01-ornl-network/featured_hu7a999994bf10253f90dcd978293f9cf7_414746_150x0_resize_lanczos_3.png" alt="On the Robustness of Network Community Structure Under Addition of Edges" loading="lazy"> </a> </div> </div> <div class="media stream-item"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> <a href="https://kalper.net/kp/kp/publication/2019-03-30-dse-cuppa/" >Novel Parallel Algorithms for Fast Multi-GPU-Based Generation of Massive Scale-Free Networks</a> </div> <a href="https://kalper.net/kp/kp/publication/2019-03-30-dse-cuppa/" class="summary-link"> <div class="article-style"> A novel parallel algorithm, cuPPA, is presented for generating random scale-free networks using the preferential attachment model. The algorithm is custom-designed for &lsquo;single instruction multiple data (SIMD)&rsquo; for GPUs. Our algorithm is the first to exploit GPUs, and also the fastest implementation available today, for scale-free networks. On an NVidia GeForce 1080 GPU, cuPPA generates a scale-free network of two billion edges in less than 3 s. On multi-GPU platforms, cuPPA-Hash generates a scale-free network of 16 billion edges in less than 7 s using a machine consisting of 4 NVidia Tesla P100 GPUs. </div> </a> <div class="stream-meta article-metadata"> <div> <span > <a href="https://kalper.net/kp/kp/author/maksudul-alam/">Maksudul Alam</a></span>, <span class="author-highlighted"> <a href="https://kalper.net/kp/kp/author/kalyan-perumalla/">Kalyan Perumalla</a></span>, <span > <a href="https://kalper.net/kp/kp/author/peter-sanders/">Peter Sanders</a></span> </div> </div> <div class="btn-links"> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://kalper.net/kp/kp/publication/2019-03-30-dse-cuppa/2019-03-30-DSE-cuPPA.pdf" target="_blank" rel="noopener"> PDF </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://doi.org/10.1007/s41019-019-0088-6" target="_blank" rel="noopener"> DOI </a> </div> </div> <div class="ml-3"> <a href="https://kalper.net/kp/kp/publication/2019-03-30-dse-cuppa/" > <img src="https://kalper.net/kp/kp/publication/2019-03-30-dse-cuppa/featured_huef8fae5b7c4d39eaa41b269383f8fcd9_2813102_150x0_resize_lanczos_3.png" alt="Novel Parallel Algorithms for Fast Multi-GPU-Based Generation of Massive Scale-Free Networks" loading="lazy"> </a> </div> </div> <div class="media stream-item"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> <a href="https://kalper.net/kp/kp/publication/2017-12-11-ieee-cuppa-simd/" >GPU-based parallel algorithm for generating massive scale-free networks using the preferential attachment model</a> </div> <a href="https://kalper.net/kp/kp/publication/2017-12-11-ieee-cuppa-simd/" class="summary-link"> <div class="article-style"> A novel parallel algorithm, cuPPA, is presented for generating random scale-free networks using the preferential-attachment model. In one of the best cases, when executed on an NVidia GeForce 1080 GPU, cuPPA generates a scale-free network of two billion edges in less than 3 seconds. </div> </a> <div class="stream-meta article-metadata"> <div> <span > <a href="https://kalper.net/kp/kp/author/maksudul-alam/">Maksudul Alam</a></span>, <span class="author-highlighted"> <a href="https://kalper.net/kp/kp/author/kalyan-perumalla/">Kalyan Perumalla</a></span> </div> </div> <div class="btn-links"> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://kalper.net/kp/kp/publication/2017-12-11-ieee-cuppa-simd/2017-12-11-IEEE-cuPPA-SIMD.pdf" target="_blank" rel="noopener"> PDF </a> <a href="#" class="btn btn-outline-primary btn-page-header btn-sm js-cite-modal" data-filename="/kp/publication/2017-12-11-ieee-cuppa-simd/cite.bib"> Cite </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://kalper.net/kp/pubdocs/2017-12-11-IEEE-cuPPA-SIMD.pdf" target="_blank" rel="noopener"> Slides </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://doi.org/10.1109/BigData.2017.8258315" target="_blank" rel="noopener"> DOI </a> </div> </div> <div class="ml-3"> <a href="https://kalper.net/kp/kp/publication/2017-12-11-ieee-cuppa-simd/" > <img src="https://kalper.net/kp/kp/publication/2017-12-11-ieee-cuppa-simd/featured_hud81741b88a9a0d5c99bec271fe05ede2_126524_150x0_resize_lanczos_3.png" alt="GPU-based parallel algorithm for generating massive scale-free networks using the preferential attachment model" loading="lazy"> </a> </div> </div> <div class="media stream-item"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> <a href="https://kalper.net/kp/kp/publication/2017-10-01-ornl-tr-cuppa-simd/" >Generating Billion-Edge Scale-Free Networks in Seconds: Performance Study of a Novel GPU-based Preferential Attachment Model</a> </div> <a href="https://kalper.net/kp/kp/publication/2017-10-01-ornl-tr-cuppa-simd/" class="summary-link"> <div class="article-style"> A novel parallel algorithm is presented for generating random scale-free networks using the preferential-attachment model. In one of the best cases, when executed on an NVidia GeForce 1080 GPU, cuPPA generates a scale free network of a billion edges in less than 2 seconds. </div> </a> <div class="stream-meta article-metadata"> <div> <span class="author-highlighted"> <a href="https://kalper.net/kp/kp/author/kalyan-perumalla/">Kalyan Perumalla</a></span>, <span > <a href="https://kalper.net/kp/kp/author/maksudul-alam/">Maksudul Alam</a></span> </div> </div> <div class="btn-links"> <a href="#" class="btn btn-outline-primary btn-page-header btn-sm js-cite-modal" data-filename="/kp/publication/2017-10-01-ornl-tr-cuppa-simd/cite.bib"> Cite </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://doi.org/10.2172/1399438" target="_blank" rel="noopener"> DOI </a> </div> </div> <div class="ml-3"> </div> </div> <div class="media stream-item"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> <a href="https://kalper.net/kp/kp/publication/pub-100-garfield-evac-pads09/" >GPU-based Real-Time Execution of Vehicular Mobility Models in Large-Scale Road Network Scenarios </a> </div> <a href="https://kalper.net/kp/kp/publication/pub-100-garfield-evac-pads09/" class="summary-link"> <div class="article-style"> A methodology and its associated algorithms are presented for mapping a novel, field-based vehicular&hellip; </div> </a> <div class="stream-meta article-metadata"> <div> <span class="author-highlighted"> <a href="https://kalper.net/kp/kp/author/kalyan-perumalla/">Kalyan Perumalla</a></span>, <span > <a href="https://kalper.net/kp/kp/author/brandon-aaby/">Brandon Aaby</a></span>, <span > <a href="https://kalper.net/kp/kp/author/srikanth-yoginath/">Srikanth Yoginath</a></span>, <span > <a href="https://kalper.net/kp/kp/author/sudip-seal/">Sudip Seal</a></span> </div> </div> <div class="btn-links"> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://kalper.net/kp/kp/publication/pub-100-garfield-evac-pads09/pub-100-garfield-evac-pads09.pdf" target="_blank" rel="noopener"> PDF </a> <a href="#" class="btn btn-outline-primary btn-page-header btn-sm js-cite-modal" data-filename="/kp/publication/pub-100-garfield-evac-pads09/cite.bib"> Cite </a> </div> </div> <div class="ml-3"> <a href="https://kalper.net/kp/kp/publication/pub-100-garfield-evac-pads09/" > <img src="https://kalper.net/kp/kp/publication/pub-100-garfield-evac-pads09/featured_hud54c1395f9fb0040015fc68bde7e67fb_23740_150x0_resize_lanczos_1.gif" alt="GPU-based Real-Time Execution of Vehicular Mobility Models in Large-Scale Road Network Scenarios " loading="lazy"> </a> </div> </div> <div class="media stream-item"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> <a