Sign in with
Sign up | Sign in
Your question

Intel/AMD Quad Core Head-to-Head and Platform Changes

Last response: in CPUs
Share
October 3, 2006 6:36:49 AM

I have some exciting news for everyone. For a long time it's looked like AMD's quad core K8L would be server oriented in it's initial introduction while Intel's quad cores in the K8L launch timeframe would be dual die types. However, it looks like there will be true single die quad core competition in Q3 2007 between AMD and Intel.

http://www.google.ca/translate?u=http%3A%2F%2Fwww.hkepc...

http://www.google.ca/translate?u=http%3A%2F%2Fwww.hkepc...

How are they accomplishing this feat you may ask? Well in the case of Intel, it looks like they are very aggressively pushing toward 45nm and it's certainly impressive that they seem to want to debut the process immediately with full size quad cores rather than smaller dual core shrinks. All we know about Yorkfield besides 45nm and single die quad core is that it'll use a 1333MHz FSB (please get it to 1600MHz). It'll probably have a 12M shared L2 cache.

On the AMD size, it seems AMD is pushing back AM3 and DDR3 support until H2 2008 or about 6 months. Instead of launching quad core K8Ls on desktop for AM3 with backwards compatibility for AM2, they will be launching on the new AM2+ in Q3 2007 with backwards compatibility for AM2 and forwards compatibility with AM3. Given the year gap between AM2+ and AM3, it may well be that the intial cores won't have a DDR3 IMC in addition to the DDR2 IMC in order to save space so it won't be as much the cores that are forward compatible than the K8L architecture itself. People wouldn't be putting 1 year old chips in a brand new platform anyways so it isn't a huge difference.

Now the difference between AM2 and AM2+ is HT3.0 support and individual core power clocking support in the later. Current motherboards are obviously AM2 and so although you can upgrade to quad core K8L you'll probably have slightly lower performance and higher power consumption than on a modern platform. The good news though is that even AM2 should support future 45nm chips so AMD is certainly keeping their upgrade paths open.

What is interesting is that K8L is now longer called Rev H but is now called Rev B. I suppose that is why all the "Hound" names were cancelled. These desktop quad core K8L's are called Altair. Now the bad (less good) news. People who were expecting miracles with AMD's 65nm process will be disappointed. First, there will be no clock speed increases initially. While Altair will be available in FX 4x4 configurations and mainstream X4 AM2+ configurations, they will be topping out around 2.9GHz (thanks to the new half multiplier in Rev G). What's worse, when AMD said quad cores within the same thermal profiles as current chips they meant it. Altair TDPs will be 125W in both FXs and high-end X4s. No doubt lower clocked X4s will have a lower 89W TDP, etc., but that's not quite the same thing. L3 cache will remain at the previously announced 2MB so the large cache versions are still targetted for 2008. (Z-RAM is not likely on the horizon at all).

Now for those of you who want to jump on 4x4 when it's released in a month, it may not be a good idea. Why? Like AM2, current Socket F based 4x4s will be replaced by Socket F+ 4x4s in a little more than 6 months. Now people who already have an AM2 then K8L is a great upgrade option, but if you are buying a yet to be released high-end platform that's already outdated it may not be as inviting. While HT3.0 support isn't important in a 1P environment of AM2+, it'll definitely be useful in the 2P 4x4. The whole point of going to HT3.0 afterall is to assist in cache-coherency. The current 4x4s lack of support for K8Ls individual core power planes will also be a killer since those 2z125W TDP numbers will end up being a lot higher without power saving features.

On a side note, I've noticed that the Kentsfield samples that have been floating around at IDF are stepping 7 up from the stepping 5 B1s that we've seen lately. Stepping 7 seems to be the next to final stepping. I just wonder if 7 implies it'll be B3 or C0. It may be C0 with launch at C1 especially if what The Inquirer said about Intel correcting some B2 Conroe errata in a new stepping is true. I doubt there's major performance increases in stepping 7, probably just steps refine power consumption and in Cloverton to enable 1333MHz FSBs.
October 3, 2006 7:31:49 AM

HKEPC isn't quite the rumour mill. I'm pretty sure all their reports are based on actual documents they've seen rather than simply talk although even the reliability of documents can be question I guess.

The 2.9GHz is probably only for quad cores so it may not be that bad. AMD probably will beat 3GHz on 65nm dual cores, it's just a matter that with focus on quad cores, it wouldn't look good to have dual core frequencies too much higher than "superior" quad cores.
October 3, 2006 10:34:01 AM

Related resources
October 3, 2006 11:12:19 AM

4 Cores @ 2.9GHz is enough, they have to develop their processor with a strong Power Consumption in mind. Im sure they can easily break the 3GHz barrier, but that would be Pentium 4 EE all over again.

Also they can push the clock speed of their cores up when needed, like the old FX series

First was FX-57, which was better than Pentium 4 EE on games with relatively low clock speed, then FX-58, 60 to match or over take the Pentium D EE.. then the FX-62 Dual Core which was the king of processors was a long while until Core 2 design took over... And it was a much superior processor architecture so pushing clock speed isn't enough (like the Pentium EE did) to regain the lost performance. As THG benchmarks always show a overclocked highend processor and its potential. But im sure AMD tested those results in their own labs before THG.

So maybe they think 2.9GHz is enough... who knows? but we all just have to be patient to see what AMD can pull out of their bags. 8)
October 3, 2006 11:48:47 AM

Quote:
4 Cores @ 2.9GHz is enough,

29Mhz is enough for for reading the forumz.
Quote:
they have to develop their processor with a strong Power Consumption in mind.
Do you mean to evolve their allready developed processor?
Quote:
Im sure they can easily break the 3GHz barrier

Why are you so sure and can you explain how do you think it is possible?

Quote:
, but that would be Pentium 4 EE all over again.
Do you know the difference between P4(northwood), P4(prescott), K8 and the unknown K8L?

Quote:
Also they can push the clock speed of their cores up when needed, like the old FX series

Really? How?

Quote:
First was FX-57, which was better than Pentium 4 EE on games
The PC general purpose are not the games. Also, have you seen the C2D vs K8 benchmarks for all purposes including games?
Quote:
with relatively low clock speed,
Relatively speaking.
Quote:
then FX-58,
Never heard about FX-58. Can you point at any link?
Quote:
60 to match or over take the Pentium D EE..
FX-60 is dual core, and it is used for other purposes also, not only for gaming.
Quote:
then the FX-62 Dual Core which was the king of processors was a long while until Core 2 design took over...
FX-62 was only coupple of days the fastest x86 CPU and than was bruttaly outperformed by the half-priced, lower clocked and the less power hungry C2D for every purpose and every benchmark known to man kind.
Quote:
And it was a much superior processor architecture so pushing clock speed isn't enough (like the Pentium EE did) to regain the lost performance.
Which processor architecture was much superior compared to which?
Quote:
As THG benchmarks always show a overclocked highend processor and its potential. But im sure AMD tested those results in their own labs before THG.
So, how does it changes the reality?

Quote:
So maybe they think 2.9GHz is enough...
No human thinks that any performance is enough.

Quote:
who knows?
Those who understand K8, K8L, 90nm SOI2 and 65nm SOI3.
Quote:
but we all just have to be patient to see what AMD can pull out of their bags. 8)
No, noobz have to be patient, but they are not.
October 3, 2006 12:30:39 PM

Hehehe, very nice gOJDO. Granted I don't know a lot about all this CPU stuff, but I'm not going to just go out there and say something because I think it's right. I want to know before posing in THG. You people would tear me apart! LOL
October 3, 2006 12:34:07 PM

Seems to me that AMD is saying a lot of stuff, but until I see actually proof, I'm not going to expect too much. Too many companies these days say stuff, and then barely deliver on it.

But having an Intel monopoly would not be good either. So I'm hoping AMD will be able to come back and at least deliver something comparable to Intel's current cpu's. Talking to some AMD people at the last career fair, they were fairly adamant about increasing performance through increasing cores, so speed wouldn't matter as much, i.e. Kentsfield slower than X6800 but still rapes it in most benchmarks...

I just don't want to buy my quad core this year, and have a 16-core processor come out in 2 years... =(
October 3, 2006 2:11:32 PM

Quote:
4 Cores @ 2.9GHz is enough,
-29Mhz is enough for for reading the forumz.

- Whats your point there?
Quote:
they have to develop their processor with a strong Power Consumption in mind.
-Do you mean to evolve their allready developed processor?

- AMD introduced the "Performance per watt" theory, Intel carry it to C2D, and why should AMD make a processor that uses 200W+ to ensure the maximum performance out of the processor and slay their own face with the "Performance per watt"? Did you not know the faster the clock speed the more watts it consumes? Im talking about clock speed here not performance.
Quote:
Im sure they can easily break the 3GHz barrier
-Why are you so sure and can you explain how do you think it is possible?

- on THG, overclocked FX-62 already @ 3.0GHz, did you not know that? Regardless either is is FSB increase or Multiplier Unlock, it is possible and has been done.
Quote:
, but that would be Pentium 4 EE all over again.
-Do you know the difference between P4(northwood), P4(prescott), K8 and the unknown K8L?

- I am using the Pentium 4 EE has a reference on power consumption, and yes i do know the difference between them and that is what this forum is for, but you sounded a very big headed there think that u r the only person here knows the basics
Quote:
Also they can push the clock speed of their cores up when needed, like the old FX series
-Really? How?

- All the processors are made of same silicons, some performs better than others. And for marketing reason that suits each budget lines. They use a thing called MULTIPLIER to limit CPU clock speed. Read Overlocking forum section, if not, email THG, and if you are really strugling, then u shudnt really be on this forum.
Quote:
First was FX-57, which was better than Pentium 4 EE on games
-The PC general purpose are not the games. Also, have you seen the C2D vs K8 benchmarks for all purposes including games?

- Of course i have seen C2D vs K8 in games, thats why i said the C2D was a much superior processor design and pushing the clock speed of the FX-62 up simply not enough to over take the crown back, can u not read?
Quote:
with relatively low clock speed,
-Relatively speaking.

- Yes big head relatively speaking
Quote:
then FX-58
-Never heard about FX-58. Can you point at any link?

-http://tomshardware.co.uk/2004/04/19/overclocking_en_ex...
Although it was only imaginery, but THG did user the term FX-58, i didnt really mean to say FX-58 (which is just an oC version of 57) but i thought u were technical enough to follow suit.
Quote:
60 to match or over take the Pentium D EE..
-FX-60 is dual core, and it is used for other purposes also, not only for gaming.

- I did not specifically metion any of these processors are design for games. But AMD market strategy did reveal that the FX series processors are aimed at high end gamers. I am sure you have heard that as well unless u need me to point out a link?
Quote:
then the FX-62 Dual Core which was the king of processors was a long while until Core 2 design took over...
-FX-62 was only coupple of days the fastest x86 CPU and than was bruttaly outperformed by the half-priced, lower clocked and the less power hungry C2D for every purpose and every benchmark known to man kind.

- A couple of days? what planet are u living in? FX-62 was announced and released in May 2006, C2D came in September 2006, how many days are there in between, you do the maths. And before the FX-62, there were FX-60 and FX-57, and how long have they managed to stay top of the benchmark chart, you tell me.
Quote:
And it was a much superior processor architecture so pushing clock speed isn't enough (like the Pentium EE did) to regain the lost performance.
-Which processor architecture was much superior compared to which?

- the C2D Conroe is Much superior than K8 and so on and so
Quote:
As THG benchmarks always show a overclocked highend processor and its potential. But im sure AMD tested those results in their own labs before THG.
-So, how does it changes the reality?

- did i say it was going to change any reality? if THG can figure out that pushing clock speed can not achieve better performance for K8 over Conroe, u think AMD doesn't know that? Maybe they should hire you as their Technical Director if they didnt...
Quote:
So maybe they think 2.9GHz is enough...
-No human thinks that any performance is enough.

- you said 29MHz is enough to read the forum... then again u dont just use ur machine to read the forum. by *enough* i meant to match their competitor's product and there also distinctively said MAYBE and if u dont know the term of MAYBE u can find it in the dictionary... MAYBE
Quote:
who knows?
-Those who understand K8, K8L, 90nm SOI2 and 65nm SOI3.

- So are you one of them?
Quote:
but we all just have to be patient to see what AMD can pull out of their bags. 8)
- No, noobz have to be patient, but they are not.

- great, you have the power to make AMD release K8L and all the new exciting things by the end of this month? or do u also have to wait to see what AMD does? if you are the second, then u just called urself a noob!
a b à CPUs
October 3, 2006 3:35:52 PM

La Guerre?

Why do you both fight over something as trivial and un-important as a Q3 2007 plausible launch for K8L (It use to be scheduled for 1H2008 but it looks like AMD have skimped on allot of features to get it out the door quickly).

To me it's not important as this is a year away. Lot's can still happen, one things for sure.. Core 2 in it's current state cannot compete on a performance 1:1 basis with K8L if those specs prove true. Intel may be able to do so by clock speed (45nm) but then they'd lose there Performance/Watt and Performance/Clock advantages.

Me thinks Intel is going to introduce much more cache can you imagine an 8MB+ of Unified Cache on a Quad Core Processor? This means Intel will likely have between 12-16MB of Cache on there 45nm Quad Core Processors in order to compete.

Either way.. this is more then a year away. While AMD Fanbois wait over a year using an inferior processor, I'll enjoy my Core 2 and then make a decision based on performance in a years time as to whether I adopt K8L or a 45nm shrink of Core 2.
October 3, 2006 3:54:16 PM

Quote:

Either way.. this is more then a year away. While AMD Fanbois wait over a year using an inferior processor, I'll enjoy my Core 2 and then make a decision based on performance in a years time as to whether I adopt K8L or a 45nm shrink of Core 2.


Amen! Buy what's best at the time! No need to argue over things that haven't been released.
October 3, 2006 3:56:26 PM

i was just giving my opinion until gOJDO came in with his big head quoted every line i said and critisized... :lol: 
October 3, 2006 4:43:28 PM

Quote:
4 Cores @ 2.9GHz is enough,
-29Mhz is enough for for reading the forumz.

- Whats your point there?
Be more specific, enough for what? 99% of the PC users today can't find any practical use of 4 core @ 2.9GHz and it will be like that in the folowing year if we take into account the speed of single-threaded to dual/multi-threaded software transition.
Quote:
they have to develop their processor with a strong Power Consumption in mind.
-Do you mean to evolve their allready developed processor?

