Sign in with
Sign up | Sign in
Your question

AMD Has Two Counters To Conroe

Last response: in CPUs
Share
May 29, 2006 8:27:48 PM

So says Charlie:

http://theinquirer.net/?article=31994

Quote:
WE ARE TOLD AMD has a response to the Intel MCW cores, but until a little bit ago, no one would say what. A third mole has now surfaced - it must be mating season - to hint at what it is.
The male moles sing in lovelorn voices that they are all looking forward to what Intel would call a quad-core part from the green team. The females sing back from the other side of the hedge that the males are full of it, and AMD is going to be coming out with a hyper-clocked FX. Mating season makes them crazy.

So, of the two, I lean towards the semi-quad core, it seems like a much more feasible stopgap - ask Intel, it is really good at stopgaps, and this is their solution of choice. The interesting part is how they will be connected, a can of worms that has both up and down sides compared to the Intel FSB approach. Intel just dumps the extra cores on the bus, and puts on a pained smile when you mention bus speed. We hear 1333 is still a stretch goal for Kentsfield and Clovertown, good luck there guys. Either way, 2x2 is easy enough to do, if you are prepared to pay the price.

Enter AMD. It has a bigger problem, as it uses a point-to-point bus. If it does things the Intel way, you end up with one core slaved off the other, and an extra hop across HT to get to the remote core. This has some pretty dire effects on latency, especially on 4S systems. The other approach is to have each die with one HT-out connected to the socket, but this again has latency problems, and potential routing issues.


Anyhow, Charlie forgets that it's intel the one who's catching up to AMD with their conroe processor. We'll have to wait until June to see what AMD has to spoil intel's launch. :wink:

More about : amd counters conroe

May 29, 2006 8:39:22 PM

Dammit 9-inch I actually read that crap!
Can I pretty please have that 2.5 minutes of my life back now?
May 29, 2006 8:48:21 PM

Who cares about Charlie? I'm SIMON! And Simon says:

STFU NOOB
Related resources
May 29, 2006 9:17:53 PM

What were the two counters again? lol
Its silly to think they wont come out with something, but it's even sillier to keep thinking Intel cant regain the crown at least at some point.
It's been a long time coming, I think were all looking forward to the competition. :lol: 
May 29, 2006 10:16:15 PM

Quote:
AMD now knows that they will get killed by Conroe, so they're trying to "give people hope" with words. Big deal, they can talk all they want.


I dont think so. It's going to take more than Conroe to gain back what was at least lost by Intel...

The thing about AM2 is marginal. Much like 478-->775...thats all.
Intel has never seen this before. They must play catch up, while AMD can
afford to say "so what?"....Lying in wait. I'd bet a great deal of money
Intel isnt to comfortable in seeing a company thats use to having to respond to their launches and is now sitting back with a bag of popcorn, earning cash and still moving forward with just a socket change.

Intel's great fear is what (will) be coming from Dresden.....
May 29, 2006 10:23:14 PM

Quote:
AMD now knows that they will get killed by Conroe, so they're trying to "give people hope" with words. Big deal, they can talk all they want.


I dont think so. It's going to take more than Conroe to gain back what was at least lost by Intel...

The thing about AM2 is marginal. Much like 478-->775...thats all.
Intel has never seen this before. They must play catch up, while AMD can
afford to say "so what?"....Lying in wait. I'd bet a great deal of money
Intel isnt to comfortable in seeing a company thats use to having to respond to their launches and is now sitting back with a bag of popcorn, earning cash and still moving forward with just a socket change.

Intel's great fear is what (will) be coming from Dresden.....

Oh god, I can't wait to see Conroe AND to see what comes out of Dresden. Just the thought of being able to get my hands on either chip and make two beefy systems to compare and benchmark... let alone overclock. Gah... if only I had the money... :( 
May 29, 2006 10:24:49 PM

I'm confident that AMD will come out with something competitive, but that article was pure speculation, and so is saying "AMD has two counters for Conroe". It was more of an "Here's two ideas of how AMD can appear competitive in the short term, until they can bring out some real competitive volume products in 2007" type article.

