LAGraph19.bib

@article{che2016programming,
  title={Programming {GPGPU} Graph Applications with Linear Algebra Building Blocks},
  author={Che, Shuai and Beckmann, Bradford M and Reinhardt, Steven K},
  journal={Intl.\ Journal of Parallel Programming},
  pages={1--23},
  year={2016},
  publisher={Springer}
}
@inproceedings{lacc2019,
  author = {Ariful Azad and Ayd{\i}n Bulu\c{c}},
  booktitle = {Proceedings of the IPDPS},
  year = {2019},
  title = {{LACC:} A Linear-Algebraic Algorithm for Finding Connected Components in Distributed Memory}
}
@article{parco16,
  title = {A matrix-algebraic formulation of distributed-memory maximal cardinality matching algorithms in bipartite graphs},
  author = {Ariful Azad and Ayd{\i}n Bulu\c{c}},
  journal = {Parallel Computing},
  year = {2016},
  doi = {http://dx.doi.org/10.1016/j.parco.2016.05.007},
}
@inproceedings{matchingipdps16,
  author = {Ariful Azad and Ayd{\i}n Bulu\c{c}},
  title = {Distributed-Memory Algorithms for Maximum Cardinality Matching in Bipartite Graphs},
  booktitle = {Proceedings of the IPDPS},
  year = {2016},
  publisher = {IEEE}
}
@inproceedings{davis2018graph,
  title={Graph algorithms via {SuiteSparse}: {GraphBLAS}: triangle counting and K-truss},
  author={Davis, Timothy A},
  booktitle={IEEE High Performance extreme Computing Conference (HPEC)},
  pages={1--6},
  year={2018},
}
@inproceedings{gilbert2006high,
  title={High-performance graph algorithms from parallel sparse matrices},
  author={Gilbert, John R and Reinhardt, Steve and Shah, Viral B},
  booktitle={International Workshop on Applied Parallel Computing},
  pages={260--269},
  year={2006},
  organization={Springer}
}
@inproceedings{wang2016comparative,
 title={A comparative study on exact triangle counting algorithms on the {GPU}},
  author={Wang, Leyuan and Wang, Yangzihao and Yang, Carl and Owens, John D},
   booktitle={Proceedings of the ACM Workshop on High Performance Graph Processing},
     pages={1--8},  
     year={2016},
       organization={ACM}
       }
@article{azad2018hipmcl,
  title={HipMCL: a high-performance parallel implementation of the Markov clustering algorithm for large-scale networks},
  author={Azad, Ariful and Pavlopoulos, Georgios A and Ouzounis, Christos A and Kyrpides, Nikos C and Bulu{\c{c}}, Aydin},
  journal={Nucleic acids research},
  volume={46},
  number={6},
  pages={e33--e33},
  year={2018},
  publisher={Oxford University Press}
}
@inproceedings{ssspgrapl19,
title = {Delta-stepping {SSSP}: from Vertices and Edges to {GraphBLAS} Implementations},
author = {Upasana Sridhar and Mark Blanco and Rahul Mayuranath and Daniele G. Spampinato and Tze Meng Low and Scott McMillan},
year = {2019},
booktitle = {IPDPSW},
}
@article{chen2019graphblas,
  title={A {GraphBLAS} Approach for Subgraph Counting},
  author={Chen, Langshi and Li, Jiayu and Azad, Ariful and Jiang, Lei and Marathe, Madhav and Vullikanti, Anil and Nikolaev, Andrey and Smirnov, Egor and Israfilov, Ruslan and Qiu, Judy},
  journal={arXiv preprint arXiv:1903.04395},
  year={2019}
}
@inproceedings{coloringgrapl19,
title = {Graph Coloring on the {GPU}},
author = {Muhammad Osama and Minh Truong and Carl Yang and Aydin Buluc and John D. Owens},
year = {2019},
booktitle = {IPDPSW},
}

