iss.bib

@inproceedings{nguyen17,
  author = {Donald Nguyen and
               Keshav Pingali},
  title = {What Scalable Programs Need from Transactional Memory},
  booktitle = {22nd ACM International Conference on Architectural Support for Programming Languages and Operating Systems, {ASPLOS} 2017},
  year = {2017},
  url = {http://iss.ices.utexas.edu/Publications/Papers/asplos426-nguyen.pdf},
  doi = {10.1145/2983990.2984015},
  tags = {stampede}
}
@inproceedings{Sree16,
  author = {Sreepathi Pai and
               Keshav Pingali},
  title = {A compiler for throughput optimization of graph algorithms on GPUs},
  booktitle = {Proceedings of the 2016 {ACM} {SIGPLAN} International Conference on
               Object-Oriented Programming, Systems, Languages, and Applications,
               {OOPSLA} 2016, part of {SPLASH} 2016, Amsterdam, The Netherlands,
               October 30 - November 4, 2016},
  pages = {1--19},
  year = {2016},
  url = {http://iss.ices.utexas.edu/Publications/Papers/OOPSLA2016.pdf},
  doi = {10.1145/2983990.2984015}
}
@inproceedings{JMNMPP16,
  author = {Hassan AbouEisha and
               Konrad Jopek and
               Bartlomiej Medygral and
               Szymon Nosek and
               Mikhail Ju Moshkov and
               Anna Paszynska and
               Maciej Paszynski and
               Keshav Pingali},
  title = {Hybrid Direct and Iterative Solver with Library of Multi-criteria Optimal Orderings for h Adaptive Finite Element Method Computations},
  booktitle = {International Conference on Computational Science 2016, {ICCS} 2016,
               6-8 June 2016, San Diego, California, {USA}},
  pages = {865--874},
  year = {2016},
  url = {http://iss.ices.utexas.edu/Publications/Papers/ICCS2016.pdf},
  doi = {10.1016/j.procs.2016.05.312},
  timestamp = {Tue, 28 Jun 2016 19:28:29 +0200}
}
@article{LenharthNP16,
  author = {Andrew Lenharth and
               Donald Nguyen and
               Keshav Pingali},
  title = {Parallel graph analytics},
  journal = {Commun. {ACM}},
  volume = {59},
  number = {5},
  pages = {78--87},
  year = {2016},
  url = {http://doi.acm.org/10.1145/2901919},
  doi = {10.1145/2901919},
  timestamp = {Wed, 27 Apr 2016 15:42:41 +0200}
}
@inproceedings{LNP16,
  author = {Anna Paszynska and
               Maciej Wozniak and
               Andrew Lenharth and
               Donald Nguyen and
               Keshav Pingali},
  title = {Hypergraph Grammars in Non-stationary hp-adaptive Finite Element Method},
  booktitle = {International Conference on Computational Science 2016, {ICCS} 2016,
               6-8 June 2016, San Diego, California, {USA}},
  pages = {875--886},
  year = {2016},
  url = {http://iss.ices.utexas.edu/Publications/Papers/ICCS16.pdf},
  doi = {10.1016/j.procs.2016.05.314},
  timestamp = {Tue, 28 Jun 2016 19:28:29 +0200}
}
@inproceedings{SuiLFP16,
  author = {Xin Sui and
               Andrew Lenharth and
               Donald S. Fussell and
               Keshav Pingali},
  title = {Proactive Control of Approximate Programs},
  booktitle = {Proceedings of the Twenty-First International Conference on Architectural
               Support for Programming Languages and Operating Systems, {ASPLOS}
               '16, Atlanta, GA, USA, April 2-6, 2016},
  pages = {607--621},
  year = {2016},
  url = {http://doi.acm.org/10.1145/2872362.2872402},
  doi = {10.1145/2872362.2872402},
  timestamp = {Thu, 31 Mar 2016 18:07:43 +0200}
}
@inproceedings{Maleki,
  author = {Saeed Maleki and
               Donald Nguyen and
               Andrew Lenharth and
               Mar{\'{\i}}a Jes{\'{u}}s Garzar{\'{a}}n and
               David A. Padua and
               Keshav Pingali},
  title = {{DSMR:} a shared and distributed memory algorithm for single-source
               shortest path problem},
  booktitle = {Proceedings of the 21st {ACM} {SIGPLAN} Symposium on Principles and
               Practice of Parallel Programming, PPoPP 2016, Barcelona, Spain, March
               12-16, 2016},
  pages = {39:1--39:2},
  year = {2016},
  url = {http://iss.ices.utexas.edu/Publications/Papers/ICS2016.pdf},
  doi = {10.1145/2851141.2851183},
  timestamp = {Thu, 07 Apr 2016 12:07:19 +0200},
  biburl = {http://dblp.uni-trier.de/rec/bib/conf/ppopp/MalekiNLGPP16},
  bibsource = {dblp computer science bibliography, http://dblp.org}
}
@inproceedings{MalekiNLGPP16,
  author = {Saeed Maleki and
               Donald Nguyen and
               Andrew Lenharth and
               Mar{\'{\i}}a Jes{\'{u}}s Garzar{\'{a}}n and
               David A. Padua and
               Keshav Pingali},
  title = {{DSMR:} {A} Parallel Algorithm for Single-Source Shortest Path Problem},
  booktitle = {Proceedings of the 2016 International Conference on Supercomputing,
               {ICS} 2016, Istanbul, Turkey, June 1-3, 2016},
  pages = {32:1--32:14},
  year = {2016},
  url = {http://iss.ices.utexas.edu/Publications/Papers/ipdps2016.pdf},
  doi = {10.1145/2925426.2926287},
  timestamp = {Thu, 14 Jul 2016 16:30:07 +0200}
}
@inproceedings{KaleemVPHP16,
  author = {Rashid Kaleem and
               Anand Venkat and
               Sreepathi Pai and
               Mary W. Hall and
               Keshav Pingali},
  title = {Synchronization Trade-Offs in {GPU} Implementations of Graph Algorithms},
  booktitle = {2016 {IEEE} International Parallel and Distributed Processing Symposium,
               {IPDPS} 2016, Chicago, IL, USA, May 23-27, 2016},
  pages = {514--523},
  year = {2016},
  url = {http://iss.ices.utexas.edu/Publications/Papers/ipdps2016.pdf},
  doi = {10.1109/IPDPS.2016.106},
  timestamp = {Tue, 26 Jul 2016 16:20:06 +0200}
}
@inproceedings{Prountzos:2015:SPG,
  author = {Prountzos, Dimitrios and Manevich, Roman and Pingali, Keshav},
  title = {Synthesizing Parallel Graph Programs via Automated Planning},
  booktitle = {Proceedings of the 36th ACM SIGPLAN Conference on Programming Language Design and Implementation},
  series = {PLDI 2015},
  year = {2015},
  isbn = {978-1-4503-3468-6},
  location = {Portland, OR, USA},
  pages = {533--544},
  numpages = {12},
  url = {http://iss.ices.utexas.edu/Publications/Papers/prountzos-2015-SPG.pdf},
  doi = {10.1145/2737924.2737953},
  acmid = {2737953},
  publisher = {ACM},
  address = {New York, NY, USA},
  keywords = {Amorphous Data-parallelism, Compiler Optimization, Concurrency, Irregular Programs, Parallelism, Synthesis},
  tags = {galois}
}
@inproceedings{Kaleem:2015:SGD,
  author = {Kaleem, Rashid and Pai, Sreepathi and Pingali, Keshav},
  title = {Stochastic {G}radient {D}escent on {GPUs}},
  booktitle = {Proceedings of the 8th Workshop on General Purpose Processing Using GPUs},
  series = {GPGPU 2015},
  year = {2015},
  isbn = {978-1-4503-3407-5},
  location = {San Francisco, CA, USA},
  pages = {81--89},
  numpages = {9},
  url = {http://iss.ices.utexas.edu/Publications/Papers/kaleem-2015-SGD-GPU.pdf},
  doi = {10.1145/2716282.2716289},
  acmid = {2716289},
  publisher = {ACM},
  address = {New York, NY, USA},
  keywords = {Edge-coloring, GPGPU, Stochastic Gradient Descent},
  tags = {galois}
}
@inproceedings{hassaan15,
  author = {M. Amber Hassaan and Donald Nguyen and Keshav Pingali},
  title = {Kinetic {D}ependence {G}raphs},
  booktitle = {Proceedings of International Conference on Architectural
  Support for Programming Languages and Operating Systems},
  series = {ASPLOS '15},
  year = {2015},
  url = {http://iss.ices.utexas.edu/Publications/Papers/asplos208-hassaan.pdf},
  doi = {10.1145/2694344.2694363},
  tags = {galois}
}
@inproceedings{karantasis14,
  author = {Konstantinos I Karantasis and Andrew Lenharth and Donald Nguyen and Mar\'{i}a J Garzar\'{a}n  and Keshav Pingali},
  title = {Parallelization of Reordering Algorithms for Bandwidth and Wavefront Reduction},
  booktitle = {Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis},
  series = {SC '14},
  year = {2014},
  isbn = {978-1-4799-5500-8},
  location = {New Orleans, Louisana},
  pages = {921--932},
  numpages = {12},
  url = {http://dx.doi.org/10.1109/SC.2014.80},
  doi = {10.1109/SC.2014.80},
  acmid = {2683694},
  publisher = {IEEE Press},
  address = {Piscataway, NJ, USA}
}
@article{goik14,
  title = {Graph Grammar based Multi-thread Multi-frontal Direct Solver with Galois Scheduler },
  journal = {Procedia Computer Science},
  volume = {29},
  number = {0},
  pages = {960 - 969},
  year = {2014},
  note = {2014 International Conference on Computational Science},
  issn = {1877-0509},
  doi = {http://dx.doi.org/10.1016/j.procs.2014.05.086},
  url = {http://www.sciencedirect.com/science/article/pii/S1877050914002634},
  author = {Damian Goik and Konrad Jopek and Maciej Paszyński and Andrew Lenharth and Donald Nguyen and Keshav Pingali},
  keywords = {h adaptive finite element method},
  keywords = {multi-frontal direct solver},
  keywords = {graph grammar},
  keywords = {Galois environment}
}
@inproceedings{nguyen14,
  author = {Nguyen, Donald and Lenharth, Andrew and Pingali, Keshav},
  title = {Deterministic Galois: On-demand, Portable and Parameterless},
  booktitle = {Proceedings of the 19th International Conference on Architectural Support for Programming Languages and Operating Systems},
  series = {ASPLOS '14},
  year = {2014},
  isbn = {978-1-4503-2305-5},
  location = {Salt Lake City, Utah, USA},
  pages = {499--512},
  numpages = {14},
  url = {http://iss.ices.utexas.edu/Publications/Papers/nguyen14.pdf},
  doi = {10.1145/2541940.2541964},
  acmid = {2541964},
  publisher = {ACM},
  address = {New York, NY, USA},
  keywords = {deterministic scheduling, irregular programs, multicore processors}
}
@inproceedings{kulkarni11,
  author = {Milind Kulkarni and Donald Nguyen and Dimitrios Prountzos and
    Xin Sui and Keshav Pingali},
  title = {Exploiting the Commutativity Lattice},
  booktitle = {Proceedings of the ACM SIGPLAN Conference on Programming
  Language Design and Implementation},
  series = {PLDI '11},
  doi = {10.1145/1993316.1993562},
  isbn = {978-1-4503-0663-8},
  pages = {542--555},
  numpages = {14},
  url = {http://iss.ices.utexas.edu/Publications/Papers/kulkarni11.pdf},
  year = {2011},
  tags = {galois}
}
@article{menon03b,
  author = { Menon, Vijay and Pingali, Keshav and Mateev, Nikolay   },
  title = {Fractal Symbolic Analysis},
  journal = {ACM TOPLAS},
  year = {2003},
  month = {March},
  tags = {fsa},
  url = {http://iss.ices.utexas.edu/Publications/Papers/TOPLAS2003.pdf},
  optkey = {},
  optvolume = {},
  optnumber = {},
  optpages = {},
  optnote = {},
  optannote = {}
}
@phdthesis{ahmed00,
  author = {Ahmed, Nawaaz},
  title = {Locality Enhancement Of Imperfectly-nested Loop Nests},
  school = {Cornell University},
  year = {2000},
  address = {Ithaca, NY, USA},
  publisher = {Cornell University},
  source = {http://www.ncstrl.org:8900/ncstrl/servlet/search?formname=detail\&id=oai%3Ancstrlh%3Acornellcs%3ACORNELLCS%3ATR2000-1811},
  tags = {mho},
  url = {http://iss.ices.utexas.edu/Publications/Theses/NawaazAhmed.pdf}
}
@inproceedings{ahmed00a,
  author = {Ahmed, Nawaaz and Mateev, Nikolay and Pingali, Keshav},
  title = {Synthesizing transformations for locality enhancement of imperfectly-nested