By the way "Conroe" is how you spell the code name for the Core 2 Duo and Core 2 Extreme desktop processors. You seem to consistantly have trouble with it.

Competition is good, Conroe looks like it is going to be a fantastic product. K8L sounds promising, but all real evidence points towards a Q1 or Q2 2007 launch for that technology, so it is not a short term solution. We'll see how it goes and in the short term, maybe Charlie is right, and maybe he is just writing filler as he often does. Either way the competition will continue and we will all benefit in the long term, with better cheaper products from both companies.
May 29, 2006 10:48:02 PM

Quote:
I'm confident that AMD will come out with something competitive, but that article was pure speculation, and so is saying "AMD has two counters for Conroe". It was more of an "Here's two ideas of how AMD can appear competitive in the short term, until they can bring out some real competitive volume products in 2007" type article.

By the way "Conroe" is how you spell the code name for the Core 2 Duo and Core 2 Extreme desktop processors. You seem to consistantly have trouble with it.

Competition is good, Conroe looks like it is going to be a fantastic product. K8L sounds promising, but all real evidence points towards a Q1 or Q2 2007 launch for that technology, so it is not a short term solution. We'll see how it goes and in the short term, maybe Charlie is right, and maybe he is just writing filler as he often does. Either way the competition will continue and we will all benefit in the long term, with better cheaper products from both companies.


Word
May 29, 2006 10:54:06 PM

a) Quad core. This isn't coming out in time for Core2Duo,nor is it likely to be soon after. Sure, it'll probably happen eventually, but it's rather misleading to say it's a "counter" to the Core2Duo. And in a way this is rather irrelevant, as for at least the first year quad core will be marketed at servers, not desktops. Most people can just about utilise 2 cores, it'll be a while before public perception, and more importantly consumer software programming, moves towards even more cores.

b) Hyperclocked FX. Highest they've got is around 4GHz on LN2, so for a regular stock cooled part I'm not thinking they'll be going much further than 3/3.2. And even that probably wouldn't beat Core2Duo , even before we consider the huge price difference. After a while fighting 65nm parts with 90nm starts to bite.

Synergy6
May 29, 2006 10:55:03 PM

You know 9nm this post sounds a lot like your handler rettihsllub, where is he? Haven't seen him around for a while.
May 29, 2006 11:50:09 PM

Quote:
You know 9nm this post sounds a lot like your handler rettihsllub, where is he? Haven't seen him around for a while.

9nm has had a die shrink to 65nm. AMD will only be counting how many crying fanboys there are if Conroe kicks AM2's a$$ (and it looks like it will).
May 30, 2006 12:15:20 AM

Quote:
You know 9nm this post sounds a lot like your handler rettihsllub, where is he? Haven't seen him around for a while.

9nm has had a die shrink to 65nm. AMD will only be counting how many crying fanboys there are if Conroe kicks AM2's a$$ (and it looks like it will).

Well, if 9inch has had a die shrink to 65nm, then that makes him an Intel processor cause he sure as hell isn't an AMD. :wink:
May 30, 2006 12:25:18 AM

Quote:
You know 9nm this post sounds a lot like your handler rettihsllub, where is he? Haven't seen him around for a while.

9nm has had a die shrink to 65nm. AMD will only be counting how many crying fanboys there are if Conroe kicks AM2's a$$ (and it looks like it will).

Well, if 9inch has had a die shrink to 65nm, then that makes him an Intel processor cause he sure as hell isn't an AMD. :wink:
Sh!t; I forgot the decimal point. I was trying to say a die shrink to 6.5nm
May 30, 2006 12:46:31 AM

Quote:
You know 9nm this post sounds a lot like your handler rettihsllub, where is he? Haven't seen him around for a while.

9nm has had a die shrink to 65nm. AMD will only be counting how many crying fanboys there are if Conroe kicks AM2's a$$ (and it looks like it will).

Well, if 9inch has had a die shrink to 65nm, then that makes him an Intel processor cause he sure as hell isn't an AMD. :wink:


Geez man! You literally made me fall out of my chair laughing with that one!
May 30, 2006 12:50:07 AM

Quote:
Herew we go with the inquirer propaganda again,,,,,,9! dewd!AMD is doing janitorial until they can beat conroe.And it was AMD catching up with Intel first of all.
remember k6 and before?Amd will catch up,thing is they dont need to "just this minute" ,they have been an incredible competitor,,,,my gawd man ,give it a rest.


