Sign in with
Sign up | Sign in
Your question

Neal Nelson and Associates cheats on AMD TDP??

Last response: in CPUs
Share
January 18, 2008 2:08:23 AM



Some of you may remember Thundermans latest AMD thread here:
AMD used in Green low power consuming PC!

Now, this, according to ZDnet's own George Ou Beware of rigged CPU efficiency study

For those who arent familiar with Mr Ou, he has a nasty habit of sniffing out and publically exposing BS...much to the chagrin of those who would pull the wool over our eyes.

In his article, Mr Ou points out:

Quote:
Nelson compared AMD’s Opteron 2350 2.0 GHz quad-core processor (may not ship again until Q2-2008 when the TLB bug hopefully gets fixed) to Intel’s older 65nm “Clovertown” E5335 and E5345 processor which were released in Q4 2006. These weren’t even the newest 65nm G Stepping Clovertown processors from mid-2007 with lower power consumption; these were the older stepping released in 2006. But Intel launched their latest 45nm “Harpertown” processors in November of 2007 and these chips were excluded from this “study” on AMD versus Intel energy efficiency. This is a classic case where the measurements are most likely accurate, but what’s being measured isn’t.



First let me say that I am not using this to bash AMD.....they didnt do the study. They may or may not have provided hardware for the study, thus skewing it, but it is moot for my purposes, and the real culprit here is Neal Nelson and Associates for publishing what is a blatently biased study.

Second, I call on Thunderman to find us a recent study to back up his claims, rather than a single "cooked" study, reguritated by The Inq and FUDzilla.

Finally, to Mr Ou....well done and thank you very much for continuing to expose BS where it rises..
January 18, 2008 2:37:10 AM

All you have to do is look at the SPEC reports for power usage.

http://www.spec.org/power_ssj2008/results/power_ssj2008...

The only AMD system submitted finished 11th out of 12 places.

AMD is free to submit entries anytime they like.
If they COULD top the charts they clearly would submit results.

January 18, 2008 2:54:38 AM

Neal Nelson & Assoc. has always have the tendency to help out AMD in their studies. From the last three "studies" they published that I can remember, everyone of them favored AMD.

Now, while I'm not questioning Mr. Nelson's motive, it is definitely deceiving to,

1. Publish results based on completely different testing methodology (measuring total system power consumption, then claim power efficiency for a particular processor.)

2. Using outdated hardware for publication.

Although George Ou has been constantly criticized to be an Intel fanboy, but I always find his comments very insightful. I guess those who really has an idea of the background and the information are getting drowned by finger pointings.
Related resources
January 21, 2008 10:31:46 AM

All of my recent test results have shown the for some configurations or in some ways Intel was better, and for other configurations or in other ways AMD was better. The white papers that we publish with our test results show this quite clearly.

The last three papers have shown that for some common configurations and workloads AMD servers are more energy efficient. We believe that this is because Intel has standardized on FB-RAM and FB-RAM uses more power than the DDR2 used by AMD.

The test machines were configured to have very similar specifications. 2.0/2.33 GHz Xeons and 2.0 GHz Opterons. Identical RAM sizes, disks, operating systems, tunables, databases and transaction loads. We will test with Intel's 45 nm parts but these cpus are advertised as having similar power usage to the 65 nm parts, and Intel continues to use FB-RAM, so I don't expect to see any major changes in energy efficiency on the these new tests. Neal
January 21, 2008 11:05:47 AM

Do you have anything to refute George Ou's claims that you used outdated 65nm steppings from 2006 instead of the latest G0 steppings?

I can assure you 45nm will cut down on power dramatically compared to 65nm. I wouldn't judge a CPU purely by the 'advertised TDP' - surely a person of your position would realise that.
a b à CPUs
January 21, 2008 11:09:07 AM

More Intel Fanboi crap ...

Is this any different to thunderman's posts? Hmm?? Not really ... just the opposite flamebait.

Well the OP is more literate ... the argument is simply the opposite.

Waiting for the horde to descend ...
Bit slow today ...

Next ... the comments about AMD lying ... ho hum ... it's getting old now guys.

Lets talk about the lies Intel told about the end of line Netburst Prescott CPU's eh??

130W TDP ... more like 145W ... burned out two mobos on the THG endurance test. It's on record If anyone cares to link it. The HSF's could not keep up either ... despite being boat anchors.

Lets talk about the RAM power draw on them Intel Servers too .... ouch !!!

Lets talk about scaling past a few sockets ... high end servers are still AMD only .... FSB is just too bandwidth limited.

Lets talk about paying companies not to buy AMD products.

Lets talk about the Penryn Errata ??

http://www.dailytech.com/Intel+Explains+45nm+Delays+Err...

Stability problems due to 4 layer mobos?? Or is it the FSB can't be stretched anymore and the "noise" threshold is too close to the signal?

All in all cranking the FSB up to 1600 should effectively squash the overclockers from getting more headroom out of the silicon tho.

That will be a showstopper till Nehalem.

Intel cares for you ... LOL
January 21, 2008 11:29:05 AM

Reynod said:


All in all cranking the FSB up to 1600 should effectively squash the overclockers from getting more headroom out of the silicon tho.


Somebody should test the max the FSB can go without getting unusable. I mean there must be a wall somewhere. Anybody have the time to lower his cpu multiplier and see if he can find a wall to the FSB on a current board? It might be far tho so don't burn anything only for this.
January 21, 2008 11:31:55 AM

frostys said:
Somebody should test the max the FSB can go without getting unusable. I mean there must be a wall somewhere. Anybody have the time to lower his cpu multiplier and see if he can find a wall to the FSB on a current board? It might be far tho so don't burn anything only for this.


On most quads the limit is between 450-500 MHz QDR. On Duals it's between 500-550ish MHz QDR. More on water.. and I've seen over 600 at times, but it's rare.

Edit: Btw, it doesn't kill overclocking. The current planned 1600 MT/s FSB processors are all EE's and have an unlocked multiplier. The rest of the processors are still running on the 1333 MT/s FSB.
a b à CPUs
January 21, 2008 11:33:26 AM

Dividers ??