- AMD introduced the "Performance per watt" theory, Intel carry it to C2D, and why should AMD make a processor that uses 200W+ to ensure the maximum performance out of the processor and slay their own face with the "Performance per watt"? Did you not know the faster the clock speed the more watts it consumes? Im talking about clock speed here not performance.
K8L is only evolution of K8, it will be very similar to K8, so K8L's architecture will be power efficient like K8. The power efficiency is more dependend on the voltage than on the freqfency, Ptotal = Pstatic + (C * V * V * F). Freqfency is dependend of both, the production process and the architecture(pipeline depth and stages delay), but voltage is dependend only of the production process. So, AMD needs better production proces, rather than more efficient architecture if they want their new processor to be efficient. K8L will come on 65nm SOI3, which is not so impressive according to the data we have today.

Quote:
Im sure they can easily break the 3GHz barrier

-Why are you so sure and can you explain how do you think it is possible?
- on THG, overclocked FX-62 already @ 3.0GHz, did you not know that? Regardless either is is FSB increase or Multiplier Unlock, it is possible and has been done.
FX-62 is on 90nm SOI2, K8L will be on 65nm SOI3. On the AMD roadmap, the highest clocked K8 will be on 90nm SOI2 and it is clocked at 3GHz. There are no such 65nm SOI3 K8 processors. We also don't know how scallable will be K8L. Thats why I am wondering how are you so sure.

Quote:
, but that would be Pentium 4 EE all over again.

-Do you know the difference between P4(northwood), P4(prescott), K8 and the unknown K8L?
- I am using the Pentium 4 EE has a reference on power consumption, and yes i do know the difference between them and that is what this forum is for, but you sounded a very big headed there think that u r the only person here knows the basicsAll of the menitoned CPUs have different architecture and different pipeline length and there are variants on different processes. K8 is so much different from both p4 Northwood and Prescott. Also TDP is differently measured by AMD and Intel, AMD's TDP is the overall maximum, while Intel's is the average.

Quote:
Also they can push the clock speed of their cores up when needed, like the old FX series

-Really? How?
- All the processors are made of same silicons, some performs better than others. And for marketing reason that suits each budget lines. They use a thing called MULTIPLIER to limit CPU clock speed. Read Overlocking forum section, if not, email THG, and if you are really strugling, then u shudnt really be on this forum.
Do you know that all CPUs have OC-ing limit which depends on both the production process and the CPU architecture. K8 architecture is not designed to clock high and the 90nm SOI2 is hitting its performance edge. Just look at the price and conclude what are the FX-62 yields.
Quote:
then FX-58

-Never heard about FX-58. Can you point at any link?
-http://tomshardware.co.uk/2004/04/19/overclocking_en_ex...
Although it was only imaginery, but THG did user the term FX-58, i didnt really mean to say FX-58 (which is just an oC version of 57) but i thought u were technical enough to follow suit.Go tell this BS to my grandmother.
Quote:
60 to match or over take the Pentium D EE..

-FX-60 is dual core, and it is used for other purposes also, not only for gaming.
- I did not specifically metion any of these processors are design for games. But AMD market strategy did reveal that the FX series processors are aimed at high end gamers. I am sure you have heard that as well unless u need me to point out a link?Do you realise that the only difference between the FX and all other K8 CPUs based on the same core is the fully unlocked multiplier and all perform same at same clock speed? The FX are the top DT/WS models and thats why AMD recomend them for gaming instead of the cheaper Athlon64/X2 and Sempron64.
Quote:
then the FX-62 Dual Core which was the king of processors was a long while until Core 2 design took over...

-FX-62 was only coupple of days the fastest x86 CPU and than was bruttaly outperformed by the half-priced, lower clocked and the less power hungry C2D for every purpose and every benchmark known to man kind.
- A couple of days? what planet are u living in? FX-62 was announced and released in May 2006, C2D came in September 2006, how many days are there in between, you do the maths. And before the FX-62, there were FX-60 and FX-57, and how long have they managed to stay top of the benchmark chart, you tell me.
FX-62 is released on 23 May 2006, Core2 Duo is released on 23 July 2006, 60 days latter. FX-57 is singlecore CPU and it is being outperformed by almost all dualcore CPUs for multithreading software. Anyway FX-60 allready was outperforming Pentium D, FX-62 was the only FX CPU for sAM2 when it was introduced.
Quote:
As THG benchmarks always show a overclocked highend processor and its potential. But im sure AMD tested those results in their own labs before THG.

-So, how does it changes the reality?
- did i say it was going to change any reality? if THG can figure out that pushing clock speed can not achieve better performance for K8 over Conroe, u think AMD doesn't know that? Maybe they should hire you as their Technical Director if they didnt...Maybe they should hire you as Santa Claus and break the 3GHz barrier whenever they think 2.9GHz is not enough. :roll:

Quote:
So maybe they think 2.9GHz is enough...

-No human thinks that any performance is enough.
- you said 29MHz is enough to read the forum... then again u dont just use ur machine to read the forum. by *enough* i meant to match their competitor's product and there also distinctively said MAYBE and if u dont know the term of MAYBE u can find it in the dictionary... MAYBEThe top perofrmance of the CPU is not important! The factor performance/price is! AMD must match their competitor's product performance/price ratio, not their competitors freqfency. You can't compare performance of different architectures by comparing their freqfency.
Quote:
who knows?

