Anandtech benches dual Magny Cours and Xeon

[jennyh]

Keep dreaming failzers lol.

MC is huge, in more ways that one 😉 Hell even if it was bad Acer would buy them all up and sell them so cheaply that even less fortunates like yourself could even afford one. 😀

 

[fazers_on_stun]

everyone wait until this BS with the FTC is over.

I dunno - I seriously think Intel actually wants to keep AMD around, for more than just avoiding stupid monopoly lawsuits. Haven't quite figured out the reason. Maybe it has something to do with the Intel engineers getting entertainment value from all the fist fights & slogging insults flying around here on THG .

Sorta like Jerry Springer for techies - every other word is bleeped out, lots of fat pregnant women & unemployed bums undergoing DNA testing to see who fathered what bastard, fights breaking out left & right - what's not to like?? 😀

We should ask Sonoran & company if that is indeed the reason Intel doesn't kill off AMD

 

[fazers_on_stun]

Keep dreaming failzers lol.

MC is huge, in more ways that one 😉 Hell even if it was bad Acer would buy them all up and sell them so cheaply that even less fortunates like yourself could even afford one. 😀

Now now - at least I don't have to go out & get a 2nd job cutting down trees to make cabers 😀..

 

[MU_Engineer]

http://it.anandtech.com/IT/showdoc.aspx?i=3784

I won't cherry pick graphs to post so you're going to have to read it yourself However, I will post these two as I thought they were rather interesting.


Looks like the Magny Cours is getting its butt handed to it, but then we look at the Linux graph and see this:

The Intel system doesn't really do any better (actually slightly worse) but the AMD one does alot better! Of course it's Alpha software at the moment so performance in later versions will likely vary alot. In any case the Linux version wipes the floor with the Windows one as long as you're not on an Intel rig.

There are a few things I can see that may cause this behavior.

1. AT said that core utilization was ~50% in the Windows blender test. With fewer cores active, the relative performance of each core becomes more important, and Intel's cores with a 50% clock speed advantage outrun AMD's. You would expect the outcome they saw in that case. I don't know if it is a function of an inferior threading model or API being used on Windows or just the Windows scheduler being inferior to Linux's, but the Windows version was obviously not as well-threaded as the Linux one.

2. The compilers used to compile the code were likely different, as are the compile options. I'll betcha the Blender team used MSVCC for the Windows binary, while the SUSE version almost certainly used GCC with no specific -march= option. That can have a pretty significant effect on performance.

3. I doubt the fact that the code is "alpha" software has much to do with performance between two different CPUs running the exact same code on the exact same OS. Unless there's a bunch of hand-optimized or assembly code going to be rolled into the final product or other optimizations specifically targeting a certain CPU, I doubt that the fact that the software isn't 100% feature-complete and frozen makes a lot of performance difference between two different CPUs.

 

[jimmysmitty]

Fazers you are really quite clueless.

What is intel without OEM's? Nothing.

Did you read what Acer's CEO said recently? Maybe you should. "Competition is good".


Do you really believe IBM/HP et-al would accept intel as the only supplier of chips, setting whatever prices they wanted?

Um pretty much any CPU or PC hardware company without OEMs are nothing. Do you think we keep companies like AMD and nVidia afloat? Nope. They still all rely on OEMs.

BTW, Acer is not that great of an OEM. In fact their products are pretty bad. I would suggest Asus over them.

 

[BadTrip]

Um pretty much any CPU or PC hardware company without OEMs are nothing. Do you think we keep companies like AMD and nVidia afloat? Nope. They still all rely on OEMs.

BTW, Acer is not that great of an OEM. In fact their products are pretty bad. I would suggest Asus over them.

Acer has sunk so bad in recent years that I would suggest e-machines over them, lol

 

[jimmysmitty]

^Ouch.

And eMachines blows. Everytime I hear a friend saying "I was thinking of getting this eMachne" I beg them not to. I even suggest Dell over them and I hate pretty much all OEMs since I build my own.

