Graph | Kalyan Perumalla

ZeroIn

Sat, 01 Jan 2022 00:00:00 +0000

Our formulation of a new AI/ML-based, real-time computational framework aims to learn and flag defects in software as early as the time of commit in the developers’ repositories.

ZeroIn Network

Overview

Using novel AI/ML techniques, ZeroIn zeroes-in onto problems in software repositories and aims to identify code vulnerabilities at their very origin, namely, at the time at which developers commit their codes into their repositories.

ZeroIn: Characterizing the Data Distributions of Commits in Software Repositories

A characterization of the software development metadata is presented in terms of distributions of data that best captures the trends in the datasets, to feed into the machine learning components of ZeroIn to exploit connectivity among the sets of repositories, commits, and developers.

Kalyan Perumalla, Aradhana Soni, Rupam Dey, Steven Rich

PDF

Using Machine Learning Towards Early Flagging of Potentially Buggy Software Commits

Using multiple classifiers we verify the feasibility of using metadata from synthetic datasets modeled by a characterization of a few large software repositories and developer profiles. Results show that the metadata-based learning approach appears promising towards early flagging of potentially buggy commits in software repositories.

Aradhana Soni, Kalyan Perumalla

PDF

Characterizing the Distributions of Commits in Large Source Code Repositories

We present preliminary results from characterizing the distribution of 452 million commits in a metadata listing from GitHub repositories. Based on multiple distributions, we find the best fits and second best fits across different ranges in the data. The characterization is aimed at synthetic repository generation suitable for use in simulation and machine learning.

Aradhana Soni, Kalyan Perumalla, Rupam Dey

PDF

Organization

Sponsor: Industry
Institutions: University of Tennessee, Knoxville
Period: 2021-2024

Gallery

Graph Networks

Fri, 01 Jul 2022 00:00:00 +0000

Parallel/Distributed implementation (1000s of GPUs), Graph algorithms, Graph Generation on multiple GPUs, Community detection-based solutions

Overview

See all items tagged Graph

Very large network generation (trillion-edge)
Very fast network generation
- GPU-based scalable algorithms
- Billion of edges per second
Scale-free and distribution-conformant networks
Community detection-based applications
- Electric grid distribution network inference

Fast GPU-Based Generation of Large Graph Networks From Degree Distributions

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.

Maksudul Alam, Kalyan Perumalla

PDF Cite DOI

Scale-Free Graph Networks with Trillions of Edges: Rapid Generation using 1000 GPUs

Our algorithm cuPPA generates scale-free networks using the preferential-attachment model, custom-designed to exploit multiple GPUs. We generate extremely large scale-free networks of 4 trillion edges 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 streaming mode without the need for explicitly storing (writing to disk) the entire network, and is suitable for targeting even larger scales with quadrillions of edges.

Maksudul Alam, Kalyan Perumalla

PDF

On the Robustness of Network Community Structure Under Addition of Edges

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.

Pablo Moriano, Kalyan Perumalla

PDF DOI

Novel Parallel Algorithms for Fast Multi-GPU-Based Generation of Massive Scale-Free Networks

A novel parallel algorithm, cuPPA, is presented for generating random scale-free networks using the preferential attachment model. The algorithm is custom-designed for ‘single instruction multiple data (SIMD)’ 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.

Maksudul Alam, Kalyan Perumalla, Peter Sanders

PDF DOI

GPU-based parallel algorithm for generating massive scale-free networks using the preferential attachment model

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.

Maksudul Alam, Kalyan Perumalla

PDF Cite Slides DOI

Generating Billion-Edge Scale-Free Networks in Seconds: Performance Study of a Novel GPU-based Preferential Attachment Model

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.

Kalyan Perumalla, Maksudul Alam

Cite DOI

GPU-based Real-Time Execution of Vehicular Mobility Models in Large-Scale Road Network Scenarios

A methodology and its associated algorithms are presented for mapping a novel, field-based vehicular…

Kalyan Perumalla, Brandon Aaby, Srikanth Yoginath, Sudip Seal

PDF Cite

Network Simulation

A detailed introduction to the design, implementation, and use of network simulation tools is presen…

Richard Fujimoto, Kalyan Perumalla, George Riley

PDF Cite

Large-Scale Network Simulation - How Big? How Fast?