href="https://kalper.net/kp/kp/publication/pub-003/" >Network Simulation</a> </div> <a href="https://kalper.net/kp/kp/publication/pub-003/" class="summary-link"> <div class="article-style"> A detailed introduction to the design, implementation, and use of network simulation tools is presen&hellip; </div> </a> <div class="stream-meta article-metadata"> <div> <span > <a href="https://kalper.net/kp/kp/author/richard-fujimoto/">Richard Fujimoto</a></span>, <span class="author-highlighted"> <a href="https://kalper.net/kp/kp/author/kalyan-perumalla/">Kalyan Perumalla</a></span>, <span > <a href="https://kalper.net/kp/kp/author/george-riley/">George Riley</a></span> </div> </div> <div class="btn-links"> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://kalper.net/kp/kp/publication/pub-003/pub-003.pdf" target="_blank" rel="noopener"> PDF </a> <a href="#" class="btn btn-outline-primary btn-page-header btn-sm js-cite-modal" data-filename="/kp/publication/pub-003/cite.bib"> Cite </a> </div> </div> <div class="ml-3"> <a href="https://kalper.net/kp/kp/publication/pub-003/" > <img src="https://kalper.net/kp/kp/publication/pub-003/featured_hu5c1d8e472383b4f498e0408e306d1ebf_53246_150x0_resize_q75_lanczos.jpg" alt="Network Simulation" loading="lazy"> </a> </div> </div> <div class="media stream-item"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> <a href="https://kalper.net/kp/kp/publication/pub-044-largenetsims-mascots03/" >Large-Scale Network Simulation - How Big? How Fast?</a> </div> <a href="https://kalper.net/kp/kp/publication/pub-044-largenetsims-mascots03/" class="summary-link"> <div class="article-style"> [Pub 44] </div> </a> <div class="stream-meta article-metadata"> <div> <span > <a href="https://kalper.net/kp/kp/author/richard-fujimoto/">Richard Fujimoto</a></span>, <span class="author-highlighted"> <a href="https://kalper.net/kp/kp/author/kalyan-perumalla/">Kalyan Perumalla</a></span>, <span > <a href="https://kalper.net/kp/kp/author/alfred-park/">Alfred Park</a></span>, <span > <a href="https://kalper.net/kp/kp/author/hao-wu/">Hao Wu</a></span>, <span > <a href="https://kalper.net/kp/kp/author/mostafa-ammar/">Mostafa Ammar</a></span>, <span > <a href="https://kalper.net/kp/kp/author/george-riley/">George Riley</a></span> </div> </div> <div class="btn-links"> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://kalper.net/kp/kp/publication/pub-044-largenetsims-mascots03/pub-044-largenetsims-mascots03.pdf" target="_blank" rel="noopener"> PDF </a> <a href="#" class="btn btn-outline-primary btn-page-header btn-sm js-cite-modal" data-filename="/kp/publication/pub-044-largenetsims-mascots03/cite.bib"> Cite </a> </div> </div> <div class="ml-3"> <a href="https://kalper.net/kp/kp/publication/pub-044-largenetsims-mascots03/" > <img src="https://kalper.net/kp/kp/publication/pub-044-largenetsims-mascots03/featured_huad36534b2bbcf547702e2934d043adf4_29371_150x0_resize_lanczos_3.png" alt="Large-Scale Network Simulation - How Big? How Fast?" loading="lazy"> </a> </div> </div> </p> https://kalper.net/kp/publication/2020-11-01-cuppa/ Sun, 01 Nov 2020 00:00:00 +0000 https://kalper.net/kp/publication/2020-11-01-cuppa/ https://kalper.net/kp/publication/2020-05-16-topc-preferential/ Sat, 16 May 2020 00:00:00 +0000 https://kalper.net/kp/publication/2020-05-16-topc-preferential/ <p><a href="https://dl.acm.org/doi/abs/10.1145/3391446" target="_blank" rel="noopener">https://dl.acm.org/doi/abs/10.1145/3391446</a></p> https://kalper.net/kp/publication/2019-03-30-dse-cuppa/ Sat, 30 Mar 2019 00:00:00 +0000 https://kalper.net/kp/publication/2019-03-30-dse-cuppa/ <p><a href="https://link.springer.com/article/10.1007/s41019-019-0088-6" target="_blank" rel="noopener">https://link.springer.com/article/10.1007/s41019-019-0088-6</a></p>