 

[piesquared]

Way to serve it Jenny! You've got these intel zealots tripping over their own tongue and backpeadling so fast they think it's yesterday. It was hilarious! lol After seeing full results from tecchannel, their only recourse was "well you just wait until beckton hits, and it'll beat it up really really good!". Of course, once those numbers surfaced, they are now just going away in shame with their tale between their legs. That was a good serving right there. Well done! 😀

 

[jimmysmitty]

Way to serve it Jenny! You've got these intel zealots tripping over their own tongue and backpeadling so fast they think it's yesterday. It was hilarious! lol After seeing full results from tecchannel, their only recourse was "well you just wait until beckton hits, and it'll beat it up really really good!". Of course, once those numbers surfaced, they are now just going away in shame with their tale between their legs. That was a good serving right there. Well done! 😀

Not too sure which benchmarks you are looking at but every one I have seen shows a 6 core Xeon pretty much near or on par and in some cases, better than the Opteron.

And Beckton will be MCs worst enemy in the 4P+ market.

 

[piesquared]

Well we can't let this thread slip away now can we! Another interesting observation is how much superior AMD's 45nm SOI process is to intel's 45nm generic process. Magny Cours can run 12 cores at 2.2GHz @ 80W while beckton runs 8 cores at 2.26 GHz @ 130W 😱 . I guess I can understand why the blue team are suddenly fighting felines for their tongue. 😀

 

[fazers_on_stun]

Well we can't let this thread slip away now can we! Another interesting observation is how much superior AMD's 45nm SOI process is to intel's 45nm generic process. Magny Cours can run 12 cores at 2.2GHz @ 80W while beckton runs 8 cores at 2.26 GHz @ 130W 😱 . I guess I can understand why the blue team are suddenly fighting felines for their tongue. 😀

Obviously you have bought AMD's "ACP" ratings hook, line & sinker. AMD talks ACP vs TDP again:

In many ways, ACP is an arbitrary definition conjured up by AMD which no other player within the industry has accepted. Instead, the big industry players like Intel, Sun, HP and IBM have settled on the suite of SPECpower benchmarks run by a committee of industry players hailing from all those firms and even AMD. This, for the most part, promotes TDP (Thermal Design Power), a measurement Intel favours and which AMD considers inherently biased.

But before we get into things, it's important to point out there is a difference between Intel's and AMD's version of the benchmarketing tool.

AMD TDP shows the worst case power draw a particular chip can experience when it's operating at max voltage.

A chip can easily draw a lot of power, but usually only for very short periods of times (like several microseconds). If enough power isn't provided, bits and bobs get lost along the way and calculation errors start cropping up, which is really bad news. So, one would need to be able to supply that much power to the CPU at any given moment, even though CPUs can't draw max current for extended periods – even, say , 1/1000th of a second – making it all very difficult. Over 1/1000th of a second, the CPU could draw between 75-150 watts, but average power usage might be 110W.

When a firm is designing heat sinks, it only really cares about those longer periods of time, while people interested in the actual power, really care about every microsecond.

Intel has a spec for the maximum power of a CPU, it also has TDP, for its heat sink/cooling guys to worry about and adds a thermal diode to shut down the CPU if it starts overheating.

AMD, which only recently began using thermal diodes, has had to be more conservative in designing heat sinks, because the chip could actually overheat. Thus, the firm has had to keep its TDP more conservative than Intel's, hence the reason AMD would rather not talk about it and use a different metric.

AMD uses a blend of different workloads to get ACP, whereas what anybody really cares about is average power draw on the workload and peak power draw/cooling needs. ACP is just an average. It depends on process technology, the temperature the CPU is operating at, ambient temperature and more, making it mighty difficult for someone outside of AMD to calculate.

