@article{Abdelkader:2017:ACR,
author = {Ahmed Abdelkader and Ahmed H. Mahmoud and Ahmad A.
Rushdi and Scott A. Mitchell and John D. Owens and
Mohamed S. Ebeida},
title = {A Constrained Resampling Strategy for Mesh
Improvement},
journal = {Computer Graphics Forum},
series = {SGP 2017},
volume = 36,
number = 5,
year = 2017,
month = jul,
pages = {189--201},
note = {Proceedings of the Symposium on Geometry Processing},
doi = {10.1111/cgf.13256},
url = {http://escholarship.org/uc/item/5347s75h},
code = {https://github.com/Ahdhn/MeshImp},
ucdcite = {a112}
}
@inproceedings{Abdelkader:2018:SCF,
author = {Ahmed Abdelkader and Chandrajit L. Bajaj and Mohamed
S. Ebeida and Ahmed H. Mahmoud and Scott A. Mitchell
and John D. Owens and Ahmad Rushdi},
title = {Sampling Conditions for Conforming {V}oronoi Meshing
by the {V}oro{C}rust Algorithm},
booktitle = {34th International Symposium on Computational
Geometry (SoCG 2018)},
pages = {1:1--1:16},
series = {Leibniz International Proceedings in Informatics
(LIPIcs)},
isbn = {978-3-95977-066-8},
issn = {1868-8969},
year = 2018,
month = jun,
volume = 99,
editor = {Bettina Speckmann and Csaba D. T{\'o}th},
publisher = {Schloss Dagstuhl---Leibniz-Zentrum f{\"{u}}r
Informatik},
address = {Dagstuhl, Germany},
doi = {10.4230/LIPIcs.SoCG.2018.1},
url = {https://escholarship.org/uc/item/43r7q64x},
ucdcite = {a120}
}
@inproceedings{Abdelkader:2018:VIT,
author = {Ahmed Abdelkader and Chandrajit L. Bajaj and Mohamed
S. Ebeida and Ahmed H. Mahmoud and Scott A. Mitchell
and John D. Owens and Ahmad A. Rushdi},
title = {{VoroCrust} Illustrated: Theory and Challenges
(Multimedia Exposition)},
booktitle = {34th International Symposium on Computational
Geometry (SoCG 2018)},
pages = {77:1--77:4},
series = {Leibniz International Proceedings in Informatics
(LIPIcs)},
isbn = {978-3-95977-066-8},
issn = {1868-8969},
month = jun,
year = 2018,
volume = 99,
editor = {Bettina Speckmann and Csaba D. T{\'o}th},
publisher = {Schloss Dagstuhl---Leibniz-Zentrum f{\"{u}}r
Informatik},
address = {Dagstuhl, Germany},
url = {http://drops.dagstuhl.de/opus/volltexte/2018/8790},
urn = {urn:nbn:de:0030-drops-87903},
doi = {10.4230/LIPIcs.SoCG.2018.77},
annote = {Keywords: sampling, surface reconstruction,
polyhedral meshing, Voronoi},
ucdcite = {a121}
}
@article{Abdelkader:2020:VVM,
title = {{VoroCrust}: {V}oronoi Meshing Without Clipping},
author = {Ahmed Abdelkader and Chandrajit L. Bajaj and Mohamed
S. Ebeida and Ahmed H. Mahmoud and Scott A. Mitchell
and John D. Owens and Ahmad A. Rushdi},
journal = {ACM Transactions on Graphics},
year = 2020,
issue_date = {June 2020},
publisher_ = {Association for Computing Machinery},
address_ = {New York, NY, USA},
volume = 39,
number = 3,
issn = {0730-0301},
doi = {10.1145/3337680},
acmauthorize = {https://dl.acm.org/doi/10.1145/3337680?cid=81100458295},
url = {https://escholarship.org/uc/item/2088s1gh},
month = may,
articleno = 23,
numpages = 16,
pages = {23:1--23:16},
keywords_ = {Poisson-disk sampling, slivers, union of balls,
refinement, sharp features, Voronoi, meshing},
ucdcite = {a137}
}
@article{Alcantara:2009:RPH,
author = {Dan A. Alcantara and Andrei Sharf and Fatemeh
Abbasinejad and Shubhabrata Sengupta and Michael
Mitzenmacher and John D. Owens and Nina Amenta},
title = {Real-Time Parallel Hashing on the {GPU}},
journal = {ACM Transactions on Graphics},
volume = 28,
number = 5,
year = 2009,
location = {Yokohama, Japan},
month = dec,
pages = {154:1--154:9},
url = {https://escholarship.org/uc/item/445536d6},
acmauthorize = {http://dl.acm.org/authorize?143436},
doi = {10.1145/1661412.1618500},
acceptance = {25\% (70/275)},
ucdcite = {a49}
}
@incollection{Alcantara:2011:BAE,
author = {Dan A. Alcantara and Vasily Volkov and Shubhabrata
Sengupta and Michael Mitzenmacher and John D. Owens
and Nina Amenta},
editor = {Wen{-mei} W. Hwu},
booktitle = {GPU Computing Gems},
volume = 2,
title = {Building an Efficient Hash Table on the {GPU}},
chapter = 4,
publisher = {Morgan Kaufmann},
month = oct,
year = 2011,
pages = {39--53},
doi = {10.1016/B978-0-12-385963-1.00004-6},
acceptance = {There were a total of 272 submissions and will be
publishing 98 over the two volumes.},
ucdcite = {a75}
}
@inproceedings{Ashkiani:2016:GM,
author = {Saman Ashkiani and Andrew A. Davidson and Ulrich
Meyer and John D. Owens},
title = {{GPU} Multisplit},
booktitle = {Proceedings of the 21st ACM SIGPLAN Symposium on
Principles and Practice of Parallel Programming},
series = {PPoPP 2016},
year = 2016,
month = mar,
pages = {12:1--12:13},
acceptance = {29 of 151 submissions, 19.2\%},
doi = {10.1145/2851141.2851169},
acmauthorize = {http://dl.acm.org/authorize?N03911},
url = {http://escholarship.org/uc/item/346486j8},
code = {https://github.com/owensgroup/GpuMultisplit},
ucdcite = {a102}
}
@inproceedings{Ashkiani:2016:PAT,
author = {Saman Ashkiani and Nina Amenta and John D. Owens},
title = {Parallel Approaches to the String Matching Problem
on the {GPU}},
booktitle = {Proceedings of the 28th ACM Symposium on Parallelism
in Algorithms and Architectures},
year = 2016,
series = {SPAA 2016},
month = jul,
pages = {275--285},
doi = {10.1145/2935764.2935800},
ee = {http://arxiv.org/abs/1701.01189},
acmauthorize = {http://dl.acm.org/authorize?N18738},
url = {http://escholarship.org/uc/item/2d46g741},
ucdcite = {a106}
}
@article{Ashkiani:2017:GMA,
author = {Saman Ashkiani and Andrew A. Davidson and Ulrich
Meyer and John D. Owens},
title = {{GPU} Multisplit: an extended study of a parallel
algorithm},
journal = {ACM Transactions on Parallel Computing},
year = 2017,
volume = 4,
number = 1,
month = aug,
pages = {2:1--2:44},
doi = {10.1145/3108139},
acmauthorize = {http://dl.acm.org/authorize?N45083},
url = {http://escholarship.org/uc/item/2kc8q23h},
code = {https://github.com/owensgroup/GpuMultisplit},
ucdcite = {a113}
}
@inproceedings{Ashkiani:2018:ADH,
author = {Saman Ashkiani and Martin Farach-Colton and John D.
Owens},
title = {A Dynamic Hash Table for the {GPU}},
booktitle = {Proceedings of the 32nd IEEE International Parallel
and Distributed Processing Symposium},
series = {IPDPS 2018},
year = 2018,
month = may,
pages = {419--429},
url = {https://escholarship.org/uc/item/2p48q0zg},
url_ = {https://arxiv.org/abs/1710.11246},
doi = {10.1109/IPDPS.2018.00052},
code = {https://github.com/owensgroup/SlabHash},
acceptance = {113 accepted out of 481, 24.5\%},
ucdcite = {a116}
}
@inproceedings{Ashkiani:2018:GLA,
author = {Saman Ashkiani and Shengren Li and Martin
Farach-Colton and Nina Amenta and John D. Owens},
title = {{GPU} {LSM}: A Dynamic Dictionary Data Structure for
the {GPU}},
booktitle = {Proceedings of the 32nd IEEE International Parallel
and Distributed Processing Symposium},
series = {IPDPS 2018},
year = 2018,
month = may,
pages = {430--440},
url = {https://escholarship.org/uc/item/65t741zg},
url_ = {https://arxiv.org/abs/1707.05354},
doi = {10.1109/IPDPS.2018.00053},
acceptance = {113 accepted out of 481, 24.5\%},
ucdcite = {a117}
}
@inproceedings{Awad:2019:EAH,
author = {Muhammad A. Awad and Saman Ashkiani and Rob Johnson
and Mart\'{\i}n Farach-Colton and John D. Owens},
title = {Engineering a High-Performance {GPU} {B}-Tree},
booktitle = {Proceedings of the 24th ACM SIGPLAN Symposium on
Principles and Practice of Parallel Programming},
series = {PPoPP 2019},
year = 2019,
month = feb,
pages = {145--157},
acceptance = {29 of 152 submissions, 19.1\%},
doi = {10.1145/3293883.3295706},
acmauthorize = {https://dl.acm.org/doi/10.1145/3293883.3295706?cid=81100458295},
url = {https://escholarship.org/uc/item/1ph2x5td},
code = {https://github.com/owensgroup/GpuBTree},
ucdcite = {a127}
}
@inproceedings{Awad:2020:DGO,
author = {Muhammad A. Awad and Saman Ashkiani and Serban D.
Porumbescu and John D. Owens},
title = {Dynamic Graphs on the {GPU}},
booktitle = {Proceedings of the 34th IEEE International Parallel
and Distributed Processing Symposium},
series = {IPDPS 2020},
year = 2020,
month = may,
pages = {739--748},
doi = {10.1109/IPDPS47924.2020.00081},
url = {https://escholarship.org/uc/item/48j4k7np},
ucdcite = {a138}
}
@article{Awad:2021:BGH,
title = {Better {GPU} Hash Tables},
author = {Muhammad A. Awad and Saman Ashkiani and Serban D.
Porumbescu and Mart{\'{i}}n Farach-Colton and John
D. Owens},
year = 2021,
month = aug,
primaryclass = {cs.DS},
journal = {CoRR},
volume = {abs/2108.07232},
archiveprefix = {arXiv},
number = {2108.07232},
eprint = {2108.07232},
code = {https://github.com/owensgroup/BGHT},
ucdcite = {c1},
nonrefereed = {true}
}
@inproceedings{Awad:2022:AGM,
author = {Muhammad A. Awad and Serban D. Porumbescu and John
D. Owens},
title = {A {GPU} Multiversion {B}-Tree},
booktitle = {Proceedings of the International Conference on
Parallel Architectures and Compilation Techniques},
series = {PACT 2022},
year = 2022,
month = oct,
pages = {481--493},
code = {https://github.com/owensgroup/MVGpuBTree},
doi = {10.1145/3559009.3569681},
url = {https://escholarship.org/uc/item/4mz5t5b7},
ucdcite = {a146}
}
@inproceedings{Awad:2023:AAI,
title = {Analyzing and Implementing {GPU} Hash Tables},
author = {Muhammad A. Awad and Saman Ashkiani and Serban D.
