Path: csiph.com!usenet.pasdenom.info!weretis.net!feeder4.news.weretis.net!eternal-september.org!feeder.eternal-september.org!mx04.eternal-september.org!.POSTED!not-for-mail From: "aminer" Newsgroups: comp.programming.threads,comp.programming Subject: Re: About lockfree_mpmc - Date: Sun, 22 Jul 2012 18:51:52 -0500 Organization: A noiseless patient Spider Lines: 124 Message-ID: References: Injection-Date: Sun, 22 Jul 2012 22:51:58 +0000 (UTC) Injection-Info: mx04.eternal-september.org; posting-host="c43ca82f9e8d62a602307fe9d2e9b807"; logging-data="1834"; mail-complaints-to="abuse@eternal-september.org"; posting-account="U2FsdGVkX1/5q7aUWu7OqQHHWaHDgmJ/" X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.5512 X-Newsreader: Microsoft Outlook Express 6.00.2900.5512 Cancel-Lock: sha1:SBEIzFOdufUsZ2761HQS/zrQhaI= X-Priority: 3 X-MSMail-Priority: Normal X-Rfc2646: Format=Flowed; Response Xref: csiph.com comp.programming.threads:960 comp.programming:1996 Hello, I have inserted an mfence between line [1] and [2] in lockfree_mpmc and i have updated all my programs that uses lockfree_mpmc, and you can download all the source codes of my programs from: http://pages.videotron.com/aminer/ Sincerely, Amine Moulay Ramdane. "aminer" wrote in message news:juhv62$sda$1@dont-email.me... > > I wrote: >> So as you have noticed the processor can then reorder the loads on line >> [2] with the older >> store on line [1] and this will cause a problem, so i think i have to >> insert a load between >> line [1] and line [2]. > > > Even if i insert a load beween line [1] and [2] this will not work , > i have to insert an mfence between line [1] and [2]. > > > What do you think ? > > > Sincerely, > Amine Moulay Ramdane. > > > > > > > "aminer" wrote in message > news:juhuo3$q5s$1@dont-email.me... >> >> 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 a load between >> line [1] and line [2]. >> >> >> What do you think ? >> >> >> >> Sincerely, >> Amine Moulay Ramdane. >> >> > >