Slashdot Mirror

Go update your drivers. Your system should be able to handle at least fullscreen 1024x768x32 Geiss or Whitecap or other 3D visualizations. Also, if you're talking about AVS, try not using the transparency option (that takes computing power, though if you've updated your drivers, the alpha blending should be handled mostly in hardware anyway).

Please don't make the assumption that Windows is the reason your system is slow with graphically intense applications. Most visualizations are not a whole lot of computation (Winamp pre-calculates the fourier transforms on the dataset sent to vis plugins, so the plugins themselves need not do so).

Go update your drivers. Your system should be able to handle at least fullscreen 1024x768x32 Geiss or Whitecap or other 3D visualizations. Also, if you're talking about AVS, try not using the transparency option (that takes computing power, though if you've updated your drivers, the alpha blending should be handled mostly in hardware anyway).

Please don't make the assumption that Windows is the reason your system is slow with graphically intense applications. Most visualizations are not a whole lot of computation (Winamp pre-calculates the fourier transforms on the dataset sent to vis plugins, so the plugins themselves need not do so).

Hmmmm? The Geforce 4 line supports dual-head display out of one AGP card. ATI 8500 cards might, I know they have both VGA and DVI outs. Hell, the new Matrox Parhelia cards support THREE monitors (check out the surround gaming screenshots). I imagine making a new northbridge chip with another set of memory bandwidth to a 4~8x agp slot wouldnt be as easy as going down to Best Buy and getting one of these cards.

The official community site is at cgshaders.org. There's a Linux Toolkit out now. There's a interview with CEO David Kirk. Along with articles, a shader repository, and forums for help.

One of the figures in a .pdf on nVidia's site says, "PS2" as well. I believe it was their Cg white paper here.

From Nvidia's Homepage you can check out the press releases and find this:

"NVIDIA's Cg Compiler is also cross platform, supporting programs written for Windows®, OS X, Linux, Mac and Xbox®."

So maybe even though the tools aren't cross platform - the compiler is. I think this is a Great step forward towards OpenGL 2.0 - this is showing that Windows doesn't have to be the only platform to write graphically intensive applications for.

Derek

*Gasp*
I didn't realize that Roller Coasters and G-Force could be that dangerous.
Guess I will have to go back to DOOM on my 486...
Curse this new technology.
I hate Moore's law...

The one thing I wish is that nVidia would roll out a card with a tv tuner and remote

Nvidia's TV Tuner option is the Personal Cinema. Its not quite "on-board" (it requires a separate breakout box), but it does include a wireless remote. I don't know if it ever really took off though because it doesn't seem to be very "mainstream" at this point... at least I never really hear anybody talking about it.

nvidia already has drivers out for Linux/IA64 with some of their higher end cards (quadro line).

nvidia already has drivers out for Linux/IA64 with some of their higher end cards (quadro line).

Not a third rate computer, this box actually has some good parts in it, for example it has pretty much the southbridge of the nForce chipset to control the soundboard, and the networking, which this is a very solid components in it, for more details on what it can do, nvidia actually placed performance details at Here. I also believe that this card is comparable to the Geforce 4? but I am not quite sure on that. Could someone confirm/deny this?

With all the issues with the VIA K7 chipset, it's natural you'd feel a little queasy about going the AMD route. Also there's the heat death issues to consider. I understand there are now safety measures in place to save an Athlon XP if the chip fan/heatsink fails, but that was not the case with earlier Athlons. But keep that fan on tight...it's important.

Much of the stuff mentioned in the article is confirmed and true, but this is a blatant lie to me:
Van's Hardware is reporting that MS is backing x86-64 over Intel's IA-64

Windows XP has been running on IA-64 for ages now, Nvidia's got drivers for it, why would they support x86-64 OVER IA-64? Why not both? It appears they're doing both, and I've seen absolutely nothing to say otherwise.

It wouldn't make any sense for MS not to support both ISAs. It's entirely possible (it's been done already), so why not keep them out there?

I think Van Smith's a little off here. :)

Linux Graphics Driver Download.

These drivers have been around almost since XFree86 4.0 has. Before that, NVIDIA had GLX drivers for the 3.x series. Do some research.

nvidia

Bzzt.. wrong! nVidia provide binary-only drivers. There are stability issues, and there's no way they're going to be resolved, because no-one's got the source to fix it.

