Sign in with
Sign up | Sign in
Your question

Official IBM Barcelona benches: INT and FP approx -10% to Xeons

Last response: in CPUs
Share
September 9, 2007 1:36:55 PM

From pdf:

SPEC CPU2006 Benchmark:
x3455 %u2013 Quad-Core AMD Opteron Model 2347 Processor (1.9GHz, 512KB L2 Cache per Core)

SPECint2006 11.3
SPECint_rate2006 83.2
SPECint_rate_base2006 72.8
SPECfp2006 11.2
SPECfp_rate2006 73.0
SPECfp_rate_base2006 68.5

Edited ...
September 9, 2007 2:13:09 PM

Nice find...

I guess it comes down to scalling...

Clock for clock at 1.86 vs 1.9 ghz these parts look pretty darn close.

Intel currently has a huge frequency lead, as AMD closes this gap will hypertransport allow AMD to pull ahead as the ghz gap closes?

On the other hand, can AMD ramp Barcelona speeds faster than Intel can ramp Penryn speeds..?
September 9, 2007 2:17:30 PM

the_vorlon said:
Nice find...

I guess it comes down to scalling...

Clock for clock at 1.86 vs 1.9 ghz these parts look pretty darn close.

Intel currently has a huge frequency lead, as AMD closes this gap will hypertransport allow AMD to pull ahead as the ghz gap closes?

On the other hand, can AMD ramp Barcelona speeds faster than Intel can ramp Penryn speeds..?


I agree. If the chips are close clock to clock it will be goodnight AMD. Intel's manufacturing is superior and has a lot more dollars at its disposal. AMD is trying to get 65nm to work while Intel is getting 45nm going.
September 9, 2007 5:42:50 PM

So, they were being retards with the NDA agreements. Yeah that's dumb, but who really cares other than the press guys?
September 9, 2007 5:46:06 PM

weskurtz81 said:
So, they were being retards with the NDA agreements. Yeah that's dumb, but who really cares other than the press guys?

anyone how reads the reviews and believ it is being objective
September 9, 2007 5:51:26 PM

BTW,

They said the press didn't sign the first NDA, they said they had to sign
a second NDA telling them they could not post confidential info without the approval of AMD.
"On Day 2 though, they were presented with another NDA to sign before a factory visit. This one stipulated that "any confidential information from this visit would need written approval from corporate communications before it could be used"". It seems that this website is being a little biased in the reporting because they end the article with

"It is highly probable that the same NDA will be used to force everyone to toe the line and publish only suitably-positive, pre-approved articles. It's either that or face the threat of lawsuits. So, keep that in mind when you wade through the inevitable deluge of articles and reports on the AMD Quad-Core Opteron (Barcelona) processor from tomorrow onwards" after they said the first crappy nda wasn't ever signed.

"Finally, AMD agreed to let Don and the other journalists attend the event without signing that particular NDA."

Am I reading this properly? It seems to me the first one wasn't used but the second one was for confidential information about the FACTORY visit. And it talked about CONFIDENTIAL information. Of course AMD might have some stuff in the factory they don't want being talked about. I would expect no less when it comes to the factory visit. So, where is the story in this article.... seems much to do about nothing.
September 9, 2007 6:08:54 PM

Wombat2 said:
So -7% on INT and +0.6% on FP clock for clock compared to Conroe class arches.


Whoa, this is WAAAY off what AMD has advertised recently. Then again, they likely aren't doing a clock-for-clock comparison...most likely TDP(Intel) vs. ACP(AMD) values. That would be like comparing a ~1.6Ghz Intel with a 2.0 Barcy...hmmm, not sure what to think of that just yet, but that would account for the AMD inflated numbers a bit.
September 9, 2007 6:18:23 PM

The real test will be when the hardware review sites get to do some hands on. The Spec benchmarks are interesting and do offer some insight but I am more interested in other benchmarks.

wes
September 9, 2007 6:30:37 PM

bixplus,

how was this 1.6ghz and 2.0ghz when it is clearly pretty close clock for clock? It's basically a 1.9ghz to a 1.86ghz.... not 1.6-2.0.
September 9, 2007 6:41:00 PM

weskurtz81 said:
bixplus,

how was this 1.6ghz and 2.0ghz when it is clearly pretty close clock for clock? It's basically a 1.9ghz to a 1.86ghz.... not 1.6-2.0.


