Some Bulldozer and Bobcat articles have sprung up

[JFAMD]

Good point.

I am also wondering *how much* these changes will help AMD's Bulldozer laptop market (from a power efficiency standpoint).

At the moment it seems like that is a weak point for AMD and if Bulldozer delivers on the xtor/power efficiency ratio maybe we will see some additional competition for future Intel dual core processors with SMT.

Bobcat and Llano are better for the notebook market because the integrated GPU helps cut down on power consumption. Battery life is one of the #1 metrics for notebooks as I understand it (but I am a server guy.)

 

[Cogman]

Bobcat and Llano are better for the notebook market because the integrated GPU helps cut down on power consumption. Battery life is one of the #1 metrics for notebooks as I understand it (but I am a server guy.)

I haven't read all your posts, but any news on the chipset that bobcat will get saddled with? Will it have an equally power-efficient chipset?

 

[JFAMD]

I haven't read all your posts, but any news on the chipset that bobcat will get saddled with? Will it have an equally power-efficient chipset?

I have no idea, that is client product. Our chipsets are pretty low power and I would guess that they will be teamed up with an equally low power chipset on the client side.

 

[GaiaHunter]

I have no idea, that is client product. Our chipsets are pretty low power and I would guess that they will be teamed up with an equally low power chipset on the client side.

But we are potential clients... Cant you grab some extra responsibilities?

 

[Cogman]

I have no idea, that is client product. Our chipsets are pretty low power and I would guess that they will be teamed up with an equally low power chipset on the client side.

Well, I'm just wondering since intel pulled the "You can't buy an atom without buying an intel chipset" deal and forced the client to buy their specific atom chipsets. I didn't know if AMD was going to pull the same stunt or if they were going to be more flexible in consumer chipset selection abilities.

 

[cbn]

Bobcat and Llano are better for the notebook market because the integrated GPU helps cut down on power consumption. Battery life is one of the #1 metrics for notebooks as I understand it (but I am a server guy.)

I see your point, this is why I can't wait to see how Bulldozer mobile fusion performs.

 

[bryanW1995]

Incorrect... see my post above, correcting the 5% figure to 50%.
I don't see why people believe in such fairy tales anyway.
HT takes up very little die space because hardly any physical hardware is added. Most of it is just partitioning the existing resources.
AMD adds actual units to it... you really think 4 integer units are only 5% of a die?

sorry, I remembered reading the article (I thought), must have missed the 50% correction.

 

[bryanW1995]

We were discussing the effects on single-threaded performance however.
So I don't see a 'problem'. Try to stay on topic.

And I disagree that a module competes with one physical core... it's about 50% larger... it falls somewhere between 1 and 2 physical cores of a K8/10.

That is not that relevant when discussing single-threaded performance however.



Does this flexibility guarantee a 50% increase in efficiency or more? If not, single-threaded performance will suffer (two ALUs need to do the same work that 3 ALUs used to do).
And as I said, I think 50% increase in efficiency is a pretty tall order.


Since a module houses two cores, that is effectively removing one decoder per core, as I said.
Especially with the decoder, the notion that a module competes with a single core is nonsense. A module NEEDS to decode two threads at a time, because there's two cores inside. Even if a core is just executing the idle thread, it still needs to decode halt instructions every cycle.



Not exactly. Each core used to have three FPU ports, two of which also handled SIMD (128-bit). Now there's two shared by two cores.
Again, this is about single-threaded performance. Hence we compare one logical Bulldozer core's IPC against one logical (and also physical) K10 core IPC.



The 50% figure is a quote from Anand who says it comes directly from AMD (correcting his earlier figure of 5%).
I'll take AMD's information over yours, thank you very much.

if it is 4alu's per module, and we're talking about single threaded performance, why couldn't one core of the module use all 4 alu's? no secret sauce would be needed in this scenario.

Of course I understand your reluctance to trust marketing types, but you are acting like a guy who got burned by 17 girls in a row. They had one shitty launch, and that was several years ago. get over it.

 

[bryanW1995]

I think they were not talking about a die, but about a module.
And a module doesn't include the uncore functionality, such as the L3 cache, which makes a big difference in terms of any die-area related issues.
There will also be multiple modules on a die, to further affect any die-area talks.
For a module, adding a second integer core, the 50% figure seems correct, and also it is meaningful. You show that the Bulldozer architecture significantly reduces die area per core, a very important metric in the current parallel climate.
For a full die, removing an integer core of every module, 5% may be correct, but what does that prove, really? It seems to be a completely random metric.

once again your theory is rebutted, at least this time you didn't outright call him a liar or offer to "bet jfamd's job on it".

 

[bryanW1995]

That is the biggest pain of all of this. Because I actually tell everyone who I am, I don't get to tell people to ^*^*&((*&%#

Being anonymous has its advantages, but creditibility isn't one of them.

john, do you know if you guys are eventually going to offer a desktop version of BD with 16 cores, maybe to compete directly with socket 2011?