The Inq is just putting out some rather pointless but comical ramblings, as is it's way. It isn't forcing anyone to post their stuff on forums and claim the ramblings constitute a known "counter to Conroe". INQ just write it, takes a fanboy to interpret it as wildly pro-AMD/anti-Intel and use it as a basis for a rather wasted argument.
Synergy6
May 30, 2006 12:59:57 AM

This thread should be made a sticky in the "Stupid AMD Fanboy" section of the Forumz.
May 30, 2006 1:03:44 AM

BUT OMG I LOVE MY AMD, I'D HATE TO SEE SOMETHING THAT'S BETTER!!11 :lol: 
May 30, 2006 1:11:26 AM

the way I see it, even if AMD can clock up an X2 to 3.2 or 3.4ghz to match up with conroe, they're still going to be beat out on power consumption, heat, and most importantly, price ($500 cpu vs. $1000 for example). AMD will have to clock the A64 high, and cut the prices significantly. that hurts for a lot AMD, and I just don't think they can afford it. I'm not saying AMD is a done deal by any means, I'm just saying that I think it's going to be somewhat of a hard fight for them for a bit.
May 30, 2006 1:15:02 AM

What ??? are these people talking about ???

Look I'm a pure blue AMD user (AMD X2 server & Turion Notebook), but lets face it - whilst in the mid size enterprise market, the Opteron is king, on the desktop side, the Athlon at best got AMD on par with Intel - except for unaffordable expensive units where AMD actually did beat Intel.

With Conroe Intel is going to take the lead again and quite substantially it seems. With affordable processors even. AMD will have to improve something drastically to again catch up to Intel.

Remenber Intel is still 20 times AMDs size with almost a 100 times the earnings - so they can invest more in development than the complete AMD yearly budget on everything.

But competition is good - it stimmulates invention. So maybe AMD will again rise to the challenge - lets hope so.
May 30, 2006 1:29:47 AM

Have you heard the rumors? 6.5nm's p3n!$ just got a die enlargement to 9nm. It must be those exercises that he talks about in his interests; I wonder if he'll give me the videotape?
May 30, 2006 1:45:27 AM

I really hope those aren't AMD's real responses to Conroe, because they bring back memories of Intel's knee-jerk reactions to K8 that everyone likes to make fun of. The first "counter" appears to be a Netburst-esque aggressive clocking of the core which may be great for the high-end, but aggressive binning really doesn't help yields for the mid-range or low-end. Their second "counter" is a very Smithfield approach that assumes they can slap 2 dies on a chip and have 1 slaved off another. This approach will actually be worse than Smithfield because Smithfield only had 2 caches to be kept coherent while an equivalent approach from AMD would have 4 caches. On top of that the 2nd die will have to get its memory bandwidth from the IMC of the 1st chip through a HT link which is of course less than ideal.

These types of rushed jobs, especially the latter "non-true" quad core approach that AMD has always marketed against Intel, should be avoided since they do nothing but tarnish the company's image. These measures and their effect on perception are the reason why Intel was forced to drop the Pentium brand. For Intel, it would be wise for them to hold off on Cloverton until they can get those chips working on a 1333MHz FSB. Doubling the cores and reducing the FSB to 1066MHz yields subpar improvements and the last thing they need is to associate the new Core 2 brand with Smithfield. At least they finally decided to give Cloverton 4MB of L2 cache per core instead of 2MB. I'd really like to see the genious who felt they could double the cores while reducing both the L2 cache and the FSB. Seeing the Core 2 samples can reach 1600MHz FSBs and above, the signal strength should be there to allow 1333MHz FSBs for quad cores even with the 3 electrical loads per bus.
May 30, 2006 1:54:44 AM

I'm very surprised that no one has said anything in particular about this article. Look closely: it says response to Conroe. But I thought AMD so high and mighty didn't have to respond to anything because they are the best there was, is, and ever will be. 9-Inch, you screwed up.
a c 448 à CPUs
a c 111 À AMD
a c 110 å Intel
May 30, 2006 2:01:17 AM

Quote:
So says Charlie:

http://theinquirer.net/?article=31994

WE ARE TOLD AMD has a response to the Intel MCW cores, but until a little bit ago, no one would say what. A third mole has now surfaced - it must be mating season - to hint at what it is.
The male moles sing in lovelorn voices that they are all looking forward to what Intel would call a quad-core part from the green team. The females sing back from the other side of the hedge that the males are full of it, and AMD is going to be coming out with a hyper-clocked FX. Mating season makes them crazy.