Bzzzzt ... wrong!

Sources for both the kernel driver and the GLX driver are available from Nvidia's linux download page in both SRPM and tarball format. This is necessary because NVidia cannot possibly provide binaries for all possible combinations of distro/kernel (the nvidia drivers have to be compiled for a specific kernel version) that might exist, especially since there exists such things as LFS, Rock Linux and Sorcerer Linux.

As for fixing the stability problems ... well, I guess you are free to do so, but the drivers are NOT "free software". Technically, I guess they are not REALLY Open Source either since you can't re-distribute the modified driver, but I imagine nvidia might look with favor on receiving a contributed patch, provided it didn't break something else.

Fully realized under windows only? Check out:

http://www.nvidia.com/view.asp?PAGE=linux

They just added Geforce 4 support and OpenGL 1.3 extensions.

NVIDIA has their own linux driver team, and the drivers perform on par with Windows machines. The only think lacking is Direct3D support, which is useless under linux anyway.

Latest nVidia drivers are 1.0-2880. Just FYI.

and anyway I would _never_ use a binary-only driver in an open-source kernel - hence my gripes with NVIDIA

Actually, you can easily download the source to the Nvidia drivers. The source is right on the same page as the binary drivers.

GLX SOURCE RPM
Kernel Source RPM

I'm not defending Nvidia here, because I still can't stand the license they use for their source code, but nonetheless you can get the source.

and anyway I would _never_ use a binary-only driver in an open-source kernel - hence my gripes with NVIDIA

Actually, you can easily download the source to the Nvidia drivers. The source is right on the same page as the binary drivers.

GLX SOURCE RPM
Kernel Source RPM

I'm not defending Nvidia here, because I still can't stand the license they use for their source code, but nonetheless you can get the source.

and anyway I would _never_ use a binary-only driver in an open-source kernel - hence my gripes with NVIDIA

Actually, you can easily download the source to the Nvidia drivers. The source is right on the same page as the binary drivers.

GLX SOURCE RPM
Kernel Source RPM

I'm not defending Nvidia here, because I still can't stand the license they use for their source code, but nonetheless you can get the source.

and anyway I would _never_ use a binary-only driver in an open-source kernel - hence my gripes with NVIDIA

Actually, you can easily download the source to the Nvidia drivers. The source is right on the same page as the binary drivers.

GLX SOURCE RPM
Kernel Source RPM

I'm not defending Nvidia here, because I still can't stand the license they use for their source code, but nonetheless you can get the source.

you worried me for a sec and I went to check the drivers here
nothing fancy in the search, it's the standard nForce driver page and they have
* Win98SE
* WinME
* Windows 2000
* Windows XP
* Linux

Right there. Now perhaps you only had Win95x to go from, but I think Win98SE is still a good solution for me...

That is 100% unacceptable and anyone with a brain will not use their hardware until they change their policies on giving us developers documentation.

Well, zealots can stick to "open" crappy, out-dated, and unmaintained stuff, and non-zealots can stick with working, timely, stable stuff. Usually, I let practicality choose instead of politics.

You know why 3D still generally sucks on the PC?

Interesting, I've never noticed that. Compared to what? Game consoles that are built solely for churning polygons, or the latest flick from Pixar?

Stupid greed.

Imagine that! A company wanting to protect the hard work it has put into their products! And on top of that, they want to turn a profit! How disgusting!

ATI makes good products but I still have to give the nod to NVIDIA because of their all-in-one drivers that still support older cards. I installed the latest drivers on a 3 year old TNT chipset (Diamond Card) and actually noticed a performance gain. So if you are using an older (NVIDIA TNT/VANTA on up) video card, try the latest drivers (Detonator 28.32) they offer improvements across the board.

Nvidia does this too. The call it Lightspeed Memory Architecture II.

Instead of fudging around with names like ATI does, they've simply decided to follow 3DFX's naming scheme and simply name their cards GeForce(n + 1).

But they do this so badly. 1 -> 2 was just an increase in clock rate. 3 was a new generation. 4 is a clock rate increase -- except for the G4 MX, which is SLOWER than any of the G3 cards. Stupid.