  loop nests},
  booktitle = {ICS '00: Proceedings of the 14th international conference on Supercomputing},
  year = {2000},
  pages = {141--152},
  address = {New York, NY, USA},
  publisher = {ACM},
  doi = {http://doi.acm.org/10.1145/335231.335245},
  isbn = {1-58113-270-0},
  location = {Santa Fe, New Mexico, United States},
  tags = {mho},
  url = {http://iss.ices.utexas.edu/Publications/Papers/ICS2000b.pdf}
}
@inproceedings{ahmed00b,
  author = {Ahmed, Nawaaz and Mateev, Nikolay and Pingali, Keshav},
  title = {A framework for sparse matrix code synthesis from high-level specifications},
  booktitle = {Supercomputing '00: Proceedings of the 2000 ACM/IEEE conference on
  Supercomputing (CDROM)},
  year = {2000},
  pages = {58},
  address = {Washington, DC, USA},
  publisher = {IEEE Computer Society},
  isbn = {0-7803-9802-5},
  location = {Dallas, Texas, United States},
  tags = {sic},
  url = {http://iss.ices.utexas.edu/Publications/Papers/SC2000c.pdf}
}
@inproceedings{ahmed00c,
  author = {Ahmed, Nawaaz and Mateev, Nikolay and Pingali, Keshav},
  title = {Tiling imperfectly-nested loop nests},
  booktitle = {Supercomputing '00: Proceedings of the 2000 ACM/IEEE conference on
  Supercomputing (CDROM)},
  year = {2000},
  pages = {31},
  address = {Washington, DC, USA},
  publisher = {IEEE Computer Society},
  isbn = {0-7803-9802-5},
  location = {Dallas, Texas, United States},
  tags = {mho},
  url = {http://iss.ices.utexas.edu/Publications/Papers/SC2000a.pdf}
}
@techreport{ahmed00d,
  author = {Ahmed, Nawaaz and Mateev, Nikolay and Pingali, Keshav and Stodghill,
  Paul},
  title = {Compiling Imperfectly-nested Sparse Matrix Codes with Dependences},
  institution = {Cornell University},
  year = {2000},
  address = {Ithaca, NY, USA},
  publisher = {Cornell University},
  source = {http://www.ncstrl.org:8900/ncstrl/servlet/search?formname=detail\&id=oai%3Ancstrlh%3Acornellcs%3ACORNELLCS%3ATR2000-1788},
  tags = {sic},
  url = {http://iss.ices.utexas.edu/Publications/Papers/EUROPAR2000b.pdf}
}
@inproceedings{ahmed00e,
  author = {Ahmed, Nawaaz and Pingali, Keshav},
  title = {Automatic Generation of Block-Recursive Codes},
  booktitle = {Euro-Par '00: Proceedings from the 6th International Euro-Par Conference
  on Parallel Processing},
  year = {2000},
  pages = {368--378},
  address = {London, UK},
  publisher = {Springer-Verlag},
  isbn = {3-540-67956-1},
  tags = {mho},
  url = {http://iss.ices.utexas.edu/Publications/Papers/EUROPAR2000a.pdf}
}
@article{ahmed01,
  author = { Ahmed, Nawaaz and Mateev, Nikolay and Pingali, Keshav },
  title = {Synthesizing Transformations for Locality Enhancement of Imperfectly-Nested
  Loop Nests},
  journal = {International Journal of Parallel Programming 29(5)},
  year = {2001},
  month = {10/01/},
  tags = {mho},
  url = {http://iss.ices.utexas.edu/Publications/Papers/IJPP2001.pdf}
}
@misc{ahuja97,
  author = {Vineet Ahuja and Nikos Chrisochoides and Induprakas Kodukula and
  Keshav Pingali},
  title = {Runtime System Support for Parallel Iterative {PDE} Computations},
  year = {1997},
  url = {http://iss.ices.utexas.edu/Publications/Papers/SIAM-PP1997a.pdf}
}
@article{arvind89,
  author = {Arvind and Nikhil, Rishiyur S. and Pingali, Keshav},
  title = {I-structures: data structures for parallel computing},
  journal = {ACM Trans. Program. Lang. Syst.},
  year = {1989},
  volume = {11},
  pages = {598--632},
  number = {4},
  address = {New York, NY, USA},
  doi = {http://doi.acm.org/10.1145/69558.69562},
  issn = {0164-0925},
  publisher = {ACM},
  tags = {fllv}
}
@article{barker02,
  author = { Barker, Kevin and Chrisochoides, Nikos and Dobbelaere, Jeffrey and
  D\'{e}mian Nave and Pingali, Keshav },
  title = {Data movement and control substrate for parallel adaptive applications},
  journal = {Concurrency and Computation: Practice and Experience},
  year = {2002},
  month = {02/01/},
  url = {http://iss.ices.utexas.edu/Publications/Papers/CONCURRENCY2002.pdf}
}
@article{barker03,
  author = { Barker, Kevin and Chernikov, Andrey and Chrisochoides, Nikos and
  Holinka, Brian and Pingali, Keshav },
  title = {Architecture and Evaluation of a Runtime System for Adaptive Applications},
  journal = {Transactions on Parallel and Distributed Systems TDPS},
  year = {2003},
  month = {03/16/},
  url = {http://iss.ices.utexas.edu/Publications/Papers/TPDS2003.pdf}
}
@inproceedings{bau95,
  author = {Bau, David and Kodukula, Induprakas and Kotlyar, Vladimir and Pingali,
  Keshav and Stodghill, Paul},
  title = {Solving Alignment Using Elementary Linear Algebra},
  booktitle = {LCPC '94: Proceedings of the 7th International Workshop on Languages
  and Compilers for Parallel Computing},
  year = {1995},
  pages = {46--60},
  address = {London, UK},
  publisher = {Springer-Verlag},
  date-added = {2009-08-21 16:43:24 -0500},
  date-modified = {2009-08-21 16:43:24 -0500},
  isbn = {3-540-58868-X},
  tags = {tc2, cdmc}
}
@inproceedings{beck90,
  author = {Beck, Micah and Pingali, Keshav},
  title = {From control flow to dataflow},
  booktitle = {Proceedings of the {I}nternational {C}onference on {P}arallel {P}rogramming
  ({ICPP})},
  year = {1990},
  tags = {pidgin, pr}
}
@article{beck90a,
  author = {Beck, Micah and Pingali, Keshav and Nicolau, Alex},
  title = {Static scheduling for dynamic dataflow machines},
  journal = {Journal of parallel and distributed computing ({JPDC})},
  year = {1990},
  volume = {10},
  pages = {279-288},
  number = {4},
  month = {December}
}
@article{beck91,
  author = {Beck, Micah and Johnson, Richard and Pingali, Keshav},
  title = {From control flow to dataflow},
  journal = {Journal of {P}arallel and {D}istributed {C}omputing},
  year = {1991},
  volume = {12},
  pages = {118-129},
  number = {2},
  month = {June},
  tags = {pidgin, pr}
}
@article{bilardi03,
  author = { Bilardi, Gianfranco and Pingali, Keshav },
  title = {Algorithms for Computing the Static Single Assignment Form},
  journal = {Journal of the ACM},
  year = {2003},
  month = {May 05/16/},
  tags = {ssaf},
  url = {http://iss.ices.utexas.edu/Publications/Papers/JACM2003.pdf}
}
@inproceedings{bilardi96,
  author = {Bilardi, Gianfranco and Pingali, Keshav},
  title = {A framework for generalized control dependence},
  booktitle = {PLDI '96: Proceedings of the ACM SIGPLAN 1996 conference on Programming
  language design and implementation},
  year = {1996},
  pages = {291--300},
  address = {New York, NY, USA},
  publisher = {ACM},
  doi = {http://doi.acm.org/10.1145/231379.231435},
  isbn = {0-89791-795-2},
  location = {Philadelphia, Pennsylvania, United States},
  tags = {cdc},
  url = {http://iss.ices.utexas.edu/Publications/Papers/PLDI1996.pdf}
}
@inproceedings{bronevetsky03,
  author = { Bronevetsky, Greg and Marques, Daniel and Pingali, Keshav and Stodghill,
  Paul},
  title = {Collective Operations in an Application-level Fault Tolerant MPI
  System},
  booktitle = {International Conference on Supercomputing},
  year = {2003},
  month = {06/23/},
  tags = {ft},
  url = {http://iss.ices.utexas.edu/Publications/Papers/ICS2003.pdf}
}
@inproceedings{bronevetsky03a,
  author = { Bronevetsky, Greg and Marques, Daniel and Pingali, Keshav and Stodghill,
  Paul},
  title = { Automated Application-level Checkpointing of MPI Programs},
  booktitle = {Principles and Practice of Parallel Programming},
  year = {2003},
  month = {06/11/},
  tags = {ft},
  url = {http://iss.ices.utexas.edu/Publications/Papers/PPoPP2003.pdf}
}
@article{bronevetsky04,
  author = {Bronevetsky, Greg and Marques, Daniel and Pingali, Keshav and Szwed,
  Peter and Schulz, Martin},
  title = {Application-level checkpointing for shared memory programs},
  journal = {SIGARCH Comput. Archit. News},
  year = {2004},
  volume = {32},
  pages = {235--247},
  number = {5},
  address = {New York, NY, USA},
  doi = {http://doi.acm.org/10.1145/1037947.1024421},
  issn = {0163-5964},
  publisher = {ACM},
  tags = {ft},
  url = {http://iss.ices.utexas.edu/Publications/Papers/ASPLOS2004.pdf}
}
@inproceedings{bronevetsky04a,
  author = {Greg Bronevetsky and Daniel Marques and Keshav Pingali and Peter
  Szwed and Martin Schulz},
  title = {Checkpointing Shared Memory Programs at the Application-Level},
  booktitle = {In European Workshop on OpenMP},
  year = {2004},
  tags = {ft},
  url = {http://iss.ices.utexas.edu/Publications/Papers/EWOMP2004.pdf}
}
@inproceedings{bronevetsky06,
  author = {Bronevetsky, Greg and Pingali, Keshav and Stodghill, Paul},
  title = {Experimental evaluation of application-level checkpointing for OpenMP
  programs},
  booktitle = {ICS '06: Proceedings of the 20th annual international conference
  on Supercomputing},
  year = {2006},
  pages = {2--13},
  address = {New York, NY, USA},
  publisher = {ACM},
  doi = {http://doi.acm.org/10.1145/1183401.1183405},
  isbn = {1-59593-282-8},
  location = {Cairns, Queensland, Australia},
  tags = {ft},
  url = {http://iss.ices.utexas.edu/Publications/Papers/ICS2006Bronevetsky.pdf}
}
@incollection{burtscher11,
  author = {Martin Burtscher and Keshav Pingali},
  title = {An Efficient {CUDA} Implementation of the Tree-based Barnes Hut n-Body
  Algorithm},
  booktitle = {GPU Computing Gems Emerald Edition},
  publisher = {Morgan Kaufmann},
  year = {2011},
  pages = {75--92},
  url = {http://iss.ices.utexas.edu/Publications/Papers/burtscher11.pdf},
  isbn = {978-0-12-384988-5},
  tags = {galois}
}
@incollection{burtscher08,
  author = {Burtscher, Martin and Kulkarni, Milind and Prountzos, Dimitrios and Pingali, Keshav},
  chapter = {On the Scalability of an Automatically Parallelized Irregular Application},
  title = {Languages and Compilers for Parallel Computing},
  editor = {Amaral, Jos\'{e} Nelson},
  year = {2008},
  isbn = {978-3-540-89739-2},
  pages = {109--123},
  numpages = {15},
  doi = {http://dx.doi.org/10.1007/978-3-540-89740-8_8},
  acmid = {1485709},
  publisher = {Springer-Verlag},
  address = {Berlin, Heidelberg},
  keywords = {amorphous data-parallelism, mesh refinement, multicore processors, optimistic execution, parallel programming, sparse graph algorithm}
}
@inproceedings{pingali11,
  author = {Pingali, Keshav and Nguyen, Donald and Kulkarni, Milind and Burtscher, Martin and Hassaan, M. Amber and Kaleem, Rashid and Lee, Tsung-Hsien and Lenharth, Andrew and Manevich, Roman and M\'{e}ndez-Lojo, Mario and Prountzos, Dimitrios and Sui, Xin},
  title = {The tao of parallelism in algorithms},
  booktitle = {Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation},
  series = {PLDI '11},
  year = {2011},
  isbn = {978-1-4503-0663-8},
  location = {San Jose, California, USA},
  pages = {12--25},
  numpages = {14},
  doi = {http://doi.acm.org/10.1145/1993498.1993501},
  acmid = {1993501},
  keywords = {amorphous data-parallelism, galois system, irregular programs, operator formulation, tao-analysis},
  url = {http://iss.ices.utexas.edu/Publications/Papers/pingali11.pdf},
  tags = {galois}
}
@inproceedings{carter00,
  author = {Carter, Bruce and Chen, Chuin-Shan and Chew, L. Paul and Chrisochoides,
  Nikos and Gao, Guang R. and Heber, Gerd and Ingraffea, Antony R.
