Slashdot Mirror
NVIDIA Gives Details On New GeForce 6
An anonymous reader writes "According to Firingsquad, NVIDIA will be announcing a new GeForce 6 card for the mainstream market at Quakecon this week. Like GeForce 6800, this new card will support shader model 3.0 and SLI (on PCI Express cards), so you can connect two $199 cards together for double the performance. NVIDIA will also be producing AGP versions of this card as well."
A beowolf cluster of video cards...??? Oh wait...
*Ducks.
If there are as many people out there with fresh copies of Doom 3 in their hands or winging their way to them as I suspect, then this will be slashdotted veerrryy soon.
i cker=NVDA&script=2100 ), NVIDIA CEO Jen Hsun Huang confirmed reports that NVIDIA would be launching a new shader model 3.0 mainstream card shortly: "In a few days we're going to turn up the heat another notch. At Quakecon in Texas, a mecca for gamers and truly a phenomenon to witness, we will officially unveil our newest mainstream member of the GeForce 6 family".
So here's the content:
In last week's conference call ( http://www.corporate-ir.net/ireye/ir_site.zhtml?t
Jen Hsun went on to say:
This mainstream GeForce 6 will be the only shader model 3.0 GPU in its class and deliver performance well beyond that of the competition. PCI Express support is native and AGP support will be provided through HSI, once again showing the versatility of the HSI strategy...sampling started in June, production is in full steam on TSMC's 110 nanometer process, with shipments to OEMs soon.
Price points and product names weren't discussed, but Jen Hsun also confirmed SLI support for this upcoming card, and also mentioned by the end of the year NVIDIA will have a top-to-bottom family of shader model 3.0 cards. In fact, he mentions "we're ramping 110 on two GeForce 6 families right now at TSMC, and very shortly we'll start a third...and this quarter we'll have five GeForce 6 GPUs in production, and that ought to cover us from top to bottom."
I can't wait for the GeForce 27, it's going to be sooo much better. :-)
Seriously, can't they figure out a new name already?
SLI was such an obvious way to make graphics rendering parallelized! I'm glad they're bringing it back... I've been missing it.
Does anyone have any idea how many PCI Express ports this uses? It's my understanding that you have a total of 20 and most motherboards are allocating 16x to the video... will this card require 8x? Or do you need a special motherboard for this?
Anyone know?
I am disrespectful to dirt! Can you see that I am serious?!
Is there a point where graphics cards get so advanced that humans can't even tell the difference anymore? Or is that virtual reality?
Only $200?
This should be interesting to see and good for competition to say the least.
This is nice and all, but it's kind of ridiculous to only be able to link two video cards together. What of one of them dies? Then you're back to single speed performance until you can get a replacement. I would much rather get a RAIVC-5 array of, say, five to ten video cards. Then if any one dies, no big deal; the others can handle the load. And does anyone know if these new NVidia cards will be hot-swappable?
I might need to dust off my textbook from "Parallel and Distributed Computing", but I'm pretty sure that getting double the performance from two cards is about as likely as getting double the performance from two processors. It's just not likely unless the graphics routines can split up jobs perfectly and not suffer from any overhead for communication. I imagine there will be a noticeable performance increase from 2 cards working in parallel since graphics algorithms do have a tendency to be very parallelizable, but claiming double performance in naive at best and dishonest at worst.
My first NVidia card was a GeForce 256, but then I upgraded to a GeForce 2. Later I bought a GeForce 4MX card which was actually slower than the GeForce 2 in my older system. Lately I've upgraded to a GeForce FX 5600... now a GeForce 6800 is the best, but they want me to buy a GeForce 6? I can't keep up with this shit. So my $250 GeForce FX 5600 card that I bought last year is no longer any good? It runs Battlefield 1942 alright, but now they're saying it's not good enough for Doom 3 which I just bought but haven't installed yet. Ugh. I suppose my Athlon XP 2400+ I built last year is now too slow as well?
