%% This BibTeX bibliography file was created using BibDesk. %% http://bibdesk.sourceforge.net/ %% Created for RandiR at 2012-05-16 11:10:08 +0200 %% Saved with string encoding Unicode (UTF-8) @webpage{spherpack_www, Date-Added = {2012-05-14 15:17:17 +0200}, Date-Modified = {2012-05-14 15:26:31 +0200}, Title = {{\sc spherpack}}, Url = {http://www.cisl.ucar.edu/css/software/spherepack/}, Bdsk-Url-1 = {http://www.cisl.ucar.edu/css/software/spherepack/}} @webpage{spharmonickit_www, Date-Added = {2012-05-14 15:16:37 +0200}, Date-Modified = {2012-05-14 15:23:29 +0200}, Title = {{\sc spharmonickit/s2kit}}, Url = {http://www.cs.dartmouth.edu/~geelong/sphere/}, Bdsk-Url-1 = {http://www.cs.dartmouth.edu/$%5Csim$geelong/sphere/}} @webpage{s2hat_www, Date-Added = {2012-05-14 15:12:57 +0200}, Date-Modified = {2012-05-16 11:09:54 +0200}, Title = {{\sc s$^2$hat}}, Url = {http://www.apc.univ-paris7.fr/APC_CS/Recherche/Adamis/MIDAS09/software/s2hat/s2hat.html}, Bdsk-Url-1 = {http://www.apc.univ-paris7.fr/$%5Csim$radek/s2hat.html}} @webpage{libpsht_www, Date-Added = {2012-05-14 15:11:17 +0200}, Date-Modified = {2012-05-14 15:25:04 +0200}, Title = {{\sc libpsht}}, Url = {http://libpsht.sourceforge.net/}, Bdsk-Url-1 = {http://www.mpa-garching.mpg.de/%5C-$%5Csim$martin/%20libpsht/doc/libpsht/index.html}} @webpage{ccsht_www, Date-Added = {2012-05-14 15:10:00 +0200}, Date-Modified = {2012-05-14 15:26:15 +0200}, Title = {{\sc ccsht}}, Url = {http://crd.lbl.gov/~cmc/ccSHTlib/doc/}, Bdsk-Url-1 = {http://crd.lbl.gov/$%5Csim$cmc/ccSHTlib/doc/}} @webpage{glesp_www, Date-Added = {2012-05-14 13:59:00 +0200}, Date-Modified = {2012-05-14 13:59:06 +0200}, Title = {{\sc glesp}}, Url = {http://www.glesp.nbi.dk/}, Bdsk-Url-1 = {http://www.glesp.nbi.dk/}} @webpage{healpix_www, Date-Added = {2012-05-14 13:58:18 +0200}, Date-Modified = {2012-05-14 13:58:44 +0200}, Title = {{\sc healpix}}, Url = {http://healpix.jpl.nasa.gov/}, Bdsk-Url-1 = {http://healpix.jpl.nasa.gov/}} @inproceedings{grigori2008communication, Author = {Grigori, L. and Demmel, J.W. and Xiang, H.}, Booktitle = {Proceedings of the 2008 ACM/IEEE conference on Supercomputing}, Organization = {IEEE Press}, Pages = {29}, Title = {Communication avoiding Gaussian elimination}, Year = {2008}} @article{wavemoth, Adsnote = {Provided by the SAO/NASA Astrophysics Data System}, Adsurl = {http://adsabs.harvard.edu/abs/2012ApJS..199....5S}, Archiveprefix = {arXiv}, Author = {{Seljebotn}, D.~S.}, Doi = {10.1088/0067-0049/199/1/5}, Eid = {5}, Eprint = {1110.4874}, Journal = {Astrophysical Journal Supplement Series}, Keywords = {methods: numerical}, Month = mar, Pages = {5}, Primaryclass = {astro-ph.IM}, Title = {{Wavemoth-Fast Spherical Harmonic Transforms by Butterfly Matrix Compression}}, Volume = 199, Year = 2012, Bdsk-Url-1 = {http://dx.doi.org/10.1088/0067-0049/199/1/5}} @article{passinggraph, Address = {Los Alamitos, CA, USA}, Author = {M.J. Sottile and V.P. Chandu and D.A. Bader}, Date-Added = {2011-11-23 18:01:48 +0100}, Date-Modified = {2011-11-23 18:06:25 +0100}, Doi = {http://doi.ieeecomputersociety.org/10.1109/IPDPS.2006.1639321}, Isbn = {1-4244-0054-6}, Journal = {Parallel and Distributed Processing Symposium, International}, Pages = {64}, Publisher = {IEEE Computer Society}, Title = {Performance analysis of parallel programs via message-passing graph traversal}, Volume = {0}, Year = {2006}, Bdsk-Url-1 = {http://doi.ieeecomputersociety.org/10.1109/IPDPS.2006.1639321}} @article{predigting_run_times, Address = {Los Alamitos, CA, USA}, Author = {R. Rugina and K. Schauser}, Date-Added = {2011-11-23 17:58:09 +0100}, Date-Modified = {2011-11-23 17:58:09 +0100}, Doi = {http://doi.ieeecomputersociety.org/10.1109/IPPS.1998.669996}, Isbn = {0-8186-8403-8}, Journal = {Parallel Processing Symposium, International}, Pages = {0654}, Publisher = {IEEE Computer