|
CUDPP
2.2
CUDA Data-Parallel Primitives Library
|
|
CUDPP
2.2
CUDA Data-Parallel Primitives Library
|
@incollection{Allusse:2008:GAG,
author = {Yannick Allusse and Patrick Horain and Ankit Agarwal
and Cindula Saipriyadarshan},
title = {{GpuCV}: A {GPU}-Accelerated Framework for Image
Processing and Computer Vision},
booktitle = {Advances in Visual Computing},
series = {Lecture Notes in Computer Science},
publisher = {Springer},
volume = 5359,
year = 2008,
month = dec,
pages = {430--439},
doi = {10.1007/978-3-540-89646-3}
}
@incollection{Aubert:2009:API,
author = {Dominique Aubert and Mehdi Amini and Romaric David},
title = {A Particle-Mesh Integrator for Galactic Dynamics
Powered by {GPGPU}s},
booktitle = {Proceedings of the 9th International Conference on
Computational Science},
series = {Lecture Notes in Computer Science},
publisher = {Springer},
volume = 5544,
year = 2008,
month = may,
pages = {874--883},
doi = {10.1007/978-3-642-01970-8_88}
}
@inproceedings{Bailer:2010:TAC,
author = {Bailer, W. and Fassold, H. and Lee, F. and Rosner,
J.},
booktitle = {2010 Conference on Visual Media Production (CVMP)},
title = {Tracking and Clustering Salient Features in Image
Sequences},
year = 2010,
pages = {17--24},
keywords = {computer graphic equipment;coprocessors;data
visualisation;image sequences;object
tracking;pattern clustering;GPU accelerated
approach;audio rendering;computer generated
objects;image sequences;media production;object
trajectories visualization;salient features
clustering;Clustering algorithms;Feature
extraction;Graphics processing unit;Hidden Markov
models;Image
sequences;Tracking;Trajectory;GPU;clustering;motion
segmentation;tracking},
doi = {10.1109/CVMP.2010.10}
}
@inproceedings{Bartocci:2014:TAG,
title = {Towards a {GPGPU}-Parallel {SPIN} model checker},
author = {Bartocci, Ezio and DeFrancisco, Richard and Smolka,
Scott A.},
booktitle = {Proceedings of the 2014 International SPIN Symposium
on Model Checking of Software},
pages = {87--96},
year = 2014,
month = jul,
organization = {ACM}
}
@inproceedings{Billeter:2009:ESC,
author = {Markus Billeter and Ola Olsson and Ulf Assarsson},
title = {Efficient Stream Compaction on Wide {SIMD} Many-Core
Architectures},
booktitle = {Proceedings of High Performance Graphics 2009},
year = 2009,
month = aug,
pages = {159--166},
doi = {10.1145/1572769.1572795}
}
@inproceedings{Bosnacki:2010:GAE,
author = {Bo{\v{s}}na{\v{c}}ki, Dragan and Edelkamp, Stefan
and Sulewski, Damien and Wijs, Anton},
booktitle = {2010 Ninth International Workshop on Parallel and
Distributed Methods in Verification/ and Second
International Workshop on High Performance
Computational Systems Biology},
title = {{GPU-PRISM}: An extension of {PRISM} for General
Purpose Graphics Processing Units},
year = 2010,
pages = {17--19},
month = sep,
keywords = {computer graphic equipment;coprocessors;formal
verification;matrix multiplication;parallel
algorithms;parallel architectures;CUDA
architecture;GPU-PRISM;PRISM model
checker;coprocessor;general purpose graphics
processing units;linear algebraic operation;linear
equation;matrix vector multiplication;parallel
algorithm;probabilistic model checking;runtime
improvement;GPU;model checker PRISM;parallel
algorithms;probabilistic model checking},
doi = {10.1109/PDMC-HiBi.2010.11}
}
@inproceedings{Cabido:2010:DEF,
title = {Differential Evolution for Global Optimization on
{GPU}},
author = {Cabido, R. and Duarte, A. and Montemayor, A. S. and
Pantrigo, J. J.},
booktitle = {International Conference on Metaheuritic and Nature
Inspired Computing},
year = 2010
}
@article{Chang:2012:SDP,
year = 2012,
issn = {1387-3326},
journal = {Information Systems Frontiers},
volume = 14,
number = 4,
doi = {10.1007/s10796-011-9322-0},
title = {Scaling database performance on {GPU}s},
publisher = {Springer US},
keywords = {GPU; CUDA; SQLite; In-Memory Database},
author = {Chang, Yue-Shan and Sheu, Ruey-Kai and Yuan,
Shyan-Ming and Hsu, Jyn-Jie},
pages = {909--924},
language = {English}
}
@article{Chen:2014:GPA,
year = 2014,
issn = {0178-2789},
journal = {The Visual Computer},
doi = {10.1007/s00371-014-0924-7},
title = {{GPU}-based polygonization and optimization for
implicit surfaces},
publisher = {Springer Berlin Heidelberg},
keywords = {Implicit surface; Polygonization; Mesh optimization;
GPU parallelization},
author = {Chen, Junjie and Jin, Xiaogang and Deng, Zhigang},
pages = {1--12},
month = mar,
language = {English}
}
@inproceedings{Chiu:2011:DTU,
author = {Chiu, Chun-Chieh and Luo, Guo-Heng and Yuan,
Shyan-Ming},
title = {A decision tree using {CUDA} {GPU}s},
booktitle = {Proceedings of the 13th International Conference on
Information Integration and Web-based Applications
and Services},
series = {iiWAS '11},
year = 2011,
isbn = {978-1-4503-0784-0},
location = {Ho Chi Minh City, Vietnam},
pages = {399--402},
numpages = 4,
doi = {10.1145/2095536.2095615},
acmid = 2095615,
publisher = {ACM},
address = {New York, NY, USA},
keywords = {CUDA, GPGPU, classification, data mining, decision
tree}
}
@inproceedings{Chong:2008:DLV,
author = {Jike Chong and Youngmin Yi and Arlo Faria and
Nadathur Satish and Kurt Keutzer},
title = {Data-Parallel Large Vocabulary Continuous Speech
Recognition on Graphics Processors},
booktitle = {Proceedings of the 1st Annual Workshop on Emerging
Applications and Many Core Architecture (EAMA)},
pages = {23--35},
month = jun,
year = 2008,
url = {http://www.gigascale.org/pubs/1499.html}
}
@article{DAgostino:2014:API,
title = {A parallel isosurface extraction component for
visualization pipelines executing on {GPU} clusters},
author = {D'Agostino, Daniele and Seinstra, Frank J},
journal = {Journal of Computational and Applied Mathematics},
pages = {383--393},
year = 2015,
month = jan,
volume = 273,
publisher = {Elsevier},
doi = {10.1016/j.cam.2014.05.019}
}
@inproceedings{Dai:2013:ISS,
author = {Dai, Qing and Yang, Xubo},
title = {Interactive Smoke Simulation and Rendering on the
{GPU}},
booktitle = {Proceedings of the 12th ACM SIGGRAPH International
Conference on Virtual-Reality Continuum and Its
Applications in Industry},
series = {VRCAI '13},
year = 2013,
month = nov,
isbn = {978-1-4503-2590-5},
location = {Hong Kong, Hong Kong},
pages = {177--182},
numpages = 6,
doi = {10.1145/2534329.2534358},
acmid = 2534358,
publisher = {ACM},
address = {New York, NY, USA},
keywords = {GPU computing, fluid simulation, multigrid,
real-time}
}
@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 (InPar
'\textln{12})},
year = 2012,
month = may,
url = {http://www.idav.ucdavis.edu/publications/print_pub?pub_id=1085},
doi = {10.1109/InPar.2012.6339592},
acceptance = {25/62 (40.3\%)}
}
@inproceedings{Dias:2013:TMS,
title = {Triangulating molecular surfaces on multiple {GPU}s},
author = {Dias, S{\'e}rgio and Gomes, Abel},
booktitle = {Proceedings of the 20th European MPI Users' Group
Meeting},
pages = {181--186},
year = 2013,
month = sep,
doi = {10.1145/2488551.2488582},
organization = {ACM}
}
@mastersthesis{Dukehart:2009:GRW,
author = {Sean Peter Dukehart},
title = {{GPU} Random Walkers for Iterative Image
Segmentation},
school = {Department of Computer Science, University of
Maryland Baltimore County},
year = 2009,
month = feb
}
@inproceedings{Eisenacher:2009:RTV,
author = {Christian Eisenacher and Quirin Meyer and Charles
Loop},
title = {Real-Time View-Dependent Rendering of Parametric
Surfaces},
booktitle = {I3D '09: Proceedings of the 2009 Symposium on
Interactive 3D Graphics and Games},
month = feb # {\slash } # mar,
year = 2009,