So, of the two, I lean towards the semi-quad core, it seems like a much more feasible stopgap - ask Intel, it is really good at stopgaps, and this is their solution of choice. The interesting part is how they will be connected, a can of worms that has both up and down sides compared to the Intel FSB approach. Intel just dumps the extra cores on the bus, and puts on a pained smile when you mention bus speed. We hear 1333 is still a stretch goal for Kentsfield and Clovertown, good luck there guys. Either way, 2x2 is easy enough to do, if you are prepared to pay the price.

Enter AMD. It has a bigger problem, as it uses a point-to-point bus. If it does things the Intel way, you end up with one core slaved off the other, and an extra hop across HT to get to the remote core. This has some pretty dire effects on latency, especially on 4S systems. The other approach is to have each die with one HT-out connected to the socket, but this again has latency problems, and potential routing issues.


Anyhow, Charlie forgets that it's intel the one who's catching up to AMD with their conroe processor. We'll have to wait until June to see what AMD has to spoil intel's launch. :wink:

I salute you because you are a true AMD fanboy.

Forget the facts and logic and just rely hope and pure speculation. Maybe that is enough to blindside the noob, but for the more intelligent posters in this forum.

Will AMD catchup to Intel, I am pretty sure they will. But for the moment Intel seems to have AMD over the barrel with Conroe. K8L will be AMD's true counter to Conroe. Do everyone a favor and stop posting useless threads like this. This will only confuse noobies and may cause them to waste money on CPU parts that may not give them thier bang for the buck.

I hold the same contempt for Intel fanboys for spreading pure speculation as well instead of relying on the current facts or waiting for new facts / information to be released.

Remember, you are not only deluding yourself, but you may also be influencing others with bad or false information.
May 30, 2006 2:03:14 AM

I know they won't but I so hope they do the dodgy quad core, man that would be funny.

Anyways, I'm expecting a ramp in FSB and 128bit SSE. That would be pretty solid.
May 30, 2006 2:11:19 AM

u kno, i hav no idea why you ppl are blinded by brands and their models, u amd fans should hope that the new core 2 duo processors are gd, so amd dosnt get lazy, and same goes around for intel fans amd x2s, 64 and fx processors beat out the intels in gaming now core 2 duo looks like its gonna take the crown from amd, in turn amd pulls out better processors, the pattern continues and everyone is happy
May 30, 2006 3:13:53 AM

Quote:
u kno, i hav no idea why you ppl are blinded by brands and their models, u amd fans should hope that the new core 2 duo processors are gd, so amd dosnt get lazy, and same goes around for intel fans amd x2s, 64 and fx processors beat out the intels in gaming now core 2 duo looks like its gonna take the crown from amd, in turn amd pulls out better processors, the pattern continues and everyone is happy
Another Piddy :roll: .
May 30, 2006 8:13:01 AM

Quote:
a) Quad core. This isn't coming out in time for Core2Duo,nor is it likely to be soon after. Sure, it'll probably happen eventually, but it's rather misleading to say it's a "counter" to the Core2Duo. And in a way this is rather irrelevant, as for at least the first year quad core will be marketed at servers, not desktops. Most people can just about utilise 2 cores, it'll be a while before public


What do you think this means??: Kentsfield Q1 2007

Quad-core Intel chip based on Core microarchitecture. Sure it won't be optimal, but it seems they'll go that way for a while before they respond with a 45nm part.