-Those who understand K8, K8L, 90nm SOI2 and 65nm SOI3.
- So are you one of them? No.
Quote:
but we all just have to be patient to see what AMD can pull out of their bags. 8)

- No, noobz have to be patient, but they are not.
- great, you have the power to make AMD release K8L and all the new exciting things by the end of this month? No.
Quote:
or do u also have to wait to see what AMD does?
No, I don't have to wait, I am guessing and so far I am guessing right.
Quote:
if you are the second, then u just called urself a noob!
Right.
a b à CPUs
October 3, 2006 5:22:12 PM

I don't want to come in between you two but why not post the obvious.

We all know that the larger the die, the more power is needed to power it. The larger the die, the lower the yields.

K8 using a 90nm SOI2 process had relatively large die's but nothing too uncommon, but now what we mustn't forget is that K8L is a K8 core with added features and a small die shrink.

K8L brings about added Cache (L3) and many new features (such as the Dual 128bit SIMD registers etc). All these features take die space. Therefore yields will be similar or not as good as those of K8 90nm SOI2 even taking into account the shrink to 65nm.

In other words, don't expect AMD to release highly clocked variants. For one thing it's not needed (seeing as K8L will increase the performance/clock ratio of the K8 core) and also it's not that feasible due to the larger die size.

Pretty Logical no? Now I must stress this is all pure speculation, Logical, but yet still speculation.
October 3, 2006 5:59:06 PM

to gOJDO:

u do relise that your second comments based on mine to your first comments were practically agreeing with me 80%.

- u agreed with me that 4 cores @ 2.90GHz is enough by saying that u can not find practical use of 4 cores @ 2.9GHz today...

- u agreed that higher clock speed will consume relatively more power than lower clock speed. U just made it more specific of other factors which we were not discussing.

- on the 3GHz barrier, you agreed that the Highest clocked K8 will be on 90nm SOI2 and it is clocked at 3GHz... barrier breached...

- on CPU architecture, your did not match what was discussed. but I just repeated that K8, Northwood and Prescott are so much different than K8, that was my initial arguement.

- All CPU has OC Limit, of course other wise we wud be all using 100GHz chips... You are right the K8 is at its performance edge, that is why AMD is developing new architecture, and Envolving the K8. Everything would eventually meet its performance edge, other wise a old Pentium MMX would still exist in common home use today

- I did tell that FX-58 bullshit to your grand mother, and she passed it on to you... but u got so pissed off because u also heard it from me...

- on FX series for games, again you agreeing with me in a different but more specific fashion, does not matter FX, A64, Sempron are using the same core, what it matters is that i said FX Series is for gamers, u second that by saying WHY it is made for highend gamers

- again, 60 days is not a couple of days... if you are to argue between "60 and a couple", go find your English teacher first. and wether FX-62 was the only FX CPU were AM2 does not matter, i did not say FX-57 was using AM2 so chill out

- No need for me to do it, many people have already done it. that comment just plan stupid because you even said yourself that the 3GHz barrier has been breached, even by the K8 FX-62, you slapping your own face...

- what does MAYBE and Performance/price ratio got to do with each other? But also you sounded so big headed to show off all those knownledges, maybe to noobs, or to yourself, but certainly it does not impress me. And did i compare their frequencies in terms of performance? i metioned "Performance per watt" that mislead you to lash out more of your knownledge that a lot people know about.

- If you don't understand K8, K8L, 90nm SOI2 and 65nm SOI3, why did you critisiz me? why did you made yourself sounded like you know it all?

- Well if you don't have to wait for K8L, are you saying you already have 1? Guessing and Not Waiting are 2 completely different things. Unless you can see the future... (now that is a different story all together)

By saying "so far you are guessing right" - what have u guessed? speaking from known facts does not call guessing my Macedonian friend

- You agreed that you are a noob, enough said...
October 3, 2006 6:04:34 PM

le puits intresting très, laisse maintenant voir est lui juste un lancement de papier ou les avoir vraiment ont fait là le travail. Je veux personnellement voir une certaine concurrence.
October 3, 2006 6:07:33 PM

Quote:
le puits intresting très, laisse maintenant voir est lui juste un lancement de papier ou les avoir vraiment ont fait là le travail. Je veux personnellement voir une certaine concurrence.


in English (not exactly correct)

The well intresting very, leave now to see is him just a paper launch or to have them really did there the work. I want personal to see a certain competition.
October 3, 2006 6:08:28 PM

Quote:
le puits intresting très, laisse maintenant voir est lui juste un lancement de papier ou les avoir vraiment ont fait là le travail. Je veux personnellement voir une certaine concurrence.