pages = {137--143},
doi = {10.1145/1507149.1507172}
}
@article{Fabijanska:2014:NAG,
title = {New accelerated graph-based method of image
segmentation applying minimum spanning tree},
author = {Fabija{\'n}ska, Anna and Goc{\l}awski, Jaros{\l}aw},
year = 2014,
journal = {IET Image Processing},
volume = 8,
number = 4,
month = apr,
publisher = {IET},
doi = {10.1049/iet-ipr.2013.0104}
}
@incollection{Feng:2011:TDM,
author = {Wu{-chun} Feng and Yong Cao and Debprakash Patnaik
and Naren Ramakrishnan},
editor = {Wen{-mei} W. Hwu},
booktitle = {GPU Computing Gems},
volume = 1,
title = {Temporal Data Mining for Neuroscience},
chapter = 15,
publisher = {Morgan Kaufmann},
month = feb,
year = 2011,
pages = {211--227},
doi = {10.1016/B978-0-12-384988-5.00015-2}
}
@article{Gao:2013:GAG,
title = {{gHull}: A {GPU} algorithm for 3{D} convex hull},
author = {Gao, Mingcen and Cao, Thanh-Tung and Nanjappa,
Ashwin and Tan, Tiow-Seng and Huang, Zhiyong},
journal = {ACM Transactions on Mathematical Software (TOMS)},
volume = 40,
number = 1,
pages = 3,
month = sep,
year = 2013,
doi = {10.1145/2513109.2513112},
publisher = {ACM}
}
@article{Garanzha:2010:FRS,
author = {Garanzha, Kirill and Loop, Charles},
title = {Fast Ray Sorting and Breadth-First Packet Traversal
for {GPU} Ray Tracing},
journal = {Computer Graphics Forum},
year = 2010,
month = may,
volume = 29,
issue = 2,
pages = {289--298},
issn = {1467-8659},
doi = {10.1111/j.1467-8659.2009.01598.x},
publisher = {Blackwell Publishing Ltd}
}
@inproceedings{Glenis:2014:PAE,
title = {Performance and energy characterization of
high-performance low-cost cornerness detection on
{GPU}s and multicores},
author = {Glenis, Apostolos and Petridis, Sergios},
booktitle = {International Conference on Information,
Intelligence, Systems and Applications},
series = {IISA 2014},
pages = {181--186},
year = 2014,
month = jul,
organization = {IEEE},
doi = {10.1109/IISA.2014.6878727}
}
@article{Goclawski:2012:AGA,
title = {A Graph-Based Approach to the Segmentation of Images
with Mould Filled Foam Matrices},
author = {Goc{\l}awski, Jaros{\l}aw and Sekulska-Nalewajko,
Joanna},
journal = {Image Processing \& Communications},
volume = 17,
number = 4,
pages = {59--70},
year = 2012
}
@incollection{Godiyal:2009:RMG,
author = {Apeksha Godiyal and Jared Hoberock and Michael
Garland and John C. Hart},
title = {Rapid Multipole Graph Drawing on the {GPU}},
booktitle = {Proceedings of the 16th International Symposium on
Graph Drawing},
series = {Lecture Notes in Computer Science},
publisher = {Springer},
volume = 5417,
pages = {90--101},
month = sep,
year = 2009,
doi = {10.1007/978-3-642-00219-9}
}
@incollection{Guo:2010:AIP,
year = 2010,
isbn = {978-3-642-13135-6},
booktitle = {Algorithms and Architectures for Parallel
Processing},
volume = 6082,
series = {Lecture Notes in Computer Science},
editor = {Hsu, Ching-Hsien and Yang, Laurence T. and Park,
JongHyuk and Yeo, Sang-Soo},
doi = {10.1007/978-3-642-13136-3_30},
title = {An Improved Parallel {MEMS} Processing-Level
Simulation Implementation Using Graphic Processing
Unit},
publisher = {Springer Berlin Heidelberg},
keywords = {MEMS; Processing-level Simulation; Parallel; GPU;
CUDA},
author = {Guo, Yupeng and Liu, Xiaoguang and Wang, Gang and
Zhang, Fan and Zhao, Xin},
pages = {289--296}
}
@article{Ha:2009:FFP,
author = {Ha, Linh and Kr{\"{u}}ger, Jens and Silva,
Cl{\'{a}}udio T.},
title = {Fast Four-Way Parallel Radix Sorting on {GPU}s},
journal = {Computer Graphics Forum},
volume = 28,
number = 8,
publisher = {Blackwell Publishing Ltd},
issn = {1467-8659},
url = {http://dx.doi.org/10.1111/j.1467-8659.2009.01542.x},
doi = {10.1111/j.1467-8659.2009.01542.x},
pages = {2368--2378},
keywords = {HPC, GPGPU, GPU sorting, collision detection,
parallel sorting},
