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
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.
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
I don't think there is an "AGP camp."
PCI Express is a replacement for PCI and AGP on desktop class motherboards (I guess PCI-X might be better for servers, but I don't know).
Its advantages are that it has switched uplinks, so, if I understand correctly, each device can have its maximum bandwidth between any other component. PCI shares its bandwidth between all devices.
PCI Express 16x replaces AGP, and roughly doubles the bandwidth, I think. Then there's 8x, 4x, 2x and 1x for devices with lower bandwidth requirements. And you could probably expand to 32x if you really need more bandwidth than 16x. It's all about the number of "lanes" you devote to a card.
Someone here has a link to an article on this stuff, in case you want a description from someone who actually knows what they're talking about.
I've come for the woman, and your head.
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?
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.
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.
DirectX is Microsofts' standart to abstract software from the hardware (not only graphics, it also covers audio, controllers, networking, and so) as much as possible. Direct3D is DirectXs` 3D rendering part.
The thing with DX is that it's aimed mostly to games, and, while full-featured, it's incompatible with everything else. OpenGL, much like D3D, is dedicated exclusively to graphics but can be ported much more easily, and it's (IMHO) overall a cleaner implementation. Both can coexist in a single machine (if you have a modern videocard, that's most likely the case), but are independent, requiering separate drivers and so.
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
They might concentrate on getting their CURRENT high end card (6800 Ultra) on the retail shelves instead of "pre-announcing" crap in the pipeline.
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.
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.
Does it have low power consumption or does it include a nuclear powerplant?
"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.
Open GL doesn't support many of the newer features of GPU's. By newer I mean anything in pretty much the past 2-3 years isn't really supported by OpenGL. As an example there isn't yet a HLSL or even a platform independant shader language at all.
That's not true. This *was* true 2-3 years ago, but in that space, the OpenGL ARB has been very quick to keep OpenGL competitive with D3D. 1.3, 1.4, and 1.5 all came out about a year apart, and 2.0 should be coming wout this year. 1.5, which came out last year, supports pretty much everything out right now, including a full high-level shading language (GLSL).
A deep unwavering belief is a sure sign you're missing something...
Okay, here's a guide for all you folks who are getting so unbelievably excited over something as mundane as pairing two video cards together.
FIRST OF ALL: THIS IS NOT "SLI".
Nvidia is simply leveraging the term to sell their version of the concept.
SECOND OF ALL: THIS IS NOT NEW.
In fact, every single consumer card that has attempted this in the past has been a failure.
** 3DFX Voodoo 2
The performance of a single Voodoo 2 was so good that people waited for prices to fall before buying a second Voodoo 2. Sales of the Voodoo3 also suffered heavily because, under many conditions, the Voodoo 2 SLI performed similarly. Thus, the long-term failure.
** Metabyte "SLI"
Shortly after 3DFX made "SLI" a household name, Metabyte developed a PCI-bridge technology that would split the framebuffer between ANY two cards and have them render in parallel.
Sound familiar? It should. There was one major drawback: both cards would have to operate in PCI mode, negating some of the advantages the newer AGP cards enjoyed. Metabyte tried to license the technology to TNT2 manufacturers, but none were interested...mainly because the upcoming GeForce 256 would make ir obsolete overnight.
** ATI Rage MAXX
This card featured two chips rendering a piece of the framebuffer, much like MEtabyte's technology. This was simply an attempt by ATI to get some experience designing a parallel-processor architecture, and to take some wind out of Nvidia's GeForce 256 sails. Because the parallelization was on-card, it could function as a normal AGP card. Bad drivers and lack of Win2k / XP support killed this card.
** 3dfx VSA 100 (Voodoo 5 5500)
The VSA 100 was designed to be used in parallel in a fashion similar to the Rage MAXX. Although this card boasted many fancy features, it could not keep up in the performance race. 3dfx also found out how hard it is to make money when the chipsets on your cards cost roughly twice that of your competitors.
** Alienware "SLI"
Yes, this is basically Metabyte's concept, but the appearance of PCIe has made it a reality for high-performance cards. PCIe also makes it possible for this to be developed entirely in software (Metabyte's vision required an on-card bridge), so why the hell wouldn't they market it?
** Nvidia Geforce 6 with SLI
Two things are readily apparent about this latest attempt:
1. The card is not a flagship, high-margin card. It is simply designed to lock-in users to a cheap Nvidia card now, and an upgrade in the future.
2. Even in SLI mode, this combo won't exceed the performance of their top-end card, meaning Nvidia won't cannibalize upgrades for their next card like the Voodoo 2 SLI did.
So sure, Alienware and Nvidia look like they've got a winner on their hands...except that there aren't many PCIe motherboards with dual 16x slots. Oh well, yet another niche-market-product-turned-failure waiting to happen.
Man is the animal that laughs.
And occasionally whores for Karma.
throw in a couple of 3 ft black candles. And you know, a baby goat.