|Original author(s)||Piotr Wendykier|
0.9.4 / March 21, 2010
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.
Parallel Colt has all the capabilities of the original Colt library, with the following additions.
- Specialized Matrix data structures
- Java port of PLASMA (Parallel Linear Algebra for Scalable Multi-core Architectures).
- CSparseJ is a Java port of CSparse (a Concise Sparse matrix package).
- 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
Example of Singular Value Decomposition (SVD):
DenseDoubleAlgebra alg = new DenseDoubleAlgebra(); DenseDoubleSingularValueDecomposition s = alg.svd(matA); DoubleMatrix2D U = s.getU(); DoubleMatrix2D S = s.getS(); DoubleMatrix2D V = s.getV();
Example of matrix multiplication:
DenseDoubleAlgebra alg = new DenseDoubleAlgebra(); DoubleMatrix2D result = alg.mult(matA,matB);