Hello, been a while, dual CPU mobos

Michael Laccetti michael-1DHYbOjWH/jDO7Nk1fN4cQ at public.gmane.org
Thu Sep 9 17:22:15 UTC 2004


I can't really comment on the opcodes in the processor, since that's a tad
above me.  (Yes, I did just admit that.  Whoops.)  I'd have to sit down and
do some research instead of pulling some random stuff out of the air.

The P4M is a cut down/low power P4.  Same long pipeline, same problem with
wasted cycles if prediction goes awry.  That said, I'd be hard pushed to say
that a 1GHz Duron can perform the same as a P4M 1.8, especially since Durons
were just cut-down Athlons.

I use Gentoo, and started with -j3 a long while ago.  Then I found the
goodness of distcc, and have been using -j10.  :)

Nothing really compelling for me to upgrade to.  The benefits of going from
my P4 3.0E (running at 3.8GHz) to an AMD 64 3x00...  There aren't really
any.  Aside from the on-die memory controller, there's no way I could
justify the cost.  The premium on high end AMD parts is somewhat outrageous,
especially since they were originally the "cheap" solution.  What are you
looking to upgrade from?  The 1GHz Duron?


________________________________

	From: owner-tlug-lxSQFCZeNF4 at public.gmane.org [mailto:owner-tlug-lxSQFCZeNF4 at public.gmane.org] On Behalf Of The
Edge of the Ice
	Sent: Thursday, September 09, 2004 11:14 AM
	To: tlug-lxSQFCZeNF4 at public.gmane.org
	Subject: Re: [TLUG]: Hello, been a while, dual CPU mobos
	
	

	On Thu, 9 Sep 2004 12:01:58 -0400, Michael Laccetti
	<michael-1DHYbOjWH/jDO7Nk1fN4cQ at public.gmane.org> wrote:
	> P4s rely on their raw speed to keep them competitive, because of
their
	> extremely long pipeline.  The newer versions are at least 20
stages, perhaps
	> even longer.  AMD, and the P3s/Pentium Ms (not Pentium 4M) have a
short
	> pipeline.  Of course, they can't scale to be as speedy.  My
Pentium M 1.7
	
	What I mentioned has nothing to do with the length of the pipeline,
and applies
	to specific opcodes which tend to be common in certain workloads
(compilation
	and crypto both qualify for "lots of bit operations" afaik).
	
	> competes quite well with my Pentium 4 2.8 in terms of compilation
times, the
	
	How does either compare to this, though?  (I'm honestly ignorant of
the Intel
	chip branching):
	cpu family      : 15
	model           : 2
	model name      : Intel(R) Pentium(R) 4 Mobile CPU 1.80GHz
	(DDR266 RAM)
	
	As I said, this machine kicks its sorry ass for compilation speed
last I checked
	(nonscientifically, granted):
	cpu family      : 6
	model           : 7
	model name      : AMD Duron(tm) Processor
	(running at 1GHz, DDR266 RAM running at 200, due to the Duron's
100MHz FSB)
	
	> only thing that holds it back is the DDR 333 vs. the DDR 480 (yay
	> overclocking) in my workstation.  That, and the laptop HD is quite
a bit
	> slower than the workstation.
	
	That may well be true, but is mitigated by doing make -j2 or -j3.
:)
	
	As it stands now, I'm caught between upgrading the CPU to an Athlon
2400+,
	or going all-out for a new mobo, AMD64, etc.  Only "problem" is that
I hear that
	PCI-Express is the next, greatest thing in PCs, and I haven't seen a
single
	AMD-compatible motherboard with it.
	
	--
	taa
	/*eof*/
	--
	The Toronto Linux Users Group.      Meetings: http://tlug.ss.org
	TLUG requests: Linux topics, No HTML, wrap text below 80 columns
	How to UNSUBSCRIBE: http://tlug.ss.org/subscribe.shtml
	



--
The Toronto Linux Users Group.      Meetings: http://tlug.ss.org
TLUG requests: Linux topics, No HTML, wrap text below 80 columns
How to UNSUBSCRIBE: http://tlug.ss.org/subscribe.shtml





More information about the Legacy mailing list