LOL
January 21, 2008 11:58:09 AM


The test machines were configured to have very similar specifications. 2.0/2.33 GHz Xeons and 2.0 GHz Opterons. Identical RAM sizes, disks, operating systems, tunables, databases and transaction loads. We will test with Intel's 45 nm parts but these cpus are advertised as having similar power usage to the 65 nm parts, and Intel continues to use FB-RAM, so I don't expect to see any major changes in energy efficiency on the these new tests. Neal[/quotemsg said:


Now, Let's assume that the only thing that matters is "Advertised" TDP.

Since we are talking about Power Usage based upon workload, you are still skewing the results.
Why Test a 2.33 Ghz part when a 3.0Ghz part has the same TDP?
Does your comment also seem to ignore general improved performance of the Penryn?
This alone should lead to a 1/3 increase in relative performance.

3.00 TDP 80w - http://processorfinder.intel.com/details.aspx?sSpec=SLA...


While there is no doubt some tests in which AMD servers excel, I use them for running VMWare ESX Servers, your statements do not show as somebody who is trying to forthright testing, but rather somebody who crafts a test to obtain the desired results.

It's best not to fool those with technical understanding.

#1) Yes, It is true that the memory for Intel servers require more power than those used in AMD Servers.
#2) Yes, It is true that Intel had released newer 65nm parts that cut power but you chose not to use those.
#3) Yes, It is true that Intel released newer 45nm parts that both cut power and increased performance, but you chose not to use those.
#4) Yes, It is try that Intel has processors nearly one-third faster with the same TDP but you chose to use the slowest CPUs so as to maximize the effect of the less efficient memory and minimize the effect of the more efficient CPU.
#5) Yes, you used AMD processors that are not generally available but failed to use the latest Intel processor that have been available for months.


Please Don't Bring arguements to the table that assume the readers here are ignorant.
As a whole, we are not.
Those statements may fly for those without sufficient technical knowledge, but here they seem to just reinforce your agenda.
January 21, 2008 12:17:56 PM

Quote:
Get a life people. Who cares?? If you feel the need to post or argue about cpu tdp, then you really have no life do you?


Says the person who has so little life they feel the need to point out to others who are debating topics they are passionate about to get a life..

It's a Hardware site, what do you expect? Do you think we are going to talk about cars or what we did over the weekend? If stuff like this bothers you.. you might want to consider leaving!
a b à CPUs
January 21, 2008 12:25:48 PM

Were you talking to someone?


Anonymous
January 21, 2008 12:27:13 PM

Quote:
Get a life people. Who cares?? If you feel the need to post or argue about cpu tdp, then you really have no life do you?



Shut your cake-hole bytch. You seem to always have time to post your stupid rants about other peoples topics. Go back to your hole.

If people can find out lies or deception about article and news, which is about 90% of the media today then let it be told. It only benefits everyone as a consumer.
January 21, 2008 12:30:18 PM

Seems like Neal is being called out by a few other people. His excuse for using the older intel chips seems pretty weak. Neal said, "The 65-nm (Intel) parts are being shipped in volume to customers today, so those are the parts that I was able to borrow to run these tests." While the 45nm chips are not shipping in volume, at least they are shipping, unlike the Barcelona chip that hasn't begin to be shipped. Which by the way he declined to say where he got it from...hmm.

http://searchdatacenter.techtarget.com/originalContent/...
Anonymous
January 21, 2008 12:39:19 PM

qurious69ss said:
Seems like Neal is being called out by a few other people. His excuse for using the older intel chips seems pretty weak. Neal said, "The 65-nm (Intel) parts are being shipped in volume to customers today, so those are the parts that I was able to borrow to run these tests." While the 45nm chips are not shipping in volume, at least they are shipping, unlike the Barcelona chip that hasn't begin to be shipped. Which by the way he declined to say where he got it from...hmm.

http://searchdatacenter.techtarget.com/originalContent/...



LoL yet he used a not to common AMD chip. That is what is very "ODD"
a b à CPUs
January 22, 2008 8:51:18 AM

Hmm ... manufacturers always want to present their best face.

Like when the hardware sites were benching Intel Cpu's that you just couldn't buy ?

Like them Penryn quads with the errata ...

Seems to be a problem with the double cheeseburger deluxe ... must be the sauce or something ??

The might be short on the buns ...

heh heh.

I tease in jest.

January 22, 2008 1:53:23 PM

Reynod said:
Hmm ... manufacturers always want to present their best face.

Like when the hardware sites were benching Intel Cpu's that you just couldn't buy ?

You mean, Barcelona? :lol: 

Quote:
Like them Penryn quads with the errata ...

...or Phenom....

Quote:
Seems to be a problem with the double cheeseburger deluxe ... must be the sauce or something ??

...or "Native quad is real" propaganda? :kaola: 

Its normal for companies to send in their soon to be released products to 3rd party manufacturers for preview. But maybe its better to fly a bunch of journalist to bench in a complete controlled environment, or NDA the press to the point of ridiculous? :sol: 
January 23, 2008 12:02:15 AM

[.....sigh]
OK Reynod, I'll play.


Reynod said:
More Intel Fanboi crap ...


Yes yes, we know, George Ou is an Intel fanboy. Im an Intel fanboy, no wait, Im an AMD fanboy, no wait, which is it? Im confused, Ive been called both so many times I dont know. Just choose your line and get in it. It always easier to call someone a fanboy because you dont like what they say rather than read or comprehend and then make the judgement

Reynod said:

Is this any different to thunderman's posts? Hmm?? Not really ... just the opposite flamebait.


Hardly. This is called a rebuttal. Its what you do when debating. Im sorry, if you want this to be an "All AMD, All the Time, All Positive" forum. Visit AMDzone (how was that for a fanboy implication without actually saying it? ;)  )

Reynod said:

Well the OP is more literate ... the argument is simply the opposite.

No, its not. It is a presentation of information which refutes Neal Nelsons claim, and points out that he was either spinning data to support that claim rather than systematically, scientifically testing all options and and using the results to reach a conclusion, or that he doesnt know what hes doing. It has nothing to do with the 'opposite'.

Reynod said:

Waiting for the horde to descend ...
Bit slow today ...

Next ... the comments about AMD lying ... ho hum ... it's getting old now guys.


