Sign in with
Sign up | Sign in
Your question

Another disaster for AMD: Phenom X4 slower than 65 nm Intel quads

Last response: in CPUs
Share
October 29, 2007 11:28:10 AM

D A A M I T , i am afraid to believe this, if this is true then Intel make us pay 1xxx buck without mercy
October 29, 2007 11:41:29 AM

And it may be worse than the chart shows.
The QX6850 and QX9650 scored identical marks on the tests despite the fact the QX9650 is the faster CPU due to larger/faster cache.

This indicates these CPUs hit a bottleneck and performance was limited by a factor besides the CPU.

Due to a slightly different design, the AMD may have hit the same bottleneck but not as certain since it was clearly slower across the board.

Related resources
a b à CPUs
October 29, 2007 11:44:31 AM

What stepping was that ?? Oh ... an ES.

Right.

So we expect some improvement on the retail chip then ??
October 29, 2007 11:55:42 AM

Also note that the 6850 is dual-core.... very scary although I don't think I'll believe these numbers just yet. A dual core vs quad core on a game that supposedly takes all cores into account shouldn't even be close. I'll reserve judgement for now. Something is askew...
October 29, 2007 12:01:34 PM

I still believe Phenom X4 could provide better C/P value.
October 29, 2007 12:11:46 PM

I dont think these benchmarks are true . I am an AMD supporter but seeing the dual-core intels get around the same as the quads something must be wrong and plus i think Phenom can do alot better .
October 29, 2007 12:30:39 PM

buzzlightbeer said:
I dont think these benchmarks are true . I am an AMD supporter but seeing the dual-core intels get around the same as the quads something must be wrong and plus i think Phenom can do alot better .


I will give you that something seems amiss.
I doubt the source tried to fake the numbers, but the range of testing was insufficient, and something seemed to be limiting the CPUs due to nearly identical numbers from the Intel CPUs which those CPUs show a broader range by other benchmarkings. I would not be surprised if the AMD chip's performance was not properly measured either.

I would really love to see AMD beat the Penryn Clock for Clock and have lower thermals which I think it may based on some of the Barcey tests I've seen.
October 29, 2007 12:59:06 PM

zen your amd-fantasism will not save amd from the second place standing and future as a wallmart pc supplier of choice!

could be drivers - the drivers have been a sticking point in amd's side
October 29, 2007 1:00:04 PM

Something is indeed amiss. I am in agreement with zenmaster.
October 29, 2007 1:02:25 PM

Damn, so let's get this straight - an OVERCLOCKED Phenom X4 @ 3GHz fails to beat a stock 3GHz C2D, let alone a 3GHz C2Q.

Considering Penryn chips are routinely hitting 4GHz overclocks... while AMD is barely hitting 3GHz, AND with a clock for clock deficit - need I say more? :pfff: 
October 29, 2007 1:20:02 PM

There are two things noticeable right away. First, either they didn't try or AMD still hasn't fixed the RAM divider. 50MHz to 800DDR2 isn't earth-shattering but it would make up the 2-3% deficit. Second, HT3 is NOT 1600MHz, it's at least 2.4GHz. And the Agena is said to run at 2.6GHz. That's probably another 5-7%.

Admittedly Penryn could get to 4GHz under 200W so we'll hope that the seeming ease they got Agena to 3GHz will mean the retail Agena - the last quad due - will get the stepping that has been said to hit 3.2 for quad.

That was a quick and dirty test though so we don't even know if they have a retail mobo sample. Either way, it's pretty close. CrySis is TOTALLY GPU dependent though so that's a bad test to use.

According to benches even a GTX can barely get above 50fps at even 1280x1024 WITH NO AA. Maybe they should use a DX9 game which will be CPU dependent at 1280.
October 29, 2007 1:35:08 PM

dragonsprayer said:
zen your amd-fantasism will not save amd from the second place standing and future as a wallmart pc supplier of choice!

could be drivers - the drivers have been a sticking point in amd's side


Are you completely unable to grasp benchmarks and analyze them like everyone else in this thread?
The Penryn is losing to the old QX6850 on two runs, basically ties two others, and really only wins one.
Also The Quads are not showing a significant difference to the Duel.
All signs the benchmark has hit a non-CPU bottleneck.
This makes the results unreliable for determining the full potential of the chips.

