% % BibTeX entries for BeBOP papers. % % Last updated: Jun. 4, 2010 % %----- 2010 -------- @inproceedings{Grigori2010:bebop:CA_Sparse_Cholesky_SPAA10, author = {David, P.-Y. and Demmel, J. and Grigori, L. and Peyronnet, S.}, title = {Lower bounds on communication for sparse {C}holesky factorization of a model problem}, booktitle = {22nd {ACM} {S}ymposium on {P}arallelism in {A}lgorithms and {A}rchitectures ({SPAA} 2010)}, note = {(to appear as a "brief announcement")}, year = {2010} } @techreport{Demmel2010:bebop:CALU_Stability_10, author = {Demmel, J. and Grigori, L. and Xiang, H.}, title = {A {C}ommunication {O}ptimal {LU} {F}actorization {A}lgorithm}, institution = {UC Berkeley}, type = {{EECS} {T}echnical {R}eport}, number = {{EECS}-2010-29}, month = {March}, year = {2010} } @phdthesis{Hoemmen2010:bebop:Hoemmen_PhDThesis, author = {Hoemmen, M.}, title = {Communication-{A}voiding {K}rylov subspace methods}, school = {EECS Department, University of California, Berkeley}, year = {2010}, month = {April}, note = {{UCB} {EECS} {T}echnical {R}eport {EECS-2010-37}} } %----- 2009 -------- @phdthesis{Kaushik2009:multicore:thesis_kaushik, Author = {Datta, Kaushik}, Title = {Auto-tuning Stencil Codes for Cache-Based Multicore Platforms}, School = {EECS Department, University of California, Berkeley}, Year = {2009}, Month = {Dec}, URL = {http://www.eecs.berkeley.edu/Pubs/TechRpts/2009/EECS-2009-177.html}, Number = {UCB/EECS-2009-177}, } @phdthesis{Nishtala2009:bebop:Nishtala_PhDThesis, author = {Nishtala, R.}, title = {Automatically tuning collective communication for one-sided programming models}, school = {EECS Department, University of California, Berkeley}, year = {2009}, month = {Dec}, note = {{UCB} {EECS} {T}echnical {R}eport {EECS-2009-168}} } @inproceedings{Datta2009:bebop:iWAPT09_stencil, author = {Kaushik Datta and Samuel Williams and Vasily Volkov and Jonathan Carter and Leonid Oliker and John Shalf and Katherine Yelick}, title = {Auto-tuning the 27-point stencil for multicore}, booktitle = {In Proc. iWAPT2009: The Fourth International Workshop on Automatic Performance Tuning}, year = {2009} } @inproceedings{Ballard2009:bebop:CA_Cholesky_SPAA_09, author = {Ballard, G. and Demmel, J. and Holtz, O. and Schwartz, O.}, title = {Communication-{O}ptimal {P}arallel and {S}equential {C}holesky {D}ecomposition}, booktitle = {Symposium on {P}arallelism in {A}lgorithms and {A}rchitectures ({SPAA} 2009)}, month = {August}, year = {2009} } @misc{Ballard2009:bebop:Minimizing_Communication_LA, author = {Ballard, G. and Demmel, J. and Holtz, O. and Schwartz, O.}, title = {Minimizing Communication in Linear Algebra}, howpublished = {submitted to {SIAM} {J}. {M}at. {A}nal. {A}ppl., {UCB} {T}echnical {R}eport {EECS}-2009-62}, year = {2009} } @misc{Kamil2009:bebop:Framework_Autotuning_Stencils_CUG09, author = {Kamil, S. and Chan, C. and Williams, S. and Oliker, L. and Shalf, J. and Howison, M. and Bethel, E. W. and Prabhat}, title = {A {G}eneralized {F}ramework for {A}uto-tuning {S}tencil {C}omputations}, howpublished = {Cray {U}ser {G}roup {C}onference, {A}tlanta, {GA} {\bf {W}inner, {B}est {P}aper}, bebop.cs.berkeley.edu}, year = {2009} } @inproceedings{Kamil2009:multicore:CUG09_stencilFramework, author={S. Kamil and C. Chan and S. Williams and others}, title={A Generalized Framework for Auto-tuning Stencil Computations}, booktitle={Cray User Group}, year=2009 } %----- 2008 -------- @Article{Datta2008:multicore:stenciljournal, author = {Kaushik Datta and Shoaib Kamil and Samuel Williams and Leonid Oliker and John Shalf and Katherine Yelick}, title = {{O}ptimization and {P}erformance {M}odeling of {S}tencil {C}omputations on {M}odern {M}icroprocessors}, journal = {Siam Review}, month = {December}, year = {2008} } @InProceedings{Datta2008:multicore:stencil, author = {Kauskik Datta and Mark Murphy and Vasily Volkov and Samuel Williams and Jonathan Carter and Leonid Oliker and David Patterson and