Dongarra, J., Ltaief, H., Luszczek, P., Weaver, V. "Energy Footprint of Advanced Dense Numerical Linear Algebra using Tile Algorithms on Multicore Architecture,"The 2nd International Conference on Cloud and Green Computing (submitted), Xiangtan, Hunan, China, November, 2012 [pdf] [bibtex]
@inproceedings{icl:711, author = {Dongarra, J. and Ltaief, H. and Luszczek, P. and Weaver, V.}, title = {Energy Footprint of Advanced Dense Numerical Linear Algebra using Tile Algorithms on Multicore Architecture}, booktitle = {The 2nd International Conference on Cloud and Green Computing (submitted)}, institution = {Innovative Computing Laboratory, University of Tennessee}, address = {Xiangtan, Hunan, China}, month = {November}, year = {2012} }
Agullo, E., Bosilca, G., Castagnède, C., Dongarra, J., Ltaief, H., Tomov, S. "Matrices Over Runtime Systems at Exascale,"Supercomputing '12 (poster), Salt Lake City, Utah, November, 2012 [bibtex]
@article{icl:730, author = {Agullo, E. and Bosilca, G. and Castagnède, C. and Dongarra, J. and Ltaief, H. and Tomov, S.}, title = {Matrices Over Runtime Systems at Exascale}, booktitle = {Supercomputing '12 (poster)}, institution = {Innovative Computing Laboratory, University of Tennessee}, address = {Salt Lake City, Utah}, month = {November}, year = {2012} }
Ltaief, H., Luszczek, P., Dongarra, J. "Enhancing Parallelism of Tile Bidiagonal Transformation on Multicore Architectures using Tree Reduction,"Lecture Notes in Computer Science, Vol. 7203, pp. 661-670, September, 2012 [pdf] [bibtex]
@article{icl:707, author = {Ltaief, H. and Luszczek, P. and Dongarra, J.}, title = {Enhancing Parallelism of Tile Bidiagonal Transformation on Multicore Architectures using Tree Reduction}, booktitle = {Lecture Notes in Computer Science}, institution = {Innovative Computing Laboratory, University of Tennessee}, volume = {Vol. 7203}, pages = {pp. 661-670}, month = {September}, year = {2012} }
Bosilca, G., Dongarra, J., Ltaief, H. "Power Profiling of Cholesky and QR Factorizations on Distributed Memory Systems,"Third International Conference on Energy-Aware High Performance Computing, Hamburg, Germany, September, 2012 [pdf] [bibtex]
@inproceedings{icl:710, author = {Bosilca, G. and Dongarra, J. and Ltaief, H.}, title = {Power Profiling of Cholesky and QR Factorizations on Distributed Memory Systems}, booktitle = {Third International Conference on Energy-Aware High Performance Computing}, institution = {Innovative Computing Laboratory, University of Tennessee}, address = {Hamburg, Germany}, month = {September}, year = {2012} }
Abdelfattah, A., Dongarra, J., Keyes, D., Ltaief, H. "Optimizing Memory-Bound Numerical Kernels on GPU Hardware Accelerators,"VECPAR 2012, Kobe, Japan, July, 2012 [pdf] [bibtex]
@article{icl:709, author = {Abdelfattah, A. and Dongarra, J. and Keyes, D. and Ltaief, H.}, title = {Optimizing Memory-Bound Numerical Kernels on GPU Hardware Accelerators}, booktitle = {VECPAR 2012}, institution = {Innovative Computing Laboratory, University of Tennessee}, address = {Kobe, Japan}, month = {July}, year = {2012} }
Haidar, A., Ltaief, H., Dongarra, J. "Toward High Performance Divide and Conquer Eigensolver for Dense Symmetric Matrices,"SIAM Journal on Scientific Computing (Accepted), July, 2012 [bibtex]
@article{icl:726, author = {Haidar, A. and Ltaief, H. and Dongarra, J.}, title = {Toward High Performance Divide and Conquer Eigensolver for Dense Symmetric Matrices}, booktitle = {SIAM Journal on Scientific Computing (Accepted)}, institution = {Innovative Computing Laboratory, University of Tennessee}, month = {July}, year = {2012} }
Haidar, A., Ltaief, H., Luszczek, P., Dongarra, J. "A Comprehensive Study of Task Coalescing for Selecting Parallelism Granularity in a Two-Stage Bidiagonal Reduction,"IPDPS 2012, Shanghai, China, May, 2012 [pdf] [bibtex]