Translation: "I surrender"

Been a while since I used my French 8)
October 3, 2006 6:18:17 PM

au-dessus du poteau
October 3, 2006 6:26:31 PM

Quote:
On the AMD size, it seems AMD is pushing back AM3 and DDR3 support until H2 2008 or about 6 months. Instead of launching quad core K8Ls on desktop for AM3 with backwards compatibility for AM2, they will be launching on the new AM2+ in Q3 2007 with backwards compatibility for AM2 and forwards compatibility with AM3. Given the year gap between AM2+ and AM3, it may well be that the intial cores won't have a DDR3 IMC in addition to the DDR2 IMC in order to save space so it won't be as much the cores that are forward compatible than the K8L architecture itself. People wouldn't be putting 1 year old chips in a brand new platform anyways so it isn't a huge difference.


Thanks for another nice post.

I've always wondered about a programmable IMC, but I guess that wouldn't bring much of a profit to AMD (let aside its feasibility, of course).
I think that, from whatever perspective one looks at it, AMD is late. Despite the appeal I find in different computing approaches & topologies (4 x 4) AMD brings to the table, it still sounds more like a cry for their followers than a true menace for Intel, in competitive terms.


Cheers!
October 3, 2006 6:28:50 PM

Quote:
Thanks for another nice post.

I've always wondered about a programmable IMC, but I guess that wouldn't bring much of a profit to AMD (let aside its feasibility, of course).
I think that, from whatever perspective one looks at it, AMD is late. Despite the appeal I find in different computing approaches & topologies (4 x 4) AMD brings to the table, it still sounds more like a cry for their followers than a true menace for Intel, in competitive terms.


Cheers!


I agree. but you always have a feeling or hoping for a exciting release by AMD like Intel did with Core 2 Duo
October 3, 2006 6:30:52 PM

I'm dying to see whether AMD diehards fall for AMDs rebranding of their dual socket Opterons as "4x4" next month.

I've been running an AMD "4x4" since January this year 8) :lol: 
October 3, 2006 6:33:42 PM

Where does it say that DDR3 IMC won't be on AM2+ K8L quad cores?? I'm just curious because I thought I read they (AM2+ QCs) were compatible with AM3 sockets. And since DDR3 memory is only compatible with AM3 (I'm pretty sure I remember reading that somewhere) then wouldn't the AM2+ K8L QCs need to be DDR3 compatible?? I'm assuming that's what the "+" in AM2+ means, AM3 compatible which means it'll work with DDR3.

Correct me if I'm wrong though, because I'm trying my best to remember the things I've read over the past few weeks.
October 3, 2006 7:59:02 PM

Quote:
Where does it say that DDR3 IMC won't be on AM2+ K8L quad cores?


You'd better read the links. :wink:


Cheers!
October 3, 2006 8:06:32 PM

Quote:
I agree. but you always have a feeling or hoping for a exciting release by AMD like Intel did with Core 2 Duo


I truly admire technology & what's behind it, first; as such, AMD is no exception & I am very curious on what this company might bring up in the near term, behind the info smoke screens...


Cheers!
October 3, 2006 8:08:38 PM

Quote:
I've been running an AMD "4x4" since January this year 8) :lol: 


Could you elaborate on that?


Cheers!
October 3, 2006 9:58:43 PM

@pete4r
K8L is allready developed and it was taped out in august. AMD will clock their K8L processors as much as possible becouse they have strong competition on the road. So far, they can hardly break the 3GHz barrier, especialy becouse they will use the 65nm SOI3. This is the point on which I disagree with you:
"Im sure they can easily break the 3GHz barrier, but that would be Pentium 4 EE all over again."
Also
"Also they can push the clock speed of their cores up when needed, like the old FX series"
They pushed the clock speed of the old FX series with pushing the TDP to 125W which is also contradictory to your statement:
"4 Cores @ 2.9GHz is enough, they have to develop their processor with a strong Power Consumption in mind."
a 2.6GHz FX-60 has 125W TDP. While the 65nm SOI3 K8 dualcore chips will have almost same TDP as 90nm SOI2 K8 dualcore chips. How do you expect the 2.9GHz improved quadcore taking more than twice silicon space to have low power consumation?
That is another point at which I disagree.
And I also disagree on this part:
"So maybe they think 2.9GHz is enough... who knows? but we all just have to be patient to see what AMD can pull out of their bags. "
AMD don't think that 2.9GHz is enough, and we don't have to be patient to see what AMD can pull out of their a$$.
October 3, 2006 10:12:30 PM

Quote:
I've been running an AMD "4x4" since January this year 8) :lol: 


Could you elaborate on that?


Cheers!

My current desktop machine is a dual socket 940 Opteron 275 2.2. Ghz server i.e. 4 cores. 4x4 is two socket F Opterons in a dual socket F mobo rebadged as "4x4" for the gamer desktop market.

Socket 939 and socket F Opterons perform identically.

Edit: Corrected 939 -> 940
October 3, 2006 10:36:53 PM

Quote:
My current desktop machine is a dual socket 939 Opteron 275 2.2. Ghz server i.e. 4 cores. 4x4 is two socket F Opterons in a dual socket F mobo rebadged as "4x4" for the gamer desktop market.

Socket 939 and socket F Opterons perform identically.
There is no such thing as a dual socket 939 board, seeing as all 939 chips only have on Hyper transport link; you probably have dual socket 940, which uses registered memory and is not targeted at gamers, but servers and workstations.

