[Date Prev][Date Next] [Thread Prev][Thread Next] [Date Index] [Thread Index]

Bug#875654: marked as done (ITP: superlu-dist -- Highly distributed solution of large, sparse systems of linear equations)

Your message dated Wed, 13 Sep 2017 04:19:59 +0000
with message-id <E1drz9b-0001O9-PP@quantz.debian.org>
and subject line closing ITP: superlu-dist -- Highly distributed solution of large, sparse systems of linear equations
has caused the Debian Bug report #875654,
regarding ITP: superlu-dist -- Highly distributed solution of large, sparse systems of linear equations
to be marked as done.

This means that you claim that the problem has been dealt with.
If this is not the case it is now your responsibility to reopen the
Bug report if necessary, and/or fix the problem forthwith.

(NB: If you are a system administrator and have no idea what this
message is talking about, this may indicate a serious mail system
misconfiguration somewhere. Please contact owner@bugs.debian.org
immediately.)


-- 
875654: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=875654
Debian Bug Tracking System
Contact owner@bugs.debian.org with problems
--- Begin Message --- 
Package: wnpp
Severity: wishlist
Owner: Drew Parsons <dparsons@debian.org>

* Package name    : superlu-dist
  Version         : 5.1.3
  Upstream Author : Xiaoye S. Li <xsli@lbl.gov>
* URL             : http://crd-legacy.lbl.gov/~xiaoye/SuperLU/#superlu_dist
* License         : BSD
  Programming Lang: C
  Description     : Highly distributed solution of large, sparse systems of linear equations

SuperLU is a general purpose library for the direct solution of large,
sparse, nonsymmetric systems of linear equations. The library is
written in C and is callable from either C or Fortran program. It uses
MPI, OpenMP and CUDA to support various forms of parallelism. It
supports both real and complex datatypes, both single and double
precision, and 64-bit integer indexing. The library routines performs
an LU decomposition with partial pivoting and triangular system solves
through forward and back substitution. The LU factorization routines
can handle non-square matrices but the triangular solves are performed
only for square matrices. The matrix columns may be preordered (before
factorization) either through library or user supplied routines. This
preordering for sparsity is completely separate from the
factorization. Working precision iterative refinement subroutines are
provided for improved backward stability. Routines are also provided
to equilibrate the system, estimate the condition number, calculate
the relative backward error, and estimate error bounds for the refined
solutions. 

SuperLU_DIST implements the algorithms for distributed memory,
targetting highly parallel distributed memory hybrid systems. The
numerical factorization routines are already implemented for hybrid
systems with multiple GPUs. Further work will be needed to implement
the other phases of the algorithms on the hybrid systems and to
enhance strong scaling to extreme scale. 

This package will be maintained under the Debian Science team.
superlu-dist complements the existing superlu package, which is the
sequential implementation of SuperLU.

SuperLU_DIST is used by PETSc and FEniCS for numerical computation.

--- End Message ---
--- Begin Message --- 
Please retitle bug 735679 from RFP to ITP and set yourself as the owner.

--- End Message ---
Reply to: