Publications describing the structure of the PSBLAS: Parallel Sparse BLAS, the library at the core of the psctoolkit

  1. Filippone, Salvatore; Buttari, Alfredo. Object-Oriented Techniques for Sparse Matrix Computations in Fortran 2003, ACM Trans. on Math. Software, vol. 38, No. 4, 2012.
  2. Filippone, Salvatore; Colajanni, Michele. PSBLAS: A library for parallel linear algebra computation on sparse matrices, ACM Trans. on Math. Software, 26(4), Dec. 2000, pp. 527-550.


This package was previously known as MLD2P4, these are the publication relative to its architecture and the preconditioner that implements.

  1. D’Ambra, Pasqua, Fabio Durastante, and Salvatore Filippone. “AMG preconditioners for linear solvers towards extreme scale.” SIAM Journal on Scientific Computing 43(5), S679–S703.
  2. D’Ambra, Pasqua; di Serafino, Daniela; Filippone, Salvatore. MLD2P4: a package of parallel algebraic multilevel domain decomposition preconditioners in Fortran 95. ACM Trans. Math. Software 37 (2010), no. 3, Art. 30, 23 pp.
  3. D’Ambra, Pasqua; di Serafino, Daniela; Filippone, Salvatore. On the development of PSBLAS-based parallel two-level Schwarz preconditioners. Appl. Numer. Math. 57 (2007), no. 11-12, 1181–1196.
  4. Buttari, Alfredo; D’Ambra, Pasqua; di Serafino, Daniela; Filippone, Salvatore. 2LEV-D2P4: a package of high-performance preconditioners for scientific and engineering applications. Appl. Algebra Engrg. Comm. Comput. 18 (2007), no. 3, 223–239.
  5. Buttari, Alfredo; D’Ambra, Pasqua; di Serafino, Daniela; Filippone, Salvatore. Extending PSBLAS to Build Parallel Schwarz Preconditioners, in Proc. of PARA’04, State of the Art in Scientific Computing, J. Dongarra, K. Madsen, J. Wasniewsky eds., LNCS series, Vol. 3732, 2005, pp. 593-602.

Methodologies, Theoretical and Technical Challenges

A part from the papers describing the implementation and the features of the libraries, a great deal of work is dedicated to answering theoretical questions, develop new algorithms, and solve technical and technological challenges. We collect here works related to these tasks.

  1. D’Ambra Pasqua; Durastante, Fabio; Ferdous, S.M.; Filippone, Salvatore; Halappanavar, Mahantesh; Pothen, Alex. AMG Preconditioners based on Parallel Hybrid Coarsening and Multi-objective Graph Matching. (2023). 31st Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP), Naples, Italy, 2023, pp. 59-67.
  2. Bernaschi, Massimo; Pasqua D’Ambra; Dario Pasquini. BootCMatchG: An adaptive Algebraic MultiGrid linear solver for GPUs. Software Impacts (2020): 100041.
  3. D’Ambra, Pasqua; Durastante, Fabio; Filippone, Salvatore; Zikatanov Ludmil. Automatic coarsening in Algebraic Multigrid utilizing quality measures for matching-based aggregations. Comput. Math. Appl. 144 (2023), 290-305.
  4. Abdullahi Hassan, Ambra; Cardellini, Valeria; D’Ambra, Pasqua; di Serafino, Daniela; Filippone, Salvatore. “Efficient algebraic multigrid preconditioners on clusters of GPUs.” Parallel Processing Letters 29.01 (2019): 1950001.
  5. Filippone, Salvatore; Cardellini, Valeria; Barbieri, Davide; Fanfarillo, Alessandro. Sparse matrix-vector multiplication on GPGPUs. ACM Trans. Math. Software 43 (2017), no. 4, Art. 30.
  6. D’Ambra, Pasqua; Filippone, Salvatore; Vassilevski, Panayot S. BootCMatch: a software package for bootstrap AMG based on graph weighted matching. ACM Trans. Math. Software 44 (2018), no. 4, Art. 39, 25 pp.
  7. Bertaccini, Daniele; Filippone, Salvatore. Sparse approximate inverse preconditioners on high performance GPU platforms. Comput. Math. Appl. 71 (2016), no. 3, 693–711.
  8. Barbieri, Domenico; Cardellini, Valeria; Filippone, Salvatore; Rouson, Damian. (2011, August). Design patterns for scientific computations on sparse matrices. In European Conference on Parallel Processing (pp. 367-376). Springer, Berlin, Heidelberg.
  9. Cardellini, Valeria; Filippone, Salvatore; Rouson, Damian. Design Patterns for sparse-matrix computations on hybrid CPU/GPU platforms, Scientific Programming, 22(2014), pp.1-19.
  10. D’Ambra, Pasqua; Vassilevski, Panayot, S. Adaptive AMG with Coarsening based on Compatible Weighted Matching, Computing and Visualization in Science, Vol. 16, 2013, pp. 59-76.

psctoolkit in the field

This is a list of works that used the libraries from psctoolkit, if you have a work in which you use one of the libraries please let us know

  1. Bertaccini, D, D’Ambra, P, Durastante, F, Filippone, S. Why diffusion-based preconditioning of Richards equation works: Spectral analysis and computational experiments at very large scale. Numer Linear Algebra Appl. 2023;e2523. Open Access
  2. D’Ambra, Pasqua; Filippone, Salvatore. A parallel generalized relaxation method for high-performance image segmentation on GPUs. J. Comput. Appl. Math. 293 (2016), 35–44.
  3. Aprovitola, Andrea; D’Ambra, Pasqua; Denaro, Filippo M.; di Serafino, Daniela; Filippone, Salvatore. SParC-LES: enabling large eddy simulations with parallel sparse matrix computation tools. Comput. Math. Appl. 70 (2015), no. 11, 2688–2700.
  4. D’Ambra, Pasqua; di Serafino, Daniela; Filippone, Salvatore. Performance analysis of parallel Schwarz preconditioners in the LES of turbulent channel flows. Comput. Math. Appl. 65 (2013), no. 3, 352–361.
  5. Borzì, Alfio; De Simone, Valentina; di Serafino, Daniela. Parallel algebraic multilevel Schwarz preconditioners for a class of elliptic PDE systems. Comput. Vis. Sci. 16 (2013), no. 1, 1–14.
  6. Marian, V. G., Gabriel, D., Knoll, G., Filippone, S. (2011). Theoretical and experimental analysis of a laser textured thrust bearing. Tribology letters, 44(3), 335.
  7. Aprovitola, Andrea; D’Ambra, Pasqua; Denaro, Filippo; di Serafino, Daniela; Filippone, Salvatore. Scalable algebraic multilevel preconditioners with application to CFD. Parallel computational fluid dynamics 2008, 15–27, Lect. Notes Comput. Sci. Eng., 74, Springer, Heidelberg, 2010.