Anyways, I'm not going to wait until 2008 for AMD to release K8L, just to have it defeated by Yorkfield.
October 3, 2006 10:51:01 PM

Quote:
My current desktop machine is a dual socket 939 Opteron 275 2.2. Ghz server i.e. 4 cores. 4x4 is two socket F Opterons in a dual socket F mobo rebadged as "4x4" for the gamer desktop market.

Socket 939 and socket F Opterons perform identically.


Well, that's some rig, indeed!
But, a dual Socket F MB will also support QC... that's 8 cores. :wink:

I believe the plus in the 4x4 topology, might be the adaptation of third parties' co-processors, aside the scalability of the platform; the very downside, is cost. Interesting approach, versatility-wise, but hardly ubiquitous.


Cheers!
October 3, 2006 10:57:10 PM

Quote:
Where does it say that DDR3 IMC won't be on AM2+ K8L quad cores?


You'd better read the links. :wink:


Cheers!

Okay, I just confused myself for a second that's all. AM2 CPUs won't be compatible with socket AM3. AM3 CPUs WILL be backwards compatible with socket AM2 (but use DDR2 only).
October 3, 2006 11:03:18 PM

Quote:

Well, that's some rig, indeed!
But, a dual Socket F MB will also support QC... that's 8 cores. :wink:

You can get an 8 core Intel machine (2x Clovertowns) ... next month ... for what an 8 core 4x4 system will cost in Q3 2007 :wink:

Quote:

I believe the plus in the 4x4 topology, might be the adaptation of third parties' co-processors, aside the scalability of the platform; the very downside, is cost. Interesting approach, versatility-wise, but hardly ubiquitous.


4x4 is a transient stopgap for AMD until they can ship their own quad cores. Dual socket solutions are highly uneconomical for desktop use. Hence nobody is going to invest in developing specialised socket accelerators for a platform that is going to be around for 6-9 months as a tiny market niche. Ageia can barely get their physics accelerator going and that just needs a PCI slot.
October 3, 2006 11:09:45 PM

Would be cool though if they could implement a 2nd socket on all new boards (essentially making all AMD boards 4x4ish) on the cheap. It would open up the market for the accelerators. Price of the 2nd socket would be the main factor though.
October 4, 2006 12:14:26 AM

Quote:
@pete4r
K8L is allready developed and it was taped out in august. AMD will clock their K8L processors as much as possible becouse they have strong competition on the road. So far, they can hardly break the 3GHz barrier, especialy becouse they will use the 65nm SOI3. This is the point on which I disagree with you:
"Im sure they can easily break the 3GHz barrier, but that would be Pentium 4 EE all over again."
Also
"Also they can push the clock speed of their cores up when needed, like the old FX series"
They pushed the clock speed of the old FX series with pushing the TDP to 125W which is also contradictory to your statement:
"4 Cores @ 2.9GHz is enough, they have to develop their processor with a strong Power Consumption in mind."
a 2.6GHz FX-60 has 125W TDP. While the 65nm SOI3 K8 dualcore chips will have almost same TDP as 90nm SOI2 K8 dualcore chips. How do you expect the 2.9GHz improved quadcore taking more than twice silicon space to have low power consumation?
That is another point at which I disagree.
And I also disagree on this part:
"So maybe they think 2.9GHz is enough... who knows? but we all just have to be patient to see what AMD can pull out of their bags. "
AMD don't think that 2.9GHz is enough, and we don't have to be patient to see what AMD can pull out of their a$$.


man over and over again u slapping your own face with what u say.

sure if we dont have to wait, where are the benchmarks of K8L vs Conroe? Where are the K8L processors in which shop? man stop ur wasting your time arguing with yourself here... I wont say more, waste of time trying to make a point for some1 who is locked in his own infinite little circle of understanding
October 4, 2006 12:16:33 AM

Quote:
Would be cool though if they could implement a 2nd socket on all new boards (essentially making all AMD boards 4x4ish) on the cheap. It would open up the market for the accelerators. Price of the 2nd socket would be the main factor though.


yeah imagine a dual socket AM2 or 939 mobo, for €200, plus 2 Athlon 62 X2 3800 @ €150 each, thats only 200 + 150 + 150 = €500 u have a quad core system :lol:  :p 
October 4, 2006 12:24:48 AM

Quote:


yeah imagine a dual socket AM2 or 939 mobo, for €200, plus 2 Athlon 62 X2 3800 @ €150 each, thats only 200 + 150 + 150 = €500 u have a quad core system :lol:  :p 


4x4 is socket F only silly. It only takes extreme-gamer priced rebadged Opterons. You cant put cheap X2s into it ... AMD isnt stupid :lol: 

http://www.dailytech.com/article.aspx?newsid=4422
October 4, 2006 12:26:43 AM

Dream on, unless you want a dual-COMPUTER motherboard.
October 4, 2006 1:31:32 AM

Quote:
4x4 is a transient stopgap for AMD until they can ship their own quad cores.