keywords = {I.3.1: Parallel processing on Graphic Processing
Units, G.1.0: Parallel algorithms},
year = 2009
}
@incollection{Harish:2011:FMS,
title = {Fast Minimum Spanning Tree Computation},
editor = {Wen-{m}ei W. Hwu},
booktitle = {GPU Computing Gems Jade Edition},
publisher = {Morgan Kaufmann},
address = {Boston},
year = 2012,
pages = {77--88},
isbn = {978-0-12-385963-1},
doi = {http://dx.doi.org/10.1016/B978-0-12-385963-1.00007-1},
author = {Pawan Harish and P. J. Narayanan and Vibhav Vineet
and Suryakant Patidar}
}
@article{HidalgoPaniagua:2013:ACS,
author = {Hidalgo-Paniagua, Alejandro and Vega-Rodríguez,
Miguel A. and Pav{\'o}n, Nieves and Ferruz, Joaquín},
title = {A comparative study of parallel software {SURF}
implementations},
journal = {Concurrency and Computation: Practice and
Experience},
issn = {1532-0634},
doi = {10.1002/cpe.3163},
keywords = {parallel implementations, SURF, comparative study,
CUDA, OpenCL, OpenMP, OpenCV},
year = 2013,
month = oct
}
@inproceedings{Hoberock:2009:SCF,
author = {Jared Hoberock and Victor Lu and Yuntao Jia and John
C. Hart},
title = {Stream Compaction for Deferred Shading},
booktitle = {Proceedings of High Performance Graphics 2009},
year = 2009,
month = aug,
pages = {173--180},
doi = {10.1145/1572769.1572797}
}
@article{Hou:2008:BBG,
title = {{BSGP}: Bulk-Synchronous {GPU} Programming},
author = {Qiming Hou and Kun Zhou and Baining Guo},
journal = {ACM Transactions on Graphics},
volume = 27,
number = 3,
month = aug,
year = 2008,
pages = {19:1--19:13}
}
@inproceedings{Huang:2009:AEO,
author = {Huang, B. and Jinlan Gao and Xiaoming Li},
booktitle = {2009 IEEE International Symposium on Parallel and
Distributed Processing with Applications},
title = {An Empirically Optimized Radix Sort for {GPU}},
year = 2009,
pages = {234--241},
keywords = {computer graphic equipment;computer
graphics;optimisation;sorting;GPU architectural
factors;GPU sort routines;NVIDIA GPU;algorithmic
parameters;empirical optimization
technique;empirically optimized radix sort;radix
sort implementations;sorting routines;Application
software;Central Processing Unit;Concurrent
computing;Distributed
processing;Frequency;Graphics;High performance
computing;Programming
profession;Sorting;Tuning;GPU;performance
tuning;radix sort},
doi = {10.1109/ISPA.2009.89}
}
@inproceedings{Ihm:2013:OTE,
title = {On the Efficient Implementation of a Real-time
{K}d-tree Construction Algorithm},
author = {Byungjoon Chang and Woong Seo and Insung Ihm},
booktitle = {Symposium on GPU Computing and Applications},
year = 2013,
month = oct,
url = {http://grmanet.sogang.ac.kr/ihm/webpapers/1309FastKdTreeConst.pdf}
}
@article{Kouassi:2011:EPL,
title = {Efficient Probabilistic Latent Semantic Indexing
using Graphics Processing Unit},
journal = {Procedia Computer Science},
volume = 4,
number = 0,
pages = {382--391},
year = 2011,
note = {Proceedings of the International Conference on
Computational Science},
issn = {1877-0509},
doi = {10.1016/j.procs.2011.04.040},
author = {Eli Koffi Kouassi and Toshiyuki Amagasa and Hiroyuki
Kitagawa},
keywords = {Graphic Processing Unit (GPGPU)},
keywords = {Clustering},
keywords = {Algorithms},
keywords = {Probabilistic Latent Semantic Indexint (PLSI)},
keywords = {Expectation Maximization (EM) Algorithm }
}
@inproceedings{Ladikos:2008:EVH,
title = {Efficient Visual Hull Computation for Real-Time 3{D}
Reconstruction using {CUDA}},
author = {Alexander Ladikos and Selim Benhimane and Nassir
Navab},
booktitle = {CVPRW '08: Computer Vision and Pattern Recognition
Workshops},
year = 2008,
month = jun,
pages = {1--8},
doi = {10.1109/CVPRW.2008.4563098}
}
@article{Li:2013:FTQ,
title = {Fast {T}-overlap query algorithms using graphics
processor units and its applications in web data
query},
