Tuesday, September 18th 2018

AMD Readying a 10-core AM4 Processor to Thwart Core i9-9900K?

To sustain its meteoric rise at the stock markets, AMD needs to keep investors convinced it has a competitive edge over Intel, even if it means investing heavily on short-term roadmap changes. According to an Elchapuzas Informatico article, AMD could be working on a new 10-core/20-thread processor for the AM4 platform, to compete with the upcoming Core i9-9900K 8-core/16-thread processor from Intel. The said processor is being labeled "Ryzen 7 2800X" and plastered over CineBench nT screenshots, where due to the sheer weight of its 10 cores, it tops the nT test in comparison to Intel's mainstream-desktop processors, including the 2P Xeon X5650 12-core/24-thread.

The Forbes article that cites the Elchapuzas Informatico, however, is skeptical that AMD could make such a short-sighted product investment. It believes that development of a 10-core die on existing "Zen+" architecture could warrant a massive redesign of the CCX (Zen Compute Complex), and AMD would only get an opportunity to do so when working on "Zen 2," which AMD still expects to debut by late-2018 on its EPYC product line. We, however, don't discount the possibility of a 10-core "Zen+" silicon just yet. GlobalFoundries, AMD's principal foundry partner for CPUs, has given up on 7 nm, making the company fall back to TSMC to meet its 7 nm roadmap commitments. TSMC already has a long list of clientele for 7 nm, including high-volume contracts from Apple, Qualcomm, and NVIDIA. This could force AMD to bolster its existing lineup as a contingency for delays in 7 nm volume production.
Source: Forbes
Add your own comment

134 Comments on AMD Readying a 10-core AM4 Processor to Thwart Core i9-9900K?

#76
lexluthermiester
hat said:
Begun, the core war has.
That started about 13 years ago with the Athlon 64 X2 and Pentium D.
(Props on channeling Master Yoda..)

Valantar said:
Don't remember where I saw it, but this has been debunked. It's fake. Why?
Please, do tell us..
Valantar said:
CineBench scores can be manipulated just by editing a text file
Yawn..
Valantar said:
The description of the CPU doesn't match AMD naming conventions in Cinebench (among other things, it says "10-core", while AMD CPUs are described with words, not numbers ("six-core", "eight-core")
Can you prove this with screen-shots of other high core-count CPU's from either Intel or AMD? (Hint, go looking..)
Valantar said:
And last but certainly not least: There's no way to get a 10-core AM4 chip without new silicon, which would mean this is 7nm. There's no way they'd launch their first 7nm CPUs as an afterthought like this.
Let's leave the engineering to the experts, ok? Alrighty then..
Valantar said:
Please stop treating this like it's real.
That is an opinion and not very good one.
Posted on Reply
#77
Valantar
lexluthermiester said:
please, do tell us..

Yawn..
You know, lex, I've come to appreciate your style of argument. Some times, there's just too much on-topic discussion and actual arguments being presented, and your derogatory tone and dismissiveness without any backing or substance is quite refreshing at times.

lexluthermiester said:
Can you prove this with screen-shots of other high core-count CPU's from either Intel or AMD? (Hint, go looking..)
Why high core count? This is supposed to be a Ryzen, not a Threadripper. My 1600X is denominated as "AMD Ryzen 5 1600X Six-Core Processor". 1800Xes are "... Eight-Core". One would expect naming to be consistent within the same product family, no? This, of course, is in addition to the other naming error: the use of "Ryzen R7" in the "leak", which isn't a naming style AMD has ever used (which makes sense, as "R7" is supposed to be short for "Ryzen 7"). While the use of numbers or words for the number of cores might vary depending on the count, it makes no sense for "R7" to appear no matter the context.
lexluthermiester said:
Let's leave the engineering to the experts, ok? Alrighty then..
Is this an engineering question? No, it's an engineering and sales/marketing question. Engineering doesn't happen in a vacuum, and the engineers aren't going to make anything that they can't sell enough of to recoup the development and production costs - they wouldn't be given the resources to do so. Besides, it's not like you've shown anything engineering-related that might counter my arguments.
lexluthermiester said:
That is an opinion and not very good one.
Welcome to the opinion club, I guess? This is a forum, where, among other things, we discuss opinions - particularly when we don't have facts to base anything off of. You're very welcome to present a counterargument if you like, and perhaps clarify why you think this "not a very good" opinion? 'Cause so far, your opinion seems limited to mine being wrong. IMO, that doesn't bring much of value or substance to the discussion.
Posted on Reply
#78
lexluthermiester
Valantar said:
You know, lex, I've come to appreciate your style of argument. Some times, there's just too much on-topic discussion and actual arguments being presented, and your derogatory tone and dismissiveness without any backing or substance is quite refreshing at times.
You know Val, it's nice to be appreciated once in a while. For example you appreciating my "derogatory" "dismissiveness" to the misguided information you tried, and failed, to offer as convincing.
Valantar said:
Why high core count? This is supposed to be a Ryzen, not a Threadripper.
If you had actually looked it up, you would know why. Clearly you did not, thus you're missing something that made your argument invalid.
Valantar said:
IMO, that doesn't bring much of value or substance to the discussion.
Ah, but the contribution being made is to discredit your opinions and notions as invalid on merit. For example, to say the AMD lacks the resources to render a new product line that effectively is a mere extention of an existing, proven technology already in mass production is completely without merit and logic. Furthermore, this new CPU line might be a rebadge and retooling of Threadripper dies that have a mix of faulty and good cores, with the faulty cores being disabled, which has been done many times in the past by many companies.