Really? A manufacturer misrepresenting its products in such a manner as to make them appear to be something they're not is getting "old"? I dont think so, but hey, I know someone who has a Ford Feista for sale. Best car ever. Trust me, why dont you buy it. It really is the best because I said so. Dont bother reading Consumer Reports or Road & Track or anything....just take me at my word. ;)  :kaola: 

Reynod said:

Lets talk about the lies Intel told about the end of line Netburst Prescott CPU's eh??


Cool. Here, I'll help you start. Netburst was crap and Intel lied to cover that fact. :hello:  Anyone want to dispute that? :pfff:  No? :ouch:  Well, guess theres nothing to talk about there since everyone seems to be in agreement about netburst.

Maybe thats why AMD, and not Intel keeps coming up. Everyone knows Netburst was crap and Intel lied about it. No one denies it and Intel suffered for it. Not everyone seems to have caught on that AMD has been lying and spinning though, and there are still those who deny it and contrive to convince others that AMD is "pure as the driven snow". Once people accept that AMD lied, and stop trying to spread more BS or spin AMD's lies away, then you'll see furor over this issue subside.

Reynod said:

130W TDP ... more like 145W ... burned out two mobos on the THG endurance test. It's on record If anyone cares to link it. The HSF's could not keep up either ... despite being boat anchors.


And Im sure we can find records showing AMD doing the same. As long as we are grave digging (Netburst), lets dig up Socket A Athlon, anything above a 2400XP will do. Those things sucked so much power and ran so hot that if you so much as looked at them crosseyed they would cook. Thats on record too, and 'getting old' as well. But if you want to build a new Netburst or AthlonXP machine, then I suppose its not grave digging, and it would certainly be relevent. What about it? Anyone planning on a 'new' Netburst or AthlonXP machine? :hello: 

Reynod said:

Lets talk about the RAM power draw on them Intel Servers too .... ouch !!!


Yes please lets. If you read the title of Mr Nelsons 'study', It wasnt termed 'AMD servers use less energy' it was titled, precisely:
'Throughput and Power Efficiency for AMD and Intel Quad Core Processors'.
Not:
'Throughput and Power Efficiency for AMD and Intel Quad Core Processor power server systems'
nor
'Effect of FB Ram on Throughput and Power Efficiency for AMD and Intel Quad Core Processor Servers'


Had it been titled correcly, had it been thorough and had it emphasized the specifics that Mr Nelson has been scrambling to publicize in his defense, there would be no problems. Why? Because, FB RAM does use more power. A butt load of it. No one is denying that, and if they were, I say they lied like AMD. But again, Mr Nelsons study said "....Processors....". Not "....systems....", not "....components....". The title specifically targeted the processors. He made a statement, incorrect at that, based on an incomplete 'study', using a limited product range. The kind of study that would have seen him fired any real consulting firm.

Reynod said:

Lets talk about scaling past a few sockets ... high end servers are still AMD only .... FSB is just too bandwidth limited.


Yes, you're right. But that wasnt the topic of the study. The topic was the the Nelson study 'Throughput and Power Efficiency for AMD and Intel Quad Core Processors'. . Changing the subject to divert attention doesnt change the fallacy presented by the study.

Reynod said:

Lets talk about paying companies not to buy AMD products.


Please yes lets do. Lets talk about how effective it was. It was so effective, that while AMD had the undisputed superior product, Intel was successful in losing over a quarter (almost 1/3) of the market to AMD. Intel was so successful that AMD hit manufacturing capacity and was able hold ASPs and thus margins comfortably high due to demand for thier superior product. Why? Because Intel had nothing to compete with except PR. During that time AMD proved, conclusively, that performance talks, BS walks. Inspite of any alleged, alleged wrong doing on Intels part. And do you know what the irony of that is? If Intel really commited those alleged acts, then every single penny they spent was a penny wasted since it did nothing to hold AMD back. I can talk about that all day long. I find it hugely amusing...a slap in the face to Intel if they really did anything illegal, and a slap in the face to all the AMD fanboys who cry Intel held AMD back, since in fact AMD wasnt held back....not in the least. And the quarterly and yearly statements prove they werent held back. In fact, considering how AMD disenfranchised the channel the second they got their hands on a Dell contract, if I were AMD, I'd be praying for more of the alleged wrong doing from Intel, since AMD was doing so well while it was supposedly going on.


Reynod said:

Lets talk about the Penryn Errata ??

http://www.dailytech.com/Intel+Explains+45nm+Delays+Err...


Stability problems due to 4 layer mobos?? Or is it the FSB can't be stretched anymore and the "noise" threshold is too close to the signal?

All in all cranking the FSB up to 1600 should effectively squash the overclockers from getting more headroom out of the silicon tho.

That will be a showstopper till Nehalem.

Cool, lets talk about it. How many Penryns has Intel had to stop ship? Whats the clockspeed limit for DT?

Did you read the article you linked to? There is not mention of FSB frequencies, or PCB layers. Heres a good quote from that article:

Quote:
Previous reports of errata degrading the L2 and L3 cache performance were described as "false" -- desktop Penryn processors do not even have L3 cache. Microcode and BIOS updates issued by Intel since November do not fix or address the "showstopper" bug affecting the launch of the quad-core Q9300, Q9450 and Q9550 processors.

The condition does not affect Xeon quad-core processors. Xeon uses a different stepping than the quad-core processors, which fixes this simulated condition. The quad-core 45nm Extreme Edition processor launched in November is also unaffected.




Reynod said:

Intel cares for you ... LOL

Who said that? I didnt. But Im glad you did, because it demonstrates a mentality. If Intel doesnt care for you, who does? AMD? Someone must care for you, and if its not Intel, it must be AMD, right? I disagree. Niether AMD nor Intel care for us. They care for our money. And thats whats really got the AMD fanboys panties in a bunch. AMD proved they could care less about the customer. If they really did, they wouldnt have lied to us. And thats what AMD did, and thats what the fanboys cant accept, and thats why they spin the lies and the facts. Because they company they love, that claimed it loved them, proved it dosent really love them.


Are we having fun yet? :??: 
January 23, 2008 12:21:09 AM

If I quote Turpit, will I get banned? :lol: 

Way too long...