...when you see the phrase "connect two $199 cards together" and say to yourself "Hey, that's a good value!".
Oh, I can't help quoting you because everything that you said rings true
Since I don't keep up with things.. Is PCI Express way better than AGP, for bandwidth on graphics cards? If so - is there anything new from the AGP camp planned?
.
I fear something like AGP EXTREME
I'm all for advancing technology, but when it comes to video cards, it's all a matter of who can keep up with Microsoft's DirectX demands the best.
Meanwhile, OpenGL, the industry standard graphics library, is getting left behind because every video chip maker wants to show off how well it supports GlibFlobber() DirectX 27 API.
Won't someone please think of the industry standard instead of the proprietary (and very small market) "standards" of Windows?
so you can connect two $199 cards together for double the performance.
Much like you can duct-tape two cars together for double the performance (but certainly not double the speed).
See this article.
tasks(723) drafts(105) languages(484) examples(29106)
From the article:
Price points and product names weren't discussed
So where did $199 come from?
Uttering logically derived and empirically supported truths to the disciples of the orthodox establishment.
Say that 5 times fast.
Best Slashdot Co
Each card draws a scan-line each, all the way down.
All I want is DirectX 9 support in hardware, not the kludges which the current NV's have. The GPU makers churn these things out so quickly, yet they can't keep up with an industry standard a year old...
"We know what happens to people who stay in the middle of the road. They get run over." - Aneurin Bevan
whoosh...
Moe: "And that's how, with a few minor adjustments, you can turn a regular gun into five guns." [applause]
Read Pynchon.
...But does this mean you have to load the same texture data into both cards in order to obtain this parallel processing? Isn't that rather inefficient?
Based on recent cinema experiences, you would have to say were still a hell of a long way from this. I just saw Spiderman 2, and a lot of the CG work still looks totally artificial. Likewise, the trailer for I, Robot made me cringe with its computer-generated aura. Even LOTR looked fake in places.
Considering these movies are using the absolute cutting edge of pre-rendered graphics technology, I would suggest we're still a decade or so from anything like 'real' looking PC graphics.
Read Pynchon.
I just wish they would give some real, across the board benchmarks. I want to know if it is going to give me enough additional FPS for nethack to make it worth the purchase? Would I have to get some exotic motherboard combo to make that happen?
How does this card compare to the 6800? I mean at 200 bucks, that sounds awefully cheap compared to the 6800 which is $500? If this card is better, I will shell out to buy two of them and a new motherboard - and my friend who just got his 6800 this past week will be bitter (he paid 400 for his one card) :)
-A
I mod down so you can mod up. Your welcome.
Am I right in thinking that most of the current crop of video cards don't really push AGP 8x at this stage? I seem to remember seeing some benchmarks where high end Radeons were not really that much faster on 8x vs 4x.
At least it will give 'gamers' a chance to brag about how fat their bandwidth is, I suppose.
Read Pynchon.
SLI, as 3dfx implemented it, had one of the paired cards render one scan line, then the other card render the next scan line while the first read in data in order to be ready to render the third scan line, and so on (this the term, Scan Line Interleave). I may be wrong, and mea culpa if I am reading your comment wrong, but you are thinking about the two cards sharing the workload in order to render the entire screen at once. This was not the case with SLI.
I haven't had time (or inclination - I'm happy for now with my AGP Radeon) to read up too much on the new method of combining video cards to render, but I seem to recall hearing that Alienware was working on a way to use two cards to render a frame, but instead of the scan-line interleave of the Voodoo2 method, each of the paired cards would render half of the screen (e.g. card 1 would render from line 1 to the middle of the frame, and card 2 would render from the following line to the very bottom of the frame). This makes sense to me: you bypass synchronization issues that Voodoo2s were prone to at the end of the useful life of the product line (once the software far exceeded what the hardware could do), and you can theoretically double the performance, since each card only has to do half the work it would have to do on its' own.
