Parallel Colt

Parallel Colt

Original author(s)	Piotr Wendykier
Stable release	0.9.4 / March 21, 2010 (2010-03-21)
Operating system	Cross-platform
Type	Library
License	Various
Website	sites.google.com/site/piotrwendykier/software/parallelcolt

Parallel Colt is a set of multithreaded version of Colt. It is a collection of open-source libraries for High Performance Scientific and Technical Computing written in Java. It contains all the original capabilities of Colt and adds several new ones, with a focus on multi-threaded algorithms.

Capabilities

Parallel Colt has all the capabilities of the original Colt library, with the following additions. ^[1]

• Multithreading
• Specialized Matrix data structures
• JPlasma
  • Java port of PLASMA (Parallel Linear Algebra for Scalable Multi-core Architectures).
• CSparseJ
  • CSparseJ is a Java port of CSparse (a Concise Sparse matrix package).
• Netlib-java
  • Netlib is a collection of mission-critical software components for linear algebra systems (i.e. working with vectors or matrices).
• Solvers and preconditioners
  • Mostly adapted from Matrix Toolkit Java
• Nonlinear Optimization
  • Java translations of the 1-dimensional minimization routine from the MINPACK
• Matrix reader/writer
• All classes that use floating-point arithmetic are implemented in single and double precision.
• Parallel quicksort algorithm

Usage example

Example of singular value decomposition (SVD):

DenseDoubleAlgebraalg=newDenseDoubleAlgebra();DenseDoubleSingularValueDecompositions=alg.svd(matA);DoubleMatrix2DU=s.getU();DoubleMatrix2DS=s.getS();DoubleMatrix2DV=s.getV();

Example of matrix multiplication:

DenseDoubleAlgebraalg=newDenseDoubleAlgebra();DoubleMatrix2Dresult=alg.mult(matA,matB);

References

1. Official site "Parallel Colt Project Page". Parallel Colt. Retrieved June 15, 2013.{{cite web}}: Check |url= value (help)