:rofl: Warboy
LiquidReactor you a AMD fanboy much?
Printable View
:rofl: Warboy
LiquidReactor you a AMD fanboy much?
http://www.youtube.com/watch?v=ELKdy...layer_embedded
HPCwire video from Nvidia booth at SC09. There are shots of fermi.
http://www.youtube.com/watch?v=x8Ipm...eature=channel
More shots of Fermi Tesla at 17. The shot at 19sec is the older tesla card. I am starting to think they did not have a Fermi Tesla running in any machine.
Nice on Warboy :)
Because daring to criticize the government is being unpatriotic and sympathetic to terrorism...right?!?Quote:
Originally Posted by clo007
If nVIDIA is guilty so is AMD/ATi ( I don't remember ATi saying "The R600 sucks, the 8800GTX rulezzz ) [ I do remember "the r600 kicks ass" though :D ]Quote:
Originally Posted by LiquidReactor
Every manufacturer claims that his product is superior, with higher performance and quality, innovations and blah blah, lies to the consumers every now and then, yet again all I see is nVIDIA & Intel bashing...
With all due respect there is a difference between out right bashing and slander and just plain hard ball questions / doubts.Quote:
Originally Posted by BenchZowner
Am I outright bashing Nvidia? No.
Just wondering what's going on and posting my opinion on the matter which you are welcome to completely disregard since you appear to know a lot more then me on the subject.
:ROTF:Quote:
Originally Posted by BenchZowner
Quote:
Originally Posted by BenchZowner
:p:Quote:
Originally Posted by Walter Bishop
On a serious note i wish Nvidia would get these out already. The GPU market is in need of some competition to drive prices down. All 5-series cards are overpriced if you take into account what 4-series cards cost 6 months ago.
They can't, if they did Fermi's would cost $1000's a piece and there would be maybe one or two per retailer.Quote:
Originally Posted by BrowncoatGR
not really, you get more performance, displayport, lower idle power and eyefinity which makes up for the extra $ you pay themQuote:
All 5-series cards are overpriced if you take into account what 4-series cards cost 6 months ago
Less performance you mean. 5770 is slower than a 4870 but also more expensive. Just about the only useful feature to me from those you mentioned is lower idle power consumptionQuote:
Originally Posted by Helloworld_98
nope, more performance, the 5770 is on it's second generation of consumer drivers, give it some time to catch up, the 4870 must be on at least its 10th set of drivers and they've had a year to be worked on.Quote:
Originally Posted by BrowncoatGR
5770 is never going to overcome its bandwith handicap with driver fixes...some games just really love the bandwidth and 5770 is going to get trashed by 4870/4890 regardless of newer/better driver fixes.Quote:
Originally Posted by Helloworld_98
It doesn't make any sense to compare prices on new product with a product which is EOL and about 17 months on the market.Quote:
Originally Posted by BrowncoatGR
The HD 4870 with only 512MB GDDR5 was introduced at $299 US and that was great price compared to NVIDIA products at that time.
The MSRP for the HD 5770 is $159 US, great deal if the performance is anywhere close to HD 4870.
even if it's bs, then how can you blame nvidia for it?Quote:
Originally Posted by FischOderAal
what did NVIDIA say? soooome person posted sooome picture on facebook... :D
hahaha nice1 :DQuote:
Originally Posted by Aerwidh
hahaha yeah, isn't that funny :DQuote:
Originally Posted by zalbard
I think the joke is on us all. We've all been feeding Nvidia with these monster threads from 1 pic :rofl:
Oops....
http://hardocp.com/news/2009/11/23/m...mi_rumors_good
http://www.driverheaven.net/news.php...#ixzz0Xhun3tPA
Ok, guys now you've got till April to save those pennies.Quote:
We heard word a short while ago from our contacts in the Far East that Fermi may very well be delayed even longer than the initial launch estimate in January. We reported last week that the goal for nVidia was to launch the product on some level at CES with reviewer kits to go out shortly afterwards. Our sources tell us today that the Fermi Build Kits were meant to go to AIBs last week but nVidia has missed this time frame. They also told us that "Gemini" is meant to be the code name for the new dual GPU Fermi card although nVidia are not confirming this.
Going on this and other inside information passed to us at the weekend it appears that the initial launch date in January may very well be pushed back until March or possibly even early April. Giving solid dates for the launch is going to be hard as nVidia seem to be running into more issues every week.