The downside would be that if one card is slightly out of spec, overheating or generally misbehaving, then you could have frames that look *really* bad, or you'd have to have some sync method in place, which would cut down on the benefit gained from separating the processing/rendering (but still better than just one card alone).
Anyone have any details? Is this going to be a generic PCI-X thing, or is it specific to nVIDIA?
"I don't get it." -- ObviousGuy
This is a bit off topic, but I'm going to ask anyway.
I've never fully understood the difference between OpenGL, Direct3D and DirectX...
If Open GL is the industry standard then what is Direct3D? Is DirectX just the way Windows handles graphics? If so, it works in conjunction with OpenGL and Direct3D?
Can anyone with some knowledge here bring me up to speed?
Thanks!
-Mark
Dovie'andi se tovya sagain.
Each card in new nVidia SLI (doesn't stand for Scan Line Interleave anymore, it is something else poncey using the same acronym) allocates a portion of the screen to render. E.g., top half and bottom half. There was an article a few weeks back which was featured on Slashdot that explained this.
I've seen some insulting posts b4, but this one has to take the cake. first of all, the world dosen't revolve around video games and hardwarde to run them. second, my AMD 2800+, 1gig DDR, GeForce5900 128mb, runs this game just fine at 1280x1024 med. detail. third, i ALWAYS post with my handle
Everyone has a photographic memory, some just don't have film.
What's weird is that nVidia already _does_ have a $200 variant of Geforce6 - the Geforce 6800LE. It's essentially a lower-clocked (GPU and RAM) 6800 with only 8 pipes (so, half of what the 6800GT/U has). One of the hardware sites did a review of it (t-break?), and it performed pretty nicely - almost always beat the 5950. It's supposedly only for OEMs, but that's never stopped the online vendors from selling a card.
If they are indeed talking about a 6600, it's going to need to go under $170 to have any sales value whatsoever. SLI is nice and everything, but most people simply don't have PCIe mobos to take advantage of it, so it's going to be a non-issue for the next year and a half.
Still, it'll be nice to see nVidia actually try to deliver a better price/performance ratio than ATI for once.
-Erwos
Plausible conjecture should not be misrepresented as proof positive.
In my Phys III class ages ago, we did the calculation for the resolvable limit for the human eye given a certain distance from 2 points. I can't recall the formula, but it seems that at some point in the near future a 8000 x 6000 screen will look exactly like a 80,000 x 60,000 screen unless your 2 cm away from it.
"I must not fear. Fear is the mind killer." -Bene Gesserit Litany Against Fear
heh.
They might concentrate on getting their CURRENT high end card (6800 Ultra) on the retail shelves instead of "pre-announcing" crap in the pipeline.
If I can get a 10 year, blanket coverage warranty on the Trane HVAC system I'm going to have to install in order to keep it cool, not to mention the active damper system to keep the noise level bearable. Oh, and It'd be pretty cool to have some kind of rebate in place so I can recoup the cost of upgrading the outlets and the breaker box in the house to 100 Amp's a piece.
I was hosting a LAN party at my place about a year or so ago. One of my coworkers showed up with his computer and another 512MB DIMM that he planned on installing before we got started.
We balked. There's an unspoken rule that no hardware changes during the LAN unless necessary. Murphy's law simply looms too large. He ignored it.
The case was a smaller mid-tower that he uses for LANs, and with a couple of hard drives and the associated cabling it gets pretty tight. As he's sliding the RAM into place, we hear a "plink." Shit. The RAM's in place, so he steps back to survey the situation. There's a capacitor sitting on the floor of the case. "Um, maybe it's one of those capacitors that's, you know, for show..." The computer throws a video error at post.