Anyways, Intel will still be competitive, and I even dare say better even by K8L time, only differentiator will become clock speeds.
May 30, 2006 9:00:53 AM

Anyways, here's what I think. K8L isn't AMD's answer to Conroe. It coincidentally looks like it, but if people believe its the truth based on it, then they aren't really looking at history. It seems K8L and Conroe will compete with each other, but it isn't really the answer. If AMD needs to put L3 caches and slapped on quad cores, then that's the answer to Conroe, a very desperate one, similar to the Intel's EE chips, and the Pentium D's.

Sometime around last year, AMD put a presentation up saying the architecture after K8 around the K8L timeframe will have Technical FP extentions, or TFP. They also said it'll have miscellaneous improvements to the core. So they were planning extensions to FP unit in one way or another. I say that because they were even planning to add it on x86-64 instruction set, which we now know they haven't.

Because of the time it takes for big microarchitecture improvement to be implemented, and be validated, they wouldn't have been able to respond to Conroe if they knew it this year.

Intel says Core microarchitecture took 4 years from scratch to near release. So they must have completed design considerations at latest by the time first Prescott CPUs were out. If anything, Core is answer to AMD's K8. And it looks like the results are better than expected.

The shortest time the CPU ever took is Pentium D. Intel said it took only one year, most of the time being validation, and testing. So even though it was a very rushed design, the time they started thinking about Pentium D is a little after Prescott introduction, which the talk about dual cores came about from AMD, and when people started about Intel's lack of dual core plans, THEY ACTUALLY HAD ONE.
May 30, 2006 1:15:29 PM

Quote:
What do you think this means??: Kentsfield Q1 2007

Quad-core Intel chip based on Core microarchitecture. Sure it won't be optimal, but it seems they'll go that way for a while before they respond with a 45nm part.

Anyways, Intel will still be competitive, and I even dare say better even by K8L time, only differentiator will become clock speeds.


Well, it means one of two things, or possibly both.

a) You believe that AMD's "counter to Core2Duo" is ..... Intel's 2007 roadmap.

b) You really have no idea what the original post, or my reply, is about.

Synergy6
May 30, 2006 2:10:06 PM

I enjoyed reading the article but it was mostly, if not purely speculation with little to no facts. None-the-less, as an AMD enthusiast I am excited at the possibilities.
May 30, 2006 2:31:03 PM

Wrong, AMD has NOTHING to counter Conroe...
May 30, 2006 3:05:06 PM

Quote:
Well, it means one of two things, or possibly both.

a) You believe that AMD's "counter to Core2Duo" is ..... Intel's 2007 roadmap.

b) You really have no idea what the original post, or my reply, is about.

Synergy6


Quote:
b) Hyperclocked FX. Highest they've got is around 4GHz on LN2, so for a regular stock cooled part I'm not thinking they'll be going much further than 3/3.2. And even that probably wouldn't beat Core2Duo , even before we consider the huge price difference. After a while fighting 65nm parts with 90nm starts to bite.


a) My mistake
b) though I haven't really considered answering b), again my mis-understanding :oops: 
May 30, 2006 3:28:48 PM

I agree with David in that I am sure AMD has been working on something new since the K8 has been out. If the 4 year cycle is to be believed, then AMD's new offering would be due out about the end of this year since the K8 has been out since late 2002. We've heard of K8L coming around the end of this year, early next, so that's about the right cycle length.

I seriously doubt more than 2 cores will be used at AMD until HT2 comes along. I could see them dividing the HT2 bus into two HT buses and giving each pair of cores its own HT bus so that the throughput remains constant to a dual core offering. AMD is all about scalability and they're not just going to drop that now to try and match some desktop processor. They know it would fail, they're smarter than that. And they know people will keep buying them anyway, because they are good processors, they've built that reputation. Just because they're not on top doesn't mean they're not good processors, unlike intel's previous offerings which were neither on top or good.

Tuning up the FPU or adding another should give better results with superpi though, which seems to be the holy grail around here for conroe fans :roll:
May 30, 2006 3:58:45 PM

I would like to see everyone on this forum try to get creditable sources when they post something...

I mean if you see some article by "the inquirer"... COME ON. It's the freaking inquirer! PLEASE, do not use that as a valid source.

