org.ejml.alg.dense.mult

Class MatrixVectorMult

java.lang.Object

org.ejml.alg.dense.mult.MatrixVectorMult

public class MatrixVectorMult
extends Object

This class contains various types of matrix vector multiplcation operations for DenseMatrix64F.

If a matrix has only one column or row then it is a vector. There are faster algorithms that can be used to multiply matrices by vectors. Strangely, even though the operations count smaller, the difference between this and a regular matrix multiply is insignificant for large matrices. The smaller matrices there is about a 40% speed improvement. In practice the speed improvement for smaller matrices is not noticeable unless 10s of millions of matrix multiplications are being performed.

Author:

Peter Abeles

Constructor Summary

Constructors

Constructor and Description
MatrixVectorMult()

Method Summary

Methods

Modifier and Type	Method and Description
static void	mult(RowD1Matrix64F a, D1Matrix64F b, D1Matrix64F c) Performs a matrix vector multiply. c = A * b and c = A * bT ci = Sum{ j=1:n, aij * bj} where A is a matrix, b is a column or transposed row vector, and c is a column vector.
static void	multAdd(RowD1Matrix64F A, D1Matrix64F B, D1Matrix64F C) Performs a matrix vector multiply. C = C + A * B or C = C + A * BT ci = Sum{ j=1:n, ci + aij * bj} where A is a matrix, B is a column or transposed row vector, and C is a column vector.
static void	multAddTransA_reorder(RowD1Matrix64F A, D1Matrix64F B, D1Matrix64F C) An alternative implementation of multAddTransA_small(org.ejml.data.RowD1Matrix64F, org.ejml.data.D1Matrix64F, org.ejml.data.D1Matrix64F) that performs well on large matrices.
static void	multAddTransA_small(RowD1Matrix64F A, D1Matrix64F B, D1Matrix64F C) Performs a matrix vector multiply. C = C + AT * B or C = CT + AT * BT ci = Sum{ j=1:n, ci + aji * bj} where A is a matrix, B is a column or transposed row vector, and C is a column vector.
static void	multTransA_reorder(RowD1Matrix64F A, D1Matrix64F B, D1Matrix64F C) An alternative implementation of multTransA_small(org.ejml.data.RowD1Matrix64F, org.ejml.data.D1Matrix64F, org.ejml.data.D1Matrix64F) that performs well on large matrices.
static void	multTransA_small(RowD1Matrix64F A, D1Matrix64F B, D1Matrix64F C) Performs a matrix vector multiply. C = AT * B where B is a column vector. or C = AT * BT where B is a row vector.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

MatrixVectorMult

public MatrixVectorMult()

Method Detail

mult

public static void mult(RowD1Matrix64F a,
        D1Matrix64F b,
        D1Matrix64F c)

Performs a matrix vector multiply.

c = A * b
and
c = A * b^T

c_i = Sum{ j=1:n, a_ij * b_j}

where A is a matrix, b is a column or transposed row vector, and c is a column vector.

Parameters:

a - A matrix that is m by n. Not modified.

b - A vector that has length n. Not modified.

c - A column vector that has length m. Modified.

multAdd

public static void multAdd(RowD1Matrix64F A,
           D1Matrix64F B,
           D1Matrix64F C)

Performs a matrix vector multiply.

C = C + A * B
or
C = C + A * B^T

c_i = Sum{ j=1:n, c_i + a_ij * b_j}

where A is a matrix, B is a column or transposed row vector, and C is a column vector.

Parameters:

A - A matrix that is m by n. Not modified.

B - A vector that has length n. Not modified.

C - A column vector that has length m. Modified.

multTransA_small

public static void multTransA_small(RowD1Matrix64F A,
                    D1Matrix64F B,
                    D1Matrix64F C)

Performs a matrix vector multiply.

C = A^T * B
where B is a column vector.
or
C = A^T * B^T
where B is a row vector.

c_i = Sum{ j=1:n, a_ji * b_j}

where A is a matrix, B is a column or transposed row vector, and C is a column vector.

This implementation is optimal for small matrices. There is a huge performance hit when used on large matrices due to CPU cache issues.

Parameters:

A - A matrix that is m by n. Not modified.

B - A that has length m and is a column. Not modified.

C - A column vector that has length n. Modified.

multTransA_reorder

public static void multTransA_reorder(RowD1Matrix64F A,
                      D1Matrix64F B,
                      D1Matrix64F C)

An alternative implementation of multTransA_small(org.ejml.data.RowD1Matrix64F, org.ejml.data.D1Matrix64F, org.ejml.data.D1Matrix64F) that performs well on large matrices. There is a relative performance hit when used on small matrices.

Parameters:

A - A matrix that is m by n. Not modified.

B - A Vector that has length m. Not modified.

C - A column vector that has length n. Modified.

multAddTransA_small

public static void multAddTransA_small(RowD1Matrix64F A,
                       D1Matrix64F B,
                       D1Matrix64F C)

Performs a matrix vector multiply.

C = C + A^T * B
or
C = C^T + A^T * B^T

c_i = Sum{ j=1:n, c_i + a_ji * b_j}

where A is a matrix, B is a column or transposed row vector, and C is a column vector.

This implementation is optimal for small matrices. There is a huge performance hit when used on large matrices due to CPU cache issues.

Parameters:

A - A matrix that is m by n. Not modified.

B - A vector that has length m. Not modified.

C - A column vector that has length n. Modified.

multAddTransA_reorder

public static void multAddTransA_reorder(RowD1Matrix64F A,
                         D1Matrix64F B,
                         D1Matrix64F C)

An alternative implementation of multAddTransA_small(org.ejml.data.RowD1Matrix64F, org.ejml.data.D1Matrix64F, org.ejml.data.D1Matrix64F) that performs well on large matrices. There is a relative performance hit when used on small matrices.

Parameters:

A - A matrix that is m by n. Not modified.

B - A vector that has length m. Not modified.

C - A column vector that has length n. Modified.