@article{icl:695, author = {Haidar, A. and Ltaief, H. and Luszczek, P. and Dongarra, J.}, title = {A Comprehensive Study of Task Coalescing for Selecting Parallelism Granularity in a Two-Stage Bidiagonal Reduction}, booktitle = {IPDPS 2012}, institution = {Innovative Computing Laboratory, University of Tennessee}, address = {Shanghai, China}, month = {May}, year = {2012} }
Agullo, E., Augonnet, C., Dongarra, J., Faverge, M., Langou, J., Ltaief, H., Tomov, S. "LU Factorization for Accelerator-based Systems,"IEEE/ACS AICCSA 2011, Sharm-El-Sheikh, Egypt, December, 2011 [pdf] [bibtex]
@article{icl:599, author = {Agullo, E. and Augonnet, C. and Dongarra, J. and Faverge, M. and Langou, J. and Ltaief, H. and Tomov, S.}, title = {LU Factorization for Accelerator-based Systems}, booktitle = {IEEE/ACS AICCSA 2011}, institution = {Innovative Computing Laboratory, University of Tennessee}, address = {Sharm-El-Sheikh, Egypt}, month = {December}, year = {2011} }
Haidar, A., Ltaief, H., Dongarra, J. "Parallel Reduction to Condensed Forms for Symmetric Eigenvalue Problems using Aggregated Fine-Grained and Memory-Aware Kernels,"Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis (SC11), Seattle, WA, November 14, 2011 [pdf] [bibtex]
@inproceedings{icl:657, author = {Haidar, A. and Ltaief, H. and Dongarra, J.}, title = {Parallel Reduction to Condensed Forms for Symmetric Eigenvalue Problems using Aggregated Fine-Grained and Memory-Aware Kernels}, booktitle = {Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis (SC11)}, institution = {Innovative Computing Laboratory, University of Tennessee}, address = {Seattle, WA}, month = {November}, year = {2011} }
Dongarra, J., Faverge, M., Ltaief, H., Luszczek, P. "High Performance Matrix Inversion Based on LU Factorization for Multicore Architectures,"Proceedings of MTAGS11, Seattle, WA, November, 2011 [pdf] [bibtex]
@inproceedings{icl:658, author = {Dongarra, J. and Faverge, M. and Ltaief, H. and Luszczek, P.}, title = {High Performance Matrix Inversion Based on LU Factorization for Multicore Architectures}, booktitle = {Proceedings of MTAGS11}, institution = {Innovative Computing Laboratory, University of Tennessee}, address = {Seattle, WA}, month = {November}, year = {2011} }
Ltaief, H., Luszczek, P., Dongarra, J. "Profiling High Performance Dense Linear Algebra Algorithms on Multicore Architectures for Power and Energy Efficiency,"International Conference on Energy-Aware High Performance Computing (EnA-HPC 2011), Hamburg, Germany, September 7-9, 2011 [pdf] [bibtex]
@inproceedings{icl:621, author = {Ltaief, H. and Luszczek, P. and Dongarra, J.}, title = {Profiling High Performance Dense Linear Algebra Algorithms on Multicore Architectures for Power and Energy Efficiency}, booktitle = {International Conference on Energy-Aware High Performance Computing (EnA-HPC 2011)}, institution = {Innovative Computing Laboratory, University of Tennessee}, address = {Hamburg, Germany}, month = {September}, year = {2011} }
Dongarra, J., Faverge, M., Ltaief, H., Luszczek, P. "Achieving Numerical Accuracy and High Performance using Recursive Tile LU Factorization,"University of Tennessee Computer Science Technical Report (also as a LAWN), ICL-UT-11-08, September, 2011 [pdf] [bibtex]
@techreport{icl:660, author = {Dongarra, J. and Faverge, M. and Ltaief, H. and Luszczek, P.}, title = {Achieving Numerical Accuracy and High Performance using Recursive Tile LU Factorization}, booktitle = {University of Tennessee Computer Science Technical Report (also as a LAWN)}, institution = {Innovative Computing Laboratory, University of Tennessee}, month = {September}, year = {2011} }
