[Haskell-cafe] Parallel weirdness

[Andrew Coppin]

Bulat Ziganshin wrote:
> Hello Brandon,
>
> Saturday, April 19, 2008, 8:24:03 PM, you wrote:
>
>   
>> contention.  (Note that resource locking will be done by the threaded
>> runtime even with only one thread, so you will see some slowdowns  
>> especially in I/O-related code.)
>>     
>
> yes, i forget about this. Simon wrote once that locking decrease
> performance by a few percents compared to single-threaded runtime
>   

...which is why I'm so damned surprised that the threaded RTS is 
*faster* than the monoprocessor RTS [which presumably lacks such locking 
overhead].