void swapBufferChunks( U8 *buf, U32 start1, U32 start2, U32 bufsize ) {
    register U64 *p1 = (U64*)&buf[ start1 ];
    register U64 *p2 = (U64*)&buf[ start2 ];
    register U64 temp;

    shift_size = p2 - p1;
    end_buf = p1 + bufsize;   # assuming bufsize is byte count
    item_count = bufsize / 8; # assuming elements are 8-bytes each
    iter_count = 0;

    bgn_ofs = p1;
    temp = *p1;

    while ( iter_count < item_count ) {
        if ( p2 = bgn_ofs ) {
            *p1 = temp;
            iter_count++;
            last if ( iter_count == item_count ); # break out of while loop as soon as this is true
            p1++;
            p2++;
            bgn_ofs = p1;
            temp = *p1;
        }
        *p1 = *p2;
        iter_count++;
        p1 = p2;
        p2 += shift_size;
        p2 -= bufsize if ( p2 >= end_buf );
    }
}