Meanwhile, SPECpower_ssj2008, is fairly unambiguous although AMD dislikes it because it feels it favours Intel. Well, the truth is, it does favour Intel a bit, but it wasn't purposefully set up that way. The reason is that the benchmark really loves cache and Intel has always had larger, faster caches than AMD. Shanghai has really gone a long way towards catching up with its big 6MB L3 cache, but the fact is, it still lags Nehalem.

Seriously, you AMD fanbois just need to get over the fact that AMD won't be competitive in the server market again until BD comes out, if then..

 

[fazers_on_stun]

Intel Tops AMD in Server Microprocessors

Intel will continue to dominate the market, says J.P. Morgan.

TUESDAY, INTEL (TICKER: INTC) launched its new Xeon 7500 "Nehalem-EX" expandable server-processor line, targeted toward the high-performance, mission-critical server market.

The launch came on the heels of Advanced Micro Devices' (AMD) March 29 unveiling of its Opteron 6100 "Magny Cours" series and just two weeks after Intel also refreshed its mainstream line with the Xeon 5600 "Westmere-EP" processor. Both Magny Cours and Westmere-EP are positioned at the high-volume, mainstream-server space.

Looks like JP Morgan can count cores too 😀...

 

[piesquared]

Obviously you have bought AMD's "ACP" ratings hook, line & sinker. AMD talks ACP vs TDP again:

In many ways, ACP is an arbitrary definition conjured up by AMD which no other player within the industry has accepted. Instead, the big industry players like Intel, Sun, HP and IBM have settled on the suite of SPECpower benchmarks run by a committee of industry players hailing from all those firms and even AMD. This, for the most part, promotes TDP (Thermal Design Power), a measurement Intel favours and which AMD considers inherently biased.

But before we get into things, it's important to point out there is a difference between Intel's and AMD's version of the benchmarketing tool.

AMD TDP shows the worst case power draw a particular chip can experience when it's operating at max voltage.

A chip can easily draw a lot of power, but usually only for very short periods of times (like several microseconds). If enough power isn't provided, bits and bobs get lost along the way and calculation errors start cropping up, which is really bad news. So, one would need to be able to supply that much power to the CPU at any given moment, even though CPUs can't draw max current for extended periods – even, say , 1/1000th of a second – making it all very difficult. Over 1/1000th of a second, the CPU could draw between 75-150 watts, but average power usage might be 110W.

When a firm is designing heat sinks, it only really cares about those longer periods of time, while people interested in the actual power, really care about every microsecond.

Intel has a spec for the maximum power of a CPU, it also has TDP, for its heat sink/cooling guys to worry about and adds a thermal diode to shut down the CPU if it starts overheating.

AMD, which only recently began using thermal diodes, has had to be more conservative in designing heat sinks, because the chip could actually overheat. Thus, the firm has had to keep its TDP more conservative than Intel's, hence the reason AMD would rather not talk about it and use a different metric.

AMD uses a blend of different workloads to get ACP, whereas what anybody really cares about is average power draw on the workload and peak power draw/cooling needs. ACP is just an average. It depends on process technology, the temperature the CPU is operating at, ambient temperature and more, making it mighty difficult for someone outside of AMD to calculate.

Meanwhile, SPECpower_ssj2008, is fairly unambiguous although AMD dislikes it because it feels it favours Intel. Well, the truth is, it does favour Intel a bit, but it wasn't purposefully set up that way. The reason is that the benchmark really loves cache and Intel has always had larger, faster caches than AMD. Shanghai has really gone a long way towards catching up with its big 6MB L3 cache, but the fact is, it still lags Nehalem.

Seriously, you AMD fanbois just need to get over the fact that AMD won't be competitive in the server market again until BD comes out, if then..

Wow, denial is strong here! Just plug your ears and go 'lalalalalla i can't hear you!', maybe the results will go away for you. 😉 As for your ACP theory, it's been debunked over and over. ACP does in fact equal intel's TDP but if you want max power, well let's just say you don't wanna go there. 😉

 

[Scotteq]

They're measures of the (estimated) amount of Heat which needs to be dissipated. Any connection to power consumption (real or imagined) is tenuous and misleading.