I'm just comparing this to what AMD has advertised recently, that they'll be 20%-35%(or something like that...correct me if I'm way off) faster than Intel in some of these benches, but don't specify exactly what the Intel processor was/is. They seem to avoid the "clock-for-clock" verbiage, or I haven't seen it anyway...so I am only guessing that they are using some other metric to compare...in this case TDP vs. ACP. /speculation

Who knows, I could be way off on this...but do agree with you that the real test will be when third parties run their own benches.
September 9, 2007 6:46:05 PM

bixplus said:
I' They seem to avoid the "clock-for-clock" verbiage, or I haven't seen it anyway...so I am only guessing that they are using some other metric to compare...in this case TDP vs. ACP. /speculation
Who knows, I could be way off on this...but do agree with you that the real test will be when third parties run their own benches.



If these numbers are remotely accurate, then It looks like AMD is using the wishful advertising vs. reality comparison.
September 9, 2007 6:46:21 PM

bixplus,

further up the page wombat posted:
"For comparison:
Hewlett-Packard Company ProLiant DL360 G5 (1.86 GHz, Intel Xeon processor E5320):


http://www.spec.org/cpu2006/result [...] 00517.html
SPECint2006 = 11.9


http://www.spec.org/cpu2006/result [...] 00585.html
SPECfp2006 = 10.9


So -7% on INT and +0.6% on FP clock for clock compared to Conroe class arches. Will be +- -20% and +- -10% compared to Penryn arch."

I am assuming those numbers are accurate, and that is what i was basing my statement on. Regardless of the above data, we both seem to agree that the most important test will be the third party benchies from trusted sites. It doesn't look all that great atm, but who knows how it will turn out.

wes
September 9, 2007 7:06:57 PM

Wes, agreed, the IBM behches that Wombat posted do seem to indicate similarity on a clock-for-clock basis. I'm just trying to wrap my mind around what AMD was thinking with their inflated performance numbers when a clock-for-clock would indicate differently.

That leads to a further discussion of whether clock-for-clock is a valid comparison, which both manufacturers will use or ignore depending on how theirs' performs against compeition at a point in time. In this case, I'm postulating that AMD will avoid the clock-for-clock comparison and use it's own home cooked TDP vs. ACP instead. I'm also wondering if this is what is implied by the title "AMD's Quadcore: defending new found territory" found in this thread: http://www.tomshardware.com/forum/245039-28-anandtech-barcelona-review

September 9, 2007 7:17:35 PM

turpit said:
If these numbers are remotely accurate, then It looks like AMD is using the wishful advertising vs. reality comparison.


lol...yeah that would be bad!!
September 9, 2007 7:51:51 PM

the_vorlon said:
Nice find...

I guess it comes down to scalling...

Clock for clock at 1.86 vs 1.9 ghz these parts look pretty darn close.

Intel currently has a huge frequency lead, as AMD closes this gap will hypertransport allow AMD to pull ahead as the ghz gap closes?

On the other hand, can AMD ramp Barcelona speeds faster than Intel can ramp Penryn speeds..?


No (IMHO).

Firstly, I don't see AMD really closing the frequency gap. Intel is using a process which will go further in clock frequency than the process which AMD is currently using (Hi-K and smaller geometries versus SOI. Intel's process expertise versus AMD's. Intel's budget versus AMD's. I'm going to call that a clear win to Intel, although maybe it will be closer than I expect and it may end up being close to a draw. But I don't see AMD winning that battle.)

