This effort is still a "work in progress". Please feel free to add comments. BRBut please make them stand out by bolding or underlining them. – Edward J. Yoon
Why sparse matrices?
ScaLAPACK handles only dense and banded matrices for using optimization strategies for High-Performance, But, Hama will be handles sparse matrices.
- Sparse matrix operations cannot be optimized, However, Optimization has no value in the large-scale
- Also, Optimization algorithms are too complexity
- Many classes of problems result in matrices with a large number of zeros
- A sparse matrix is a special class of matrix that allows only the non-zero terms to be stored
- Reduction in the storage requirements for sparse matrices
- Significant speed improvement as many calculations involving zero elements are neglected
Storage of sparse matrices
I choosed HBase(sparse matrix storage) to reduce storage and complexity.
- Hama use column-oriented storage of matrices (HBase) , and so compressed column format is a natural choice of sparse storage
- Hama forces the elements of each column to be stored in increasing order of their row index
1 0 0 (1,1) = 1 0 3 1 (2,2) = 3 0 0 0 (2,3) = 1
Sparse Functions
- conversion
- Manipulate sparse matrices
- Graph Theory
- Reordering
- Linear Algebra
- Iterative techniques
- Miscellaneous