John Shalf and Katherine Yelick}, title = {{Stencil Computation Optimization and Auto-tuning on State-of-the-Art Multicore Architectures}}, booktitle={Supercomputing}, month = {November}, year = {2008}} @InProceedings{Volkov2008:gpu:bench, author = {Vasily Volkov and James Demmel}, title = {{Benchmarking GPUs to Tune Dense Linear Algebra}}, booktitle={Supercomputing}, month = {November}, year = {2008}} @InProceedings{Jain2008:optical:network, author={Ankit Jain and Shoaib Kamil and Marghoob Mohiyuddin and John Shalf and John D. Kubiatowicz}, booktitle = {HotInterconnects 2008} title = {{H}ybrid {E}lectric/{P}hotonic {N}etworks for {S}cientific {A}pplications on {T}iled {CMP}s}, month = {August}, year = {2008} } @misc{Demmel2008:bebop:TSQR_08, author = {Demmel, J. and Grigori, L. and Hoemmen, M. and Langou, J.}, title = {Communication-optimal parallel and sequential {QR} and {LU} factorizations}, howpublished = {{UCB} {T}echnical {R}eport {EECS}-2008-89 (submitted)}, year = {2008} } @TechReport{Volkov2008:gpu:factor, author = {Vasily Volkov and James Demmel}, title = {{LU}, {QR} and {C}holesky {F}actorizations using {V}ector {C}apabilities of {GPU}s}, institution = {University of California, Berkeley}, address = {Berkeley, CA, USA}, month = {May}, year = {2008} } @InProceedings{Demmel2008:commavoid, author = {James Demmel and Mark Hoemmen and Marghoob Mohiyuddin and Katherine Yelick}, title = {{A}voiding {C}ommunication in {S}parse {M}atrix {C}omputations}, booktitle={IEEE International Parallel and Distributed Processing Symposium}, month = {April}, year = {2008} } @InProceedings{Williams2008:multicore:lbmhd, author = {Samuel Williams and Jonathan Carter and Leonid Oliker and John Shalf and Katherine Yelick}, title = {{L}attice {B}oltzmann {S}imulation {O}ptimization on {L}eading {M}ulticore {P}latforms}, booktitle={IEEE International Parallel and Distributed Processing Symposium}, month = {April}, year = {2008} } %----- 2007 ----- @TechReport{Volkov2007:gpu:eigenvalues, author = {Vasily Volkov and James Demmel}, title = {{U}sing {GPU}s to {A}ccelerate the {B}isection {A}lgorithm for {F}inding {E}igenvalues of {S}ymmetric {T}ridiagonal {M}atrices}, institution = {University of California, Berkeley}, address = {Berkeley, CA, USA}, month = {December}, year = {2007} } @InProceedings{Williams2007:multicore:spmv, author = {Samuel Williams and Leonid Oliker and Richard Vuduc and John Shalf and Katherine Yelick and James Demmel}, title = {{O}ptimization of {S}parse {M}atrix-{V}ector {M}ultiplication on {E}merging {M}ulticore {P}latforms}, booktitle={Supercomputing}, month = {November}, year = {2007}} @TechReport{Demmel2007:krylov:comm, author = {James Demmel and Mark Hoemmen and Marghoob Mohiyuddin and Katherine Yelick}, title = {{Avoiding Communication in Computing Krylov Subspaces}}, institution = {University of California, Berkeley}, address = {Berkeley, CA, USA}, month = {October}, year = {2007} } @Article{Williams2007:cell, author = {Samuel Williams and John Shalf and Leonid Oliker and Shoaib Kamil and Parry Husbands and Katherine Yelick}, title = {{Scientific Computing Kernels on the Cell Processor}}, journal={International Journal of Parallel Programming}, month = {April}, year = {2007} } @Article{Nishtala2007:spmv:cb, author = {Rajesh Nishtala and Richard Vuduc and James Demmel and Katherine Yelick}, title = {{When Cache Blocking Sparse Matrix Vector Multiply Works and Why}}, journal = {Applicable Algebra in Engineering, Communication and Computing}, month = {March}, year = {2007} } @InProceedings{Gahvari2007:spmvbench, author = {Hormozd Gahvari and Mark Hoemmen and James Demmel and Katherine Yelick}, title = {{Benchmarking Sparse Matrix-Vector Multiply in Five Minutes}}, booktitle = {{SPEC Benchmark Workshop}}, month = {January}, year = {2007} } %---- 2006 ---- @Article{Gahvari2006:masters:spmvbench, author = {Hormozd Gahvari}, title = {{Benchmarking Sparse Matrix-Vector