Society}, Title = {Predicting the Running Times of Parallel Programs by Simulation}, Volume = {0}, Year = {1998}, Bdsk-Url-1 = {http://doi.ieeecomputersociety.org/10.1109/IPPS.1998.669996}} @article{bruck, Address = {Los Alamitos, CA, USA}, Author = {Jehoshua Bruck and Ching-Tien Ho and Shlomo Kipnis and Eli Upfal and Derrick Weathersby}, Date-Added = {2011-09-28 18:59:09 +0200}, Date-Modified = {2011-09-28 18:59:20 +0200}, Doi = {http://doi.ieeecomputersociety.org/10.1109/71.642949}, Issn = {1045-9219}, Journal = {IEEE Transactions on Parallel and Distributed Systems}, Pages = {1143-1156}, Publisher = {IEEE Computer Society}, Title = {Efficient Algorithms for All-to-All Communications in Multiport Message-Passing Systems}, Volume = {8}, Year = {1997}, Bdsk-Url-1 = {http://doi.ieeecomputersociety.org/10.1109/71.642949}} @manual{mpich, Author = {MPICH2}, Date-Added = {2011-09-28 17:38:43 +0200}, Date-Modified = {2011-11-23 17:22:58 +0100}, Howpublished = {http://www.mcs.anl.gov/research/projects/mpich2/}, Title = {{MPICH} -- A portable implementation of {MPI}}, Urldate = {\url{http://www.mcs.anl.gov/research/projects/mpich2/}}, Year = {2011}} @inproceedings{performanceanalysis, Author = {Thara Angskun and George Bosilca and Graham E. Fagg and Edgar Gabriel and Jack J. Dongarra}, Booktitle = {In: Proceedings of the 19th IEEE International Parallel and Distributed Processing Symposium (IPDPS'05) - Workshop 15}, Date-Added = {2011-09-28 15:10:17 +0200}, Date-Modified = {2011-09-28 15:10:26 +0200}, Title = {Performance Analysis of MPI Collective Operations}, Year = {2005}} @article{Drake_algorithm888, Acmid = {1404581}, Address = {New York, NY, USA}, Articleno = {23}, Author = {Drake, John B. and Worley, Pat and D'Azevedo, Eduardo}, Date-Added = {2011-09-28 14:54:39 +0200}, Date-Modified = {2011-09-28 14:54:54 +0200}, Doi = {http://doi.acm.org/10.1145/1391989.1404581}, Issn = {0098-3500}, Issue = {3}, Issue_Date = {October 2008}, Journal = {ACM Trans. Math. Softw.}, Keywords = {Spectral transform methods, fluid dynamics, geophysical flow, high performance computing, spherical}, Month = {October}, Numpages = {23}, Pages = {23:1--23:23}, Publisher = {ACM}, Title = {Algorithm 888: Spherical Harmonic Transform Algorithms}, Url = {http://doi.acm.org/10.1145/1391989.1404581}, Volume = {35}, Year = {2008}, Bdsk-Url-1 = {http://doi.acm.org/10.1145/1391989.1404581}} @inproceedings{mpi_collective, Author = {Thara Angskun and George Bosilca and Graham E. Fagg and Edgar Gabriel and Jack J. Dongarra}, Booktitle = {In: Proceedings of the 19th IEEE International Parallel and Distributed Processing Symposium (IPDPS'05) - Workshop 15}, Date-Added = {2011-09-28 14:44:34 +0200}, Date-Modified = {2011-09-28 14:44:51 +0200}, Title = {Performance Analysis of MPI Collective Operations}, Year = {2005}} @article{citeulike:8443250, Abstract = {{General-purpose computing on graphics processing units (GPGPU) is becoming popular in HPC because of its high peak performance. However, in spite of the potential performance improvements as well as recent promising results in scientific computing applications, its real performance is not necessarily higher than that of the current high-performance CPUs, especially with recent trends towards increasing the number of cores on a single die. This is because the GPU performance can be severely limited by such restrictions as memory size and bandwidth and programming using graphics-specific APIs. To overcome this problem, we propose a model-based, adaptive library for 2D FFT that automatically achieves optimal performance using available heterogeneous CPU-GPU computing resources. To find optimal load distribution ratios between CPUs and GPUs, we construct a performance model that captures the respective contributions of CPU vs. GPU, and predicts the total execution time of 2D-FFT