But I agree with most of it :p 
January 23, 2008 12:21:31 AM

NealNelson said:
All of my recent test results have shown the for some configurations or in some ways Intel was better, and for other configurations or in other ways AMD was better. The white papers that we publish with our test results show this quite clearly.

The last three papers have shown that for some common configurations and workloads AMD servers are more energy efficient. We believe that this is because Intel has standardized on FB-RAM and FB-RAM uses more power than the DDR2 used by AMD.

The test machines were configured to have very similar specifications. 2.0/2.33 GHz Xeons and 2.0 GHz Opterons. Identical RAM sizes, disks, operating systems, tunables, databases and transaction loads. We will test with Intel's 45 nm parts but these cpus are advertised as having similar power usage to the 65 nm parts, and Intel continues to use FB-RAM, so I don't expect to see any major changes in energy efficiency on the these new tests. Neal



Mr Nelson, the title of you study says:

"Throughput and Power Efficiency
for
AMD and Intel Quad Core
Processors"

It does not say, 'a comparison of server system configurations'.
It does not say, 'a comparison of server system components'
It makes a blanket statement......"AMD and Intel Quad Core Processors", but not a 'blanket' test.

Your study does not cover all possible configurations.
Your study does not cover all available options.
Your study does compare old technology to new technology.
Your study is limited to 3 processors, out of dozens, yet carries all inclusive that all inclusive title:
"Throughput and Power Efficiency
for
AMD and Intel Quad Core
Processors"
...rather than....
"Throughput and Power Efficiency
for
AMD 2350 Barcelona and Intel E5335/E5345 Clovertown Quad Core
Processors".


I find it incredulous that you continue to defend your study and your methodolgy.
You chose to make the blanket statement, not we the consumers. You chose to limit the test subjects, not we the consumers. You refer to your customers, yet you release this data publically. Honestly, niether I nor the vast majority of intelligent members here need to see your data, as we know where to find the power requirements elsewhere, and frankly from more reputable sources.

Perhaps, in the future, to avoid having to defend yourself, you should limit the release of your studie's 'results' to those who pay for them.

January 23, 2008 12:24:11 AM

Evilonigiri said:
If I quote Turpit, will I get banned? :lol: 

Way too long...

But I agree with most of it :p 


Yes.

Meh, Reynod seemed to be having some fun, so I thought Id join in. No law against that, or you joining in, as long as you dont start calling Reynod names. Unless its fanboy :kaola: 
January 23, 2008 12:28:44 AM

turpit said:
Yes.

Meh, Reynod seemed to be having some fun, so I thought Id join in. No law against that, or you joining in, as long as you dont start calling Reynod names. Unless its fanboi :kaola: 


Fixed.
January 23, 2008 12:57:12 AM

Turpit, well put. Those posts should probably be a thread ender. Oooouuuch!

Of course now we will get a bunch of BS posts in defense of AMD.
January 23, 2008 1:09:09 AM

turpit said:
[.....sigh]
OK Reynod, I'll play.




Yes yes, we know, George Ou is an Intel fanboy. Im an Intel fanboy, no wait, Im an AMD fanboy, no wait, which is it? Im confused, Ive been called both so many times I dont know. Just choose your line and get in it. It always easier to call someone a fanboy because you dont like what they say rather than read or comprehend and then make the judgement



Hardly. This is called a rebuttal. Its what you do when debating. Im sorry, if you want this to be an "All AMD, All the Time, All Positive" forum. Visit AMDzone (how was that for a fanboy implication without actually saying it? ;)  )


No, its not. It is a presentation of information which refutes Neal Nelsons claim, and points out that he was either spinning data to support that claim rather than systematically, scientifically testing all options and and using the results to reach a conclusion, or that he doesnt know what hes doing. It has nothing to do with the 'opposite'.



Really? A manufacturer misrepresenting its products in such a manner as to make them appear to be something they're not is getting "old"? I dont think so, but hey, I know someone who has a Ford Feista for sale. Best car ever. Trust me, why dont you buy it. It really is the best because I said so. Dont bother reading Consumer Reports or Road & Track or anything....just take me at my word. ;)  :kaola: 



Cool. Here, I'll help you start. Netburst was crap and Intel lied to cover that fact. :hello:  Anyone want to dispute that? :pfff:  No? :ouch:  Well, guess theres nothing to talk about there since everyone seems to be in agreement about netburst.

Maybe thats why AMD, and not Intel keeps coming up. Everyone knows Netburst was crap and Intel lied about it. No one denies it and Intel suffered for it. Not everyone seems to have caught on that AMD has been lying and spinning though, and there are still those who deny it and contrive to convince others that AMD is "pure as the driven snow". Once people accept that AMD lied, and stop trying to spread more BS or spin AMD's lies away, then you'll see furor over this issue subside.



And Im sure we can find records showing AMD doing the same. As long as we are grave digging (Netburst), lets dig up Socket A Athlon, anything above a 2400XP will do. Those things sucked so much power and ran so hot that if you so much as looked at them crosseyed they would cook. Thats on record too, and 'getting old' as well. But if you want to build a new Netburst or AthlonXP machine, then I suppose its not grave digging, and it would certainly be relevent. What about it? Anyone planning on a 'new' Netburst or AthlonXP machine? :hello: 



Yes please lets. If you read the title of Mr Nelsons 'study', It wasnt termed 'AMD servers use less energy' it was titled, precisely:
'Throughput and Power Efficiency for AMD and Intel Quad Core Processors'.
Not:
'Throughput and Power Efficiency for AMD and Intel Quad Core Processor power server systems'
nor
'Effect of FB Ram on Throughput and Power Efficiency for AMD and Intel Quad Core Processor Servers'


Had it been titled correcly, had it been thorough and had it emphasized the specifics that Mr Nelson has been scrambling to publicize in his defense, there would be no problems. Why? Because, FB RAM does use more power. A butt load of it. No one is denying that, and if they were, I say they lied like AMD. But again, Mr Nelsons study said "....Processors....". Not "....systems....", not "....components....". The title specifically targeted the processors. He made a statement, incorrect at that, based on an incomplete 'study', using a limited product range. The kind of study that would have seen him fired any real consulting firm.