Add to that the Phenom is in a legacy MB.

I'm really shocked you are the only one who fails to grasp that the Intel Chips may be significantly better than what is shown. Or that possible ALL of the chips are much better than what is shown.

What everyone else in this thread has realized is that the benches do not reveal any real potential.
October 29, 2007 1:36:39 PM

How about taking into effect Crysis probably isn't optimized
October 29, 2007 1:46:06 PM

Well, on the flipside, at least Phenom will be less costly.

AND games are still GPU pigs.

AND you get a proper camlock HSF, no need to reinstall pushpin cheepy BS. Set it and forget it.

Thank god for competition.
October 29, 2007 2:08:10 PM

What's the deal with the 200mhz x15?

Shouldn't they run at higher FSB? Or is that one of those hyperthreading things?
October 29, 2007 2:13:31 PM

BaronMatrix said:
There are two things noticeable right away.

Some good points... and some bad points...
Quote:
First, either they didn't try or AMD still hasn't fixed the RAM divider. 50MHz to 800DDR2 isn't earth-shattering but it would make up the 2-3% deficit.

Good point, but I'm afraid that RAM divider will continue to haunt AMD in the future. Since the die area is limited, AMD simply didn't have enough space to implement complex RAM logic in the memory controller. In addition to that, AMD would need to go back to the drawing board to come up with a new IMC. In Intel's approach though, since the memory controller is on the chipset, Intel can implement complex logic to accommodate more RAM speed.

I agree that RAM speed will indeed hinder Phenom's performance, but I'm not sure if AMD will do something to rectify that.

Quote:

Second, HT3 is NOT 1600MHz, it's at least 2.4GHz. And the Agena is said to run at 2.6GHz. That's probably another 5-7%.

Bad point... bad bad point. Contrary to public, and especially your belief, HT3 will not cause a significant performance difference in desktop applications. Phenom is not data hungry, and having a wider (not faster) bus will not help at all; maybe on server, but definitely not on desktop.

Quote:

Admittedly Penryn could get to 4GHz under 200W so we'll hope that the seeming ease they got Agena to 3GHz will mean the retail Agena - the last quad due - will get the stepping that has been said to hit 3.2 for quad.

Another bad point. So far we've not seen a 3.0Ghz Phenom demonstrated by a 3rd party (ie. Not AMD), and the faster Phenom tested to date is 2.5Ghz. According to VR-Zone, Phenom 2.5Ghz will likely to have a TDP of 125W, and a lot more by 2.7Ghz. Therefore, I'm not sure if 3.0Ghz Phenom will have lower TDP than Penryn at 4.0Ghz.

Thing could change though, as AMD will bin significantly lower leakage part for Phenom 3.0Ghz.

Quote:
That was a quick and dirty test though so we don't even know if they have a retail mobo sample. Either way, it's pretty close. CrySis is TOTALLY GPU dependent though so that's a bad test to use.

I'm not entirely sure if Crysis is totally GPU bound. Its developer highly recommend the use of quad core over any other hardware component.

http://www.shacknews.com/featuredarticle.x?id=639


According to benches even a GTX can barely get above 50fps at even 1280x1024 WITH NO AA. Maybe they should use a DX9 game which will be CPU dependent at 1280. said:

According to benches even a GTX can barely get above 50fps at even 1280x1024 WITH NO AA. Maybe they should use a DX9 game which will be CPU dependent at 1280.

Again, even though the demo seemed to have minimal effect on multicores, it appears that game is still slightly CPU IPC bound.