We pull the card. Murphy's law has struck; it's a GeForce 5800 Ultra (the old dustbuster model), and a cap has sheared right off the card. I don't have a soldering iron in my apartment, so the coworker is prepaing for an evening of staring over shoulders. That's when we break out the electrical tape. We give the card a good hard wrap with the tape to hold the cap in place, and...
It works spedtacularly. No crashs, no video glitches, no problem. In fact, it works for another month while he waits for the 5900 Ultra to release before exchanging the card. It led us to praise NVidia for the Unified ELectrical TApe architecture (ELTA), which we theorized could provided bootleg performance maintenance across the entire NVidia line, from the TNT2 up.
Or so I've read. with SLI I believe you can only get about 70% better performance versus 1 card. Can't remember where I read this. Try googling it!
NVDA has just reported a HORRIBLE quarter. Many are wonder what the F is going on with that company. This is a PR release. They need to say these things. They need to say they have native PCIe despite not a SINGLE OEM design win. They need to say 6800 volume will ramp up and product will be driven down to the low end. Will this actually happen? I have no idea, but this is the least I would expect NVDA to say on this horrible week for NVDA longs. ATI has really put the hurt on. This next 12 months should be pivotal for NVDA's future.
Replies from a website where people want more options in Operating Systems, but they bitch about more options from hardware, just makes me wonder if people just want to bitch.
DirectX is Microsoft's standard to abstract software from the hardware
Just to be picky: OpenGL is a standard, DirectX is not. It's a popular API, sure, but it's not a standard.
2 $200 cards plus a PCI Express mobo (say, a Gigabyte GA-8I915P) @ $130-200 plus switching CPU's (if necessary) will still wind up costing you more than his single card. Add to this, his single card may well outperform your new setup (as far as GPU benchmarks go).
Of course, you will definately be ahead of the game in terms of mobo technology... which is quite right by me. =)
#SickNotWeak
Does this mean we'll see a price drop for the GeForce line? I've been putting off buying a new card, I don't want to end up buying it a couple of weeks before a price drop.
WURD!!
Mod the parent up, I snarfed on the keyboard. But seriously, Bitboys have apparently ditched the video card and are instead aiming for the mobile market. Bitboys' website has the vapor. Personally I think they'll never get something out. They had a good prototype card but suddenly ATi and nVidia came with cards that crushed them completely. And there are competitors in the mobile market too.
Does it have low power consumption or does it include a nuclear powerplant?
Maybe it would be time now for them to release the specs for GeForce2 MX, GeForce 3 and similar,
so we can finally develop drivers for more operating systems/platforms!?
You could fit over 5 hours of programming on an L-830 tape at Beta III.
The problem is Joe Sixpack understands a 6 hour tape alot better than the difference between L500, L750, L830.
The other marketing Sony screwed up on were the tape speeds. Joe Sixpack won't understand Beta II or Beta III but will understand Extended Play or Slow Play
So in review:
Which is easier to understand if I want to record Knight Rider:
I can fit 6 episodes on a 6 hour tape at Extended Play with VHS
I can fit 5 episodes (6 episodes without commercials) on an L-830 running at Beta III
Sony just didn't understand the common American man.
if you steal from one source, that is plagiarism, if you steal from many, well, that's just research.
"In a few days we're going to turn up the heat another notch."
;)
Translation: my computer's electricity bill and my winter heating bill just became synonymous.
For a second there, I thought were going to see enough technical details to write drivers (heaven forbid!) for the hardware.
flying-rhenquest died a couple weeks back (The fan base may have noticed that the web page is down,) so I upgraded to a system with a ATI X600 PCIE card. You can force the system to recognize it as a radeon for 2D, but apparently PCIE is not yet supported by the ATI proprietary driver nor the Xfree86 radeon driver. Rumor has it the Nvidia proprietary drivers have PCIE support, but I haven't had any solid confirmation of that yet. So does anyone know for sure that if you drop this card into a Linux system, you'd be able to get 3D acceleration?
I'm trying to teach myself to set people on fire with my mind... Is it hot in here?