^ Lets hope a miracle happens and that doesn't come true!
we've known it would be March at the absolute earliest for a few weeks now, it's only news that journalists have posted article's on it.Quote:
Originally Posted by trinibwoy
Here is the correct link for the [H]ard|OCP news.Quote:
Originally Posted by trinibwoy
Kyle was already speculating about the Fermi In Q1/Q2 in the forum, 10-02-2009 post.
I already saved all the pennies for the HD 5970, hope the Fermi is not going to be on store shelf first.:)
Rys throws down with some serious speculation (supposedly seasoned with a little insider info).
http://techreport.com/articles.x/17815/1
It's a bit long but a good read and sums up a lot of the speculation so far plus a few new tidbits.
http://img517.imageshack.us/img517/9...peculation.png
yay for breaking 200GB/s finally, should have happened a while ago.
Since they made the comparison at the end between Fermi and the 5870, beating the 5870 (which i can agree with), i cannot understand why they didn't say that it will probably have lower performance than the 5970.
Isnt ati having the next generation out soon?
and can fermi do 1ghz?
If it cant, why get it?
I rather have a 1ghz card than a 650mhz one.
What would be the point of that. They could then say the dual-Fermi card will be faster than 5970 etc, etc.Quote:
Originally Posted by Florinmocanu
dual Fermi was not officially announced, not even rumoured, while the 5970 is already on the market and it will probably be the direct competitor to Fermi in it's price area. So a fair comparison should include the 5970 as well, even if it is a dual gpu.
In the same way, people compared the 5870 with GTX 295, so Fermi vs 5970 is a valid comparison as well.
at 200-220W as the real TDP for Fermi, we can all kind of agree it is unrealistic to have a fully fledged Fermi X2 in the works. Probably at a 32-28nm shrink.
4200mhz = 201.6gb/s = 256bitQuote:
Originally Posted by trinibwoy
4200mhz = 302.4gb/s = 384bit
No, optimistic rumors put it around sept-nov 2010. (Note I said optimistic, IMO it will be later than that)Quote:
Originally Posted by flopper
Fair enough.Quote:
Originally Posted by Florinmocanu
Although, I would always prefer the single gpu card over the double gpu. (If performance is somewhat similar).
Hmm... no?!Quote:
Originally Posted by NapalmV5
384BIT / 8 * 4200 = 201600
256BIT / 8 * 4200 = 134400
Too much Vodka ? :p:
Not according to Fudzilla :rolleyes:Quote:
Originally Posted by Helloworld_98
Quote:
Fermi expected in January
Written by Fuad Abazovic
Tuesday, 24 November 2009 10:04
In retail & e-tail
Multiple sources now claim that Nvidia has promised to ship Fermi in January 2010. We are talking about GF100 Fermi, the GPU that is expected to defeat ATIs Radeon HD 5000-series offerings. To make matters more clear, January is the time when you can hope to buy a high-end Geforce desktop graphics card based on Fermi.
Nvidia Fermi-based cards in the enthusiast market have been pushed from a late November launch to a January launch mainly due the fact that the A2 silicon chip revision was not good enough for volume production, so A3 is about to ship to partners soon. With this in mind and if all goes well, Geforce graphics cards based on Fermi architecture are expected to ship in January.
We have also heard that the launch won't take place at CES 2010, which starts on January 7th and ends of January 10th. Instead, Nvidia might launch it later at some point, but nevertheless still sometime during the month.
that table loses its credibility in the first box of data, nvidia has already confirmed 3.1 billion transistors, that table is 100 million off.
:toast2: hey!! why u messs wid my fun mann?!? :toast2: just trying to scare ati dudes :rofl: :toast2: why u messsin wig my calkulasions man?!? :toast2: was enjoin dat 300gb/s @ 5 inda mornin.. that thing better oc to 5000mhz ;) :toast2: 240gb/s huh?!? :toast: yeh.. alright good nite everyone! :coffee:Quote:
Originally Posted by BenchZowner
Hehe, I'm a downer, sorry :p:
Well not only should it be included but it should be the primary competitor to Fermi. If after all this hype GF100 doesn't get 70%+ of Hemlock's performance it'll be a wash.Quote:
Originally Posted by Florinmocanu
Who knows for sure? Especially as ATI/AMD said RV870 will be the last GPU based on R600. Maybe they will be just as "late" as NVIDIA's Fermi ;)Quote:
Originally Posted by flopper
woo woo, Lets start up the rumor mill. Because we're making some theorybread tonight!:rolleyes::rolleyes:Quote:
Originally Posted by FischOderAal
Those clocks seem a little high, particular the shaders.Quote:
Originally Posted by trinibwoy
If they are true those, I have no doubt it will be competitive with the 5970.