  and Krause, Roland and Myers, Chris and Nave, D\'{e}mian and Pingali,
  Keshav and Stodghill, Paul and Vavasis, Stephen and Wawrzynek, Paul},
  title = {Parallel {FEM} Simulation of Crack Propagation - Challenges, Status,
  and Perspectives},
  booktitle = {IPDPS '00: Proceedings of the 15 IPDPS 2000 Workshops on Parallel
  and Distributed Processing},
  year = {2000},
  pages = {443--449},
  address = {London, UK},
  publisher = {Springer-Verlag},
  isbn = {3-540-67442-X},
  tags = {wsdsc},
  url = {http://iss.ices.utexas.edu/Publications/Papers/irregular2000.pdf}
}
@inproceedings{chew03,
  author = { Chew, L. Paul and Chrisochoides, Nikos and Gopalsamy, S and Heber,
  Gerd and Ingraffea, Tony and Luke, Edward and Neto, Joaquim and Pingali,
  Keshav and Shih, Alan and Soni, Bharat and Stodghill, Paul and Thompson,
  David and Vavasis, Stephen and Wawrzynek, Paul },
  title = {Computational Science Simulations based on Web Services},
  booktitle = {International Conference on Computational Science},
  year = {2003},
  month = {06/23/},
  tags = {wsdsc},
  url = {http://iss.ices.utexas.edu/Publications/Papers/ICCS2003.pdf}
}
@inproceedings{chrisochoides97,
  author = {Chrisochoides, Nikos and Kodukula, Induprakas and Pingali, Keshav},
  title = {Data Movement and Control Substrate for Parallel Scientific Computing},
  booktitle = {CANPC '97: Proceedings of the First International Workshop on Communication
  and Architectural Support for Network-Based Parallel Computing},
  year = {1997},
  pages = {256--268},
  address = {London, UK},
  publisher = {Springer-Verlag},
  isbn = {3-540-62573-9},
  url = {http://iss.ices.utexas.edu/Publications/Papers/CANPC1997.pdf}
}
@inproceedings{chrisochoides97a,
  author = {Chrisochoides, Nikos and Kodukula, Induprakas and Pingali, Keshav},
  title = {Compiler and run-time support for semi-structured applications},
  booktitle = {ICS '97: Proceedings of the 11th international conference on Supercomputing},
  year = {1997},
  pages = {229--236},
  address = {New York, NY, USA},
  publisher = {ACM},
  doi = {http://doi.acm.org/10.1145/263580.263639},
  isbn = {0-89791-902-5},
  location = {Vienna, Austria},
  url = {http://iss.ices.utexas.edu/Publications/Papers/ICS1997a.pdf}
}
@inproceedings{donadio05,
  author = {Sebastien Donadio and James Brodman and Thomas Roeder and Kamen Yotov
  and Denis Barthou and Albert Cohen and Mara Jesus Garzaran and David
  Padua and Keshav Pingali and Bull Sa and Inria Futurs},
  title = {A Language for the Compact Representation of Multiple Program Versions},
  booktitle = {In Languages and Compilers for Parallel Computers (LCPC’05), Lecture
  Notes in Computer Science},
  year = {2005},
  pages = {15},
  publisher = {Springer Verlag},
  url = {http://iss.ices.utexas.edu/Publications/Papers/LCPC2005.pdf}
}
@inproceedings{epshteyn05,
  author = {Arkady Epshteyn and Maria Garzaran and Gerald Dejong and David Padua
  and Gang Ren and Xiaoming Li and Kamen Yotov and Keshav Pingali},
  title = {Analytic Models and Empirical Search: A Hybrid Approach to Code Optimization},
  booktitle = {In Proceedings of the International Workshop on Languages and Compilers
  for Parallel Computing (LCPC)},
  year = {2005},
  tags = {eo},
  url = {http://iss.ices.utexas.edu/Publications/Papers/LCPC2005Epshteyn.pdf}
}
@techreport{ezick01,
  author = { Ezick, James and Bilardi, Gianfranco and Pingali, Keshav},
  title = {Efficient Computation of Interprocedural Control Dependence},
  institution = {Cornell Computer Science Department},
  year = {2001},
  month = {08/15/},
  opttype = {Technical Report TR2001-1850},
  tags = {cdc},
  url = {http://iss.ices.utexas.edu/Publications/Papers/TR01-1850.pdf}
}
@techreport{ezick03,
  author = { Ezick, James },
  title = {Resolving Constrained Existential Queries over Context-Sensitive
  Analyses},
  institution = {Cornell University Computing and Information Science},
  year = {2003},
  month = {06/04/},
  opttype = {Technical Report TR2003-1913},
  tags = {mchsm},
  url = {http://iss.ices.utexas.edu/Publications/Papers/TR03-1913.pdf}
}
@inproceedings{ezick04,
  author = {Ezick, James},
  title = {Resolving and applying constraint queries on context-sensitive analyses},
  booktitle = {PASTE '04: Proceedings of the 5th ACM SIGPLAN-SIGSOFT workshop on
  Program analysis for software tools and engineering},
  year = {2004},
  pages = {2--7},
  address = {New York, NY, USA},
  publisher = {ACM},
  doi = {http://doi.acm.org/10.1145/996821.996826},
  isbn = {1-58113-910-1},
  location = {Washington DC, USA},
  tags = {mchsm},
  url = {http://iss.ices.utexas.edu/Publications/Papers/PASTE2004.pdf}
}
@inproceedings{ezick04a,
  author = {Ezick, James},
  title = {An optimizing compiler for batches of temporal logic formulas},
  booktitle = {ISSTA '04: Proceedings of the 2004 ACM SIGSOFT international symposium
  on Software testing and analysis},
  year = {2004},
  pages = {183--194},
  address = {New York, NY, USA},
  publisher = {ACM},
  doi = {http://doi.acm.org/10.1145/1007512.1007537},
  isbn = {1-58113-820-2},
  location = {Boston, Massachusetts, USA},
  tags = {mchsm},
  url = {http://iss.ices.utexas.edu/Publications/Papers/ISSTA2004.pdf}
}
@phdthesis{ezick04b,
  author = {Ezick, James},
  title = {An end-to-end system for model checking over context-sensitive analyses},
  school = {Cornell University},
  year = {2004},
  address = {Ithaca, NY, USA},
  note = {Chair-Pingali, Keshau},
  isbn = {0-496-09317-7},
  order_no = {AAI3149492},
  publisher = {Cornell University},
  tags = {mchsm},
  url = {http://iss.ices.utexas.edu/Publications/Theses/JamesEzick.pdf}
}
@inproceedings{fernandes06,
  author = {Fernandes, Rohit and Pingali, Keshav and Stodghill, Paul},
  title = {Mobile MPI programs in computational grids},
  booktitle = {PPoPP '06: Proceedings of the eleventh ACM SIGPLAN symposium on Principles
  and practice of parallel programming},
  year = {2006},
  pages = {22--31},
  address = {New York, NY, USA},
  publisher = {ACM},
  doi = {http://doi.acm.org/10.1145/1122971.1122977},
  isbn = {1-59593-189-9},
  location = {New York, New York, USA},
  tags = {ft},
  url = {http://iss.ices.utexas.edu/Publications/Papers/PPOPP2006.pdf}
}
@techreport{gupta95,
  author = {Gupta, Sudeep and Pingali, Keshav},
  title = {Fast Compiled Logic Simulation Using Linear BDDs},
  institution = {Cornell University},
  year = {1995},
  address = {Ithaca, NY, USA},
  date-added = {2009-08-21 16:44:07 -0500},
  date-modified = {2009-08-21 16:44:07 -0500},
  publisher = {Cornell University},
  source = {http://www.ncstrl.org:8900/ncstrl/servlet/search?formname=detail\&id=oai%3Ancstrlh%3Acornellcs%3ACORNELLCS%3ATR95-1522}
}
@inproceedings{hassaan11,
  author = {Hassaan, Muhammad Amber and Burtscher, Martin and Pingali, Keshav},
  title = {Ordered vs unordered: a comparison of parallelism and work-efficiency
  in irregular algorithms},
  booktitle = {Proceedings of the 16th ACM symposium on Principles and practice
  of parallel programming},
  year = {2011},
  series = {PPoPP '11},
  pages = {3--12},
  address = {New York, NY, USA},
  publisher = {ACM},
  acmid = {1941557},
  doi = {http://doi.acm.org/10.1145/1941553.1941557},
  isbn = {978-1-4503-0119-0},
  keywords = {amorphous data-parallelism, discrete-event simulation, galois system,
  minimal spanning tree, multicore processors, parallel breadth first
  search, single-source shortest path},
  location = {San Antonio, TX, USA},
  numpages = {10},
  tags = {galois},
  url = {http://iss.ices.utexas.edu/Publications/Papers/ppopp016s-hassaan.pdf}
}
@inproceedings{heber02,
  author = { Heber, Gerd and Lifka, David and Stodghill, Paul },
  title = {Post-Cluster Computing and the Next Generation of Scientific Applications},
  booktitle = {Sixth World Multiconference on Systemics, Cybernetics and Informatics},
  year = {2002},
  month = {07/14/},
  tags = {wsdsc},
  url = {http://iss.ices.utexas.edu/Publications/Papers/sci2002.pdf}
}
@article{huff93,
  author = {Huff, Richard A.},
  title = {Lifetime-sensitive modulo scheduling},
  journal = {SIGPLAN Not.},
  year = {1993},
  volume = {28},
  pages = {258--267},
  number = {6},
  address = {New York, NY, USA},
  bdsk-url-1 = {http://portal.acm.org/ft_gateway.cfm?id=155115&type=pdf&coll=GUIDE&dl=GUIDE&CFID=48352235&CFTOKEN=60105274},
  bdsk-url-2 = {http://doi.acm.org/10.1145/173262.155115},
  date-added = {2009-08-21 16:28:36 -0500},
  date-modified = {2009-08-21 16:28:36 -0500},
  doi = {http://doi.acm.org/10.1145/173262.155115},
  issn = {0362-1340},
  publisher = {ACM},
  url = {http://portal.acm.org/ft_gateway.cfm?id=155115&type=pdf&coll=GUIDE&dl=GUIDE&CFID=48352235&CFTOKEN=60105274}
}
@inproceedings{jagadeesan89,
  author = {Jagadeesan, Radha and Panangaden, Prakash and Pingali, Keshav},
  title = {A fully abstract semantics for a functional language with logic variables
  },
  booktitle = {Proceedings of the Fourth Annual IEEE Symp. on Logic in Computer
  Science, {LICS} 1989},
  year = {1989},
  editor = {Rohit Parikh},
  pages = {294--303},
  month = {June},
  publisher = {IEEE Computer Society Press},
  location = {Pacific Grove, CA, USA},
  tags = {fllv}
}
@phdthesis{jagadeesan91,
  author = {Jagadeesan, Radha},
  title = {Investigations into abstraction and concurrency},
  school = {Cornell University},
  year = {1991},
  tags = {fllv}
}
@techreport{jagadeesan91a,
  author = {Jagadeesan, Radha and Pingali, Keshav},
  title = {Abstract Semantics for a Higher Order Functional Language with Logic
  Variables},
  institution = {Cornell University},
  year = {1991},
  number = {TR 91-1220},
  tags = {fllv}
}
@article{jagadeesan91b,
  author = {Jagadeesan, Radha and Pingali, Keshav and Panangaden, Prakash},
  title = {A fully abstract semantics for a first-order functional language
  with logic variables},
  journal = {{ACM} {T}ransactions on {P}rogramming {L}anguages and {S}ystems},
  year = {1991},
  volume = {13},
  pages = {577--625},
  number = {4},
  address = {New York, NY, USA},
  doi = {http://doi.acm.org/10.1145/115372.115371},
  issn = {0164-0925},
  publisher = {ACM}
}
@inproceedings{jagadeesan92,
  author = {Jagadeesan, Radha and Pingali, Keshav},
  title = {Abstract semantics for a higher-order functional language with logic
  variables},
  booktitle = {POPL '92: Proceedings of the 19th ACM SIGPLAN-SIGACT symposium on
  Principles of programming languages},
  year = {1992},
  pages = {355--366},
  address = {New York, NY, USA},
  publisher = {ACM},
  bdsk-url-1 = {http://portal.acm.org/ft_gateway.cfm?id=143236&type=pdf&coll=GUIDE&dl=GUIDE&CFID=48352099&CFTOKEN=85554553},
  bdsk-url-2 = {http://doi.acm.org/10.1145/143165.143236},
  date-added = {2009-08-21 16:26:58 -0500},
  date-modified = {2009-08-21 16:26:58 -0500},
  doi = {http://doi.acm.org/10.1145/143165.143236},
  isbn = {0-89791-453-8},
  location = {Albuquerque, New Mexico, United States},
  tags = {fllv},
  url = {http://portal.acm.org/ft_gateway.cfm?id=143236&type=pdf&coll=GUIDE&dl=GUIDE&CFID=48352099&CFTOKEN=85554553}
}
@inproceedings{johnson91,
  author = {Johnson, Richard and Li, Wei and Pingali, Keshav},