 

[Scali]

once again your theory is rebutted, at least this time you didn't outright call him a liar or offer to "bet jfamd's job on it".

I'm betting JFAMD's job only on the claim that single-threaded IPC is going up compared to Phenom II.
I haven't seen that being rebutted yet, as we've not seen any working Bulldozer silicon, let alone any benchmarks.

If I turn out to be right, I have every right to call JFAMD a liar (just like Randy Allen when claiming Barcelona would be 40% faster: http://www.youtube.com/watch?v=G_n3wvsfq4Y), and then I demand that he quits his job, or that AMD fires him, for deliberate false advertisement of AMD's products (which is against the law in most countries).

I also have every right of saying the AMD PR people aren't doing their job well, when Anand and various other sites *repeatedly* misinterpret their information.
I have known Dave Baumann (another AMD-employed LIAR just like Randy Allen) to deliberately refer to misinterpreted information on third-party sites. That's just some of the underhanded tactics that AMD employs. You guys should be attacking AMD, not me. I'm just calling it as I see it.

 

[richierich1212]

Scali, you are hilarious.

 

[Scali]

Scali, you are hilarious.

I'm dead serious actually... and it's a shame that people find the truth to be hilarious. It's an outrage.

 

[DrMrLordX]

You guys should be attacking AMD, not me. I'm just calling it as I see it.

Nobody should be attacking anybody. If you feel like people are attacking you then . . . I don't know what to tell you. But attacking JF and/or AMD seems more than a tad unnecessary, and none of us are in any position to ask that he resign now or in the future.

 

[richierich1212]

I'm dead serious actually... and it's a shame that people find the truth to be hilarious. It's an outrage.

And it's an outrage some of the tactics Intel has used to gain the upperhand in this market. Do we want to act like you and call out an employee or two? No, of course not. Get over it and quit blaming AMD PR guys and John who's really here to help clarify things.

 

[heyheybooboo]

I haven't read all your posts, but any news on the chipset that bobcat will get saddled with? Will it have an equally power-efficient chipset?

Well, I'm just wondering since intel pulled the "You can't buy an atom without buying an intel chipset" deal and forced the client to buy their specific atom chipsets. I didn't know if AMD was going to pull the same stunt or if they were going to be more flexible in consumer chipset selection abilities.

My understanding is the 'Ontario' platform is in the 18w range with a BGA only socket. There have been some articles surrounding this in the last few months.

That said, it would not prevent someone like nV from packaging a chipset and 'rolling their own' with a Bobcat APU.

BUT the issue is the integrated- integrated GPU (did that make sense? - LOL) on Bobcat. What more could nV bring to the table by providing their own graphics power to the platform if AMD uses a cut-down, low-power Radeon 5xxx on the die (with DX11, xxx shaders, combined with TrueHD and DTS-HD, UVD, etc. ...) ?

The additional graphics from nV would drive up the wattage and that defeats the purpose of the low-power platform, right?

And actually, Intel originally bundled Atom with the 845 chipset, but today you may purchase an ION Atom with the nV 9300 (?) chipset. You may be thinking about 'Clarkdale' and Sandy Bridge, but the same issues as noted above with Ontario apply, especially in the mobile space and SFF desktop.




--

 

[Cogman]

My understanding is the 'Ontario' platform is in the 18w range with a BGA only socket. There have been some articles surrounding this in the last few months.

That said, it would not prevent someone like nV from packaging a chipset and 'rolling their own' with a Bobcat APU.

BUT the issue is the integrated- integrated GPU (did that make sense? - LOL) on Bobcat. What more could nV bring to the table by providing their own graphics power to the platform if AMD uses a cut-down, low-power Radeon 5xxx on the die (with DX11, xxx shaders, combined with TrueHD and DTS-HD, UVD, etc. ...) ?

The additional graphics from nV would drive up the wattage and that defeats the purpose of the low-power platform, right?

And actually, Intel originally bundled Atom with the 845 chipset, but today you may purchase an ION Atom with the nV 9300 (?) chipset. You may be thinking about 'Clarkdale' and Sandy Bridge, but the same issues as noted above with Ontario apply, especially in the mobile space and SFF desktop.




--

Well, while nvidia did release a chipset for the atom, it took time, and intel end up suing them for it.

Though I agree with your point, there isn't much beyond an APU that you could really offer. I just like having options is all. More to the point, I like knowing that my chipset isn't consuming as much if not more power than my CPU.

 

[Martimus]

Deleted pointless post, that I posted out of frustration. Sorry for any problems it caused.

 

[Scali]

Do we want to act like you and call out an employee or two?

No, I think we sued the company as a whole, and the results was some fines and settlements.
But that really wasn't the topic here.

Get over it and quit blaming AMD PR guys and John who's really here to help clarify things.

I'm just saying they're doing a poor job. Customer feedback. They should do something with that.

 

[Scali]

I have never seen you write the truth about anything.

