Release date: 06/16.

This material is based upon work supported by the National Science Foundation and the Department of Energy under Grant No. NSF-OCI-1032861, NSF-CCF-00444486, NSF-CNS 0325873, NSF-EIA 0122599, NSF-ACI-0090127, DOE-DE-FC02-01ER25478, DOE-DE-FC02-06ER25768.

LAPACK is a software package provided by Univ. of Tennessee, Univ. of California, Berkeley, Univ. of Colorado Denver and NAG Ltd..

1. Support and questions:

2. Thanks

Thanks for bug-report/patches/suggestions to:

Forum users:

3. LAPACK 3.6.1: What’s new

  • [Mark Gates, UTK] blocked back-transformation for the non-symmetric eigenvalue problem

It blocks NB gemv calls into one gemm call inside trevc. To do that, it needs a new routine, trevc3, because unfortunately the lwork was not passed into trevc. Attached is the performance speedup for dgeev. It gives a nice 1.5x speedup for N=20000, and that appears to still be increasing with N. This is not the improvements that Greg Henry recently provided for doing the triangular solves as BLAS-3 instead of BLAS-1. That will take a while to process, but we expect another, even larger increase in performance when those changes are applied. This also does not include doing multiple (BLAS-1) triangular solves in parallel, which is available in MAGMA, since that requires OpenMP or pthreads.

Added:

SRC/strevc3.f
SRC/dtrevc3.f
SRC/ctrevc3.f
SRC/ztrevc3.f

Modified:

SRC/sgeev.f
SRC/dgeev.f
SRC/cgeev.f
SRC/zgeev.f
SRC/sgeevx.f
SRC/dgeevx.f
SRC/cgeevx.f
SRC/zgeevx.f

3. External Contributors

4. Thanks

  • Edward Smyth (NAG): r1683, r1684

  • Tim Hopkins (University of Kent): r1734, r1735, r1764, r1765, r1766, r1764, r1765, r1766

  • Eugene Chereshnev (Intel): r1670, r1737, r1759, r1760, r1761, r1762, r1763

  • Dmitry Baksheev (Intel): r1686, r1687, r1689-r1730

  • Alex Zotkevich (Intel): r1755, r1756, r1757, r1758

  • Nathan Whitehead: r1740, r1742, r1744

  • Lawrence Mulholland (NAG): r1649, r1654, r1655, r1656, r1688, r1746

  • Orion Poplawski (NWRA): r1653, r1751, r1754

  • Vladimir Chalupecky: r1752

  • Pavel Holoborodko: r1648

  • Julien Schueller: r1650, r1651, r1748, r1749

  • Mathieu Faverge: r1658, r1662, r1663

  • Martin Köhler Max Planck Institute for Dynamics of Complex Technical Systems): r1660

  • Tracey Brendan: r1667, r1668

  • Andreas Noack (MIT): 1669

  • Berend Hasselman: r1671

  • Sébastien Villemot: r1672, r1733

  • Christoph Conrads: r1673

  • Elena Ivanova (Oracle): r1674, r1675, r1676

  • David Vowles: r1677, r1679

  • Viswanathan Elumalai (University of Pittsburgh): r1681

  • Mark Gates: r1739, r1750

  • nathanw: r1740

  • Nathan Whitehead: r1742, r1744

5. Developer list

Principal Investigators
  • Jim Demmel (University of California, Berkeley, USA)

  • Jack Dongarra (University of Tennessee and ORNL, USA)

  • Julien Langou (University of Colorado Denver, USA)

LAPACK developers involved in this release
  • Julie Langou (University of Tennessee, USA)

  • Osni Marques (University of California, Berkeley, USA)

  • Lawrence Mulholland (NAG Ltd.)

  • Mark Gates (University of Tennessee, USA)

  • Igor Kozachenko (University of California, Berkeley, USA)

6. More details

7. Bug Fix