author = {Li, Mengjuan and Jia, Lianyin and You, Jinguo and
Xi, Jianqing and Qin, HaiFei and Zeng, Rui},
journal = {World Wide Web},
pages = {1--17},
year = 2013,
month = jun,
publisher = {Springer},
doi = {10.1007/s11280-013-0232-6}
}
@inproceedings{Lin:2011:TDA,
author = {Chia-Feng Lin and Shyan-Ming Yuan},
booktitle = {2011 Fifth International Conference on Genetic and
Evolutionary Computing (ICGEC)},
title = {The Design and Evaluation of GPU Based Memory
Database},
year = 2011,
pages = {224-231},
keywords = {SQL;computer graphic equipment;coprocessors;storage
management;C language;CUDA;GPU based memory
database;NVIDIA;SQLite;graphics processing
unit;memory capacity;parallel computing
language;rational database;Algorithm design and
analysis;Arrays;Databases;Graphics processing
unit;Instruction
sets;Libraries;Sorting;Database;GPU;memory},
doi = {10.1109/ICGEC.2011.61}
}
@inproceedings{Lipscomb:2012:PVN,
author = {Lipscomb, Tyson J. and Zou, Anqi and Cho, Samuel S.},
title = {Parallel {V}erlet Neighbor List Algorithm for
{GPU}-Optimized {MD} Simulations},
booktitle = {Proceedings of the ACM Conference on Bioinformatics,
Computational Biology and Biomedicine},
series = {BCB '12},
year = 2012,
isbn = {978-1-4503-1670-5},
location = {Orlando, Florida},
pages = {321--328},
numpages = 8,
doi = {10.1145/2382936.2382977},
acmid = 2382977,
publisher = {ACM},
address = {New York, NY, USA},
keywords = {CUDPP, CURAND, coarse-grained MD simulations, energy
drift, floating point analysis}
}
@article{Lo:2014:CAC,
title = {{CUDT}: A {CUDA} Based Decision Tree Algorithm},
author = {Lo, Win-Tsung and Chang, Yue-Shan and Sheu, Ruey-Kai
and Chiu, Chun-Chieh and Yuan, Shyan-Ming},
journal = {The Scientific World Journal},
year = 2014,
month = jul,
publisher = {Hindawi Publishing Corporation},
doi = {10.1155/2014/745640}
}
@article{Matic:2014:CGA,
title = {{CPU}, {GPU} and {FPGA} Implementations of {MALD}:
Ceramic Tile Surface Defects Detection Algorithm},
author = {Mati{\'c}, Tomislav and Aleksi, Ivan and Hocenski,
{\v{Z}}eljko},
journal = {AUTOMATIKA: {\v{c}}asopis za automatiku, mjerenje,
elektroniku, ra{\v{c}}unarstvo i komunikacije},
volume = 55,
number = 1,
pages = {9--21},
year = 2014,
month = jan,
publisher = {KoREMA-Hrvatsko dru{\v{s}}tvo za komunikacije,
ra{\v{c}}unarstvo, elektroniku, mjerenja i
automatiku}
}
@inproceedings{Oikonomidis:2011:EM3,
title = {Efficient Model-based 3{D} Tracking of Hand
Articulations using {K}inect},
author = {Iason Oikonomidis and Nikolaos Kyriazis and Antonis
Argyros},
year = 2011,
pages = {101.1--101.11},
booktitle = {Proceedings of the British Machine Vision
Conference},
publisher = {BMVA Press},
editors = {Hoey, Jesse and McKenna, Stephen and Trucco,
Emanuele},
isbn = {1-901725-43-X},
doi = {10.5244/C.25.101},
month = sep
}
@incollection{Parveen:2013:VOS,
title = {Visualization of Small World Networks Using
Similarity Matrices},
author = {Parveen, Saima and Sreevalsan-Nair, Jaya},
booktitle = {Big Data Analytics},
pages = {151--170},
year = 2013,
month = dec,
publisher = {Springer},
doi = {10.1007/978-3-319-03689-2_10}
}
@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 (InPar
'\textln{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\%)}
}
@article{Patil:2013:AGF,
title = {A {GPU}-Accelerated Framework for Image Processing
and Computer Vision},
author = {Patil, Ashwini A and Shahapure, Pankaja A},
year = 2013,
journal = {International Journal of Latest Trends in
Engineering and Technology},
pages = {115--120}
}
@inproceedings{Patnaik:2009:AAT,
author = {Patnaik, D. and Ponce, S. P. and Yong Cao and
Ramakrishnan, N.},
booktitle = {Sixth IFIP International Conference on Network and
Parallel Computing (NPC '09)},
title = {Accelerator-Oriented Algorithm Transformation for
