% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@INPROCEEDINGS{DiNapoli:127961,
      author       = {Di Napoli, Edoardo and Berljafa, Mario},
      title        = {{P}arallel block {C}hebyshev subspace iteration algorithm
                      optimized for sequences of correlated dense eigenproblems},
      reportid     = {FZJ-2012-00907},
      year         = {2012},
      abstract     = {In many material science applications simulations are made
                      of dozens of sequences, where each sequence groups together
                      eigenproblems with increasing self-consistent cycle
                      outer-iteration index. Successive eigenproblems in a
                      sequence possess a high degree of correlation. In particular
                      it has been demonstrated that eigenvectors of adjacent
                      eigenproblems become progressively more collinear to each
                      other as the outer-iteration index increases. This result
                      suggests one could use eigenvectors, computed at a certain
                      outer-iteration, as approximate solutions to improve the
                      performance of the eigensolver at the next one. In order to
                      opti- mally exploit the approximate solution, we developed a
                      block iterative eigensolver augmented with a Chebyshev
                      polynomial accelerator (BChFSI). Numerical tests show that,
                      when the sequential version of the solver is fed approximate
                      solutions instead of random vectors, it achieves up to a 5X
                      speedup. Moreover the parallel shared memory implementation
                      of the algorithm obtains a high level of efficiency up to 80
                      $\\%$ of the theoretical peak performance. Despite the
                      eigenproblems in the sequence being relatively large and
                      dense, the parallel BChFSI fed with ap- proximate solutions
                      performs substantially better than the corresponding direct
                      eigensolver, even for a significant portion of the
                      sought-after spectrum},
      month         = {Dec},
      date          = {2012-12-02},
      organization  = {5th International Conference of the
                       ERCIM Working Group, Oviedo (Spain), 2
                       Dec 2012 - 2 Dec 2012},
      subtyp        = {Other},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {411 - Computational Science and Mathematical Methods
                      (POF2-411) / Simulation and Data Laboratory Quantum
                      Materials (SDLQM) (SDLQM)},
      pid          = {G:(DE-HGF)POF2-411 / G:(DE-Juel1)SDLQM},
      typ          = {PUB:(DE-HGF)6},
      url          = {https://juser.fz-juelich.de/record/127961},
}