[gclist] Precise GC's performance

[Darius Blasband]

> 
> The question is what kind of collector you have for precise collection.
> If you have a generational collector then the malloc becomes faster than
> an ordinary malloc. Substuting the null collector is not a fair test.
> YAFL must somehow figure out how to free storage. That has a cost. Manual
> adhoc methods of collection are often far more expensive than highly
> the tuned ones you find in garbage collectors.

Please understand that this was not the issue of my experiment: the
purpose here is not to measure the performance of GC vs a non-GC system,
but to measure the performance penalty of a given GC design (precise)
when compared with another approach (Conservative). The measure I made
was related to what happens as long as GC is not required. It does not
include any measure about GC itself.

Of course, in the real world, YAFL has to free storage. I do agree with 
you when saying that manual allocation methods are rarely more efficient 
than automatic ones.



Darius