  title = {An executable representation of distance and direction},
  booktitle = {Workshop on {L}anguages and {C}ompilers for {P}arallel {C}omputing
  ({LCPC})},
  year = {1991},
  tags = {pidgin, pr}
}
@inproceedings{johnson93,
  author = {Johnson, Richard and Pingali, Keshav},
  title = {Dependence-based program analysis},
  booktitle = {PLDI '93: Proceedings of the ACM SIGPLAN 1993 conference on Programming
  language design and implementation},
  year = {1993},
  pages = {78--89},
  address = {New York, NY, USA},
  publisher = {ACM},
  bdsk-url-1 = {http://portal.acm.org/ft_gateway.cfm?id=155098&type=pdf&coll=GUIDE&dl=GUIDE&CFID=48352316&CFTOKEN=72896644},
  bdsk-url-2 = {http://doi.acm.org/10.1145/155090.155098},
  date-added = {2009-08-21 16:29:59 -0500},
  date-modified = {2009-08-21 16:29:59 -0500},
  doi = {http://doi.acm.org/10.1145/155090.155098},
  isbn = {0-89791-598-4},
  location = {Albuquerque, New Mexico, United States},
  tags = {cdc},
  url = {http://portal.acm.org/ft_gateway.cfm?id=155098&type=pdf&coll=GUIDE&dl=GUIDE&CFID=48352316&CFTOKEN=72896644}
}
@inproceedings{johnson94,
  author = {Johnson, Richard and Pearson, David and Pingali, Keshav},
  title = {The program structure tree: computing control regions in linear time},
  booktitle = {PLDI '94: Proceedings of the ACM SIGPLAN 1994 conference on Programming
  language design and implementation},
  year = {1994},
  pages = {171--185},
  address = {New York, NY, USA},
  publisher = {ACM},
  doi = {http://doi.acm.org/10.1145/178243.178258},
  isbn = {0-89791-662-X},
  location = {Orlando, Florida, United States},
  tags = {cdc}
}
@phdthesis{johnson95,
  author = {Johnson, Richard},
  title = {Efficient program analysis using dependence flow graphs},
  school = {Cornell University},
  year = {1995},
  address = {Ithaca, NY, USA},
  date-added = {2009-08-21 16:41:30 -0500},
  date-modified = {2009-08-21 16:41:30 -0500},
  order_no = {UMI Order No. GAX95-11882},
  publisher = {Cornell University},
  tags = {pidgin, pr}
}
@article{kodukula01,
  author = { Kodukula, Induprakas and Pingali, Keshav },
  title = {Data-Centric Transformations for Locality Enhancement},
  journal = {International Journal of Parallel Programming},
  year = {2001},
  month = {10/01/},
  tags = {mho},
  url = {http://iss.ices.utexas.edu/Publications/Papers/IJPP2001b.pdf}
}
@inproceedings{kodukula96,
  author = {Kodukula, Induprakas and Pingali, Keshav},
  title = {Transformations for imperfectly nested loops},
  booktitle = {Supercomputing '96: Proceedings of the 1996 ACM/IEEE conference on
  Supercomputing (CDROM)},
  year = {1996},
  pages = {12},
  address = {Washington, DC, USA},
  publisher = {IEEE Computer Society},
  doi = {http://doi.acm.org/10.1145/369028.369051},
  isbn = {0-89791-854-1},
  location = {Pittsburgh, Pennsylvania, United States},
  tags = {mho},
  url = {http://iss.ices.utexas.edu/Publications/Papers/SC1996.pdf}
}
@inproceedings{kodukula97,
  author = {Kodukula, Induprakas and Ahmed, Nawaaz and Pingali, Keshav},
  title = {Data-centric multi-level blocking},
  booktitle = {PLDI '97: Proceedings of the ACM SIGPLAN 1997 conference on Programming
  language design and implementation},
  year = {1997},
  pages = {346--357},
  address = {New York, NY, USA},
  publisher = {ACM},
  doi = {http://doi.acm.org/10.1145/258915.258946},
  isbn = {0-89791-907-6},
  location = {Las Vegas, Nevada, United States},
  tags = {mho},
  url = {http://iss.ices.utexas.edu/Publications/Papers/PLDI1997.pdf}
}
@phdthesis{kodukula98,
  author = {Kodukula, Induprakas},
  title = {Data-centric compilation},
  school = {Cornell University},
  year = {1998},
  address = {Ithaca, NY, USA},
  isbn = {0-591-96991-2},
  order_no = {AAI9900086},
  publisher = {Cornell University},
  tags = {mho},
  url = {http://iss.ices.utexas.edu/Publications/Theses/InduprakasKodukula.pdf}
}
@inproceedings{kodukula99,
  author = {Kodukula, Induprakas and Pingali, Keshav and Cox, Robert and Maydan,
  Dror},
  title = {An experimental evaluation of tiling and shackling for memory hierarchy
  management},
  booktitle = {ICS '99: Proceedings of the 13th international conference on Supercomputing},
  year = {1999},
  pages = {482--491},
  address = {New York, NY, USA},
  publisher = {ACM},
  doi = {http://doi.acm.org/10.1145/305138.305243},
  isbn = {1-58113-164-X},
  location = {Rhodes, Greece},
  tags = {mho},
  url = {http://iss.ices.utexas.edu/Publications/Papers/ICS1999b.pdf}
}
@inproceedings{kotlyar97,
  author = {Kotlyar, Vladimir and Pingali, Keshav},
  title = {Sparse code generation for imperfectly nested loops with dependences},
  booktitle = {ICS '97: Proceedings of the 11th international conference on Supercomputing},
  year = {1997},
  pages = {188--195},
  address = {New York, NY, USA},
  publisher = {ACM},
  doi = {http://doi.acm.org/10.1145/263580.263630},
  isbn = {0-89791-902-5},
  location = {Vienna, Austria},
  tags = {sic},
  url = {http://iss.ices.utexas.edu/Publications/Papers/ICS1997b.pdf}
}
@inproceedings{kotlyar97a,
  author = {Kotlyar, Vladimir and Pingali, Keshav and Stodghill, Paul},
  title = {A Relational Approach to the Compilation of Sparse Matrix Programs},
  booktitle = {Euro-Par '97: Proceedings of the Third International Euro-Par Conference
  on Parallel Processing},
  year = {1997},
  pages = {318--327},
  address = {London, UK},
  publisher = {Springer-Verlag},
  isbn = {3-540-63440-1},
  tags = {bsct, sic},
  url = {http://iss.ices.utexas.edu/Publications/Papers/EUROPAR1997.pdf}
}
@inproceedings{kotlyar97b,
  author = {Kotlyar, Vladimir and Pingali, Keshav and Stodghill, Paul},
  title = {Compiling parallel code for sparse matrix applications},
  booktitle = {Supercomputing '97: Proceedings of the 1997 ACM/IEEE conference on
  Supercomputing (CDROM)},
  year = {1997},
  pages = {1--18},
  address = {New York, NY, USA},
  publisher = {ACM},
  doi = {http://doi.acm.org/10.1145/509593.509603},
  isbn = {0-89791-985-8},
  location = {San Jose, CA},
  tags = {sic},
  url = {http://iss.ices.utexas.edu/Publications/Papers/SC1997.pdf}
}
@techreport{kotlyar97c,
  author = {Kotlyar, Vladimir and Pingali, Keshav and Stodghill, Paul},
  title = {Compiling Parallel Sparse Code for User-Defined Data Structures},
  institution = {Cornell University},
  year = {1997},
  address = {Ithaca, NY, USA},
  publisher = {Cornell University},
  source = {http://www.ncstrl.org:8900/ncstrl/servlet/search?formname=detail\&id=oai%3Ancstrlh%3Acornellcs%3ACORNELLCS%3ATR97-1633},
  tags = {sic},
  url = {http://iss.ices.utexas.edu/Publications/Papers/SIAM-PP1997b.pdf}
}
@techreport{kotlyar97d,
  author = {Kotlyar, Vladimir and Pingali, Keshav and Stodghill, Paul},
  title = {Unified framework for sparse and dense {SPMD} code generation },
  institution = {Cornell University},
  year = {1997},
  address = {Ithaca, NY, USA},
  publisher = {Cornell University},
  source = {http://www.ncstrl.org:8900/ncstrl/servlet/search?formname=detail\&id=oai%3Ancstrlh%3Acornellcs%3ACORNELLCS%3ATR97-1625},
  tags = {sic},
  url = {http://iss.ices.utexas.edu/Publications/Papers/TR97-1625.pdf}
}
@phdthesis{kotlyar99,
  author = {Kotlyar, Vladimir},
  title = {Relational Algebraic Techniques for the Synthesis of Sparse Matrix
  Programs},
  school = {Cornell University},
  year = {1999},
  address = {Ithaca, NY, USA},
  publisher = {Cornell University},
  source = {http://www.ncstrl.org:8900/ncstrl/servlet/search?formname=detail\&id=oai%3Ancstrlh%3Acornellcs%3ACORNELLCS%3ATR99-1732},
  url = {http://iss.ices.utexas.edu/Publications/Theses/VladimirKotlyar.pdf}
}
@inproceedings{kulkarni06,
  author = {Milind Kulkarni and L. Paul Chew and Keshav Pingali},
  title = {Using Transactions in Delaunay Mesh Generation },
  booktitle = { Workshop on Transactional Memory Workloads (WTW '06)},
  year = {2006},
  publisher = {Springer Verlag},
  url = {http://iss.ices.utexas.edu/Publications/Papers/WTW2006.pdf}
}
@article{kulkarni07,
  author = {Milind Kulkarni and Keshav Pingali and Bruce Walter and Ganesh Ramanarayanan
  and Kavita Bala and L. Paul Chew},
  title = {Optimistic parallelism requires abstractions},
  journal = {SIGPLAN Not. (Proceedings of PLDI)},
  year = {2007},
  volume = {42},
  pages = {211--222},
  number = {6},
  address = {New York, NY, USA},
  bdsk-url-1 = {http://doi.acm.org/10.1145/1273442.1250759},
  date-added = {2008-10-08 19:01:42 -0500},
  date-modified = {2008-10-08 19:01:42 -0500},
  doi = {http://doi.acm.org/10.1145/1273442.1250759},
  group = {My Papers},
  issn = {0362-1340},
  publisher = {ACM},
  tags = {galois},
  url = {http://iss.ices.utexas.edu/Publications/Papers/PLDI2007.pdf}
}
@inproceedings{kulkarni08,
  author = {Kulkarni, Milind and Carribault, Patrick and Pingali, Keshav and
  Ramanarayanan, Ganesh and Walter, Bruce and Bala, Kavita and Chew,
  L. Paul},
  title = {Scheduling strategies for optimistic parallel execution of irregular
  programs},
  booktitle = {Proc. Symp. on Parallelism in algorithms and architectures (SPAA)},
  year = {2008},
  pages = {217--228},
  address = {New York, NY, USA},
  doi = {http://doi.acm.org/10.1145/1378533.1378575},
  isbn = {978-1-59593-973-9},
  location = {Munich, Germany},
  url = {http://iss.ices.utexas.edu/Publications/Papers/SPAA2008.pdf}
}
@article{kulkarni08a,
  author = {Kulkarni, Milind and Pingali, Keshav},
  title = {An Experimental Study of Self-Optimizing Dense Linear Algebra Software},
  journal = {Proceedings of the IEEE},
  year = {2008},
  volume = {96},
  pages = {832-848},
  number = {5},
  month = {May},
  doi = {10.1109/JPROC.2008.917732},
  issn = {0018-9219},
  keywords = {cache storage, divide and conquer methods, linear algebra, mathematics
  computing, matrix multiplication, memory architecture, program compilers,
  self-adjusting systemsapproximate blocking, cache blocking, cache
  memory, cache-oblivious approach, compiler generated-code, dense
  linear algebra kernel, divide-and-conquer, generate-and-test approach,
  matrix multiplication, memory architecture, portable memory hierarchy
  optimization, self-optimizing dense linear algebra software, self-optimizing
  software system},
  tags = {eo},
  url = {http://iss.ices.utexas.edu/Publications/Papers/IEEE2008.pdf}
}
@article{kulkarni08b,
  author = {Kulkarni, Milind and Pingali, Keshav and Ramanarayanan, Ganesh and
  Walter, Bruce and Bala, Kavita and Chew, L. Paul},
  title = {Optimistic parallelism benefits from data partitioning},
  journal = {SIGARCH Comput. Archit. News},
  year = {2008},
  volume = {36},
  pages = {233--243},
  number = {1},
  address = {New York, NY, USA},
  doi = {http://doi.acm.org/10.1145/1353534.1346311},
  issn = {0163-5964},
  publisher = {ACM},
  url = {http://iss.ices.utexas.edu/Publications/Papers/ASPLOS2008.pdf}
}
@inproceedings{kulkarni09,
  author = {Kulkarni, Milind and Burtscher, Martin and Cas\c{c}aval, Calin and
  Pingali, Keshav},
  title = {Lonestar: A Suite of Parallel Irregular Programs},
  booktitle = {ISPASS '09: IEEE International Symposium on Performance Analysis
  of Systems and Software},
  year = {2009},
  location = {Boston, MA, USA},