Lol, I'm probably the most honest guy on the internet.
I *always* tell the truth about things.

You are hilarious, because unlike in the Video forum, everyone in this forum knows that you don't know what you are talking about; yet you continue posting without realizing that.

Yea right. I know a whole lot more than most of you, being an industry insider.
I am willing to bet I know more than JFAMD as well, because I'm an engineer and he's just a PR guy who gets told what to say by engineers (and sometimes gets confused because he's not very good at his job).
People like jvroig and Idontcare can vouch for this. They are some of the few people who also know what they're talking about, and some of the few people who usually agree with what I say.

 

[Martimus]

The thing that excites me over this new architecture is to find out how well the new branch prediction works. I hope that the more aggressive prefetchers improve performance substantially.

 

[bryanW1995]

Do we want to act like you and call out an employee or two?

No, I think we sued the company as a whole, and the results was some fines and settlements.
But that really wasn't the topic here.

yes, and neither is calling jf a liar. at least rollo had a financial incentive to derail threads.

Get over it and quit blaming AMD PR guys and John who's really here to help clarify things.

I'm just saying they're doing a poor job. Customer feedback. They should do something with that.

amd pr doesn't exactly have the best reputation, as you have so vociferously pointed out during this entire thread. However, I don't see how poor communication with anand during november 2009 has gotten your panties so wadded up. Clearly you favor intel, as I'm certain most people here do. While intel is certainly just as, and probably more, underhanded and sneaky as amd, they have at least managed to avoid nvidia's focus groups and other such truly nasty tricks. Plus, intel currently has such an enormous advantage that under most circumstances they are the clear choice. Typically in this sort of situation people tend to "root for the underdog", or at least not kick the shit out of the underdog while he's down, then break his leg while he's trying to stand up, then run over him once he finally starts walking again. Is bulldozer going to be great? I would bet no because amd's track record hasn't been all that great lately, plus anand and kyle both seem to agree for once that they should take a "wait and see" attitude. However, I'm willing to at least give amd the benefit of the doubt, and hope that something competitive comes out, because if nothing else the competition will push intel to be a bit more aggressive with their pricing. Who knows, maybe you'll even end up getting a BD before all is said and done.

 

[bryanW1995]

Lol, I'm probably the most honest guy on the internet.
I *always* tell the truth about things.



Yea right. I know a whole lot more than most of you, being an industry insider.
I am willing to bet I know more than JFAMD as well, because I'm an engineer and he's just a PR guy who gets told what to say by engineers (and sometimes gets confused because he's not very good at his job).
People like jvroig and Idontcare can vouch for this. They are some of the few people who also know what they're talking about, and some of the few people who usually agree with what I say.

yeah, pretty much all my employees know what they're talking about because they usually agree with me. I know what you mean

if jvroig and idontcare are so knowledgeable, then why aren't they castigating amd the same way you are? Isn't it funny how 2 people with the same information will reach different conclusions and/or take different actions based upon that information? You don't like amd's actions in the past, we get it. Please quit derailing the thread and stay on topic.

 

[Scali]

Clearly you favor intel, as I'm certain most people here do.

There's plenty of other companies you know.
I'm a bit of a hard-core guy myself, so the DEC Alpha has always been high on my list.
Motorola's 68k and PPC were also among my favourites, and I enjoyed dabbling with PA-RISC and Sun's Niagara at universities, to name but a few things.
x86? Nah. Not even Intel's.

Typically

I'm not your typical guy, what can I say?

 

[Cogman]

amd pr doesn't exactly have the best reputation, as you have so vociferously pointed out during this entire thread. However, I don't see how poor communication with anand during november 2009 has gotten your panties so wadded up. Clearly you favor intel, as I'm certain most people here do. While intel is certainly just as, and probably more, underhanded and sneaky as amd, they have at least managed to avoid nvidia's focus groups and other such truly nasty tricks. Plus, intel currently has such an enormous advantage that under most circumstances they are the clear choice. Typically in this sort of situation people tend to "root for the underdog", or at least not kick the shit out of the underdog while he's down, then break his leg while he's trying to stand up, then run over him once he finally starts walking again. Is bulldozer going to be great? I would bet no because amd's track record hasn't been all that great lately, plus anand and kyle both seem to agree for once that they should take a "wait and see" attitude. However, I'm willing to at least give amd the benefit of the doubt, and hope that something competitive comes out, because if nothing else the competition will push intel to be a bit more aggressive with their pricing. Who knows, maybe you'll even end up getting a BD before all is said and done.

One thing I do love about these forums is the fact that most of the posters are pretty unbiased. Back in the days of the A64 and X2's, most people would recommend an AMD system over intel in a heart beat. That changed dramatically when the Core2s were released. All the sudden, AMD was out, and intel was in as the main recommendation.

I think most here really want to see AMD come out with some spectacular processor that completely thrashes all of intel's offerings. We realize that strong competition is good for the consumer. Alas, we also realize that the likelihood of that is slim to none.