And they certainly are NOT the same measurement:

http://www.dailytech.com/AMD+Clarifies+ACP+TDP+Enigma/article9981.htm

Several processor architectures ago, AMD and rival Intel used the same methods for calculating Thermal Design Power with regard to microprocessors. From an engineering standpoint, the TDP represents the amount of power the cooling mechanism for the CPU must dissipate before failure.

AMD and Intel now differ with TDP calculations, and for different reasons. Intel's current architecture, for example, allows the CPU to exceed the TDP rating for a small period of time before the processor throttles its frequency clock in order to reduce the temperature at the processor level. AMD's current-generation processors do not practice this method, and thus AMD intentionally publishes conservative TDP ratings.

http://www.formortals.com/?p=137

We can easily verify that AMD’s ACP rating is not comparable to Intel’s TDP rating by looking at the actual performance of the newest AMD Shanghai based servers versus Intel’s current servers. When we look at the official published SPECpower measurements between an AMD “Shanghai” 2384 2.7 GHz system with an ACP rating of 75 watts and an Intel L5430 with a TDP rating of 50 watts with comparable components in the rest of the server, we would expect a power difference of roughly 50 watts (25W per processor) if AMD’s claim that AMD’s ACP was most comparable to Intel’s TDP rating. But according the official SPECpower benchmarks which is optimized for low power consumption, the Intel L5430 server peaks at 161 watts while the AMD 2384 based server peaks at 264 watts.

That’s more than a 100 watt delta and when we account for the fact that the Intel server has an additional North Bridge memory controller to deal with, the actual difference between the CPUs is even greater than 100 watts. We can negate the fact that the AMD server has two more memory DIMMs which consume an additional 8.4 watts of power because AMD uses hard drives that use 6 watts less power than the Intel system. This strongly suggests that an AMD TDP rating of 95 watts is far more likely to explain the 100 watt more power consumption than the Intel system with 50 watt TDP processors, so calling the “Shanghai” 2384 processor a 75 watt part simply doesn’t reflect the actual efficiency of the chip.

http://www.dailytech.com/AMD+The+Lies+About+Power+Consumption+Start+Here/article9955.htm

Look at those numbers closely. The first thing to notice is that TDP measurements are significantly higher than ACP. When AMD compared its power consumption figures to Intel's TDP, ACP measurements significantly underestimate power consumption. TDP differed between the two versions of the white paper by as much as 20 W, which is a 21% increase in the case of the quad-core Opteron. AMD did not increased its ACP estimates, emphasized in bold, despite the TDP increase.

Either the ACP is an arbitrarily measured system, and AMD changed it at will for its convenience, or AMD's document team failed to update the document properly. There is no other feasible explanation of why a 20 Watt TDP increase would be accompanied by no increase in ACP.

http://it.anandtech.com/show/2807/2

The only thing clear about the TDP numbers of AMD and Intel is that they are confusing and not comparable. It is clear that no power consumption or thermal design point number is going to make much sense to the server buyer unless the method of determining power consumption (or dissipation) is precisely defined by an independent third party. From that point of view, AMD Average CPU Power (ACP) only blurs the picture, even though it offers interesting information to those who are well informed about its purpose.

 

[jennyh]

Acer has sunk so bad in recent years that I would suggest e-machines over them, lol

Lol?

You do realise Acer took over Dell as #2 largest OEM last year, right? If that's them sinking, I sure am looking forward to them floating. :lol:

 

[roofus]

I consider Acer garbage but they are snapping at HP's heels.

 

[fazers_on_stun]

Wow, denial is strong here! Just plug your ears and go 'lalalalalla i can't hear you!', maybe the results will go away for you. 😉 As for your ACP theory, it's been debunked over and over. ACP does in fact equal intel's TDP but if you want max power, well let's just say you don't wanna go there. 😉

LOL - numerous links showing you wrong and yet you persist. Typical AMDZoner behavior, since that's the only place "it's been debunked over & and over" ..