Haidar, A., Ltaief, H., Dongarra, J. "Parallel Reduction to Condensed Forms for Symmetric Eigenvalue Problems using Aggregated Fine-Grained and Memory-Aware Kernels,"University of Tennessee Computer Science Technical Report, UT-CS-11-677, (also Lawn254), August 5, 2011 [pdf] [bibtex]
@techreport{icl:627, author = {Haidar, A. and Ltaief, H. and Dongarra, J.}, title = {Parallel Reduction to Condensed Forms for Symmetric Eigenvalue Problems using Aggregated Fine-Grained and Memory-Aware Kernels}, booktitle = {University of Tennessee Computer Science Technical Report, UT-CS-11-677, (also Lawn254)}, institution = {Innovative Computing Laboratory, University of Tennessee}, month = {August}, year = {2011} }
Ltaief, H., Luszczek, P., Dongarra, J. "High Performance Bidiagonal Reduction using Tile Algorithms on Homogeneous Multicore Architectures,"University of Tennessee Computer Science Technical Report, UT-CS-11-673, (also Lawn 247), May 18, 2011 [pdf] [bibtex]
@techreport{icl:629, author = {Ltaief, H. and Luszczek, P. and Dongarra, J.}, title = {High Performance Bidiagonal Reduction using Tile Algorithms on Homogeneous Multicore Architectures}, booktitle = {University of Tennessee Computer Science Technical Report, UT-CS-11-673, (also Lawn 247)}, institution = {Innovative Computing Laboratory, University of Tennessee}, month = {May}, year = {2011} }
Luszczek, P., Ltaief, H., Dongarra, J. "Two-stage Tridiagonal Reduction for Dense Symmetric Matrices using Tile Algorithms on Multicore Architectures,"IEEE International Parallel and Distributed Processing Symposium (submitted), Anchorage, AK, May 16-20, 2011 [bibtex]
@inproceedings{icl:592, author = {Luszczek, P. and Ltaief, H. and Dongarra, J.}, title = {Two-stage Tridiagonal Reduction for Dense Symmetric Matrices using Tile Algorithms on Multicore Architectures}, booktitle = {IEEE International Parallel and Distributed Processing Symposium (submitted)}, institution = {Innovative Computing Laboratory, University of Tennessee}, address = {Anchorage, AK}, month = {May}, year = {2011} }
Dongarra, J., Faverge, M., Ltaief, H., Luszczek, P. "Exploiting Fine-Grain Parallelism in Recursive LU Factorization,"Proceedings of PARCO'11, Gent, Belgium, ICL-UT-11-04, April, 2011 [bibtex]
@inproceedings{icl:611, author = {Dongarra, J. and Faverge, M. and Ltaief, H. and Luszczek, P.}, title = {Exploiting Fine-Grain Parallelism in Recursive LU Factorization}, booktitle = {Proceedings of PARCO'11}, institution = {Innovative Computing Laboratory, University of Tennessee}, address = {Gent, Belgium}, month = {April}, year = {2011} }
Haidar, A., Ltaief, H., YarKhan, A., Dongarra, J. "Analysis of Dynamically Scheduled Tile Algorithms for Dense Linear Algebra on Multicore Architectures,"University of Tennessee Computer Science Technical Report, UT-CS-11-666, (also Lawn 243), March 10, 2011 [bibtex]
@techreport{icl:631, author = {Haidar, A. and Ltaief, H. and YarKhan, A. and Dongarra, J.}, title = {Analysis of Dynamically Scheduled Tile Algorithms for Dense Linear Algebra on Multicore Architectures}, booktitle = {University of Tennessee Computer Science Technical Report, UT-CS-11-666, (also Lawn 243)}, institution = {Innovative Computing Laboratory, University of Tennessee}, month = {March}, year = {2011} }
Haidar, A., Ltaief, H., Dongarra, J. "Toward High Performance Divide and Conquer Eigensolver for Dense Symmetric Matrices.,"Submitted to SIAM Journal on Scientific Computing (SISC), 2011 [bibtex]
@article{icl:604, author = {Haidar, A. and Ltaief, H. and Dongarra, J.}, title = {Toward High Performance Divide and Conquer Eigensolver for Dense Symmetric Matrices.}, booktitle = {Submitted to SIAM Journal on Scientific Computing (SISC)}, institution = {Innovative Computing Laboratory, University of Tennessee}, year = {2011} }
