760MP article

G

Guest

Guest
Tom still doesnt have a clue when it comes to testing SMP systems. His choice of benchmarks is questionable to say the least. A few remarks:

1) Sysmark “internet creation”. Though adding synthetic benchmarks like these doesn’t hurt, I fail to see the point. I work for an internet agency, I can tell you neither our developers or graphic designers are in need of anything faster than a 600 Mhz CPU. Or would you like to visit websites that have 500 Mb graphics ? (Our servers on the other hand could use any performance increase we can get.. Just to install Vignette on our application & database servers takes more than 24 hrs !!!)
2) Quake3. Yeah sure, fun to see, but really, what Quake gamer is going to get a SMP system ? For what ? To play 640x480 ??
3) 3D Mark 2001.. pffffffffff
4) Sandra.. do I need to comment ?
5) I cant wait to see the Win98 benchmarks.. Why not install windows 3.1 while you are at it, Tom ?

So, this leaves us three useful benchmarks for SMP:

1) Flask
2) 3D Max
3) Cinema 4D

All these benchmarks relate to graphics, and most to 3D rendering power. Very specific applications too, that rely very much on software optimisation. Very important if you run one of these apps daily, not useful at all however, if you don’t.
Whatever happened to Photoshop ? CAD, pro engineer and stuff ? Software development ? Database server performance ? Webserver performance ?
There is not even *one* Unix/Linux benchmark in there. I’d really like to see what a dual A4 is worth compared to a dual Xeon as a *server* platform.

When I read his conclusion, I almost fainted:
“Right now, the release of AMD's new dual-Athlon chipset seems more like a technology demonstration rather than a full-blown product release. We have learned that dual-AthlonMP is performing very well indeed, but as long as AMD doesn't supply AthlonMP at high enough clock speeds, Intel's Xeon 4 solution has a clear performance advantage. “
Yeah, it does.. In Sandra, Quake3, Sysmark. The typical applications that I will run on a SMP server (or workstation).

If you want to have a look of how a dual A4 performs on more typical server/ws applications, have a look <A HREF="http://www.anandtech.com/showdoc.html?i=1483" target="_new"> here at Anand’s review </A>. And lets just hope Aces gives us a real review…

THG was a great reference in the good old Monster Truck Madness days, but he hasn’t evolved much since..


---- Owner of the only Dell computer with a AMD chip
 

leonov

Distinguished
Dec 31, 2007
66
0
18,630
I totally agree! What a complete waste of time the review is. Absolutely NO-ONE cares about the most of benches tested.

Flask is P4 optimised and it is interesting to see how a 1.2GHz Athlon MP system is closer. I think the test was using doubles (and thus can use SSE-2 optimisations), using floats or integers may well present a different picture. Could Tom please clarify the Flask setup.

Use of databases would be much more useful for "backroom" server tests.
 
G

Guest

Guest
I said that months ago and got frowned apon.

SPUDMUFFIN

<font color=red>Being Evil Is Good. Cause I Can Be A Prick And Get Away With It.</font color=red> :lol:
 
G

Guest

Guest
You know what you are absolutly right. i haven't even read Tom's review and I don't think I will. I personally like Anand's articles over Tom's.
 
G

Guest

Guest
I agree. The Anandtech article is much better. The choice of benchmarks here was pretty lame.


<i>Cognite Tute</i>
(Think for Yourself)
 
G

Guest

Guest
Very, very difficult to get a real review on SMP. Anandtech have got a few doubtfull ones two. Personally I am glad they ran the 3D max test, they're not much point in testing Internet graphics apps...everything is designed at 72 ppi and vectors where ever possible. Its the lowest of low end spectrum. Even Pentium 2@166Mhz will do a good job. A 56k modem downloads at about 5k/bs and not to many people will wait around for longer than 5 seconds so that means most pages aren't greater than 20k....wow a 20k file. Stupid to even try to benchmark. Photoshop isn't a bad one and most production drawings in CAD are still done in wireframe mode, shaded at best. Anandtech like to promote whatever they make the greatest margin on..I never even bother going there anymore.

"Cock-a-doodle-do" is what I say to my girl when I wake her UP in the morning!!
 
G

Guest

Guest
Ye...make that a Pentium 1 !!!

"Cock-a-doodle-do" is what I say to my girl when I wake her UP in the morning!!
 

MeTaLrOcKeR

Distinguished
May 2, 2001
1,515
0
19,780
Unless of course he's talkign about underclocking...LoL
I did that on purpose to a PII 266...i got it rnning at 133MHz.....i think the FSB was set to 33 or 50MHz....can't remember.....heh heh

Back to AMD 760MP...I liek this statement from AnandTech...

"If you can't tell by now, we're very impressed with the AMD 760MP chipset. In fact, one of the reasons we spent so long on this comparison is because the outcome of our results would influence what platform we used in our next database server for the AnandTech Forums. The choice is simple; the AMD 760MP is the DP workstation and server platform to have. It's reliable, it's high performing and it's very flexible; everything you'd expect from an Intel based server solution, except that it's from AMD instead."

-MeTaL RoCkEr

Burn MF, BURN!!!
 

Makaveli

Splendid
I agree with you all on this one. Tom's review wasn't as good as expected. And I found the AnandTech review to be more informative, and just better overall. Also the programs he choose for benchmarking Hmmm......?