@inproceedings{trianglegabb15,
  author = {Ariful Azad and Ayd{\i}n Bulu\c{c} and John R Gilbert},
  title = {Parallel Triangle Counting and Enumeration using Matrix Algebra},
  booktitle = {Proceedings of the IPDPSW, Workshop on Graph Algorithm Building Blocks (GABB)},
  year = {2015},
  pages = {804 - 811},
  doi = {10.1109/IPDPSW.2015.75}
}
@inproceedings{satish2014navigating,
  title={Navigating the maze of graph analytics frameworks using massive graph datasets},
  author={Satish, Nadathur and Sundaram, Narayanan and Patwary, Md Mostofa Ali and Seo, Jiwon and Park, Jongsoo and Hassaan, M Amber and Sengupta, Shubho and Yin, Zhaoming and Dubey, Pradeep},
  booktitle={Proceedings of the 2014 ACM SIGMOD international conference on Management of data},
  pages={979--990},
  year={2014},
  organization={ACM}
}
@inproceedings{kepner2017enabling,
  title={Enabling massive deep neural networks with the {GraphBLAS}},
  author={Kepner, Jeremy and Kumar, Manoj and Moreira, Jos{\'e} and Pattnaik, Pratap and Serrano, Mauricio and Tufo, Henry},
  booktitle={IEEE High Performance Extreme Computing Conference (HPEC)},
  pages={1--10},
  year={2017},
}
@inproceedings{ca_apsp,
  author = {Solomonik, Edgar and Bulu\c{c}, Ayd{\i}n and Demmel, James},
  title = {Minimizing communication in all-pairs shortest paths},
  booktitle = {Proceedings of the IPDPS},
  year = {2013},
  publisher = {IEEE Computer Society},
  doi = {10.1109/IPDPS.2013.111}
}
@article{brandes2001faster,
  title={A faster algorithm for betweenness centrality},
  author={Brandes, Ulrik},
  journal={Journal of mathematical sociology},
  volume={25},
  number={2},
  pages={163--177},
  year={2001},
  publisher={Taylor \& Francis}
}
@article{robinson2011complex,
  title={Complex graph algorithms},
  author={Robinson, Eric},
  journal={Graph Algorithms in the Language of Linear Algebra},
  volume={22},
  pages={59},
  year={2011},
  publisher={SIAM Philadelphia, PA}
}
@inproceedings{mathgraphblas16,
 author = {Jeremy Kepner and Peter Aaltonen and David Bader and Ayd{\i}n Bulu\c{c} and Franz Franchetti and John Gilbert and Dylan Hutchison and Manoj Kumar and Andrew Lumsdaine and Henning Meyerhenke and Scott McMillan and Jos{\'e} Moreira and John Owens and Carl Yang and Marcin Zalewski and Timothy Mattson},
  title = {Mathematical Foundations of the {GraphBLAS}},
  booktitle = {IEEE High Performance Extreme Computing (HPEC)},
  year = {2016}
} 
@book{george2012graph,
  title={Graph theory and sparse matrix computation},
  author={George, Alan and Gilbert, John R and Liu, Joseph WH},
  volume={56},
  year={2012},
  publisher={Springer Science \& Business Media}
}
@book{kepner2011graph,
  title={Graph algorithms in the language of linear algebra},
  author={Kepner, Jeremy and Gilbert, John},
  volume={22},
  year={2011},
  publisher={SIAM}
}
@article{sundaram2015graphmat,
  title={GraphMat: High performance graph analytics made productive},
  author={Sundaram, Narayanan and Satish, Nadathur and Patwary, Md Mostofa Ali and Dulloor, Subramanya R and Anderson, Michael J and Vadlamudi, Satya Gautam and Das, Dipankar and Dubey, Pradeep},
  journal={Proceedings of the VLDB Endowment},
  volume={8},
  number={11},
  pages={1214--1225},
  year={2015},
  publisher={VLDB Endowment}
}
@inproceedings{gadepally2015graphulo,
  title={Graphulo: Linear algebra graph kernels for {NoSQL} databases},
  author={Gadepally, Vijay and Bolewski, Jake and Hook, Dan and Hutchison, Dylan and Miller, Ben and Kepner, Jeremy},
  booktitle={Intl.\ Parallel \& Distributed Processing Symposium Workshop (IPDPSW)},
  pages={822--830},
  year={2015},
  organization={IEEE}
}
@inproceedings{bulucc2011parallel,
  title={Parallel breadth-first search on distributed memory systems},
  author={Bulu{\c{c}}, Aydin and Madduri, Kamesh},
  booktitle={International Conference for High Performance Computing, Networking, Storage and Analysis},
  pages={65},
  year={2011},
  organization={ACM}
}
@inproceedings{gbtl-cuda16,
  title={{GBTL-CUDA}: Graph Algorithms and Primitives for {GPU}s},
  author={Zhang, Peter and Zalewski, Marcin and Lumsdaine, Andrew and Misurda, Samantha and McMillan, Scott},
  booktitle={Intl.\ Parallel \& Distributed Processing Symposium Workshop (IPDPSW)},
  pages={912--920},
  year={2016},
  organization={IEEE}
}
@misc{gbtl-github,
 title = {{GraphBLAS} {T}emplate {L}ibrary ({GBTL})},
 howpublished = {\url{https://github.com/cmu-sei/gbtl}},
}