If the hypertransport bus gives AMD an edge, that will show up in the multi-socket arena. That is, 4 socket and 8 socket servers (each socket populated by a quad cpu... just don't think about the power consumption for home use) will hit the wall first. When this truly happens, Intel will have their new architecture which will circumvent this problem (and, judging by the things Intel has been patenting, it looks superficially like HT, but with some interesting refinements).

Then what happens is that some of the tech that intel has introduced into the multi-socket server space makes its way down into the desktop space.

So, if Intel were to leave their arch alone for ~5 years and just turn up the clock speed, this would be a problem, but they aren't that dumb, can see this coming and won't. Sorry. (Mind you, it does look as if they won't introduce it a minute before it is needed, either.)

So (in my opinion) AMD must have a better arch in clock for clock terms than Intel if they are to win, or even fight effectively, the performance war. They could go back to the socket 7 days when they didn't fight the performance war but offered better value in mid-range computing, but its not what I'm hoping for and I don't think its what you are hoping for either.
September 9, 2007 8:03:18 PM

weskurtz81 said:
bixplus,

further up the page wombat posted:
"For comparison:
Hewlett-Packard Company ProLiant DL360 G5 (1.86 GHz, Intel Xeon processor E5320):


http://www.spec.org/cpu2006/result [...] 00517.html
SPECint2006 = 11.9


http://www.spec.org/cpu2006/result [...] 00585.html
SPECfp2006 = 10.9


So -7% on INT and +0.6% on FP clock for clock compared to Conroe class arches. Will be +- -20% and +- -10% compared to Penryn arch."

I am assuming those numbers are accurate, and that is what i was basing my statement on. Regardless of the above data, we both seem to agree that the most important test will be the third party benchies from trusted sites. It doesn't look all that great atm, but who knows how it will turn out.

wes


Pre-frag.

NDA NDA NDA NDA NDA NDA NDA NDA NDA NDA NDA NDA NDA NDA NDA NDA NDA NDA
September 9, 2007 8:17:05 PM

TechnologyCoordinator said:
Pre-frag.

NDA NDA NDA NDA NDA NDA NDA NDA NDA NDA NDA NDA NDA NDA NDA NDA NDA NDA


lol...awe, man, come on. Is that all you can give us? :o 
September 9, 2007 8:36:53 PM

I think we have come to all valid conclusions on this argument. I agree with you bixplus. I am not sure how (if the above figures are accurate) in the world AMD came up with the numbers that they released in the past months. I know an employee of said company that keeps reassuring me that a release on the 10th will be a big one(won't say if ATI is releasing something too). This person seems sure AMD will come out with some good stuff tomorrow.

It seems now though that this good stuff cannot be the Barcy launch. I will reserve my end judgment of the CPU though. I want to see some 3rd party stuff.

wes
September 9, 2007 8:38:09 PM

what do you guys think about the NDA article posted above? It really doesn't seem like a big deal because none of the journalists signed the first NDA agreement.
September 9, 2007 8:44:04 PM

weskurtz81 said:
I know an employee of said company that keeps reassuring me that a release on the 10th will be a big one(won't say if ATI is releasing something too). This person seems sure AMD will come out with some good stuff tomorrow.

wes


Yeah, I've seen you mention this in other threads...got me real curious too.
September 9, 2007 9:09:01 PM

weskurtz81 said:
I think we have come to all valid conclusions on this argument. I agree with you bixplus. I am not sure how (if the above figures are accurate) in the world AMD came up with the numbers that they released in the past months. I know an employee of said company that keeps reassuring me that a release on the 10th will be a big one(won't say if ATI is releasing something too). This person seems sure AMD will come out with some good stuff tomorrow.
It seems now though that this good stuff cannot be the Barcy launch. I will reserve my end judgment of the CPU though. I want to see some 3rd party stuff.