Years ago, when AMD released 3 core CPU's, people said it wasn't possible or AMD couldn't do it because this, that or the other thing. They did it anyway. When Intel released the Core series of CPU's and claimed that it was a massive leap forward and that the bottom tier Core CPU's could stand their ground with the top tier Pentium series, people said it wasn't possible and yet it happened.

@Valantar, for someone like you to say a company like AMD can't do something they have literally already done is so absurd that it is almost beyond belief. It is preposterous for you, or anyone else, to say with any level of credibility that a 10 core, or even an 11 core, CPU can not be produced by a company that has already produced CPU's with over triple that core count in mass amounts. So when I said that your opinions are not very good, it is because they lack logic, reason and merit, but also stand in the face of known technological, scientific and historical facts. Those arguments are as incredulous and vapid as they are illogical.
Posted on Reply
#79
Valantar
lexluthermiester said:
You know Val, it's nice to be appreciated once in a while. For example you appreciating my "derogatory" "dismissiveness" to the misguided information you tried, and failed, to offer as convincing.

If you had actually looked it up, you would know why. Clearly you did not, thus you're missing something that made your argument invalid.

Ah, but the contribution being made is to discredit your opinions and notions as invalid on merit. For example, to say the AMD lacks the resources to render a new product line that effectively is a mere extention of an existing, proven technology already in mass production is completely without merit and logic. Furthermore, this new CPU line might be a rebadge and retooling of Threadripper dies that have a mix of faulty and good cores, with the faulty cores being disabled, which has been done many times in the past by many companies.

Years ago, when AMD released 3 core CPU's, people said it wasn't possible or AMD couldn't do it because this, that or the other thing. They did it anyway. When Intel released the Core series of CPU's and claimed that it was a massive leap forward and that the bottom tier Core CPU's could stand their ground with the top tier Pentium series, people said it wasn't possible and yet it happened.

@Valantar, for someone like you to say a company like AMD can't do something they have literally already done is so absurd that it is almost beyond belief. It is preposterous for you, or anyone else, to say with any level of credibility that a 10 core, or even an 11 core, CPU can not be produced by a company that has already produced CPU's with over triple that core count in mass amounts. So when I said that your opinions are not very good, it is because they lack logic, reason and merit, but also stand in the face of known technological, scientific and historical facts. Those arguments are as incredulous and vapid as they are illogical.
I have no idea where you're getting these claims from, but they're definitely not from my post. Let's see:
  • I didn't say AMD didn't have the resources to do this, I said it wouldn't make sense to waste resources on a one-off product added to an existing product line that wouldn't stand a chance to recoup the R&D costs.
  • "A rebadge of Threadripper dies" makes no sense, given that all Ryzen dies on the same process are the same die, just different bins. Ryzen 1000, TR 1000 and Epyc 1st gen are all the same die. Ryzen 2000 and TR 2000 is also the same die. Ryzen 3000 (and likely TR 3000) will in all likelihood be the same (Zen2) die as 7nm Epyc.
  • Whether these were "Threadripper dies" or not, it doesn't take away from the inherent issues with cramming two dice within the confines of an AM4 package. This would require a thicker/more complex substrate, which would mess with cooler compatibility, at the very least. Nor would getting the IF traces implemented be an easy task in a package that small.
  • The need for symmetric CCXes within a die is a documented feature of the Ryzen architecture. Of course AMD isn't flaunting this, but I've seen it reported from reputable sources that asymmetrical disabling of cores is impossible with the current design. This might change with Zen2, or it might not - we don't know.
  • Previous 3-core AMD chips were all based on a fundamentally different design from Zen. Don't see how this is applicable. Sure, the concept has been realized before, but with an entirely different basis.
Beyond this, nothing you've said is really applicable. TR and Epyc are MCM products, while the AM4 has no such thing. Making one wouldn't be impossible, but complicated, expensive, and would introduce the same issues we see with TR for consumer-facing applications (NUMA awareness, latency, etc.). It doesn't seem reasonable whatsoever that AMD would spend a significant amount of money on this when it would be obsolete in 6-8 months when 7nm Zen2 Ryzen CPUs arrive.

Of course, a 10-core could be a 7nm chip based on a 2x8-core Zeppelin (with three cores disabled per CCX) - but that would mean launching their first 7nm Ryzen as an afterthought product on an existing product line. Sure, the standalone launch would garner attention, but wouldn't it then make more sense for this to kickstart the 3000-series, rather than call it "2800X" and make it seem like a minor upgrade from the 2700X when it's in fact based on a significantly updated architecture?