I doubt it will be competitive with the 5970, those specs would put it at about GTX 295 performance on release unless they're still having performance issues.Quote:
Originally Posted by tajoh111
Thats assuming its the same core. Its a totally new core. This leads me to believe its a fair bit faster than gtx295. Unless the core itself is a total flop... just raw performance this thing should come close to a gtx295 and couple that with the fact that its a new core... Unless the core is worse which is highly unlikely... its unlikely for it to have similar performance to the gtx295 imoQuote:
Originally Posted by Helloworld_98
Worst case scenario is an Asus Mars performance ( only worst case is being worse clock per clock than the G200, which is kinda impossible :D ).Quote:
Originally Posted by orangekiwii
why its worst case lol nvidia probaly will jump with hapiness if they can achive that. ati couldn't do that with 5870 and fermi specs aren't that different frm double gtx 285Quote:
Originally Posted by BenchZowner
new architecture?
g80 specs weren't SO far different from g70... and yet it performed way better... why? because of architecture
5870 from 4870 is just a hardware increase with minor core tweaks
gf100 from gtx280 is a LARGER hardware increase AND a new architecture... its foolish to think gf100 is going to fail... it might not be godlike but to think Nvidia has no idea what they're doing is just plain ignorant
No were you can read official change of architecture. :rofl:Quote:
Originally Posted by orangekiwii
At any rate Nvidia squeezes more work per core than ATI and they more than doubled their core count so the potential is there even without new core tweaks along with the 384bit memory controller for bandwidth.
and its stupid to think its not a new architecture
how long has it been since g80? 3 years? at least? 3 years without any major architectural changes... do you REALLY think they sat on their asses doing NOTHING this entire time... just because they seem stupid doesn't mean they are... and they clearly aren't no business is that stupid and second if they are they would go bankrupt in a matter of years and nvidia is FAR from going bankrupt
Single GPU with 512 "SPs" is different ( efficiency-wise ) than a dual 256 "SPs" GPU solutionQuote:
Originally Posted by eric66
More TMUs/TFUs/ROPs
Way higher tris/clock
Architectural changes
Enhanced memory controller
refined "SPs"
...
Guys I know this has been a long wait, but we are really starting to digress here. There is no doubt that Fermi is new architecture. That is not something your imaginary Nvidia fanboy demons are lying to you about. We have the freaking white paper, the architecture is different.
Comments on new architecture aside, 5870 doubled the transistor count, but we got less than that backQuote:
Originally Posted by orangekiwii
Its unlikely to be slower, but it could be a flop, and we could not see the returns we expect when judging it by its components
I personally have a bad feeling about fermi, but until the 2gb 5870's come out, I'm just waiting and watching. We'll see how close fermi is to release when those 2gb'ers get here, and then I'll decide if I wait for nvidia or not.
well 4870x2 prooved that wrong dual 800 shaders performed better plus Rop are lower than dual gtx 285 according to that report and we also don't know anything about tmus so there is big possibility for it to perform on par with dual gtx 285s or worse. and just because its new arch doesn't mean it will be something phenomenal nv 30 and r600 were new archs too lol there is big chance for failure cause nvidia tries to acomplish too much thing with same gpu .....Quote:
Originally Posted by BenchZowner
It is a REVISED, new mArch, yes, but will it be THAT GOOD efficiencywise for gaming purpose compared to its older brother mArch? who knows ? All that we have is speculation, and both perspectives, optimist and pessimist one, have their own merits.
now correct me if im wrong..but its only double the SP's but nothing else is double correct? as far as TMU's/TFU's/ROP's?..
The shader differences is huge. At 1700, those shaders are more than 33% faster, with the extra addition in shader power, that should mean 40% more performance than a gtx 295. That should make it competitive with the 5970. If it's 10 percent slower than this figure, it is still competitive with the 5970.Quote:
Originally Posted by Helloworld_98
I expect more linear scaling from NV architecture, because it is a new architecture and I don't think NV would fool around when r7xx caught them off guard.
1700mhz is pretty fast for shaders those, I am not sure NV clocked it that fast.
Here you goQuote:
Originally Posted by madcho
Offical
http://www.hardocp.com/article/2009/...re_white_paper
page 4. "The Fermi architecture is the most significant leap forward in GPU architecture since the original G80."
Now remove the hype from this statement and basically it means new architecture at the least.
And a great article
http://www.anandtech.com/video/showdoc.aspx?i=3651
The problem with new architecture is that drivers take time to really take advantage (cue. 8800 series). Also the R600 and to a lesser extent the G200b (esp. the 280 GTX) prove that what looks good on paper doesn't guarantee incredible performance.