for arbitrary problem sizes and load distribution. The performance model divides the FFT computation into several small sub steps, and predicts the execution time of each step using profiling results. Preliminary evaluation with our prototype shows that the performance model can predict the execution time of problem sizes that are 16 times as large as the profile runs with less than 20\% error, and that the predicted optimal load distribution ratios have less than 1\% error. We show that the resulting performance improvement using both CPUs and GPUs can be as high as 50\% compared to using either a CPU core or a GPU.}}, Author = {Ogata, Y. and Endo, T. and Maruyama, N. and Matsuoka, S.}, Booktitle = {Parallel and Distributed Processing, 2008. IPDPS 2008. IEEE International Symposium on}, Citeulike-Article-Id = {8443250}, Date-Added = {2011-09-27 11:07:58 +0200}, Date-Modified = {2011-09-27 11:09:52 +0200}, Issn = {1530-2075}, Journal = {Parallel and Distributed Processing, 2008. IPDPS 2008. IEEE International Symposium on}, Keywords = {allocation, api, application, computer, computing, cpu-gpu, fast, fft, fourier, general-purpose, graphics, graphics-specific, heterogeneous, interfaces, libraries, library, pfarna, processing, program, resource, software, transforms, units}, Pages = {1--10}, Posted-At = {2010-12-17 10:44:34}, Priority = {2}, Title = {An efficient, model-based CPU-GPU heterogeneous FFT library}, Year = {2008}} @techreport{gpu_soman, Author = {Vikrant Soman}, Date-Added = {2011-09-27 10:23:03 +0200}, Date-Modified = {2011-11-15 15:03:36 +0100}, Institution = {Department of Electrical Engineering, University of Wisconsin}, Title = {ACCELERATING SPHERICAL HARMONIC TRANSFORMS ON THE NVIDIA GPU}, Urldate = {http://homepages.cae.wisc.edu/~ece734/project/s09/soman_rpt.pdf}, Year = {2009}} @article{Mohlenkamp99afast, Author = {Martin J. Mohlenkamp}, Date-Added = {2011-09-27 10:06:47 +0200}, Date-Modified = {2011-09-27 10:06:47 +0200}, Journal = {J. Fourier Anal. Appl}, Pages = {159--184}, Title = {A fast transform for spherical harmonics}, Volume = {5}, Year = {1999}} @article{Xiao2007311, Author = {Huadong Xiao and Yang Lu}, Date-Added = {2011-09-27 09:39:13 +0200}, Date-Modified = {2011-09-28 14:50:55 +0200}, Doi = {10.1016/j.cageo.2006.07.005}, Issn = {0098-3004}, Journal = {Computers \& amp; Geosciences}, Keywords = {FFT}, Number = {3}, Pages = {311 -- 317}, Title = {Parallel computation for spherical harmonic synthesis and analysis}, Url = {http://www.sciencedirect.com/science/article/pii/S0098300406001452}, Volume = {33}, Year = {2007}, Bdsk-Url-1 = {http://www.sciencedirect.com/science/article/pii/S0098300406001452}, Bdsk-Url-2 = {http://dx.doi.org/10.1016/j.cageo.2006.07.005}} @inproceedings{Foster93parallelizingthe, Author = {Ian Foster and Patrick H. Worley}, Booktitle = {in Parallel Processing for Scientific Computing}, Date-Added = {2011-09-27 09:20:50 +0200}, Date-Modified = {2011-09-27 09:20:50 +0200}, Pages = {100--107}, Title = {Parallelizing the Spectral Transform Method: A Comparison of Alternative Parallel Algorithms}, Year = {1993}} @inproceedings{Chen:2010, Acmid = {1810128}, Address = {New York, NY, USA}, Author = {Chen, Yifeng and Cui, Xiang and Mei, Hong}, Booktitle = {Proceedings of the 24th ACM International Conference on Supercomputing}, Date-Added = {2011-09-27 09:14:09 +0200}, Date-Modified = {2011-09-27 10:50:17 +0200}, Doi = {http://doi.acm.org/10.1145/1810085.1810128}, Isbn = {978-1-4503-0018-6}, Keywords = {FFT, GPU clusters, array dimensions}, Location = {Tsukuba, Ibaraki, Japan}, Numpages = {10}, Pages = {315--324}, Publisher = {ACM}, Series = {ICS '10}, Title = {Large-scale FFT on GPU clusters}, Url = {http://doi.acm.org/10.1145/1810085.1810128}, Year = {2010}, Bdsk-Url-1 = {http://doi.acm.org/10.1145/1810085.1810128}} @article{inda2001efficient, Author = {Inda, M.A. and Bisseling, R.H. and Maslen, D.K.