diff options
Diffstat (limited to 'zarb-ml/mageia-dev/20100927/000321.html')
| -rw-r--r-- | zarb-ml/mageia-dev/20100927/000321.html | 111 |
1 files changed, 111 insertions, 0 deletions
diff --git a/zarb-ml/mageia-dev/20100927/000321.html b/zarb-ml/mageia-dev/20100927/000321.html new file mode 100644 index 000000000..cfa6d0954 --- /dev/null +++ b/zarb-ml/mageia-dev/20100927/000321.html @@ -0,0 +1,111 @@ +<!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=%3C4CA0CDE5.4040507%40arcor.de%3E"> + <META NAME="robots" CONTENT="index,nofollow"> + <META http-equiv="Content-Type" content="text/html; charset=us-ascii"> + <LINK REL="Previous" HREF="000315.html"> + <LINK REL="Next" HREF="000323.html"> + </HEAD> + <BODY BGCOLOR="#ffffff"> + <H1>[Mageia-dev] i686 must be Pentium II ?</H1> + <B>Florian Hubold</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=%3C4CA0CDE5.4040507%40arcor.de%3E" + TITLE="[Mageia-dev] i686 must be Pentium II ?">doktor5000 at arcor.de + </A><BR> + <I>Mon Sep 27 19:01:25 CEST 2010</I> + <P><UL> + <LI>Previous message: <A HREF="000315.html">[Mageia-dev] List Options: Is it possible to disable HTML? +</A></li> + <LI>Next message: <A HREF="000323.html">[Mageia-dev] i686 must be Pentium II ? +</A></li> + <LI> <B>Messages sorted by:</B> + <a href="date.html#321">[ date ]</a> + <a href="thread.html#321">[ thread ]</a> + <a href="subject.html#321">[ subject ]</a> + <a href="author.html#321">[ author ]</a> + </LI> + </UL> + <HR> +<!--beginarticle--> +<PRE> Am 25.09.2010 17:53, schrieb Giuseppe Ghibò: +><i> IMHO the problem is not finding an architecture to fit the i586 or i686 rpm +</I>><i> flags, rather to find the minimum CPU and memory requirement worthwhile for a +</I>><i> decent usage. With KDE if we look at the Mandriva 2010.1, it's barely usable +</I>><i> on a P4-3000 with 1-2GB RAM, or a AMD Barton 2500. Barely means that windows +</I>><i> and applications are pretty slow to open, switching is slow, etc.; since +</I>><i> netbook are so popular we can consider the minimum requirements as those of a +</I>><i> typical 2010 netbook, which has ATOM 1.6Ghz processor and 1GB memory. In +</I>><i> other words we can consider as default the presence of the SSE instruction +</I>><i> set. ATOM has even the SSE2, which would be even better, but that would left +</I>><i> out some AMD CPU (some older AMD, like 1.2Ghz has only the 3DNow and not +</I>><i> SSE). I would drop compiling for old ISA drivers in kernel (think to some old +</I>><i> ISA 3com card, like 3C505, etc.). +</I>><i> +</I>If you have a P4 with 2GB RAM, and that is slow/sluggish with KDE4, +i think you definitely should pay more attention to KDE configuration. +We have some forum users at mandrivauser.de who run KDE4 on +machines that have less than half of the power of the machines you +describe, there it is sluggish, but still usable. +My laptop has a P4 2.8GHz with originally 512 MB RAM, it will swap +out mostly all the time if you have more openend than a browser, +but it's not slow/sluggish, and definitely usable. + +More on-topic, at mandrivauser.de, some years ago we did hand- +optimized packages for i686 and Pentium M, for some bigger apps +like OpenOffice, and if you fine-tune compiler and linker flags +for every package and every arch you support, there is definitely +a measurable performance gain, sometimes as big as 15-40%, +f.ex. startup time for OOo, but not in general. + +The downside of that is, optimizing compiler flags is really risky +and can't be done in general, at least not those optimizations +that really make the difference. -Os vs. -O2 is not, what i'm talking about, +it's more stuff like -funroll-loops, -ffast-math and the like. +But even Gentoo recommendations say those should be avoided, +and you have to do them on a per-package-basis. + +I think we should stay with plain old i586, but the mageia-light +thing sounds like a nice idea, i must say. We should not do what fedora +has done and abandon support for those older cpus at the cost +of what? 1% performance gain? C'mon ... + + + +PS: Sorry, wanted to get this mail out yesterday, but Thunderbird didn't want to :( +</PRE> + + + + + + + + + + + + +<!--endarticle--> + <HR> + <P><UL> + <!--threads--> + <LI>Previous message: <A HREF="000315.html">[Mageia-dev] List Options: Is it possible to disable HTML? +</A></li> + <LI>Next message: <A HREF="000323.html">[Mageia-dev] i686 must be Pentium II ? +</A></li> + <LI> <B>Messages sorted by:</B> + <a href="date.html#321">[ date ]</a> + <a href="thread.html#321">[ thread ]</a> + <a href="subject.html#321">[ subject ]</a> + <a href="author.html#321">[ 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> |