wes


With all the hype from AMD this year, one has to question what they consider "big", or "good". Remember, the "Ulitmate Enthusiast System" turned out to be ultimate only in AMDs overestimation of its performance, and that AMDs idea of "Something Big" this summer turned out to be a tiny logo sticker, for a product which didnt exist, placed on the side of an F1 drivers helmet
September 9, 2007 9:21:29 PM

should this CPU have come out ages ago, pafetic
September 9, 2007 9:44:59 PM

turpit said:
With all the hype from AMD this year, one has to question what they consider "big", or "good". Remember, the "Ulitmate Enthusiast System" turned out to be ultimate only in AMDs overestimation of its performance, and that AMDs idea of "Something Big" this summer turned out to be a tiny logo sticker, for a product which didnt exist, placed on the side of an F1 drivers helmet


True that! Tomorrow will be tell tale. If K10 flops and there's nothing else announced/delivered that falls within this "BIG" category it'll do some serious damage to AMD cred. Not so much for the analysts community because they're easily fooled as history has proven, but the enthusiasts will be po'd and that'll send shockwaves through the community.
September 9, 2007 10:00:35 PM

bixplus,

I am not getting my hopes up, but I just can't help but wonder what the hell it is this person is talking about. This person is obviously aware of the performance of Barcy.... or this it seems. So either Barcy performs better than we think, they are going to come out with something on the SAME date(ATI or AMD based?)..... otherwise this person has been sniffing the same stuff the execs have been sniffing.

We will see tomorrow though....

Edit: this person won't give me the slightest clue whether it's AMD or ATI related.... but this person says it's a big deal. Now Barcy is obviously a big deal to AMD but it won't be a big(positive) deal if it under performs. This person eludes to something outstanding. Take it with a grain of salt as I have though.
September 9, 2007 10:05:10 PM

turpit, bixplus,

agreed with both of you. I am a fan of AMD (not fanboy). I hope they come out with something worth buying that way I can justify spending money on an AMD product. The current products aren't bad, just not as good as what the competition offers. ATI is getting better with each driver update but they still haven't released the enthusiast GPU yet. I was thinking the XTX might come around tomorrow.... but that is just opinion and nothing to back it up.
September 9, 2007 11:44:00 PM

weskurtz81 said:
bixplus,

I am not getting my hopes up, but I just can't help but wonder what the hell it is this person is talking about. This person is obviously aware of the performance of Barcy.... or this it seems. So either Barcy performs better than we think, they are going to come out with something on the SAME date(ATI or AMD based?)..... otherwise this person has been sniffing the same stuff the execs have been sniffing.

We will see tomorrow though....

Edit: this person won't give me the slightest clue whether it's AMD or ATI related.... but this person says it's a big deal. Now Barcy is obviously a big deal to AMD but it won't be a big(positive) deal if it under performs. This person eludes to something outstanding. Take it with a grain of salt as I have though.


Hmmm...coult it be that IBM is buying AMD?

Ok, don't even reply to that nonsense...my brain already hurts enough with all this speculation. :pt1cable: 
September 10, 2007 12:20:30 AM

weskurtz81 said:
Edit: this person won't give me the slightest clue whether it's AMD or ATI related.... but this person says it's a big deal. Now Barcy is obviously a big deal to AMD but it won't be a big(positive) deal if it under performs. This person eludes to something outstanding. Take it with a grain of salt as I have though.


Ok, one more speculation...this dave_graham dude seems to think that the latest stepping due upon release will be substantially faster than previous benches indicate:

http://www.xtremesystems.org/forums/showthread.php?t=158237&page=2 Post #31

Maybe that's the big news! ???
September 10, 2007 12:36:54 AM

Sounds like a good time to buy some put options on AMD.
a b à CPUs
September 10, 2007 12:40:25 AM





How come I can not find the exact same .pdf document when I do a search on IBM's site, nor do I find any x3455 benchmark documents dated past August 28th, 2007?!

Is this some magical pre-release document that doesn't show up unless you follow the above link. I did search on IBM's site and did not find the same document as the link above and either I'm failing to type "barcelona" or "quad core" or "AMD benchmarks" into IBM's search box incorrectly of something ain't right. I could not find the benchmark results on the SPECcpu site either.