  tags = {galois},
  url = {http://iss.ices.utexas.edu/Publications/Papers/ispass2009.pdf}
}
@inproceedings{kulkarni09a,
  author = {Kulkarni, Milind and Burtscher, Martin and Inkulu, Rajasekhar and
  Pingali, Keshav and Cas\c{c}aval, Calin},
  title = {How much parallelism is there in irregular applications?},
  booktitle = {Proc. Symp. on Principles and practice of parallel programming (PPoPP)},
  year = {2009},
  pages = {3--14},
  address = {New York, NY, USA},
  doi = {http://doi.acm.org/10.1145/1504176.1504181},
  isbn = {978-1-60558-397-6},
  location = {Raleigh, NC, USA},
  tags = {galois},
  url = {http://iss.ices.utexas.edu/Publications/Papers/ppopp2009.pdf}
}
@techreport{kulkarni09b,
  author = {Milind Kulkarni and Dimitrios Prountzos and Donald Nguyen and Keshav
  Pingali},
  title = {Defining and Implementing Commutativity Conditions for Parallel Execution},
  institution = {School of Electrial and Computer Engineering, Purdue University},
  year = {2009},
  type = {regular rech report},
  number = {TR-ECE-09-11},
  month = {August},
  tags = {galois},
  url = {https://engineering.purdue.edu/~milind/docs/tr-ece-09-11.pdf}
}
@inproceedings{li92,
  author = {Li, Wei and Pingali, Keshav},
  title = {Access normalization: loop restructuring for NUMA compilers},
  booktitle = {ASPLOS-V: Proceedings of the fifth international conference on Architectural
  support for programming languages and operating systems},
  year = {1992},
  pages = {285--295},
  address = {New York, NY, USA},
  publisher = {ACM},
  bdsk-url-1 = {http://portal.acm.org/ft_gateway.cfm?id=143541&type=pdf&coll=GUIDE&dl=portal,ACM&CFID=48353676&CFTOKEN=51596766},
  bdsk-url-2 = {http://doi.acm.org/10.1145/143365.143541},
  date-added = {2009-08-21 16:48:04 -0500},
  date-modified = {2009-08-21 16:48:04 -0500},
  doi = {http://doi.acm.org/10.1145/143365.143541},
  isbn = {0-89791-534-8},
  location = {Boston, Massachusetts, United States},
  tags = {lambda, mho},
  url = {http://portal.acm.org/ft_gateway.cfm?id=143541&type=pdf&coll=GUIDE&dl=portal,ACM&CFID=48353676&CFTOKEN=51596766}
}
@phdthesis{li93,
  author = {Li, Wei},
  title = {Compiling for {NUMA} parallel machines},
  school = {Cornell University},
  year = {1993},
  address = {Ithaca, NY, USA},
  date-added = {2009-08-21 16:32:52 -0500},
  date-modified = {2009-08-21 16:32:52 -0500},
  order_no = {UMI Order No. GAX94-06185},
  publisher = {Cornell University},
  tags = {mho}
}
@article{li93a,
  author = {Li, Wei and Pingali, Keshav},
  title = {Access normalization: Loop restructuring for NUMA compilers},
  journal = {ACM Transactions on Computer Systems},
  year = {1993},
  volume = {11},
  pages = {353-375},
  bdsk-url-1 = {http://130.203.133.121:8080/viewdoc/summary?doi=10.1.1.30.7553},
  date-added = {2009-08-21 16:50:54 -0500},
  date-modified = {2009-08-21 16:50:54 -0500},
  doi = {10.1.1.30.7553},
  tags = {mho}
}
@techreport{li94,
  author = {Wei Li and Li, Wei and Pingali, Keshav},
  title = {The Lambda Loop Transformation Toolkit (User's Reference Manual)},
  institution = {Cornell University},
  year = {1994},
  bdsk-url-1 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.53.50},
  date-added = {2009-08-21 16:36:42 -0500},
  date-modified = {2009-08-21 16:36:42 -0500},
  doi = {10.1.1.53.50},
  tags = {lambda, mho}
}
@inproceedings{mateev00,
  author = {Mateev, Nikolay and Menon, Vijay and Pingali, Keshav},
  title = {Left-Looking to Right-Looking and Vice Versa: An Application of Fractal
  Symbolic Analysis to Linear Algebra Code Restructuring},
  booktitle = {Euro-Par '00: Proceedings from the 6th International Euro-Par Conference
  on Parallel Processing},
  year = {2000},
  pages = {379--388},
  address = {London, UK},
  publisher = {Springer-Verlag},
  isbn = {3-540-67956-1},
  tags = {fsa},
  url = {http://iss.ices.utexas.edu/Publications/Papers/EUROPAR2000c.pdf}
}
@techreport{mateev00a,
  author = {Mateev, Nikolay and Menon, Vijay and Pingali, Keshav},
  title = {Fractal Symbolic Analysis for Program Transformations},
  institution = {Cornell University},
  year = {2000},
  address = {Ithaca, NY, USA},
  publisher = {Cornell University},
  source = {http://www.ncstrl.org:8900/ncstrl/servlet/search?formname=detail\&id=oai%3Ancstrlh%3Acornellcs%3ACORNELLCS%3ATR2000-1781},
  tags = {fsa},
  url = {http://iss.ices.utexas.edu/Publications/Papers/TR00-1781.pdf}
}
@inproceedings{mateev00b,
  author = {Mateev, Nikolay and Pingali, Keshav and Stodghill, Paul and Kotlyar,
  Vladimir},
  title = {Next-generation generic programming and its application to sparse
  matrix computations},
  booktitle = {ICS '00: Proceedings of the 14th international conference on Supercomputing},
  year = {2000},
  pages = {88--99},
  address = {New York, NY, USA},
  publisher = {ACM},
  doi = {http://doi.acm.org/10.1145/335231.335240},
  isbn = {1-58113-270-0},
  location = {Santa Fe, New Mexico, United States},
  tags = {sic},
  url = {http://iss.ices.utexas.edu/Publications/Papers/ICS2000.pdf}
}
@inproceedings{mateev01,
  author = { Mateev, Nikolay and Menon, Vijay and Pingali, Keshav },
  title = {Fractal Symbolic Analysis},
  booktitle = { International Conference on Supercomputing},
  year = {2001},
  month = {06/16/},
  tags = {fsa},
  url = {http://iss.ices.utexas.edu/Publications/Papers/ICS2001.pdf}
}
@inproceedings{mendez-lojo10,
  author = {Mario Mendez-Lojo and Augustine Mathew and Keshav Pingali},
  title = {Parallel Inclusion-based Points-to Analysis},
  booktitle = {Proceedings of the {ACM SIGPLAN} Conference on Object-Oriented
  Programming, Systems, Languages, and Applications},
  series = {OOPSLA '10},
  year = {2010},
  month = {October},
  location = {Reno, USA},
  tags = {galois},
  doi = {10.1145/1932682.1869495},
  url = {http://iss.ices.utexas.edu/Publications/Papers/oopsla10-mendezlojo.pdf}
}
@inproceedings{mendez-lojo10a,
  author = {Mario Mendez-Lojo and Donald Nguyen and Dimitrios Prountzos and Xin
  Sui and M. Amber Hassaan and Milind Kulkarni and Martin Burtscher
  and Keshav Pingali},
  title = {Structure-driven Optimizations for Amorphous Data-parallel Programs},
  booktitle = {Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of
  Parallel Programming},
  year = {2010},
  series = {PPoPP '10},
  pages = {3--14},
  doi = {10.1145/1837853.1693457},
  location = {Bangalore, India},
  tags = {galois},
  url = {http://iss.ices.utexas.edu/Publications/Papers/PPoPP2010.pdf}
}
@article{menon03,
  author = { Menon, Vijay and Pingali, Keshav },
  title = {Look Left, Look Right, Look Left Again: An Application of Fractal
  Symbolic Analysis to Linear Algebra Code Restructuring},
  journal = {(submitted to) International Journal of Parallel Programming},
  year = {2003},
  month = {03/16/},
  tags = {fsa},
  url = {http://iss.ices.utexas.edu/Publications/Papers/IJPP2003.pdf}
}
@article{menon03a,
  author = { Menon, Vijay and Pingali, Keshav and Mateev, Nikolay },
  title = {Fractal Symbolic Analysis},
  journal = {Transactions on Programming Languages and Systems, TOPLAS},
  year = {2003},
  month = {03/16/},
  tags = {fsa},
  url = {http://iss.ices.utexas.edu/Publications/Papers/TOPLAS2003.pdf}
}
@inproceedings{menon99,
  author = {Menon, Vijay and Pingali, Keshav},
  title = {High-level semantic optimization of numerical codes},
  booktitle = {ICS '99: Proceedings of the 13th international conference on Supercomputing},
  year = {1999},
  pages = {434--443},
  address = {New York, NY, USA},
  publisher = {ACM},
  doi = {http://doi.acm.org/10.1145/305138.305230},
  isbn = {1-58113-164-X},
  location = {Rhodes, Greece},
  url = {http://iss.ices.utexas.edu/Publications/Papers/ICS1999a.pdf}
}
@inproceedings{menon99a,
  author = {Menon, Vijay and Pingali, Keshav},
  title = {A case for source-level transformations in MATLAB},
  booktitle = {PLAN '99: Proceedings of the 2nd conference on Domain-specific languages},
  year = {1999},
  pages = {53--65},
  address = {New York, NY, USA},
  publisher = {ACM},
  doi = {http://doi.acm.org/10.1145/331960.331972},
  isbn = {1-58113-255-7},
  location = {Austin, Texas, United States},
  url = {http://iss.ices.utexas.edu/Publications/Papers/DSL1999.pdf}
}
@article{moudgill93,
  author = {Mayan Moudgill and Moudgill, Mayan and Pingali, Keshav and Vassiliadis,
  Stamatis},
  title = {Register Renaming and Dynamic Speculation: an Alternative Approach},
  journal = {IN PROCEEDINGS OF MICRO-26},
  year = {1993},
  pages = {202--213},
  bdsk-url-1 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.47.9283},
  date-added = {2009-08-21 16:35:08 -0500},
  date-modified = {2009-08-21 16:35:08 -0500},
  doi = {10.1.1.47.9283}
}
@inproceedings{nguyen11,
  author = {Donald Nguyen and Keshav Pingali},
  title = {Synthesizing Concurrent Schedulers for Irregular Algorithms},
  booktitle = {Proceedings of International Conference on Architectural
  Support for Programming Languages and Operating Systems},
  series = {ASPLOS '11},
  doi = {10.1145/1961296.1950404},
  pages = {333--344},
  numpages = {12},
  year = {2011},
  tags = {galois},
  url = {http://iss.ices.utexas.edu/Publications/Papers/nguyen11.pdf}
}
@inproceedings{nguyen13,
  author = {Donald Nguyen and Andrew Lenharth and Keshav Pingali},
  title = {A Lightweight Infrastructure for Graph Analytics},
  booktitle = {Proceedings of ACM Symposium on Operating Systems Principles},
  series = {SOSP '13},
  year = {2013},
  tags = {galois},
  isbn = {978-1-4503-2388-8},
  location = {Farminton, Pennsylvania},
  pages = {456--471},
  numpages = {16},
  doi = {10.1145/2517349.2522739},
  acmid = {2522739},
  url = {http://iss.ices.utexas.edu/Publications/Papers/nguyen13.pdf}
}
@inproceedings{prountzos12,
  author = {Dimitrios Prountzos and Roman Manevich and Keshav Pingali},
  title = {Elixir: A System for Synthesizing Concurrent Graph Programs},
  booktitle = {Proceedings of the Conference on Object-Oriented
  Programming, Systems, Languages, and Applications},
  series = {OOPSLA '12},
  doi = {10.1145/2398857.2384644},
  year = {2012},
  tags = {galois},
  url = {http://iss.ices.utexas.edu/Publications/Papers/prountzos12.pdf}
}
@inproceedings{sui12,
  author = {Xin Sui and Tsung-Hsien Lee and Joyce Jiyoung Whang and Berkant Savas and Saral Jain and Keshav Pingali and Inderjit Dhillon},
  title = {Parallel Clustered Low-rank Approximation of Graphs and Its Application to Link Prediction},
  booktitle = {Proceedings of the International Workshop on Languages and Compilers for Parallel Computing},
  series = {LCPC '12},
  year = {2012},
  doi = {10.1007/978-3-642-37658-0_6},
  url = {http://iss.ices.utexas.edu/Publications/Papers/xui12.pdf},
  tags = {galois}
}
@inproceedings{burtscher12,
  author = {Martin Burtscher and Rupesh Nasre and Keshav Pingali},
  booktitle = {IEEE International Symposium on Workload Characterization (IISWC) },
  title = {A quantitative study of irregular programs on {GPUs}},
  year = {2012},
  pages = {141--151},
  doi = {10.1109/IISWC.2012.6402918},
  tags = {galois},
  url = {http://iss.ices.utexas.edu/Publications/Papers/burtscher12.pdf}
}
@inproceedings{nasre12,
  author = {Rupesh Nasre},