Temporal Data Mining},
year = 2009,
pages = {93--100},
month = oct,
keywords = {data analysis;data mining;temporal databases;GPU
architectures;Nvidias GTX 280;accelerator-oriented
algorithm transformation;computational
neuroscience;episode discovery
algorithm;multineuronal datasets;port existing
algorithms;spike train data analysis;temporal data
mining;Acceleration;Algorithm design and
analysis;Application software;Central Processing
Unit;Computer architecture;Concurrent computing;Data
mining;Neurons;Neuroscience;Parallel
processing;Frequent episodes;GPGPU;Spike train
analysis;Temporal data mining},
doi = {10.1109/NPC.2009.26}
}
@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,
url = {http://graphics.idav.ucdavis.edu/publications/print_pub?pub_id=952},
doi = {10.1145/1409060.1409096},
pages = {143:1--143:8}
}
@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 2009},
year = 2009,
month = aug,
pages = {99--108},
url = {http://graphics.idav.ucdavis.edu/publications/print_pub?pub_id=964},
doi = {10.1145/1572769.1572785}
}
@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}
}
@inproceedings{Peters:2009:FCI,
author = {Hagen Peters and Ole Schulz-Hildebrandt and Norbert
Luttenberger},
title = {Fast comparison-based in-place sorting with {CUDA}},
booktitle = {Eighth International Conference on Parallel
Processing and Applied Mathematics},
year = 2009,
month = sep
}
@mastersthesis{Ponce:2009:TAT,
author = {Sean P. Ponce},
title = {Towards Algorithm Transformation for Temporal Data
Mining on {GPU}},
school = {Department of Computer Science, Virginia Polytechnic
Institute and State University},
year = 2009,
month = {7~} # jul
}
@inproceedings{Qiu:2009:GNN,
author = {Deyuan Qiu and Stefan May and Andreas N{\"{u}}chter},
title = {{GPU}-accelerated Nearest Neighbor Search for 3{D}
Registration},
booktitle = {ICVS \textln{2009}: Proceedings of the 7th
International Conference on Computer Vision Systems},
year = 2009,
month = oct
}
@article{Riise:2014:OPL,
title = {On parallel local search for permutations},
author = {Riise, Atle and Burke, Edmund K},
journal = {Journal of the Operational Research Society},
year = 2014,
publisher = {Palgrave Macmillan},
doi = {10.1057/jors.2014.29}
}
@incollection{Saetra:2013:SWS,
year = 2013,
isbn = {978-3-642-33133-6},
booktitle = {Numerical Mathematics and Advanced Applications
2011},
editor = {Cangiani, Andrea and Davidchack, Ruslan L. and
Georgoulis, Emmanuil and Gorban, Alexander N. and
Levesley, Jeremy and Tretyakov, Michael V.},
doi = {10.1007/978-3-642-33134-3_71},
title = {Shallow Water Simulation on {GPU}s for Sparse
Domains},
publisher = {Springer Berlin Heidelberg},
author = {S{\ae}tra, M. L.},
pages = {673--680}
}
@inproceedings{Satish:2009:DES,
author = {Nadathur Satish and Mark Harris and Michael Garland},
title = {Designing Efficient Sorting Algorithms for Manycore
{GPU}s},
booktitle = {Proceedings of the \textln{23}rd IEEE International
Parallel and Distributed Processing Symposium},
month = may,
year = 2009
}
@inproceedings{Sengupta:2007:SPF,
title = {Scan Primitives for {GPU} Computing},
author = {Shubhabrata Sengupta and Mark Harris and Yao Zhang
and John D. Owens},
booktitle = {Graphics Hardware \textln{2007}},
year = 2007,
month = aug,
pages = {97--106},
url = {http://graphics.idav.ucdavis.edu/publications/print_pub?pub_id=915}
}
@techreport{Sengupta:2008:SPF,
title = {Efficient Parallel Scan Algorithms for {GPUs}},
author = {Shubhabrata Sengupta and Mark Harris and Michael
Garland},
number = {NVR-2008-003},
institution = {NVIDIA Corporation},
year = 2008,
month = dec,
url = {http://mgarland.org/papers.html#segscan-tr}
}
@article{Sibai:2014:PEA,
title = {Performance evaluation and comparison of parallel
conjugate gradient on modern multi-core accelerator