Porumbescu and Mart{\'{i}}n Farach-Colton and John
D. Owens},
booktitle = {SIAM Symposium on Algorithmic Principles of Computer
Systems},
series = {APOCS23},
year = 2023,
month = jan,
pages = {33--50},
archiveprefix_ = {arXiv},
eprint_ = {2108.07232},
code = {https://github.com/owensgroup/BGHT},
doi = {10.1137/1.9781611977578.ch3},
url = {https://escholarship.org/uc/item/6cb1q6rz},
ucdcite = {a149}
}
@inproceedings{Brock:2019:RVR,
author = {Benjamin Brock and Yuxin Chen and Jiakun Yan and
John D. Owens and Ayd{\i}n Bulu\c{c} and Katherine
Yelick},
title = {{RDMA} vs.\ {RPC} for Implementing Distributed Data
Structures},
booktitle = {Proceedings of the IEEE/ACM 9th Workshop on
Irregular Applications: Architectures and
Algorithms},
year = 2019,
series = {IA$^3$ 2019},
month = nov,
pages = {17--22},
url = {https://arxiv.org/abs/1910.02158},
doi = {10.1109/IA349570.2019.00009},
ucdcite = {a135}
}
@article{Budge:2009:ODM,
author = {Brian Budge and Tony Bernardin and Jeff A. Stuart
and Shubhabrata Sengupta and Kenneth I. Joy and John
D. Owens},
title = {Out-of-core Data Management for Path Tracing on
Hybrid Resources},
journal = {Computer Graphics Forum (Proceedings of Eurographics
2009)},
year = 2009,
volume = 28,
number = 2,
month = apr,
pages = {385--396},
url = {https://escholarship.org/uc/item/1750k9st},
doi = {10.1111/j.1467-8659.2009.01378.x},
acceptance = {23.0\% (56/243)},
ucdcite = {a44}
}
@inproceedings{Chen:2022:AAT,
author = {Yuxin Chen and Benjamin Brock and Serban Porumbescu
and Ayd{\i}n Bulu\c{c} and Katherine Yelick and John
D. Owens},
title = {{A}tos: A Task-Parallel {GPU} Scheduler for Graph
Analytics},
booktitle = {Proceedings of the International Conference on
Parallel Processing},
series = {ICPP 2022},
year = 2022,
eprint = {2112.00132},
month = aug # {\slash } # sep,
doi = {10.1145/3545008.3545056},
acceptance = {27\% (84/311)},
ucdcite = {a145},
full_talk = {https://youtu.be/Y-jcmmzRPsQ}
}
@inproceedings{Chen:2022:SIP,
author = {Yuxin Chen and Benjamin Brock and Serban Porumbescu
and Ayd{\i}n Bulu\c{c} and Katherine Yelick and John
D. Owens},
title = {Scalable Irregular Parallelism with {GPU}s: Getting
{CPU}s Out of the Way},
booktitle = {Proceedings of the International Conference on High
Performance Computing, Networking, Storage and
Analysis},
series = {SC '22},
year = 2022,
month = nov,
pages = {708--723},
doi = {10.1109/SC41404.2022.00055},
url = {https://escholarship.org/uc/item/9j6337h7},
acceptance = {23.4\% (75/320)},
code = {https://github.com/owensgroup/ATOS},
ucdcite = {a147}
}
@inproceedings{Chen:2024:AME,
author = {Yuxin Chen and Ayd{\i}n Bulu\c{c} and Katherine
Yelick and John D. Owens},
title = {Accelerating Multi-{GPU} Embedding Retrieval with
{PGAS}-Style Communication for Deep Learning
Recommendation Systems},
booktitle = {Parallel Applications Workshop, Alternatives To
MPI+X},
year = 2024,
series = {PAW-ATM2024},
month = nov,
url = {https://escholarship.org/uc/item/0246g3qz},
doi = {10.1109/SCW63240.2024.00167}
}
@inproceedings{Davidson:2010:TTF,
author = {Andrew Davidson and John D. Owens},
title = {Toward Techniques for Auto-Tuning {GPU} Algorithms},
booktitle = {State of the Art in Scientific and Parallel
Computing},
series = {Para 2010},
year = 2010,
month = jun,
url = {http://www.idav.ucdavis.edu/publications/print_pub?pub_id=1035},
ucdcite = {a55}
}
@inproceedings{Davidson:2011:AAM,
author = {Andrew Davidson and Yao Zhang and John D. Owens},
title = {An Auto-tuned Method for Solving Large Tridiagonal
Systems on the {GPU}},
booktitle = {Proceedings of the 25th IEEE International Parallel
and Distributed Processing Symposium},
series = {IPDPS 2011},
month = may,
year = 2011,
pages = {956--965},
acceptance = {112/571 (19.6\%)},
doi = {10.1109/IPDPS.2011.92},
url = {https://escholarship.org/uc/item/20j103rs},
ucdcite = {a64}
}
@inproceedings{Davidson:2011:RPF,
author = {Andrew Davidson and John D. Owens},
title = {Register Packing for Cyclic Reduction: A Case Study},
booktitle = {Proceedings of the Fourth Workshop on General
Purpose Processing on Graphics Processing Units},
series = {GPGPU-4},
year = 2011,
month = mar,
doi = {10.1145/1964179.1964185},
acceptance = {13/35 (37.1\%)},
pages = {4:1--4:6},
url = {https://escholarship.org/uc/item/70h8r4km},
acmauthorize = {http://dl.acm.org/authorize?474065},
ucdcite = {a63}
}
@inproceedings{Davidson:2012:EPM,
author = {Andrew Davidson and David Tarjan and Michael Garland
and John D. Owens},
title = {Efficient Parallel Merge Sort for Fixed and Variable
Length Keys},
booktitle = {Proceedings of Innovative Parallel Computing},
series = {InPar '12},
year = 2012,
month = may,
url = {https://escholarship.org/uc/item/2514r4h1},
doi = {10.1109/InPar.2012.6339592},
acceptance = {25/62 (40.3\%)},
ucdcite = {a82}
}
@incollection{Davidson:2012:TTF,
author = {Andrew Davidson and John Owens},
title = {Toward Techniques for Auto-tuning {GPU} Algorithms},
booktitle = {Applied Parallel and Scientific Computing},
series = {Lecture Notes in Computer Science},
editor = {J{\'{o}}nasson, Kristj{\'{a}}n},
publisher = {Springer Berlin / Heidelberg},
isbn = {978-3-642-28144-0},
pages = {110--119},
volume = 7134,
doi = {10.1007/978-3-642-28145-7_11},
month = feb,
year = 2012,
ucdcite = {a78}
}
@inproceedings{Davidson:2014:WPG,
author = {Andrew Davidson and Sean Baxter and Michael Garland
and John D. Owens},
title = {Work-Efficient Parallel {GPU} Methods for
Single-Source Shortest Paths},
booktitle = {Proceedings of the 28th IEEE International Parallel
and Distributed Processing Symposium},
series = {IPDPS 2014},
year = 2014,
month = may,
pages = {349--359},
url = {http://escholarship.org/uc/item/8qr166v2},
doi = {10.1109/IPDPS.2014.45},
acceptance = {114/541 (21.1\%)},
ucdcite = {a89}
}
@inproceedings{Ebeida:2011:EAG,
author = {Mohamed S. Ebeida and Scott A. Mitchell and Andrew
A. Davidson and Anjul Patney and Patrick M. Knupp
and John D. Owens},
title = {Efficient and Good {D}elaunay Meshes From Random
Points},
booktitle = {Proceedings of the SIAM Conference on Geometric and
Physical Modeling},
series = {GD/SPM11},
year = 2011,
month = oct,
pages = {1506--1515},
acceptance = {22/76 (29\%)},
doi = {10.1016/j.cad.2011.08.012},
url = {http://www.cs.sandia.gov/~samitch/bibliography_2007.html#random-delaunay-mesh-repost},
ucdcite = {a74}
}
@article{Ebeida:2011:EMP,
author = {Mohamed S. Ebeida and Anjul Patney and Scott A.
Mitchell and Andrew Davidson and Patrick M. Knupp
and John D. Owens},
title = {Efficient Maximal {P}oisson-Disk Sampling},
journal = {ACM Transactions on Graphics},
year = 2011,
volume = 30,
number = 4,
month = jul,
pages = {49:1--49:12},
acceptance = {82/432 (19\%)},
doi = {10.1145/1964921.1964944},
url = {https://escholarship.org/uc/item/8xv0237z},
acmauthorize = {http://dl.acm.org/authorize?6551698},
ucdcite = {a68}
}
@article{Ebeida:2011:ICR,
author = {Mohamed S. Ebeida and Anjul Patney and John D. Owens
and Eric Mestreau},
title = {Isotropic conforming refinement of quadrilateral and
hexahedral meshes using two-refinement templates},
journal = {International Journal for Numerical Methods in
Engineering},
volume = 88,
number = 10,
year = 2011,
month = {9~} # dec,
pages = {974--985},
doi = {10.1002/nme.3207},
url = {http://www.idav.ucdavis.edu/publications/print_pub?pub_id=1058},
ucdcite = {a60}
}
@article{Ebeida:2012:ASA,
author = {Mohamed S. Ebeida and Scott A. Mitchell and Anjul
Patney and Andrew A. Davidson and John D. Owens},
title = {A Simple Algorithm for Maximal {P}oisson-Disk
Sampling in High Dimensions},
journal = {Computer Graphics Forum},
year = 2012,
volume = 31,
number = 2,
month = may,
pages = {785--794},
acceptance = {66/260 (25\%)},
doi = {10.1111/j.1467-8659.2012.03059.x},
url = {http://www.cs.sandia.gov/~samitch/bibliography_2007.html#mps-eurographics},
idavurl = {http://www.idav.ucdavis.edu/publications/print_pub?pub_id=1083},
ucdcite = {a81}
}
@article{Ebeida:2013:SD,
author = {Mohamed S. Ebeida and Ahmed H. Mahmoud and Muhammad
A. Awad and Mohammed A. Mohammed and Scott A.
Mitchell and Alex Rand and John D. Owens},
title = {Sifted Disks},
journal = {Computer Graphics Forum},
year = 2013,
volume = 32,
number = 2,
month = may,
pages = {509--518},
acceptance = {52/205 (25.3\%)},
doi = {10.1111/cgf.12071},
url = {https://cfwebprod.sandia.gov/cfdocs/CCIM/docs/SiftedDisks_final.pdf},
ucdcite = {a86}
}
@incollection{Ebeida:2014:EIH,
author = {Mohamed Ebeida and Scott Mitchell and Anjul Patney
and Andrew Davidson and Stanley Tzeng and Muhammad
Awad and Ahmed Mahmoud and John D. Owens},
title = {Exercises in High-Dimensional Sampling: Maximal
{P}oisson-disk Sampling and $k$-d Darts},
booktitle = {Topological and Statistical Methods for Complex Data
-- Tackling Large-Scale, High-Dimensional, and
Multivariate Data Sets},
publisher = {Springer},
year = 2014,
month = nov,
editor = {Janine Bennett and Fabien Vivodtzev and Valerio
Pascucci},
pages = {221--238},
doi = {10.1007/978-3-662-44900-4_13},
url = {http://escholarship.org/uc/item/64f9c6h3},
ucdcite = {a92}
}
@article{Ebeida:2014:KDS,
author = {Mohamed S. Ebeida and Anjul Patney and Scott A.
Mitchell and Keith R. Dalbey and Andrew A. Davidson
and John D. Owens},
title = {$k$-d Darts: Sampling by $k$-Dimensional Flat
Searches},
journal = {ACM Transactions on Graphics},
volume = 33,
number = 1,
year = 2014,
month = jan,
pages = {3:1--3:16},
doi = {10.1145/2522528},
url = {http://escholarship.org/uc/item/1k55d10f},
acmauthorize = {http://dl.acm.org/authorize?79280},
ucdcite = {a87}
}
@article{Ebeida:2016:DDT,
author = {Mohamed S. Ebeida and Ahmad A. Rushdi and Muhammad
A. Awad and Ahmed H. Mahmoud and Dong-Ming Yan and
Shawn A. English and John D. Owens and Chandrajit L.
Bajaj and Scott A. Mitchell},
title = {Disk Density Tuning of a Maximal Random Packing},
journal = {Computer Graphics Forum},
series = {SGP 2016},
volume = 35,
number = 5,
year = 2016,
month = jun,
pages = {259--269},
note = {Proceedings of the Symposium on Geometry Processing},
doi = {10.1111/cgf.12981},
url = {http://www.sandia.gov/~samitch/papers/disk-tuning-paper.pdf},
acceptance = {32\% (26/81)},
ucdcite = {a105}
}
@inproceedings{Gegan:2016:RGT,
author = {Ross K. Gegan and Vishal Ahuja and John D. Owens and
Dipak Ghosal},
title = {Real-Time {GPU}-based Timing Channel Detection using
Entropy},
booktitle = {Proceedings of the IEEE Conference on Communications
and Network Security},
year = 2016,
series = {CNS 2016},
month = oct,
pages = {296--305},
url = {http://escholarship.org/uc/item/1vf9f3t6},
doi = {10.1109/CNS.2016.7860497},
acceptance = {29.0\% (38/131)},
ucdcite = {a109}
}
@inproceedings{Geil:2014:WGC,
author = {Afton Geil and Yangzihao Wang and John D. Owens},
title = {{WTF}, {GPU}! {C}omputing {T}witter's Who-To-Follow
on the {GPU}},
booktitle = {Proceedings of the Second ACM Conference on Online
Social Networks},
year = 2014,
series = {COSN '14},
month = oct,
pages = {63--68},
doi = {10.1145/2660460.2660481},
url = {http://escholarship.org/uc/item/5xq3q8k0},
acmauthorize = {http://dl.acm.org/authorize?N82343},
acceptance = {15.9\% (22/138)},
ucdcite = {a90}
}
@inproceedings{Geil:2018:QFA,
author = {Afton Geil and Martin Farach-Colton and John D.
Owens},
title = {Quotient Filters: Approximate Membership Queries on
the {GPU}},
booktitle = {Proceedings of the 32nd IEEE International Parallel
and Distributed Processing Symposium},
series = {IPDPS 2018},
year = 2018,
month = may,
pages = {451--462},
url = {http://escholarship.org/uc/item/3v12f7dn},
doi = {10.1109/IPDPS.2018.00055},
acceptance = {113 accepted out of 481, 24.5\%},
ucdcite = {a118}
}
@inproceedings{Geil:2023:MCE,
author = {Afton Geil and Serban D. Porumbescu and John D.
