Matrix4f NIO naive

public void mul4f(Matrix4fBuffer leftM, Matrix4fBuffer rightM) {
    final FloatBuffer left = leftM.buffer;
    final FloatBuffer right = rightM.buffer;

    float m00 = left.get(0) * right.get(0) + left.get(1) * right.get(4) + left.get(2) * right.get(8) + left.get(3) * right.get(12);
    float m10 = left.get(0) * right.get(1) + left.get(1) * right.get(5) + left.get(2) * right.get(9) + left.get(3) * right.get(13);
    float m20 = left.get(0) * right.get(2) + left.get(1) * right.get(6) + left.get(2) * right.get(10) + left.get(3) * right.get(14);
    float m30 = left.get(0) * right.get(3) + left.get(1) * right.get(7) + left.get(2) * right.get(11) + left.get(3) * right.get(15);

    float m01 = left.get(4) * right.get(0) + left.get(5) * right.get(4) + left.get(6) * right.get(8) + left.get(7) * right.get(12);
    float m11 = left.get(4) * right.get(1) + left.get(5) * right.get(5) + left.get(6) * right.get(9) + left.get(7) * right.get(13);
    float m21 = left.get(4) * right.get(2) + left.get(5) * right.get(6) + left.get(6) * right.get(10) + left.get(7) * right.get(14);
    float m31 = left.get(4) * right.get(3) + left.get(5) * right.get(7) + left.get(6) * right.get(11) + left.get(7) * right.get(15);

    float m02 = left.get(8) * right.get(0) + left.get(9) * right.get(4) + left.get(10) * right.get(8) + left.get(11) * right.get(12);
    float m12 = left.get(8) * right.get(1) + left.get(9) * right.get(5) + left.get(10) * right.get(9) + left.get(11) * right.get(13);
    float m22 = left.get(8) * right.get(2) + left.get(9) * right.get(6) + left.get(10) * right.get(10) + left.get(11) * right.get(14);
    float m32 = left.get(8) * right.get(3) + left.get(9) * right.get(7) + left.get(10) * right.get(11) + left.get(11) * right.get(15);

    float m03 = left.get(12) * right.get(0) + left.get(13) * right.get(4) + left.get(14) * right.get(8) + left.get(15) * right.get(12);
    float m13 = left.get(12) * right.get(1) + left.get(13) * right.get(5) + left.get(14) * right.get(9) + left.get(15) * right.get(13);
    float m23 = left.get(12) * right.get(2) + left.get(13) * right.get(6) + left.get(14) * right.get(10) + left.get(15) * right.get(14);
    float m33 = left.get(12) * right.get(3) + left.get(13) * right.get(7) + left.get(14) * right.get(11) + left.get(15) * right.get(15);

    final FloatBuffer buffer = this.buffer;

    buffer.put(0, m00);
    buffer.put(1, m10);
    buffer.put(2, m20);
    buffer.put(3, m30);

    buffer.put(4, m01);
    buffer.put(5, m11);
    buffer.put(6, m21);
    buffer.put(7, m31);

    buffer.put(8, m02);
    buffer.put(9, m12);
    buffer.put(10, m22);
    buffer.put(11, m32);

    buffer.put(12, m03);
    buffer.put(13, m13);
    buffer.put(14, m23);
    buffer.put(15, m33);
}