@misc{cook,
 title = {{GraphBLAS} C99 library},
 author={Bob Cook},
 howpublished = {\url{https://github.com/bobcgausa/GraphBLAS}},
}

@inproceedings{gpi2016,
 author = {Ekanadham, K. and Horn, W. P. and Kumar, Manoj and Jann, Joefon and Moreira, Jos{\'e} and Pattnaik, Pratap and Serrano, Mauricio and Tanase, Gabriel and Yu, Hao},
 title = {{Graph Programming Interface (GPI)}: A Linear Algebra Programming Model for Large Scale Graph Computations},
 booktitle = {Proc.\ ACM Intl.\ Conference on Computing Frontiers},
 series = {CF '16},
 year = {2016},
 location = {Como, Italy},
 pages = {72--81},
 numpages = {10},
 acmid = {2903164},
 publisher = {ACM},
 address = {New York, NY, USA},
}
@article{bader2006designing,
  title={Designing scalable synthetic compact applications for benchmarking high productivity computing systems},
  author={Bader, D and Madduri, Kamesh and Gilbert, J and Shah, Viral and Kepner, Jeremy and Meuse, Theresa and Krishnamurthy, Ashok},
  journal={Cyberinfrastructure Technology Watch},
  volume={2},
  pages={1--10},
  year={2006},
  publisher={Citeseer}
}
@inproceedings{chiuw17,
 author = {Ariful Azad and Ayd{\i}n Bulu\c{c}},
 title = {Towards a {GraphBLAS} Library in {C}hapel},
 booktitle = {Intl.\ Parallel \& Distributed Processing Symposium Workshop (IPDPSW)},
 year = {2017},
}
@article{jpdc15,
  title = {Parallel Processing of Filtered Queries in Attributed Semantic Graphs},
  author = {Lugowski, Adam and Kamil, Shoaib and Ayd{\i}n Bulu\c{c} and Williams, Samuel and Duriakova, Erika and Oliker, Leonid and Fox, Armando and Gilbert, John},
  journal = {Journal of Parallel and Distributed Computing (JPDC))},
  year = {2015},
  volume = {79-80},
  pages = {115-131},
  doi = {10.1016/j.jpdc.2014.08.010}
}
@article{combblas,
  author = {Ayd{\i}n Bulu\c{c} and John R. Gilbert},
  title = {The {C}ombinatorial {BLAS}: Design, Implementation, and Applications},
  journal = {The Intl.\ Journal of High Performance Computing Applications},
  year = {2011},
  volume = {25},
  number = {4},
  pages = {496 - 509},
}

