Socket 1567 Xeon Nehalem-EX

[Drwho?]

I broke the argument down to say that in the end power at the wall is the best way to measure this. That has always been my position.

The rest of it IS confusing. Power at the wall is pretty straightforward, wouldn't you agree that it is a better way to compare?

No, it is not true either, because otherwise, you discard the level of performance at a given power watt usage.
It is much more complexe than this when you have a dynamic architecture.
It is OK to have high peak of power when you need a high peak of processing FLOPS or MIPS.
Soon, you ll tell us that your platform has better idle, so basically, your platform is better when you don't need it?
If you don't need it, don't buy it ...

Basically, Nehalem and westmere are scaling in Cores and core performance, provide the best today's avaivalble performance when you need it, and it is capable to step back to awesome idle power, all of this, at a maximize power usage for each level of load.
The problematic of choosing a server is not about comparing 2 or 4 numbers into 2 different PDF ... pretending it is as simple as this is "funny"

[Nedjo]

Before I clean the living crap out of this thread I want to say to you that this time Francois was right and fair in what he said.

See here's difference: I have no objection with you agreeing with dr. who, or for that matter I have no objection on anyones personal opinion, but apparently you have objection on my own! And what's worse, you have the power to simply shut me of if you don't like what I think!

He was replying to JF-AMD's comment and he works for AMD.
So do you from what I've been told.

we're in complitelly different line of business for AMD. he's insider, I'm not... but regardless we're both comming here as "JF-AMD" and "Nedjo" with our own personal opinions, not companye policies!

And that's crucial thing in this thread that in all your fairness you failed to see! Nor JF, nor my self are comparing AMD's and Intel's tech! JF made remark on power consumtion of Bextons, and dr. who slapped him with bunch of R_O_F_L_S and false acusations of FUD-ing!

Why haven't you reacted then?? What right does dr. who has in dishing out people from the thread just 'cos he has abjection with different opinion?

Doesn't we all have right to expose our own opinion about the subject? I agree on this with JF - Bexton is power hog ACORDING TO THE ARTICLE! NOT ACRODING TO AMD!!

XS is NOT the place for company employees to drop trou and have a "Whose is bigger" biatching match.
As I said politely earlier last night to one gentleman from a company: Tout your own product, don't dump on the other guy's.

Does that mean that I'm forbidden to express opinion on company "X" products? Or to comment on things written in some article about company "X" products?

I've seen this crap go on since I got here over 4 years ago.
When the hell are you children going to grow up?

Well you're taking this crap to seriously and personal... NHF!

It's a frigging processor not life or death and no matter how much either company dumps on the other it won't make a tinker's dam in your sales.
The public will decide that.

Exactly!! So why are you so persistent in trying to give so much seriousness to this beatching?!

So what if I don't agree with dr. who, and think of his company product differently than he (naturally) does? I'm I not entitled in expressing my opinion? Does he has some exclusive privileges on this forum? I don't think so!

Honest to God, I'd like to reach out and slap some damned sense into some of you and it's always the same people.I think I'll grab some coffee before I lose my temper and start handing out bans![/COLOR][/B]

well you do that! 'cos my friend you've taken this way to much serious.

On the other side, if it's forbidden to comment on anything that comes out from Intel just 'cos I prefer green instead of blue, just say so, and I'll obey the rule... 'cos after all this is not democracy this is forum, and you're mod, and I'm just a member

[Drwho?]

I am out to Game Dev conference, have fun guys!

[[XC] gomeler]

lol it doesn't get more fanboi than employees going at it.

The more cores you have side by side, the wider the CPU is.

the package is so large due to all the pads necessary. 1567 pads is a lot.. 2011 will be nuts.

But can it run Crysis?


I took it for the team. Seriously however, is this socket relevant to regular enthusiasts? What is the projected lifespan of 1366?

I should ban you for that.

[Hornet331]

Now on a more serious note: why has everything here degenerated this much and every thread has to be only about AMD??? For example the reply I got to my previous post was a flamebait ending in AMD something...

Oh theres a simple reason for that...

the package is so large due to all the pads necessary. 1567 pads is a lot.. 2011 will be nuts.