There is a reason why people call the inquirer a rag newspaper. So next time anyone has a post with "the inquirer"... it's probably best to just ignore it all together.

Shame on everyone in this post for even responding to something that uses the inquirer as its primary source.
May 30, 2006 4:01:14 PM

Quote:
There is a reason why people call the inquirer a rag newspaper. So next time anyone has a post with "the inquirer"... it's probably best to just ignore it all together.

Shame on everyone in this post for even responding to something that uses the inquirer as its primary source.


No. You just filter out some of the authors. Some, are plain incorrect, some are funny, and few are right, like Charlie.

He didn't say what will be faster, AMD's response or Conroe or whether AMD's response will be faster at all than current AM2 CPUs. He just said there are two answers. Whether that means there are actually two choices or he is speculating, we don't know.
May 30, 2006 4:32:21 PM

The Inquirer is, in this case, not a newspaper. Nor is it, in my opinion, definable as a "rag", though that may well be your opinion. Any news article can be taken as evidence by fanboys, from the National Inquirer to the NYT.

If the Inq posted an article claiming to have known proof of AMD's "counter to Core2Duo", with this content, then yes, it would classify as rag material. As it stands, it just posted a light-hearted ramble which happened to be flagged up on the global fanboy radar system (GFRS). Not really their fault, unless they're going to put "Not to be used by fanboys" at the bottom of every article.

Really, shame on anyone unsure enough about the content of their writing that they require large, bold type to have any hope of someone bothering to trawl through it.

Synergy6
May 30, 2006 6:47:32 PM

Quote:
I really hope those aren't AMD's real responses to Conroe, because they bring back memories of Intel's knee-jerk reactions to K8 that everyone likes to make fun of. The first "counter" appears to be a Netburst-esque aggressive clocking of the core which may be great for the high-end, but aggressive binning really doesn't help yields for the mid-range or low-end. Their second "counter" is a very Smithfield approach that assumes they can slap 2 dies on a chip and have 1 slaved off another. This approach will actually be worse than Smithfield because Smithfield only had 2 caches to be kept coherent while an equivalent approach from AMD would have 4 caches. On top of that the 2nd die will have to get its memory bandwidth from the IMC of the 1st chip through a HT link which is of course less than ideal.


I also hope they won't use this stupid idea since doing so will label them as stupid as intel.

What Charlie didn't mention is the upcoming revision G chip which AMD might use to spoil intel's launch until they have K8L ready. :wink:

Here's a link:
http://129.15.202.185/athlon_rev_g/wtf_mates.html

Quote:
The extra hardware in between the L2 cache and the data cache is likely an out-of-order L2 read/write buffer that expedites data neeeded for execution. The large bank on the other side of the data cache would be the logical placement for an out-of-order load/store buffer. This prevents cache misses from waiting on Stores to main memory. The extra complex decoder was spotted by a poster on some website. It was the first feature that caught my eye. This shot is definitely not of K-8. Given the layout of the additions, their functions can be inferred.


...And here's what a well-knowledgeable member from XS forums had to say about it:

Quote:
Well I can, won't reveil how or what regarding this pic, everbody knows it came from tweakers.net and what guys they discussed it with.

The extra decoders means the pipeline gets filled much faster giving an overal boost in pure ALU performance. In the 'older' cores more complex instructions would even have to be broken up an extra time (they get broken up anyways) so we'll see SSE3 performance raise a lot.

Also they prolly combine this fast feeder with more powerfull ALUs comparable to what Conroe has. This means you get excellent ALU performance (clearly seen in synthetic ALU benches like DryStone, WhetStone, PiFast, SuperPi etc). It's a total guess at how fast the new decoders and ALUs will be, we'll have to wait.

The out-of-order L2 has been a heavily requested feature and the part AMD has gotten a lot of bad press (in techy world that is). It's kinda hard to explain how it really works without writing up a 3000 word essay with a lot of technobabble, so I'm not going to do that. I'll try to explain why they did it instead of what it does:

It's well known cache isn't as important for K8 as it is for netburst, this is because of a couple of reasons:

Shorter pipelines so pipeline stalls have less of an impact (but relatively very bad anyways)
Reasonable prefetchers and branch predictors (not as good as Intel's netburst)
Very high speed memory interface (so pipeline stalls can be fixed much faster)

There are a few problems when trying to increase the performance of the cache and the predictors/prefetchers. You can simply increase cache size which reduces cache misses and thus pipeline stalls. You can also improve the prefecters and predictors.