Yes, you're right. But that wasnt the topic of the study. The topic was the the Nelson study 'Throughput and Power Efficiency for AMD and Intel Quad Core Processors'. . Changing the subject to divert attention doesnt change the fallacy presented by the study.



Please yes lets do. Lets talk about how effective it was. It was so effective, that while AMD had the undisputed superior product, Intel was successful in losing over a quarter (almost 1/3) of the market to AMD. Intel was so successful that AMD hit manufacturing capacity and was able hold ASPs and thus margins comfortably high due to demand for thier superior product. Why? Because Intel had nothing to compete with except PR. During that time AMD proved, conclusively, that performance talks, BS walks. Inspite of any alleged, alleged wrong doing on Intels part. And do you know what the irony of that is? If Intel really commited those alleged acts, then every single penny they spent was a penny wasted since it did nothing to hold AMD back. I can talk about that all day long. I find it hugely amusing...a slap in the face to Intel if they really did anything illegal, and a slap in the face to all the AMD fanboys who cry Intel held AMD back, since in fact AMD wasnt held back....not in the least. And the quarterly and yearly statements prove they werent held back. In fact, considering how AMD disenfranchised the channel the second they got their hands on a Dell contract, if I were AMD, I'd be praying for more of the alleged wrong doing from Intel, since AMD was doing so well while it was supposedly going on.



Cool, lets talk about it. How many Penryns has Intel had to stop ship? Whats the clockspeed limit for DT?

Did you read the article you linked to? There is not mention of FSB frequencies, or PCB layers. Heres a good quote from that article:

Quote:
Previous reports of errata degrading the L2 and L3 cache performance were described as "false" -- desktop Penryn processors do not even have L3 cache. Microcode and BIOS updates issued by Intel since November do not fix or address the "showstopper" bug affecting the launch of the quad-core Q9300, Q9450 and Q9550 processors.

The condition does not affect Xeon quad-core processors. Xeon uses a different stepping than the quad-core processors, which fixes this simulated condition. The quad-core 45nm Extreme Edition processor launched in November is also unaffected.





Who said that? I didnt. But Im glad you did, because it demonstrates a mentality. If Intel doesnt care for you, who does? AMD? Someone must care for you, and if its not Intel, it must be AMD, right? I disagree. Niether AMD nor Intel care for us. They care for our money. And thats whats really got the AMD fanboys panties in a bunch. AMD proved they could care less about the customer. If they really did, they wouldnt have lied to us. And thats what AMD did, and thats what the fanboys cant accept, and thats why they spin the lies and the facts. Because they company they love, that claimed it loved them, proved it dosent really love them.


Are we having fun yet? :??: 


:bounce:  :bounce:  :bounce: 

Word, Playa.
a c 122 à CPUs
a b À AMD
January 23, 2008 1:45:47 AM

Rock on turpit. Thats why you have my respect. Funny thing is they could have even just gotten the QX9650 back since November and yet they used older 65nm parts. Not even a G0 stepping which is now the only thing you can get really or the 45NM parts which are fine. Yet do use a unfindable until B3 maybe Opteron.

I found it weird when I read that article at work. Just didn't seem right. Thanks for the info though turpit.
a b à CPUs
January 23, 2008 4:47:16 AM

Well I had (it got off) a 3000lb trout (turpit) on a 5lb line (AMD's) and the mongrel just jumped into my boat (heavily refinanced) and sank it.

< swims back to shore ... shakes fist at sky >

Turpit ... I beg you ... please keep your posts inside the thesis word limit or I shall have to fail you next time for excessive verbiage !!

Kind regards,

fanboi on the run :) 

P.S. I imagine you spent a good hour on that reply ... or more. Was that on company time ... or did I cut into your "drinking" time??
January 23, 2008 5:06:19 AM

This study also conveniently ignores Intel's new 5100 chipset that allows the use of registered DDR2 over FB-DIMM memory with DP Xeon systems.

This study uses Opteron CPUs that won't be available until 2Q 2008, and compares them against Intel CPUs from 2006. I think that shows right there how pathetic this comparison is.

If Neal Nelson wants to compare energy effiency, why didn't he use the most energy efficient Intel system that one could buy? That is, a 5100 chipset board, a pair of 50W Xeons and 4, 8 or possibly even 16GB of RDDR2 memory.
January 23, 2008 6:38:28 AM

Reynod said:
Well I had (it got off) a 3000lb trout (turpit) on a 5lb line (AMD's) and the mongrel just jumped into my boat (heavily refinanced) and sank it.

< swims back to shore ... shakes fist at sky >

Turpit ... I beg you ... please keep your posts inside the thesis word limit or I shall have to fail you next time for excessive verbiage !!

Kind regards,

fanboi on the run :) 

P.S. I imagine you spent a good hour on that reply ... or more. Was that on company time ... or did I cut into your "drinking" time??


No offense but...

I think you just got conclusively owned...
January 23, 2008 7:03:41 AM

Gee Mandrake, it's not that I hate you but
Quote:
This study also conveniently ignores Intel's new 5100 chipset that allows the use of registered DDR2 over FB-DIMM memory with DP Xeon systems
have you seen what the slower interface does to the xeon's I/O numbers?
Without FBdimms even the single quad xeon stations will loose out badly to the barcelonas.
January 23, 2008 7:09:16 AM

Quote:
I think you just conclusively owned...

It's not wise to fool with Turpit. He is the most well informed mod we have, even if he is a fanboy.
Dont you just hate those performance fanboys.
a b à CPUs
January 23, 2008 7:36:01 AM

You know what, you come in with a title that again a AMD processor has not worked as well as everyone expected on the power efficiency and AMD has got some one to lie on proberly their behalf because they like AMD so much.....

Just like if GM or Ford made a crap car, they need to be justifiable slated for it, but for one or the either to say such stupid claims that it can do this or that is just un-remarkable......

Turpit, I dont think your a fanboy, you just want kit that does what it says on the box, but even if you were bias, its your choice - your the forum master so the others can get over it.

If it does anymore than that then you in for a bonus - as with the Intel Core 2 Duo Quad Q6600 processorat that remarkable cheap price.

AMD owners or followers or extremists as you might call them, that Intel have made a better, bugless, overclocking, faster processor than anything that AMD have produced SO FAR.....