Again: neither of these theories make sense in terms of business, economics, or engineering when factoring in the running of the business. Can it be done? Sure, probably. Would it be smart? No. And if there's one thing we can say about AMDs strategies over the last few years, they're damn smart.
Posted on Reply
#80
mastrdrver
lexluthermiester said:
That started about 13 years ago with the Athlon 64 X2 and Pentium D.
(Props on channeling Master Yoda..)....Let's leave the engineering to the experts, ok? Alrighty then........
You don't have to leave it to engineering. If you want a 10 core where you have a mask for 8 core you have to make a new mask. Just because you have a 8 core mask does not mean that adding 2 more cores to the mask will make it work. You have to certify the chips to make sure the mask is working. Lets not mention that there are the metal layers and the wires to connect the metal layers that have to be done too. When you get like 10 metal layers alone, there's a lot to go wrong.

Even if they went this route, I'd expect it more for Zen2. The time needed to get the silicon back from the fab and make the fixes and go through the changes needed to make it work, you're already looking at close to a year out hoping you only need to make 1 change in those 10+ metal layers.
Posted on Reply
#81
lexluthermiester
Valantar said:
I didn't say AMD didn't have the resources to do this
You directly implied it by saying..
Valantar said:
And last but certainly not least: There's no way to get a 10-core AM4 chip without new silicon, which would mean this is 7nm. There's no way they'd launch their first 7nm CPUs as an afterthought like this.
.. which it patently incorrect.
Valantar said:
Of course, a 10-core could be a 7nm chip based on a 2x8-core Zeppelin (with three cores disabled per CCX) - but that would mean launching their first 7nm Ryzen as an afterthought product on an existing product line. Sure, the standalone launch would garner attention, but wouldn't it then make more sense for this to kickstart the 3000-series, rather than call it "2800X" and make it seem like a minor upgrade from the 2700X when it's in fact based on a significantly updated architecture?
You're thinking to small. They could take two 6core dies each with one of it's cores disabled. What makes sense is that AMD likely has a ton of wafer dies that have minor defects and they want to put them to use, as they have done in the past.
Valantar said:
Again: neither of these theories make sense in terms of business, economics, or engineering when factoring in the running of the business. Can it be done? Sure, probably. Would it be smart? No.
Maybe it doesn't make sense to you. But you, nor anyone outside AMD, can say definitively what actually makes sense for AMD.
Valantar said:
And if there's one thing we can say about AMDs strategies over the last few years, they're damn smart.
At least we can agree on something.
mastrdrver said:
You don't have to leave it to engineering. If you want a 10 core where you have a mask for 8 core you have to make a new mask. Just because you have a 8 core mask does not mean that adding 2 more cores to the mask will make it work. You have to certify the chips to make sure the mask is working. Lets not mention that there are the metal layers and the wires to connect the metal layers that have to be done too. When you get like 10 metal layers alone, there's a lot to go wrong.

Even if they went this route, I'd expect it more for Zen2. The time needed to get the silicon back from the fab and make the fixes and go through the changes needed to make it work, you're already looking at close to a year out hoping you only need to make 1 change in those 10+ metal layers.
You really need to read the rest of the conversation.
Posted on Reply
#82
Valantar
lexluthermiester said:
You directly implied it by saying..

.. which it patently incorrect.
You're misreading me there, there is no implication that AMD doesn't have the resources to do this. Saying it's too expensive doesn't mean they couldn't afford it if they wanted to - strategically smart use of money and the capability to spend money are not the same thing. What I've said all along is that two of the three possible ways of achieving this (new 12nm silicon or a MCM package for AM4) don't make sense for economic reasons. No implication that AMD can't do it, just that doing so - particularly for a single SKU that will be eclipsed by a new product series in 6-8 months - would essentially be throwing R&D money out the window with no chance whatsoever of recouping the costs (high-end, >$300 SKUs represent a quite small portion of sales). Strategically, this would be really dumb.

The third option, using defective 7nm dies, doesn't make sense for strategic and marketing reasons - while launching a retail 7nm CPU in 2018 would be a triumph, it'd be a short-lived, low-volume, very expensive product that would essentially undermine the entire 3000-series when it launches next spring. And the converse option, kick-starting the 3000-series with a high-end 7nm part in late 2018, would be downright dumb in terms of marketing - the vast majority of customers would want to wait for more reasonably priced 6-8-core parts, which would then arrive more than half a year later. That's more than long enough for people to lose interest and buy whatever's available. Of course, this also presupposes that they can't use defective 7nm dice (once these enter volume production) for Epyc CPUs, which have far higher margins and would make far more sense for a low-volume part (especially as there'd be no extra R&D cost).

lexluthermiester said:
You're thinking to small. They could take two 6core dies each with one of it's cores disabled. What makes sense is that AMD likely has a ton of wafer dies that have minor defects and they want to put them to use, as they have done in the past.
... but they already harvest defective dice for <8-core SKUs (and 12c/24c Threadripper). No need to put them to use in any other way unless the defect rate on 12nm is far higher than what's reasonable at this stage in production. In all likelihood they're already disabling fully functioning silicon to fulfill the need for low-end silicon. And why would they design a 6-core die? Unless you're expecting next-gen APUs to have 6 cores in a single CCX, this doesn't really align with AMD's stated strategies either. And given that Epyc is confirmed to launch with 64 cores, that means that the next-gen larger CCX is 8 cores, not 6. While it does make sense to separate out consumer and enterprise silicon as sales volumes grow, it makes more sense for them to launch single-CCX =<8-core CPUs (essentially the entire consumer lineup in a single-CCX design) than having up to 6 in one CCX and 8-12 in two.

lexluthermiester said:
Maybe it doesn't make sense to you. But you, nor anyone outside AMD, can say definitively what actually makes sense for AMD.
That is of course true. But then again, neither can you. Unless you're working for AMD developing their CPU strategy?
Posted on Reply
#83
lexluthermiester
Valantar said:
blah blah blah
Yawn
Valantar said:
That is of course true.
Gee, thanks for the unneeded and unnecessary validation. Of course it's true. It doesn't take a genius to figure such out.