... how can I tell if my newish Dell has PCI Express? Other than looking at it's spec which I nolonger have.
Hmm, that prompts an intriuging question: how much duct tape would you need to attach two cars together securely. Surely the quantity would be a function of things like engine horsepower, tire/steering/braking preformance, tape strength, how it was fastened, etc.
:-)
This would make an interesting experiment. If someone does it, post a journal with pics somewhere!
PCI Express slots look nothing like regular PCI slots. PCIE-E 1x are tiny, about a half inch or so long.
:|)
That being said, your new Dell likely does not have PCI-E. Such motherboards only became available in the past couple months. (And then got promptly recalled.
--LordPixie
Whoa, I didn't even know there was a GeForce 5
Oh well, I'm happy with my 32mb TNT2 card.
As long as we're talking about nVidia, does anyone have access to a long term performance graph of old nVidia cards? Rating them from generation to generation to how much improvement there was in each era.
I tried googling for it, but the keywords are just too popular, and everyone is google spamming and bombing and such. Don't even bother trying to search on Yahoo.
I used to have a good chart that showed dollars-per-FPS, but it's totally lost now.
"so you can connect two $199 cards together for double the performance."
This stuff crops up all the time, I figured I was safe from it on a technical oriented website. A 64 bit processor is not twice as fast as a 32. Two processors are not twice as fast as one, or four twice as fast as two. Running two video cards in SLI will not "double the performance".
There are many factors that would prevent this from happening, CPU speed, bandwidth, and communication overhead to name three. A "signifigant increase in performance" would be an accurate discription.
This kind of broken logic may work for Apple PR firms, however it dosent play in the real world.
For once, someone isn't spouting FUD. SLI has only been scan-line interleave since voodoo2, but ever since those vsa100 chips, it has not been truly SLI. People just use the term SLI since everyone knows it. Just like Honda's new hybrid is under the civic brand name. Nobody would know "Honda Insight" but they'd know the Honda Civic. Same goes here... if they gave SLI a new name, it wouldn't sell as well.
For several years, I hosted my webserver out of my apartment. Now, in Seattle, the tempature doesn't get that low (Compared to the midwest or say, Siberia), but my dual 300mhz P2 server kept the place quite comfortable. In the three years I lived there, I only turned on the heat twice.
HA! I just wasted some of your bandwidth with a frivolous sig!
Only reason I was waiting for ATI to come out with PS 3.0 cards was the mammoth powere supply reqs for the last gen Geforces.. I wonder if these new budget cards are gonna require all that BS. I'm assuming they won't have dustbester fans like the previous gen budget cards, but I'm surprised no mention has been made of the PSU reqs here.. Hmm.. I guess I'll have to poke 'round on http://8dimensional.com and look at the more hardcore reviews.
-taosk8r
throw in a couple of 3 ft black candles. And you know, a baby goat.
... he's just playing, because he's looking at the data visualization window, and not reading the /. page over to the right of the display:
u m-VisIt.jpg
http://www.llnl.gov/icc/sdd/img/images/DMX-Chromi
It's great that they've got lower cards coming out, but what I really wanna know is when we can purchase a 6800 ultra DDL for the PC (yes, to run the 30" apple monitor.)
damn, I need low-profile stuff, does anyone know if all pci is low profile...sorry, I know so little about video cards.
http://www.commaecho.com
Shader this, shader that, shader the latest smells and bells. Yet another shader is like improving the aerodynamics of a race car that still uses a Model T Ford engine. Vertex manipulation has been negelcted since the dawn of time. Roll on OpenGL 2 with programmable vertex manipulation as a standard part of the render pipe.
Should virtual dogs poo?
I'm not a color expert, but I've been told that there are many colors that can't be displayed accurately on a CRT, and I assume LCD, due to the limitations of the device.
Mea navis aericumbens anguillis abundat
but will it run Microsoft Bob?