This is the mail archive of the libc-alpha@sources.redhat.com mailing list for the glibc project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]

Re: malloc


Momchil Velikov wrote:
> 
> >>>>> "TYR124840" == TYR124840  <TYR124840@tyler.net> writes:
> 
> TYR124840> [...] some allocators would no doubt be tuned for certain
> TYR124840> "behavior" patterns and as i said, i want to make this fair.
> 
> In case I haven't made myself clear enough:
> 
>  - Patterns of behavior DOES exist in ALL programs (well, almost all).
>  - Good allocators exploit these patterns.
>  - A "fair" test would be one, which exhibits the same patterns of
>    behavior as the real programs.
>  - This is no cheating from the allocators' side.
> 
> OK ?
> 
> Regards,
> -velco

im not implying cheating from the allocator's side, obviously. and its
also quite obvious that most programs exhibit patterns. however, im not
going to limit myself to what an allocator is designed to do. im going
to stress whatever i can, whenever i can, and obtain as complete a
picture as i can of the capabilities of each.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]