Anyone posting a link to very inaccurate should get a 1 week suspension and be publicly flogged. Same goes for the Daily Mail or Sun
-
Competitor rules
Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.
More Fermi bad news
- Thread starter ennogs
- Start date
Anyone posting a link to very inaccurate should get a 1 week suspension and be publicly flogged. Same goes for the Daily Mail or Sun
A quote from the article:
"Why are things this bad? The simple answer is that Nvidia didn't do its homework. Just like the failures that lead to the bad bumps, Nvidia simply didn't do test, instead it tried to brute force things that require nuance and methodical forethought. ATI did test. ATI put out a full production run of HD4770 (RV740 silicon) GPUs and used that as a test of TSMC's 40nm process. TSMC looks to have failed, badly, but crucially, ATI learned why and how the parts failed to yield. That learning was fed back in to the Evergreen 5000 series GPUs, and those come off the line at perfectly acceptable yield rates now."
Sounds like an accurate assessment from a legitamite news source to me. It is never a good sign when a company can not meet their own deadlines. Duke Nukem Forever comes to mind.
"Why are things this bad? The simple answer is that Nvidia didn't do its homework. Just like the failures that lead to the bad bumps, Nvidia simply didn't do test, instead it tried to brute force things that require nuance and methodical forethought. ATI did test. ATI put out a full production run of HD4770 (RV740 silicon) GPUs and used that as a test of TSMC's 40nm process. TSMC looks to have failed, badly, but crucially, ATI learned why and how the parts failed to yield. That learning was fed back in to the Evergreen 5000 series GPUs, and those come off the line at perfectly acceptable yield rates now."
Sounds like an accurate assessment from a legitamite news source to me. It is never a good sign when a company can not meet their own deadlines. Duke Nukem Forever comes to mind.
Last edited:
Associate
- Joined
- 28 Jan 2009
- Posts
- 581
Didnt someone say that the video on the nvidia site which was supposed to be rendered by fermi was rendered by something completely different ?
Associate
- Joined
- 10 Nov 2009
- Posts
- 1,099
- Location
- London
Maybe you could present a counter argument outlining why you think the information is inaccurrate? or at least pointing to instances where the source has been wrong previously?
Or is it just because you don't want ot hear it? If that's the case then I'd advise not opening any threads with 'Fermi' in the title, because the way things have been going it's most likely going to be bad news.
Charlie isn't objective about Nvidia due to a historic spat, whilst his articles may be truthful in part they are also hysterical in part against Nvidia.
Associate
- Joined
- 11 Oct 2007
- Posts
- 1,287
Lately he has been correct, biased against or not. That's what matters.
Until proven otherwise my feeling is that Fermi will end up disappointing loads of people. And that's disappointing really because the market needs competition... even though at the moment AMD needs as much cash as they can to compete with Intel in the CPU space.
Associate
- Joined
- 15 Jun 2007
- Posts
- 1,201
- Location
- Liverpool
Charlie is kinda like the ATI fanboy god and is worshiped as such. While there may be a smattering of facts in the essay-long rants you must take anything he says with a lorry-load of gritting salt (If you can find any).
Couldn't agree more.
Unfortunately he has been right about most things Fermi. Quote from last july- "In the end, there won't be any GT300s this year, and early next year is really iffy. Press stunts aside, it is vaporware for 2009, but it has, finally taped out."
If only half of that article is correct then Fermi is Nvidia's 2900XT.
If only half of that article is correct then Fermi is Nvidia's 2900XT.
Soldato
- Joined
- 25 Sep 2009
- Posts
- 10,244
- Location
- Billericay, UK
And the big difference here is at least the 2900XT was apart of strategy shift to target the sweet spot between performance and value for money, I can't see see how Fermi is going to be anything close to good value for money given what it costs make.
Also doesn't look like Nvidia will be selling many other last gen GPU's.
Maybe some last last last gen GPU based products.
^^^
This guy should NEVER get into a position of power. Wishing ill on his fellow forum members simply for posting info from a site he doesn't 'like'.
If any one needs flogging, it's you mate!
Soldato
- Joined
- 22 Nov 2007
- Posts
- 3,763
- Location
- Ayr, Scotland
Read the whole article and if true, and it all sounds perfectly reasonable, this is a disaster, not only for Nvidia, but for us consumers, as Amd will have no competition and therefore no reason to drop prices. Arghhhhhhh........
Man of Honour
- Joined
- 21 Nov 2004
- Posts
- 47,243
Fermi STILL isn't out? Any updated (accurate) news? Glad I moved from Nvidia when I did.
Having read that article, I think that he more than likely raised at least some issues that are true.
If you take into account both his and Anandtech's recent article, nVidia has always been reluctant to transition on to a new fab process, hanging on to tried and tested methods for longer and letting ATi do all the leg work. It seems though that where ATi has been through the pain of transitioning to 40nm and has learnt from the experience, nVidia simply wasn't ready and the new architecture chip is proving a real headache to produce.
Whereas Charlie noted in his article that at least Intel held up their hands and said "it ain't working guys" with Larabee, graphics isn't Intel's core competency; they could afford to write it off. How do you reckon nVidia investors would feel if nVidia did the same and 'fessed up that it really wasn't going to work for this generation after all the time and money invested.
Regardless of whether you like/believe Charlie, there's simply no escaping the fact that nVidia is so late to market with Fermi that AMD/ATi now have products that cover practically every single price point possible, not just the performance parts.
Ultimately, what nVidia will have gained is valuable technology/IP in the Fermi architecture, which they'll put to good use in future products, but is just incapable of implementing effectively this time round due to their own/TSMC problems.
If you take into account both his and Anandtech's recent article, nVidia has always been reluctant to transition on to a new fab process, hanging on to tried and tested methods for longer and letting ATi do all the leg work. It seems though that where ATi has been through the pain of transitioning to 40nm and has learnt from the experience, nVidia simply wasn't ready and the new architecture chip is proving a real headache to produce.
Whereas Charlie noted in his article that at least Intel held up their hands and said "it ain't working guys" with Larabee, graphics isn't Intel's core competency; they could afford to write it off. How do you reckon nVidia investors would feel if nVidia did the same and 'fessed up that it really wasn't going to work for this generation after all the time and money invested.
Regardless of whether you like/believe Charlie, there's simply no escaping the fact that nVidia is so late to market with Fermi that AMD/ATi now have products that cover practically every single price point possible, not just the performance parts.
Ultimately, what nVidia will have gained is valuable technology/IP in the Fermi architecture, which they'll put to good use in future products, but is just incapable of implementing effectively this time round due to their own/TSMC problems.
He's been right on this particular subject for nearly 10 months now. Your argument is getting more and more stale by the day.
Maybe, but it seems ati have squeezed out Nvidia's profit, so Nvidia has cut back on RnD to save money which creates a viscous cycle that's hard to get out of.
Nvidia will need to improve it's performance on allot smaller budget.
I doubt they will do it, it reminds me a little of what Intel did to AMD except the Anti-Trust part