  title = {Exploiting the structure of the constraint graph for efficient points-to analysis},
  booktitle = {Proceedings of the International Symposium on Memory Management},
  series = {ISMM '12},
  year = {2012},
  pages = {121-132},
  ee = {http://doi.acm.org/10.1145/2258996.2259013},
  doi = {10.1145/2426642.2259013},
  tags = {galois},
  bibsource = {DBLP, http://dblp.uni-trier.de}
}
@inproceedings{mendez-lojo12,
  author = {Mario M{\'e}ndez-Lojo and Martin Burtscher and Keshav Pingali},
  title = {A {GPU} implementation of inclusion-based points-to analysis},
  booktitle = {Proceedings of the 17th ACM SIGPLAN Symposium on Principles
               and Practice of Parallel Programming},
  series = {PPoPP '12},
  year = {2012},
  pages = {107-116},
  doi = {10.1145/2145816.2145831},
  ee = {http://doi.acm.org/10.1145/2145816.2145831},
  url = {http://iss.ices.utexas.edu/Publications/Papers/mendez-lojo12.pdf},
  tags = {galois},
  bibsource = {DBLP, http://dblp.uni-trier.de}
}
@inproceedings{pingali06,
  author = {Pingali, Keshav and Stodghill, Paul},
  title = {A distributed system based on web services for computational science
  simulations},
  booktitle = {ICS '06: Proceedings of the 20th annual international conference
  on Supercomputing},
  year = {2006},
  pages = {297--306},
  address = {New York, NY, USA},
  publisher = {ACM},
  doi = {http://doi.acm.org/10.1145/1183401.1183443},
  isbn = {1-59593-282-8},
  location = {Cairns, Queensland, Australia},
  tags = {wsdsc},
  url = {http://iss.ices.utexas.edu/Publications/Papers/ICS2006Pingali.pdf}
}
@techreport{pingali09,
  author = {Keshav Pingali and Milind Kulkarni and Donald Nguyen and Martin Burtscher
  and Mario Mendez-Lojo and Dimitrios Prountzos and Xin Sui and Zifei
  Zhong},
  title = {Amorphous Data-parallelism in Irregular Algorithms},
  institution = {The University of Texas at Austin},
  year = {2009},
  type = {regular tech report},
  number = {TR-09-05},
  tags = {galois},
  url = {ftp://ftp.cs.utexas.edu/pub/techreports/tr09-05.pdf}
}
@techreport{pingali87,
  author = {Keshav Pingali},
  title = {Lazy evaluation and the logic variable},
  institution = {Cornell University},
  year = {1987},
  number = {TR 87-877},
  tags = {fllv}
}
@techreport{pingali88,
  author = {Keshav Pingali},
  title = {Fine-grain compilation for pipelined machines},
  institution = {Cornell University},
  year = {1988}
}
@inproceedings{pingali90,
  author = {Pingali, Keshav and Beck, Micah and Johnson, Richard and Moudgill,
  Mayan and Johnson, Richard},
  title = {Dependence flow graphs: an algebraic approach to program dependencies},
  booktitle = {Proceedings of the Workshop on Languages and Compilers for Parallel
  Computing (LCPC)},
  year = {1990},
  tags = {pidgin, pr}
}
@techreport{pingali90a,
  author = {Pingali, Keshav and Rogers, Anne},
  title = {Compiler parallelization of {SIMPLE} for a distributed-memory machine},
  institution = {Cornell University},
  year = {1990},
  tags = {cdmc}
}
@inproceedings{pingali91,
  author = {Pingali, Keshav and Beck, Micah and Johnson, Richard and Moudgill,
  Mayan and Stodghill, Paul},
  title = {Dependence flow graphs: an algebraic approach to program dependencies},
  booktitle = {POPL '91: Proceedings of the 18th ACM SIGPLAN-SIGACT symposium on
  Principles of programming languages},
  year = {1991},
  pages = {67--78},
  address = {New York, NY, USA},
  publisher = {ACM},
  doi = {http://doi.acm.org/10.1145/99583.99595},
  isbn = {0-89791-419-8},
  location = {Orlando, Florida, United States},
  tags = {pidgin, pr}
}
@article{pingali91a,
  author = {Pingali, Keshav and Ekanadham, Kattamuri},
  title = {Accumulators: new logic variable abstractions for functional languages},
  journal = {Theoretical {C}omputer {S}cience},
  year = {1991},
  volume = {81},
  number = {2},
  tags = {fllv}
}
@article{pingali95,
  author = {Pingali, Keshav and Bilardi, Gianfranco},
  title = {APT: a data structure for optimal control dependence computation},
  journal = {SIGPLAN Not.},
  year = {1995},
  volume = {30},
  pages = {32--46},
  number = {6},
  address = {New York, NY, USA},
  bdsk-url-1 = {http://portal.acm.org/ft_gateway.cfm?id=207114&type=pdf&coll=GUIDE&dl=GUIDE&CFID=48353393&CFTOKEN=10986308},
  bdsk-url-2 = {http://doi.acm.org/10.1145/223428.207114},
  date-added = {2009-08-21 16:44:43 -0500},
  date-modified = {2009-08-21 16:44:43 -0500},
  doi = {http://doi.acm.org/10.1145/223428.207114},
  issn = {0362-1340},
  publisher = {ACM},
  tags = {cdc},
  url = {http://portal.acm.org/ft_gateway.cfm?id=207114&type=pdf&coll=GUIDE&dl=GUIDE&CFID=48353393&CFTOKEN=10986308}
}
@article{pingali97,
  author = {Pingali, Keshav and Bilardi, Gianfranco},
  title = {Optimal control dependence computation and the Roman chariots problem},
  journal = {ACM Trans. Program. Lang. Syst.},
  year = {1997},
  volume = {19},
  pages = {462--491},
  number = {3},
  address = {New York, NY, USA},
  doi = {http://doi.acm.org/10.1145/256167.256217},
  issn = {0164-0925},
  publisher = {ACM},
  tags = {cdc},
  url = {http://iss.ices.utexas.edu/Publications/Papers/TOPLAS1997.pdf}
}
@inproceedings{prountzos11,
  author = {Prountzos, Dimitrios and Manevich, Roman and Pingali, Keshav and
  McKinley, Kathryn S.},
  title = {A shape analysis for optimizing parallel graph programs},
  booktitle = {Proceedings of the 38th annual ACM SIGPLAN-SIGACT symposium on Principles
  of programming languages},
  year = {2011},
  series = {POPL '11},
  pages = {159--172},
  address = {New York, NY, USA},
  publisher = {ACM},
  acmid = {1926405},
  doi = {http://doi.acm.org/10.1145/1926385.1926405},
  isbn = {978-1-4503-0490-0},
  keywords = {abstract interpretation, amorphous data-parallelism, cautious operators,
  compiler optimization, concurrency, irregular programs, optimistic
  parallelization, parallelism, shape analysis, static analysis, synchronization
  overheads},
  location = {Austin, Texas, USA},
  numpages = {14},
  tags = {galois},
  url = {http://iss.ices.utexas.edu/Publications/Papers/prountzos11.pdf}
}
@inproceedings{rogers89,
  author = {Rogers, Anne and Pingali, Keshav},
  title = {Process decomposition through locality of reference},
  booktitle = {PLDI '89: Proceedings of the ACM SIGPLAN 1989 Conference on Programming
  language design and implementation},
  year = {1989},
  pages = {69--80},
  address = {New York, NY, USA},
  publisher = {ACM},
  doi = {http://doi.acm.org/10.1145/73141.74824},
  isbn = {0-89791-306-X},
  location = {Portland, Oregon, United States},
  tags = {cdmc}
}
@article{rogers94,
  author = {Rogers, Anne and Pingali, Keshav},
  title = {Compiling for Distributed Memory Architectures},
  journal = {IEEE Trans. Parallel Distrib. Syst.},
  year = {1994},
  volume = {5},
  pages = {281--298},
  number = {3},
  address = {Piscataway, NJ, USA},
  bdsk-url-1 = {http://portal.acm.org/ft_gateway.cfm?id=629268&type=external&coll=GUIDE&dl=GUIDE&CFID=48353017&CFTOKEN=43908872},
  bdsk-url-2 = {http://dx.doi.org/10.1109/71.277789},
  date-added = {2009-08-21 16:39:26 -0500},
  date-modified = {2009-08-21 16:39:26 -0500},
  doi = {http://dx.doi.org/10.1109/71.277789},
  issn = {1045-9219},
  publisher = {IEEE Press},
  tags = {cdmc},
  url = {http://portal.acm.org/ft_gateway.cfm?id=629268&type=external&coll=GUIDE&dl=GUIDE&CFID=48353017&CFTOKEN=43908872}
}
@inproceedings{schulz04,
  author = {Martin Schulz and Greg Bronevetsky and Rohit Fernandes and Daniel
  Marques and Keshav Pingali and Paul Stodghill},
  title = {Implementation and Evaluation of a Scalable Application-level Checkpoint-Recovery
  Scheme for MPI Programs},
  booktitle = {In ACM/IEEE SC2004},
  year = {2004},
  pages = {38--51},
  tags = {ft}
}
@phdthesis{stodghill97,
  author = {Stodghill, Paul},
  title = {A Relational Approach to the Automatic Generation of Sequential Sparse
  Matrix Codes},
  school = {Cornell University},
  year = {1997},
  address = {Ithaca, NY, USA},
  publisher = {Cornell University},
  source = {http://www.ncstrl.org:8900/ncstrl/servlet/search?formname=detail\&id=oai%3Ancstrlh%3Acornellcs%3ACORNELLCS%3ATR97-1635},
  tags = {sic},
  url = {http://iss.ices.utexas.edu/Publications/Theses/PaulStodghill.pdf}
}
@inproceedings{sui10,
  author = {Xin Sui and Donald Nguyen and Martin Burtscher and Keshav Pingali},
  title = {Parallel Graph Partitioning on Multicore Architectures},
  booktitle = {Proceedings of the International Workshop on Languages
  and Compilers for Parallel Computing},
  year = {2010},
  series = {LCPC '10},
  tags = {galois},
  url = {http://www.cs.utexas.edu/~ddn/papers/sui10.pdf}
}
@inproceedings{theobald00,
  author = {Theobald, Kevin B. and Agrawal, Gagan and Kumar, Rishi and Heber,
  Gerd and Gao, Guang R. and Stodghill, Paul and Pingali, Keshav},
  title = {Landing CG on EARTH: a case study of fine-grained multithreading
  on an evolutionary path},
  booktitle = {Supercomputing '00: Proceedings of the 2000 ACM/IEEE conference on
  Supercomputing (CDROM)},
  year = {2000},
  pages = {4},
  address = {Washington, DC, USA},
  publisher = {IEEE Computer Society},
  isbn = {0-7803-9802-5},
  location = {Dallas, Texas, United States},
  url = {http://iss.ices.utexas.edu/Publications/Papers/SC2000b.pdf}
}
@inproceedings{walter08,
  author = {Walter, Bruce and Bala, Kavita and Kulkarni, Milind and Pingali,
  Keshav},
  title = {Fast agglomerative clustering for rendering},
  booktitle = {Interactive Ray Tracing, 2008. RT 2008. IEEE Symposium on},
  year = {2008},
  pages = {81-86},
  month = {Aug.},
  doi = {10.1109/RT.2008.4634626},
  keywords = {computational complexity, pattern clustering, query processing, ray
  tracing, rendering (computer graphics), tree data structures, very
  large databasesbottom-up clustering tree, bounding volume hierarchy,
  divisive clustering tree, fast agglomerative clustering tree, hierarchical
  data set representation, lightcuts rendering algorithm, locally-ordered
  algorithm, ray tracing, top-down clustering tree, tree quality, very
  large data query},
  url = {http://iss.ices.utexas.edu/Publications/Papers/RT2008.pdf}
}
@inproceedings{yotov03,
  author = { Yotov, Kamen and Li, Xiaoming and Ren, Gang and Cibulskis, Michael
  and Dejong, Gerald and Garzaran, Maria and Padua, David and Pingali,
  Keshav and Stodghill, Paul and Wu, Peng},
  title = {A Comparison of Empirical and Model-driven Optimization },
  booktitle = {Programming Language Design and Implementation},
  year = { 2003},
  month = {06/09/},
  tags = {eo},
  url = {http://iss.ices.utexas.edu/Publications/Papers/PLDI2003.pdf}
}
@techreport{yotov04,
  author = {Yotov, Kamen and Pingali, Keshav and Stodghill, Paul},
  title = {Think Globally, Search Locally},
  institution = {DSpace at Cornell University [http://dspace.library.cornell.edu:8080/dspace-oai/request]
  (United States)},
  year = {2004},
  abstract = {A key step in program optimization is the determination of optimal
  values for code optimization parameters such as cache tile sizes
  and loop unrolling factors. One approach, which is implemented in
  most compilers, is to use analytical models to determine these values.