@inproceedings{hpec13,
  author = {T. Mattson and D. Bader and J. Berry and A. Bulu\c{c} and J. Dongarra and C. Faloutsos and J. Feo and J. Gilbert and J. Gonzalez and B. Hendrickson and J. Kepner and C. Leiserson and A. Lumsdaine and D. Padua and S. Poole and S. Reinhardt and M. Stonebraker and S. Wallach and A. Yoo},
  title = {Standards for Graph Algorithm Primitives},
  booktitle = {High Performance Extreme Computing Conf. (HPEC)},
  year = 2013,
  organization = {IEEE},
}

@inproceedings{cspec,
  author = {Ayd{\i}n Bulu\c{c} and Tim Mattson and Scott McMillan and Jos{\'e} Moreira and Carl Yang},
  title = {Design of the {GraphBLAS} {API} for {C}},
  booktitle = {Graph Algorithms Building Blocks workshop at IPDPS (GABB)},
  year = 2017,
  organization = {IEEE},
}

@misc{graphblas_web,
 title = {The {GraphBLAS} {F}orum},
 howpublished = {\url{http://graphblas.org/}},
}

@misc{ibmGraphBLAS,
 title = {{IBM}'s {GraphBLAS} implementation},
 howpublished = {\url{http://graphblas.org/}},
}

@ARTICLE{topc17,
	author = {{Wang}, Y. and {Pan}, Y. and {Davidson}, A. and {Wu}, Y. and 
	{Yang}, C. and {Wang}, L. and {Osama}, M. and {Yuan}, C. and 
	{Liu}, W. and {Riffel}, A.~T. and {Owens}, J.~D.},
	title = "{Gunrock: GPU Graph Analytics}",
	journal = {ArXiv e-prints},
	archivePrefix = "arXiv",
	eprint = {1701.01170},
	primaryClass = "cs.DC",
	keywords = {Computer Science - Distributed, Parallel, and Cluster Computing},
	year = 2017,
	month = jan,
	adsurl = {http://adsabs.harvard.edu/abs/2017arXiv170101170W},
	adsnote = {Provided by the SAO/NASA Astrophysics Data System}
}

@article{Gustavson78,
        author={Gustavson, F. G.},
        year={1978},
        title={Two Fast Algorithms for Sparse Matrices: Multiplication and Permuted Transposition},
        journal={ACM Trans. Math. Softw.},
        volume={4},
        number={3},
        pages={250--269},
        doi={ http://dx.doi.org/10.1145/355791.355796 }, }

@inproceedings{BulucGilbert08,
    author={Bulu\c{c}, A. and Gilbert, J. R.},
    booktitle={IEEE International Symposium on Parallel and Distributed Processing}, 
    title={On the representation and multiplication of hypersparse matrices}, 
    year={2008}, 
    volume={}, 
    number={}, 
    pages={1-11}, 
    doi={10.1109/IPDPS.2008.4536313}, 
    ISSN={1530-2075}, 
    month={April},}

@book{Davis06book,
        author={Davis, T. A.},
        title={Direct Methods for Sparse Linear Systems},
        publisher={SIAM},
        year={2006},
        address={Philadelphia, PA}
}

@article{Davis19,
    author={Davis, T. A.},
    title={Algorithm 9xx: {SuiteSparse:GraphBLAS:} graph algorithms in the language of sparse linear algebra},
    journal={ACM Trans. Math. Software},
    note = {see \url{http://suitesparse.com}},
    year={2019 (under submission)}
}

@techreport{MM,
    author={Boisvert, R. F. and Pozo, R. and Remington, K. A.},
    title={The {Matrix Market} exchange formats: initial design},
    publisher={NIST, Gaithersburg, MD},
    number={NISTIR 5935},
    year={1996}
}

 
 @inproceedings{McMillan2016,
    author={S. McMillan},
    booktitle={{GraphBLAS}: Graph Algorithms in the Language of Linear Algebra Minisymposium at SIAM Annual Meeting (AN16)},
    title={Design and Implementation of the {GraphBLAS Template Library (GBTL)}},
    year={2016}, 
    volume={}, 
    number={}, 
    month={July},
} 

