• The GT300 Thread - Nvidia's New Kid on the Block
    155 replies, posted
Guys just because it's not [B]only[/B] aimed at gamers it does not mean it won't be good for games, for all we know it could beat the 5000-series by far. Lets wait for benchmarks before dismissing it as not being a GPU for gamers (not saying that anybody has done so, but I can see that coming sooner or later in this thread). Also personally I don't think Nvidia will do too much to oppose eyefinity, afterall Nvidia has the whole 3D thing, which I personally would greatly prefer to eyefinity (two completely different things I know, but since you have to choose between the two, I'd choose 3D). By the way my opinion on the Eyefinity vs Nvidia 3D is, as I said, an [B]opinion[/B], I don't prefer 3D because it's made by Nvidia, it's just a matter of personal opinion.
I love my cards as expensive AND as big as a football field, so Nvidia is my favorite company.
[QUOTE=:smug:;17601077]Its gona be like £150-£200 ($240-$320), i bet[/QUOTE] I'm pretty sure this is quite literally impossible. The yields on such an immensely huge and complicated die together with the sheer size of the damn thing are going to drive costs off the charts. I'm thinking this is going to be closer in the $500 range.
[editline]02:58PM[/editline] More info: [quote] Just hours before Nvidia decided to share the Fermi, GT300 specification with the world, we managed to get most of the spec and share it with you. The chip has three billion transistors, a 384-bit memory interface and 512 shader cores, something that Nvidia plans to rename to Cuda cores. The chip is made of clusters so the slower iterations with less shaders should not be that hard to spin off. Each cluster of the chip has 32 Cuda cores meaning that Fermi has 16 clusters. Another innovation is 1MB of L1 cache memory divided into 16KB Cache - Shared Memory as well as 768KB L2 of unified cache memory. This is something that many CPUs have today and as of this day Nvidia GPUs will go down that road. The chip supports GDDR5 memory and up to 6 GB of it, depending on the configuration as well as Half Speed IEEE 754 Double Precision. We also heard that the chip can execute C++ code directly and, of course, it's [highlight]full DirectX 11 capable[/highlight]. Nvidia’s next gen GPU is surely starting to look like a CPU. Looks like Nvidia is doing reverse Fusion and every generation they add some CPU parts on their GPU designs. [/quote] Source: [url]http://www.fudzilla.com/content/view/15756/1/[/url]
[QUOTE=:smug:;17601077]Its gona be like £150-£200 ($240-$320), i bet[/QUOTE] Nope. [editline]03:15PM[/editline] [QUOTE=Hatsen;17601151]It really looks quite hardcore. [img]http://images.bit-tech.net/news_images/2009/09/first-fermi-card-pictured/fermi1.jpg[/img][/QUOTE] At least wipe the smudges off.
[QUOTE=:smug:;17601077]Its gona be like £150-£200 ($240-$320), i bet[/QUOTE] The 5870's are still £300, ATi are the cheaper of the two manufacturers, there is no way in hell this would be priced lower than the 5870 unless it was actually incredibly shit, and nVidia were just lying about it's awesome power.
[QUOTE=Shogoll;17602394]I'm pretty sure this is quite literally impossible. The yields on such an immensely huge and complicated die together with the sheer size of the damn thing are going to drive costs off the charts. I'm thinking this is going to be closer in the $500 range.[/QUOTE] $600. This is nvidia, remember?
Yeah knowing nvidia, this will beat the 5870 by a few FPS, and seeing that the 5870 costs 380, it will cost 500. (trubitar will get 4 anyways :\)
[QUOTE=Hatsen;17601151]It really looks quite hardcore. [img]http://images.bit-tech.net/news_images/2009/09/first-fermi-card-pictured/fermi1.jpg[/img][/QUOTE] Seeing his nasty greasy thumb that close to the gold plated PCI-E connector is almost heart wrenching:frown:
Did you guys notice that it only has one 8 pin PCI-E power connector? [editline]05:13PM[/editline] [QUOTE=johanz;17601134]It's funny how people think that new nvidia card won't support dx11 fully because nvidia said it's not the main reason to buy it. They never said they won't support dx11 or it's features, they're just not their main focus.[/QUOTE] Yet I get 21 disagrees on my post saying that. :saddowns:
Did you guys notice that the tesla is a fake
[QUOTE=cryticfarm;17605628]Yeah knowing nvidia, this will beat the 5870 by a few FPS, and seeing that the 5870 costs 380, it will cost 500. (trubitar will get 4 anyways :\)[/QUOTE] Well that is why I still think I'll be going red again. I honestly will not pay another $50-100 for a few FPS here and there (just to own a specific brand). They're going to have to give me some pretty significant increases over what ATI has on the table right now (to justify that supposed cost increase), or match ATI price-wise. But I will try and hold out until I see some legitimate benchmarks on these cards before making a choice. [editline]07:02PM[/editline] But again, maybe they'll surprise us with their launch prices. I personally am not counting on it...but who knows. Things have changed quite a bit.