Although I agree it is still too early to hand down a verdict in terms of Phenom's performance, bear in mind that Phenom is slated to launch next month. Therefore, we probably won't see significant performance difference between the ES and the finalized version.
October 29, 2007 2:17:04 PM

There may not be significant performance difference between the ES and the production stepping, but can you at least see that there is something very wrong with this benchmark? Even Intel's own quad is neck and neck with it's little dual-core brother. Makes no sense.
October 29, 2007 2:21:39 PM

Thanatos421 said:
There may not be significant performance difference between the ES and the production stepping, but can you at least see that there is something very wrong with this benchmark? Even Intel's own quad is neck and neck with it's little dual-core brother. Makes no sense.


As I said, the game seems to be not multi-core optimized... but that doesn't mean its not CPU bounded. It could be clockspeed bounded, or IPC bounded. I'm leaning towards the latter, as there is still performance difference between Phenom and Core 2, despite a slight one.

What I find weird is that Crysis is not multicore optimized. According to its developers, having a quad core will result in a measurable, if not significant boost in performance. I guess we'll know after the real game comes out.
October 29, 2007 2:32:00 PM

Indeed. Maybe I'm just trying to justify poor performance from the Phenom. I love AMD, and I'm really looking for a reason to buy one over a Penryn quad. If this is any indication, then I guess I'll just be "blue".
October 29, 2007 2:42:59 PM

Thanatos421 said:
Indeed. Maybe I'm just trying to justify poor performance from the Phenom. I love AMD, and I'm really looking for a reason to buy one over a Penryn quad. If this is any indication, then I guess I'll just be "blue".


Well, TBH, the final Phenom speed is still up for grabs. Even though the chances don't look good (at all), there's still a possibility that AMD may scale Phenom without too much heat penalty. Given Phenom's near perfect scaling in clockspeed, and if Phenom and Core 2 has similar IPC (not likely though), Phenom should perform head to head, if not better than Core 2 at the same clockspeed.

We'll see though.
October 29, 2007 3:17:47 PM

Not upset. The Phenom is at least close. Good enough to keep Intel from dragging it's heels.
The final Crysis isn't released yet anyway.
October 29, 2007 3:34:00 PM

Thanatos421 said:
Also note that the 6850 is dual-core.... very scary although I don't think I'll believe these numbers just yet. A dual core vs quad core on a game that supposedly takes all cores into account shouldn't even be close. I'll reserve judgement for now. Something is askew...
Neither the beta or demo has taken advantage of more than two cores.
October 29, 2007 4:00:53 PM

I'd like to see a benchmark that tests the CPU more than the graphics card.
a b à CPUs
October 29, 2007 4:13:27 PM

I agree - Hardly a valid test of CPUs.
a b à CPUs
October 29, 2007 4:13:39 PM

Could the author of this threa please tell me why he considers this a "disaster" for AMD?

From what I see, we have one unsubstantiated early comparative test done by a source I don't recognize (no idea of independence or reliability) on a single game with a single set of configurations that produce some strange results. AMD purportedly performs a little slower. Now why is this a "disaster"?

I think the bias of the person starting this thread is fairly obvious.
October 29, 2007 4:49:34 PM

Its a Fake !

Hype !
October 29, 2007 5:10:55 PM

Heyyou27 said:
Neither the beta or demo has taken advantage of more than two cores.



That would be what's out of whack then :)  Why o why would they use it to bench the CPUs then. Seems like this should have come from Fudzilla or Inq with that kind of pre-planning and foresight. Perhaps they did it to show clock for clock (still ES vs Production chips, but meh) what kind of performance you could roughly expect.

It's by no means a disaster, but until we can see these chips, post-production, in identical situations with benchmarks that take advantage of the entire processors and their features, I'll hold my final judgement.
October 29, 2007 5:14:40 PM

cah027 said:
Its a Fake !

Hype !



I wouldn't say that the test was a fake or hype. I would agree with Rocky that the test shows anything but that Phenom is a "disaster". Yes it looses, but not by much. At least its close enough to be in the running. This test was extremely limited, as many have pointed out, used an engineering sample of the Phenom, which may or may not bear out the real capabilities of the chip when its finally released, may have had driver or other coding problems as Dragonsrpayer pointed out, and the test itself showed more problems with bottlenecking all the CPUs tested. Thus the test may be real, but very limited in scope.

