Paper Info
Title
PyTrilinos: High-performance distributed-memory solvers for Python
Abstract
PyTrilinos is a collection of Python modules that are useful for serial and parallel scientific computing. This collection contains modules that cover serial and parallel dense linear algebra, serial and parallel sparse linear algebra, direct and iterative linear solution techniques, domain decomposition and multilevel preconditioners, nonlinear solvers, and continuation algorithms. Also included are a variety of related utility functions and classes, including distributed I/O, coloring algorithms, and matrix generation. PyTrilinos vector objects are integrated with the popular NumPy Python module, gathering together a variety of high-level distributed computing operations with serial vector operations. PyTrilinos is a set of interfaces to existing, compiled libraries. This hybrid framework uses Python as front-end, and efficient precompiled libraries for all computationally expensive tasks. Thus, we take advantage of both the flexibility and ease of use of Python, and the efficiency of the underlying C++, C, and FORTRAN numerical kernels. Out numerical results show that, for many important problem classes, the overhead required by the Python interpreter is negligible. To run in parallel, PyTrilinos simply requires a standard Python interpreter. The fundamental MPI calls are encapsulated under an abstract layer that manages all interprocessor communications. This makes serial and parallel scripts using PyTrilinos virtually identical.
Year
DOI
Venue
2006
10.1145/1326548.1326549
ACM Transactions on Mathematical Software (TOMS)
Keywords
DocType
Volume
nonlinear solvers,script languages,underlying c,serial vector operation,popular numpy python module,standard python interpreter,iterative linear solution technique,high-performance distributed-memory solvers,object-oriented programming,computational engine,fortran numerical kernel,python interpreter,pytrilinos vector object,multilevel preconditioners,parallel sparse linear algebra,coloring algorithm,parallel dense linear algebra,numerical result,python module,parallel script,direct solvers,parallel scientific computing,scripting language,front end,linear algebra,ease of use,distributed memory,object oriented programming,distributed computing
Conference
34
Issue
ISSN
ISBN
2
0098-3500
3-540-75754-6
Citations 
PageRank 
References 
7
0.62
9
Authors
3
Name
Order
Citations
PageRank
Marzio Sala1737.89
William F. Spotz2263.37
Michael A. Heroux397469.20