Is Intel pulling a Fermi?

[JAYDEEJOHN]

We all saw earlier nVidia showing a card that wasnt there, even have pictures of its CEO holding up a fake.
Earlier this week, Intel showed off what some believed to be LRB. Some even wrote about it as such
http://www.theregister.co.uk/2009/11/17/sc09_rattner_keynote/
While others took the time to see the others pulling a "mistake"
http://www.computerworld.com/s/article/9140949/Intel_to_unveil_energy_efficient_many_core_research_chip?taxonomyId=1
Its not hard to see someone was pulling something or other

 

[jennyh]

Nice attempt at deflecting the discussion to long past technology

But...no we're discussing Larrabee here, or more accurately, the complete lack of Larrabee.

 

[JAYDEEJOHN]

Gee, and all I can say is, Ive got 1.25 billion reasons why, nuff said
Anyways, if trhis is a straight translation of LRB, then these tests can apply, which gives a a framework of capability without approach, or possibly both.
Itll be interesting, and the hints are thick, as Intel said theyre closer than they thought, and it wont be as big as 80 cores, hint hint

 

[jennyh]

http://arstechnica.com/hardware/news/2008/01/larrabee-becomes-laterbee.ars

Larabee first silicon should be late this year in terms of samples and we'll start playing with it and sampling it to developers," said Otellini. "I still think we are on track for a product in late 2009, 2010 timeframe.

 

[fazers_on_stun]

Nice attempt at deflecting the discussion to long past technology

But...no we're discussing Larrabee here, or more accurately, the complete lack of Larrabee.

LOL - neither has Bulldozer, but that hasn't stopped you from silly comments like "Intel fanboys are very worried" or "Bulldozer will reclaim the crown" or some such .

Besides, I was just showing Intel is, in fact, copying AMD here by flogging unreleased products . Hopefully Intel won't copy AMD verbatim and release Larrabee as a total dog

 

[BadTrip]

http://arstechnica.com/hardware/news/2008/01/larrabee-becomes-laterbee.ars

Larabee first silicon should be late this year in terms of samples and we'll start playing with it and sampling it to developers," said Otellini. "I still think we are on track for a product in late 2009, 2010 timeframe.

Last I checked it is still late 2009. Sounds like he still has over a quarter time frame left.

 

[fazers_on_stun]

http://arstechnica.com/hardware/news/2008/01/larrabee-becomes-laterbee.ars

Larabee first silicon should be late this year in terms of samples and we'll start playing with it and sampling it to developers," said Otellini. "I still think we are on track for a product in late 2009, 2010 timeframe.

Hmm, I just checked my calendar and guess what - it ain't 2010 yet .

Face it - AMD won't have anything new for the next 12+ months except 2 extra cores and a speed bump on a 45nm CPU. Big yawner there. Intel will be at 32nm, achieved "fusion" first, and have the next-gen architecture Sandy Bridge out next year. As well as Larrabee.

 

[JAYDEEJOHN]

Either Intel is afraid to tip its hat, or, its aways off yet.
Usually, the hype machine starts aways ahead of release.
The gaing aspect wont be coming anytime soon. Its been said the gpgpu use would be shown and done first.
It fits here.
I think Intels pulling a Fermi, as yes, the first "showing" wasnt anything anyone could get their hands on, say, unlike the 5xxxseries showing.
But its loike a picture on facebook.
I remember all the crap Barcy got from a no hands on approach during first showings, and yes, the number werent typical then, whos to say different now?
If they had more, wed see more.

 

[ElMoIsEviL]

Either Intel is afraid to tip its hat, or, its aways off yet.
Usually, the hype machine starts aways ahead of release.
The gaing aspect wont be coming anytime soon. Its been said the gpgpu use would be shown and done first.
It fits here.
I think Intels pulling a Fermi, as yes, the first "showing" wasnt anything anyone could get their hands on, say, unlike the 5xxxseries showing.
But its loike a picture on facebook.
I remember all the crap Barcy got from a no hands on approach during first showings, and yes, the number werent typical then, whos to say different now?
If they had more, wed see more.

To pull a Fermi would require Otellini to hold up a badly assembled Lego model and exclaim.. "This is Larrabee". Intel seem to be making good progress on Larrabee in my opinion. To come out of the blue with a single product and try and tackle the big boys who have been at it for decades is no easy task. Last time around, Intel bought a GPU maker and released their product (i740 or something like that) now they're actually working on a product that is entirely theirs.

Even if it doesn't beat Fermi or RV870, if it get's somewhat close.. give it two to three generations and it will compete handsomely.

 

[jennyh]

We aren't even seeing numbers from intel, that's the thing. Maybe they realised like Nvidia, that making chips this big is '****ing hard' lol.

ATI must be laughing their backside off at the pair of them.

 

[jennyh]

Even if it doesn't beat Fermi or RV870, if it get's somewhat close.. give it two to three generations and it will compete handsomely.

Same old argument.

If larrabee comes in behind, there is no reason to believe it will ever get ahead. Do you see intel igp's catching up on the big two in graphics?

 

[ElMoIsEviL]

Same old argument.