Agullo, E., Augonnet, C., Dongarra, J., Ltaief, H., Namyst, R., Thibault, S., Tomov, S. "A Hybridization Methodology for High-Performance Linear Algebra Software for GPUs,"in GPU Computing Gems, Jade Edition, Hwu, W. eds. Elsevier, 2, 473-484, 2011 [bibtex]
@article{icl:653, author = {Agullo, E. and Augonnet, C. and Dongarra, J. and Ltaief, H. and Namyst, R. and Thibault, S. and Tomov, S.}, title = {A Hybridization Methodology for High-Performance Linear Algebra Software for GPUs}, booktitle = {in GPU Computing Gems, Jade Edition}, institution = {Innovative Computing Laboratory, University of Tennessee}, volume = {2}, pages = {473-484}, year = {2011} }
Song, F., Ltaief, H., Hadri, B., Dongarra, J. "Scalable Tile Communication-Avoiding QR Factorization on Multicore Cluster Systems,"SC'10, ACM SIGARCH/ IEEE Computer Society, New Orleans, LA, November 13-19, 2010 [pdf] [bibtex]
@article{icl:559, author = {Song, F. and Ltaief, H. and Hadri, B. and Dongarra, J.}, title = {Scalable Tile Communication-Avoiding QR Factorization on Multicore Cluster Systems}, booktitle = {SC'10}, institution = {Innovative Computing Laboratory, University of Tennessee}, address = {New Orleans, LA}, month = {November}, year = {2010} }
Haidar, A., Ltaief, H., YarKhan, A., Dongarra, J. "Analysis of Dynamically Scheduled Tile Algorithms for Dense Linear Algebra on Multicore Architectures,"Submitted to Concurrency and Computations: Practice and Experience, November 3, 2010 [pdf] [bibtex]
@article{icl:533, author = {Haidar, A. and Ltaief, H. and YarKhan, A. and Dongarra, J.}, title = {Analysis of Dynamically Scheduled Tile Algorithms for Dense Linear Algebra on Multicore Architectures}, booktitle = {Submitted to Concurrency and Computations: Practice and Experience}, institution = {Innovative Computing Laboratory, University of Tennessee}, month = {November}, year = {2010} }
Agullo, E., Augonnet, C., Dongarra, J., Faverge, M., Ltaief, H., Thibault, S., Tomov, S. "QR Factorization on a Multicore Node Enhanced with Multiple GPU Accelerators,"Proceedings of IPDPS 2011, Anchorage, AK, ICL-UT-10-04, October 1, 2010 [pdf] [bibtex]
@inproceedings{icl:577, author = {Agullo, E. and Augonnet, C. and Dongarra, J. and Faverge, M. and Ltaief, H. and Thibault, S. and Tomov, S.}, title = {QR Factorization on a Multicore Node Enhanced with Multiple GPU Accelerators}, booktitle = {Proceedings of IPDPS 2011}, institution = {Innovative Computing Laboratory, University of Tennessee}, address = {Anchorage, AK}, month = {October}, year = {2010} }
Bosilca, G., Bouteiller, A., Danalis, A., Faverge, M., Haidar, H., Herault, T., Kurzak, J., Langou, J., Lemariner, P., Ltaief, H., Luszczek, P., YarKhan, A., Dongarra, J. "Distributed Dense Numerical Linear Algebra Algorithms on Massively Parallel Architectures: DPLASMA,"University of Tennessee Computer Science Technical Report, UT-CS-10-660, Sept. 15, 2010 [pdf] [bibtex]
@techreport{icl:563, author = {Bosilca, G. and Bouteiller, A. and Danalis, A. and Faverge, M. and Haidar, H. and Herault, T. and Kurzak, J. and Langou, J. and Lemariner, P. and Ltaief, H. and Luszczek, P. and YarKhan, A. and Dongarra, J.}, title = {Distributed Dense Numerical Linear Algebra Algorithms on Massively Parallel Architectures: DPLASMA}, booktitle = {University of Tennessee Computer Science Technical Report, UT-CS-10-660}, institution = {Innovative Computing Laboratory, University of Tennessee}, month = {Sept}, year = {2010} }
Ltaief, H., Tomov, S., Nath, R., Du, P., Dongarra, J. "A Scalable High Performant Cholesky Factorization for Multicore with GPU Accelerators,"Proc. of VECPAR'10 (to appear), Berkeley, CA, June 22-25, 2010 [pdf] [bibtex]
@article{icl:521, author = {Ltaief, H. and Tomov, S. and Nath, R. and Du, P. and Dongarra, J.}, title = {A Scalable High Performant Cholesky Factorization for Multicore with GPU Accelerators}, booktitle = {Proc. of VECPAR'10 (to appear)}, institution = {Innovative Computing Laboratory, University of Tennessee}, address = {Berkeley, CA}, month = {June}, year = {2010} }