More in the line of this:
http://www.dailytech.com/article.aspx?newsid=1920

See, technologies come & go but there's a cumulative net effect, on what regards Technology; whatever AMD (or any other company) comes up with, it'll be good news for the big "T"; competition also has a net effect on selective filtering. Sure, 4x4 will vanish but so will LGA sockets/packaging & Next Generation [micro] Architectures; the beauty lies somewhere in between, from brainstorms to the drawing boards, from there to materialization & into our own laps. That's the way I see it, anyway.


Cheers!
October 4, 2006 1:50:41 AM

Quote:

Could you post a handful of benchmarks to give the readers who are following the 4x4 some idea of rough performance, preferably applications similar to the current obserations used with Kentsfield.

Jack


Just look up the past benchmarks for the 2.2 Ghz 1mb cache X2s 4400+ ... same performance as my 275s. I just get two extra cores.

A 3 Ghz C2D is about 40% faster than an equivalently clocked X2. So I expect a 4x4 with 3 Ghz chips to be roughly the same speed as one QE6700 at 2.66 Ghz. However, the QE6700 will be VASTLY more overclockable than the 4x4. The k8 arch is near its limit so offers very little OC room. OCing on dual socket mobos is also much more difficult. The kentsfield on the other hand has been OCed to 3.8 Ghz on air cooling. At that clock it will totally anihillate the 4x4.

As gamers are OC addicts I expect them to prefer the Kentsfield route. It also uses less power.
October 4, 2006 2:02:07 AM

Quote:


yeah imagine a dual socket AM2 or 939 mobo, for €200, plus 2 Athlon 62 X2 3800 @ €150 each, thats only 200 + 150 + 150 = €500 u have a quad core system :lol:  :p 


4x4 is socket F only silly. It only takes extreme-gamer priced rebadged Opterons. You cant put cheap X2s into it ... AMD isnt stupid :lol: 

http://www.dailytech.com/article.aspx?newsid=4422

did u not notice the IMAGINE before everything else was said?
October 4, 2006 2:03:37 AM

Cinebench is an very poor multicore benchmark at it scales very poorly.

On the scientific software I use which is designed to scale to thousands of cores, the scale up is linear over 4 cores. Opterons have huge memory bandwidth so scaling is excellent.

So on properly multithreaded sw you can expect 4x4 to scale linearly.

Kentsfield scales linearly over 4 cores on properly multithreaded sw.
October 4, 2006 2:09:20 AM

Quote:
Could you post a handful of benchmarks to give the readers who are following the 4x4 some idea of rough performance, preferably applications similar to the current obserations used with Kentsfield.

Jack


Quote:
Just look up the past benchmarks for the 2.2 Ghz 1mb cache X2s 4400+ ... same performance as my 275s. I just get two extra cores.


And, most of the times, reality pops up & bumps into you. :D 

There's no AMD 4x4 (yet...), you know that & there's no way you can argue back.


Cheers!
October 4, 2006 2:43:32 AM

The last Cinebench benchmark I saw showed a 3.2x speedup on 4 cores which is crappy. 3d studio max showed excellent 4 core scaling but that isnt exactly cheap.

The problem is that there simply isnt a good consumer-orientated freely available multicore benchmark that scales properly to 8+ cores.
October 8, 2006 10:22:45 AM

I am looking forward to 4x4 personally. I think that it will bring a new level to high-end desktops and to workstations. Also, it is going to give users enormous potential to upgrade in 12 months by adding 2 quad cores - changing the chips gets you 8 cores and a new (upgraded) chip architecture!

Also, if the 4x4 platform is basically a tweaked server platform, so much the better! I have an old fx51 system - now 3 years old - which is basically an opteron server tweaked and rebadged (with a server class Mobo, 2.2GHz clawhammer cpu under the hood, and came complete with registered memory). Its still a great machine. Rock solid, reliable, and still pretty fast (for a single core system). A lot of that is down to the fact that it's basically a server. It's built for stability & reliability, and it's also pretty fast! Yes, you sacrifice a little speed because of the server class mobo and RAM, but you're never really going to notice that.
October 8, 2006 11:13:51 PM

Quote:
I am looking forward to 4x4 personally. I think that it will bring a new level to high-end desktops and to workstations. Also, it is going to give users enormous potential to upgrade in 12 months by adding 2 quad cores - changing the chips gets you 8 cores and a new (upgraded) chip architecture!


That would be AMD's 4x4 'platform' (mpjesse's [forum member] words... & I concur) main advantage, towards any other platform: its upgradeability. However, both price & AMD's own concurrence (Altair) in the upcoming year, might seriously limit the scope of such a platform; server/workstation-wise, it's understandable & desirable (RAS, improved FP on the upcoming FX-7x, scaleability); DT-wise, it would seem like committing suicide in two steps: High price premium at start up, w/1 QC & decide between the rope & the knife within 12 months, or rather, between a second 4x4 QC or Altair. I'm, purposefully, leaving Intel outside of the ballpark.


Cheers!
!