I guess repetition of AMD marketing mantra is what passes for intelligent discussion there, in-between perma-banning people who fail to drink sufficient Koolaid of course

Face it, the industry is not buying AMD's ACP marketing crap. Just like they won't be buying Mega Corpulent crap 😀..

 

[fazers_on_stun]

Looks like one of AMDZone's moderators posted an April Fool's article about Bulldozer, and got himself into some hot water :

by MKruer on Thu Apr 01, 2010 7:41 am
Discuss and have fun
AMD Exclusive: Bulldozer
Edit: Yeah Yeah, forgot the system configs, will get them up tomorrow.
Yes it was joke, I accept full responsibility, I have corrected the article. John had no involvement sorry for besmearing your name and causing any problems.

What's hilarious however are the Zoner responses:

by stcollins on Thu Apr 01, 2010 9:03 am
What an incredible come back, AMD has once again proven that it is more than capable of re-creating X86.
Let's hope that this Bulldozer core will have a long and prosperous life.

I'm still in shock at how well this performs, i wonder what the pricing will be?

by Ozzyrulez on Thu Apr 01, 2010 9:07 am
Sweet Jesus, its beautiful! I will be getting my hands on one of these!

And my favorite:

by grunge100 on Thu Apr 01, 2010 1:32 pm
IMHO this is a pretty shitty April fools joke. A stunt like this can ruin the credibility of AMDZone. I hope for this sites sake that JF is able to forgive.

ROFL

 

[jennyh]

Why is anybody arguing about ACP or TDP?

It's ok, MC already won that one clearly. You can move on to something you might win at, but it won't ever be performance/watt. 😀

 

[BadTrip]

Lol?

You do realise Acer took over Dell as #2 largest OEM last year, right? If that's them sinking, I sure am looking forward to them floating. :lol:

Doesnt mean they arent JUNK.

 

[jennyh]

Doesnt mean they arent JUNK.

What are you saying, HP 'Walmart Edition' and Dell's are high quality pc's now? :lol:

 

[piesquared]

Face it, the industry is not buying AMD's ACP marketing crap. Just like they won't be buying Mega Corpulent crap 😀..

Well those are pure intel talking points right there. No doubt about it, and it's the same message they've been trying to get the online community to adopt for about 2 years now. Unfortunatly for intel, the industry doesn't fall for online viral marketing. They do the tests themselves, and in fact it is the industry that urged AMD to adopt a different thermal measurment as they were overspeccing their machines for a theoretical value that was never encountered. On the other hand, intel's max power for a 130W TDP nehalem is ~180W vs AMD's 80W ACP/125W TDP.

The numbers at the wall prove and bear this out. As per the charts that Jenny has posted. There's no denying for you intel pundits, face it.

 

[fazers_on_stun]

Well those are pure intel talking points right there. No doubt about it, and it's the same message they've been trying to get the online community to adopt for about 2 years now. Unfortunatly for intel, the industry doesn't fall for online viral marketing. They do the tests themselves, and in fact it is the industry that urged AMD to adopt a different thermal measurment as they were overspeccing their machines for a theoretical value that was never encountered. On the other hand, intel's max power for a 130W TDP nehalem is ~180W vs AMD's 80W ACP/125W TDP.

The numbers at the wall prove and bear this out. As per the charts that Jenny has posted. There's no denying for you intel pundits, face it.

LOL - sure, industry urged AMD to market its stuff better and lie about power consumption with bogus measurements .

The real reason why AMD wanted to get rid of TDP is because they didn't have thermal throttling like Intel did, so of course they had to spec their CPUs conservatively. Otherwise they probably would have been class-action sued by end-users with burnt-out CPUs.

 

[jennyh]

http://www.internetnews.com/hardware/article.php/3874276

 

[warmon6]

look randomizer, see what you did. you got all fan people arguing from both sides now. 😛 (not like thats hard to do......)