}, Journal = {SIAM Journal on Scientific Computing}, Number = {1}, Pages = {271--303}, Publisher = {SIAM}, Title = {On the efficient parallel computation of Legendre transforms}, Volume = {23}, Year = {2001}} @article{collective_mpi, Author = {Rajeev Thakur and Rolf Rabenseifner and William Gropp}, Date-Added = {2011-09-27 00:31:41 +0200}, Date-Modified = {2011-09-27 00:33:10 +0200}, Journal = {Int'l Journal of High Performance Computing Applications}, Pages = {49--66}, Title = {Optimization of Collective Communication Operations in MPICH}, Volume = {19}, Year = {2005}} @article{st_analysis, Author = {Roy W. Melton and Linda M. Wills}, Date-Added = {2011-08-30 17:59:57 +0200}, Date-Modified = {2011-08-30 18:02:24 +0200}, Journal = {SIAM J. Sci. Comput.}, Number = {1}, Pages = {167--188}, Title = {An analysis of the Spectral Transfrom Operations in climat and weather models}, Volume = {31}, Year = {2008}} @book{anova_experiment, Author = {David R. Cox and Nancy M. Reid}, Date-Added = {2011-04-15 19:12:44 +0200}, Date-Modified = {2011-04-15 19:15:30 +0200}, Publisher = {Chapman \& Hall-CRC}, Title = {The theory of design of experiments}, Year = {2000}} @book{anova_book, Author = {R. A. Bailey and Queen Mary}, Date-Added = {2011-04-15 19:09:52 +0200}, Date-Modified = {2011-04-15 19:11:03 +0200}, Publisher = {University of London}, Title = {Design of Comparative Experiments}, Year = {2008}} @article{overflow, Author = {G. Pr{\'e}zeau and M. Reinecke}, Date-Added = {2011-04-13 18:10:08 +0200}, Date-Modified = {2011-09-28 14:53:05 +0200}, Journal = {The Astrophysical Journal Supplement Series}, Number = {2}, Pages = {267}, Title = {Algorithm for the Evaluation of Reduced Wigner Matrices}, Volume = {190}, Year = {2010}, Bdsk-Url-1 = {http://stacks.iop.org/0067-0049/190/i=2/a=267}} @book{ArfkenBook, Adsnote = {Provided by the SAO/NASA Astrophysics Data System}, Adsurl = {http://adsabs.harvard.edu/abs/2005mmp..book.....A}, Author = {{Arfken}, G.~B. and {Weber}, H.~J.}, Booktitle = {Materials and Manufacturing Processes}, Date-Added = {2011-04-13 16:00:13 +0200}, Date-Modified = {2011-04-13 16:00:13 +0200}, Publisher = {{Academic Press}}, Title = {{Mathematical methods for physicists 6th ed.}}, Year = 2005} @article{Bennett_etal_2003, Adsnote = {Provided by the SAO/NASA Astrophysics Data System}, Adsurl = {http://adsabs.harvard.edu/abs/2003ApJ...583....1B}, Author = {{Bennett}, C.~L. and {Bay}, M. and {Halpern}, M. and {Hinshaw}, G. and {Jackson}, C. and {Jarosik}, N. and {Kogut}, A. and {Limon}, M. and {Meyer}, S.~S. and {Page}, L. and {Spergel}, D.~N. and {Tucker}, G.~S. and {Wilkinson}, D.~T. and {Wollack}, E. and {Wright}, E.~L.}, Date-Added = {2011-04-13 16:00:13 +0200}, Date-Modified = {2011-09-28 14:49:50 +0200}, Doi = {10.1086/345346}, Eprint = {arXiv:astro-ph/0301158}, Journal = {ApJ}, Keywords = {Cosmology: Cosmic Microwave Background, Cosmology: Observations, Cosmology: Dark Matter, Cosmology: Early Universe, Space Vehicles: Instruments}, Month = jan, Pages = {1-23}, Title = {{The Microwave Anisotropy Probe Mission}}, Volume = 583, Year = 2003, Bdsk-Url-1 = {http://dx.doi.org/10.1086/345346}} @inproceedings{BROQUEDIS:2010:INRIA, Address = {{P}isa {I}talie}, Affiliation = {{L}aboratoire {B}ordelais de {R}echerche en {I}nformatique - {L}a{BRI} - {CNRS} : {UMR}5800 - {U}niversit{\'e} {S}ciences et {T}echnologies - {B}ordeaux {I} - {E}cole {N}ationale {S}up{\'e}rieure d'{E}lectronique, {I}nformatique et {R}adiocommunications de {B}ordeaux - {U}niversit{\'e} {V}ictor {S}egalen - {B}ordeaux {II} - {RUNTIME} - {INRIA} {B}ordeaux - {S}ud-{O}uest - {INRIA} - {CNRS} : {UMR}5800 - {U}niversit{\'e} {S}ciences et {T}echnologies - {B}ordeaux {I} - {E}cole {N}ationale {S}up{\'e}rieure d'{E}lectronique, {I}nformatique