When its all said and done, I have to place my vote for nVidia, hands down. There are many reasons for this... howerver this is the most compelling...

nVidia Drivers page link

• Windows 95/98/Me Drivers
• Windows XP/2000 Drivers
• Windows XP 64-bit Drivers
• Windows NT Drivers
• Linux Drivers

ATI Drivers page link

• Windows XP
• Windows ME
• Windows 2000
• Windows NT

At home I run about 7 computers, a mix of linux winXp 2k and 98. The fact that my geforceX cards can and will run great in all of the above os's using proper driver support is all I need to buy from nVidia. Good customer support, and good OS support. That will bring in my dollars...

NVidia's developer site is why they will win the GPU war. Only because they help developers by prodiving an extensive forum in which they can educate themselves about their technologies. I recently started researching vertex programming, I went to NVidia's site and they had a entire SDK dedicated just to it. I haven't see anything like that on ATI's site. Keeping the people that develop for your hardware informed is the only way to win support, ATI hasn't realized that yet.

Unless I'm horribly mistaken, this claims their cards support Dimension Technologies 3d lcd displays. Their monitors use a single lcd but have special optics that makes alternating columns of pixels visable to each eye.

why the hell is everybody so intent on making some sort of BE/Linux hybrid?

Not to "save" the BeOS legacy/religion/apps obiously, but to save the linux kernel with all its drivers/features/fans/developers/sponsors/bouty from becoming a platform used for running nothing but posix webservers on headless pc hardware while it can be better (in design) then OSX for (even old) pc hardware.

This BefrankensteinAtOS is just a step toward what is my dreamworld:

- a cheap Nforce like mainbord with onboard graphics(nvidia, nuff said),audio(dolby 5.1 encoder),network(100mbit is 100mbit) and firewire (usb is now a "legacy connector" ;-))

- A dvb-c card

- two or four Clawhammer cpu`s

- Cooling that makes sense, not noise

- a linux-based kernel that loads directly from eeprom instead of an ugly old bios that doesn`t even understand todays harddrives. but still load ms-dos 3.00

- no more X, just every bit of experiance nvidia has with performace drivers

- A really fast gui, just try going back from Be`s Beos to windows

- a simple gui and cli shell that doesn`t eat more reasorces then it offers functinality but has a noice look and feel

- configurable translators

A filesystem that is fast, doen`t need complex journaling couse the oswrites metadata in a recoverable order and the hardware is fast enough to offer reasonable fast recovery anyway and has optional metadata (like the BeFS mime filetype)

I think this is really close to what others on slashdot want, note the lack of "evil" technology (except for perhaps nvidia).
After reading it back I found it also lacks girls and a social life but then again you can`t have it all ;-)
I guess for now I will have to do with the dano leak....

If you're willing to spend the money to get the speed, the nVidia Quadro4 900XGL is the current SPECviewperf record holder, supports two displays (2048x1536 each, better than the XVR's dual 1280x1024), and costs well under half the XVR-1000. It also supports stereo viewing and a programmable vertex & pixel pipeline.

True, its DACs are 24 bits instead of 30 bits (SGI workstations are still the go there, with 36 bit RGB DACs), but the NV30 may change that. It also does multisampled anti-aliasing (currently 9-tap 4-sample, though older drivers did offer a 16-sample mode too).

actually, according to this article, you can do it in real time. of course, that doesn't factor in the time spent re-rendering each frame to get the PERFECT aki ross porno film, which is factored in, according to that second article.

• Vertex processing can (and often do) do lighting and coordinate transformations, but it does far more than that. It can be used for anisotropic lighting schemes, matrix blending/skinning, keyframe interpolation, surface deformation, various procedural lighting & texturing approaches, even pseudo-motion-blur & complete particle systems. Take a look at this pdf for some of the many uses found so far.
• Fragment processing is more for new ways of combining textures, fancy bump/reflection mapping, or creating procedural textures from scratch. You can do relatively complex mathematical operations (think "massively parallel SIMD") - even cool stuff like using textures as multidimensional lookup tables for further texturing. More than just "better access to texture memory".
• The pack/unpack processors are actually pixel pack/unpack processors, and AFAIK unrelated to vertices. They're used for encoding/decoding the myriad of possible formats of image data from the host (e.g. textures). OpenGL currently copes with a large number of possibilities (RGBA, BGRA, 32 bit, 48 bit, floating point data, different numbers of channels, etc), but a programmable processor will simplify all this, and also allow for more exotic encoding schemes like the various 2D and 3D texture compression formats around. One of the stated goals of OpenGL 2.0 is to reduce the huge number of vendor-specific extensions. A lot of those extensions deal with accessing textures.