I may take the mickey in my previous threads, but the Phenom was a crap name and its looking to be a bit of a crappy processor like the K9 before it ( does any AMD fan talk about the abomination of the mega expensive 4x4 platfrom - no, more BS ).

So cut this childish crap and listen to what Turpit says. Ban these trolls Turpit, this forum is becoming sick of fanboys saying which is better..... Making claims that are also unreasable, untrue and just there to get people wound up when there is more to get upset about than this ugly banter.

As I have said before, I dont care what name is on the tin, its what inside the tin that counts.....

AMD deserve a break, but they seem to be breaking themselves at the moment. Infact I am not going to put a AMD processor in another machine untill they sort them selves out period.
When Intel had the calcuation bug on the Pentium at least they replaced them, not got everyone to flash their bios, make it slower and forget about it like AMD has allegedly done.

Intel have only made one mistake and that was the Prescott. Great for a Silicon space heater which over heats, throttles and goes slower and needs a fan bigger than a air intake on a Boeing 747. I didnt sell a Prescot due to these factors.
And I wont sell AMD till those factors are corrected.


AMD Onwers / Followers / Extremists - get over it.......
January 23, 2008 7:41:14 AM

Who cares.
a b à CPUs
January 23, 2008 9:28:09 AM

I just posted something funny so as to diffuse the tension.

Jeez ... tough crowd ... not even a post with "hey ... that was funny".

I won't get into arguing because I'll simply get banned or hounded out of the place like the Baron ... and I actually enjoy it here.

I also don't know enough about servers and had trouble understanding the articles because I have a disability ... the AMD Fanboi blindness thing ... LOL.

I hope I at least gave you a laugh because I'm not that serious.

There are far more serious things in the world ... unless your in a wheelchair on a disability pension and bolted to a PC with a catheter installed ... your not?? ... are you?
January 23, 2008 9:46:21 AM

Reynod said:
Well I had (it got off) a 3000lb trout (turpit) on a 5lb line (AMD's) and the mongrel just jumped into my boat (heavily refinanced) and sank it.

< swims back to shore ... shakes fist at sky >

Turpit ... I beg you ... please keep your posts inside the thesis word limit or I shall have to fail you next time for excessive verbiage !!

Kind regards,

fanboi on the run :) 

P.S. I imagine you spent a good hour on that reply ... or more. Was that on company time ... or did I cut into your "drinking" time??


:lol:  :lol:  :lol: 
Oh cmon now. What your the only one who gets to play? Dont think so sir :kaola: 

and no, you didnt cut into my drinking time, I was inside my 12 hour window and couldnt drink anyway.
January 23, 2008 9:49:59 AM

Congrats Turpit, you have owned thunderman and Reynod, and show that neal guy for the AMD shill that he is, so now for the $64,000 question.
Once a working barcelona is released (new stepping and all) do you believe that clock for clock, and with the xeon using FDdimms, the xeon will use less power than the barcalounger
a b à CPUs
January 23, 2008 10:16:48 AM

Well at least someone laughed ...

So ... you have a job big T ??

I'm into speculative journalism myself ... the free kind you dislike.

Rumours and such ... facts are inconvenient truths.

I'm a small fish ... not a large important fish.

My AMD buddies have fled the scene here ... ??

I'll await B3 ... call me a sucker for punishment.



[.....sigh]
OK Reynod, I'll play. GREAT !!


reynod wrote :

More Intel Fanboi crap ...



Yes yes, we know, George Ou is an Intel fanboy. Im an Intel fanboy, no wait, Im an AMD fanboy, no wait, which is it? Im confused, Ive been called both so many times I dont know. Just choose your line and get in it. It always easier to call someone a fanboy because you dont like what they say rather than read or comprehend and then make the judgement

SORRY BUT I EXPECT MODS TO BE MODERATING NOT CREATING MORE FLAMEBAIT FOR THE HORDE.

reynod wrote :


Is this any different to thunderman's posts? Hmm?? Not really ... just the opposite flamebait.



Hardly. This is called a rebuttal. Its what you do when debating. Im sorry, if you want this to be an "All AMD, All the Time, All Positive" forum. Visit AMDzone (how was that for a fanboy implication without actually saying it? ;)  )

MY POINT STANDS ... YOUR NO BETTER THAN HIM.

reynod wrote :


Well the OP is more literate ... the argument is simply the opposite.


No, its not. It is a presentation of information which refutes Neal Nelsons claim, and points out that he was either spinning data to support that claim rather than systematically, scientifically testing all options and and using the results to reach a conclusion, or that he doesnt know what hes doing. It has nothing to do with the 'opposite'.

THAT WAS A COMPLIMENT TO YOU OLD CHAP.

reynod wrote :


Waiting for the horde to descend ...
Bit slow today ...

Next ... the comments about AMD lying ... ho hum ... it's getting old now guys.



Really? A manufacturer misrepresenting its products in such a manner as to make them appear to be something they're not is getting "old"? I dont think so, but hey, I know someone who has a Ford Feista for sale. Best car ever. Trust me, why dont you buy it. It really is the best because I said so. Dont bother reading Consumer Reports or Road & Track or anything....just take me at my word. ;)  :kaola: 

THEY BOTH LIE ... SO WHY DO YOU SPEND SO MUCH TIME ON AMD ?? INTEL FANBOI YOU MUST BE !!

reynod wrote :


Lets talk about the lies Intel told about the end of line Netburst Prescott CPU's eh??



Cool. Here, I'll help you start. Netburst was crap and Intel lied to cover that fact. :hello:  Anyone want to dispute that? :pfff:  No? :ouch:  Well, guess theres nothing to talk about there since everyone seems to be in agreement about netburst.

Maybe thats why AMD, and not Intel keeps coming up. Everyone knows Netburst was crap and Intel lied about it. No one denies it and Intel suffered for it. Not everyone seems to have caught on that AMD has been lying and spinning though, and there are still those who deny it and contrive to convince others that AMD is "pure as the driven snow". Once people accept that AMD lied, and stop trying to spread more BS or spin AMD's lies away, then you'll see furor over this issue subside.