Owens},
title = {Maximum Clique Enumeration on the {GPU}},
booktitle = {Proceedings of the Workshop on Graphs,
Architectures, Programming, and Learning},
series = {GrAPL 2023},
year = 2023,
month = may,
pages = {234--244},
doi = {10.1109/IPDPSW59300.2023.00047},
url = {https://escholarship.org/uc/item/7j96s061}
}
@inproceedings{Glavtchev:2011:FSL,
author = {Vladimir Glavtchev and P{\i}nar
Muyan-{\"{O}}z{\c{c}}elik and Jeffrey M. Ota and
John D. Owens},
title = {Feature-Based Speed Limit Sign Detection Using a
Graphics Processing Unit},
booktitle = {Proceedings of the 2011 IEEE Intelligent Vehicles
Symposium},
series = {IV '11},
year = 2011,
month = jun,
pages = {195--200},
doi = {10.1109/IVS.2011.5940539},
url = {https://escholarship.org/uc/item/26k663ts},
ucdcite = {a66}
}
@techreport{Gosink:2008:BIA,
author = {Luke J. Gosink and Kesheng Wu and E. Wes Bethel and
John D. Owens and Kenneth I. Joy},
title = {{B}in-{H}ash Indexing: A Parallel Method For Fast
Query Processing},
institution = {Lawrence Berkeley National Laboratory},
number = {LBNL-729E},
year = 2008,
url = {http://www.vis.lbl.gov/Publications/2008/LBNL-729E.pdf},
month = {20~} # aug
}
@inproceedings{Gosink:2009:DPB,
author = {Luke J. Gosink and Kesheng Wu and E. Wes Bethel and
John D. Owens and Kenneth I. Joy},
title = {Data Parallel Bin-Based Indexing for Answering
Queries on Multi-Core Architectures},
booktitle = {Proceedings of the 21st International Conference on
Scientific and Statistical Database Management},
series = {Lecture Notes in Computer Science},
volume = 5566,
publisher = {Springer},
year = 2009,
month = jun,
pages = {110--129},
url = {https://escholarship.org/uc/item/7wb7h84w},
doi = {10.1007/978-3-642-02279-1_9},
acceptance = {38.1\% (29/76)},
ucdcite = {a46}
}
@inproceedings{Gupta:2009:TOF,
author = {Kshitij Gupta and John D. Owens},
title = {Three-Layer Optimizations for Fast {GMM}
Computations on {GPU}-like Parallel Processors},
booktitle = {Proceedings of the IEEE Workshop on Automatic Speech
Recognition \& Understanding},
series = {ASRU 2009},
year = 2009,
month = dec,
url = {https://escholarship.org/uc/item/7z36z8wq},
pages = {146--151},
doi = {10.1109/ASRU.2009.5373410},
acceptance = {43.0\% (96/223)},
ucdcite = {a48}
}
@inproceedings{Gupta:2011:CAM,
author = {Kshitij Gupta and John D. Owens},
title = {Compute \& Memory Optimizations for High-Quality
Speech Recognition on Low-End {GPU} Processors},
booktitle = {Proceedings of the International Conference on High
Performance Computing},
series = {HiPC 2011},
year = 2011,
month = dec,
url = {https://escholarship.org/uc/item/7678h7zb},
doi = {10.1109/HiPC.2011.6152741},
acceptance = {"Only 40 papers could be accepted out of 206
submissions, representing an acceptance rate of
19.4\%."},
ucdcite = {a76}
}
@inproceedings{Gupta:2012:ASO,
author = {Kshitij Gupta and Jeff Stuart and John D. Owens},
title = {A Study of Persistent Threads Style {GPU}
Programming for {GPGPU} Workloads},
booktitle = {Proceedings of Innovative Parallel Computing},
series = {InPar '12},
year = 2012,
month = may,
url = {https://escholarship.org/uc/item/3j76d3td},
doi = {10.1109/InPar.2012.6339596},
acceptance = {25/62 (40.3\%)},
ucdcite = {a80}
}
@incollection{Harris:2007:PPS,
author = {Mark Harris and Shubhabrata Sengupta and John D.
Owens},
editor = {Hubert Nguyen},
booktitle = {GPU Gems 3},
title = {Parallel Prefix Sum (Scan) with {CUDA}},
chapter = 39,
publisher = {Addison Wesley},
month = aug,
year = 2007,
pages = {851--876},
url = {http://www.idav.ucdavis.edu/publications/print_pub?pub_id=916},
ucdcite = {a34},
acceptance = {20.5\% (41/200)}
}
@inproceedings{Jenkins:2011:LLF,
author = {John Jenkins and Isha Arkatkar and John D. Owens and
Alok Choudhary and Nagiza F. Samatova},
title = {Lessons Learned from Exploring the Backtracking
Paradigm on the {GPU}},
booktitle = {Euro-Par 2011: Proceedings of the 17th International
European Conference on Parallel and Distributed
Computing},
series = {Lecture Notes in Computer Science},
volume = 6853,
publisher = {Springer},
year = 2011,
month = aug # {\slash } # sep,
pages = {425--437},
acceptance = {29.9\% (81/271)},
doi = {10.1007/978-3-642-23397-5_42},
url = {https://escholarship.org/uc/item/7w25q253},
ucdcite = {a70}
}
@inproceedings{Kapasi:2000:ECO,
author = {Ujval J. Kapasi and William J. Dally and Scott
Rixner and Peter R. Mattson and John D. Owens and
Brucek Khailany},
title = {Efficient Conditional Operations for Data-parallel
Architectures},
booktitle = {Proceedings of the 33rd Annual ACM/IEEE
International Symposium on Microarchitecture},
series = {MICRO-33},
year = 2000,
month = dec,
pages = {159--170},
ucdcite = {a6},
url = {http://cva.stanford.edu/publications/2000/imagine-cstream/},
acmauthorize = {http://dl.acm.org/authorize?00119},
doi = {10.1145/360128.360145}
}
@inproceedings{Kapasi:2001:SS,
author = {Ujval J. Kapasi and Peter Mattson and William J.
Dally and John D. Owens and Brian Towles},
title = {Stream Scheduling},
booktitle = {Proceedings of the 3rd Workshop on Media and
Streaming Processors},
pages = {101--106},
year = 2001,
address = {Austin, TX},
month = {2~} # dec,
url = {http://cva.stanford.edu/publications/2002/imagine-sscd-tr/},
ucdcite = {a8}
}
@inproceedings{Kapasi:2002:TIS,
author = {Ujval J. Kapasi and William J. Dally and Brucek
Khailany and John D. Owens and Scott Rixner},
title = {The Imagine Stream Processor},
booktitle = {Proceedings of the IEEE International Conference on
Computer Design},
series = {ICCD 2002},
pages = {282--288},
year = 2002,
address = {Freiburg, Germany},
month = sep,
url = {http://cva.stanford.edu/publications/2002/imagine-overview-iccd/},
doi = {10.1109/ICCD.2002.1106783}
}
@article{Kapasi:2003:PSP,
author = {Ujval J. Kapasi and Scott Rixner and William J.
Dally and Brucek Khailany and Jung Ho Ahn and Peter
Mattson and John D. Owens},
title = {Programmable Stream Processors},
journal = {IEEE Computer},
volume = 36,
number = 8,
pages = {54--62},
year = 2003,
month = aug,
url = {http://cva.stanford.edu/publications/2003/imagine-ieeecomputer/},
doi = {10.1109/MC.2003.1220582},
ucdcite = {a14}
}
@techreport{Kass:2006:IDO,
author = {Michael Kass and Aaron Lefohn and John Owens},
title = {Interactive Depth of Field Using Simulated Diffusion
on a {GPU}},
institution = {Pixar Animation Studios},
year = 2006,
month = jan,
number = {\#06-01},
note = {http://graphics.pixar.com/library/DepthOfField},
url = {http://graphics.pixar.com/library/DepthOfField},
ucdcite = {f6}
}
@inproceedings{Kemal:2015:MSA,
author = {Jonathan Kemal and Roger L. Davis and John D. Owens},
title = {Multidisciplinary Simulation Acceleration using
Multiple Shared-Memory Graphical Processing Units},
booktitle = {AIAA Infotech @ Aerospace},
year = 2015,
series = {AIAA Science and Technology Forum},
month = jan,
doi = {10.2514/6.2015-1952},
url = {http://escholarship.org/uc/item/95630828},
ucdcite = {a93}
}
@article{Kemal:2016:MSA,
author = {Jonathan Y. Kemal and Roger L. Davis and John D.
Owens},
title = {Multidisciplinary simulation acceleration using
multiple shared memory graphical processing units},
journal = {International Journal of High Performance Computing
Applications},
year = 2016,
volume = 30,
number = 4,
month = nov,
pages = {486--508},
url = {http://escholarship.org/uc/item/4vg647c3},
doi = {10.1177/1094342016639114},
ucdcite = {a103}
}
@inproceedings{Kepner:2016:MFO,
author = {Jeremy Kepner and Peter Aaltonen and David Bader and
Ayd{\i}n Bulu\c{c} and Franz Franchetti and John
Gilbert and Dylan Hutchison and Manoj Kumar and
Andrew Lumsdaine and Henning Meyerhenke and Scott
McMillan and Jose Moreira and John D. Owens and Carl
Yang and Marcin Zalewski and Timothy Mattson},
title = {Mathematical Foundations of the {GraphBLAS}},
booktitle = {Proceedings of the IEEE High Performance Extreme
Computing Conference},
year = 2016,
month = sep,
doi = {10.1109/HPEC.2016.7761646},
url = {http://escholarship.org/uc/item/6xt0c99v},
ucdcite = {a108}
}
@inproceedings{Khailany:2000:ISA,
author = {Brucek Khailany and William J. Dally and Scott
Rixner and Ujval J. Kapasi and Peter Mattson and Jin
Namkoong and John D. Owens and Brian Towles},
title = {{I}magine: Signal and Image Processing Using
Streams},
booktitle = {Hotchips 12},
year = 2000,
month = aug,
url = {http://cva.stanford.edu/publications/2000/imagine-hotchips/}
}
@article{Khailany:2001:IMP,
author = {Brucek Khailany and William J. Dally and Ujval J.
Kapasi and Peter Mattson and Jinyung Namkoong and
John D. Owens and Brian Towles and Andrew Chang and
Scott Rixner},
title = {{Imagine}: {M}edia Processing with Streams},
journal = {IEEE Micro},
volume = 21,
number = 2,
pages = {35--46},
month = mar # {\slash } # apr,
year = 2001,
url = {http://cva.stanford.edu/publications/2001/imagine-ieeemicro/},
doi = {10.1109/40.918001},
ucdcite = {a7}
}
@inproceedings{Khailany:2003:ETV,
author = {Brucek Khailany and William J. Dally and Scott
Rixner and Ujval J. Kapasi and John D. Owens and
Brian Towles},
title = {Exploring the {VLSI} Scalability of Stream
Processors},
booktitle = {Proceedings of the Ninth Annual International
Symposium on High-Performance Computer Architecture},
series = {HPCA-9},
month = feb,
year = 2003,
pages = {153--164},
url = {http://cva.stanford.edu/publications/2003/imagine-scalability/},
doi = {10.1109/HPCA.2003.1183534},
acceptance = {31/141, 22\%},
ucdcite = {a13}
}
@inproceedings{Kniss:2005:OTO,
author = {Joe Kniss and Aaron Lefohn and Shubhabrata Sengupta
and Robert Strzodka and John D. Owens},
title = {Octree Textures on Graphics Hardware},
booktitle = {Technical Sketches Program, ACM SIGGRAPH},
month = aug,
year = 2005,
url = {https://escholarship.org/uc/item/9cg0w3q7},
acmauthorize = {http://dl.acm.org/authorize?842742},
doi = {10.1145/1187112.1187129},
ucdcite = {a19},
acceptance = {148/>350, 42\%}
}
@inproceedings{Lefohn:2005:DAS,
author = {Aaron Lefohn and Shubhabrata Sengupta and Joe Kniss
and Robert Strzodka and John D. Owens},
title = {Dynamic Adaptive Shadow Maps on Graphics Hardware},
booktitle = {Technical Sketches Program, ACM SIGGRAPH},
month = aug,
year = 2005,
url = {https://escholarship.org/uc/item/1mr768b6},
acmauthorize = {http://dl.acm.org/authorize?842749},
doi = {10.1145/1187112.1187126},
ucdcite = {a20},
acceptance = {148/>350, 42\%}
}
@incollection{Lefohn:2005:IEP,
author = {Aaron Lefohn and Joe Kniss and John Owens},
editor = {Matt Pharr},
booktitle = {GPU Gems 2},
title = {Implementing Efficient Parallel Data Structures on
{GPU}s},
chapter = 33,
publisher = {Addison Wesley},
month = mar,
year = 2005,
pages = {521--545},
url = {http://www.idav.ucdavis.edu/publications/print_pub?pub_id=832},
ucdcite = {a17},
acceptance = {33\%}
}
@inproceedings{Lefohn:2006:GGD,
title = {Glift: Generic Data Structures for the {GPU}},
booktitle = {Proceedings of the 2006 Workshop on Edge Computing
Using New Commodity Architectures},
author = {Aaron E. Lefohn and Shubhabrata Sengupta and Joe
Kniss and Robert Strzodka and John D. Owens},
year = 2006,
month = may,
pages = {D-15--16},
location = {Chapel Hill, NC},
eventtime = {May 23--24, 2006},
url = {https://escholarship.org/uc/item/1qg509fg},
ucdcite = {a26},
acceptance = {we were able to accommodate almost all submitted}
}
@article{Lefohn:2006:GGE,
author = {Aaron E. Lefohn and Joe Kniss and Robert Strzodka
and Shubhabrata Sengupta and John D. Owens},
title = {Glift: Generic, Efficient, Random-Access {GPU} Data
Structures},
journal = {ACM Transactions on Graphics},
year = 2006,
month = jan,
volume = 25,
number = 1,
pages = {60--99},
url = {https://escholarship.org/uc/item/6gc3x9w1},
acmauthorize = {http://dl.acm.org/authorize?805447},
doi = {10.1145/1122501.1122505},
ucdcite = {a24}
}
@article{Lefohn:2007:RSM,
author = {Aaron E. Lefohn and Shubhabrata Sengupta and John D.