If AMD thinks they can profit from a 10 core product, then they are going to do it regardless.
Posted on Reply
#84
Valantar
lexluthermiester said:
If AMD thinks they can profit from a 10 core product, then they are going to do it regardless.
Well, duh. That's a gross oversimplification, though. Not to mention that my entire line of argumentation revolves around how likely it is that they could profit from this or not. You don't seem to want to discuss that, though, nor to discuss the validity of the leak in question here. If you're so strongly opposed to discussing speculation and opinion, why are you even here? The "leak" itself is unverified and there are strong indications that it's fake. There are no facts to discuss here.
Posted on Reply
#85
mastrdrver
lexluthermiester said:
You really need to read the rest of the conversation.
There is nothing else to read because it's all senseless babel. Nothing you've stated addresses the root of the issue of which I pointed out.
Posted on Reply
#86
lexluthermiester
Valantar said:
Well, duh. That's a gross oversimplification, though.
Not really.
Valantar said:
You don't seem to want to discuss that, though, nor to discuss the validity of the leak in question here.
Hmm. Interesting that.
Valantar said:
If you're so strongly opposed to discussing speculation and opinion, why are you even here?
Discussing speculation is very different from sharing opinion. I'm not opposed to either. What I am opposed to is needless, meritless AMD/Intel/"Company name here" bashing which is very much what you seemed to be doing here.
Valantar said:
The "leak" itself is unverified and there are strong indications that it's fake.
That is possible. It's also possible that it is real. We won't know until AMD goes public with a statement one way or the other.
Valantar said:
There are no facts to discuss here.
Oh? How can that correct? There are plenty of facts to speak of.

Fact; If AMD thinks they can benefit from the release of a 10core CPU line and it is worth their time to do so, they will without fail.
Fact; As AMD has already released CPU lines with core counts greater than 10, making a 10core line is very possible and equally plausible.
Fact; AMD has historically been known for taking advantage of any and every opportunity available, including reworking existing designs to maximize capitalization.
mastrdrver said:
There is nothing else to read because it's all senseless babel.
Yeah you seem to do that quite often..
mastrdrver said:
Nothing you've stated addresses the root of the issue of which I pointed out.
And you think that because you failed to read through everything.
Posted on Reply
#87
mtcn77
Everyone seems to discount there is money in server chips and Intel has asymmetrically arranged mesh topology, but AMD is not to counter that? Where do you get that from, the parrot magazine?
Fact, Raven Ridge comes with a similar half-CCX variant. One only needs to add it to the 'Summit Ridge', potentially 4+4+2.

Raven Ridge vs Zeppelin


CCX Variants (WikiChip)
Posted on Reply
#88
Valantar
lexluthermiester said:
What I am opposed to is needless, meritless AMD/Intel/"Company name here" bashing which is very much what you seemed to be doing here.
Sorry, what? Seriously? Wow. I don't even mean this as snark: you really need to work on your reading comprehension. What have I said here that can be seen as "bashing" any company, and how exactly? This is ridiculous. Oh, and not that it matters, but all the three desktop PCs in my household are AMD-based, two of them built/upgraded within the last year and a half...

I have been discussing the merits of this leak, as well as the engineering/marketing/sales/strategy aspects of going forward with a design like this. I think it's a genuinely bad idea. You don't. We disagree. Deal with it. This is not bashing AMD, it's the complete opposite: not wanting AMD to waste their relatively limited resources on a silly product that won't do them any good in neither the short or long term. If you read this as bashing AMD, there is something very much wrong with how you're reading this.

Now, either please reread my posts here and try to figure out what you've misunderstood, or stop replying to me. I really can't be bothered dealing with this any more, as the misunderstanding is entirely on you.
Posted on Reply
#89
lexluthermiester
Valantar said:
Sorry, what? Seriously? Wow. I don't even mean this as snark: you really need to work on your reading comprehension.
Comprehension is not the problem.
Valantar said:
I have been discussing the merits of this leak, as well as the engineering/marketing/sales/strategy aspects of going forward with a design like this. I think it's a genuinely bad idea. You don't. We disagree.
Clearly
Valantar said:
This is not bashing AMD
It comes off that way, whether you realize it or not. I'm leaning towards not..
Valantar said:
it's the complete opposite: not wanting AMD to waste their relatively limited resources
That's just it, it wouldn't be a waste of resources. It would in fact be very wise to utilize in such a way. And because of the success of Ryzen, AMD's resources are not "relatively limited". For you to state that AMD's resources are limited and that making such a product would be outside the scope of those resources is bashing by implication.
Valantar said:
If you read this as bashing AMD, there is something very much wrong with how you're reading this.
Or it could be the way you're stating things.
Valantar said:
Now, either please reread my posts here and try to figure out what you've misunderstood, or stop replying to me. I really can't be bothered dealing with this any more, as the misunderstanding is entirely on you.
Ok, I'll yield on this one. I did reread your posts and still conclude that you seemed to be bashing AMD. If that is not your intent then I apologize.