 
 @inproceedings{Chamberlin2016,
    author={J. Chamberlin and M. Zalewksi and S. McMillan and A. Lumsdaine},
    booktitle={Graph Algorithms Building Blocks (GABB) Workshop at IEEE Intl. Parallel and Distributed Processing Symposium}, 
    title={{PyGB:} {GraphBLAS} {DSL} in {Python} with Dynamic Compilation into Efficient {C++}}, 
    year={2018}, 
    volume={}, 
    number={}, 
    month={May},
} 

@inproceedings{Yang:2018:IPE,
	title =	 {Implementing Push-Pull Efficiently in {GraphBLAS}},
	author =	 {Carl Yang and Ayd\i{}n Bulu\c{c} and John D. Owens},
	booktitle =	 {Proceedings of the International Conference on
	Parallel Processing},
	series =	 {ICPP 2018},
	month =	 aug,
	year =	 2018,
	pages =	 {89:1--89:11},
	doi =		 {10.1145/3225058.3225122},
	code =	 {https://github.com/owensgroup/push-pull}
}

@misc{Yang:2019:GBL,
	author =	 {Yang, Carl},
	title =	 {{GraphBLAST} Library},
	year =	 2015,
	howpublished = {\url{http://github.com/gunrock/graphblast}}
}

@inproceedings{Beamer:2012:DOB,
	title={Direction-optimizing Breadth-First Search},
	author={Beamer, Scott and Asanovic, Krste and Patterson, David},
	booktitle={International Conference for High Performance Computing, Networking, Storage and Analysis (SC)},
	pages={1--10},
	year={2012},
}

@article{Wang:2017:GGG,
	author =	 {Yangzihao Wang and Yuechao Pan and Andrew Davidson
	and Yuduo Wu and Carl Yang and Leyuan Wang and
	Muhammad Osama and Chenshan Yuan and Weitang Liu and
	Andy T. Riffel and John D. Owens},
	title =	 {{G}unrock: {GPU} Graph Analytics},
	journal =	 {ACM Transactions on Parallel Computing},
	year =	 2017,
	volume =	 4,
	number =	 1,
	month =	 aug,
	pages =	 {3:1--3:49},
	doi =		 {10.1145/3108140},
	ee =		 {http://arxiv.org/abs/1701.01170},
	acmauthorize = {http://dl.acm.org/authorize?N45082},
	url_ =	 {http://escholarship.org/uc/item/9gj6r1dj},
	code =	 {https://github.com/gunrock/gunrock},
}

@article{Zhang:2018:GHP,
	title={{GraphIt}: A High-Performance {DSL} for Graph Analytics},
	author={Zhang, Yunming and Yang, Mengjiao and Baghdadi, Riyadh and Kamil, Shoaib and Shun, Julian and Amarasinghe, Saman},
	journal={arXiv preprint arXiv:1805.00923},
	year={2018}
}

@inproceedings{Shun:2013:Ligra,
 author = {Shun, Julian and Blelloch, Guy E.},
 title = {Ligra: A Lightweight Graph Processing Framework for Shared Memory},
 booktitle = {Proceedings of the 18th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming},
 series = {PPoPP '13},
 year = {2013},
 isbn = {978-1-4503-1922-5},
 location = {Shenzhen, China},
 pages = {135--146},
 numpages = {12},
 doi = {10.1145/2442516.2442530},
 acmid = {2442530},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {graph algorithms, parallel programming, shared memory},
}

@article{sisc3dspgemm,
  title = {Exploiting Multiple Levels of Parallelism in Sparse Matrix-Matrix Multiplication},
  author = {Ariful Azad and Grey Ballard and Ayd{\i}n Bulu\c{c} and James Demmel and Laura Grigori and Oded Schwartz and Sivan Toledo and Samuel Williams},
  journal = {SIAM Journal on Scientific Computing (SISC)},
  year = {2016},
  volume = {38},
  number = {6},
  pages = {C624-C651},
  doi = {http://dx.doi.org/10.1137/15M104253X},
  arxiv = {http://arxiv.org/abs/1510.00844},
  code = {https://people.eecs.berkeley.edu/~aydin/CombBLAS/html/index.html}
}

