diff options
Diffstat (limited to 'zarb-ml/mageia-dev/20100926/000259.html')
| -rw-r--r-- | zarb-ml/mageia-dev/20100926/000259.html | 202 |
1 files changed, 202 insertions, 0 deletions
diff --git a/zarb-ml/mageia-dev/20100926/000259.html b/zarb-ml/mageia-dev/20100926/000259.html new file mode 100644 index 000000000..ce4f255f6 --- /dev/null +++ b/zarb-ml/mageia-dev/20100926/000259.html @@ -0,0 +1,202 @@ +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<HTML> + <HEAD> + <TITLE> [Mageia-dev] i686 must be Pentium II ? + </TITLE> + <LINK REL="Index" HREF="index.html" > + <LINK REL="made" HREF="mailto:mageia-dev%40mageia.org?Subject=Re%3A%20%5BMageia-dev%5D%20i686%20must%20be%20Pentium%20II%20%3F&In-Reply-To=%3C4C9F4425.4070709%40iki.fi%3E"> + <META NAME="robots" CONTENT="index,nofollow"> + <META http-equiv="Content-Type" content="text/html; charset=us-ascii"> + <LINK REL="Previous" HREF="000256.html"> + <LINK REL="Next" HREF="000273.html"> + </HEAD> + <BODY BGCOLOR="#ffffff"> + <H1>[Mageia-dev] i686 must be Pentium II ?</H1> + <B>Thomas Backlund</B> + <A HREF="mailto:mageia-dev%40mageia.org?Subject=Re%3A%20%5BMageia-dev%5D%20i686%20must%20be%20Pentium%20II%20%3F&In-Reply-To=%3C4C9F4425.4070709%40iki.fi%3E" + TITLE="[Mageia-dev] i686 must be Pentium II ?">tmb at iki.fi + </A><BR> + <I>Sun Sep 26 15:01:25 CEST 2010</I> + <P><UL> + <LI>Previous message: <A HREF="000256.html">[Mageia-dev] i686 must be Pentium II ? +</A></li> + <LI>Next message: <A HREF="000273.html">[Mageia-dev] i686 must be Pentium II ? +</A></li> + <LI> <B>Messages sorted by:</B> + <a href="date.html#259">[ date ]</a> + <a href="thread.html#259">[ thread ]</a> + <a href="subject.html#259">[ subject ]</a> + <a href="author.html#259">[ author ]</a> + </LI> + </UL> + <HR> +<!--beginarticle--> +<PRE>Giuseppe Ghibò skrev 26.9.2010 15:25: +><i> 2010/9/26 Thomas Backlund <<A HREF="https://www.mageia.org/mailman/listinfo/mageia-dev">tmb at iki.fi</A> <mailto:<A HREF="https://www.mageia.org/mailman/listinfo/mageia-dev">tmb at iki.fi</A>>> +</I>><i> +</I>><i> Giuseppe Ghibò skrev 26.9.2010 02:09: +</I>><i> +</I>><i> +</I>><i> Not exactly. I'm not talking in just using -march=<something> but in +</I>><i> also pushing -mfpmath=sse -msse (and maybe -msse2) , which should be +</I>><i> much more than JUST 1-2% (1-2% is usually the benchmark +</I>><i> tolerance)... +</I>><i> +</I>><i> +</I>><i> Well, here is a simple fact. +</I>><i> +</I>><i> Yes, going for i686 + SSE2 would/could give some benefits, +</I>><i> +</I>><i> BUT +</I>><i> +</I>><i> It would close support for all theese: +</I>><i> - Intel i586 (all) +</I>><i> +</I>><i> - Intel Pentium Pro +</I>><i> - Intel Pentium II +</I>><i> - Intel Pentium III (Including some Pentium D) +</I>><i> - 32-bit AMD Athlon +</I>><i> - AMD Geode +</I>><i> - VIA C3 +</I>><i> - Transmeta Crusoe +</I>><i> +</I>><i> So, thats not an option. +</I>><i> +</I>><i> +</I>><i> As I said I would see someone with such hardware, taking a CD of latest +</I>><i> MDV or cooker and try to install to do something and do a report. +</I>><i> +</I> +No point in trying the Cooker installer, as its currently broken. + +Last time I tried (around 2010.0), I had no problem using the textmode +installer, wich is the most lightway method of installing we have. + +><i> That reminds me also one suggestion. If someone has old hardware that +</I>><i> not in use anymore then could be donated to who is willing to test the +</I>><i> latest MDV|Mageia on it. +</I> +I will next week, as I still think we have some old i586 stored at work... + +><i> It's not ironic (I think this is a +</I>><i> brainstorming), or I'm not kidding, but there could be an wiki hardware +</I>><i> section for that. For old hardware schools and institutes or +</I>><i> corporations have even to pay for dismantling: such hardware is usually +</I>><i> recycled for: +</I>><i> +</I>><i> a) extracting gold (there are nowadays new chemical processes that +</I>><i> found more affordable