Slashdot Mirror
3DLabs Launching New GPU
h0tblack writes "...or VPU as they've seen fit to call it. The Register is reporting that 3DLabs will be releasing the P10 later this year. It's targeted at workstation and gaming markets with OpenGl2.0 and DX9 drivers having been seeded to developers already. Could be interesting as 3DLabs have been one of the key players in the development of OpenGL2.0. The P10 has over 200 SIMD processors throughout its geometry, texture and pixel processing pipeline stages to deliver over 170Gflops and one TeraOp of programmable graphics performance together with a full 256-bit DDR memory interface for up to 20GBytes/sec of memory bandwidth. More info can be found in the press release." There are also examinations of the new chip on Anandtech, Tom's Hardware, and no doubt many other hardware sites too.
Its look like some one try to re invent AMIGA...
Damn why we spend these bucks that PC architecture...
Capitalism...
[My english is better than most other people's Turkish, so please point out mistakes politely. Thank you.]
Press releases can't render anything, to the best of my knowledge. I'll reserve judgement until I get my hands on a review unit. However, this can only be a good thing. Competition drives prices down and features up.
Hopefully, this will not turn out to be a flop like the Permedia. I remember waiting for that and proclaiming that it would be faster than anything else when it came out. *cough* NOT *cough*
The specs were great, but the actual implementation and drivers, well, sucked hard.
'He was a dreamer, a thinker, a speculative philosopher... or, as his wife would have it, an idiot.' - Douglas Adams
I've been waiting for the next 3DLabs chip for a long time! The last experience with Permedia 2 = Rock *solid* drivers + 100% OpenGL compliance + low power consumption....
If Creative makes a card with them with OSS Linux drivers and *NO FAN* then I'm sold!
This is an article about two unreleased graphics cards, one $600, one $900. No, that's not a typo, these graphics cards cost as much as a nice Athlon system. These aren't targetted at gamers, they're targeted at workstation users, and fuckwits.
Speak for yourself, I'm a gamer, and I'm more than willing to fork out $900 for a good video card. Hell if I spent $700 on the Geforce1 DDR when it first came out, why the hell not spend $900 on a fully opengl accelerated card? I've seen the current generation of High end cards from 3DLabs, and if this new generation is anything like the current, it's worth the $900 for gamers.
---
Programming is like sex... Make one mistake and support it the rest of your life.
Extra! Extra! Linux ported to GPU!
Really, these things are getting massively more complicated than your ordinary P4 or Athlon.
And think; There's one less layer between the OS and the framebuffer!
"Draco dormiens nunquam titillandus."
Beyond3d, home to many respected (and notorious ) workers at various 3d companies such as nvidia, ati, and bitboys are discussing this right now.
An Education is the Font of All Liberty
One great feature is the virtual memory, which should improve the appearance of depth and richness of models. I wonder how much more textures designers can cram onto a model? Does this mean more games will start to utilize multi-pass rendering and ID will rewrite their engine once again for models with massive amounts of textures? I haven't kept up with the latest trend in 3D game technology, so someone more informed can tell the rest of us?
When Geforce3 came out it didn't have much of a clock speed increase, but boasted features that if taken advantage of by the developers would make the games look *MUCH* better. And yet, the only trend in the gaming industry that I've spotted is cranking up the poly counts.
Ñ'
I paid CAN$410 to get a GF1-DDR card in Toronto, right after it got here. Granted, it was from a small PC shop, not an electronics store with a %50 markup.
No, that's not a typo, these graphics cards cost as much as a nice Athlon system.
I don't care. It's still a lot cheaper than a top of the line SGI workstation.
The ratio of costs for all the parts in a typical PC)
(motherboard:CPU:disk:powersupply:OS:graphicscard
have shifted some over the years. More accurately, though, as the performnce of certain keys pieces has increased to adequately fulfill the needs of the users, it's natural to start looking to satisfy unmet needs.
An OpenGL card like this would be wonderful for scientific visualization, CAD, CAM, etc.
While the price is an important point, in my market $600-$900 is not a big deal.
"Provided by the management for your protection."
Well - is it? If the boards will be 600 bucks in december, they'll start coming down around the time they need cheap boards for PS3. I'm guessing about 2004-2005?
Stop the brainwash
It's worth pointing out that Creative has bought 3d labs, and Creative's CEO Sim Wong Hoo has every intention of taking 3d Labs out on an aggressive push into the consumer 3d market. See article.
Sometimes you have to read between the lines.
3D Labs was recently purchased. I won't bore you with the details but the purchasing company was none other than Creative Labs. Creative Labs' focus has not historically been the professional workstation, it has been mainstream consumers.
Although the initial cards brought to market will be targetted to the workstation market, it is highly likely that Creative Labs will leverage this technology to produce a card targeted to the gamers market. One of the benefits of the architecture is that it can achieve a larger number of textures with a more limited amount of memory through caching. This will allow Creative Labs to trade off memory size for memory speed in the gamers market.