All this will be done in software (although fragment processing is notoriously slow to do in software), but hardware already exists that does programmable vertex & fragment processing. It wouldn't surprise me if programmable pack/unpack hardware also existed on modern GPUs, and was just waiting for an API to expose it.

It's not like your old card is worthless, some of us mortals still get along with 550mhz Pentium III's and TNT2's

Some of us get along just semi-fine with 500mhz celerons and generic Intel graphic cards... :)

Speaking of which, nVidia's web site has a performance analyzer that compares your CPU / Graphics Card combination against similar setups taken from a benchmarking database (and it's also a page that probably everybody knows about.)
It estimates what your computer's new performance level would be for each graphic card in their product line, should you buy and install it. (A GeForce3 would supposedly increase my computer's performance to 1179% of what it's now.)

And 20fps/640x480 in CS is fine--not like cool people play anything besides HL, anyway... ;)

Squid
Wolfman (i guess this is the best)
Tidepool

Looks like they had some spelling errors on some of the videos (they spelled content as contnent).

Squid
Wolfman (i guess this is the best)
Tidepool

Looks like they had some spelling errors on some of the videos (they spelled content as contnent).

Squid
Wolfman (i guess this is the best)
Tidepool

Looks like they had some spelling errors on some of the videos (they spelled content as contnent).

It looks like it's being pushed back to February 6th. I can only guess that's what's being announced on Nvidia's website.

The new Doom likely will require a no less powerful chip than the soon-to-be-released Nvidia GeForce3

Obviously Nvidia is lying, when they claim to have already released this chipset. :)

No they're not; you on crack, boy? The GLX driver's only available as a binary. Only the NVdriver has the source code available for it, and that's a simple pass-thru driver that hands stuff back and forth to the GLX portion. Look for yourself. Open Source my ass..

nVidia only makes the Geforce3 and Geforce2MX for the Apple. Check out their products page. The dude probably got confused between G4 and Geforce. There's probably a Geforce2 in that thing. And everybody knows that the Geforce2MX are pretty shit. And 1.1 billion textured pixels, as Apple claims in their add, is about par for the Geforce2MX.

nVidia only makes the Geforce3 and Geforce2MX for the Apple. Check out their products page. The dude probably got confused between G4 and Geforce. There's probably a Geforce2 in that thing. And everybody knows that the Geforce2MX are pretty shit. And 1.1 billion textured pixels, as Apple claims in their add, is about par for the Geforce2MX.

Or, you could lose the conspiracy theory and enter the real world. nVidia will not release the source to their drivers for one simple reason -- they have a lot of intellectual property tied up into those drivers, property they developed by spending millions in R&D funds. Opening the drivers is simply an invitation for their competitors to steal all their hard work. Maybe that's fine if you subscribe to RMS's unreachable utopia where no proprietary software exists (and nobody goes hungry, and nobody shits, and we all sit around singing filk songs at morale meetings ...), but here in the real world that's the perfect way to bankruptcy.

So, you say, why don't they just give us the specs to the boards, if they won't open the drivers? The answer here is two-fold. First, it can easily be dismissed by the IP argument above. But that's a cop-out. The real reason is because nVidia uses a unified architecture that allows them to write drivers that will work on any of their cards, from the oldest Riva TNT (not the Riva128 or earlier) to the latest GeForce 3 ti500. Releasing register-level information would undermine that process, and generate many different, incompatible drivers. I for one like to know that regardless of what nVidia-based graphics card I have, I can always go to www.nvidia.com and get drivers that will work. So why don't they release the specs to the layer above the register-level hardware? Intellectual property :) (hey, you knew it was coming.)

