About lockfreE_mpmc .....

About lockfreE_mpmc .....

Hello,

I wrote:
 > Hello all,
>
> I think i have discovered a problem
with lockfree_mpmc:
>
> You will find the source code of
lockfree_mpmc at:
>
> http://pages.videotron.com/aminer/
>

>
> So please follow with me:
>
> If you take a look
at the lockfree_mpmc , here is  the source code
> of the push()
method:
>
> ---
>
> function TLockfree_MPMC.push(tm :
tNodeQueue):boolean;
> var lasttail,newtemp:long;
>
i,j:integer;
> begin
>
> if getlength >= fsize

then
>      begin
>          result:=false;
>         
exit;
>      end;
> result:=true;
>
>
newTemp:=LockedIncLong(temp);
>
> [1] lastTail:=newTemp-1;
>
[2] setObject(lastTail,tm);
>
> repeat
>
> if
CAS(tail,lasttail,newtemp)
>   then
>      begin
>      
exit;
>      end;
> sleep(0);
> until false;
>
>
end;
>
> ---
>
> As you know in the x86 architecture
Loads may be reordered with older stores
> to different locations.
>

> So in line [2] there is a load of tail and lasttail to the registers of
the
> processor
> before calling setobject() and just before on
line [1] there is a store to
> lasttail.
>
> So as you have
noticed the processor can then reorder the loads on line [2]
> with the
older
> store on line [1] and this will cause a problem, so i think i have
to insert
> an mfence between
> line [1] and line [2].

In the intel's processor manual: link in section 8.2.3.4 it is stated that
loads may not be
reordered with earlier stores to the same location, so lockfree_mpmc
doesn't need
and mfence between line [1] and [2] cause there is a store and after that a
load to
the same location that is lastTail:.
 
 
You can download lockfree_mpmc from:
 
http://pages.videotron.com/aminer/
 
 
 
Sincerely,
Amine Moulay Ramdane.
 
 
 
 

1 contenuto / 0 nuovi
Per informazioni complete sulle ottimizzazioni del compilatore, consultare l'Avviso sull'ottimizzazione