Yeah, but also dont forget, sandybridge has a GPU and a Quadcore cpu on one package, so its quite obvious why it needs that many pads.

[Fuji]

Oh theres a simple reason for that...

Yeah, but also dont forget, sandybridge has a GPU and a Quadcore cpu on one package, so its quite obvious why it needs that many pads.

unless it contains some features beneficial to the market which the Xeon-MP is marketed toward I don't see an integrated GPU on sandybridge.

http://news.softpedia.com/images/new...nveiled-2.jpeg

The GPU looks like it would take the die area of 1.5-2 cores.

and if the I/O hub is the server variant of the x58

http://www.hardwarecanucks.com/wp-co...-ex-8-core.jpg

In maintaining socket compatibility, I would speculate that the future Sandybridge based Xeon-MPs won't have the integrated PCI-E controller either.

[Movieman]

See here's difference: I have no objection with you agreeing with dr. who, or for that matter I have no objection on anyones personal opinion, but apparently you have objection on my own! And what's worse, you have the power to simply shut me of if you don't like what I think!

we're in complitelly different line of business for AMD. he's insider, I'm not... but regardless we're both comming here as "JF-AMD" and "Nedjo" with our own personal opinions, not companye policies!

And that's crucial thing in this thread that in all your fairness you failed to see! Nor JF, nor my self are comparing AMD's and Intel's tech! JF made remark on power consumtion of Bextons, and dr. who slapped him with bunch of R_O_F_L_S and false acusations of FUD-ing!

Why haven't you reacted then?? What right does dr. who has in dishing out people from the thread just 'cos he has abjection with different opinion?

Doesn't we all have right to expose our own opinion about the subject? I agree on this with JF - Bexton is power hog ACORDING TO THE ARTICLE! NOT ACRODING TO AMD!!


Does that mean that I'm forbidden to express opinion on company "X" products? Or to comment on things written in some article about company "X" products?


Well you're taking this crap to seriously and personal... NHF!


Exactly!! So why are you so persistent in trying to give so much seriousness to this beatching?!

So what if I don't agree with dr. who, and think of his company product differently than he (naturally) does? I'm I not entitled in expressing my opinion? Does he has some exclusive privileges on this forum? I don't think so!


well you do that! 'cos my friend you've taken this way to much serious.

On the other side, if it's forbidden to comment on anything that comes out from Intel just 'cos I prefer green instead of blue, just say so, and I'll obey the rule... 'cos after all this is not democracy this is forum, and you're mod, and I'm just a member

I'm going to tell you what the difference is in plain f-ing words that you better understand because I'm not repeating it again;
When a known AMD employee, especially one with your background of dumping on Intels products, come into an Intel thread it not only appears, but smells to high heaven of misinformation designed to delude, misinform and plain outright lie for the sole purpose of trying to gain market share.
This isn't the first time I've seen you pull this crap but I'm telling you it's the last time. Stay the hell out of the Intel threads if you know whats good for you or I'll toss your account into the barrel with all the other trolls and spammers.
Now I don't have a Beckton system so I can't speak to whether it runs hot, takes umtynine million watts to run it or not, JUST as I don't have a magny-cours system to see how it stands up.
When the systems hit the public( us) then we will know and only then based on what unbiased people have to say not company employees.

[Hornet331]

unless it contains some features beneficial to the market which the Xeon-MP is marketed toward I don't see an integrated GPU on sandybridge.

http://news.softpedia.com/images/new...nveiled-2.jpeg

The GPU looks like it would take the die area of 1.5-2 cores.

and if the I/O hub is the server variant of the x58

http://www.hardwarecanucks.com/wp-co...-ex-8-core.jpg

In maintaining socket compatibility, I would speculate that the future Sandybridge based Xeon-MPs won't have the integrated PCI-E controller either.

S2011 is rumored to be replacement for S1336 (and maybe S1156), it has nothing to do with the highend mp server socket.

I wouldn't be suprised if we see a totaly different socket for the next MP-Xeon, cause S1567 still will stay for some time.

