Given Athlon's success there is no way RedHat could use -march=pentium4 without alienating a _large_ share of their user base.
I have an Athlon myself. I finally got it to install, but it lost the keyboard when trying to boot. It also hung on the pcmcia loading portion when initializing the driver.
I didn't get an answer on the loss of the keyboard, after install. But this symptom mirrors my attempt to install another linux distribution. (Mandrake)
Anyway, I had trouble with trying to install RHL through the normal install. So I tried to install using the text install method.
The whole thing installed fine. It tested out the X server and was successful.
The system is an HP Pavilion ze4315us. I am stumped as to why this happens.
Back to the athlon being such a used processor. What makes the processor not to be able to deal with i686 instructions? And why does it include i386 compatible instructions?
But they could use -mcpu=pentium4 instead of -mcpu=i686 as the Pentium3s
are being phased out. This would be faster on P4 and would stll run
athlons.
i'm still running a P III and plan to until I either get the HP to work or the 64 bit processors get to the mainstream computer users.
I do still have some 486 machines around, but they haven't seen electricity for a few years. I feel that processors in the PII and higher are the most used machines. But the Pentium has it's use for file servers and other duties.
Also given that the only remaining "useful" processors have MMX capabilities (except for the PentiumPro who never was around in large numbers) RedHat could and should use:
-mcpu=pentium4 -mmmx
I like the concept. If the scheme would help the higher end and keep the PII and higher users up and running.
I think that there are other distributions that could concentrate on keeping the pre-PII machines active. (Firewalls and other uses)
Of course all the discussion above assumes:
a) that Gcc P4 or MMX code generation is not as buggy as hell
MMX seemed useless for my machine. PII optimization seemed useful. I might be able to get on a P4 to see how buggy it is or how much better the programs run. It is a Dell computer.
b) that it makes a real difference on the P4 (don't assume it beforehand: it depnds on how much manpower has gone into that part of Gcc: at one point I found that the code genartion for the K6 was so bad that programs "optimized" for it were slower than whne compiled for the 686)
It sounds like a very hard feat for the gcc teasm to have to undergo. Not to mention the 64 bit processors. AMD and Intel, with their different strategies.
c) That it does not take an unordinate performance hit on the PIII and Athlons. Probable since AFAIK both are far less picky than the P4
I'm even more tempted to partition the P4 now for use with Linux. Discussing the P4 has stirred my curiousity.
On Sat, 2003-07-19 at 16:16, Steve Snyder wrote:
On Saturday 19 July 2003 6:53 am, Chris Adams wrote:
Once upon a time, Audioslave - 7M3 - Live <creed7m3live@xxxxxxxxxxxxxxx>
said:
I hope that the programs start to be compiled for at least 586 and higher applications. (maybe more efficient programs)
Red Hat has been compiling the packages that matter for specific architectures for years. There isn't any point in compiling _everything_ for anything other than i386; do you think "ls" or "vi" will run faster somehow? Also, everything is built optimized for i686 but using only the i386 instruction set. That way, it is optimized for higher CPUs (affects memory and instruction layout), but will run on any x86 CPU.
I was just about to write the same thing.
[RANT]
Now then: where's my Pentium4-optimized RPMs? The 1990s are long gone and GCC v2.x with it. It's a shame that the "-march=pentium4" and "-msse2" switches in GCC v3.x are going unused in a major distro like Red Hat's.
[/RANT]
-- No wonder you're tired! You understood so much today.
-- Shrike-list mailing list Shrike-list@xxxxxxxxxx https://www.redhat.com/mailman/listinfo/shrike-list