Owens},
title = {Resolution-Matched Shadow Maps},
journal = {ACM Transactions on Graphics},
year = 2007,
volume = 26,
number = 4,
month = oct,
pages = {20:1--20:17},
url = {https://escholarship.org/uc/item/40v513qg},
acmauthorize = {http://dl.acm.org/authorize?936589},
doi = {10.1145/1289603.1289611},
ucdcite = {b1}
}
@inproceedings{Li:2012:KOT,
author = {Shengren Li and Lance Simons and Jagadeesh Bhaskar
Pakaravoor and Fatemeh Abbasinejad and John D. Owens
and Nina Amenta},
title = {k{ANN} on the {GPU} with Shifted Sorting},
booktitle = {Proceedings of High Performance Graphics},
series = {HPG '12},
year = 2012,
month = jun,
pages = {39--47},
url = {https://escholarship.org/uc/item/7h61t57k},
doi = {10.2312/EGGH/HPG12/039-047},
acceptance = {30\% (14/47)},
ucdcite = {a84}
}
@inproceedings{Lin:2018:BDL,
author = {Zhongyi Lin and Jeffrey M. Ota and John D. Owens and
P{\i}nar Muyan-{\"{O}}z{\c{c}}elik},
title = {Benchmarking Deep Learning Frameworks with
{FPGA}-suitable Models on a Traffic Sign Dataset},
booktitle = {Proceedings of the 2018 IEEE Intelligent Vehicles
Symposium},
series = {IV '18},
year = 2018,
month = jun,
pages = {1197--1203},
url = {https://escholarship.org/uc/item/7dc8d5vb},
doi = {10.1109/IVS.2018.8500685},
ucdcite = {a122}
}
@article{Lin:2019:BDL,
author = {Zhongyi Lin and Matthew Yih and Jeffrey M. Ota and
John D. Owens and P{\i}nar
Muyan-{\"{O}}z{\c{c}}elik},
title = {Benchmarking Deep Learning Frameworks and
Investigating {FPGA} Deployment for Traffic Sign
Classification and Detection},
journal = {IEEE Transactions on Intelligent Vehicles},
year = 2019,
month = sep,
volume = 4,
number = 3,
pages = {385--395},
url = {https://escholarship.org/uc/item/4sk284kw},
doi = {10.1109/TIV.2019.2919458},
code = {https://github.com/owensgroup/TrafficSignBench},
ucdcite = {a132}
}
@inproceedings{Lin:2021:TFA,
title = {Towards Flexible and Compiler-friendly Layer Fusion
for {CNN}s on Multi-core {CPU}s},
author = {Zhongyi Lin and Evangelos Georganas and John D.
Owens},
booktitle = {Euro-Par 2021: Proceedings of the 27th International
European Conference on Parallel and Distributed
Computing},
month = sep,
year = 2021,
doi = {10.1007/978-3-030-85665-6_15},
url_ = {https://easychair.org/publications/preprint/NLd7},
url = {https://escholarship.org/uc/item/9v75738g},
acceptance = {38/136 (27.9\%)},
ucdcite = {a141}
}
@inproceedings{Lin:2022:BAP,
author = {Zhongyi Lin and Louis Feng and Ehsan K. Ardestani
and Jaewon Lee and John Lundell and Changkyu Kim and
Arun Kejariwal and John D. Owens},
title = {Building a Performance Model for Deep Learning
Recommendation Model Training on {GPU}s},
booktitle = {2022 IEEE 29th International Conference on High
Performance Computing, Data, and Analytics},
series = {HiPC 2022},
year = 2022,
month = dec,
pages = {48--58},
doi = {10.1109/hipc56025.2022.00019},
url = {https://escholarship.org/uc/item/6rt535s6},
publisher = {IEEE},
eprint_ = {2201.07821v1},
acceptance = {35/131 (26.7\%)},
ucdcite = {a148}
}
@article{Lin:2025:TUP,
author = {Zhongyi Lin and Ning Sun and Pallab Bhattacharya and
Xizhou Feng and Louis Feng and John D. Owens},
title = {Towards Universal Performance Modeling for Machine
Learning Training on Multi-{GPU} Platforms},
journal = {Transactions on Parallel and Distributed Systems},
year = 2025,
month = feb,
volume = 36,
number = 2,
code = {https://github.com/owensgroup/ml_perf_model},
publisher = {IEEE},
pages = {226--238},
doi = {10.1109/TPDS.2024.3507814},
url = {http://escholarship.org/uc/item/5mv1s1gg}
}
@article{Liu:2018:OLA,
title = {Object Localization and Motion Transfer learning
with Capsules},
author = {Weitang Liu and Emad Barsoum and John D. Owens},
journal = {CoRR},
month = may,
year = 2018,
volume = {abs/1805.07706},
archiveprefix = {arXiv},
number = {1805.07706v1},
eprint = {1805.07706v1},
primaryclass = {cs.CV},
nonrefereed = {true}
}
@article{Liu:2019:UOS,
title = {Unsupervised Object Segmentation with Explicit
Localization Module},
author = {Weitang Liu and Lifeng Wei and James Sharpnack and
John D. Owens},
journal = {CoRR},
month = nov,
year = 2019,
volume = {abs/1911.09228},
archiveprefix = {arXiv},
number = {1911.09228v1},
eprint = {1911.09228v1},
primaryclass = {cs.CV},
nonrefereed = {true}
}
@inproceedings{Liu:2020:EOD,
author = {Weitang Liu and Xiaoyun Wang and John D. Owens and
Yixuan Li},
title = {Energy-based Out-of-distribution Detection},
booktitle = {Advances in Neural Information Processing Systems},
volume = 33,
year = 2020,
series = {NeurIPS 2020},
month = dec,
code = {https://github.com/wetliu/energy_ood},
url = {https://proceedings.neurips.cc/paper/2020/hash/f5496252609c43eb8a3d147ab9b9c006-Abstract.html},
acceptance = {20.1\% (1900/9454)},
ucdcite = {a139}
}
@incollection{Luebke:2017:PAS,
author = {David Luebke and John Owens},
booktitle = {Frontiers of Engineering: Reports on Leading-Edge
Engineering from the 2016 Symposium},
title = {Pixels at Scale: High-Performance Computer Graphics
and Vision},
publisher = {The National Academies Press},
year = 2017,
pages = {3--5},
doi = {10.17226/23659},
ucdcite = {bc1}
}
@article{Ma:2007:UVR,
author = {Kwan-Liu Ma and Robert Ross and Jian Huang and Greg
Humphreys and Nelson Max and Kenneth Moreland and
John D. Owens and Han-Wei Shen},
title = {Ultra-Scale Visualization: Research and Education},
journal = {Journal of Physics: Conference Series},
volume = 78,
month = jun,
year = 2007,
pages = {012088 (6pp)},
url = {http://stacks.iop.org/1742-6596/78/012088},
doi = {10.1088/1742-6596/78/1/012088},
ucdcite = {a32}
}
@article{Mahmoud:2021:RAG,
author = {Ahmed H. Mahmoud and Serban D. Porumbescu and John
D. Owens},
title = {{RXM}esh: A {GPU} Mesh Data Structure},
journal = {ACM Transactions on Graphics},
year = 2021,
volume = 40,
number = 4,
month = aug,
issue_date = {August 2021},
articleno = 104,
numpages = 16,
pages = {104:1--104:16},
url = {https://escholarship.org/uc/item/8r5848vp},
full_talk = {https://youtu.be/Se_cNAol4hY},
short_talk = {https://youtu.be/V_SHMXnCVws},
doi = {10.1145/3450626.3459748},
acmauthorize = {https://dl.acm.org/doi/10.1145/3450626.3459748?cid=81100458295},
acceptance = {149/444 (33.6\%)},
ucdcite = {a140}
}
@incollection{Mak:2014:ACS,
author = {Jason Mak and Mauricio Hess-Flores and Shawn Recker
and John D. Owens and Kenneth I. Joy},
title = {A Comparative Study of Recent {GPU}-Accelerated
Multi-View Sequential Reconstruction Triangulation
Methods for Large-Scale Scenes},
booktitle = {Big Data in 3D Computer Vision (Computer
Vision---ACCV 2014 Workshops)},
volume = 9008,
series = {Lecture Notes in Computer Science},
editor = {Jawahar, C. V. and Shan, Shiguang},
publisher = {Springer International Publishing},
year = 2014,
pages = {254--269},
month = nov,
url = {http://escholarship.org/uc/item/5jf612x9},
doi = {10.1007/978-3-319-16628-5_19},
ucdcite = {a88}
}
@inproceedings{Mak:2014:GAE,
author = {Jason Mak and Mauricio Hess-Flores and Shawn Recker
and John D. Owens and Kenneth I. Joy},
title = {{GPU}-Accelerated and Efficient Multi-View
Triangulation for Scene Reconstruction},
booktitle = {Proceedings of the IEEE Winter Conference on
Applications of Computer Vision},
series = {WACV '14},
year = 2014,
month = mar,
pages = {61--68},
url = {http://escholarship.org/uc/item/4nf4n0bc},
doi = {10.1109/WACV.2014.6836117},
ucdcite = {a91}
}
@inproceedings{Mattson:2000:CS,
author = {Peter Mattson and William J. Dally and Scott Rixner
and Ujval J. Kapasi and John D. Owens},
title = {Communication Scheduling},
booktitle = {Proceedings of the Ninth International Conference on
Architectural Support for Programming Languages and
Operating Systems},
series = {ASPLOS-IX},
year = 2000,
month = nov,
pages = {82--92},
url = {http://cva.stanford.edu/publications/2000/commsched_new.pdf},
acmauthorize = {http://dl.acm.org/authorize?16185},
doi = {10.1145/378995.379005},
ucdcite = {a5}
}
@inproceedings{Moerschell:2006:DTM,
author = {Adam Moerschell and John D. Owens},
title = {Distributed Texture Memory in a Multi-{GPU}
Environment},
year = 2006,
month = sep,
booktitle = {Proceedings of the 21st ACM SIGGRAPH/EUROGRAPHICS
Symposium on Graphics Hardware},
series = {GH '06},
pages = {31--38},
url = {https://escholarship.org/uc/item/15z072x5},
acmauthorize = {http://dl.acm.org/authorize?912688},
doi = {10.1145/1283900.1283905},
acceptance = {31.1\% (14/45)},
ucdcite = {a29}
}
@article{Moerschell:2008:DTM,
author = {Adam Moerschell and John D. Owens},
title = {Distributed Texture Memory in a Multi-{GPU}
Environment},
journal = {Computer Graphics Forum},
year = 2008,
volume = 27,
number = 1,
month = mar,
pages = {130--151},
url = {http://www.idav.ucdavis.edu/publications/print_pub?pub_id=918},
doi = {10.1111/j.1467-8659.2007.01101.x},
ucdcite = {b2}
}
@inproceedings{Muyan-Ozcelik:2008:FDR,
author = {P{\i}nar Muyan-{\"{O}}z{\c{c}}elik and John D. Owens
and Junyi Xia and Sanjiv S. Samant},
title = {Fast Deformable Registration on the {GPU}: A {CUDA}
Implementation of {D}emons},
booktitle = {Proceedings of the 2008 International Conference on
Computational Science and Its Applications (First
Technical Session on UnConventional High Performance
Computing)},
series = {UCHPC '08},
year = 2008,
month = jul,
pages = {223--233},
eventtime = {June 30th to July 3rd, 2008},
doi = {10.1109/ICCSA.2008.22},
url = {https://escholarship.org/uc/item/7fv9s4s4},
ucdcite = {a40}
}
@inproceedings{Muyan-Ozcelik:2010:ATA,
author = {P{\i}nar Muyan-{\"{O}}z{\c{c}}elik and Vladimir
Glavtchev and Jeffery M. Ota and John D. Owens},
title = {A Template-Based Approach for Real-Time
Speed-Limit-Sign Recognition on an Embedded System
using {GPU} Computing},
booktitle = {DAGM 2010: Proceedings of the 32nd Annual Symposium
of the German Association for Pattern Recognition},
series = {Lecture Notes in Computer Science},
volume = 6376,
publisher = {Springer},
editor = {Michael Goesele and Stefan Roth and Arjan Kuijper
and Bernt Schiele and Konrad Schindler},
year = 2010,
month = sep,
pages = {162--171},
doi = {10.1007/978-3-642-15986-2_17},
url = {https://escholarship.org/uc/item/5521275t},
acceptance = {58/133 (44\%)},
ucdcite = {a57}
}
@incollection{Muyan-Ozcelik:2011:RSR,
author = {P{\i}nar Muyan-{\"{O}}z{\c{c}}elik and Vladimir
Glavtchev and Jeffrey M. Ota and John D. Owens},
editor = {Wen{-mei} W. Hwu},
booktitle = {GPU Computing Gems},
volume = 1,
title = {Real-Time Speed-Limit-Sign Recognition on an
Embedded System Using a {GPU}},
chapter = 32,
publisher = {Morgan Kaufmann},
month = feb,
year = 2011,
pages = {497--516},
doi = {10.1016/B978-0-12-384988-5.00032-2},
url = {http://www.idav.ucdavis.edu/publications/print_pub?pub_id=1074},
acceptance = {There were a total of 272 submissions and will be
publishing 98 over the two volumes.},
ucdcite = {a62}
}
@inproceedings{Muyan-Ozcelik:2016:MRE,
author = {P{\i}nar Muyan-{\"{O}}z{\c{c}}elik and John D.