to extract gold from old PCs than from mines) +</I>><i> b) avoid pollutions with the lead, plastics they contain, if thrown +</I>><i> in the dumpster etc. (note there isn't just the CPU, but also CRT +</I>><i> monitors, printers, disks, etc.) +</I>><i> +</I> + c) keep donating the old harware to schools that take anything + they can get (so no dismantling). + + +><i> IIRC there is a EU law that if you buy a new PC the vendor is obeyed to +</I>><i> retire the old one and take care for the dismantling. +</I>><i> +</I> +Nope. +But there is a "recycling fee" in the price of new hw, so should be able +to get tid of old hw without any cost... + +><i> +</I>><i> +</I>><i> Now what about only i686 + SSE then? +</I>><i> It would still close support for all theese: +</I>><i> - Intel i586 (all) +</I>><i> - Some Intel Pentium D +</I>><i> - 32-bit AMD Athlon < XP/MP +</I>><i> - AMD Geode < NX +</I>><i> - VIA C3 (Samuel* and Ezra) +</I>><i> - Transmeta Crusoe +</I>><i> +</I>><i> So, still not an option. +</I>><i> +</I>><i> +</I>><i> Now what about only i686 then? +</I>><i> It would still close support for all theese: +</I>><i> - Intel i586 (all) +</I>><i> - Some Intel Pentium D +</I>><i> - AMD Geode < NX +</I>><i> - VIA C3 (Samuel* and Ezra) +</I>><i> - Transmeta Crusoe +</I>><i> +</I>><i> So, still not an option. +</I>><i> +</I>><i> +</I>><i> And then to point out some other facts: +</I>><i> +</I>><i> Some of the benefits are already accounted for like you noted earlier: +</I>><i> +</I>><i> "Of course we shouldn't forget that the MDV had already a system for +</I>><i> providing optimized (look at /usr/lib/sse2 for instance) version of +</I>><i> libraries according to instruction set supported." +</I>><i> +</I>><i> And many applications capable of utilizing sse2 and other +</I>><i> instruction sets already have runtime detection support, so no +</I>><i> problem there. +</I>><i> +</I>><i> +</I>><i> So, where does that leave us? +</I>><i> +</I>><i> Simple. +</I>><i> For 32bit installs, we will still support i586 as base. +</I>><i> For 64bit installs, it's simple as x86_64 is SSE2 by default. +</I>><i> +</I>><i> +</I>><i> Now, _if_ the Mageia community gets enough developers to think of +</I>><i> _and_ support a "light netbook/legacy edition", then maybe we can +</I>><i> think of doing a i586/i686 split, but for now we will use i586 as base. +</I>><i> +</I>><i> +</I>><i> And many of the users wanting i686/sse2 already have hardware +</I>><i> capable of running x86_64, so that's what they should do, as there +</I>><i> is where the future is. +</I>><i> +</I>><i> +</I>><i> You are forgetting a midrange. Which is the midrange of not the latest +</I>><i> hardware but a memory around 2-4GB RAM. In that set a 32bit OS is still +</I>><i> consuming 30-50% fewer memory than 64bit. +</I> +I'm not forgetting them... +The current i586 base supports them +We also provide i686 kernels for them (desktop and server) +We have the "/usr/lib/sse2" and "apps with runtime detection support" +mentioned above. + +><i> As I said to complete the circle it is needed to provide on a per +</I>><i> --target|dialect .rpm package for the kernel as well as for the glibc. +</I>><i> We have just to ensure the targets and fix compilation errors (though +</I>><i> that wouldn't resolve the problem of bloatware distro). +</I>><i> +</I> +-- +Thomas +</PRE> + + + +<!--endarticle--> + <HR> + <P><UL> + <!--threads--> + <LI>Previous message: <A HREF="000256.html">[Mageia-dev] i686 must be Pentium II ? +</A></li> + <LI>Next message: <A HREF="000273.html">[Mageia-dev] i686 must be Pentium II ? +</A></li> + <LI> <B>Messages sorted by:</B> + <a href="date.html#259">[ date ]</a> + <a href="thread.html#259">[ thread ]</a> + <a href="subject.html#259">[ subject ]</a> + <a href="author.html#259">[ author ]</a> + </LI> + </UL> + +<hr> +<a href="https://www.mageia.org/mailman/listinfo/mageia-dev">More information about the Mageia-dev +mailing list</a><br> +</body></html> |