Multiply}}, journal={University of California, Berkeley, Masters Thesis}, month = {December}, year = {2006}} @InProceedings{Kamil2006:stencil, author = {Shoaib Kamil and Kaushik Datta and Samuel Williams and Leonid Oliker and John Shalf and Katherine Yelick}, title = {{Implicit and Explict Optimizations for Stencil Computations}}, booktitle = {Memory Systems Performance and Correctness}, month = {October}, year = {2006}} @InProceedings{Williams2006:cell:potential, author = {Samuel Williams and John Shalf and Leonid Oliker and Shoaib Kamil and Parry Husbands and Katherine Yelick}, title = {{The Potential of the Cell Processor for Scientific Computing}}, booktitle = {Computing Frontiers} month = {May}, year = {2006}} %---- 2005 ---- @TechReport{Vuduc2005:bebop:oski, author = {Richard Vuduc and James Demmel and Katherine Yelick}, title = {An interface for a self-adapting sparse kernel library}, institution = {University of California, Berkeley}, address = {Berkeley, CA, USA}, month = {September}, year = {2004} } @InProceedings{Vuduc2005:OSKI:SciDAC, author = {Richard Vuduc and James W. Demmel and Katherine A. Yelick}, title = {{OSKI}: {A} library of automatically tuned sparse matrix kernels}, booktitle = {Proceedings of SciDAC 2005}, series = {Journal of Physics: Conference Series}, publisher = {Institute of Physics Publishing}, address = {San Francisco, CA, USA}, month = {June}, year = {2005}, note = {({\it to appear})} } % % R&R: UCRL-CONF-213753 % % % ---------- Published ---------- % @InProceedings{Vuduc2005:ubcsrsplit, author = {Richard Vuduc and Hyun-Jin Moon}, title = {Fast sparse matrix vector multiplication by exploiting variable block structure}, booktitle = {Proceedings of the International Conference on High-Performance Computing and Communications}, address = {Sorrento, Italy}, series = {LNCS 3726}, month = {September}, year = {2005} } @InProceedings{Demmel2005:selftune:linalg, author = {James Demmel and Jack Dongarra and Victor Eijkhout and Erika Fuentes and Antoine Petitet and Richard Vuduc and R. Clint Whaley and Katherine Yelick}, title = {Self Adapting Linear Algebra Algorithms and Software}, booktitle = {Proceedings of the IEEE: Special Issue on Program Generation, Optimization, and Adaptation}, volume = {93}, number = {2}, month = {February}, year = {2005} } @InProceedings{Lee2004:spmv:symm, author = {Benjamin C. Lee and Richard Vuduc and James Demmel and Katherine Yelick}, title = {Performance models for evaluation and automatic tuning of symmetric sparse matrix-vector multiply}, booktitle = {Proceedings of the International Conference on Parallel Processing}, address = {Montreal, Quebec, Canada}, month = {August}, year = {2004} } % Winner, Best Paper Award @InProceedings{Nishtala2004:cacheblock:smvm, author = {Rajesh Nishtala and Richard Vuduc and James Demmel and Katherine Yelick}, title = {When cache blocking sparse matrix vector multiply works and why}, booktitle = {Proceedings of the PARA'04 Workshop on the State-of-the-art in Scientific Computing}, address = {Copenhagen, Denmark}, month = {June}, year = {2004} } @InProceedings{Im2004:mat3prod, author = {Eun-Jin Im and Ismail Bustany and Cleve Ashcraft and James Demmel and Katherine Yelick}, title = {Toward automatic performance tuning of matrix triple products based on matrix structure}, booktitle = {Proceedings of the PARA'04 Workshop on the State-of-the-art in Scientific Computing}, address = {Copenhagen, Denmark}, month = {June}, year = {2004} } @Article{Im2004:sparsity, author = {Eun-Jin Im and Katherine A. Yelick and Richard Vuduc}, title = {{SPARSITY}: Framework for Optimizing Sparse Matrix-Vector Multiply}, journal = {International Journal of High Performance Computing Applications}, month = {February}, year = {2004}, publisher = {Sage Publications}, volume = {18}, number = {1}, pages = {135--158} } @Article{Vuduc2004:statmodel, author = {Richard Vuduc and James Demmel and Jeff Bilmes}, title = {Statistical