Owens},
title = {Multitasking Real-time Embedded {GPU} Computing
Tasks},
booktitle = {Proceedings of the 7th International Workshop on
Programming Models and Applications for Multicores
and Manycores},
year = 2016,
series = {PMAM 2016},
month = mar,
pages = {78--87},
doi = {10.1145/2883404.2883408},
url = {http://escholarship.org/uc/item/7jc3q2q9},
acmauthorize = {http://dl.acm.org/authorize?N03919},
acceptance = {13/22, 59.1\%},
ucdcite = {a101}
}
@article{Muyan-Ozcelik:2017:MFM,
author = {P{\i}nar Muyan-{\"{O}}z{\c{c}}elik and John D.
Owens},
title = {Methods for Multitasking among Real-time Embedded
Compute Tasks Running on the {GPU}},
journal = {Concurrency and Computation: Practice and
Experience},
year = 2017,
month = aug,
volume = 29,
number = 15,
pages = {e4118:1--e4118:14},
doi = {10.1002/cpe.4118},
ucdcite = {a114}
}
@inproceedings{Odemuyiwa:2023:ASD,
author = {Toluwanimi O. Odemuyiwa and Hadi Asghari-Moghaddam
and Michael Pellauer and Kartik Hegde and Po-An Tsai
and Neal Crago and Aamer Jaleel and John D. Owens
and Edgar Solomonik and Joel Emer and Christopher
Fletcher},
title = {Accelerating Sparse Data Orchestration via Dynamic
Reflexive Tiling},
booktitle = {Proceedings of the 28th ACM International Conference
on Architectural Support for Programming Languages
and Operating Systems},
volume = 3,
series = {ASPLOS '23},
year = 2023,
month = mar,
pages = {18--32},
doi = {10.1145/3582016.3582064},
url = {https://escholarship.org/uc/item/03w7t86h}
}
@article{Odemuyiwa:2024:TEL,
author = {Toluwanimi O. Odemuyiwa and Joel S. Emer and John D.
Owens},
title = {The {EDGE} Language: Extended General Einsums for
Graph Algorithms},
year = 2024,
month = apr,
number = {2404.11591},
eprint = {2404.11591},
journal = {CoRR},
volume = {abs/2404.11591},
archiveprefix = {arXiv},
primaryclass = {cs.DS},
nonrefereed = {true}
}
@inproceedings{Osama:2019:GCO,
author = {Muhammad Osama and Minh Truong and Carl Yang and
Ayd{\i}n Bulu\c{c} and John D. Owens},
title = {Graph Coloring on the {GPU}},
booktitle = {Proceedings of the Workshop on Graphs,
Architectures, Programming, and Learning},
year = 2019,
series = {GrAPL 2019},
month = may,
pages = {231--240},
doi = {10.1109/IPDPSW.2019.00046},
url = {https://escholarship.org/uc/item/6kp4p18t},
code = {https://github.com/gunrock/gunrock},
ucdcite = {a128}
}
@inproceedings{Osama:2022:EOP,
author = {Muhammad Osama and Serban D. Porumbescu and John D.
Owens},
title = {Essentials of Parallel Graph Analytics},
booktitle = {Proceedings of the Workshop on Graphs,
Architectures, Programming, and Learning},
year = 2022,
series = {GrAPL 2022},
month = may,
pages = {314--317},
doi = {10.1109/IPDPSW55747.2022.00061},
url = {https://escholarship.org/uc/item/2p19z28q},
code = {https://github.com/gunrock/essentials-cpp},
ucdcite = {a143}
}
@inproceedings{Osama:2023:APM,
author = {Muhammad Osama and Serban D. Porumbescu and John D.
Owens},
title = {A Programming Model for {GPU} Load Balancing},
booktitle = {Proceedings of the 28th ACM SIGPLAN Symposium on
Principles and Practice of Parallel Programming},
series = {PPoPP 2023},
year = 2023,
month = feb # {\slash } # mar,
pages = {79--91},
acceptance = {31 of 131 submissions, 23.7\%},
code = {https://github.com/gunrock/loops},
doi = {10.1145/3572848.3577434},
url = {https://escholarship.org/uc/item/9nq090zg},
ucdcite = {a150}
}
@article{Osama:2023:SWP,
title = {{Stream-K}: Work-centric Parallel Decomposition for
Dense Matrix-Matrix Multiplication on the {GPU}},
author = {Muhammad Osama and Duane Merrill and Cris Cecka and
Michael Garland and John D. Owens},
year = 2023,
month = jan,
journal = {CoRR},
volume = {abs/2301.03598},
number = {2301.03598},
eprint = {2301.03598},
archiveprefix = {arXiv},
primaryclass = {cs.DS},
nonrefereed = {true}
}
@inproceedings{Owens:2000:PRO,
author = {John D. Owens and William J. Dally and Ujval J.
Kapasi and Scott Rixner and Peter Mattson and Ben
Mowery},
title = {Polygon Rendering on a Stream Architecture},
year = 2000,
month = aug,
booktitle = {Proceedings of the ACM SIGGRAPH/Eurographics
Workshop on Graphics Hardware},
series = {HWWS '00},
pages = {23--32},
url = {http://graphics.stanford.edu/papers/prsa/},
acmauthorize = {http://dl.acm.org/authorize?1185},
doi = {10.1145/346876.346883},
ucdcite = {a4}
}
@phdthesis{Owens:2002:CGO,
author = {John D. Owens},
title = {Computer Graphics on a Stream Architecture},
school = {Stanford University},
month = nov,
year = 2002,
url = {http://graphics.stanford.edu/papers/jowens_thesis/}
}
@inproceedings{Owens:2002:CRA,
author = {John D. Owens and Brucek Khailany and Brian Towles
and William J. Dally},
title = {Comparing {R}eyes and {OpenGL} on a Stream
Architecture},
year = 2002,
month = sep,
booktitle = {Proceedings of the ACM SIGGRAPH/EUROGRAPHICS
Conference on Graphics Hardware},
series = {GH '02},
pages = {47--56},
url = {http://graphics.stanford.edu/papers/reyes-vs-opengl/}
}
@inproceedings{Owens:2002:MPA,
author = {John D. Owens and Ujval J. Kapasi and Peter Mattson
and Brian Towles and Ben Serebrin and Scott Rixner
and William J. Dally},
title = {Media Processing Applications on the {I}magine
Stream Processor},
booktitle = {Proceedings of the IEEE International Conference on
Computer Design},
series = {ICCD 2002},
pages = {295--302},
month = sep,
year = 2002,
address = {Freiburg, Germany},
url = {http://cva.stanford.edu/publications/2002/media-apps/},
doi = {10.1109/ICCD.2002.1106785},
ucdcite = {a11}
}
@article{Owens:2004:GTF,
author = {John D. Owens},
title = {{GPU}s tapped for general computing},
journal = {EE Times},
year = 2004,
month = {13~} # dec,
note = {http://www.eet.com/news/latest/showArticle.jhtml?articleID=55300884},
url = {http://www.eet.com/news/latest/showArticle.jhtml?articleID=55300884},
ucdcite = {---},
nonrefereed = {true}
}
@techreport{Owens:2004:OTS,
author = {John D. Owens},
title = {On The Scalability of Sensor Network Routing and
Compression Algorithms},
institution = {Computer Engineering Research Laboratory, University
of California, Davis},
year = 2004,
number = {ECE-CE-2004-1},
nonrefereed = {true},
note = {http://www.ece.ucdavis.edu/cerl/techreports/2004-1/},
url = {http://www.ece.ucdavis.edu/cerl/techreports/2004-1/}
}
@techreport{Owens:2005:AOG,
title = {Assessment of Graphic Processing Units ({GPU}s) for
{D}epartment of {D}efense ({DoD}) Digital Signal
Processing ({DSP}) Applications},
author = {John D. Owens and Shubhabrata Sengupta and Daniel
Horn},
year = 2005,
month = oct,
number = {ECE-CE-2005-3},
institution = {Department of Electrical and Computer Engineering,
University of California, Davis},
note = {http://www.ece.ucdavis.edu/cerl/techreports/2005-3/},
url = {http://www.ece.ucdavis.edu/cerl/techreports/2005-3/}
}
@inproceedings{Owens:2005:ASO,
author = {John D. Owens and David Luebke and Naga Govindaraju
and Mark Harris and Jens Kr\"{u}ger and Aaron E.
Lefohn and Tim Purcell},
title = {A Survey of General-Purpose Computation on Graphics
Hardware},
booktitle = {Eurographics 2005, State of the Art Reports},
year = 2005,
month = aug,
pages = {21--51},
ucdcite = {a21},
url = {https://escholarship.org/uc/item/4nq8h63h},
acceptance = {27.3\% (6/22)}
}
@incollection{Owens:2005:SAA,
author = {John Owens},
editor = {Matt Pharr},
booktitle = {GPU Gems 2},
title = {Streaming Architectures and Technology Trends},
chapter = 29,
publisher = {Addison Wesley},
month = mar,
year = 2005,
pages = {457--470},
url = {https://developer.nvidia.com/gpugems/gpugems2/part-iv-general-purpose-computation-gpus-primer/chapter-29-streaming-architectures},
ucdcite = {a16},
acceptance = {33\%}
}
@article{Owens:2006:TIA,
author = {John D. Owens},
title = {The Installation and Use of {OpenType} Fonts in
{\LaTeX}},
journal = {TUGboat: Communications of the {\TeX} Users Group},
volume = 27,
number = 2,
month = dec,
year = 2006,
pages = {112--118},
url = {http://www.ece.ucdavis.edu/cerl/publications/owens:2006:tia/},
ucdcite = {a28}
}
@article{Owens:2007:ASO,
author = {John D. Owens and David Luebke and Naga Govindaraju
and Mark Harris and Jens Kr\"{u}ger and Aaron E.
Lefohn and Tim Purcell},
title = {A Survey of General-Purpose Computation on Graphics
Hardware},
journal = {Computer Graphics Forum},
year = 2007,
volume = 26,
number = 1,
month = mar,
pages = {80--113},
url = {https://escholarship.org/uc/item/9ns2d70c},
doi = {10.1111/j.1467-8659.2007.01012.x},
ucdcite = {a30}
}
@article{Owens:2007:RCF,
author = {John D. Owens and William J. Dally and Ron Ho and D.