I'll reserve judgment for when the production Phenom is released. I'm personally holding off my next build until both Penryn and Phenom get out in the wild and benches are available. Then I can make an informed choice, rather than just guess and hope for the best.
October 29, 2007 5:50:28 PM

It is a disaster, IMO, is because Phenom X4 3.0Ghz was obtained by overclocking.


K10 apparently needed approx. 1.53V to reach 3.0Ghz, while the similarly clocked Q9650 only needs 1.25V, and 1.32V for Q6850.

Now given that circumstance, it is likely that AMD will not release a 3.0Ghz version of Phenom before going 45nm w/ HK/MG. Unless of course, AMD uses special stress techniques, as well as even worse yields, to obtain some golden 3.0Ghz chips for sale. I don't think the possibility of that is great though.
October 29, 2007 6:06:49 PM

yomamafor1 said:
It is a disaster, IMO, is because Phenom X4 3.0Ghz was obtained by overclocking.


That is an opinion, and it it no more or less valid than mine or most anyone else's. I don't think its a disaster, but it is a disappointment. At least the engineering sample shows that AMD is in the running and not left far off in the distance.

One thing I know for sure is that I have made enough money from trading AMD stocks this year so that I can buy a new Phenom and mobo if I want with the profits, so I do like AMD for something, even if its not their present line of CPUs. Of course, I might use the profits to buy something from Intel. I'll wait and see what the benches show next month before deciding that.
October 29, 2007 6:19:54 PM

Good point, but I'm afraid that RAM divider will continue to haunt AMD in the future. Since the die area is limited, AMD simply didn't have enough space to implement complex RAM logic in the memory controller. In addition to that, AMD would need to go back to the drawing board to come up with a new IMC. In Intel's approach though, since the memory controller is on the chipset, Intel can implement complex logic to accommodate more RAM speed.

I agree that RAM speed will indeed hinder Phenom's performance, but I'm not sure if AMD will do something to rectify that.

Bad point... bad bad point. Contrary to public, and especially your belief, HT3 will not cause a significant performance difference in desktop applications. Phenom is not data hungry, and having a wider (not faster) bus will not help at all; maybe on server, but definitely not on desktop.


Stop making statements that seem like you are privy to all of AMDs perf info. You're not. K10 is described as data-hungry in Anand's tests. Take an Intel chip at 800FSB and one at 1333FSB at the same clock and see what happens. The same for AMD. There are still chips at 800MHz HT.

They don't need a new IMC just a MEM divider like they USED to have. And like I said if a GTX can barely get above 50fps in CrySIS it IS NOT A GOOD CPU test. It's bottlenecked even at 1024.
October 29, 2007 6:47:37 PM

BaronMatrix said:

Stop making statements that seem like you are privy to all of AMDs perf info. You're not. K10 is described as data-hungry in Anand's tests. Take an Intel chip at 800FSB and one at 1333FSB at the same clock and see what happens. The same for AMD. There are still chips at 800MHz HT.

Sure! Let's see if faster FSB does benefit Core 2.
http://www.nordichardware.com/Guides/?page=5&skrivelse=...
Humm... I guess not.

Now where did Anandtech said "K10 is data hungry, and is hindered by bandwidth"? Please provide a link before putting words into Anand's mouth. Thank you.

They don't need a new IMC just a MEM divider like they USED to have. And like I said if a GTX can barely get above 50fps in CrySIS it IS NOT A GOOD CPU test. It's bottlenecked even at 1024. said:
They don't need a new IMC just a MEM divider like they USED to have. And like I said if a GTX can barely get above 50fps in CrySIS it IS NOT A GOOD CPU test. It's bottlenecked even at 1024.

They used to have?
http://www.behardware.com/articles/625-2/socket-am2-ddr...