I've said it a million times. whether it's Ati (and i love their new cards and direction) or Nividia. The current gen and next gen will continue to improve gaming performance (from 150 fps today to 200 fps+ for most games). The real test will be DX11. Until then Nvidia (Dynamic Ambient Occlusion) and Ati (eyeinfinity) are inventing new ways to make your card crawl. Sadly this is because no game actually pushes these powerful cards at all.
I guess we'll just have to wait and see then...Quote:
Originally Posted by eric66
I'm pretty certain that's a rebadged GT2xx.
Fermi! , it's here!
Very efficient too.. 1 phase power and no power connector!
hmmm. the GT310 is early according to charlies roadmap :yepp:
http://www.semiaccurate.com/static/u...on_roadmap.jpg
New architecture doesn't necessarily mean that the 3D performance will be better.
For me, it looks like the changes in architecture are aimed squarely at parallel computing. I'm not sure that GF100 will perform much better than RV870, if at all.
no, its a change to the graphics pipeline and some architectural changes too. graphics is parallel computing. gf100 will remove bottlenecks from gt200 so we cant say how fast it will be but with 200GB/s should be powerful.Quote:
Originally Posted by Teemax
3D is parallel computing with some extra stuff thrown in. And I'm afraid that the "extra stuff" (like ROP, TMU, HW tessellation) might not get the full treatment with GF100.Quote:
Originally Posted by Chumbucket843
As for GT200, what "bottle necks" are you talking about?
Ya, it's a GT210 DDR2 according to Hardware.fr :DQuote:
Originally Posted by trinibwoy
so here we go again.... new round of rebranding! who would thought?:rolleyes:Quote:
Originally Posted by Olivon
lol,what has nvidia done??
http://www.nvidia.com/object/product...ce_210_us.html
http://www.nvidia.com/object/product...ce_310_us.html
:rofl:
rofl, ridiculous. no wonder it's ahead of the schedule...Quote:
Originally Posted by Olivon
Please tell me that is some kind of joke?Quote:
Originally Posted by Frananta
yay, not only rebranded, but actually identical:D:ROTF:
way to go:shakes:
That's so bad it's laugh out loud hilarious. :rofl:
Come on guys next gen card with the same TDP of the last gen despite being 10% larger than the Geforce 210 (according to the pics) = win.
+1Quote:
Originally Posted by Tim
:ROTF:
I want the same stuff nVidia's PR ppl are smoking!!
I wonder if the Geforce 410 will sport a different fan.
so we have something like 8500GT = 9400GT = GT210 = GT310? Wow, that's a really resilient product. This is like a James Bond of the GPU world, it's a super agent with multiple identities... and you cannot kill it. :rofl::ROTF:
I almost feel sorry for the fools who followed this upgrade path.Quote:
Originally Posted by Florinmocanu
oh my god i thought it was joke or something lol way to go nvidia
Where do I apply for a job at Nvidia?Quote:
Originally Posted by Frananta
Seems like a nice place to work at.
Boss: Give me a new product!!
Me: Ok.... let's see.... we remove this 2 here, and put a 3... Here you go!
Boss: Flawless! pay rise for you.... and for me!
:rofl:Quote:
Originally Posted by Piotrsama
They pretty much resized the picture and renamed the page? :rofl:Quote:
Originally Posted by Frananta
Oh lord..
I find it hard to take Nvidia Products seriously lately.
Specially the main stream cards. To think my friend wanted to buy the 250 as an upgrade over his 8800 Ultra :(
8800gt-9800gt-9800gtx-9800gtx+GTS250Quote:
Originally Posted by N19h7m4r3
The way it was meant to be upgraded :D
We all gonna die before G92 does - that much is certain.:eek:
Quote:
Originally Posted by SocketMan
G92 the herpes of graphics cards.
Since it got out it'll never go away and just spread. :wth:
lol, dont forget 'compare and buy button' on the geforce 210 pageQuote:
Originally Posted by Aerwidh
do you guys think 310 will fit in a regular slot though? :rofl:
You will need resized motherboard from nVidia for that!Quote:
Originally Posted by motopen1s
Fermi - the story so far
1. High clocks, lots of transistors, revolutionary architecture - NV30 good video card make did not.
2. Nobody has ever made a great video card, late. The "comeback" is a dream yet to be realized. Radeon < GF2. fx5800 < 9700pro. X2900XT < 8800GTX, Fermi...