@misc{redisgraph,
 title ={{RedisGraph} Module for the {Redis} Database System},
 howpublished ={\url{https://oss.redislabs.com/redisgraph/}}
}

@techreport{GPI,
    title={Graph Programming Interface: Rationale and Specification},
    author={Ekanadham, K. and Horn, B. and Jann, J. and  Kumar, M. and Moreira, J. and Pattnaik, P. and Serrano, M. and  Tanase, G. and Yu H.},
    number={RC25508 (WAT1411-052)},
    year={2014},
    month={Nov.},
    day={19},
    address={Yorktown Heights, NY},
    publisher={Computer Science Research Division, Thomas J. Watson Research Center, IBM}
    }

@article{KuJour,
  author = {Kumar, M and P. Horn, W and Kepner, J and E. Moreira, J and Pattnaik, P},
  year = {2018},
  month = {06},
  pages = {1-1},
  title = {{IBM} {POWER9} and cognitive computing},
  volume = {PP},
  journal = {IBM Journal of Research and Development},
  doi = {10.1147/JRD.2018.2846958}
  }

@INPROCEEDINGS{KuHPEC2016,
author={M. Kumar and M. Serrano and J. Moreira and P. Pattnaik and W. P. Horn and J. Jann and G. Tanase},
booktitle={2016 IEEE High Performance Extreme Computing Conference (HPEC)},
title={Efficient implementation of scatter-gather operations for large scale graph analytics},
year={2016},
pages={1-7},
month={Sept},}

@INPROCEEDINGS{jwHPEC,
author={J. Wise and E. Lederman and M. Kumar and P. Pattnaik},
booktitle={2018 IEEE High Performance extreme Computing Conference (HPEC)},
title={Performance of Graph Analytics Applications on Many-Core Processors},
year={2018},
volume={},
number={},
pages={1-7},
abstract={Attaining good performance on graph analytics applications on modern day many-core processors is challenging, because these processors have complex pipelines to manage out of order execution of hundreds of instructions in flight. These pipelines have been optimized for high performance computing (HPC) applications, not for graph analytics. It is preferable to leave the task of attaining good performance to the system developers, and to separate the performance concern from the application programmer's concerns. In this paper, we show that the linear algebra formulation of graph-analytics effectively handles the aforementioned separation of concerns. This formulation is a better fit for many-core processors as the many-core processors are optimized for HPC applications which have a substantial linear algebra component. We show that on POWER8, a many-core processor, an eightfold performance advantage can be attained on the Graph500 benchmark by adopting the linear algebra formulation. We also present the CPI stack analysis of three graph analytics kernels, and show that the linear algebra implementations of these kernels make efficient use of the POWER8 core. Inhibitors to still better performance are discussed.},
keywords={graph theory;linear algebra;microprocessor chips;parallel processing;performance evaluation;graph analytics;high performance computing;POWER8 core;graph analytics kernels;Graph500 benchmark;substantial linear algebra component;graph-analytics;linear algebra formulation;application programmer;modern day many-core processors;many-core processor;Linear algebra;Instruction sets;Task analysis;Phasor measurement units;Benchmark testing;Kernel},
doi={10.1109/HPEC.2018.8547558},
ISSN={2377-6943},
month={Sep.},}

@inproceedings{low2018linear,
  title={Linear Algebraic Formulation of Edge-centric K-truss Algorithms with Adjacency Matrices},
  author={Low, Tze Meng and Spampinato, Daniele G and Kutuluru, Anurag and Sridhar, Upasana and Popovici, Doru Thom and Franchetti, Franz and McMillan, Scott},
  booktitle={2018 IEEE High Performance extreme Computing Conference (HPEC)},
  pages={1--7},
  year={2018},
  organization={IEEE}
}