If larrabee comes in behind, there is no reason to believe it will ever get ahead. Do you see intel igp's catching up on the big two in graphics?

Intel's IGP aren't getting the level of resources (investment in R&D) and aren't aiming to compete. They're aiming to simply offer basic functionality for a limited cost (cost to Intel and cost to customers/OEMs).

That it's not an old argument. It is how things have always played out.

Here's some history.

- 3Dfx releases the Voodoo Graphics card
- nVIDIA release the Riva 128

Riva 128 doesn't win but it offers up some level of competition. nVIDIA then release the Riva TNT which bests the Voodoo. 3Dfx reply with the Voodoo2 which bests the Riva TNT (and has capabilities for SLI).

nVIDIA respond with the TNT2 to which 3Dfx responds with the Voodoo3. nVIDIA is catching up. Their card may not be as fast but it can do 32-bit rendering whereas the Voodoo3 is stuck at 16-bit.

nVIDIA then releases the GeForce256, 3Dfx has nothing to offer yet...
nVIDIA releases the Geforce2 and 3Dfx responds with the Voodoo5 5500. GeForce 2 wins.

3Dfx goes belly up.

You claim what I am saying as being the "same old argument" but I am basing it on historical knowledge (precedence). You simply despise Intel with a passion and wish them failure in anything they do (blind hatred). And this blind faith you have is blinding you from what most of us see as rather obvious.

 

[jennyh]

Rather obvious being...Larrabee is imminent and going to be worth the $bn's spent?

Lol please...

If you are no good at doing something, trying hard isn't going to make enough of a difference vs somebody who is naturally good at it.

 

[ElMoIsEviL]

Rather obvious being...Larrabee is imminent and going to be worth the $bn's spent?

Lol please...

If you are no good at doing something, trying hard isn't going to make enough of a difference vs somebody who is naturally good at it.

I think that, given the roll Intel is on and with Otellini in charge, Larrabee will be a success. I don't see it being a failure. I don't see what would lead you to think otherwise.

And as for claiming that Intel are "no good at doing something" I have to ask based on what? Their IGPs? Their IGPs weren't meant to be competitive with discrete solutions from other competitors (as I explained in my previous post).

I don't see any evidence to sustain your assertion that Larrabee is an imminent failure. Is it possible? Yes of course but the question you have to ask yourself is "Given Intel's current trend, is it plausible that Intel will release a product meant for failure?"... I think the answer is rather obvious... but I want to know what you think.

 

[JAYDEEJOHN]

But Intels response has been "Itll perform against highend gpus"
Its the bees knees for programming and can do anything, even power arrangement. etc
This is not a easy approach, but a "watch out, here comes LRB!!!" type of hype.
Lets see them do as well as the 5970, which should double those numbers you put up, which they cant.
Lets see them have working drivers for every 16-32-64 bit game ever made, and beating and competing with other gpus on the highend.
And, as far as FC2 goes, no one wins there, as the cpus of today are bottelnecking that game at 25x16, and no, its not an old game.
The use of x86 is being held high as a banner, yet they dont go on about the LRB language, and barely mention the c++ additions, and like these are to be easy as well.
It all sounds good, and from what weve actually seen?
You tell me, what have we actually seen?
Yes, its a Fermi

 

[ElMoIsEviL]

But Intels response has been "Itll perform against highend gpus"
Its the bees knees for programming and can do anything, even power arrangement. etc
This is not a easy approach, but a "watch out, here comes LRB!!!" type of hype.
Lets see them do as well as the 5970, which should double those numbers you put up, which they cant.
Lets see them have working drivers for every 16-32-64 bit game ever made, and beating and competing with other gpus on the highend.
And, as far as FC2 goes, no one wins there, as the cpus of today are bottelnecking that game at 25x16, and no, its not an old game.
The use of x86 is being held high as a banner, yet they dont go on about the LRB language, and barely mention the c++ additions, and like these are to be easy as well.
It all sounds good, and from what weve actually seen?
You tell me, what have we actually seen?
Yes, its a Fermi

The fact that it is based on the x86 architecture won't affect it's gaming performance but rather it's GPGPU performance. It can execute the entire C++ Library (where as Fermi and RV870 cannot). Fermi and RV870 both rely on a host processor to feed them data whereas Larrabee can fetch it's own data (MIMD). So you can program directly for Larrabee and not have to play around with workarounds for routines that are not compatible with RV870/Fermi. It is an advantage for Larrabee for sure.

Have we seen it? Umm no.. but I hadn't seen RV870 until a month or two before it was released either.

The difference with Fermi is that nVIDIAs CEO held up a fake card and claimed it was Fermi. So you can't call Larrabee a Fermi.

 

[jennyh]

I think that, given the roll Intel is on and with Otellini in charge, Larrabee will be a success. I don't see it being a failure. I don't see what would lead you to think otherwise.

Interesting pov you have there elmo. Completely whacked in terms of reality, but interesting none the less.

I can say that given the roll intel is on...legally and with Otellini in charge, they won't have enough money left to pay for R&D if it continues.