Does wombat work for IBM or have some way of linking to a document that is not available on the public site?
September 10, 2007 2:54:58 AM

chunkymonster.....

it's on an FTP server. I didn't even bother looking at the lonk earlier.
http://www.google.com/search?hl=en&q=ibm+ftp+server&btn...
That would probably lead you to where it is being held.

Rodney_Ws,

Yeah, could be put time and could be call time. I am not convinced of either yet nor am I willing to get whacked. The market is so crazy right now that bad news from AMD combined with bad economic data would put an option so far out of the money that it would be hard to make it back up. Also, last I checked.... AMD options are pretty low volume and low return. Better off selling the stock short or buying shares.

bixplus,

Very interesting, that might just be what is going on. The early steppings might have had major issues that have since been worked out. I am very interested to see if this is the case. The guy does make a convincing argument and seems to actually have some insight in the matter. We shall see soon enough.
September 10, 2007 4:01:39 AM

weskurtz81 said:

Edit: this person won't give me the slightest clue whether it's AMD or ATI related.... but this person says it's a big deal. Now Barcy is obviously a big deal to AMD but it won't be a big(positive) deal if it under performs. This person eludes to something outstanding. Take it with a grain of salt as I have though.


Next node for ATI? The r600 was supposedly designed for a smaller node than it was released on, and I cant recall having seen anything regarding a shrink recently.
September 10, 2007 4:08:53 AM

That is what I was thinking. Nothing has been coming from ATI lately. It has been my thought that they might be releasing the 2950Pro variant and/or maybe the new high end version with a die shrink to 65nm. It just makes sense.... plus very little news has been coming from ATI for a while now.
September 10, 2007 4:20:18 AM

weskurtz81 said:
turpit, bixplus,

agreed with both of you. I am a fan of AMD (not fanboy). I hope they come out with something worth buying that way I can justify spending money on an AMD product. The current products aren't bad, just not as good as what the competition offers. ATI is getting better with each driver update but they still haven't released the enthusiast GPU yet. I was thinking the XTX might come around tomorrow.... but that is just opinion and nothing to back it up.


Yeah, I hope there is a suprise tomorrow, and its that Barcelona does perform better than C2D (nothing against Intel) regardless of all the BS from AMD this year. They've done so much, and if they fall, it will all be for nothing, and Intel will have an uncontest rule.
September 10, 2007 4:25:05 AM

weskurtz81 said:
http://www.fudzilla.com/index.php?option=com_content&ta...
http://www.vr-zone.com/?i=4188
http://maxpctech.blogspot.com/2007/08/hd-2950pro-rv670-...

Who knows though, September is around the correct time for sampling according to the articles, but maybe they already started. I think though if they did we would have had some leaked info.

Sounds interesting!!! With all the attention on AMD and Intel, and ATI now in AMDs grips (and no doubt the AMD lawyers have been writing the NDAs for ATI) seems very plausible that ATI could have sneaked this by the media. It would be great news for AMD and IMO would definately qualify as "big"
September 10, 2007 4:29:12 AM

rodney_ws said:
Sounds like a good time to buy some put options on AMD.


'Gutsy move Mav'......More power to you, I dont know that I would have the stomach to take that gamble with all those Senior Notes out there.
a b à CPUs
September 10, 2007 7:10:06 PM

weskurtz81 said:
chunkymonster.....

it's on an FTP server. I didn't even bother looking at the lonk earlier.
http://www.google.com/search?hl=en&q=ibm+ftp+server&btn...
That would probably lead you to where it is being held.
Yeah, I understand the document is on IBM's ftp site, and referring to a google search was pointless. But, my point is unless you follow the link in wombat2's thread, the barcelona benchmarks results can not be accessed any other way. A "worldwide" search at IBM's site still does not produce that particular .pdf.

Today is 9/10 and the document is still not available on IBM's public site.

Just seems a little funny that you can only find that document thru the link in the thread and not actually from IBM's benchmark web/ftp site.

September 10, 2007 8:17:20 PM

chunky,

Yeah I was never able to locate it without using the link. I am not sure what is going on with that pdf. I messed around with that all night long and wasn't able to figure out what was going on.