et {R}adiocommunications de {B}ordeaux}, Audience = {internationale}, Author = {{B}roquedis, {F}ran{\c{c}}ois and {C}let-{O}rtega, {J}{\'e}r{\^o}me and {M}oreaud, {S}t{\'e}phanie and {F}urmento, {N}athalie and {G}oglin, {B}rice and {M}ercier, {G}uillaume and {T}hibault, {S}amuel and {N}amyst, {R}aymond}, Booktitle = {{PDP} 2010 - {T}he 18th {E}uromicro {I}nternational {C}onference on {P}arallel, {D}istributed and {N}etwork-{B}ased {C}omputing}, Date-Added = {2011-04-13 16:00:13 +0200}, Date-Modified = {2011-04-13 16:00:13 +0200}, Day = {17}, Editor = {{IEEE}}, Language = {{A}nglais}, Month = {02}, Title = {hwloc: a {G}eneric {F}ramework for {M}anaging {H}ardware {A}ffinities in {HPC} {A}pplications}, Url = {http://hal.inria.fr/inria-00429889/en/}, Year = {2010}, Bdsk-Url-1 = {http://hal.inria.fr/inria-00429889/en/}} @book{cpp_programming, Author = {Bjarne Stroustrup}, Date-Added = {2011-04-13 16:00:13 +0200}, Date-Modified = {2011-04-13 16:00:13 +0200}, Editor = {3}, Publisher = {Addison-Wesley}, Title = {The \verb!C++! Programming Language}, Year = {1997}} @inproceedings{csb, Address = {New York, NY, USA}, Author = {Bulu\c{c}, Aydin and Fineman, Jeremy T. and Frigo, Matteo and Gilbert, John R. and Leiserson, Charles E.}, Booktitle = {SPAA '09: Proceedings of the twenty-first annual symposium on Parallelism in algorithms and architectures}, Date-Added = {2011-04-13 16:00:13 +0200}, Date-Modified = {2011-04-13 16:00:13 +0200}, Doi = {http://doi.acm.org/10.1145/1583991.1584053}, Isbn = {978-1-60558-606-9}, Location = {Calgary, AB, Canada}, Pages = {233--244}, Publisher = {ACM}, Title = {Parallel sparse matrix-vector and matrix-transpose-vector multiplication using compressed sparse blocks}, Year = {2009}, Bdsk-Url-1 = {http://doi.acm.org/10.1145/1583991.1584053}} @manual{CUDABestPractices, Author = {Nvidia}, Date-Added = {2011-04-13 16:00:13 +0200}, Date-Modified = {2011-04-13 16:00:13 +0200}, Title = {NVIDIA CUDA Best Practices Guide}, Year = {2010}} @manual{CUDAFermi, Author = {Nvidia}, Date-Added = {2011-04-13 16:00:13 +0200}, Date-Modified = {2011-04-13 16:00:13 +0200}, Title = {Tuning CUDA Applications for Fermi}, Year = {2010}} @manual{CUDAManual, Author = {Nvidia}, Date-Added = {2011-04-13 16:00:13 +0200}, Date-Modified = {2011-04-13 16:00:13 +0200}, Title = {NVIDIA CUDA Programming Guide}, Year = {2010}} @manual{CUFFT, Author = {Nvidia}, Date-Added = {2011-04-13 16:00:13 +0200}, Date-Modified = {2011-04-13 16:00:13 +0200}, Title = {CUDA CUFFT Library}, Year = {2010}} @article{Doroshkevich_etal_2005, Adsnote = {Provided by the SAO/NASA Astrophysics Data System}, Adsurl = {http://adsabs.harvard.edu/abs/2005astro.ph..1494D}, Author = {{Doroshkevich}, A.~G. and {Naselsky}, P.~D. and {Verkhodanov}, O.~V. and {Novikov}, D.~I. and {Turchaninov}, V.~I. and {Novikov}, I.~D. and {Christensen}, P.~R. and {Chiang}, {L.~-.}}, Date-Added = {2011-04-13 16:00:13 +0200}, Date-Modified = {2011-04-13 16:00:13 +0200}, Eprint = {arXiv:astro-ph/0501494}, Journal = {ArXiv Astrophysics e-prints}, Keywords = {Astrophysics}, Month = jan, Title = {{First Release of Gauss-Legendre Sky Pixelization (GLESP) software package for CMB analysis}}, Year = 2005} @article{Driscoll_Healy_1994, Author = {J. R. Driscoll and D. M. Healy}, Date-Added = {2011-04-13 16:00:13 +0200}, Date-Modified = {2011-04-13 16:00:13 +0200}, Doi = {DOI: 10.1006/aama.1994.1008}, Issn = {0196-8858}, Journal = {Advances in Applied Mathematics}, Number = {2}, Pages = {202 - 250}, Title = {Computing Fourier Transforms and Convolutions on the 2-Sphere}, Url = {http://www.sciencedirect.com/science/article/B6W9D-45P0H0G-B/2/44060d9d048f53ab56ccc47adf07d705}, Volume = {15}, Year = {1994}, Bdsk-Url-1 = {http://www.sciencedirect.com/science/article/B6W9D-45P0H0G-B/2/44060d9d048f53ab56ccc47adf07d705}, Bdsk-Url-2 = {http://dx.doi.org/10.1006/aama.1994.1008}} @article{frigo2005design, Author = {Frigo, M. and Johnson, S.G.