C:\test\C>bufswap 536870912 268435456 2   ### 2^29 2^28
size:536870912 offset;268435456
[         0          1 ...  268435454    268435455 ^  268435456    268435457   ...  536870910  536870911 ]
[ 268435456  268435457 ...  536870910    536870911 ^          0            1   ...  268435454  268435455 ]
iterative: swaps:536870912 took 4.364767872 secs.

[         0          1 ...  268435454    268435455 ^  268435456    268435457   ...  536870910  536870911 ]
[ 268435456  268435457 ...  536870910    536870911 ^          0            1   ...  268435454  268435455 ]
recursive: swaps:268435456 took 2.476348362 secs.

##</code><code>##

C:\test\C>bufswap 30000000 20000000 2
size:30000000 offset;20000000
[         0          1 ...   19999998     19999999 ^   20000000     20000001   ...   29999998   29999999 ]
[  20000000   20000001 ...   29999998     29999999 ^          0            1   ...   19999998   19999999 ]
iterative: swaps:30000000 took 0.235516729 secs.

[         0          1 ...   19999998     19999999 ^   20000000     20000001   ...   29999998   29999999 ]
[  20000000   20000001 ...   29999998     29999999 ^          0            1   ...   19999998   19999999 ]
recursive: swaps:20000000 took 0.163142653 secs.

##</code><code>##

C:\test\C>bufswap 536870855 268435399 2      ### 2^28+prime prime
size:536870855 offset;268435399
[         0          1 ...  268435397    268435398 ^  268435399    268435400   ...  536870853  536870854 ]
[ 268435399  268435400 ...  536870853    536870854 ^          0            1   ...  268435397  268435398 ]
iterative: swaps:536870855 took 23.912365889 secs.

[         0          1 ...  268435397    268435398 ^  268435399    268435400   ...  536870853  536870854 ]
[ 268435399  268435400 ...  536870853    536870854 ^          0            1   ...  268435397  268435398 ]
recursive: swaps:536870854 took 3.633964430 secs.

##</code><code>##

C:\test\C>bufswap 2097147 1048571 2          ### 2^20+prime prime
size:2097147 offset;1048571
[         0          1 ...    1048569      1048570 ^    1048571      1048572   ...    2097145    2097146 ]
[   1048571    1048572 ...    2097145      2097146 ^          0            1   ...    1048569    1048570 ]
iterative: swaps:2097147 took 0.050917112 secs.

[         0          1 ...    1048569      1048570 ^    1048571      1048572   ...    2097145    2097146 ]
[   1048571    1048572 ...    2097145      2097146 ^          0            1   ...    1048569    1048570 ]
recursive: swaps:2097146 took 0.022471381 secs.

[         0          1 ...    1048569      1048570 ^    1048571      1048572   ...    2097145    2097146 ]
[   1048571    1048572 ...    2097145      2097146 ^          0            1   ...    1048569    1048570 ]
reversive: swaps:2097146 took 0.030067538 secs.


C:\test\C>bufswap 33554429 16777213 2       ### 2^24+prime prime
size:33554429 offset;16777213
[         0          1 ...   16777211     16777212 ^   16777213     16777214   ...   33554427   33554428 ]
[  16777213   16777214 ...   33554427     33554428 ^          0            1   ...   16777211   16777212 ]
iterative: swaps:33554429 took 0.519861854 secs.

[         0          1 ...   16777211     16777212 ^   16777213     16777214   ...   33554427   33554428 ]
[  16777213   16777214 ...   33554427     33554428 ^          0            1   ...   16777211   16777212 ]
recursive: swaps:33554428 took 0.212679449 secs.

[         0          1 ...   16777211     16777212 ^   16777213     16777214   ...   33554427   33554428 ]
[  16777213   16777214 ...   33554427     33554428 ^          0            1   ...   16777211   16777212 ]
reversive: swaps:33554428 took 0.275975182 secs.

C:\test\C>bufswap 134217723 67108859 2    ### 2^26+prime prime
size:134217723 offset;67108859
[         0          1 ...   67108857     67108858 ^   67108859     67108860   ...  134217721  134217722 ]
[  67108859   67108860 ...  134217721    134217722 ^          0            1   ...   67108857   67108858 ]
iterative: swaps:134217723 took 2.986443308 secs.

[         0          1 ...   67108857     67108858 ^   67108859     67108860   ...  134217721  134217722 ]
[  67108859   67108860 ...  134217721    134217722 ^          0            1   ...   67108857   67108858 ]
recursive: swaps:134217722 took 0.957572077 secs.

[         0          1 ...   67108857     67108858 ^   67108859     67108860   ...  134217721  134217722 ]
[  67108859   67108860 ...  134217721    134217722 ^          0            1   ...   67108857   67108858 ]
reversive: swaps:134217722 took 1.185514126 secs.

C:\test\C>bufswap 268435417 134217689 2  ### 2^27+prime prime
size:268435417 offset;134217689
[         0          1 ...  134217687    134217688 ^  134217689    134217690   ...  268435415  268435416 ]
[ 134217689  134217690 ...  268435415    268435416 ^          0            1   ...  134217687  134217688 ]
iterative: swaps:268435417 took 11.702352647 secs.

[         0          1 ...  134217687    134217688 ^  134217689    134217690   ...  268435415  268435416 ]
[ 134217689  134217690 ...  268435415    268435416 ^          0            1   ...  134217687  134217688 ]
recursive: swaps:268435416 took 1.888340531 secs.

[         0          1 ...  134217687    134217688 ^  134217689    134217690   ...  268435415  268435416 ]
[ 134217689  134217690 ...  268435415    268435416 ^          0            1   ...  134217687  134217688 ]
reversive: swaps:268435416 took 2.337291168 secs.

##</code><code>##

abcdef123
321fedcba reverse the entire buffer.
123fedcba reverse the smaller partition.
123abcdef reverse the larger partition.

##</code><code>##

U32 reverseBuffer( register U64 *p, const U32 start, const U32 size ) {
    register U32 i, swaps = 0;
    const U32 half = size >> 1;

    for( i = start; i < half; ++i ) {
        swapElems( p, i, size -1 -i );
        ++swaps;
    }
    return swaps;
}

U32 xchgBufferV( U64 *p, U32 size, U32 offset ) {
    register U32 swaps = 0;
    swaps += reverseBuffer( p, 0, size );
    swaps += reverseBuffer( p, 0, size - offset );
    swaps += reverseBuffer( p + (size - offset), 0, offset );
    return swaps;
}