Song, F., Ltaief, H., Hadri, B., Dongarra, J. "Scalable Tile Communication-Avoiding QR Factorization on Multicore Cluster Systems,"University of Tennessee Computer Science Technical Report, UT-CS-10-653, April, 2010 [pdf] [bibtex]
@techreport{icl:530, author = {Song, F. and Ltaief, H. and Hadri, B. and Dongarra, J.}, title = {Scalable Tile Communication-Avoiding QR Factorization on Multicore Cluster Systems}, booktitle = {University of Tennessee Computer Science Technical Report}, institution = {Innovative Computing Laboratory, University of Tennessee}, volume = {UT-CS-10-653}, month = {April}, year = {2010} }
Ltaief, H., Kurzak, J., Dongarra, J. "Parallel Band Two-Sided Matrix Bidiagonalization for Multicore Architectures,"IEEE Transactions on Parallel and Distributed Systems, pp. 417-423, April, 2010 [pdf] [bibtex]
@article{icl:569, author = {Ltaief, H. and Kurzak, J. and Dongarra, J.}, title = {Parallel Band Two-Sided Matrix Bidiagonalization for Multicore Architectures}, booktitle = {IEEE Transactions on Parallel and Distributed Systems}, institution = {Innovative Computing Laboratory, University of Tennessee}, pages = {pp. 417-423}, month = {April}, year = {2010} }
Ltaief, H., Tomov, S., Nath, R., Dongarra, J. "Hybrid Multicore Cholesky Factorization with Multiple GPU Accelerators,"IEEE Transaction on Parallel and Distributed Systems (submitted), March 26, 2010 [pdf] [bibtex]
@article{icl:526, author = {Ltaief, H. and Tomov, S. and Nath, R. and Dongarra, J.}, title = {Hybrid Multicore Cholesky Factorization with Multiple GPU Accelerators}, booktitle = {IEEE Transaction on Parallel and Distributed Systems (submitted)}, institution = {Innovative Computing Laboratory, University of Tennessee}, month = {March}, year = {2010} }
Tomov, S., Nath, R., Ltaief, H., Dongarra, J. "Dense Linear Algebra Solvers for Multicore with GPU Accelerators,"Proc. of IPDPS'10, Atlanta, GA, January 15, 2010 [pdf] [bibtex]
@article{icl:523, author = {Tomov, S. and Nath, R. and Ltaief, H. and Dongarra, J.}, title = {Dense Linear Algebra Solvers for Multicore with GPU Accelerators}, booktitle = {Proc. of IPDPS'10}, institution = {Innovative Computing Laboratory, University of Tennessee}, address = {Atlanta, GA}, month = {January}, year = {2010} }
Kurzak, J., Ltaief, H., Dongarra, J., Badia, R. "Scheduling Dense Linear Algebra Operations on Multicore Processors,"Concurrency and Computation: Practice and Experience, Vol. 22, no. 1, pp. 15-44, January, 2010 [pdf] [bibtex]
@article{icl:540, author = {Kurzak, J. and Ltaief, H. and Dongarra, J. and Badia, R.}, title = {Scheduling Dense Linear Algebra Operations on Multicore Processors}, booktitle = {Concurrency and Computation: Practice and Experience}, institution = {Innovative Computing Laboratory, University of Tennessee}, volume = {Vol. 22, no. 1}, pages = {pp. 15-44}, month = {January}, year = {2010} }
Ltaief, H., Kurzak, J., Dongarra, J., M. Badia, R. "Scheduling Two-sided Transformations using Tile Algorithms on Multicore Architectures,"Journal of Scientific Computing, Vol. 18, No. 1, pp. 33-50, 2010 [pdf] [bibtex]
@article{icl:473, author = {Ltaief, H. and Kurzak, J. and Dongarra, J. and M. Badia, R.}, title = {Scheduling Two-sided Transformations using Tile Algorithms on Multicore Architectures}, booktitle = {Journal of Scientific Computing}, institution = {Innovative Computing Laboratory, University of Tennessee}, volume = {Vol. 18, No. 1}, pages = {pp. 33-50}, year = {2010} }