}, Date-Added = {2011-04-13 16:00:13 +0200}, Date-Modified = {2011-04-13 16:00:13 +0200}, Journal = {Proceedings of the IEEE}, Number = {2}, Pages = {216--231}, Publisher = {IEEE}, Title = {{The design and implementation of FFTW3}}, Volume = {93}, Year = {2005}} @article{Gorski_etal_2005, Adsnote = {Provided by the SAO/NASA Astrophysics Data System}, Adsurl = {http://adsabs.harvard.edu/abs/2005ApJ...622..759G}, Author = {{G{\'o}rski}, K.~M. and {Hivon}, E. and {Banday}, A.~J. and {Wandelt}, B.~D. and {Hansen}, F.~K. and {Reinecke}, M. and {Bartelmann}, M.}, Date-Added = {2011-04-13 16:00:13 +0200}, Date-Modified = {2011-09-28 14:50:13 +0200}, Doi = {10.1086/427976}, Eprint = {arXiv:astro-ph/0409513}, Journal = {ApJ}, Keywords = {Cosmology: Cosmic Microwave Background, Cosmology: Observations, Methods: Statistical}, Month = apr, Pages = {759-771}, Title = {{HEALPix: A Framework for High-Resolution Discretization and Fast Analysis of Data Distributed on the Sphere}}, Volume = 622, Year = 2005, Bdsk-Url-1 = {http://dx.doi.org/10.1086/427976}} @misc{hpc_multicore, Date-Added = {2011-04-13 16:00:13 +0200}, Date-Modified = {2011-09-28 15:07:28 +0200}, Note = {\url{http://www.hpccommunity.org/f55/multi-core-strategies-mpi-openmpi-702/}}, Title = {{M}ulti-core {S}trategies: {MPI} and {O}pen{MP}}, Urldate = {2010-01-28}} @techreport{hupca, Author = {Hupca, I.O. and Falcou, J. and Grigori, L. and Stompor, R.}, Date-Added = {2011-04-13 16:00:13 +0200}, Date-Modified = {2011-04-15 20:47:19 +0200}, Institution = {INRIA}, Number = {7409}, Title = {Spherical harmonic transform with GPUs}, Year = {2010}} @article{libpsht, Adsnote = {Provided by the SAO/NASA Astrophysics Data System}, Adsurl = {http://adsabs.harvard.edu/abs/2011A\%26A...526A.108R}, Archiveprefix = {arXiv}, Author = {{Reinecke}, M.}, Doi = {10.1051/0004-6361/201015906}, Eid = {A108}, Eprint = {1010.2084}, Journal = {Astronomy and Astrophysics}, Keywords = {methods: numerical, cosmic background radiation, large-scale structure of the Universe}, Month = feb, Pages = {A108}, Primaryclass = {astro-ph.IM}, Title = {{Libpsht - algorithms for efficient spherical harmonic transforms}}, Volume = 526, Year = 2011, Bdsk-Url-1 = {http://dx.doi.org/10.1051/0004-6361/201015906}} @book{mathForphysicist, Author = {G.B. Arfken and H. J. Weber}, Date-Added = {2011-04-13 16:00:13 +0200}, Date-Modified = {2011-04-13 16:00:13 +0200}, Edition = {6}, Publisher = {Academic Press}, Title = {Mathematical methods for physicists}, Year = {2005}} @book{MPI1994, Author = {W. Grop and E. Lusk and A. Skjellum}, Date-Added = {2011-04-13 16:00:13 +0200}, Date-Modified = {2011-04-13 16:00:13 +0200}, Publisher = {MIT Press}, Title = {Using MPI: Portable Parallel Programming with Message-Passing Interface}, Year = {1994}} @article{Muciaccia_etal_1997, Adsnote = {Provided by the SAO/NASA Astrophysics Data System}, Adsurl = {http://adsabs.harvard.edu/abs/1997ApJ...488L..63M}, Author = {{Muciaccia}, P.~F. and {Natoli}, P. and {Vittorio}, N.}, Date-Added = {2011-04-13 16:00:13 +0200}, Date-Modified = {2011-09-28 14:49:19 +0200}, Doi = {10.1086/310921}, Eprint = {arXiv:astro-ph/9703084}, Journal = {ApJ}, Month = oct, Pages = {L63+}, Title = {{Fast Spherical Harmonic Analysis: A Quick Algorithm for Generating and/or Inverting Full-Sky, High-Resolution Cosmic Microwave Background Anisotropy Maps}}, Volume = 488, Year = 1997, Bdsk-Url-1 = {http://dx.doi.org/10.1086/310921}} @inproceedings{Nukada09, Address = {New York, NY, USA}, Author = {Nukada, Akira and Matsuoka, Satoshi}, Booktitle = {SC '09: Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis}, Date-Added = {2011-04-13 16:00:13 +0200}, Date-Modified = {2011-04-13 16:00:13 +0200}, Doi = {http://doi.acm.org/10.1145/1654059.1654090}, Isbn = {978-1-60558-744-8}, Location = {Portland, Oregon}, Pages = {1--10}, Publisher = {ACM}, Title = {Auto-tuning 3-{D} {FFT} library for {CUDA} {GPU}s}, Year = {2009}, Bdsk-Url-1 = {http://doi.acm.org/10.1145/1654059.1654090}} @inproceedings{petsc-efficient, Author = {Satish Balay and William D. Gropp and Lois Curfman McInnes and Barry F. Smith}, Booktitle = {Modern Software Tools in Scientific Computing}, Date-Added = {2011-04-13 16:00:13 +0200}, Date-Modified = {2011-04-13 16:00:13 +0200}, Editor = {E. Arge and A. M. Bruaset and H. P. Langtangen}, Pages = {163--202}, Publisher = {Birkh{\"{a}}user Press}, Title = {Efficient Management of Parallelism in Object Oriented Numerical Software Libraries}, Year = {1997}} @book{Schw82, Author = {P. N. Swarztrauber}, Date-Added = {2011-04-13 16:00:13 +0200}, Date-Modified = {2011-04-13 16:00:13 +0200}, Publisher = {Academic Press}, Title = {Vectorizing the FFTs, in Parallel Computations}, Year = {1982}} @article{Smoot_etal_1992, Adsnote = {Provided by the SAO/NASA Astrophysics Data System}, Adsurl = {http://adsabs.harvard.edu/abs/1992ApJ...396L...1S}, Author = {{Smoot}, G.~F. and {Bennett}, C.~L. and {Kogut}, A. and {Wright}, E.~L. and {Aymon}, J. and {Boggess}, N.~W. and {Cheng}, E.~S. and {de Amici}, G. and {Gulkis}, S. and {Hauser}, M.~G. and {Hinshaw}, G. and {Jackson}, P.~D. and {Janssen}, M. and {Kaita}, E. and {Kelsall}, T. and {Keegstra}, P. and {Lineweaver}, C. and {Loewenstein}, K. and {Lubin}, P. and {Mather}, J. and {Meyer}, S.~S. and {Moseley}, S.~H. and {Murdock}, T. and {Rokke}, L. and {Silverberg}, R.~F. and {Tenorio}, L. and {Weiss}, R. and {Wilkinson}, D.~T.}, Date-Added = {2011-04-13 16:00:13 +0200}, Date-Modified = {2011-09-28 14:48:37 +0200}, Doi = {10.1086/186504}, Journal = {ApJ}, Keywords = {COSMIC BACKGROUND EXPLORER SATELLITE, MICROWAVE RADIOMETERS, NORMAL DENSITY FUNCTIONS, RELIC RADIATION, ROOT-MEAN-SQUARE ERRORS, ASTRONOMICAL MAPS, MILKY WAY GALAXY}, Month = sep, Pages = {L1-L5}, Title = {{Structure in the COBE differential microwave radiometer first-year maps}}, Volume = 396, Year = 1992, Bdsk-Url-1 = {http://dx.doi.org/10.1086/186504}} @article{suda_sht, Author = {Relji SUDA and Masayasu Takami}, Date-Added = {2011-04-13 16:00:13 +0200}, Date-Modified = {2011-04-13 16:00:13 +0200}, Journal = {Mathematic of Computation}, Month = {November}, Number = {238}, Pages = {703--715}, Title = {A Fast Spherical Harmonics Transform Algorithm}, Volume = {71}, Year = {2001}} @book{Tanner1992, Adsnote = {Provided by the SAO/NASA Astrophysics Data System}, Adsurl = {http://adsabs.harvard.edu/abs/1992tsio.book.....T}, Author = {{Tanner}, M.A.}, Booktitle = {Lecture Notes in Statistics, Berlin a.o.: Springer, 1991, 2nd, corrected printing 1992}, Date-Modified = {2011-04-15 13:33:33 +0200}, Publisher = {Springer Verlag}, Title = {{Tools for statistical inference. Observed data and data augmentation methods}}, Year = 1992} @article{Tygert2008, Author = {Mark Tygert}, Date-Added = {2011-04-13 16:00:13 +0200}, Date-Modified = {2011-04-13 16:00:13 +0200}, Doi = {DOI: 10.1016/j.jcp.2007.12.019}, Issn = {0021-9991}, Journal = {Journal of Computational Physics}, Keywords = {Spectral}, Number = {8}, Pages = {4260 - 4279}, Title = {Fast algorithms for spherical harmonic expansions, II}, Url = {http://www.sciencedirect.com/science/article/B6WHY-4RGTXFJ-2/2/b4cdaa8705711759b875bcb7331c8a1a}, Volume = {227}, Year = {2008}, Bdsk-Url-1 = {http://www.sciencedirect.com/science/article/B6WHY-4RGTXFJ-2/2/b4cdaa8705711759b875bcb7331c8a1a}, Bdsk-Url-2 = {http://dx.doi.org/10.1016/j.jcp.2007.12.019}} @techreport{Volkov08, Author = {Volkov, V. and Demmel, J.W.