  The other approach, used in library generators like ATLAS, is to
  perform a global search over the space of parameter values by generating
  different versions of the code and executing them on the actual machine
  to find the parameter values that give the best performance. Neither
  approach is suitable for use in general-purpose compilers that must
  generate high quality code for large programs running on complex
  architectures. Model-driven optimization may incur a performance
  penalty of 10-20\% even for a relatively simple code like matrix
  multiplication, as was shown recently by Yotov et al. On the other
  hand, global search is not tractable for optimizing large programs
  for complex architectures because the optimization space is too large.
  To address this problem, some researchers are exploring more sophisticated
  search algorithms such as the simplex method, but it remains to be
  seen if these methods are successful in reducing search time without
  compromising on the quality of the solution. In this paper, we advocate
  a different methodology for generating high-performance code without
  increasing search time dramatically. Our methodology has three components:
  (i) modeling, (ii) local search, and (iii) model refinement. We use
  analytical models to estimate optimal values for transformation parameters.
  Since it is impossible to build tractable analytical models that
  capture all the features of complex architectures, we advocate improving
  these estimates by using a local search in the neighborhood of the
  model-predicted values. Finally, if the performance gap between handwritten
  code and generated code is substantial on some architecture, we advocate
  model refinement. To demonstrate this methodology, we built a modified
  ATLAS system that used a simple analytical model and local search,
  and showed that on most architectures, the performance of the code
  produced by this system was comparable to that of code produced by
  the original ATLAS system using global search. However, on x86 architectures,
  the gap in performance was substantial, and could not be bridged
  by local search alone. We argue that the problem is that the model
  assumed aggressive operation scheduling to mask instruction latencies,
  but such scheduling can actually be harmful on x86 architectures,
  a somewhat surprising fact that does not appear to be known widely.
  To address this problem, we use model refinement to generate a more
  sophisticated model that, when combined with local search, enables
  the production of high-quality code on both RISC and CISC architectures.},
  keywords = {computer science, technical report},
  location = {http://www.scientificcommons.org/21472032},
  publisher = {Cornell University},
  tags = {eo},
  url = {http://techreports.library.cornell.edu:8081/Dienst/UI/1.0/Display/cul.cis/TR2004-1969}
}
@techreport{yotov04a,
  author = {Yotov, Kamen and Pingali, Keshav and Stodghill, Paul},
  title = {X-Ray : Automatic Measurement of Hardware Parameters},
  institution = {DSpace at Cornell University [http://dspace.library.cornell.edu:8080/dspace-oai/request]
  (United States)},
  year = {2004},
  abstract = {There is growing interest in autonomic, self-tuning software that
  can optimize itself on new platforms, without manual intervention.
  Optimization requires detailed knowledge of the target platform such
  as the latency and throughput of instructions, the numbers of registers,
  and the organization of the memory hierarchy. An autonomic optimization
  system needs to determine such platform-specific information on its
  own. In this paper, we describe the design and implementation of
  X-Ray, which is a tool that automatically measures a large number
  of such platform-specific parameters. For some of these parameters,
  we also describe novel algorithms, which are more robust than existing
  ones. X-Ray is written in C for maximum portability, and it is based
  on accurate timing of a number of carefully designed micro-benchmarks.
  A novel feature of X-Ray is that it is easily extensible because
  it provides simple infrastructure and a code generator that can be
  used to produce the large number of micro-benchmarks needed for such
  measurements. There are few existing tools that address this problem.
  Our experiments show that X-Ray produces more accurate and more complete
  results than any of them.},
  keywords = {computer science, technical report},
  location = {http://www.scientificcommons.org/37978297},
  publisher = {Cornell University},
  tags = {eo},
  url = {http://techreports.library.cornell.edu:8081/Dienst/UI/1.0/Display/cul.cis/TR2004-1966}
}
@techreport{yotov04b,
  author = {Yotov, Kamen and Pingali, Keshav and Stodghill, Paul},
  title = {Automatic Measurement of Memory Hierarchy Parameters},
  institution = {DSpace at Cornell University [http://dspace.library.cornell.edu:8080/dspace-oai/request]
  (United States)},
  year = {2004},
  abstract = {On modern computers, the running time of many applications is dominated
  by the cost of memory operations. To optimize such applications for
  a given platform, it is necessary to have a detailed knowledge of
  the memory hierarchy parameters of that platform. In practice, this
  information is usually poorly documented if at all. Moreover, there
  is growing interest in self-tuning, autonomic software systems that
  can optimize themselves for different platforms, and these systems
  must determine memory hierarchy parameters automatically without
  human intervention. One solution is to use micro-benchmarks to determine
  the parameters of the memory hierarchy. In this paper, we argue that
  existing micro-benchmarks are inadequate, and present novel micro-benchmarks
  for determining the parameters of all levels of the memory hierarchy,
  including registers, all caches levels and the translation look-aside
  buffer. We have implemented these micro-benchmarks into an integrated
  tool that can be ported with little effort to new platforms. We present
  experimental results that show that this tool successfully determines
  memory hierarchy parameters on many current platforms, and compare
  its accuracy with that of existing tools.},
  keywords = {computer science, technical report},
  location = {http://www.scientificcommons.org/37978301},
  publisher = {Cornell University},
  tags = {eo},
  url = {http://techreports.library.cornell.edu:8081/Dienst/UI/1.0/Display/cul.cis/TR2004-1970}
}
@inproceedings{yotov05,
  author = {Kamen Yotov and Ra Jackson and Tyler Steele and Keshav Pingali and
  Paul Stodghill},
  title = {Automatic Measurement of Instruction Cache Capacity},
  booktitle = {In Languages and Compilers for Parallel Computers (LCPC’05), Lecture
  Notes in Computer Science},
  year = {2005},
  tags = {eo},
  url = {http://iss.ices.utexas.edu/Publications/Papers/LCPC2005Yotov.pdf}
}
@article{yotov05a,
  author = {Yotov, Kamen and Li, Xiaoming and Ren, Gang and Garzaran, Maria and
  Padua, David and Pingali, Keshav and Stodghill, Paul},
  title = {Is Search Really Necessary to Generate High-Performance BLAS?},
  journal = {Proceedings of the IEEE},
  year = {2005},
  volume = {93},
  pages = {358-386},
  number = {2},
  month = {Feb. },
  doi = {10.1109/JPROC.2004.840444},
  issn = {0018-9219},
  keywords = {linear algebra, mathematics computing, optimising compilers, software
  librariesATLAS, BLAS, Basic Linear Algebra Subprograms, code generation,
  global search engine, library generators, model driven optimization
  engine, program compilers, program optimization, search based empirical
  optimization},
  tags = {eo},
  url = {http://iss.ices.utexas.edu/Publications/Papers/ieee05.pdf}
}
@techreport{yotov05b,
  author = {Yotov, Kamen and Pingali, Keshav and Stodghill, Paul},
  title = {Automatic Measurement of Hardware Parameters for Embedded Processors},
  institution = {DSpace at Cornell University [http://dspace.library.cornell.edu:8080/dspace-oai/request]
  (United States)},
  year = {2005},
  abstract = {Embedded processor designs are increasingly based on general-purpose
  processor families, modified and extended in various ways. However,
  the production of software for embedded processors remains a challenging
  problem. One promising approach for addressing this problem is self-optimizing
  software: instead of writing a program, one implements a program
  generator that produces a large number of program variants, and then
  determines empirically which variant performs best. The particular
  aspect of performance that is optimized can be execution time, power
  consumption, throughout, etc. To prevent a combinatorial explosion
  in the number of program variants that have to be considered, self-optimizing
  systems bound the search space by exploiting knowledge of hardware
  parameters such as the number of registers, the capacity of the L1
  cache, etc. For software to be truly self-optimizing, hardware parameter
  values relevant for software optimization must be determined automatically.
  This paper makes the following contributions. - We describe X-Ray
  - a robust and extensible micro-benchmark framework for measuring
  hardware parameters, in which it is very easy to implement new micro-benchmarks.
  This is particularly important in the embedded processor context
  because designers constantly add new features to architectures. -
  We describe novel algorithms for measuring commonly used hardware
  parameters and show how they can be implemented in this framework.
  We evaluate our implementation experimentally on both embedded and
  desktop architectures, and show that it produces more accurate and
  complete results than existing tools.},
  keywords = {computer science, technical report},
  location = {http://www.scientificcommons.org/37978305},
  publisher = {Cornell University},
  tags = {eo},
  url = {http://techreports.library.cornell.edu:8081/Dienst/UI/1.0/Display/cul.cis/TR2005-1974}
}
@article{yotov05c,
  author = {Yotov, Kamen and Pingali, Keshav and Stodghill, Paul},
  title = {Automatic measurement of memory hierarchy parameters},
  journal = {SIGMETRICS Perform. Eval. Rev.},
  year = {2005},
  volume = {33},
  pages = {181--192},
  number = {1},
  address = {New York, NY, USA},
  doi = {http://doi.acm.org/10.1145/1071690.1064233},
  issn = {0163-5999},
  publisher = {ACM},
  tags = {eo},
  url = {http://iss.ices.utexas.edu/Publications/Papers/SIGMETRICS2005.pdf}
}
@inproceedings{yotov05d,
  author = {Yotov, Kamen and Pingali, Keshav and Stodghill, Paul},
  title = {Think globally, search locally},
  booktitle = {ICS '05: Proceedings of the 19th annual international conference
  on Supercomputing},
  year = {2005},
  pages = {141--150},
  address = {New York, NY, USA},
  publisher = {ACM},
  doi = {http://doi.acm.org/10.1145/1088149.1088168},
  isbn = {1-59593-167-8},
  location = {Cambridge, Massachusetts},
  tags = {eo},
  url = {http://iss.ices.utexas.edu/Publications/Papers/ICS2005.pdf}
}
@inproceedings{yotov05e,
  author = {Yotov, Kamen and Pingali, Keshav and Stodghill, Paul},
  title = {Automatic measurement of memory hierarchy parameters},
  booktitle = {SIGMETRICS '05: Proceedings of the 2005 ACM SIGMETRICS international
  conference on Measurement and modeling of computer systems},
  year = {2005},
  pages = {181--192},
  address = {New York, NY, USA},
  publisher = {ACM},
  doi = {http://doi.acm.org/10.1145/1064212.1064233},
  isbn = {1-59593-022-1},
  location = {Banff, Alberta, Canada},
  tags = {eo},
  url = {http://iss.ices.utexas.edu/Publications/Papers/SIGMETRICS2005.pdf}
}
@inproceedings{yotov05f,
  author = {Kamen Yotov and Keshav Pingali and Paul Stodghill},
  title = {X-Ray: A Tool for Automatic Measurement of Hardware Parameters},
  booktitle = {In Proceedings of the 2nd International Conference on Quantitative
  Evaluation of SysTems},
  year = {2005},
  tags = {eo},
  url = {http://iss.ices.utexas.edu/Publications/Papers/QEST2005.pdf}
}
@inproceedings{yotov07,
  author = {Yotov, Kamen and Roeder, Thomas and Pingali, Keshav and Gunnels,
  John and Gustavson, Fred},
  title = {An experimental comparison of cache-oblivious and cache-conscious
  programs},
  booktitle = {Proc. Symp. on Parallel algorithms and architectures (SPAA)},
  year = {2007},
  pages = {93--104},
  address = {New York, NY, USA},
  publisher = {ACM},
  doi = {http://doi.acm.org/10.1145/1248377.1248394},
  isbn = {978-1-59593-667-7},
  location = {San Diego, California, USA},
  tags = {eo},