Bosilca, G., Bouteiller, A., Danalis, A, Faverge, M., Haidar, A., Herault, T., Kurzak, J., Langou, J., Lemarinier, P., Ltaief, H., Luszczek, P., YarKhan, A., Dongarra, J. "Distributed-Memory Task Execution and Dependence Tracking within DAGuE and the DPLASMA Project,"Innovative Computing Laboratory Technical Report, ICL-UT-10-02, 2010 [pdf] [bibtex]
@techreport{icl:529, author = {Bosilca, G. and Bouteiller, A. and Danalis, A, Faverge, M. and Haidar, A. and Herault, T. and Kurzak, J. and Langou, J. and Lemarinier, P. and Ltaief, H. and Luszczek, P. and YarKhan, A. and Dongarra, J.}, title = {Distributed-Memory Task Execution and Dependence Tracking within DAGuE and the DPLASMA Project}, booktitle = {Innovative Computing Laboratory Technical Report}, institution = {Innovative Computing Laboratory, University of Tennessee}, year = {2010} }
Agullo, E., Augonnet, C., Dongarra, J., Ltaief, H., Namyst, R., Thibault, S., and Tomov, S. "Faster, Cheaper, Better - a Hybridization Methodology to Develop Linear Algebra Software for GPUs,"LAPACK Working Note 230, 2010 [pdf] [bibtex]
@article{icl:585, author = {Agullo, E. and Augonnet, C. and Dongarra, J. and Ltaief, H. and Namyst, R. and Thibault, S. and and Tomov, S.}, title = {Faster, Cheaper, Better - a Hybridization Methodology to Develop Linear Algebra Software for GPUs}, booktitle = {LAPACK Working Note 230}, institution = {Innovative Computing Laboratory, University of Tennessee}, year = {2010} }
Hadri, B., Ltaief, H., Agullo, E., Dongarra, J. "Enhancing Parallelism of Tile QR Factorization for Multicore Architectures,"Submitted to Transaction on Parallel and Distributed Systems, December, 2009 [pdf] [bibtex]
@article{icl:524, author = {Hadri, B. and Ltaief, H. and Agullo, E. and Dongarra, J.}, title = {Enhancing Parallelism of Tile QR Factorization for Multicore Architectures}, booktitle = {Submitted to Transaction on Parallel and Distributed Systems}, institution = {Innovative Computing Laboratory, University of Tennessee}, month = {December}, year = {2009} }
Hadri, B., Ltaief, H., Agullo, E., Dongarra, J. "Tile QR Factorization with Parallel Panel Processing for Multicore Architectures,"accepted in 24th IEEE International Parallel and Distributed Processing Symposium (IPDPS 2010), Atlanta, GA, December, 2009 [pdf] [bibtex]
@inproceedings{icl:522, author = {Hadri, B. and Ltaief, H. and Agullo, E. and Dongarra, J.}, title = {Tile QR Factorization with Parallel Panel Processing for Multicore Architectures}, booktitle = {accepted in 24th IEEE International Parallel and Distributed Processing Symposium (IPDPS 2010)}, institution = {Innovative Computing Laboratory, University of Tennessee}, address = {Atlanta, GA}, month = {December}, year = {2009} }
Hadri, B., Ltaief, H., Agullo, E., Dongarra, J. "Tall and Skinny QR Matrix Factorization Using Tile Algorithms on Multicore Architectures,"Innovative Computing Laboratory Technical Report (also LAPACK Working Note 222 and CS Tech Report UT-CS-09-645), ICL-UT-09-03, September 4, 2009 [pdf] [bibtex]
@techreport{icl:487, author = {Hadri, B. and Ltaief, H. and Agullo, E. and Dongarra, J.}, title = {Tall and Skinny QR Matrix Factorization Using Tile Algorithms on Multicore Architectures}, booktitle = {Innovative Computing Laboratory Technical Report (also LAPACK Working Note 222 and CS Tech Report UT-CS-09-645)}, institution = {Innovative Computing Laboratory, University of Tennessee}, month = {September}, year = {2009} }
Kurzak, J., Ltaief, H., Dongarra, J., Badia, R. "Dependency-Driven Scheduling of Dense Matrix Factorizations on Shared-Memory Systems,"PPAM 2009, Poland, September, 2009 [bibtex]
@article{icl:518, author = {Kurzak, J. and Ltaief, H. and Dongarra, J. and Badia, R.}, title = {Dependency-Driven Scheduling of Dense Matrix Factorizations on Shared-Memory Systems}, booktitle = {PPAM 2009}, institution = {Innovative Computing Laboratory, University of Tennessee}, address = {Poland}, month = {September}, year = {2009} }