However: Cache is expensive, they are simple memory circuits but need to operate at core speed. If you have a lot of cache the yields can go down and cache is expensive stuff. Compare it to TFT technologies, even if yields are very good 1 in say 100.000.000 cache circuits go wrong if you have a big cache the chance the cache is faulty becomes bigger and bigger.

Cache also increases die size and use up a lot of resources. The effect is also exponentially flawed, you need to increase the cache size exponentially to get the same results. So that's something you only do if you're desperate (like we've seen Intel do with Xeons).

The other way is to increase the predictors and pre-fetchers, this is not only difficult (the circuits become very complex and hard to design and fabricate) it also requires a LOT of extra circuits to make even small improvements. We've all seen the Presler die pics and saw how much of the core was actually dedicated to the pre-fetchers. Intel has a lot of experience from the netburst, AMD does not.

The branch predictors and pre-fetchers are expensive to design, but aren't as expensive to produce. Altough the die size increases it isn't as bad as the cache where die size increases exponentially. There is however a BIG downside: These circuits get hot, they need to switch a lot so micro-wear becomes an issue as well.

Because AMD has developed this new more dense cache technology we'll prolly see an increase from 2MB to 4MB or maybe 8MB. This will improve performance, AMD has prolly done a lot of research where the 'cut-off' point is between more expensive CPUs and improved performance and prolly found a good point. (Don't think the CPUs will become more expensive as they now are, they'll release single core and sempron versions with less cache and the AM2 CPUs are now expensive but prices will drop making place for the new CPUs with the same prices as they are now).

The out-of-order L2 buffer helps with the new branch predictors and prefetchers so that's prolly why they did it. This alone has almost no impact on performance but is needed to get better branch predictors and prefecters. It also takes away a argument for most techies who want to badmouth AMD.

Rev G. will improve performance and when die-shrinking it to 65nm we can see clockspeeds up to 4 ghz. This however isn't the answer to Conroe from AMD. AMD and Intel are out of sync, the answer from one is put into the market about 6 months after the release of the other.

It's important to also understand the way AMD runs their factories, it's completely different from Intel's fabs. AMD actually has a system where yield automatically get better and better. They have techniques where faults in the production of the CPUs (and the whole process before the actual CPUs are made) can be corrected. Also they have the possibility to implement improvements in the design at a weekly basis (where Intel requires as much as a month or 2 to implement changes).

I've got a report written by Wouter Tinus in Dutch about AMD's fabs, it's actually amazing what they've got.

I know my post doesn't always make stuff any clearer, but that's because it is a complex world, the world of computers and especially CPUs


http://www.xtremesystems.org/forums/showthread.php?t=101139[/code]
May 30, 2006 7:15:38 PM

Quote:
You know 9nm this post sounds a lot like your handler rettihsllub, where is he? Haven't seen him around for a while.

9nm has had a die shrink to 65nm. AMD will only be counting how many crying fanboys there are if Conroe kicks AM2's a$$ (and it looks like it will).

Well, if 9inch has had a die shrink to 65nm, then that makes him an Intel processor cause he sure as hell isn't an AMD. :wink:
Sh!t; I forgot the decimal point. I was trying to say a die shrink to 6.5nm

Rather than all that, maybe a visit to a shrink is what the poor guy needs...
May 30, 2006 8:02:20 PM

Quote:
Wrong, AMD has NOTHING to counter Conroe...


Since your obviously way smarter than everyone else and can see into the future can you tell me who will win the stanley cup this year? :roll:
May 30, 2006 8:51:56 PM

Quote:
What were the two counters again? lol
Its silly to think they wont come out with something, but it's even sillier to keep thinking Intel cant regain the crown at least at some point.
It's been a long time coming, I think were all looking forward to the competition. :lol: 

Yup, going to get really interesting when these 2 companies get their stuff to market..........
not so interesting is all the Extremist talk from both sides that have nothing to do with either of the companies.
May 30, 2006 9:31:11 PM

Quote:
...they require large, bold type to have any hope of someone bothering to trawl through it.