[duploxxx]

No, it is not true either, because otherwise, you discard the level of performance at a given power watt usage.
It is much more complexe than this when you have a dynamic architecture.
It is OK to have high peak of power when you need a high peak of processing FLOPS or MIPS.
Soon, you ll tell us that your platform has better idle, so basically, your platform is better when you don't need it?
If you don't need it, don't buy it ...

well actually i showed before already in a few threads with power calculations of the largest OEM suppliers that it is like that , idle and medio core load is better on istanbul then Nehalem for E series. (not talking about the L series where you really own the market performance/power for the moment)

so not going into discussion about TDP/ACP/MAX TDP, for me they are all useless and I use the official power calculation tools from OEM, that way I can calculate max heat and power and compare real easy between platforms.

Basically, Nehalem and westmere are scaling in Cores and core performance, provide the best today's avaivalble performance when you need it,

keep those words just for a few days more, yes you will remain to have the fastest single threaded performance but there it will end for a large amount of applications.

Your little FUD on the power stuff should be kept on your own processors, you obviously don't understand the difference between electrical max power and Thermal max power, and I know why, your processors don't have a PCU, (power control unit), and you are trying to confuse people on it. Reality is that Nehalem and Westmere are able to make the difference between Electrical and thermal power, and we exploit this to provide maximum performance for a given TDP. Again, stay away from what you don t understand.

Francois

comparing a 2009 platform against 2006..... yeah again you are right there is no PCU in the old platform... just a few more days.

And NO i don't work for any CPU brand I just happen to decide what to buy for a few 1000 of both

[JPQY]

Just show me some Chess results and i know enough

http://www.xtremesystems.org/forums/...d.php?t=202139

JP.

[Movieman]

well actually i showed before already in a few threads with power calculations of the largest OEM suppliers that it is like that , idle is better on istanbul then Nehalem for E series. (not talking about the L series where you really own the market performance/power for the moment)

so not going into discussion about TDP/ACP/MAX TDP, for me they are all useless and I use the official power calculation tools from OEM, that way I can calculate max heat and power and compare real easy between platforms.



keep those words just for a few days more, yes you will remain to have the fastest single threaded performance but there it will end for a large amount of applications.

Lets settle this ok.
You name the benchmark that's closest to the type of application yopu have in mind. I'll run it this weekend on not a 16 core or 32 core Beckton but on a wimpy 12 core Westmere and we can see the results ok?
Pick the one that YOU want that factors in both cpu power and IO and lets show all these people some facts and get away from all this heresay..
How's that for fair? Yes?

[JPQY]

I'am a neutral player here..just use the chess program..all cores will run at 100%..i have many results to compare!
And eveyone will see these result in my list if i have the right screen and analyses!

JP.

[duploxxx]

Lets settle this ok.
You name the benchmark that's closest to the type of application yopu have in mind. I'll run it this weekend on not a 16 core or 32 core Beckton but on a wimpy 12 core Westmere and we can see the results ok?
Pick the one that YOU want that factors in both cpu power and IO and lets show all these people some facts and get away from all this heresay..
How's that for fair? Yes?

we had these discussion before you remember when i had woodcrest,barcelona,tigertown,shanghai beta. yes we could do that, but we never agreed on a test suite and accept for the fact that my MC beta is crunching on VMware vsphere all the time... don't worry you don' t have to wait that long anymore to see final reviews.

Again I am not going to start debating power consumption on a certain solution, i don't care, rule nr1 in for example VMware when running avarage load is to disable power management

Al I know is and those are facts, take powercalulations from large oem and compare them, you will see some amazing results.

I'am a neutral player here..just use the chess program..all cores will run at 100%..i have many results to compare!
And eveyone will see these result in my list if i have the right screen and analyses!

JP.

yes i know i told you i was going to provide date as soon as possible, but my MC didn't ship any default OS, no time for the moment to install a stupid MS OS on bare metal.

[s0lid]

I could swear i've seen that mobos picture at september or earlier when intel showed us the first becton (nehalem-ex) demos.

[poke349]

I'am a neutral player here..just use the chess program..all cores will run at 100%..i have many results to compare!
And eveyone will see these result in my list if i have the right screen and analyses!

JP.

I'm not entirely sure that a single benchmark will do.
As far as I know, all quad-socket machines are NUMA memory. So unless the program is written properly for NUMA, I don't think it will be a good benchmark for these machines.