[url]http://www.techpowerup.com/index.php?105052[/url]
[img]http://i33.tinypic.com/104ra5s.jpg[/img] I personally think that's pretty damn sexy.
[QUOTE=Zorlok;17607249][img]http://i33.tinypic.com/104ra5s.jpg[/img] I personally think that's pretty damn sexy.[/QUOTE] What's the point of a mirror finish on a graphics card?
[QUOTE=Hatsen;17601151]It really looks quite hardcore. [img]http://images.bit-tech.net/news_images/2009/09/first-fermi-card-pictured/fermi1.jpg[/img][/QUOTE] only one 8 pin too.
Well there's also that 6 pin on the top.
[QUOTE=hexpunK;17602970]nVidia were just lying about it's awesome power.[/QUOTE] You mean like their good old plan of rebranding their new series and having miner changes done to it to make it just slightly better?
[QUOTE=Zorlok;17607511]Well there's also that 6 pin on the top.[/QUOTE] That's stupid, why would they put the power connectors on different sides of the card...
also [url]http://translate.google.com/translate?hl=fi&sl=fi&tl=en&u=http%3A%2F%2Fplaza.fi%2Fmuropaketti%2Fnvidian-esittelema-fermi-naytonohjain-olikin-vaarennos[/url] [editline]02:26AM[/editline] [QUOTE=TheDestroyerOfall;17607485]only one 8 pin too.[/QUOTE] And the best part about is that it's not even soldered to the board
[QUOTE=Quantuam VTX;17602410][editline]02:58PM[/editline] More info: Source: [url]http://www.fudzilla.com/content/view/15756/1/[/url][/QUOTE] Full DX11 capable? That means OpenCL and tessellation too? If it was the right price, I might buy it for the benefit of having PhysX/CUDA, the current leaders in GPU powered physics in games along with OpenCL. Of course, if it was substantially more expensive, I wouldn't pay more just to see cloth and broken tiles. Plus tessellation is fucking awesome, and if it's being used in AvP, then those screenshots I saw in a magazine just might not be prerendered. But Nvidia aren't known as the kings of undercutting, so I'm gonna hold out until they've had a little price battle with ATi first.
[url]http://www.semiaccurate.com/2009/10/01/nvidia-fakes-fermi-boards-gtc/[/url]
[QUOTE=ShaRose;17611531][url]http://www.semiaccurate.com/2009/10/01/nvidia-fakes-fermi-boards-gtc/[/url][/QUOTE] hahah, Nvidia Get fucked
[QUOTE=ShaRose;17611531][url]http://www.semiaccurate.com/2009/10/01/nvidia-fakes-fermi-boards-gtc/[/url][/QUOTE] hahahahahahaha
[QUOTE=Xplodzion;17598969]Nvidia's Shaders are faster than ATI's so ATI having a crap load more of them doesn't make that much of a difference, the 4890 has 800 of them while the GTX275 only has 240, but both cards perform similar, the GTX380 has more than doubled them (512 vs 240) while ati's have been exactly doubled (1600 vs 800), so it's already a sign that the GTX380's might be faster. [editline]02:56PM[/editline] [url]http://forums.guru3d.com/showthread.php?t=305808[/url][/QUOTE] Wait wait wait, don't the shader units differ from eachother?
[QUOTE=ShaRose;17611531][url]http://www.semiaccurate.com/2009/10/01/nvidia-fakes-fermi-boards-gtc/[/url][/QUOTE] Well shit, Nvidia seems to be having a tad bit of trouble.
Oh jesus god, Nvidia you dolts. And ATi has GPU Accelerated Havok you say? I might buy ATi and hold out for ValVe including that in an engine update. Why the dumbs? Imagine Gmod with that tech. I'll be using those boxes to store the debris from the thousands of exploding barrels that I'm gonna be apawning.
[QUOTE=Pandamobile;17607477]What's the point of a mirror finish on a graphics card?[/QUOTE] Whats the point of a giant sticker of a half naked armor clad woman on a video card? Both are pointless, it's in your computer. NVIDIA is not going to release a card over their standard price bracket, it's just the rules of economics, NVIDIA knows what they are doing and they are not leaving the target demographics. Just because it's a better die archecture and size doesn't mean it will cost more, efficiency doesn't equal more expensive.
I'd only get one if: a) nvidia lowers their prices (like thats gonna happen) b) this is way better than the 5870
[QUOTE=Zorlok;17607249][img]http://i33.tinypic.com/104ra5s.jpg[/img] I personally think that's pretty damn sexy.[/QUOTE] Indeed it looks hot, I'm sure the mirror plating is to show you how it can turn anything hot, even you.
Sorry, you need to Log In to post a reply to this thread.