Yes the bold big type is annoying 8O !





Quote:
...shame on anyone unsure enough about the content of their writing ...

But for the record I am not unsure about what I wrote. I stand by what I am saying. But I admit that it had annoying typeface.
May 30, 2006 9:49:54 PM

Quote:
I would like to see everyone on this forum try to get creditable sources when they post something...

I mean if you see some article by "the inquirer"... COME ON. It's the freaking inquirer! PLEASE, do not use that as a valid source.

There is a reason why people call the inquirer a rag newspaper. So next time anyone has a post with "the inquirer"... it's probably best to just ignore it all together.

Shame on everyone in this post for even responding to something that uses the inquirer as its primary source.

YES GOD DAMNIT STOP FLJCKING POSTING ENQUIRER BULLSH1T
May 30, 2006 10:16:01 PM

You can't even put that as a source it a love letter to AMD based on no facts but some lame titles hyper FX. I got a hyper PSP same as the regular one just I wrote hyper on the side.
May 30, 2006 10:19:18 PM

For me , in my point of view, the next generation core 2 duo, i just more that a research for more that 4 years that intel does under pressure from amd, in my way of think i can be for sure that the amd am2 will be a competitive product up to the next arrival and sucessor K8L architecture, also there's rumors about a FX SUPERCLOCKED version just for hold on intel from he's mass destruction conroe cores. I hope and i believe that AMD, will make a good response by the time become.

Also in the last quarter of this year, amd will introduce the 0.65nm manufacture process, so with the existing architecture, they can reach better speed and better TDP ratios., is amazing what amd does with 0.90nm , power manangment, TDP, and speed. Here's the advantages of AMD.





The performance is going with intel Core Duo 2 by the short time , but my heart is with AMD.

Just the time will tell us the real road.
May 30, 2006 10:56:06 PM

I'm starting to believe the 2MB L3 + better SSE plus more decoder's are truly going to be what we see. This is going to be stop-gap though as K8L will be the realization of the technology. I'm thinking that this Rev G is going to be AMD's "Yonah" with a very short lifespan.
May 30, 2006 11:21:54 PM

Quote:
Wrong, AMD has NOTHING to counter Conroe...


I find it odd that so many people are writing AMD off as though their next set of processors will be worthless. We have seen in the past that AMD has put out some incredibly powerful chips, and I see no reason to think that it will be any different in the future. This current crop of AM2 proc's are merely a migration of the current 939 ones to the new socket. When AMD puts out its next architectures, then I will be willing to compare the two (and if history is repeats itself, AMD will win, again).

Or maybe the world will implode because the performance crown will change hands so many times in the next year or so. But such is the market. Maybe we will see the same thing happen with proc's as we have seen with the video cards: intense competition driving more innovation and better prices. Sounds like a great way for things to go, if you ask me. Except for the whole imploding thing, that wouldn't be very cool for very long.
May 30, 2006 11:28:45 PM

Quote:
Wrong, AMD has NOTHING to counter Conroe...


Since your obviously way smarter than everyone else and can see into the future can you tell me who will win the stanley cup this year? :roll:

Oilers!!!
May 30, 2006 11:39:45 PM

Quote:
Wrong, AMD has NOTHING to counter Conroe...


Since your obviously way smarter than everyone else and can see into the future can you tell me who will win the stanley cup this year? :roll:

Oilers!!!

You could hear the cheer's from the coliseum from downtown whenever they scored and people are driving around all night honking and i have seen 1000's of flags on cars(even got one myself).....
They had better win.
May 30, 2006 11:49:34 PM

Quote:
Wrong, AMD has NOTHING to counter Conroe...


Since your obviously way smarter than everyone else and can see into the future can you tell me who will win the stanley cup this year? :roll:

Oilers!!!

You could hear the cheer's from the coliseum from downtown whenever they scored and people are driving around all night honking and i have seen 1000's of flags on cars(even got one myself).....
They had better win.

I hope so too!!!
!