  url = {http://iss.ices.utexas.edu/Publications/Papers/SPAA2007.pdf}
}
@inproceedings{nasre13-gpgpu,
  author = {Nasre, Rupesh and Burtscher, Martin and Pingali, Keshav},
  title = {Atomic-free irregular computations on {GPUs}},
  booktitle = {Proceedings of the 6th Workshop on General Purpose Processor Using Graphics Processing Units},
  series = {GPGPU-6},
  year = {2013},
  isbn = {978-1-4503-2017-7},
  location = {Houston, Texas},
  pages = {96--107},
  numpages = {12},
  doi = {10.1145/2458523.2458533},
  acmid = {2458533},
  publisher = {ACM},
  address = {New York, NY, USA},
  keywords = {GPGPU, atomic-free, graph algorithms, irregular algorithms},
  tags = {galois},
  url = {http://iss.ices.utexas.edu/Publications/Papers/nasre13-gpgpu.pdf}
}
@inproceedings{nasre13-ipdps,
  author = {Nasre, Rupesh and Burtscher, Martin and Pingali, Keshav},
  booktitle = {IEEE 27th International Parallel and Distributed Processing Symposium (IPDPS) },
  title = {Data-Driven Versus Topology-driven Irregular Computations on {GPUs}},
  year = {2013},
  pages = {463-474},
  keywords = {data structures;graphics processing units;parallel processing;topology;GPU threads;complex main data structures;data-driven irregular computation;directed graph;iterated application;multicore implementations;topology-driven irregular computation;undirected graph;Algorithm design and analysis;Graphics processing units;Indexes;Instruction sets;Kernel;Optimization;Synchronization;GPGPU;algorithmic properties;data-driven;irregular algorithms;topology-driven},
  doi = {10.1109/IPDPS.2013.28},
  tags = {galois},
  url = {http://iss.ices.utexas.edu/Publications/Papers/nasre13-ipdps.pdf},
  issn = {1530-2075}
}
@inproceedings{nasre13-ppopp,
  author = {Nasre, Rupesh and Burtscher, Martin and Pingali, Keshav},
  title = {Morph algorithms on {GPUs}},
  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},
  tags = {galois},
  pages = {147--156},
  numpages = {10},
  doi = {10.1145/2442516.2442531},
  acmid = {2442531},
  publisher = {ACM},
  address = {New York, NY, USA},
  url = {http://iss.ices.utexas.edu/Publications/Papers/nasre13-ppopp.pdf}
}
@inproceedings{prountzos13,
  author = {Prountzos, Dimitrios and Pingali, Keshav},
  title = {Betweenness centrality: algorithms and implementations},
  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},
  tags = {galois},
  pages = {35--46},
  numpages = {12},
  doi = {10.1145/2442516.2442521},
  acmid = {2442521},
  publisher = {ACM},
  address = {New York, NY, USA},
  keywords = {amorphous data-parallelism, betweenness centrality, concurrency, irregular programs, optimistic parallelization, parallelism}
}
@inproceedings{Kaleem14,
  author = {Kaleem, Rashid and Barik, Rajkishore and Shpeisman,
      Tatiana and Lewis, Brian T. and Hu, Chunling and Pingali,
      Keshav},
  title = {Adaptive Heterogeneous Scheduling for Integrated GPUs},
  booktitle = {Proceedings of the 23rd International Conference on
      Parallel Architectures and Compilation},
  series = {PACT '14},
  year = {2014},
  isbn = {978-1-4503-2809-8},
  location = {Edmonton, AB, Canada},
  pages = {151--162},
  numpages = {12},
  url = {http://iss.ices.utexas.edu/Publications/Papers/PACT14.pdf},
  doi = {10.1145/2628071.2628088},
  acmid = {2628088},
  publisher = {ACM},
  address = {New York, NY, USA},
  keywords = {heterogeneous computing, integrated gpus,
      irregular applications, load balancing,
      scheduling}
}
@inproceedings{voegele,
  author = {Chad Voegele and Yi-Shan Lu and Sreepathi Pai and Keshav Pingali},
  booktitle = {2017 IEEE High Performance Extreme Computing Conference (HPEC)},
  title = {Parallel triangle counting and k-truss identification using graph-centric methods (Graph Challenge Champion)},
  year = {2017},
  volume = {},
  number = {},
  pages = {1-7},
  keywords = {graph theory;graphics processing units;mathematics computing;microprocessor chips;parallel processing;CPU;GPU;Galois systems;IEEE HPEC static graph challenge;IrGL systems;graph-centric abstraction;graph-centric methods;input graph;k-truss identification;parallel triangle counting;Arrays;Graphics processing units;Optimization;Parallel processing;Partitioning algorithms;Programming;Runtime},
  doi = {10.1109/HPEC.2017.8091037},
  issn = {},
  tags = {galois},
  month = {Sept}
}
@article{luparallel,
  title = {{Parallel Tools for Asynchronous VLSI Systems}},
  author = {Lu, Yi-Shan and Ataei, Samira and He, Jiayuan and Hua, Wenmian and Maleki, Sepideh and Yang, Yihang and Burtscher, Martin and Pingali, Keshav and Manohar, Rajit},
  booktitle = {Workshop on Open-Source EDA Technology},
  series = {WOSET 2018},
  year = {2018}
}
@article{wos19,
  title = {{Toward a digital flow for asynchronous VLSI systems}},
  author = {Samira Ataei and Yi-Shan Lu and Jiayuan He and Wenmian Hua and Sepideh Maleki and Yihang Yang and Rajit Manohar and Keshav Pingali},
  booktitle = {Workshop on Open-Source EDA Technology},
  series = {WOSET 2019},
  year = {2019}
}
@inproceedings{partitioningVLDB19,
  author = {Gurbinder Gill and Roshan Dathathri and Loc Hoang and Keshav Pingali},
  title = {{A Study of Partitioning Policies for Graph Analytics on Large-scale Distributed Platforms}},
  tags = {galois},
  year = {2018},
  series = {PVLDB},
  volume = {12(4)},
  number = {4},
  pages = {321--334},
  doi = {10.14778/3297753.3297754}
}
@inproceedings{Hoang08,
  author = {Hoang-Vu Dang and Roshan Dathathri and Gurbinder Gill and Alex Brooks and Nikoli Dryden and Andrew Lenharth and Loc Hoang and Keshav Pingali and Marc Snir},
  title = {{A Lightweight Communication Runtime for Distributed Graph Analytics}},
  booktitle = {International Parallel and Distributed Processing Symposium (IPDPS)},
  tags = {galois},
  year = {2018}
}
@inproceedings{Lu2018,
  author = {Yi-Shan Lu and Keshav Pingali},
  title = {{Can Parallel Programming Revolutionize EDA Tools?}},
  booktitle = {Advanced Logic Synthesis},
  publisher = {Springer International Publishing},
  year = {2018},
  address = {Cham},
  pages = {21--41},
  isbn = {978-3-319-67295-3},
  doi = {10.1007/978-3-319-67295-3_2},
  tags = {galois},
  url = {https://doi.org/10.1007/978-3-319-67295-3_2}
}
@inproceedings{Roshan08,
  author = {*Roshan Dathathri and *Gurbinder Gill and Loc Hoang and Hoang-Vu Dang and Alex Brooks and Nikoli Dryden and Marc Snir and Keshav Pingali (*Both authors contributed equally)},
  title = {{Gluon: A Communication Optimizing Framework for Distributed Heterogeneous Graph Analytics}},
  booktitle = {Proceedings of the 39th ACM SIGPLAN Conference on Programming Language Design and Implementation},
  series = {PLDI 2018},
  year = {2018},
  isbn = {978-1-4503-5698-5},
  location = {Philadelphia, PA, USA},
  pages = {752--768},
  numpages = {17},
  url = {http://doi.acm.org/10.1145/3192366.3192404},
  doi = {10.1145/3192366.3192404},
  acmid = {3192404},
  publisher = {ACM},
  address = {New York, NY, USA},
  keywords = {Distributed-memory graph analytics, GPUs, big data, communication optimizations, heterogeneous architectures},
  tags = {galois}
}
@inproceedings{Gurbinder08,
  author = {Gurbinder Gill and Roshan Dathathri and Loc Hoang and Andrew Lenharth and Keshav Pingali},
  title = {{Abelian: A Compiler and Runtime for Graph Analytics on Distributed, Heterogeneous Platforms}},
  booktitle = {Euro-Par 2018: Parallel Processing},
  tags = {galois},
  year = {2018},
  publisher = {Springer International Publishing},
  address = {Cham},
  pages = {249--264},
  isbn = {978-3-319-96983-1}
}
@inproceedings{sepideh08,
  author = {Sepideh Maleki and Martin Burtscher},
  title = {{Automatic Hierarchical Parallelization of Linear Recurrences}},
  booktitle = {Proceedings of the Twenty-Third International Conference on Architectural Support for Programming Languages and Operating Systems},
  series = {ASPLOS '18},
  year = {2018},
  isbn = {978-1-4503-4911-6},
  location = {Williamsburg, VA, USA},
  pages = {128--138},
  numpages = {11},
  url = {http://doi.acm.org/10.1145/3173162.3173168},
  doi = {10.1145/3173162.3173168},
  acmid = {3173168},
  publisher = {ACM},
  address = {New York, NY, USA},
  keywords = {automatic parallelization, code optimization, linear recurrences, prefix sums, recursive filters}
}
@inproceedings{multigpuIPDPS20,
  author = {Vishwesh Jatala and Roshan Dathathri and Gurbinder Gill and Loc Hoang and V. Krishna Nandivada and Keshav Pingali},
  title = {{A Study of Graph Analytics for Massive Datasets on Distributed GPUs}},
  booktitle = {International Parallel and Distributed Processing Symposium (IPDPS)},
  tags = {galois},
  year = {2020}
}
@inproceedings{pangolinVLDB20,
  author = {Xuhao Chen and Roshan Dathathri and Gurbinder Gill and Keshav Pingali},
  title = {{Pangolin: An Efficient and Flexible Graph Mining System on CPU and GPU}},
  tags = {galois},
  year = {2020},
  series = {PVLDB},
  volume = {13(8)}
}
@inproceedings{optaneVLDB20,
  author = {Gurbinder Gill and Roshan Dathathri and Loc Hoang and Ramesh Peri and Keshav Pingali},
  title = {{Single Machine Graph Analytics on Massive Datasets Using Intel Optane DC Persistent Memory}},
  tags = {galois},
  year = {2020},
  series = {PVLDB},
  volume = {13(8)}
}
@inproceedings{sprouteiccad19,
  author = {Jiayuan He and Martin Burtscher and Rajit Manohar and Keshav Pingali},
  title = {{SPRoute: A Scalable Parallel Negotiation-based Global Router}},
  booktitle = {Proceedings of the 38th International Conference on Computer-Aided Design (ICCAD 2019)},
  series = {ICCAD '19},
  year = {2019},
  publisher = {IEEE/ACM},
  keywords = {},
  tags = {galois}
}
@inproceedings{slambooster,
  author = {Yan Pei and Swarnendu Biswas and Donald Fussell and Keshav Pingali},
  title = {{SLAMBooster: An Application-aware Online Controller for Approximation in Dense SLAM}},
  booktitle = {Proceedings of the 28th International Conference on Parallel Architectures and Compilation Techniques (PACT 2019)},
  series = {PACT '19},
  year = {2019},
  publisher = {IEEE}
}
@inproceedings{gluonasync,
  author = {Roshan Dathathri and Gurbinder Gill and Loc Hoang and Hoang-Vu Dang and Vishwesh Jatala and V. Krishna Nandivada and Marc Snir and Keshav Pingali},
  title = {{Gluon-Async: A Bulk-Asynchronous System for Distributed and Heterogeneous Graph Analytics}},
  booktitle = {Proceedings of the 28th International Conference on Parallel Architectures and Compilation Techniques (PACT 2019)},
  series = {PACT '19},
  year = {2019},
  publisher = {IEEE},
  keywords = {graph analytics, distributed and heterogeneous, BSP model, asynchronous parallel execution models},
  tags = {galois}
}
@inproceedings{disttc,
  author = {Loc Hoang* and Vishwesh Jatala* and Xuhao Chen and Udit Agarwal and Roshan Dathathri and Gurbinder Gill and Keshav Pingali (*authors contributed equally)},
  title = {{DistTC: High Performance Distributed Triangle Counting}},
  booktitle = {2019 IEEE High Performance Extreme Computing Conference (HPEC 2019)},
  series = {HPEC '19},
  year = {2019},
  tags = {galois},
  publisher = {IEEE}
}
@inproceedings{cuspIPDPS19,
  author = {Loc Hoang and Roshan Dathathri and Gurbinder Gill and Keshav Pingali},
  title = {{CuSP: A Customizable Streaming Edge Partitioner for Distributed Graph Analytics}},
  booktitle = {International Parallel and Distributed Processing Symposium (IPDPS)},
  tags = {galois},
  year = {2019}
}
@inproceedings{phoenixASPLOS19,
  author = {*Roshan Dathathri and *Gurbinder Gill and Loc Hoang and Keshav Pingali (*Both authors contributed equally)},
  title = {{Phoenix: A Substrate for Resilient Distributed Graph Analytics}},
  booktitle = {Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS'19)},
  series = {ASPLOS '19},
  year = {2019},
  doi = {10.1145/3297858.3304056},
  publisher = {ACM},
  address = {New York, NY, USA},
  keywords = {fault tolerance, distributed-memory graph analytics, big data, self-stabilizing algorithms},
  tags = {galois},
  location = {Providence, RI,USA}
}
@inproceedings{mrbcPPoPP19,
  author = {Loc Hoang and Matteo Pontecorvi and Roshan Dathathri and Gurbinder Gill and Bozhi You and Keshav Pingali and Vijaya Ramachandran},
  title = {{A Round-Efficient Distributed Betweenness Centrality Algorithm}},
  booktitle = {Proceedings of the 24th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP'19)},
  tags = {galois},
  year = {2019},
  series = {PPoPP},
  location = {Washington, DC, USA},
  doi = {10.1145/3293883.3295729},
  numpages = {15},
  publisher = {ACM},
  address = {New York, NY, USA},
  url = {http://doi.acm.org/10.1145/3293883.3295729}
}