[Pub 44]

Richard Fujimoto, Kalyan Perumalla, Alfred Park, Hao Wu, Mostafa Ammar, George Riley

PDF Cite

Extending the Naming Game in Social Networks to Multiple Hearers per Speaker

Mon, 18 Apr 2022 00:00:00 +0000

ZeroIn: Characterizing the Data Distributions of Commits in Software Repositories

Sat, 16 Apr 2022 00:00:00 +0000

Using Machine Learning Towards Early Flagging of Potentially Buggy Software Commits

Fri, 08 Apr 2022 00:00:00 +0000

Characterizing the Distributions of Commits in Large Source Code Repositories

Wed, 15 Dec 2021 00:00:00 +0000

Scale-Free Graph Networks with Trillions of Edges: Rapid Generation using 1000 GPUs

Sun, 01 Nov 2020 00:00:00 +0000

On the Robustness of Network Community Structure Under Addition of Edges

Tue, 01 Sep 2020 00:00:00 +0000

https://www.osti.gov/biblio/1661212

Generating Massive Scale-free Networks: Novel Parallel Algorithms using the Preferential Attachment Model

Sat, 16 May 2020 00:00:00 +0000

https://dl.acm.org/doi/abs/10.1145/3391446

COVID-relevant Scalable Computational Research Directions and Tools

Thu, 09 Apr 2020 00:00:00 +0000

This seminar conveys some directions and technical ideas being pursued by the Discrete Computing Systems Group of the Computer Science and Mathematics Division, in collaboration with others at the lab. Some of the scalable computational tools ready for applying to challenging computational problems are presented. Actual working codes ready for customization to COVID-related efforts are described, which are built for scaling to supercomputing platforms such as Summit.

Topics that are covered include:

A high resolution simulator, ExaCorona, that scales from laptops to leadership class supercomputers, is outlined that uses a discrete event model of virus spread, with probabilistically timed state transitions at the individual level across millions of individuals represented with arbitray geography and mobility characteristics.
A clonable simulation framework, CloneX, is introduced that enables millions of “what-if” scenarios to be executed rapidly on thousands of GPUs of Summit and similar supercomputers. An SEIR-based epidemiological model is outlined for numerous what-if simulations of disease spread that can be executed for country-scale populations like India’s, with ‘what-if’ scenarios, each varying in the outbreak points (hotspots), quarantines, vaccinations and hospitalizations.
A machine learning pipeline for the prediction of material structure properties directly from their neutron scattering profiles (development as part of the ExaLearn ECP co-design project). A brief overview of this system is provided, which is being applied for studies of new therapeutic targets and viral protein-structure-assisted drug design studies related to the COVID outbreak.
Network science methods are outlined for detecting information cascades in time varying large-scale social communication networks. We discuss its implications for detecting occurrence/response or epidemic related events from Twitter and similar global interaction systems.

Novel Parallel Algorithms for Fast Multi-GPU-Based Generation of Massive Scale-Free Networks

Sat, 30 Mar 2019 00:00:00 +0000

https://link.springer.com/article/10.1007/s41019-019-0088-6

GPU-based parallel algorithm for generating massive scale-free networks using the preferential attachment model

Mon, 11 Dec 2017 00:00:00 +0000

https://ieeexplore.ieee.org/abstract/document/8258315

Generating Billion-Edge Scale-Free Networks in Seconds: Performance Study of a Novel GPU-based Preferential Attachment Model

Sun, 01 Oct 2017 00:00:00 +0000

https://www.osti.gov/biblio/1399438

Graph | Kalyan Perumalla

ZeroIn

Overview

Related Publications

Organization

Gallery

Graph Networks

Overview

Related Publications

Extending the Naming Game in Social Networks to Multiple Hearers per Speaker

ZeroIn: Characterizing the Data Distributions of Commits in Software Repositories

Using Machine Learning Towards Early Flagging of Potentially Buggy Software Commits

Characterizing the Distributions of Commits in Large Source Code Repositories

Scale-Free Graph Networks with Trillions of Edges: Rapid Generation using 1000 GPUs

On the Robustness of Network Community Structure Under Addition of Edges

Generating Massive Scale-free Networks: Novel Parallel Algorithms using the Preferential Attachment Model

COVID-relevant Scalable Computational Research Directions and Tools

Novel Parallel Algorithms for Fast Multi-GPU-Based Generation of Massive Scale-Free Networks

GPU-based parallel algorithm for generating massive scale-free networks using the preferential attachment model

Generating Billion-Edge Scale-Free Networks in Seconds: Performance Study of a Novel GPU-based Preferential Attachment Model