3. It takes more than just a year to make an ASIC, and with so many changes, odds are stacked against nVidia:
Feb 2010 launch may be optimistic.. enormous amount of testing and bugs possible with:
- GDDR5 (unlike AMD whiich has already used it for a year, this will be nVidias first)
- 40nm & 3.1B transistors & clocks (high yields are virtually impossible - praying for avg)
- lots of work required for DX11 (ie AMD had DX10.1 since HD3xx..)
- huge architectural changes to SPs to accommodate DFP performance (AMD just doubled theirs with minor tweaks)
- pressure-cooker deadlines produce glitchy product: PSU problems, mobo/chipset incompatability, XP/Vista/Win7 compatibility
Even if Fermi is perfect in every way possible and has enormous performance improvement:
- certainly, a price to match
- not even rumours of mid/low range parts - AMD already has HD57xx out last month.
- no mention of anything to counter eyeInfinity
- exclusive PhysX advantage lost since DX11 provides open standard
(just wait it can get much worse!!)
depending on extent of delay ..
- despite popular TWIMTBP game dev forced to partner with AMD since only DX11 market solution
- nVidia loses OEM contracts since no Win7+DX11 check box feature
- games are made and QA according to AMD spec - after months game dev unlikely to patch to fix nVidia bugs and nVidia likely to have more rough unoptimized glitchy driver
- nVidia only has graphics to rely on. Can't make chipsets for either AMD or Intel. No CPU business. And even last generation GTX280/260 lost bad in price/performance compared to HD4870/4850.
- super bad: last couple nVidia OEM/retail releases - parts that struggle to compete with HD4650 - already giving lame has-been impression...
Quote:
Originally Posted by SocketMan
I guess you haven't heard then?
Fermi is nothjng more than just 4 x G92 shrinked dies.
:rofl::ROTF:
Although I realize this is xtremesystems, 90% of gamers and I wont be even able to buy Fermi. Its awefully concerning that we dont even have rumours of nVidia DX11 mid/low end parts, and yet AMD already has cheap cards that make virtually all nVidia cards obsolete. Think about that for a minute.
Fermi reviled:
http://upload.wikimedia.org/wikipedi...doo_5_6000.jpg
With enhanced G92 cores in a 4 way SLi configuration. Pay less get performance more than a 5870, fastest single card in the market.
lol aja
My bad, guess they actually changed something, then :DQuote:
Originally Posted by motopen1s
what? availability from average to nvidia?Quote:
Originally Posted by Aerwidh
Quote:
Originally Posted by ***Deimos***
*cough* *cough*
Don't know about that, I just meant that the 310's site also has no "compare and buy" button, maybe they just haven't gotten around to it yet. Still, it is a differenceQuote:
Originally Posted by Helloworld_98
Wow , terribly sorry of meQuote:
Originally Posted by Warboy
I should definetly have noticed this Preview a week ago.
http://www.legitreviews.com/article/1138/4/
Afterall, what crazy lunatic wouldn't rush stark raving mad into Best Buy clamoring for his super dooper 128bit 512MB 3.4Ghz GDDR5 equipped GT 240.
This turbo charged GDDR3 HD4670 beating speed deamon is nVidia's DX10.1 flagship!!
:rofl::ROTF::rofl:
Anyone noticed this totally totally legit comparison in that article?
http://www.legitreviews.com/images/r..._240_physx.jpg
Who needs Fermi, GTX 275 is already k.i.n.g.! (the real way it's mean to bs) ;)
Hmm is that like the 8800GS but with 128bit / GDDR5?Quote:
Originally Posted by Warboy
96 sp's but 128bit and 512mb of ram. I wonder if the ROPs got cut even more down to 8.
edit: Yup, thats funny that I called the specs.
http://www.techpowerup.com/reviews/P..._GT_240_Sonic/
It seems like a 9600GT with GDDR5 to me. But 9600gt has 64 sp, 16 rops and 256bit.Quote:
Originally Posted by LiquidReactor
lol whats that :ROTF:Quote:
Originally Posted by Teemax
PR spinning at its best. (or worst) :down:Quote:
Originally Posted by eric66
Can someone explain that graph to me? Especially the 5870 being at ~14%. 14% better than what? :confused:
BTW, is that article written by Nvidia directly?
that's 14fps, it's because that fps is from a PhysX game and they aren't using an nvidia card or an i7 with Physics set to use all cores.Quote:
Originally Posted by eleeter
Ah, okay I should have known. :shakes:Quote:
Originally Posted by Helloworld_98
How any reviewer could put that on their website without a disclaimer* is beyond me.Quote:
Originally Posted by Teemax
*Above graph was made courtesy of the BS brigade.