Difference Between Xeon versus Desktop?

[Nebulus]

I saw this article posted by a user in another forum.

http://www.custompc.co.uk/labs/14938...00-series.html

Excerpt:

However, the Xeon X3200-series CPUs aren't just Core 2 Quads with a different name engraved in the top of the heatspreader. As Xeons are aimed at servers and workstations, the four prefetchers are tuned for these sorts of applications, rather than standard desktop applications and games. As a result of this subtle tuning, the X3220 was 3 per cent slower than the otherwise identical Core 2 Quad Q6600 in our Media Benchmarks, and 25 per cent slower in games. However, in our Folding@home test and Cinebench R10, the X3220 was 3 per cent faster than the Q6600. Unless you're building a server or workstation, you're better off buying a Q6600 over an X3220.

25% slower in games?... anyone know more about this topic?

I have an X3350 (Q9450 equivalent) on order but now I'm not so sure.

[zanzabar]

i dont think that that benchmark is correct but the x3350 should be the same but some1 should test it

[RunawayPrisoner]

17198 3DMark06 score... and you're still afraid of the gaming performance of this chip? Yeah... right.

[RedHOT]

Where is the sites actual benchmark showing the 25% difference?

[Nebulus]

17198 3DMark06 score... and you're still afraid of the gaming performance of this chip? Yeah... right.

The question is, would a Q9450 at those exact same settings get the same score? Perhaps someone on this forum with a Q9450 could test this for us.

[Crankybugga]

You are comparing findings with 65nm counterparts to the difference between 45nm chips?

[RunawayPrisoner]

I have seen Singaporean reviews of the Q9450, and most of them could only hit 480MHz and bench at 475MHz max or something. I'm running mine 475MHz 24/7 now, though, and there's the difference. Here's the source:

http://forums.hardwarezone.com.sg/sh...&postcount=137

And to think I benched mine at 490MHz FSB... wow...

Edit: There's the 1500 points in the difference between 3.80GHz and 3.90GHz as proof for you, too. If anything, I think these Xeons would clock better and fare lower voltages than the actual Q9450. Sure, there might be a difference in CPU score (different boards, maybe?), but the question is... can they run at 3.80GHz or even 3.60GHz stable 24/7 when their max stable FSB is at 475MHz on an Asus Striker II? And versus a budget G35 board?

Edit 2: Just realized... Vista versus XP. 600 points in CPU difference. Now I'm confident that there would be none at all. Heck... I dare them to be able to clock at 490MHz and boot into Vista stable enough to achieve a full run of 3DMark06. To me, it seems like Vista just requires a hell of a lot more voltage (and effort) to even boot... whereas you can sail smoothly into XP anytime. I'm going to try installing 3DMark06 onto XP and see what happens.

[zanzabar]

u guys need to use the same ram settings they make a huge difference in the 3d mark score

[Nebulus]

I have seen Singaporean reviews of the Q9450, and most of them could only hit 480MHz and bench at 475MHz max or something. I'm running mine 475MHz 24/7 now, though, and there's the difference. Here's the source:

http://forums.hardwarezone.com.sg/sh...&postcount=137

And to think I benched mine at 490MHz FSB... wow...

Edit: There's the 1500 points in the difference between 3.80GHz and 3.90GHz as proof for you, too. If anything, I think these Xeons would clock better and fare lower voltages than the actual Q9450. Sure, there might be a difference in CPU score (different boards, maybe?), but the question is... can they run at 3.80GHz or even 3.60GHz stable 24/7 when their max stable FSB is at 475MHz on an Asus Striker II? And versus a budget G35 board?

I'm not really questioning the overclockability of each nor their voltages and temps. If you ran your x3350 at 400 x 8 and benched some games and then swapped out your cpu for a Q9450 at 400 x 8 and benched some games, would the results be the same? That is my question. Given that every single condition and piece of hardware would be the same, I would think they would score the same, but the article is saying otherwise. If course the article is comparing the 65 nm Q6600 with its equivalent 65 nm xeon. Still, its a question worth investigating don't you guys think?

[zanzabar]

some people said that about the opteron too but it was just bad testing that got most of those scores

[Nebulus]

some people said that about the opteron too but it was just bad testing that got most of those scores

Very true. For good testing, the ONLY variable should be the cpu: x3350 or Q9450. So to truly confirm/disprove the claim in the article, we need someone with BOTH chips to test them at identical settings in the same hardware.