As for underperforming drivers, that's a by-product of nVidia's aggressive production cycles (where they generally try to have a new product or a refresh of the last product out every six months). They learned their lesson way back in the day, after nearly going under because they took so long on the nv1 (oddly enough, Sega bailed them out by contracting nVidia to do the graphics in the Saturn, and now Sega is the one in financial trouble and nVidia has moved to a different console manufacturer ...). If you only have six months to get your new hardware or hardware refresh out the door, you don't have much time to work on drivers. However, driver development is always happening (just look at the frequency of "leaked" alpha and beta drivers). And on top of all that, and as a by-product of the above unified design, all owners of nVidia products (well, again, anything RivaTNT1 or newer, anyway) benefit from these driver advances. Two years after buying a TNT2 Ultra board, I was still able to get a performance increase simply by downloading the latest drivers (well, I run a GF3 now, but because of nVidia's aggressive driver development, my TNT2 latested much longer than a comparable 3dfx board for example).

Point: You need to learn how nVidia runs their business (and it's a good lesson to learn, as nVidia went from near-bankruptcy to insanely successful in only a few short years) before you go promoting conspiracy theories with no basis in reality.

My question resumes...When will the MIT X Consortium sue Microsoft over patent infringement for the use of XBox? XBox is a term used on Unix boxes running X (X Windows System aka X aka X11). Many people have been using XBox to label their Unix machines as running X, and for the past 10 years we've been using XBox and Microsoft has violated intellectual property of the MIT X Consortium. mono doesn't infringe on Microsoft's .NET by being named LINUX.NET. Lindows didn't infringe on Microsoft Windows by being called Linux Windows. Microsoft is trying to steal our classification of being the first to use XBox to describe our PC Gaming Desktop.

The arachnologists are smoking dope and the politicians are doing it too!

Who needs to feel lucky on Google? NVidia makes it fairly easy to find Linux drivers. On their home page, under "Download Drivers", there's an item for 'Linux'. Not particularly hard to find, and (amazingly) it's in the logical place, too!

Who needs to feel lucky on Google? NVidia makes it fairly easy to find Linux drivers. On their home page, under "Download Drivers", there's an item for 'Linux'. Not particularly hard to find, and (amazingly) it's in the logical place, too!

Just because a card provides hardware support for a feature (such as npatches) does not mean that the software (eg games) that you're using is utilizing that hardware. I do not know of a single shipping title that's currently using npatches, and the GL_NV_evaluators extension was only released to developers a year ago. I would not consider addition or elimination of hardware support for npatches to be a deal-breaker when deciding what video card to buy, unless I was planning on writing software myself that utilizes that feature.

It's been my experience that the NVIDIA drivers are superior to the ATI drivers. I've been using an ELSA GLADIAC 920 GeForce3 board in my workstation for a year now, with the NVIDIA drivers, and have nothing but praise for both the hardware and software. I have had problems with the software drivers for the ATI RAGE LT Pro in my laptop computer.

Your TV set has a tuner, and your vcr has a tuner; that's why you can watch and record...

The ATI has a tuner. Your TV set has a tuner. Why, in this case, would you be unable to watch and record? I use Nvidia's Personal Cinema and do this all the time.

it will not let you pause live tv, in fact it writes nothing to the hard drive unless I ask it to. And lastly, (as I understand it not every PVR does this) it lacks a 30 second/ skip ahead button.

Both features are present in the Personal Cinema and accompanying software. ATI's latest (Radeon 8500 "DV") iteration claims the same features and more. TiVo does not have 30-second skip, most attribute this lack to heavy investment from the TV Networks.

umm maybe it's just me, but I always thought that the source RPMS provided by NVIDIA actually contained source code. And as far as I know those things are indeed drivers. Possibly not windows drivers, but that doesn't matter.
You can see them here.

With its second generation transform and lighting capabilities, per-pixel shading operations, a fill rate of up to 350M pixels per second and an internal 8X AGP interface, the integrated GeForce2...

I didn't mean to imply that the only reason the integrated GeForce2 is 8x (I said 6x, my bad) is because it's in the IGP - merely that it is equivalent to 8x AGP, as a consequence of its location and nVidia's nice work.

You have no idea how hard I found it to respond to your comment in a civil manner. Next time, you try the whole "civility" thing.

It was a incomplete comparison

It really should have been a VIA KT266 vs VIA KT266A vs NVidia NForce vs AMD 760 vs SIS 735 vs SIS 745 vs ALI MAGiK 1 / M1647 (both revisions)
comparison.