}, Date-Added = {2011-04-13 16:00:13 +0200}, Date-Modified = {2011-04-13 16:00:13 +0200}, Institution = {EECS Department, University of California, Berkeley}, Month = {May}, Number = {UCB/EECS-2008-49}, Title = {{LU}, {QR} and {C}holesky Factorizations using Vector Capabilities of GPUs}, Url = {http://www.eecs.berkeley.edu/Pubs/TechRpts/2008/EECS-2008-49.html}, Year = {2008}, Bdsk-Url-1 = {http://www.eecs.berkeley.edu/Pubs/TechRpts/2008/EECS-2008-49.html}} @article{volkov08:_bench_gpus_to_tune_dense_linear_algeb, Author = {Volkov, V. and Demmel, J. W.}, Date-Added = {2011-04-13 16:00:13 +0200}, Date-Modified = {2011-04-13 16:00:13 +0200}, Journal = {ACM/IEEE Conference on Supercomputing (SC08)}, Title = {Benchmarking {GPU}s to tune dense linear algebra}, Year = 2008} @article{Goldbergetal1967, Adsnote = {Provided by the SAO/NASA Astrophysics Data System}, Adsurl = {http://adsabs.harvard.edu/abs/1967JMP.....8.2155G}, Author = {{Goldberg}, J.~N. and {Macfarlane}, A.~J. and {Newman}, E.~T. and {Rohrlich}, F. and {Sudarshan}, E.~C.~G.}, Date-Modified = {2011-04-13 16:26:00 +0200}, Doi = {10.1063/1.1705135}, Journal = {Journal of Mathematical Physics}, Month = nov, Pages = {2155-2161}, Title = {{Spin-s Spherical Harmonics and D}}, Volume = 8, Year = 1967, Bdsk-Url-1 = {http://dx.doi.org/10.1063/1.1705135}} @article{SudaTakami2002, Acmid = {589617}, Address = {Boston, MA, USA}, Author = {Suda, Reiji and Takami, Masayasu}, Doi = {10.1090/S0025-5718-01-01386-2}, Issn = {0025-5718}, Issue = {238}, Journal = {Math. Comput.}, Keywords = {associated Legendre transform, computational complexity, fast transform algorithm, spherical harmonics transform}, Month = {April}, Numpages = {13}, Pages = {703--715}, Publisher = {American Mathematical Society}, Title = {A fast spherical harmonics transform algorithm}, Url = {http://portal.acm.org/citation.cfm?id=589604.589617}, Volume = {71}, Year = {2002}, Bdsk-Url-1 = {http://portal.acm.org/citation.cfm?id=589604.589617}, Bdsk-Url-2 = {http://dx.doi.org/10.1090/S0025-5718-01-01386-2}} @book{Varshalovich, Author = {D. Varshalovich and A. Moskalev and V. Khersonskii}, Masid = {1983112}, Publisher = {World Scientific Publishing}, Title = {Quantum Theory of Angular Momentum}, Year = {1988}} @article{Mohlenkamp1999, Author = {Mohlenkamp, M.J.}, Journal = {Journal of Fourier Analysis and Applications}, Number = {2}, Pages = {159--184}, Publisher = {Springer}, Title = {A fast transform for spherical harmonics}, Volume = {5}, Year = {1999}} @article{Tygert2010, Author = {Tygert, M.}, Journal = {Journal of Computational Physics}, Number = {18}, Pages = {6181--6192}, Publisher = {Elsevier}, Title = {Fast algorithms for spherical harmonic expansions, III}, Volume = {229}, Year = {2010}} @article{Elsner2011, Adsnote = {Provided by the SAO/NASA Astrophysics Data System}, Adsurl = {http://adsabs.harvard.edu/abs/2011A26A...532A..35E}, Archiveprefix = {arXiv}, Author = {{Elsner}, F. and {Wandelt}, B.~D.}, Doi = {10.1051/0004-6361/201116963}, Eid = {A35}, Eprint = {1104.0672}, Journal = {Astronomy and Astrophysics}, Keywords = {methods: data analysis, methods: numerical, techniques: image processing, cosmic background radiation}, Month = aug, Pages = {A35}, Primaryclass = {astro-ph.IM}, Title = {{ARKCoS: artifact-suppressed accelerated radial kernel convolution on the sphere}}, Volume = 532, Year = 2011, Bdsk-Url-1 = {http://dx.doi.org/10.1051/0004-6361/201116963}} @article{Wiaux_etal_2006, Adsnote = {Provided by the SAO/NASA Astrophysics Data System}, Adsurl = {http://adsabs.harvard.edu/abs/2006ApJ...652..820W}, Author = {{Wiaux}, Y. and {Jacques}, L. and {Vielva}, P. and {Vandergheynst}, P.}, Doi = {10.1086/507692}, Eprint = {arXiv:astro-ph/0508516}, Journal = {\apj}, Keywords = {Cosmology: Cosmic Microwave Background, Methods: Data Analysis, Methods: Numerical}, Month = nov, Pages = {820-832}, Title = {{Fast Directional Correlation on the Sphere with Steerable Filters}}, Volume = 652, Year = 2006, Bdsk-Url-1 = {http://dx.doi.org/10.1086/507692}}