and massively parallel systems},
author = {Sibai, Fadi N and El-Moursy, Ali},
journal = {International Journal of Parallel, Emergent and
Distributed Systems},
volume = 29,
number = 1,
month = jan,
pages = {38--67},
year = 2014,
publisher = {Taylor \& Francis},
doi = {10.1080/17445760.2012.762774}
}
@article{Stantchev:2008:FPP,
author = {George Stantchev and William Dorland and Nail
Gumerov},
title = {Fast parallel Particle-To-Grid interpolation for
plasma {PIC} simulations on the {GPU}},
journal = {Journal of Parallel and Distributed Computing},
volume = 68,
number = 10,
pages = {1339--1349},
year = 2008,
month = oct,
doi = {10.1016/j.jpdc.2008.05.009},
url = {http://www.sciencedirect.com/science/article/B6WKJ-4SW144M-1/2/914e9b94290a555f36b8238a9781aa1d}
}
@article{Stein:2012:CFP,
title = {{CudaHull}: Fast parallel 3{D} convex hull on the
{GPU} },
journal = {Computers \& Graphics},
volume = 36,
number = 4,
pages = {265--271},
year = 2012,
month = mar,
note = {Applications of Geometry Processing},
issn = {0097-8493},
doi = {10.1016/j.cag.2012.02.012},
author = {Ayal Stein and Eran Geva and Jihad El-Sana},
keywords = {Convex hull},
keywords = {Parallel processing},
keywords = {GPU processing},
keywords = {CUDA programming }
}
@inproceedings{Sun:2010:FSE,
author = {Weidong Sun and Weiwei Wang and Zongmin Ma},
booktitle = {2010 3rd International Conference on Biomedical
Engineering and Informatics (BMEI)},
title = {Fast Short Exact Repeats Finding on {GPU}},
year = 2010,
month = oct,
volume = 5,
pages = {2197--2200},
keywords = {DNA;biology computing;computer architecture;computer
graphics;genomics;proteomics;CUDA
platform;DNA;GPU;NVIDIA Corporation;compute unified
device architecture;exact repeats finding;fast short
exact repeats;genome sequencing;graphic processing
unit;proteome sequence analysis;scalable parallel
algorithm;text processing task;vital biological
functions;Algorithm design and
analysis;Arrays;Bioinformatics;DNA;Genomics;Graphics
processing unit;Instruction sets;CUDA;Regulator
Detect;Repeats Finding},
doi = {10.1109/BMEI.2010.5639638}
}
@inproceedings{Thall:2011:FMP,
author = {Thall, Andrew},
title = {Fast Mersenne Prime Testing on the GPU},
booktitle = {Proceedings of the Fourth Workshop on General
Purpose Processing on Graphics Processing Units},
series = {GPGPU-4},
year = 2011,
month = mar,
isbn = {978-1-4503-0569-3},
location = {Newport Beach, California},
pages = {6:1--6:8},
articleno = 6,
numpages = 8,
doi = {10.1145/1964179.1964188},
acmid = 1964188,
publisher = {ACM},
address = {New York, NY, USA},
keywords = {CUDA, GPGPU, IBDWT, Lucas-Lehmer test, Mersenne
primes, discrete weighted transforms, fast carry
propagation, multiprecision arithmetic, parallel
carry-save arithmetic}
}
@inproceedings{Vineet:2009:FMS,
author = {Vibhav Vineet and Pawan Harish and Suryakant Patidar
and P. J. Narayanan},
title = {Fast Minimum Spanning Tree for Large Graphs on the
{GPU}},
booktitle = {Proceedings of High Performance Graphics 2009},
year = 2009,
month = aug,
pages = {167--171},
doi = {10.1145/1572769.1572796}
}
@incollection{Wang:2012:GAO,
year = 2012,
isbn = {978-3-642-31964-8},
booktitle = {Communications and Information Processing},
volume = 288,
series = {Communications in Computer and Information Science},
editor = {Zhao, Maotai and Sha, Junpin},
doi = {10.1007/978-3-642-31965-5_28},
title = {{GPU}-Based Aggregation of On-Line Analytical
Processing},
publisher = {Springer Berlin Heidelberg},
keywords = {Real-time Aggregation; OLAP; CUDA; GPUOLAP},
author = {Wang, Guilan and Zhou, Guoliang},
pages = {234--245}
}
@inproceedings{Wang:2013:AIC,
title = {Accelerating In-memory Cross Match of Astronomical
Catalogs},
author = {Wang, Senhong and Zhao, Yan and Luo, Qiong and Wu,
