PBLAS

From HandWiki
Revision as of 16:54, 6 February 2024 by Rtextdoc (talk | contribs) (simplify)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

Parallel Basic Linear Algebra Subprograms (PBLAS) is an implementation of Level 2 and 3 BLAS intended for distributed memory architectures.[1] It provides a computational backbone for ScaLAPACK, a parallel implementation of LAPACK. It depends on Level 1 sequential BLAS operations for local computation and BLACS for communication between nodes.[2][3]

References

  1. Choi, Jaeyoung; Dongarra, Jack; Ostrouchov, Susan; Petitet, Antoine; Walker, David; Whaley, R. Clinton (1996). "A proposal for a set of parallel basic linear algebra subprograms". Applied Parallel Computing Computations in Physics, Chemistry and Engineering Science. Lecture Notes in Computer Science. 1041. pp. 107. doi:10.1007/3-540-60902-4_13. ISBN 978-3-540-60902-5. 
  2. Petitet, Antoine (1995). "PBLAS". Netlib. http://www.netlib.org/utk/papers/scalapack/node9.html. Retrieved 13 July 2012. 
  3. Jaeyoung Choi; Dongarra, J.J.; Walker, D.W. (May 1994). "PB-BLAS: A set of Parallel Block Basic Linear Algebra Subprograms". Proceedings of IEEE Scalable High Performance Computing Conference. pp. 534–541. doi:10.1109/SHPCC.1994.296688. ISBN 0-8186-5680-8. http://www.netlib.org/utk/people/JackDongarra/journals/079_1996_pb-blas-a-set-of-parallel-block-basic-linear-algebra-subroutines.pdf.