I'm not a fan of company bashing in general unless the company in question has few or no redeeming qualities. In the case of AMD, they currently hold two very important crowns in the X86 CPU market; They have the highest performing single socket CPU crown and they have the best value for money spent crown. In Intel's case, they hold the best gaming performance crown, but not by much and they may loose it. In the last 18ish months AMD has forged ahead and they show no signs of slowing down. This is good for the entire industry as it is forcing Intel to actually compete with someone other than themselves. AMD releasing a 10core CPU not only makes sense from a logistics perspective, but it makes sense from a competition perspective. A 10core offering is good for the market even if the benefit isn't large as it will show everyone that AMD doesn't just have bite, but also ability to sustain.
Posted on Reply
#90
Valantar
lexluthermiester said:
That's just it, it wouldn't be a waste of resources. It would in fact be very wise to utilize in such a way. And because of the success of Ryzen, AMD's resources are not "relatively limited". For you to state that AMD's resources are limited and that making such a product would be outside the scope of those resources is bashing by implication.

Or it could be the way you're stating things.

Ok, I'll yield on this one. I did reread your posts and still conclude that you seemed to be bashing AMD. If that is not your intent then I apologize.
I think I've identified the source of the misunderstanding, but feel free to correct me if I'm wrong. In post #63, I said
Valantar said:
They probably could, but it would be quite limited in terms of availability, not to mention a PR disaster ("MAD [sic - my phone's autocorrect never seems to accept that I type "AMD" quite often] returning to their space-heater roots" and so on).
I'm guessing you misread the part in quotes as something I was saying - which it wasn't. While that could have been made more obvious, the context and quotation marks really ought to be enough to make it obvious that I was showing an example of the classic AMD-bashing that they would open themselves up to from Intel fans if they were to launch a new AM4 part with a TDP even higher than the 105W of the 2700X. It would be a PR disaster, as it would make it far too easy for both Intel and their fans to bash AMD over their history of inefficient chips - even if Zen is arguably more efficient than CFL. AMD has a branding and mindshare disadvantage, and playing into overblown public perceptions of their previous weaknesses would be too dumb a strategy for me to believe AMD would even consider it. (This, of course, ignores the fact that current Intel offerings consume far more power than their TDP at the frequencies people applaud them for reaching (including their rated boost clocks), something that I've addressed earlier in this thread.)

As for AMD having limited resources: of course they do. Arguing anything else is kind of absurd, really. They've just recently gone from losing money over multiple years to making a profit (an achievement that deserves a lot of praise, but nonetheless hasn't lasted long enough for them to have a lot of cash on hand). In terms of revenue, they're less than 1/10 the size of Intel. They're half the size of Nvidia by the same measure, and Nvidia only competes with them in half their product stack. There is zero question that AMD's R&D and silicon development budgets are far smaller than those of their competitors. What does this mean? That relative to their competition (which is the only reasonable metric), they have limited resources.

This is actually one of the absolutely brilliant things of the base Zen design and the MCM approach: they turned an economic disadvantage into a technological advantage. AMD has also clearly stated that they went for the "one die to rule them all" design approach (plus APUs, of course) for cost reasons - which, given their size and resources was very smart. I'm quite convinced they will add another design in relatively short order (for a product stack of three, not two designs), but not before 7nm is here, and to me it seems most likely for that design to be an 8-core single-CCX (given the 8-core CCXes shown by 64-core EPYC), possibly with an iGPU.

Their current silicon product stack consists of two parts: 4c+GPU and 4c+4c. If the leaks of 64-core Epycs are true, that means an 8c+8c die is incoming. That leaves a significant gap between it and the (inevitable, as more doesn't make sense for ULV mobile) 4c+GPU refresh. 10 cores in silicon would strike a weird balance here - it would require two CCXes (unless you're implying they design yet another CCX, with 10 cores, which would be more expensive), and is a core count that makes sense for low-end harvested dice from the 16-core die. Designing an in-between 8c-single-CCX (either with or without an iGPU, based on the same CCX design as the 8c+8c Zeppelin) die to fill this gap makes a lot more sense. The 8c+8c die seen in current 7nm Epyc leaks would make a single-die 10-core AM4 design quite easy (and I don't really doubt we'll see it once 7nm Ryzen launches), but launching it at this time makes no sense for either marketing or sales reasons, as I've said before. There's more money to be had by selling the same harvested dice as lower-end Epycs.

As for my posts being "bashing": in my understanding of that term, that would require me to be unequivocally and universally critical of AMD at every level; presenting them as if they had few or no redeeming qualities. Which it should be plenty clear from my posts that I haven't done whatsoever. Nor have I even actually criticized AMDs current products or strategies - quite the opposite! What I've said is that this leak, which neither aligns with AMDs public roadmaps, their stated strategies, their publicized silicon development, or their product segmentation strategy, would be a strategically bad move - in particular as any Ryzen 3000-series based off a 16-core Zeppelin would render it obsolete when it launches in 6-8 months.