Guess the MEM divider AMD "used to have" also suffer from the same problem. The problem is embedded in AMD's implementation of memory controller, and it is likely they have to partially redesign the controller to fix this problem.
October 29, 2007 6:50:32 PM

How is not using GTX not a good test. If you use the same card, then you would know the difference in CPUs. The video card is the control system.
October 29, 2007 7:23:40 PM

itotallybelieveyou said:
How is this trolling? He found a benchmark he showed it to us

you say as if wombat was objective in claims :)  "Another disaster for AMD" is obviously trolling or usual fanboy comment, pick whichever you prefer.
a b à CPUs
October 29, 2007 7:41:17 PM

Ho hum

Here we go


AMD is better than Intel

Intel is better than AMD

AMD is better than Intel because . ..... .... er er because we are amd owners and we .... er .... er.


Look if these figures are correct, and Intel buying Havok has not helped AMDs stance then there IS ONLY ONE THING TO SAY.........


AMD won round 1 and 2

INTEL WON ROUND 3 and INTEL WON ROUND 4, but these rounds are bigger than the last and if theyre not carefull will fail..........


So Samsung buy AMD now and stop this suffering.........

Ill say this again . face facts AMD without financial backing your stuffed , you have lost another 3-400 million dollars like a gambler needs 5 100000 limit credit cards, your stock holders worry is as stable as Buzz Aldrins backside when he went into space and the Radeon X2xxx series is not the beater we all wanted it to be considering all your cards are now in second runnings.

Will AMD followers admitt that this is a 1 horse race now with amd running a worn out pony......

There last 4x4 cost more than a SUV - 880 dollars for a motherboard is absolutley obscene and it does not give what it says for the money . Does it...........No....

I have owned both AMD - over 10 processors and Intel over 20 --- at the time which suited me fine - yes even amd had a 20mhz 286

So dont say its a flame war, Im Biased - read this - I AM NOT BIASED........

But AMD owners are in DENIAL if you feel these conversations are going anywhere....


I liked AMD with Hypertransport bus and the 64 bit chip was so chic and so was the x2 but things have moved on even faster now...

October 29, 2007 7:41:46 PM

yomamafor1 said:
Sure! Let's see if faster FSB does benefit Core 2.
http://www.nordichardware.com/Guides/?page=5&skrivelse=...
Humm... I guess not.

Now where did Anandtech said "K10 is data hungry, and is hindered by bandwidth"? Please provide a link before putting words into Anand's mouth. Thank you.


They used to have?
http://www.behardware.com/articles/625-2/socket-am2-ddr...
http://www.behardware.com/medias/photos_news/00/17/IMG0017061.gif

Guess the MEM divider AMD "used to have" also suffer from the same problem. The problem is embedded in AMD's implementation of memory controller, and it is likely they have to partially redesign the controller to fix this problem.




From Nordic Hardware:

The same applies to Cinebench when we only use one core, but when we use all four cores and these are forced to share the available resources we can see that a higher FSB is preferable.

Do you not remember K7 which had a 100MHz bus but used 333MHz RAM? That's what I meant. It was only a problem when AMD went to DDR2 which needs a 400MHz base speed to run DDR2 800 or 533MHz base speed to run DDR2 1066.


But all that's moot when you consider the difference is 2% and the dual core is right there with quad. They need to use a different game.

Also, how can you say that Phenom won't need more bandwidth than X2 when everything is 2X as wide?
October 29, 2007 8:09:13 PM

bfellow said:
How is not using GTX not a good test. If you use the same card, then you would know the difference in CPUs. The video card is the control system.


Video games generally are limited more by the graphics card than the CPU. If we want to benchmark the processor then we shouldn't use FRAMES PER SECOND because those frames are generated by the GRAPHICS CARD!

I'm the biggest Intel troll and I'm saying this is a bunch a bologna.