Ltaief, H., Kurzak, J., Dongarra, J. "Parallel Band Two-Sided Matrix Bidiagonalization for Multicore Architectures,"IEEE Transactions on Parallel and Distributed Systems (to appear), May, 2009 [pdf] [bibtex]
@article{icl:489, author = {Ltaief, H. and Kurzak, J. and Dongarra, J.}, title = {Parallel Band Two-Sided Matrix Bidiagonalization for Multicore Architectures}, booktitle = {IEEE Transactions on Parallel and Distributed Systems (to appear)}, institution = {Innovative Computing Laboratory, University of Tennessee}, month = {May}, year = {2009} }
Agullo, E., Demmel, J., Dongarra, J., Hadri, B., Kurzak, J., Langou, J., Ltaief, H., Luszczek, P., Tomov, S. "Numerical linear algebra on emerging architectures: The PLASMA and MAGMA projects,"Journal of Physics: Conference Series, Vol. 180, 2009 [pdf] [bibtex]
@inproceedings{icl:486, author = {Agullo, E. and Demmel, J. and Dongarra, J. and Hadri, B. and Kurzak, J. and Langou, J. and Ltaief, H. and Luszczek, P. and Tomov, S.}, title = {Numerical linear algebra on emerging architectures: The PLASMA and MAGMA projects}, booktitle = {Journal of Physics: Conference Series}, institution = {Innovative Computing Laboratory, University of Tennessee}, volume = {Vol. 180}, year = {2009} }
Agullo, E., Hadri, B., Ltaief, H., Dongarra, J. "Comparative Study of One-Sided Factorizations with Multiple Software Packages on Multi-Core Hardware,"2009 International Conference for High Performance Computing, Networking, Storage, and Analysis (SC '09) (to appear), 2009 [pdf] [bibtex]
@inproceedings{icl:488, author = {Agullo, E. and Hadri, B. and Ltaief, H. and Dongarra, J.}, title = {Comparative Study of One-Sided Factorizations with Multiple Software Packages on Multi-Core Hardware}, booktitle = {2009 International Conference for High Performance Computing, Networking, Storage, and Analysis (SC '09) (to appear)}, institution = {Innovative Computing Laboratory, University of Tennessee}, year = {2009} }
Kurzak, J., Ltaief, H., Dongarra, J., Badia, R. "Scheduling Linear Algebra Operations on Multicore Processors,"University of Tennessee Computer Science Department Technical Report, UT-CS-09-636 (Also LAPACK Working Note 213), 2009 [pdf] [bibtex]
@techreport{icl:495, author = {Kurzak, J. and Ltaief, H. and Dongarra, J. and Badia, R.}, title = {Scheduling Linear Algebra Operations on Multicore Processors}, booktitle = {University of Tennessee Computer Science Department Technical Report, UT-CS-09-636 (Also LAPACK Working Note 213)}, institution = {Innovative Computing Laboratory, University of Tennessee}, year = {2009} }
Kurzak, J., Ltaief, H., Dongarra, J., Badia, R. "Scheduling Linear Algebra Operations on Multicore Processors,"Concurrency Practice and Experience (to appear), 2009 [bibtex]
@article{icl:510, author = {Kurzak, J. and Ltaief, H. and Dongarra, J. and Badia, R.}, title = {Scheduling Linear Algebra Operations on Multicore Processors}, booktitle = {Concurrency Practice and Experience (to appear)}, institution = {Innovative Computing Laboratory, University of Tennessee}, year = {2009} }
Ltaief, H., Kurzak, J., Dongarra., J. "Parallel Block Hessenberg Reduction using Algorithms-By-Tiles for Multicore Architectures Revisited,"University of Tennessee Computer Science Technical Report, UT-CS-08-624 (also LAPACK Working Note 208), August 7, 2008 [pdf] [bibtex]
@techreport{icl:431, author = {Ltaief, H. and Kurzak, J. and Dongarra. and J.}, title = {Parallel Block Hessenberg Reduction using Algorithms-By-Tiles for Multicore Architectures Revisited}, booktitle = {University of Tennessee Computer Science Technical Report, UT-CS-08-624 (also LAPACK Working Note 208)}, institution = {Innovative Computing Laboratory, University of Tennessee}, month = {August}, year = {2008} }