Let's see:
Valantar said:
TR is excellent for what it's made for, but gaming isn't among that. AMD likes to push the gaming+streaming angle, which is somewhat valid, but with that kind of budget you'd be better off getting a secondary streaming PC anyhow, so that's kind of moot. The 18-core X299 Intel chip doesn't exactly game well either...
Is this bashing?
Valantar said:
I bought a 1600X when it launched, and even if the 2600x is measurably faster across the board, I'm still very happy with mine. The 2700X is a crazy powerful processor
Or this? Just based on these two quotes alone, you should have been entirely able to tell that I haven't been bashing - or even criticizing! - AMD. Again: this has to boil down to reading comprehension. I'm leaning towards you wanting to antagonize me or read what I'm saying in an oppositional light due to the other thread where we've been arguing, but that might be going a bit far. Still, your reading of my posts makes no sense.

lexluthermiester said:
I'm not a fan of company bashing in general unless the company in question has few or no redeeming qualities. In the case of AMD, they currently hold two very important crowns in the X86 CPU market; They have the highest performing single socket CPU crown and they have the best value for money spent crown. In Intel's case, they hold the best gaming performance crown, but not by much and they may loose it. In the last 18ish months AMD has forged ahead and they show no signs of slowing down. This is good for the entire industry as it is forcing Intel to actually compete with someone other than themselves. AMD releasing a 10core CPU not only makes sense from a logistics perspective, but it makes sense from a competition perspective. A 10core offering is good for the market even if the benefit isn't large as it will show everyone that AMD doesn't just have bite, but also ability to sustain.
You're preaching to the choir here, man. This right here is exactly why it makes no sense for AMD to go off-roadmap and spend tens of millions of dollars on a 10-core piece of silicon on 12nm that will inevitably be short-lived and still won't recapture the gaming crown from Intel. To quote myself yet again:
Valantar said:
For the foreseeable future, 8c16t will be plenty for gaming (even 8c8t will likely last for years and years), and we definitely need an increase in per-core performance. [...] But there's not really any reason not to expect that from 7nm Zen2, is there? Given that AMD has a core count advantage, they know they need to work on IPC and clock speed, and they've said there's plenty of low-hanging fruit to improve the former, while the latter should improve with the new node.
I really don't know who it is you're arguing against - it certainly isn't me.


mtcn77 said:
Everyone seems to discount there is money in server chips and Intel has asymmetrically arranged mesh topology, but AMD is not to counter that? Where do you get that from, the parrot magazine?
Fact, Raven Ridge comes with a similar half-CCX variant. One only needs to add it to the 'Summit Ridge', potentially 4+4+


AMD has countered Intel's mesh topology. Their counter is the IF-linked MCM design. It works wonderfully as long as your workload doesn't exceed 8 cores/16 threads per task (which very few workloads even for servers do, and the upcoming 16c/32t Zeppelins will make up for any deficiencies here). AMDs response has a latency disadvantage in some scenarios, but a whole host of advantages that more than make up for this.

What you're effectively saying here is that AMD should ditch their current (known working, performant, efficient, easy to produce) IF-connected MCM approach and spend another on-die IF link on hooking up two measly cores? Why? Those cores would still not have direct access to a memory controller (unless they make this a three-channel design, making it require a non-AM4 platform) or PCIe controller, both of which are attached to the two current CCXes.

As for your half-CCX example, care to share a link? I can't find that image in any AMD/Zen-related WikiChip page that I've looked at. And that's really besides the point: the 2-core image is showing a Raven Ridge chip with two cores disabled after production, such as the Athlon 200GE. AMD hasn't (yet, at least) made available any in-silicon CCX with any more or less the 4 physical cores. Given how small 4 cores will be on 7nm, there's little reason to believe a piece of silicon like that will ever be made.
Posted on Reply
#91
lexluthermiester
Valantar said:
I think I've identified the source of the misunderstanding, but feel free to correct me if I'm wrong.
There were others. Like I said it's all good. You're not being like the standard "fanboy". I still contend it would not take much engineering(which might have been done ahead of time) to link two flawed 6core Ryzens to make a 10core. It's been done and it really wouldn't take much. Did the math on the physical dimensions and two dies would fit, with a bit of room to spare, in an AM4 package.
Posted on Reply
#92
londiste
lexluthermiester said:
I still contend it would not take much engineering(which might have been done ahead of time) to link two flawed 6core Ryzens to make a 10core. It's been done and it really wouldn't take much. Did the math on the physical dimensions and two dies would fit, with a bit of room to spare, in an AM4 package.
As @Valantar mentioned, would vertical dimensions fit in AM4 package?
Adding another core would bring the same latency/NUMA issues Threadripper has (in gaming and other desktop use cases) to desktop. It would basically only be able to compete better than 2700X in workstation applications, maybe not even too well at that. Additional cost, complexity, power management/usage (2 cores, additional IF links) on top of all this.
While it could be done I cannot see how that would be worth the effort.