BOTH LIED ... SO WHY CAN'T YOU LET IT GO?? OR ARE YOU BEING PAID?

reynod wrote :


130W TDP ... more like 145W ... burned out two mobos on the THG endurance test. It's on record If anyone cares to link it. The HSF's could not keep up either ... despite being boat anchors.



And Im sure we can find records showing AMD doing the same. As long as we are grave digging (Netburst), lets dig up Socket A Athlon, anything above a 2400XP will do. Those things sucked so much power and ran so hot that if you so much as looked at them crosseyed they would cook. Thats on record too, and 'getting old' as well. But if you want to build a new Netburst or AthlonXP machine, then I suppose its not grave digging, and it would certainly be relevent. What about it? Anyone planning on a 'new' Netburst or AthlonXP machine? :hello: 

MY STATEMENT IS TRUE? THG SHOULD HAVE BAGGED INTEL ABOUT IT BUT DIDN'T ?? WHY ... THEY WERE RENTING THE BUILDING INTEL OWNED AT THE TIME.


reynod wrote :


Lets talk about the RAM power draw on them Intel Servers too .... ouch !!!



Yes please lets. If you read the title of Mr Nelsons 'study', It wasnt termed 'AMD servers use less energy' it was titled, precisely:
'Throughput and Power Efficiency for AMD and Intel Quad Core Processors'.
Not:
'Throughput and Power Efficiency for AMD and Intel Quad Core Processor power server systems'
nor
'Effect of FB Ram on Throughput and Power Efficiency for AMD and Intel Quad Core Processor Servers'


Had it been titled correcly, had it been thorough and had it emphasized the specifics that Mr Nelson has been scrambling to publicize in his defense, there would be no problems. Why? Because, FB RAM does use more power. A butt load of it. No one is denying that, and if they were, I say they lied like AMD. But again, Mr Nelsons study said "....Processors....". Not "....systems....", not "....components....". The title specifically targeted the processors. He made a statement, incorrect at that, based on an incomplete 'study', using a limited product range. The kind of study that would have seen him fired any real consulting firm.

SEMANTICS ... BUT I CONCEDE THE POINT AND APOLOGISE.

reynod wrote :


Lets talk about scaling past a few sockets ... high end servers are still AMD only .... FSB is just too bandwidth limited.



Yes, you're right. But that wasnt the topic of the study. The topic was the the Nelson study 'Throughput and Power Efficiency for AMD and Intel Quad Core Processors'. . Changing the subject to divert attention doesnt change the fallacy presented by the study.

THANKS FOR THE VOTE OF SUPPORT.

reynod wrote :


Lets talk about paying companies not to buy AMD products.



Please yes lets do. Lets talk about how effective it was. It was so effective, that while AMD had the undisputed superior product, Intel was successful in losing over a quarter (almost 1/3) of the market to AMD. Intel was so successful that AMD hit manufacturing capacity and was able hold ASPs and thus margins comfortably high due to demand for thier superior product. Why? Because Intel had nothing to compete with except PR. During that time AMD proved, conclusively, that performance talks, BS walks. Inspite of any alleged, alleged wrong doing on Intels part. And do you know what the irony of that is? If Intel really commited those alleged acts, then every single penny they spent was a penny wasted since it did nothing to hold AMD back. I can talk about that all day long. I find it hugely amusing...a slap in the face to Intel if they really did anything illegal, and a slap in the face to all the AMD fanboys who cry Intel held AMD back, since in fact AMD wasnt held back....not in the least. And the quarterly and yearly statements prove they werent held back. In fact, considering how AMD disenfranchised the channel the second they got their hands on a Dell contract, if I were AMD, I'd be praying for more of the alleged wrong doing from Intel, since AMD was doing so well while it was supposedly going on.

AMD MARKETING IS POOR... THERE IS NO DOUBT THERE. IT IS CLEAR INTEL WAS PAYING CUSTOMERS TO EXCLUDE AMD ... THAT'S BEEN PROVEN SEVERAL TIMES OVER. THE CHANNEL ISSUE WAS ONE OF INABILITY TO SUPPLY THE MARKET - AMD THREW ALL THEIR CHIPS AT ONE AND NOT BOTH ... THEY CANNOT SUPPLY EVERYONE BECAUSE THEY DONT FAB ENOUGH ... PLUS THE CHANNEL ISSUE WAS IMPACTED BY CONROE ... A SUPERIOR PRODUCT.


reynod wrote :


Lets talk about the Penryn Errata ??

http://www.dailytech.com/Intel+Exp [...] e10362.htm


Stability problems due to 4 layer mobos?? Or is it the FSB can't be stretched anymore and the "noise" threshold is too close to the signal?

All in all cranking the FSB up to 1600 should effectively squash the overclockers from getting more headroom out of the silicon tho.

That will be a showstopper till Nehalem.


Cool, lets talk about it. How many Penryns has Intel had to stop ship? Whats the clockspeed limit for DT?

Did you read the article you linked to? There is not mention of FSB frequencies, or PCB layers. Heres a good quote from that article:

Quote :

Previous reports of errata degrading the L2 and L3 cache performance were described as "false" -- desktop Penryn processors do not even have L3 cache. Microcode and BIOS updates issued by Intel since November do not fix or address the "showstopper" bug affecting the launch of the quad-core Q9300, Q9450 and Q9550 processors.

The condition does not affect Xeon quad-core processors. Xeon uses a different stepping than the quad-core processors, which fixes this simulated condition. The quad-core 45nm Extreme Edition processor launched in November is also unaffected.

I WAS MORE INTERESTED IN THE POSTERS COMMENTS AT THE END OF THE ARTICLE ... YOU SHOULD BE AS WELL ...

IT IS CLEAR THEY CAN"T EXTRACT ANY MORE BANDWIDTH FROM THE PRODUCT WITH A HIGHER FREQUENCY AND MAKE IT STABLE.

WHAT IS THE FSB FOR THE STATED ZEON'S ??



reynod wrote :


Intel cares for you ... LOL


Who said that? I didnt. But Im glad you did, because it demonstrates a mentality. If Intel doesnt care for you, who does? AMD? Someone must care for you, and if its not Intel, it must be AMD, right? I disagree. Niether AMD nor Intel care for us. They care for our money. And thats whats really got the AMD fanboys panties in a bunch. AMD proved they could care less about the customer. If they really did, they wouldnt have lied to us. And thats what AMD did, and thats what the fanboys cant accept, and thats why they spin the lies and the facts. Because they company they love, that claimed it loved them, proved it dosent really love them.

