@InProceedings{toledo:solar,
  author = {Sivan Toledo and Fred G. Gustavson},
  title = {The Design and Implementation of {SOLAR}, a Portable Library for
  Scalable Out-of-Core Linear Algebra Computations},
  booktitle = {Proceedings of the Fourth Workshop on Input/Output in Parallel
  and Distributed Systems},
  year = {1996},
  month = {May},
  pages = {28--40},
  publisher = {ACM Press},
  address = {Philadelphia},
  keywords = {parallel I/O, out-of-core, linear algebra, pario-bib},
  abstract = {SOLAR is a portable high-performance library for out-of-core
  dense matrix computations. It combines portability with high performance by
  using existing high-performance in-core subroutine libraries and by using an
  optimized matrix input-output library. SOLAR works on parallel computers,
  workstations, and personal computers. It supports in-core computations on
  both shared-memory and distributed-memory machines, and its matrix
  input-output library supports both conventional I/O interfaces and parallel
  I/O interfaces. This paper discusses the overall design of SOLAR, its
  interfaces, and the design of several important subroutines. Experimental
  results show that SOLAR can factor on a single workstation an out-of-core
  positive-definite symmetric matrix at a rate exceeding 215 Mflops, and an
  out-of-core general matrix at a rate exceeding 195 Mflops. Less than 16\% of
  the running time is spent on I/O in these computations. These results
  indicate that SOLAR's portability does not compromise its performance. We
  expect that the combination of portability, modularity, and the use of a
  high-level I/O interface will make the library an important platform for
  research on out-of-core algorithms and on parallel I/O.},
  comment = {Sounds great. Library package that supports LAPACK-like
  functionality on in-core and out-of-core matrices. Good performance. Good
  portability (IBM workstation, IBM SP-2, and OS/2 laptop). They separate the
  matrix algorithms from the underlying I/O routines in an interesting way
  (read and write submatrices), leaving just enough information to allow the
  I/O system to do some higher-level optimizations.}
}