At the same time Zen 2 is reportedly planned for 2019H1.
Posted on Reply
#93
Slizzo
lexluthermiester said:
There were others. Like I said it's all good. You're not being like the standard "fanboy". I still contend it would not take much engineering(which might have been done ahead of time) to link two flawed 6core Ryzens to make a 10core. It's been done and it really wouldn't take much. Did the math on the physical dimensions and two dies would fit, with a bit of room to spare, in an AM4 package.
As stated before, currently Ryzen requires symmetrical dies, even when pairing them together (otherwise you would have already have core counts not filled out by first gen Threadripper with 12 and 16 core CPUs).

Whether or not your theoretical core count comes to pass who knows? I don't see them breaking up the need for symmetry in the current line of Zen considering their cadence (yearly releases). They don't have a lot of time to course correct on Zen itself with the cash they have on hand (not much), and engineering team they have (small comparative to Intel).
Posted on Reply
#94
Valantar
lexluthermiester said:
There were others. Like I said it's all good. You're not being like the standard "fanboy". I still contend it would not take much engineering(which might have been done ahead of time) to link two flawed 6core Ryzens to make a 10core. It's been done and it really wouldn't take much. Did the math on the physical dimensions and two dies would fit, with a bit of room to spare, in an AM4 package.
To me, even implying that I might be in the same spectrum as an Intel fanboy is downright insulting - I'm quite an ardent AMD supporter, for quite a few reasons. You really wouldn't have to look very far for confirmation on this - as I see it, including this thread (not wanting AMD to make dumb-a**ed decisions and waste R&D money on short-lived one-off products is supporting them, not criticism. I would criticize them if they did what this rumor says, but I don't see it as likely whatsoever). Outside of work-mandated laptops, I haven't bought/owned an Intel-based PC since my ThinkPad X201 back in ... 2010? Something like that. I've never bought an Nvidia GPU either, for that matter (well, I frankly don't remember what GPU was in my first two PCs, but considering I was 10-15 years old (and subsequently dirt poor) I doubt I could afford anything by Nvidia then either, even if it was the early 2000s and I was an idiot. I love both my Fury X and my 1600X).

Anyhow, as @londiste reiterated above, x and y measurements are not the main limitation for adding a second die to AM4. Adding an internal IF link between two dice would necessitate adding layers to the substrate, making it thicker than it is. This would again make the package incompatible with the AM4 spec, meaning that a lot of coolers would no longer fit (particularly the ones with clip-on mounting, though also likely quite a few with short mounting screws). If you doubt this - have you seen a Threadripper CPU in person? If not, let me tell you from experience: the substrate is insanely thick. I took this when I was installing the 1920X in my GF's video editing workstation:

That substrate alone is thicker than an entire mobile CPU package (I googled: CFL-H is 1.49mm, and that substrate is thicker than that), and comes close to some desktop packages. Sure, the TR substrate is designed for EPYC, and thus has room for even more IF links, two extra memory channels and extra PCIe - but it's also around 4x the area of AM4. Less area means more layers for fitting the same number of traces. In other words, fitting a 2-die package with the requisite IF link inside of the restrictions of the AM4 package dimensions would be quite the challenge, if possible at all.
For reference: while not as good a picture, the AM4 package is clearly a lot thinner than the TR4 package.


Then, again, there are issues like NUMA awareness (or the lack of it), latency between the dice, leaving one die without directly connected PCIe (at the very least) and RAM (unless you run one channel off each die, which would bring its own performance issues), and so on and so forth. A package like this would probably be a decent workstation chip (even with two less memory channels than TR it would be a beast for multi-threaded workloads), but it wouldn't make sense as a high-end consumer chip.

Saying this isn't bashing AMD. It's providing sound reasoning why this rumor doesn't ring true in terms of the technology behind AMD's current offerings (and what they have publicized about their future plans). It doesn't align with what they've said, and it would only barely make sense as a product. It definitely wouldn't be a suitable "answer" to the 9700K/9900K for those who need such an answer (Intel fans or people who only play games), as it wouldn't outperform the 2700X in those applications). In short: it makes far more sense for AMD to have a bit of patience, wait until 7nm Zen2 is available in sufficient quantities for a consumer launch (which I'm willing to bet will be around April, as a yearly cadence makes sense), and blow people's minds by how good it is. Zen2 should bring both higher clocks, even better efficiency (I'm really looking forward to 7nm APUs!), and improved IPC. It should be a real triple threat. There's no reason for AMD to rush out some oddball in-between "answer" to Intel's rather desperate attempt at matching AMD's core count advantage before that.
Posted on Reply
#95
mtcn77
Valantar said:
AMD has countered Intel's mesh topology. Their counter is the IF-linked MCM design. It works wonderfully as long as your workload doesn't exceed 8 cores/16 threads per task (which very few workloads even for servers do, and the upcoming 16c/32t Zeppelins will make up for any deficiencies here). AMDs response has a latency disadvantage in some scenarios, but a whole host of advantages that more than make up for this.

What you're effectively saying here is that AMD should ditch their current (known working, performant, efficient, easy to produce) IF-connected MCM approach and spend another on-die IF link on hooking up two measly cores? Why? Those cores would still not have direct access to a memory controller (unless they make this a three-channel design, making it require a non-AM4 platform) or PCIe controller, both of which are attached to the two current CCXes.