[RunawayPrisoner]

Okay... you know what? I think the Xeon is even faster than the Q9450 at the same clock... or at least they perform on the same level. Check this out:



And compare that to the CPU score of this guy:

http://forums.hardwarezone.com.sg/sh...&postcount=137

X3350: 6286
Q9450: 6238

Both at 3.80GHz (475 x 8), both under Windows XP. I think we can rest the case now. And I now think I can break 18000 points in 3DMark06 under Windows XP as well... eheheheh...

Edit: and in case you want to keep it up, I think it's time I point out that... the said article doesn't have anything to back its own statement up aside from some statistics. That, and 3% of a difference is not that much IMO.

[Metroid]

RunawayPrisoner@ You know 3DMark is a synthetic benchmark. So we should not take that as proof to retaliate what another user said it. We need more benchmarks as I am convicted what he is saying about the prefetcher's are true, about the gaming, I am still not really sure as I have never seen a game running on a server processor to date.

Metroid.

[RunawayPrisoner]

RunawayPrisoner@ You know 3DMark is a synthetic benchmark. So we should not take that as proof to retaliate what another user said it. We need more benchmarks as I am convicted what he is saying about the prefetcher's are true, about the gaming, I am still not really sure as I have never seen a game running on a server processor to date.

Metroid.

Then here you go. A real game benchmark... and probably the hottest one in the world right now, too:

DX9 all High


DX10 all Very High


I'd do more games if I have the time to. But sincerely, this thing handles Crysis well enough.

[Nebulus]

Prisoner, the crysis benchmark doesn't tell us anything because we don't have an equivalently clocked Q9450 in an identical system to compare it to.

[RunawayPrisoner]

I compared my results with another user with a E8400 @ 4.25GHz and the favors are to these chips. What I'm trying to say is not that there is no difference or anything but that these chips do their jobs really well... so why should you care about whether or not they have the name Q9450? I owned a E3110 and now I have an E8400, and IMHO, running in the same setup, the E8400 requires more volts to stay stable, and perform somewhat a bit inferior to the E3110 in... every way. What you're worrying about is some myth about the difference (very subtle) between 65nm chips and their xeon counterparts. And I did try to say that the said article did not even have any benchmark to back their own statements up, didn't I? You ordered the chip, so right now, just compare it to the people who own the same chip instead of worrying about something like the Q9450. I'm sure you made the right choice.

Edit: And oh well, I guess I'll tell you this: BIOS 0405 on my motherboard was supposed to support Q9450, yet it did not recognize the Xeon chip. I had to update to 0503 so the board can recognize the chip correctly. So my conclusion is that THERE IS indeed a difference between these two chips, and that may explain why I don't ram into that 480MHz FSB wall like most others. But then... there is still no sign of this chip being outperformed by its Quad counterpart.

[Metroid]

Then here you go. A real game benchmark... and probably the hottest one in the world right now, too:

I'd do more games if I have the time to. But sincerely, this thing handles Crysis well enough.

I like your efforts. I really do but when I said more benchmarks. I was saying made by them(The Professionals in this area).

You could do the tests if you had the necessary hardware or if you were a hardware fanatic. I would really appreciate it.

It is a powerful hardware for games. Why do not you use it for our crunching team

Metroid.

[RunawayPrisoner]

I'm only providing future owners of this chip all the information I can provide... so they know what to expect from the chip. Of course, I'm quite concerned about this "myth" as well, and that's why I'd like to try and see... although I doubt anyone will buy both this and a Q9450 chip at the same time.

Edit: Oh, and I'm quoting what another user asked before:

Where is the sites actual benchmark showing the 25% difference?

Yeah... I'd like to know that as well. I'm a guy of actual pictures and numbers, not of statistical talks.

And by the way, since we are going with a "myth" from the 65nm quads, let's go back and look at the 65nm quads, yeah?

http://forums.anandtech.com/messagev...&enterthread=y

After reading that, here's what I gather: Xeon might require less voltage than their desktop counterparts to run stable at the same clock speed, thus making them potentially better overclockers. Also Xeon can withstand higher thermal than their desktop counterparts. This has actually been proven in the case of E3110 versus E8400 processors, so I'd say that this is probably true.

And... back to google.

[Metroid]

I'm only providing future owners of this chip all the information I can provide... so they know what to expect from the chip. Of course, I'm quite concerned about this "myth" as well, and that's why I'd like to try and see... although I doubt anyone will buy both this and a Q9450 chip at the same time.

Edit: Oh, and I'm quoting what another user asked before:



Yeah... I'd like to know that as well. I'm a guy of actual pictures and numbers, not of statistical talks.