Models for Empirical Search-Based Performance Tuning}, journal = {International Journal of High Performance Computing Applications}, month = {February}, year = {2004}, publisher = {Sage Publications}, volume = {18}, number = {1}, pages = {65--94} } @PhDThesis{Vuduc2003:thesis, author = {Richard W. Vuduc}, title = {Automatic performance tuning of sparse matrix kernels}, school = {University of California, Berkeley}, month = {December}, year = {2003} } @TechReport{Lee2003:TR:symm, author = {Benjamin C. Lee and Richard W. Vuduc and James W. Demmel and Katherine A. Yelick and Michael deLorimier and Lijue Zhong}, title = {Performance optimizations and bounds for sparse symmetric matrix-multiple vector multiply}, institution = {University of California, Berkeley}, address = {Berkeley, CA, USA}, number = {UCB/CSD-03-1297}, month = {November}, year = {2003} } @Misc{Hsu2003:blzpack:srthesis, author = {Christopher Hsu}, title = {Effects of block size on the block {Lanczos} algorithm}, school = {Dept. of Mathematics, U.C. Berkeley}, month = {June}, year = {2003}, note = {Senior thesis} } @InProceedings{Vuduc2003:ata:bounds, author = {Richard Vuduc and Attila Gyulassy and James W. Demmel and Katherine A. Yelick}, title = {Memory Hierarchy Optimizations and Bounds for Sparse {$A^TAx$}}, booktitle = {Proceedings of the ICCS Workshop on Parallel Linear Algebra}, editor = {Peter M. A. Sloot and David Abramson and Alexander V. Bogdanov and Jack J. Dongarra and Albert Y. Zomaya and Yuriy E. Gorbachev}, volume = {LNCS 2660}, publisher = {Springer}, address = {Melbourne, Australia}, month = {June}, year = {2003}, pages = {705--714} } @TechReport{Vuduc2003:TR:ata:bounds, author = {Richard Vuduc and Attila Gyulassy and James W. Demmel and Katherine A. Yelick}, title = {Memory Hierarchy Optimizations and Bounds for Sparse {$A^TAx$}}, institution = {University of California, Berkeley}, address = {Berkeley, CA, USA}, number = {UCB/CSD-03-1232}, month = {February}, year = {2003} } @InProceedings{Demmel2003:fpsum, author = {James W. Demmel and Yozo Hida}, title = {Fast and accurate floating point summation with applications to computational geometry}, booktitle = {Proceedings of the 10th GAMM-IMACS International Symposium on Scientific Computing, Computer Arithmetic, and Validated Numerics (SCAN 2002)}, month = {January}, year = {2003} } @InProceedings{Vuduc2002:smvm:bounds, author = {Richard Vuduc and James W. Demmel and Katherine A. Yelick and Shoaib Kamil and Rajesh Nishtala and Benjamin Lee}, title = {Performance Optimizations and Bounds for Sparse Matrix-Vector Multiply}, booktitle = {Proceedings of Supercomputing}, address = {Baltimore, MD, USA}, month = {November}, year = {2002} } % Finalist, Best Student Paper @InProceedings{Vuduc2002:sts:bounds, author = {Richard Vuduc and Shoaib Kamil and Jen Hsu and Rajesh Nishtala and James W. Demmel and Katherine A. Yelick}, title = {Automatic Performance Tuning and Analysis of Sparse Triangular Solve}, booktitle = {ICS 2002: Workshop on Performance Optimization via High-Level Languages and Libraries}, address = {New York, USA}, month = {June}, year = {2002} } % Winner, Best Student Paper @InProceedings{Im2001:sparsity:reg, author = {Eun-Jin Im and Katherine A. Yelick}, title = {Optimizing Sparse Matrix Computations for Register Reuse in {SPARSITY}}, booktitle = {Proceedings of the International Conference on Computational Science}, address = {San Francisco, CA}, publisher = {Springer}, series = {LNCS}, volume = {2073}, pages = {127--136}, month = {May}, year = {2001} } @InProceedings{Vuduc2001:statmod, author = {Richard Vuduc and James W. Demmel and Jeff A. Bilmes}, title = {Statistical Models for Automatic Performance Tuning}, booktitle = {Proceedings of the International Conference on Computational Science}, address = {San Francisco, CA}, publisher = {Springer}, series = {LNCS}, volume = {2073}, pages = {117--126}, month = {May}, year = {2001} } % % eof %