Chao and Xv, Yang},
booktitle = {IEEE 9th International Conference on eScience},
year = 2013,
month = oct,
pages = {326--333},
organization = {IEEE},
doi = {10.1109/eScience.2013.9}
}
@article{Wong:2014:AAO,
title = {An adaptive octree grid for {GPU}-based collision
detection of deformable objects},
author = {Wong, Tsz Ho and Leach, Geoff and Zambetta, Fabio},
journal = {The Visual Computer},
volume = 30,
number = {6--8},
pages = {729--738},
year = 2014,
month = may,
publisher = {Springer},
doi = {10.1007/s00371-014-0954-1}
}
@article{Yang:2013:EDM,
author = {Xin Yang and Duan-qing Xu and Lei Zhao},
title = {Efficient data management for incoherent ray
tracing},
journal = {Applied Soft Computing},
volume = 13,
number = 1,
pages = {1--8},
year = 2013,
month = jan,
issn = {1568-4946},
doi = {10.1016/j.asoc.2012.07.002}
}
@incollection{Zeng:2012:AMK,
year = 2012,
isbn = {978-3-642-34262-2},
booktitle = {Computational Visual Media},
volume = 7633,
series = {Lecture Notes in Computer Science},
editor = {Hu, Shi-Min and Martin, Ralph R.},
doi = {10.1007/978-3-642-34263-9_30},
title = {A Memory-Efficient {KinectFusion} Using Octree},
publisher = {Springer Berlin Heidelberg},
keywords = {Octree; GPU; KinectFusion; 3D Reconstruction},
author = {Zeng, Ming and Zhao, Fukai and Zheng, Jiaxiang and
Liu, Xinguo},
pages = {234--241}
}
@inproceedings{Zhao:2013:FPI,
title = {Fast parallel interpolation algorithm using {CUDA}},
author = {Zhao, Yanwei and Qiu, Qiang and Fang, Jinyun and Li,
Liang},
booktitle = {IEEE International Geoscience and Remote Sensing
Symposium},
series = {IGARSS 2013},
pages = {3662--3665},
year = 2013,
month = jul,
organization = {IEEE},
doi = {10.1109/IGARSS.2013.6723624}
}
@inproceedings{Zhao:2013:PAS,
title = {Parallelizing Astronomical Source Extraction on the
{GPU}},
author = {Zhao, Baoxue and Luo, Qiong and Wu, Chao},
booktitle = {IEEE 9th International Conference on eScience},
pages = {88--97},
year = 2013,
month = oct,
organization = {IEEE},
doi = {10.1109/eScience.2013.10}
}
@techreport{Zhou:2008:HPS,
author = {Kun Zhou and Minmin Gong and Xin Huang and Baining
Guo},
title = {Highly Parallel Surface Reconstruction},
institution = {Microsoft Research},
year = 2008,
number = {MSR-TR-2008-53},
month = {1~} # apr
}
@article{Zhou:2008:RKC,
title = {Real-time {KD}-tree Construction on Graphics
Hardware},
author = {Kun Zhou and Qiming Hou and Rui Wang and Baining
Guo},
journal = {ACM Transactions on Graphics},
volume = 27,
number = 5,
month = dec,
year = 2008,
pages = {126:1--126:11}
}
@article{Zhou:2012:GPC,
year = 2012,
issn = {2095-2732},
journal = {Frontiers of Electrical and Electronic Engineering},
volume = 7,
number = 1,
doi = {10.1007/s11460-012-0187-x},
title = {{GPU} parallel computing: Programming language,
debugging tools and data structures},
publisher = {SP Higher Education Press},
keywords = {graphics processing unit (GPU); parallel computing;
programming languages; debugging tools; data
structures},
author = {Zhou, Kun},
pages = {5--15},
language = {English}
}
@article{Zhu:2013:EPO,
title = {Efficient polygonization of tree trunks modeled by
convolution surfaces},
author = {Zhu, XiaoQiang and Guo, XueKun and Jin, XiaoGang},
journal = {Science China Information Sciences},
volume = 56,
number = 3,
pages = {1--12},
year = 2013,
month = mar,
publisher = {Springer},
doi = {10.1007/s11432-013-4790-0}
}
@article{souto2013performance,
title = {Performance Evaluation of Quicksort with {GPU}
Dynamic Parallelism for Gene-Expression Quantile
Normalization},
author = {Souto, Roberto Pinto and Osthoff, Carla and Augusto,
Douglas and Trelles, Oswaldo and others},
journal = {Journal of Communication and Computer},
volume = 10,
number = 12,
pages = {1522--1528},
year = 2013,
month = dec
}
1.8.6