And by the way, since we are going with a "myth" from the 65nm quads, let's go back and look at the 65nm quads, yeah?

http://forums.anandtech.com/messagev...&enterthread=y

After reading that, here's what I gather: Xeon might require less voltage than their desktop counterparts to run stable at the same clock speed, thus making them potentially better overclockers. Also Xeon can withstand higher thermal than their desktop counterparts. This has actually been proven in the case of E3110 versus E8400 processors, so I'd say that this is probably true.

And... back to google.

Yes you are right. He did not have any real benchmarks to back up his claiming, also yes that is right as it is a server processor is requires less voltage and it has to be much more efficient once it has to contain heat as it will work 24/7. So what I have yet to make my mind is, it gives much more stability, less voltage, better thermal compound than desktops right? It must have some hidden weakness processing things not related.

Servers processors always have been very good for reliability and much more expensive too. The things may be changing on the right direction, not sure though.

Metroid.

[RunawayPrisoner]

Okay... quad-core server chip versus dual-core desktop chip article here:

http://fanboyreview.blogspot.com/200...3210-that.html

Hmm... not sure how legit that is... but oh well. At least it shows Doom 3 running... a lot better on the Xeon chip. Now... would someone jump in here and tell me that the Doom 3 engine was built to take advantage of quad-core processors?

[Metroid]

Okay... quad-core server chip versus dual-core desktop chip article here:

http://fanboyreview.blogspot.com/200...3210-that.html

Hmm... not sure how legit that is... but oh well. At least it shows Doom 3 running... a lot better on the Xeon chip. Now... would someone jump in here and tell me that the Doom 3 engine was built to take advantage of quad-core processors?

When Doom 3 was launched did not have any quad core support and no support was ever being announced.

Edit: That guy was drunk, see the doom 3 resolution that is why was so much faster.

Metroid.

[RunawayPrisoner]

So much faster at the same clock speed? I'd run the game at the lowest resolution possible, too, if I want to test my CPU out.

Okay... found a professional review after some tedious searches:

http://www.benchmark.co.yu/modules.p...12432&oliver=0

From what I can see, E6600 @ 2.4GHz only outperforms X3220 @ 2.4GHz by a little tiny bit in gaming... almost invisible differences. E6600 was also faster in some cases, too... and I'm just guessing that Q6600 would yield the same result... somewhat. But I don't think it can be up to 25% in gaming. As far as I know, Crysis is the only game that might benefit just a little from quad-core processors.

[Metroid]

So much faster at the same clock speed? I'd run the game at the lowest resolution possible, too, if I want to test my CPU out.

Okay... found a professional review after some tedious searches:

http://www.benchmark.co.yu/modules.p...12432&oliver=0

From what I can see, E6600 @ 2.4GHz only outperforms X3220 @ 2.4GHz by a little tiny bit in gaming... almost invisible differences. E6600 was also faster in some cases, too... and I'm just guessing that Q6600 would yield the same result... somewhat. But I don't think it can be up to 25% in gaming. As far as I know, Crysis is the only game that might benefit just a little from quad-core processors.

I think that guy was drunk, should have had similar results maybe Xeon had something that could slice a bit of performance.

25% is just too much. So we could say both were drunk the guy who did that Doom 3 test and the guy said 25% for desktops counterparts.

We need more benchs. We will have soon. I know it.

Metroid.

[Nebulus]

So much faster at the same clock speed? I'd run the game at the lowest resolution possible, too, if I want to test my CPU out.

Okay... found a professional review after some tedious searches:

http://www.benchmark.co.yu/modules.p...12432&oliver=0

From what I can see, E6600 @ 2.4GHz only outperforms X3220 @ 2.4GHz by a little tiny bit in gaming... almost invisible differences. E6600 was also faster in some cases, too... and I'm just guessing that Q6600 would yield the same result... somewhat. But I don't think it can be up to 25% in gaming. As far as I know, Crysis is the only game that might benefit just a little from quad-core processors.

Well, thats good news; I would go as far as to say that the differences in the gaming benchmarks were well within the margins of error:
968.3 vs 969.7 fps for Quake III... basically the same here
206.6 vs 209.6 fps for Doom III... basically the same (slight edge toE6600)
158.18 vs 161.85 for Farcry... basically the same (slight edge toE6600)

I agree 25% seems a bit far fetched.

We need more benchs. We will have soon. I know it.

Hehe, I think so too. Hopefully when people see this thread tomorrow we will get some more up to date benching done.

[RunawayPrisoner]

Yeah... and I wonder what would be reliable as a benchmark... :p