Turpit,

I went ahead and bit the bullet. I picked up a few hundred shares of AMD this morning. I really don't like messing with options on shares of AMD. I think PUTS will be a bad call at the moment. AMD has a product out now that can compete with Intel. That is good enough to drive the stock up. Also, the rating for AMD has been raised a little which will get all the mullets in there to push the stock up. Good luck though if you go short.

wes
September 10, 2007 9:20:49 PM

turpit said:
With all the hype from AMD this year, one has to question what they consider "big", or "good". Remember, the "Ulitmate Enthusiast System" turned out to be ultimate only in AMDs overestimation of its performance, and that AMDs idea of "Something Big" this summer turned out to be a tiny logo sticker, for a product which didnt exist, placed on the side of an F1 drivers helmet


you talk so much bullshit and critisies AMD on a per minute basis, your brillance in over seeing the market, and AMD's problem could either land you a job as Hector's new right hand man or Intel's Anti-AMD hooligan CEO...

but unfortunately you are not, you are just some guy who think he knows everything... :hello: 

My personal view is, we should wait, took Intel 3 years to find a solution to beat K8, took AMD 1 year for a solution to match Core, the chip is still in an early stage as we all agree, AMD had problems, and had to rush out the chip to meet the launch on the 10th Sep 2007...

We should be here to give our opions maybe on how AMD should improve the chip's performance, for example, some of you have mentioned cache size - very good (which Turpid did not manage to mention anything useful for the last 24 hours)

Wether meet the claimed performance or not, its called Marketing, Intel does the same thing, and has done so from day 1 until the day finally everyone relised that Pentium 4/D is NOT better than K8.

BMW M3 claims to have 350BHP, put the car on a real test, you will see you would get lucky to get 300BHP out of the car. Its all part of the harsh world we live in these days, and no 1 here is dumb enough to not relise what AMD said over the past a few months and what it is delivered, but we live with it, and move on, you just happen to having a faint about it, and over and over and over again... AMD let you down that much, sounded like you are considering jumping off a bridge and kill yourself...

RELAX .... TAKE A DEEP BREATH... there is life after Barcelona Launch Day...
September 10, 2007 10:56:42 PM

You're simplifying some things.

It took Intel 3 years to break free from the neck and neck competition with AMD typically barely on top to Intel is the top choice in every segment except some specialized markets.

If benchmarks from anand are reflected by others, it took AMD 1 year (although Barcy has been in development for far longer than a year) to bring the race alllllmost back to competative (just about there in the server market but the desktop market has nothing still). And this right in front of Intel's next major launch.

Methinks you paint too rosey a picture of AMD's position.

AMD's not licked and they should get a little breathing room (since they've been crushed under a rock for awhile), but they're certainly not soaring and won't be for a looooooong time, if ever.
September 11, 2007 2:53:12 AM

wolverino,

I would call it competitive not almost competitive. They are only behind on a clock speed basis. In that aspect I can agree with you but, the hardest part is over. They have released the cpu, now they will do what they always do and make it faster and more efficient with each revision.

One other thing, AMD beat Intel in almost every category except synthetics since dual core has been available. I am speaking of the PD's and X2's.
September 11, 2007 3:50:38 AM

Wow.... we start off with this...
pete4r said:
you talk so much bullshit and critisies AMD on a per minute basis, your brillance in over seeing the market, and AMD's problem could either land you a job as Hector's new right hand man or Intel's Anti-AMD hooligan CEO...

but unfortunately you are not, you are just some guy who think he knows everything... :hello: 


...and almost in the same breath you follow it up with this...
Quote:

My personal view is,


Quote:

RELAX .... TAKE A DEEP BREATH...

Physician, heal thyself.

September 11, 2007 4:58:09 AM

Just wanted to say, apparently investors were happy with the release. The stock was up quite a bit today so my decision to go long is working so far. At least one analyst raised AMD to the $15 range.

I am ready to sell it at a moments notice though!
!