N. Jayasimha and Stephen W. Keckler and Li-Shiuan
Peh},
title = {Research Challenges for On-Chip Interconnection
Networks},
journal = {IEEE Micro},
volume = 27,
number = 5,
year = 2007,
month = sep # {\slash } # oct,
pages = {96--108},
url = {http://www.ece.ucdavis.edu/~ocin06/ieeemicro.html},
doi = {10.1109/MM.2007.4378787},
ucdcite = {b3}
}
@article{Owens:2007:TMS,
author = {John D. Owens},
title = {Towards Multi-{GPU} Support for Visualization},
journal = {Journal of Physics: Conference Series},
volume = 78,
month = jun,
pages = {012055 (5pp)},
year = 2007,
url = {http://stacks.iop.org/1742-6596/78/012055},
doi = {10.1088/1742-6596/78/1/012055},
ucdcite = {a33}
}
@article{Owens:2008:GC,
author = {John D. Owens and Mike Houston and David Luebke and
Simon Green and John E. Stone and James C. Phillips},
title = {{GPU} Computing},
journal = {Proceedings of the IEEE},
month = may,
year = 2008,
volume = 96,
number = 5,
pages = {879--899},
url = {http://escholarship.org/uc/item/0cv1p1nc},
doi = {10.1109/JPROC.2008.917757},
ucdcite = {b4}
}
@article{Owens:2018:TPG,
author = {John D. Owens},
title = {Technical Perspective: Graphs, Betweenness
Centrality, and the {GPU}},
journal = {Communications of the ACM},
year = 2018,
volume = 61,
number = 8,
pages = 84,
month = aug,
url = {https://escholarship.org/uc/item/9tn2q0ks},
acmauthorize = {https://dl.acm.org/doi/10.1145/3230483?cid=81100458295},
doi = {10.1145/3230483},
ucdcite = {a123}
}
@inproceedings{Owens:2024:HFT,
author = {John D. Owens and Bruce Hoppe},
title = {Helping Faculty Teach Software Performance
Engineering},
url = {https://escholarship.org/uc/item/2fj7x89s},
booktitle = {Proceedings of the 14th NSF/TCPP Workshop on
Parallel and Distributed Computing Education},
year = 2024,
series = {EduPar-24},
month = may,
pages = {338--341},
doi = {10.1109/IPDPSW63119.2024.00078}
}
@inproceedings{Pan:2017:MGA,
author = {Yuechao Pan and Yangzihao Wang and Yuduo Wu and Carl
Yang and John D. Owens},
title = {Multi-{GPU} Graph Analytics},
booktitle = {Proceedings of the 31st IEEE International Parallel
and Distributed Processing Symposium},
series = {IPDPS 2017},
year = 2017,
month = may # {\slash } # jun,
pages = {479--490},
url = {http://escholarship.org/uc/item/39r145g1},
doi = {10.1109/IPDPS.2017.117},
code = {https://github.com/gunrock/gunrock},
acceptance = {116 accepted out of 508, 22.8\%},
ucdcite = {a110}
}
@inproceedings{Pan:2018:SBS,
author = {Yuechao Pan and Roger Pearce and John D. Owens},
title = {Scalable Breadth-First Search on a {GPU} Cluster},
booktitle = {Proceedings of the 32nd IEEE International Parallel
and Distributed Processing Symposium},
series = {IPDPS 2018},
year = 2018,
month = may,
pages = {1090--1101},
url = {https://escholarship.org/uc/item/9bd842z6},
url_ = {http://arxiv.org/abs/1803.03922},
doi = {10.1109/IPDPS.2018.00118},
acceptance = {113 accepted out of 481, 24.5\%},
ucdcite = {a119}
}
@inproceedings{Park:2005:AFF,
author = {Sung Park and Lars Linsen and Oliver Kreylos and
John D. Owens and Bernd Hamann},
title = {A Framework for Real-Time Volume Visualization of
Streaming Scattered Data},
booktitle = {Proceedings of the Tenth International Fall Workshop
on Vision, Modeling, and Visualization},
series = {VMV 2005},
year = 2005,
month = nov,
pages = {225--232},
url = {https://escholarship.org/uc/item/3m687574},
ucdcite = {a22},
acceptance = {They drew over 100 papers and they published 63
papers, where 33 papers were accepted for oral
presentation [including ours] and another 30 were
accepted for poster presentation.}
}
@article{Park:2006:DSI,
author = {Sung W. Park and Lars Linsen and Oliver Kreylos and
John D. Owens and Bernd Hamann},
title = {Discrete {S}ibson Interpolation},
journal = {IEEE Transactions on Visualization and Computer
Graphics},
year = 2006,
month = mar # {\slash } # apr,
volume = 12,
number = 2,
pages = {243--253},
url = {https://escholarship.org/uc/item/27v9h554},
doi = {10.1109/TVCG.2006.27},
ucdcite = {a23}
}
@inproceedings{Patel:2012:PLD,
author = {Ritesh A. Patel and Yao Zhang and Jason Mak and John
D. Owens},
title = {Parallel Lossless Data Compression on the {GPU}},
booktitle = {Proceedings of Innovative Parallel Computing},
series = {InPar '12},
year = 2012,
month = may,
url = {http://www.idav.ucdavis.edu/publications/print_pub?pub_id=1087},
doi = {10.1109/InPar.2012.6339599},
acceptance = {25/62 (40.3\%)},
ucdcite = {a79}
}
@article{Patney:2008:RRA,
author = {Anjul Patney and John D. Owens},
title = {Real-Time {R}eyes-Style Adaptive Surface
Subdivision},
journal = {ACM Transactions on Graphics},
volume = 27,
number = 5,
year = 2008,
month = dec,
pages = {143:1--143:8},
url = {https://escholarship.org/uc/item/3nb470qj},
acmauthorize = {http://dl.acm.org/authorize?030035},
doi = {10.1145/1409060.1409096},
acceptance = {18.4\% (59/321)},
ucdcite = {a42}
}
@inproceedings{Patney:2009:PVT,
author = {Anjul Patney and Mohamed S. Ebeida and John D.
Owens},
title = {Parallel View-Dependent Tessellation of
{C}atmull-{C}lark Subdivision Surfaces},
booktitle = {Proceedings of High Performance Graphics},
series = {HPG '09},
year = 2009,
month = aug,
pages = {99--108},
url = {https://escholarship.org/uc/item/5h95328x},
acmauthorize = {http://dl.acm.org/authorize?103333},
doi = {10.1145/1572769.1572785},
acceptance = {29.2\% (21/72)},
ucdcite = {a47}
}
@article{Patney:2010:FCA,
author = {Anjul Patney and Stanley Tzeng and John D. Owens},
title = {Fragment-Parallel Composite and Filter},
journal = {Computer Graphics Forum (Proceedings of the
Eurographics Symposium on Rendering)},
year = 2010,
month = jun,
volume = 29,
number = 4,
pages = {1251--1258},
doi = {10.1111/j.1467-8659.2010.01720.x},
acceptance = {38.9\% (28/72)},
url = {http://www.idav.ucdavis.edu/publications/print_pub?pub_id=1037},
ucdcite = {a54}
}
@article{Patney:2015:PAF,
author = {Anjul Patney and Stanley Tzeng and Seitz, Jr., Kerry
A. and John D. Owens},
title = {{P}iko: A Framework for Authoring Programmable
Graphics Pipelines},
journal = {ACM Transactions on Graphics},
year = 2015,
month = aug,
volume = 34,
number = 4,
pages = {147:1--147:13},
doi = {10.1145/2766973},
acmauthorize = {http://dl.acm.org/authorize?N05619},
url = {http://escholarship.org/uc/item/7dx346m6},
ucdcite = {a98}
}
@inproceedings{Phillips:2009:RAP,
author = {Everett H. Phillips and Yao Zhang and Roger L. Davis
and John D. Owens},
title = {Rapid Aerodynamic Performance Prediction on a
Cluster of Graphics Processing Units},
booktitle = {Proceedings of the 47th AIAA Aerospace Sciences
Meeting},
year = 2009,
month = jan,
number = {AIAA 2009-565},
url = {https://escholarship.org/uc/item/0hx199m6},
doi = {10.2514/6.2009-565},
ucdcite = {a43}
}
@inproceedings{Phillips:2010:UTS,
author = {Everett H. Phillips and Roger L. Davis and John D.
Owens},
title = {Unsteady Turbulent Simulations on a Cluster of
Graphics Processors},
booktitle = {Proceedings of the 40th AIAA Fluid Dynamics
Conference},
year = 2010,
month = jun,
number = {AIAA 2010-5036},
url = {https://escholarship.org/uc/item/2xt3q8ts},
doi = {10.2514/6.2010-5036},
ucdcite = {a53}
}
@article{Phillips:2011:AO2,
author = {Everett H. Phillips and Yao Zhang and Roger L. Davis
and John D. Owens},
title = {Acceleration of 2-{D} Compressible Flow Solvers with
Graphics Processing Unit Clusters},
journal = {Journal of Aerospace Computing, Information, and
Communication},
year = 2011,
volume = 8,
number = 8,
pages = {237--249},
month = aug,
doi = {10.2514/1.44909},
url = {http://www.idav.ucdavis.edu/publications/print_pub?pub_id=1071},
ucdcite = {a69}
}
@inproceedings{Riffel:2004:MFM,
author = {Andrew T. Riffel and Aaron E. Lefohn and Kiril
Vidimce and Mark Leone and John D. Owens},
title = {Mio: Fast Multipass Partitioning via Priority-Based
Instruction Scheduling},
year = 2004,
month = aug,
booktitle = {Proceedings of the ACM SIGGRAPH/EUROGRAPHICS
Conference on Graphics Hardware},
series = {GH '04},
pages = {35--44},
ucdcite = {a15},
url = {https://escholarship.org/uc/item/7ff751pf},
acmauthorize = {http://dl.acm.org/authorize?866557},
doi = {10.1145/1058129.1058135},
acceptance = {32.6\% (14/43)}
}
@inproceedings{Rixner:1998:ABA,
author = {Scott Rixner and William J. Dally and Ujval J.
Kapasi and Brucek Khailany and Abelardo
Lopez-Lagunas and Peter Mattson and John D. Owens},
title = {A Bandwidth-Efficient Architecture for Media
Processing},
booktitle = {Proceedings of the 31st Annual ACM/IEEE
International Symposium on Microarchitecture},
series = {MICRO-31},
month = dec,
year = 1998,
pages = {3--13},
url = {http://cva.stanford.edu/publications/1998/imagine.pdf},
doi = {10.1109/MICRO.1998.742118}
}
@inproceedings{Rixner:2000:MAS,
author = {Scott Rixner and William J. Dally and Ujval J.
Kapasi and Peter Mattson and John D. Owens},
title = {Memory Access Scheduling},
booktitle = {Proceedings of the 27th International Symposium on
Computer Architecture},
series = {ISCA-2000},
year = 2000,
month = jun,
pages = {128--138},
url = {http://cva.stanford.edu/publications/2000/mas.pdf},
acmauthorize = {http://dl.acm.org/authorize?9220},
doi = {10.1145/339647.339668}
}
@inproceedings{Rixner:2000:ROF,
author = {Scott Rixner and William J. Dally and Brucek
Khailany and Peter Mattson and Ujval Kapasi and John
D. Owens},
title = {Register Organization for Media Processing},
booktitle = {Proceedings of the Sixth Annual International
Symposium on High-Performance Computer Architecture},
series = {HPCA-6},
year = 2000,
month = jan,
pages = {375--386},
url = {http://cva.stanford.edu/publications/2000/register.pdf},
doi = {10.1109/HPCA.2000.824366}
}
@incollection{Rixner:2023:MAS,
author = {Scott Rixner and William J. Dally and Ujval J.
Kapasi and Peter Mattson and John D. Owens},
editor = {Jos{\'e} F. Mart{\'\i}nez and Lizy K. John},
title = {{RETROSPECTIVE}: {M}emory Access Scheduling},
booktitle = {{ISCA@50 25-Year Retrospective: 1996--2020}},
month = jun,
year = 2023,
publisher = {ACM SIGARCH and IEEE TCCA},
url = {https://bit.ly/isca50_retrospective}
}
@article{Samant:2008:HPC,
author = {Sanjiv S. Samant and Junyi Xia and P{\i}nar
Muyan-{\"{O}}z{\c{c}}elik and John D. Owens},
title = {High performance computing for deformable image
registration: Towards a new paradigm in adaptive
radiotherapy},
journal = {Medical Physics},
year = 2008,
volume = 35,
number = 8,
month = aug,
pages = {3546--3553},
doi = {10.1118/1.2948318},
ucdcite = {a41}
}
@article{Seitz:2013:AGI,
author = {Seitz, Jr., Kerry A. and Alex Kennedy and Owen
Ransom and Bassam A. Younis and John D. Owens},
title = {A {GPU} Implementation for Two-Dimensional Shallow
Water Modeling},
journal = {CoRR},
year = 2013,
month = sep,
volume = {abs/1309.1230},
archiveprefix = {arXiv},
number = {1309.1230v1},
eprint = {1309.1230v1},
primaryclass = {cs.DC},
nonrefereed = {true}
}
@article{Seitz:2019:SMF,
author = {Seitz, Jr., Kerry A. and T. Foley and Serban D.
Porumbescu and John D. Owens},
title = {Staged Metaprogramming for Shader System
Development},
journal = {ACM Transactions on Graphics},
year = 2019,
month = nov,
volume = 38,
number = 6,
pages = {202:1--202:15},
doi = {10.1145/3355089.3356554},
acmauthorize = {https://dl.acm.org/doi/10.1145/3355089.3356554?cid=81100458295},
url = {https://escholarship.org/uc/item/2f8448n2},
acceptance = {30\% (93/309)},
ucdcite = {a136}
}
@article{Seitz:2022:SUS,
author = {Seitz, Jr., Kerry A. and Theresa Foley and Serban D.
Porumbescu and John D. Owens},
title = {Supporting Unified Shader Specialization by
Co-opting {C}++ Features},
journal = {Proceedings of the ACM on Computer Graphics and
Interactive Techniques},
year = 2022,
volume = 5,
number = 3,
pages = {25:1--25:17},
month = jul,
doi = {10.1145/3543866},
url = {https://escholarship.org/uc/item/3127f66s},
eprint_ = {2109.14682},
acmauthorize = {
https://dl.acm.org/doi/10.1145/3543866?cid=81100458295},
ucdcite = {a144}
}
@inproceedings{Sengupta:2006:AWS,
title = {A Work-Efficient Step-Efficient Prefix Sum
Algorithm},
booktitle = {Proceedings of the 2006 Workshop on Edge Computing
Using New Commodity Architectures},
author = {Shubhabrata Sengupta and Aaron E. Lefohn and John D.