I don't see any evidence to sustain your assertion that Larrabee is an imminent failure. Is it possible? Yes of course but the question you have to ask yourself is "Given Intel's current trend, is it plausible that Intel will release a product meant for failure?"... I think the answer is rather obvious... but I want to know what you think.

You're right without realising it. Intel won't release a product meant for failure and that is why Larrabee is months behind schedule already.

 

[JAYDEEJOHN]

Ahh, but the similarities Im not ignoring either.
No ones seen it. Its been hyped.
Its been "shown" hint hint
And always close to another gpu release. hint hint
Yes, the only difference is, Otelini hasnt held up a fake yet, otherwise, its the same, like when will it be here?
Weve been hearing about it.
Weve been toldabout it.
Ive see DrWho bragging it up
Ive seen his poor arguments about the gpgpu usage and the x86 usage.
Ive also seen whats possible in Fermi too.
Its notthe norm with ECC tacked on.
L1 L2 cache, ECC, widening etc etc
But that gets no play? Or hasnt anyone taken the time?
David Kanter has stopped, as hes heard enough for him to sit and wait too.
New approaches, one familiar, the other saying the language is familiar.
One HW we know, works great. One HW, we havnt a clue but talk.
It all comes down to approaches, and since Fermi will fail bigtime if its only good at gpgpu, so too may LRB, if its no good at gaming

 

[jennyh]

I said it before and I believe it. Intel and Nvidia psyched each other out over this. Neither has a product worth bringing out for the simple reason that neither of them can compete with ATI.

That's why ATI graphics are running the #5 supercomputer and not nvidia or intel graphics. Both of them are chasing a rainbow.

 

[ElMoIsEviL]

I said it before and I believe it. Intel and Nvidia psyched each other out over this. Neither has a product worth bringing out for the simple reason that neither of them can compete with ATI.

That's why ATI graphics are running the #5 supercomputer and not nvidia or intel graphics. Both of them are chasing a rainbow.

That's an AMDZone argument if I ever saw one (in fact we were making fun of such arguments earlier at X C P U S).

Bringing a Super Computer into this argument is irrelevant. Larrabee is an unreleased product so thinking that something that is unreleased should already be running a super computer is ridiculous.

The level of bias you're under is very strong. You are asking more of Intel then you are of AMD or nVIDIA.

It's like Intel must jump through hoops to convince you when you feel comfortable taking AMD at their word.

This argument is over. I'll let the THG readers decide who won.

 

[BadTrip]

You and JDJ are just grasping at straws. Neither of you have one shred of evidence on the failure of LRB. AMD should pay you two for all the propaganda.

 

[jennyh]

That's an AMDZone argument if I ever saw one (in fact we were making fun of such arguments earlier at X C P U S).

Bringing a Super Computer into this argument is irrelevant. Larrabee is an unreleased product so thinking that something that is unreleased should already be running a super computer is ridiculous.

Yes Larrabee is unreleased...and not imminent. That is the point of the thread lol?

The level of bias you're under is very strong. You are asking more of Intel then you are of AMD or nVIDIA.

That's interesting. You are the one suggesting that intel have so much money that they can hardly fail. I didn't put any expectation on intel, you did.

It's like Intel must jump through hoops to convince you when you feel comfortable taking AMD at their word.

This argument is over. I'll let the THG readers decide who won.

Won? Argument? Lol, this was never an argument elmo so I don't see how anyone can win.

 

[jennyh]

You and JDJ are just grasping at straws. Neither of you have one shred of evidence on the failure of LRB. AMD should pay you two for all the propaganda.

That is true, we don't have any evidence. But that is also the point. There is no evidence proving otherwise either.

Larrabee Q4 2009 'gauranteed'. Ottellini said so, nearly.

Where is it? We've been seeing Clarkdale benches for *months* now but we haven't seen a single thing about Larrabee. Where is it?

 

[dasickninja]

You're right without realising it. Intel won't release a product meant for failure and that is why Larrabee is months behind schedule already

And you have proof of this from where?...

 

[jennyh]

You should look at what Otellini is saying.

"Larabee first silicon should be late this year in terms of samples and we'll start playing with it and sampling it to developers," said Otellini. "I still think we are on track for a product in late 2009, 2010 timeframe."

If Larrabee exists in the wild? It must be under the best kept nda yet because nobody has the slightest inkling that it is doing the rounds in samples.

Nothing. Nothing at all is what the Larrabee news equates to. You can bury your head in the sand if you like, but in the tech sector, no news = no product.

 

[JAYDEEJOHN]

Hey ninja, LTNS.
If the ROI isnt there, it just isnt there, Intel has lasting power, but so does nVidia in this scenario,
If neither does well in gaming, the ROI simply wont be there.
They could both fail, if this market never takes off.
That being said, its better that both are arriving to this, so the market to be will have options, and possibly shake enough interest for growth within it.
AMD on the other hand can well afford to wait, and just profit from the market, if they too can eventually create something, tho, as jennyh pointed out, AMD does have a few things already in the overall market.
But, to sustain a slow market, gfx usage is primary for ROI, until the market takes hold