void MyMatrixMultiply( vFloat A[4], vFloat B[4], vFloat C[4] )

{

    vFloat A1 = vLoad( A );         //Row 1 of A

    vFloat A2 = vLoad( A + 1 );     //Row 2 of A

    vFloat A3 = vLoad( A + 2 );     //Row 3 of A

    vFloat A4 = vLoad( A + 3);      //Row 4 of A

    vFloat C1 = vZero();         //Row 1 of C, initialized to zero

    vFloat C2 = vZero();         //Row 2 of C, initialized to zero

    vFloat C3 = vZero();         //Row 3 of C, initialized to zero

    vFloat C4 = vZero();         //Row 4 of C, initialized to zero

    vFloat B1 = vLoad( B );         //Row 1 of B

    vFloat B2 = vLoad( B + 1 );     //Row 2 of B

    vFloat B3 = vLoad( B + 2 );     //Row 3 of B

    vFloat B4 = vLoad( B + 3);      //Row 4 of B

    //Multiply the first row of B by the first column of A (do not  sum across)

    C1 = vMADD( vSplat( A1, 0 ), B1, C1 );

    C2 = vMADD( vSplat( A2, 0 ), B1, C2 );

    C3 = vMADD( vSplat( A3, 0 ), B1, C3 );

    C4 = vMADD( vSplat( A4, 0 ), B1, C4 );

    // Multiply the second row of B by the second column of A and

    // add to the previous result (do not sum across)

    C1 = vMADD( vSplat( A1, 1 ), B2, C1 );

    C2 = vMADD( vSplat( A2, 1 ), B2, C2 );

    C3 = vMADD( vSplat( A3, 1 ), B2, C3 );

    C4 = vMADD( vSplat( A4, 1 ), B2, C4 );

    // Multiply the third row of B by the third column of A and

    // add to the previous result  (do not sum across)

    C1 = vMADD( vSplat( A1, 2 ), B3, C1 );

    C2 = vMADD( vSplat( A2, 2 ), B3, C2 );

    C3 = vMADD( vSplat( A3, 2 ), B3, C3 );

    C4 = vMADD( vSplat( A4, 2 ), B3, C4 );

    // Multiply the fourth row of B by the fourth column of A and

    // add to the previous result (do not sum across)

    C1 = vMADD( vSplat( A1, 3 ), B4, C1 );

    C2 = vMADD( vSplat( A2, 3 ), B4, C2 );

    C3 = vMADD( vSplat( A3, 3 ), B4, C3 );

    C4 = vMADD( vSplat( A4, 3 ), B4, C4 );

    // Write out the result to the destination

    vStore( C1, C );

    vStore( C2, C + 1 );

    vStore( C3, C + 2 );

    vStore( C4, C + 3 );

}