Owens},
year = 2006,
month = may,
pages = {D-26--27},
location = {Chapel Hill, NC},
eventtime = {May 23--24, 2006},
url = {https://escholarship.org/uc/item/6j57h5zw},
acceptance = {we were able to accommodate almost all submitted},
ucdcite = {a25}
}
@inproceedings{Sengupta:2007:SPF,
title = {Scan Primitives for {GPU} Computing},
author = {Shubhabrata Sengupta and Mark Harris and Yao Zhang
and John D. Owens},
booktitle = {Proceedings of the 22nd ACM SIGGRAPH/EUROGRAPHICS
Symposium on Graphics Hardware},
series = {GH '07},
year = 2007,
month = aug,
pages = {97--106},
url = {https://escholarship.org/uc/item/8051p6nd},
doi = {10.2312/EGGH/EGGH07/097-106},
cvnote = {Best Paper Award. 2017 High Performance Graphics
Test of Time Award for the most influential paper
from HPG's 2007--08 predecessor conferences.},
acceptance = {12/30 (40\%)},
ucdcite = {a31}
}
@incollection{Sengupta:2011:EPS,
author = {Shubhabrata Sengupta and Mark Harris and Michael
Garland and John D. Owens},
editor = {Jakub Kurzak and David A. Bader and Jack Dongarra},
booktitle = {Scientific Computing with Multicore and
Accelerators},
title = {Efficient Parallel Scan Algorithms for many-core
{GPU}s},
chapter = 19,
publisher = {Taylor \& Francis},
year = 2011,
series = {Chapman \& Hall/CRC Computational Science},
month = jan,
pages = {413--442},
url = {https://escholarship.org/uc/item/985331m3},
doi = {10.1201/b10376-29},
ucdcite = {a59}
}
@inproceedings{Serebrin:2002:ASP,
author = {Ben Serebrin and John D. Owens and Brucek Khailany
and Peter Mattson and Ujval J. Kapasi and Chen H.
Chen and Jinyung Namkoong and Stephen P. Crago and
Scott Rixner and William J. Dally},
title = {A Stream Processor Development Platform},
booktitle = {Proceedings of the IEEE International Conference on
Computer Design},
series = {ICCD 2002},
pages = {303--308},
year = 2002,
address = {Freiburg, Germany},
month = sep,
url = {http://cva.stanford.edu/publications/2002/serebrin_iccd2002_devel.pdf},
doi = {10.1109/ICCD.2002.1106786}
}
@inproceedings{Shashkov:2015:EDR,
author = {Mikhail M. Shashkov and Jason Mak and Shawn Recker
and Connie Nguyen and John Owens and Kenneth I. Joy},
title = {Efficient Dense Reconstruction Using Geometry and
Image Consistency Constraints},
series = {AIPR 2015},
year = 2015,
booktitle = {Proceedings of the IEEE Applied Imagery Pattern
Recognition Workshop},
month = oct,
numpages = 7,
url = {http://escholarship.org/uc/item/2rj6w5pb},
doi = {10.1109/AIPR.2015.7444539},
ucdcite = {a99}
}
@article{Shinn:2023:TSR,
author = {Cameron Shinn and Collin McCarthy and Saurav
Muralidharan and Muhammad Osama and John D. Owens},
title = {The Sparsity Roofline: Understanding the Hardware
Limits of Sparse Neural Networks},
year = 2023,
month = sep,
number = {2310.00496},
eprint = {2310.00496},
journal = {CoRR},
volume = {abs/2310.00496},
archiveprefix = {arXiv},
primaryclass = {cs.CV},
nonrefereed = {true}
}
@inproceedings{Silberstein:2008:ECO,
author = {Mark Silberstein and Assaf Schuster and Dan Geiger
and Anjul Patney and John D. Owens},
title = {Efficient Computation of Sum-products on {GPU}s
Through Software-Managed Cache},
booktitle = {Proceedings of the 22nd ACM International Conference
on Supercomputing},
series = {ICS '08},
year = 2008,
month = jun,
pages = {309--318},
url = {https://escholarship.org/uc/item/8js4v3f7},
acmauthorize = {http://dl.acm.org/authorize?072887},
doi = {10.1145/1375527.1375572},
acceptance = {37/140 (26\%)},
ucdcite = {a39}
}
@incollection{Silberstein:2011:ASC,
author = {Mark Silberstein and Assaf Schuster and John D.
Owens},
editor = {Wen{-mei} W. Hwu},
booktitle = {GPU Computing Gems},
volume = 2,
title = {Applying Software-Managed Caching and {CPU/GPU} Task
Scheduling for Accelerating Dynamic Workloads},
chapter = 36,
publisher = {Morgan Kaufmann},
month = oct,
year = 2011,
pages = {501--517},
doi = {10.1016/B978-0-12-385963-1.00036-8},
acceptance = {There were a total of 272 submissions and will be
publishing 98 over the two volumes.},
ucdcite = {a73}
}
@inproceedings{Stone:2011:GPA,
author = {Christopher P. Stone and Earl P. N. Duque and Yao
Zhang and David Car and John D. Owens and Roger L.
Davis},
title = {{GPGPU} parallel algorithms for structured-grid
{CFD} codes},
booktitle = {Proceedings of the 20th AIAA Computational Fluid
Dynamics Conference},
number = {2011-3221},
year = 2011,
month = jun,
url = {https://escholarship.org/uc/item/9hv9327j},
doi = {10.2514/6.2011-3221},
ucdcite = {a67}
}
@inproceedings{Stuart:2009:MPO,
author = {Jeff A. Stuart and John D. Owens},
title = {Message Passing on Data-Parallel Architectures},
booktitle = {Proceedings of the 23rd IEEE International Parallel
and Distributed Processing Symposium},
series = {IPDPS 2009},
month = may,
year = 2009,
url = {https://escholarship.org/uc/item/1vc4t6jg},
doi = {10.1109/IPDPS.2009.5161065},
acceptance = {100/440 (22.7\%)},
ucdcite = {a45}
}
@inproceedings{Stuart:2010:GC,
author = {Jeff A. Stuart and Michael Cox and John D. Owens},
title = {{GPU}-to-{CPU} Callbacks},
series = {Lecture Notes in Computer Science},
volume = 6586,
publisher = {Springer},
booktitle = {Euro-Par 2010 Workshops: Proceedings of the Third
Workshop on UnConventional High Performance
Computing (UCHPC 2010)},
year = 2011,
pages = {365--372},
url = {https://escholarship.org/uc/item/58j4v6f8},
doi = {10.1007/978-3-642-21878-1_45},
month = jul,
lncsurl = {http://www.springer.com/computer/communication+networks/book/978-3-642-21877-4},
acceptance = {9/16 (56\%)},
ucdcite = {a56}
}
@inproceedings{Stuart:2010:MVR,
author = {Jeff A. Stuart and Cheng-Kai Chen and Kwan-Liu Ma
and John D. Owens},
title = {Multi-{GPU} Volume Rendering using {M}ap{R}educe},
year = 2010,
booktitle = {Proceedings of the 19th ACM International Symposium
on High Performance Distributed Computing / The
First International Workshop on MapReduce and its
Applications},
series = {HPDC '10 / MAPREDUCE '10},
month = jun,
pages = {841--848},
doi = {10.1145/1851476.1851597},
acceptance = {We had 19 submissions and 11 were accepted.},
url = {https://escholarship.org/uc/item/65c2x71h},
acmauthorize = {http://dl.acm.org/authorize?395829},
ucdcite = {a52}
}
@inproceedings{Stuart:2011:EMT,
author = {Jeff A. Stuart and Pavan Balaji and John D. Owens},
title = {Extending {MPI} to Accelerators},
booktitle = {Proceedings of the First Workshop on Architectures
and Systems for Big Data},
series = {ASBD 2011},
year = 2011,
month = oct,
pages = {19--23},
url = {https://escholarship.org/uc/item/6xz3v4f9},
doi = {10.1145/2377978.2377981},
acmauthorize = {http://dl.acm.org/authorize?62766},
ucdcite = {a72}
}
@article{Stuart:2011:ESP,
author = {Jeff A. Stuart and John D. Owens},
title = {Efficient Synchronization Primitives for {GPU}s},
journal = {CoRR},
year = 2011,
month = oct,
volume = {abs/1110.4623},
archiveprefix = {arXiv},
number = {1110.4623v1},
eprint = {1110.4623v1},
primaryclass = {cs.OS},
dblprecord = {http://dblp.uni-trier.de/rec/bibtex/journals/corr/abs-1110-46},
nonrefereed = {true},
ucdcite = {f7}
}
@inproceedings{Stuart:2011:MMO,
author = {Jeff A. Stuart and John D. Owens},
title = {Multi-{GPU} {MapReduce} on {GPU} Clusters},
booktitle = {Proceedings of the 25th IEEE International Parallel
and Distributed Processing Symposium},
series = {IPDPS 2011},
month = may,
year = 2011,
pages = {1068--1079},
acceptance = {112/571 (19.6\%)},
doi = {10.1109/IPDPS.2011.102},
url = {https://escholarship.org/uc/item/5rw127tw},
ucdcite = {a65}
}
@techreport{Szumel:2003:OTF,
author = {Leo Szumel and John D. Owens},
title = {On the Feasibility of the {UC} {D}avis {M}etanet},
institution = {Computer Engineering Research Laboratory, University
of California, Davis},
year = 2003,
number = {ECE-CE-2003-2},
nonrefereed = {true},
note = {http://www.ece.ucdavis.edu/cerl/techreports/2003-2/},
url = {http://www.ece.ucdavis.edu/cerl/techreports/2003-2/}
}
@inproceedings{Szumel:2005:TAM,
author = {Leo Szumel and Jason LeBrun and John D. Owens},
title = {Towards a Mobile Agent Framework for Sensor
Networks},
booktitle = {Proceedings of the Second IEEE Workshop on Embedded
Networked Sensors},
series = {EmNetS-II},
year = 2005,
month = may,
pages = {79--87},
url = {http://www.ece.ucdavis.edu/~lpszumel/pubs.html},
doi = {10.1109/EMNETS.2005.1469102},
acceptance = {17/43, 39.5\%},
ucdcite = {a18}
}
@inproceedings{Szumel:2006:TVP,
author = {Leo Szumel and John D. Owens},
title = {The Virtual Pheromone Communication Primitive},
booktitle = {Proceedings of the Second IEEE International
Conference on Distributed Computing in Sensor
Systems},
series = {Lecture Notes in Computer Science},
volume = 4026,
publisher = {Springer},
editor = {Phillip B. Gibbons and Tarek Abdelzaher and James
Aspnes and Ramesh Rao},
month = jun,
year = 2006,
pages = {135--149},
url = {http://www.ece.ucdavis.edu/cerl/publications/szumel:2006:tvp/},
doi = {10.1007/11776178_9},
acceptance = {33/87, 37.9\%},
ucdcite = {a27}
}
@inproceedings{Tzeng:2010:TMF,
author = {Stanley Tzeng and Anjul Patney and John D. Owens},
title = {Task Management for Irregular-Parallel Workloads on
the {GPU}},
booktitle = {Proceedings of High Performance Graphics},
series = {HPG '10},
year = 2010,
month = jun,
pages = {29--37},
url = {https://escholarship.org/uc/item/9r15d4zk},
doi = {10.2312/EGGH/HPG10/029-037},
acceptance = {31.7\% (19/60)},
ucdcite = {a51},
cvnote = {2019 High Performance Graphics Test of Time Award
for the most influential paper from HPG's 2010
predecessor conferences.}
}
@article{Tzeng:2012:AGT,
author = {Stanley Tzeng and Brandon Lloyd and John D. Owens},
title = {A {GPU} Task-Parallel Model with Dependency
Resolution},
journal = {IEEE Computer},
year = 2012,
volume = 45,
number = 8,
month = aug,
pages = {34--41},
url = {https://escholarship.org/uc/item/4956q122},
doi = {10.1109/MC.2012.255},
ucdcite = {a85}
}
@article{Tzeng:2012:FCH,
title = {Finding Convex Hulls Using {Q}uickhull on the {GPU}},
author = {Stanley Tzeng and John D. Owens},
journal = {CoRR},
month = jan,
year = 2012,
volume = {abs/1201.2936},
archiveprefix = {arXiv},
number = {1201.2936v1},
eprint = {1201.2936v1},
primaryclass = {cs.OS},
nonrefereed = {true},
ucdcite = {f8}
}
@inproceedings{Tzeng:2012:HPD,
author = {Stanley Tzeng and Anjul Patney and Andrew Davidson
and Mohamed S. Ebeida and Scott A. Mitchell and John
D. Owens},
title = {High-Quality Parallel Depth-of-Field Using Line
Samples},
booktitle = {Proceedings of High Performance Graphics},
series = {HPG '12},
year = 2012,
month = jun,
pages = {23--31},
doi = {10.2312/EGGH/HPG12/023-031},
url = {https://escholarship.org/uc/item/6n59n3br},
acceptance = {30\% (14/47)},
ucdcite = {a83}
}
@inproceedings{Wang:2015:FSA,
author = {Leyuan Wang and Sean Baxter and John D. Owens},
title = {Fast Parallel Suffix Array on the {GPU}},
booktitle = {Euro-Par 2015: Proceedings of the 21st International
European Conference on Parallel and Distributed
Computing},
series = {Lecture Notes in Computer Science},
volume = 9233,
publisher = {Springer},
year = 2015,
month = aug,
pages = {573--587},
cvnote = {Distinguished Paper},
doi = {10.1007/978-3-662-48096-0_44},