As for your half-CCX example, care to share a link? I can't find that image in any AMD/Zen-related WikiChip page that I've looked at. And that's really besides the point: the 2-core image is showing a Raven Ridge chip with two cores disabled after production, such as the Athlon 200GE. AMD hasn't (yet, at least) made available any in-silicon CCX with any more or less the 4 physical cores. Given how small 4 cores will be on 7nm, there's little reason to believe a piece of silicon like that will ever be made.
These bulletpoints cannot be appreciated enough. When Zen v.1 took charge, the first reviews were mixed between that and 5960x, however since then Intel had to resort to bigger dies(10-core entrant to the mainstream) and split the HEDT line altogether because 6950x just didn't live up to hype due to overheating and nasty overclocking instability.

I know about the presence of CCX variants, but that is about it. Nothing solid other than the topology clues. It would be very easy actually, since the chip is an SoC and just adding more CCX islands only insert to the existing 'SoC' layout. The core matrices are asymmetrical anyway, this whole 'symmetrical die' rumour couldn't end soon enough. Infinity Fabric is outside the respective scope.
Posted on Reply
#96
Valantar
mtcn77 said:
These bulletpoints cannot be appreciated enough. When Zen v.1 took charge, the first reviews were mixed between that and 5960x, however since then Intel had to resort to bigger dies(10-core entrant to the mainstream) and split the HEDT line altogether because 6950x just didn't live up to hype due to overheating and nasty overclocking instability.

I know about the presence of CCX variants, but that is about it. Nothing solid other than the topology clues. It would be very easy actually, since the chip is an SoC and just adding more CCX islands only insert to the existing 'SoC' layout. The core matrices are asymmetrical anyway, this whole 'symmetrical die' rumour couldn't end soon enough. Infinity Fabric is outside the respective scope.
You seem to have misunderstood a few fundamentals here:
  • CCXes on the same die are also connected through Infinity Fabric. As such, IF is never beyond the scope of any multi-CCX Zen design.
  • You can't "just add" parts without accounting for I/O, even if it's an SoC. Your reasoning doesn't at all account for how the parts of the SoC actually communicate or work together.
  • The part about Zen requiring symmetrical CCXes is not a rumor - this has been confirmed by AMD in interviews. As for requiring symmetrical dice in MCM setups, I haven't seen that part confirmed, but it makes sense in a system architecture/resource allocation perspective. It might be possible, but making an asymmetrical MCM setup would be far more challenging to implement and balance/tune in terms of cache migration, PCIe, RAM, thread scheduling, and so on. Possibly doable, but impractical.
Now, you say "I know about the presence of CCX variants". What does that mean? Where do you know of this from? Do you know of anything that isn't simply a version with disabled silicon, like <8-core Ryzen or <4-core APUs? If so, from where? I would be very interested in reading further about this, as it would be a very unexpected turn in AMD's strategy. The only variants I've seen are the CCXes with different cache layouts between the CPU and APU CCXes. Do you know this (as in: have evidence) or is it something deduced from looking at core layouts? I don't mean to come off as too critical here, it's just that I have never seen this reported anywhere by anyone, so any new info is very interesting to me.
Posted on Reply
#97
mastrdrver
lexluthermiester said:
There were others. Like I said it's all good. You're not being like the standard "fanboy". I still contend it would not take much engineering(which might have been done ahead of time) to link two flawed 6core Ryzens to make a 10core. It's been done and it really wouldn't take much. Did the math on the physical dimensions and two dies would fit, with a bit of room to spare, in an AM4 package.
Your ability to understand how to make a silicon die is quite the laughter.

If it was really this simple, what are you doing on here? You should be telling AMD how they're leaders are idiots and you should be running the company.
Posted on Reply
#98
lexluthermiester
Valantar said:
To me, even implying that I might be in the same spectrum as an Intel fanboy is downright insulting
No insult was intended.
mastrdrver said:
Your ability to understand how to make a silicon die is quite the laughter.
If it was really this simple, what are you doing on here? You should be telling AMD how they're leaders are idiots and you should be running the company.
Go troll someone else.
Posted on Reply
#99
ypsylon
Just going back to topic a bit. What for are all these cores when CPU provides only paltry 16 PCIe lanes anyway? That's pathetic on a -possible- 10 core chip while TR4 gets 60 on 12. How about something in between AMD?
Posted on Reply
#100
Valantar
ypsylon said:
Just going back to topic a bit. What for are all these cores when CPU provides only paltry 16 PCIe lanes anyway? That's pathetic on a -possible- 10 core chip while TR4 gets 60 on 12. How about something in between AMD?
That would require a new platform, as AM4 is limited to 16+4+4. What they could do is integrate a PCIe 3.0 switch into upcoming chipsets, though. With one SSD connected directly to the CPU, there wouldn't be much chance of bottlenecking the switch. More PCIe for anything outside of SSDs is meaningless for mainstream desktop usage, as multi-GPU gaming is dead and only a few non-prosumers want/need 10GBe. As such, adding 8-12 PCIe 3.0 lanes off the chipset would make this pretty much perfect.
Posted on Reply
Add your own comment