Based on the results and posts in your thread. Your chess benchmark is highly bound by memory - as evidenced by single socket Core i7s beating out higher clocked skulltrails...
So it probably means that it won't be able to fully utilize these quad-socket machines. (mine can't either... since single-socket Core i7 can beat out quad-socket Barcelona...)

Of course, I have no other evidence to support this other than what's in your thread, but you get the idea...

[zalbard]

I am out to Game Dev conference, have fun guys!

Have fun you, too!

I should ban you for that.

Why? Isn't any thread about the performance not complete without this question?

And it'd be interesting to compare the performance of these vs. Magny Cours imo. I realise that performance per watt may be more important for server environments, but since most of us cannot afford any of these anyway, would be nice to at least see some mind blowing numbers!

[Fuji]

S2011 is rumored to be replacement for S1336 (and maybe S1156), it has nothing to do with the highend mp server socket.

I wouldn't be suprised if we see a totaly different socket for the next MP-Xeon, cause S1567 still will stay for some time.

i am aware that the sandybridge architecture in 2011 won't be the same one as the next gen 4P+ market however, the main architecture is the same.

Nehalem EX while it has its difference from Nehalem-EP has pretty much the same architecture.

I don't understand what you mean by:

"I wouldn't be suprised if we see a totaly different socket for the next MP-Xeon, cause S1567 still will stay for some time."

If you feel that S1567 will be around for a while, they wouldn't it be used for the sandybridge architecture? I think Intel knows that spending a thousand+ for a board only to replace it for the next upgrade is not logical.

[ibby]

hmmm Dave!

[mstp2009]

we had these discussion before you remember when i had woodcrest,barcelona,tigertown,shanghai beta. yes we could do that, but we never agreed on a test suite and accept for the fact that my MC beta is crunching on VMware vsphere all the time... don't worry you don' t have to wait that long anymore to see final reviews.

I smell chicken.


Put up or shut up.

[Drwho?]

Al I know is and those are facts, take powercalulations from large oem and compare them, you will see some amazing results.

well, you are taking about the "powercaculation" that are by OEM for price negociation ... lol ... you are more naive than I though if you believe those ... They are design to get your price down my friend ... wake up

I have a story for you ...

It is a man who go to a watch store, he ask to the clock master, do you have a clock that is red with green dot in the back ground ... then, he master says "hell no!"
Then , the customer says: "So, it is 10% off on the others" ...

lol man ... you are so funny some time.

[Hornet331]

i am aware that the sandybridge architecture in 2011 won't be the same one as the next gen 4P+ market however, the main architecture is the same.

Nehalem EX while it has its difference from Nehalem-EP has pretty much the same architecture.

I don't understand what you mean by:

"I wouldn't be suprised if we see a totaly different socket for the next MP-Xeon, cause S1567 still will stay for some time."

If you feel that S1567 will be around for a while, they wouldn't it be used for the sandybridge architecture? I think Intel knows that spending a thousand+ for a board only to replace it for the next upgrade is not logical.

meaning = S2011 is no MP socket and will be a different one than S2011. So S1567 will stay for some time, even when S2011 (or whatever is the socket for sandybridge) is around. When ever intel decides to release a replacement for nehalem EX i guess well see a new socket, but i don't think that will happen before 2013-14. It took nehalem ex 2 years and several months to be available after nehalem was released. Sof if it follows the same pattern and sandybridge comes beginning 2011 the eraliest date we can expect MP sandybridge will be 2013.

[mrcape]

Wow I haven't paid much attention to this type of hardware in a while, but as a former mainframe and midrange (AS400) ERP SE, it's insane to me to see this much power in a PC server. PC is officially no joke.

[clo007]

I love you all!!!

[Movieman]

Wow I haven't paid much attention to this type of hardware in a while, but as a former mainframe and midrange (AS400) ERP SE, it's insane to me to see this much power in a PC server. PC is officially no joke.

Imagine how I feel. I grew up with sliderules and adding machines.
Both companies look to have amazing products out this year.

[radaja]

Both companies look to have amazing products out this year

and just think what AMD and Intel will have in a few more years.its going to make
this years hardware look a little weak i cant wait till 2013-2014,its going to be
so sweet,because then i'll be able to play with this years hardware