url = {http://escholarship.org/uc/item/83r7w305},
acceptance = {26.8\% (51/190). 2 papers of the 51 accepted were
Distinguished Papers, including this one.},
ucdcite = {a96}
}
@inproceedings{Wang:2016:ACS,
author = {Leyuan Wang and Yangzihao Wang and Carl Yang and
John D. Owens},
title = {A Comparative Study on Exact Triangle Counting
Algorithms on the {GPU}},
booktitle = {Proceedings of the 1st High Performance Graph
Processing Workshop},
year = 2016,
series = {HPGP '16},
month = may,
pages = {1--8},
doi = {10.1145/2915516.2915521},
url = {http://escholarship.org/uc/item/9hf0m6w3},
acmauthorize = {http://dl.acm.org/authorize?N04321},
acceptance = {83\% (5/6)},
ucdcite = {a104}
}
@article{Wang:2016:FPS,
author = {Leyuan Wang and Sean Baxter and John D. Owens},
title = {Fast Parallel Skew and Prefix-Doubling Suffix Array
Construction on the {GPU}},
journal = {Concurrency and Computation: Practice \& Experience},
year = 2016,
month = {25~} # aug,
volume = 28,
number = 12,
pages = {3466--3484},
doi = {10.1002/cpe.3867},
url = {http://escholarship.org/uc/item/8p59h957},
ucdcite = {a107}
}
@inproceedings{Wang:2016:GAH,
author = {Yangzihao Wang and Andrew Davidson and Yuechao Pan
and Yuduo Wu and Andy Riffel and John D. Owens},
title = {{G}unrock: A High-Performance Graph Processing
Library on the {GPU}},
booktitle = {Proceedings of the 21st ACM SIGPLAN Symposium on
Principles and Practice of Parallel Programming},
series = {PPoPP 2016},
year = 2016,
month = mar,
pages = {11:1--11:12},
acceptance = {29 of 151 submissions, 19.2\%. 2 papers of the 29
accepted were Distinguished Papers, including this
one.},
cvnote = {Distinguished Paper.},
doi = {10.1145/2851141.2851145},
acmauthorize = {https://dl.acm.org/doi/10.1145/3108140?cid=81100458295},
url = {http://escholarship.org/uc/item/6xz7z9k0},
code = {https://github.com/gunrock/gunrock},
ucdcite = {a100}
}
@article{Wang:2017:GGG,
author = {Yangzihao Wang and Yuechao Pan and Andrew Davidson
and Yuduo Wu and Carl Yang and Leyuan Wang and
Muhammad Osama and Chenshan Yuan and Weitang Liu and
Andy T. Riffel and John D. Owens},
title = {{G}unrock: {GPU} Graph Analytics},
journal = {ACM Transactions on Parallel Computing},
year = 2017,
volume = 4,
number = 1,
month = aug,
pages = {3:1--3:49},
doi = {10.1145/3108140},
ee = {http://arxiv.org/abs/1701.01170},
acmauthorize = {https://dl.acm.org/doi/10.1145/3108140?cid=81100458295},
url = {http://escholarship.org/uc/item/9gj6r1dj},
code = {https://github.com/gunrock/gunrock},
ucdcite = {a115}
}
@inproceedings{Wang:2017:MAL,
author = {Yangzihao Wang and Sean Baxter and John D. Owens},
title = {Mini-{G}unrock: A Lightweight Graph Analytics
Framework on the {GPU}},
booktitle = {Graph Algorithms Building Blocks},
year = 2017,
series = {GABB 2017},
month = may,
pages = {616--626},
doi = {10.1109/IPDPSW.2017.116},
url = {http://escholarship.org/uc/item/5wm061tr},
code = {https://github.com/gunrock/mini},
ucdcite = {a111}
}
@inproceedings{Wang:2019:ADI,
author = {Xiaoyun Wang and Zhongyi Lin and Carl Yang and John
D. Owens},
title = {Accelerating {DNN} Inference with {GraphBLAS} and
the {GPU}},
booktitle = {Proceedings of the IEEE High Performance Extreme
Computing Conference},
series = {HPEC '19},
year = 2019,
month = sep,
url = {https://escholarship.org/uc/item/1fg335kd},
doi = {10.1109/HPEC.2019.8916498},
cvnote = {2019 GraphChallenge Student Innovation Award.},
ucdcite = {a133}
}
@inproceedings{Wang:2019:FBT,
author = {Leyuan Wang and John D. Owens},
title = {Fast {BFS}-Based Triangle Counting on {GPU}s},
booktitle = {Proceedings of the IEEE High Performance Extreme
Computing Conference},
series = {HPEC '19},
year = 2019,
month = sep,
url = {https://escholarship.org/uc/item/5961r5qs},
doi = {10.1109/HPEC.2019.8916434},
cvnote = {2019 GraphChallenge Finalist.},
ucdcite = {a134}
}
@article{Wang:2020:FGS,
title = {Fast {G}unrock Subgraph Matching ({GSM}) on {GPU}s},
author = {Leyuan Wang and John D. Owens},
journal = {CoRR},
month = mar,
year = 2020,
volume = {abs/2003.01527},
archiveprefix = {arXiv},
number = {2003.01527v1},
eprint = {2003.01527v1},
primaryclass = {cs.DC},
nonrefereed = {true}
}
@inproceedings{Wapman:2023:HCA,
author = {Jonathan D. Wapman and Sean Treichler and Serban D.
Porumbescu and John D. Owens},
title = {Harmonic {CUDA}: Asynchronous Programming on {GPUs}},
booktitle = {Proceedings of the 14th International Workshop on
Programming Models and Applications for Multicores
and Manycores},
year = 2023,
series = {PMAM '23},
month = feb,
pages = {39--49},
doi = {10.1145/3582514.3582517},
url = {https://escholarship.org/uc/item/9539763j}
}
@inproceedings{Weber:2015:PRA,
author = {Thomas Weber and Michael Wimmer and John D. Owens},
title = {Parallel {R}eyes-style Adaptive Subdivision with
Bounded Memory Usage},
booktitle = {Proceedings of the ACM SIGGRAPH Symposium on
Interactive 3D Graphics and Games},
year = 2015,
series = {i3D 2015},
month = feb # {\slash } # mar,
pages = {39--45},
url = {http://escholarship.org/uc/item/8kn7c65q},
acmauthorize = {http://dl.acm.org/authorize?N05610},
doi = {10.1145/2699276.2699289},
code = {https://github.com/ginkgo/micropolis},
acceptance = {38\% (15/39)},
ucdcite = {a94}
}
@inproceedings{Wu:2015:PCO,
author = {Yuduo Wu and Yangzihao Wang and Yuechao Pan and Carl
Yang and John D. Owens},
title = {Performance Characterization of High-Level
Programming Models for {GPU} Graph Analytics},
booktitle = {IEEE International Symposium on Workload
Characterization},
year = 2015,
series = {IISWC-2015},
month = oct,
pages = {66--75},
acceptance = {32.8\% (20/61)},
doi = {10.1109/IISWC.2015.13},
url = {http://escholarship.org/uc/item/2t69m5ht},
cvnote = {Best Paper finalist.},
ucdcite = {a97}
}
@inproceedings{Yang:2015:FSM,
author = {Carl Yang and Yangzihao Wang and John D. Owens},
title = {Fast Sparse Matrix and Sparse Vector Multiplication
Algorithm on the {GPU}},
booktitle = {Graph Algorithms Building Blocks},
year = 2015,
series = {GABB 2015},
month = may,
pages = {841--847},
doi = {10.1109/IPDPSW.2015.77},
url = {http://escholarship.org/uc/item/1rq9t3j3},
ucdcite = {a95}
}
@inproceedings{Yang:2018:DPF,
title = {Design Principles for Sparse Matrix Multiplication
on the {GPU}},
author = {Carl Yang and Ayd{\i}n Bulu\c{c} and John D. Owens},
booktitle = {Euro-Par 2018: Proceedings of the 24th International
European Conference on Parallel and Distributed
Computing},
editor = {Aldinucci, Marco and Padovani, Luca and Torquati,
Massimo},
month = aug,
year = 2018,
pages = {672--687},
url = {https://escholarship.org/uc/item/5h35w3b7},
doi = {10.1007/978-3-319-96983-1_48},
cvnote = {Distinguished Paper and Best Artifact Award.},
code = {https://github.com/owensgroup/merge-spmm},
acceptance = {28.9\% (57/197)},
ucdcite = {a124}
}
@inproceedings{Yang:2018:IPE,
title = {Implementing Push-Pull Efficiently in {GraphBLAS}},
author = {Carl Yang and Ayd{\i}n Bulu\c{c} and John D. Owens},
booktitle = {Proceedings of the International Conference on
Parallel Processing},
series = {ICPP 2018},
month = aug,
year = 2018,
pages = {89:1--89:11},
url = {https://escholarship.org/uc/item/021076bn},
doi = {10.1145/3225058.3225122},
acmauthorize = {https://dl.acm.org/doi/10.1145/3225058.3225122?cid=81100458295},
code = {https://github.com/owensgroup/push-pull},
acceptance = {91/313 (29\%)},
ucdcite = {a125}
}
@article{Yang:2022:GAH,
title = {{GraphBLAST}: A High-Performance Linear
Algebra-based Graph Framework on the {GPU}},
author = {Carl Yang and Ayd{\i}n Bulu\c{c} and John D. Owens},
journal = {ACM Transactions on Mathematical Software},
issue_date = {March 2022},
volume = 48,
number = 1,
month = feb,
articleno = 1,
numpages = 51,
year = 2022,
pages = {1:1--1:51},
note = {Editors' Pick for Notable Papers, ACM TOMS, 2024},
doi = {10.1145/3466795},
url = {https://escholarship.org/uc/item/292901ks},
ucdcite = {a142}
}
@inproceedings{Yih:2018:FVG,
author = {Matthew Yih and Jeffrey M. Ota and John D. Owens and
P{\i}nar Muyan-{\"{O}}z{\c{c}}elik},
title = {{FPGA} versus {GPU} for Speed-Limit-Sign
Recognition},
booktitle = {Proceedings of the 21st IEEE International
Conference on Intelligent Transportation Systems},
series = {ITSC 2018},
month = nov,
year = 2018,
pages = {843--850},
doi = {10.1109/ITSC.2018.8569462},
url = {https://escholarship.org/uc/item/8ww3d2gg},
code = {https://github.com/owensgroup/TrafficSignBench},
ucdcite = {a126}
}
@inproceedings{Zhang:2010:FTS,
author = {Yao Zhang and Jonathan Cohen and John D. Owens},
title = {Fast Tridiagonal Solvers on the {GPU}},
booktitle = {Proceedings of the 15th ACM SIGPLAN Symposium on
Principles and Practice of Parallel Programming},
series = {PPoPP 2010},
year = 2010,
month = jan,
pages = {127--136},
doi = {10.1145/1693453.1693472},
url = {https://escholarship.org/uc/item/7b441610},
acmauthorize = {http://dl.acm.org/authorize?296045},
also = {ACM SIGPLAN Notices - PPoPP '10; Volume 45 Issue 5,
May 2010, Pages: 127--136},
acceptance = {29 of 173 submissions, 16.8\%},
ucdcite = {a50}
}
@incollection{Zhang:2011:AHM,
author = {Yao Zhang and Jonathan Cohen and Andrew A. Davidson
and John D. Owens},
editor = {Wen{-mei} W. Hwu},
booktitle = {GPU Computing Gems},
volume = 2,
title = {A Hybrid Method for Solving Tridiagonal Systems on
the {GPU}},
chapter = 11,
publisher = {Morgan Kaufmann},
month = oct,
year = 2011,
pages = {117--132},
acceptance = {There were a total of 272 submissions and will be
publishing 98 over the two volumes.},
doi = {10.1016/B978-0-12-385963-1.00011-3},
url = {http://www.idav.ucdavis.edu/publications/print_pub?pub_id=1075},
ucdcite = {a71}
}
@inproceedings{Zhang:2011:APE,
author = {Yao Zhang and John Ludd Recker and Robert Ulichney
and Giordano B. Beretta and Ingeborg Tastl and
I-Jong Lin and John D. Owens},
title = {A Parallel Error Diffusion Implementation on a
{GPU}},
booktitle = {Proceedings of SPIE: IS\&T/SPIE Electronic Imaging
2011 / Parallel Processing for Imaging Applications},
year = 2011,
volume = 7872,
month = jan,
pages = {78720K:1--9},
url = {https://escholarship.org/uc/item/7b78v752},
doi = {10.1117/12.872616},
ucdcite = {a58}
}
@inproceedings{Zhang:2011:AQP,
author = {Yao Zhang and John D. Owens},
title = {A Quantitative Performance Analysis Model for {GPU}
Architectures},
booktitle = {Proceedings of the 17th IEEE International Symposium
on High-Performance Computer Architecture},
series = {HPCA-17},
year = 2011,
month = feb,
pages = {382--393},
doi = {10.1109/HPCA.2011.5749745},
acceptance = {42 accepted out of 227, 18.5\%},
url = {https://escholarship.org/uc/item/8gp0x7tc},
ucdcite = {a61}
}
@inproceedings{Zhang:2012:PDE,
author = {Yao Zhang and John Ludd Recker and Robert Ulichney
and Ingeborg Tastl and John D. Owens},
title = {Plane-dependent Error Diffusion on a {GPU}},
booktitle = {Proceedings of SPIE: IS\&T/SPIE Electronic Imaging
2012 / Parallel Processing for Imaging Applications
II},
volume = {8295B},
pages = {8295B-59:1--10},
year = 2012,
month = jan,
url = {http://www.idav.ucdavis.edu/publications/print_pub?pub_id=1080},
doi = {10.1117/12.906966},
ucdcite = {a77}
}
This file was generated by bibtex2html 1.99.