I LOVE THEM BOTH ... DEARLY.

Are we having fun yet? :??: 

I AM .... THO MY SHIFT FINGER HURTS BIG T !!


January 23, 2008 10:18:01 AM

endyen said:
Congrats Turpit, you have owned thunderman and Reynod, and show that neal guy for the AMD shill that he is, so now for the $64,000 question.
Once a working barcelona is released (new stepping and all) do you believe that clock for clock, and with the xeon using FDdimms, the xeon will use less power than the barcalounger


And heres the $0 answer. I'll be safe, wait for that to happen, and for the products to be tested and results to be published. By someone not associated with the the Inq, Fudzilla, or Nelson. Not much point in trying to deduce whats going to happen, because who knows when a working Barcelona will be released? By working, I assume you mean without the TLB bug and able to clock higher than they are currently capable of. 2 years ago, I would have counted on anything AMD said as if it was written in stone. Theses days their words are written in jello. So when they say Barcelona is going to do this that or the other by a certain date, I say wait and see what it really does, not what AMD claims it will do. Especially considering that at face value, what you say has a historical foundation supporting it, but given AMDs recent ability to screw up a wet dream, I wouldnt be supprised if their 'B3' or 'C4' or 'D5478' stepping 'solution' winds up having to suck a butload more power. Hell, maybe it'll use a lot less. Cant trust AMDs word anymore, so who knows?

I didnt own Thunderman. You cant own a troll, silly. :pt1cable:  Trolls are free spirits, living wild and unfettered by social constraints, deep in the recess's of their own sad little worlds. Creatures that contrive to ammuse themselves at our expense. You can pity them, or you can take them for what they are and enjoy their antics, but you can never own a troll. And Reynod was playing. How come Reynod gets to play, and with me its 'owning'. Ok.....yeah, looking back at my post....I cant deny it....it looks like I got over zealous and the fun turned harsh. My appologies to Reynod....that wasnt what I intended. I just started out to play, and clearly got carried away. My bad. :kaola: 

I dont know if Nelson is a shill or not. George Ou seems to thinks so, and looking at the way Nelson worded his study, and the evasive tactics he used over at ZDnet in response to George Ou, and Mr Ou's questions, it kind of looks like it. But unless he 'fess's' up and says AMD provided him with the systems to test and was paying his consulting fee, we'll never know. Maybe he really did just goon up some text in his study and its a matter of semantics. I dont know the whys or hows, only the appearance of the white papaer...and it appears pretty clear to me.
a b à CPUs
January 23, 2008 10:20:45 AM

endyen ... your a sheep right???

nothing to add ??

baaaa !!!
a b à CPUs
January 23, 2008 10:21:57 AM

Thanks ... I apologise too !!

Wait ... I want to be the troll you described ... I am happy to be one of the unfettered .... lonely and free !!!


January 23, 2008 10:51:00 AM

Reynod said:
Well at least someone laughed ...

So ... you have a job big T ??

I'm into speculative journalism myself ... the free kind you dislike.

Rumours and such ... facts are inconvenient truths.

I'm a small fish ... not a large important fish.

My AMD buddies have fled the scene here ... ??

I'll await B3 ... call me a sucker for punishment.

I dont dislike speculative journalism.. not at all. Without speculation we'd still be rubbing sticks together, and comparing the number of beads on the AMD abacus to Intels abacus. But people need to be careful when they speculate lest their theories be taken by some kiddie as fact and proliferate.....how often have we seen that here? Far, far too often and speaking of speculation and your buddies, where the one who took turning speculation into "fact" and made it into an artform? 10 points if you get it right on the first guess.

BTW, my appologies on the post. I entered into it in a spirit of fun, and got off track......just way too far off track and looking at it now, it comes off as an attack, and I really didnt mean it as such.


EDIT: BTW, when THG starts paying me to moderate, then I'll stop participating. Until then, ya'll just have to live with me being both, because without particpation, theres no reason for me to be here. Moderating sucks.
a b à CPUs
January 23, 2008 11:15:30 AM

I hereby apply for a moderators license ... hopefully I can skip the written test and just do the practical bit ... I'm not good with numbers ... LOL.

I have plenty of experience ...

You probably need a hand anyway ...

It's a full-time job keeping up with the cpu threads let alone those strange guys down there in graphics ... heh heh.

Now if Intel (cheap mongrels) would pay me $10 for every time I recommended a Q6600 here to a n00b (as an AMD Fanboi it hurts ... yes it hurts) then I'd be bloody rich.

Though I'd have also sold a few 5000+'s just to be able to sleep at night.

Cheers :) 
January 23, 2008 11:19:57 AM

If I had a fraction of that for every Athon XP system I built or configured, Id be rich as well. Sadly, AMD just takes us for free advertising. Not even a free chip. Bastages. And I just had to replace my 939 HTPC because the mobo died...meaning new mobo and chip. AMD of course. Does AMD have any idea how hard it is to find an am2 mobo with AGP? Again, I say, bastages.
January 23, 2008 2:56:11 PM

endyen said:
Gee Mandrake, it's not that I hate you but
Quote:
This study also conveniently ignores Intel's new 5100 chipset that allows the use of registered DDR2 over FB-DIMM memory with DP Xeon systems
have you seen what the slower interface does to the xeon's I/O numbers?
Without FBdimms even the single quad xeon stations will loose out badly to the barcelonas.


No, I haven't seen the numbers. Do you know of some benchmarks? A quick search on Google didn't find anything. Of course, for maximum performance on an Intel system dual 1600mhz FSB with quad channel 800mhz FB-DIMMs are required.
January 23, 2008 3:24:21 PM

Mandrake_ said:
No, I haven't seen the numbers. Do you know of some benchmarks? A quick search on Google didn't find anything. Of course, for maximum performance on an Intel system dual 1600mhz FSB with quad channel 800mhz FB-DIMMs are required.


I'm Honestly curious about this myself.

FB-DIMMS are $$$.

I would love to toss some workstations together that got by with less expensive RAM.
!