I think Phenom will be a flop, but this doesn't prove anything.
October 29, 2007 8:11:53 PM

Quote:
i ain't sure how long you have been around but trust me, i have seen wombat around for a while. He never starts any decent threads, he only posts derogatory threads about AMD and tries to pick fights with baron matrix then claims he is the fanboy.

he is a troll who needs banning, he brings nothing to the forums. Given enough time you will see that you do not need to read his threads to know what they will contain.

no, he is is a long time troll and flamer who should have went ages ago but nothing ever happens and he spreads his filth without punishment.

You're right, there. It's funny how the biggest trolls are still around and some of the more objective and knowledgable people were banned...
October 29, 2007 8:15:14 PM

More to the point, AMD is definitely having issues with this most recent crop of processors. They're behind on the IPC count and the process -> clockspeed. That's trouble. So they need to compete on price, but with their yields (at least what people are believably speculating about their yields) they will struggle to make money. The whole native quad-core thing is not panning out. We need them to get healthy quick.
October 29, 2007 8:22:34 PM

russki said:
More to the point, AMD is definitely having issues with this most recent crop of processors. They're behind on the IPC count and the process -> clockspeed. That's trouble. So they need to compete on price, but with their yields (at least what people are believably speculating about their yields) they will struggle to make money. The whole native quad-core thing is not panning out. We need them to get healthy quick.


Yes, AMD definitely needs to get healthy quick. And while this is an enthusiasts forum, the real place that AMD needs to concern itself with profits is in the office environment, where high frame rates in games is not a concern, but the ability to do lots of work at minimal cost is paramount. The enthusiast market is rather small compared to the business market.
October 29, 2007 8:41:24 PM

Quote:
i ain't sure how long you have been around but trust me, i have seen wombat around for a while. He never starts any decent threads, he only posts derogatory threads about AMD and tries to pick fights with baron matrix then claims he is the fanboy.

he is a troll who needs banning, he brings nothing to the forums. Given enough time you will see that you do not need to read his threads to know what they will contain.

no, he is is a long time troll and flamer who should have went ages ago but nothing ever happens and he spreads his filth without punishment.

if ya say so... you got 5000s posts ill trust ya
October 29, 2007 8:50:59 PM

itotallybelieveyou said:
if ya say so... you got 5000s posts ill trust ya


Try looking at it in this way, Stranger has about 10 posts for every 1 of Wombat's posts. That says something about longevity and the ability to see what's going on.

A second thing is that Wombat posted and then left, making no further comment about his post. So he seems something like an arsonist, lighting a match and standing back to watch the excitment as everyone else gets involved. That says something about the situation as well.

A thunderstorm has just started here, so I'm shutting down for a while to protect my computer. Good day all.
October 29, 2007 9:34:06 PM

Quote:
i ain't sure how long you have been around but trust me, i have seen wombat around for a while. He never starts any decent threads, he only posts derogatory threads about AMD and tries to pick fights with baron matrix then claims he is the fanboy.

he is a troll who needs banning, he brings nothing to the forums. Given enough time you will see that you do not need to read his threads to know what they will contain.

no, he is is a long time troll and flamer who should have went ages ago but nothing ever happens and he spreads his filth without punishment.

im sorry dude im really sorry i thought you were talking about ALL intel fans sorry homs :sarcastic: 
October 29, 2007 9:50:34 PM

Quote:
Not much faster, you guys are really pulling at strings now. It must have eaten you alive inside when AMD trounced Intel from 2003-2006.



totally untrue, must i constantly bring this up

amd only had a significant lead in may 2005 (x2 release) through july 2006 (c2d)


all most all testing in 2003-2005 was single task non multitasking - amd performance edge was slight


no i did not bother me since athlons are such poor multitaskers p4's smoke them in the real world

OK i promise not to bring this up,again, for 31 days
October 29, 2007 10:11:14 PM

No matter this time AMD wins or not, the competition in CPU market won't stop. Even if AMD doesn't exist, there's always another company would take her place to keep the competition go on. Intel can not reap profit too high, or it will induce more and more companies to join this competition. In my opinion, don't be a fanboy, just buy what you want, what you need.
October 29, 2007 10:14:35 PM

Ehh.... 1k would kinda be a reasonable price considering what the qx6850 is priced
!