A Cache Efficient Matrix Transpose Program?

Question

So the obvious way to transpose a matrix is to use :

  for( int i = 0; i < n; i++ )

    for( int j = 0; j < n; j++ )

      destination[j+i*n] = sourc         


        

Answer 1

Steve Jessop mentioned a cache oblivious matrix transpose algorithm. For the record, I want to share an possible implementation of a cache oblivious matrix transpose.

public class Matrix {
    protected double data[];
    protected int rows, columns;

    public Matrix(int rows, int columns) {
        this.rows = rows;
        this.columns = columns;
        this.data = new double[rows * columns];
    }

    public Matrix transpose() {
        Matrix C = new Matrix(columns, rows);
        cachetranspose(0, rows, 0, columns, C);
        return C;
    }

    public void cachetranspose(int rb, int re, int cb, int ce, Matrix T) {
        int r = re - rb, c = ce - cb;
        if (r <= 16 && c <= 16) {
            for (int i = rb; i < re; i++) {
                for (int j = cb; j < ce; j++) {
                    T.data[j * rows + i] = data[i * columns + j];
                }
            }
        } else if (r >= c) {
            cachetranspose(rb, rb + (r / 2), cb, ce, T);
            cachetranspose(rb + (r / 2), re, cb, ce, T);
        } else {
            cachetranspose(rb, re, cb, cb + (c / 2), T);
            cachetranspose(rb, re, cb + (c / 2), ce, T);
        }
    }
}

More details on cache oblivious algorithms can be found here.