The specs were great, but the actual implementation and drivers, well, sucked hard.
Sure, the Permedia wasn't the quickest card on the block in its time, and neither was the Permedia 2 nor the Permedia 3...
But both the NT and Win9x drivers were absolutely 100% rock-solid, the OpenGL implementation was flawless and very, very fast, and the card supported a whole bunch of features that no other consumer-level chipset at the time supported, like anisotropic filtering, or multiple video overlay windows at once. The RAMDACs were really good on the Permedia 2 also - razor-sharp, much much better than the TNT2 I ended up replacing it with. It was also rather faster at GUI acceleration than the TNT2, which was a surprise and a disappointment.
Really it was a semi-pro card at consumer-level prices. It would never have been the card you bought if you wanted the ultimate Quake framerate, but it absolutely oozed quality.
It's the only graphics card I've ever used that hasn't annoyed me in some way, be it dodgy image quality (NVIDIA, S3), unstable drivers (ATI, NVIDIA), bus latency greediness (NVIDIA, S3, Matrox, often leads to choppy, stuttering audio), or just being dog-slow (all the usual suspects - hello Trident, earth calling). I've never used a 3dfx card for more than a few minutes so I can't really comment on them, but I suspect their poor OpenGL support would have annoyed me greatly.
If only 3Dlabs had 3d-accelerated Linux drivers (preferably open source) I'd buy another one in a heartbeat. I've been disappointed with every other card I've had since my Permedia 2...
High end? MySQL? BWAHAHAHA! Good one.
how about we just give you a GF2 with the XF86_SVGA server and we'll just RIP THE FAN OFF FOR YOU!
there you go! you're welcome!
oh, you DIDN'T want it to catch on fire...
-c
...where all you have are CPU cards with whatever specialized adapter is necessary to provide the apporpriate electrical connectivity to peripherals.
Each card is a basically a CPU board with its own memory. The common bus between cards is really a switch to limit card-card contention. One card is the bus master running the kernel. Processes can be shuttled between CPU boards as processing power is available.
The thing is we're getting to the point where just about every PCI device has a CPU on it (NICs with encryption/acceleration engines, RAID cards). Why not just put high-speed general purpose CPUs on the cards and use it as a highly integratable/segmentable cluster?
The actual kernel could do more scheduling and less work, since the "NIC" CPU card could theoretically run large parts of the IP stack in addition to the NIC driver, as an example.
...was the first PC-market, full programmable graphics chip, as far as I know.
Any website proclaiming full programmability as new or revolutionaly is simply demonstrating a lack of historical knowledge. 34010/34020 based boards competed with the first-gen fixed function graphics accelerators for Win 3.x, but couldn't compete on price/performance with the fixed function BitBLT engines from S3 et al, and the flexibility of being fully programmable meant nothing to PC users who were accustomed to dumb EGA/VGA cards.
The article on Tom's mentions the end of VGA as the common denomenator for video, but mentions no replacement. So what's the new standard? When it comes to a standard video format, we really need to have SOMETHING common to all (most) platforms...
-- Minds are like parachutes... they work best when open.
how many next-gen cards have come out since bit-boys said that they've reached silicon stages are are persuing a fab plant? hahahaha... Oy!
-Christopher Wu
http://www.christopherwu.net/
blockquoth the poster (evermore with emphasis added):
Now then, the emphasized bits beg the question: Why has Creative gained and lost its footholds in these areas?
For this Creative customer, the reason is and has always been (across all product lines) one, very important issue: Software.
When and where the Creative development machine manages to mate decent, uncluttered, non-glitzy, tweakable, and trouble-free software (very very seldom IMO/) to the excellent-to-amazing hardware that they are deservably famous for, the results have been very good indeed.
However, in the normal course of events, Creative's hardware ships with installation, driver, ancillary programs, updaters, bundled "features", and enough just outright useless crap to annoy any self-respecting consumer. And while I admit that this occurs largely on the Windows platforms, you should admit to yourself that that's Creative's largest area of concern. Fortunately, they haven't yet figured that they could push for inclusion of enough Creative ad-ware to sicken a telemarketer drone into the driver packages for other platforms.
So, in this reader's experience, the issue is simple. Too much software that users don't want or need, too many features that won't work without all the glitzy junk (anyone like using the LiveDrive product, it's great, but the software to make it worthwhile--remote control--is a cast-iron bitch, crashy, seldom-updated, and too tied to useless trash in the installation). Now these issues seem somewhat prevalent along Creative's product lines, and they're killers.
Fortunately, the answer is simple. Creative needs to give the people who buy their hardware good, stable, and full-featured drivers without the need for a dozen attendant Creative-logo-displaying bits of crapware. If that parts' impossible, then it'd at least be nice to be able to grab reference drivers from the chipset manufacturer (how many people don't use NVidia's Detonator drivers in favor of the card-vendor's?)
.
Failing those... license the hardware designs to vendors who'll give us good, honest, and stable software. Of course, they can always continue to lose business to the competition, afterall, it's . . . "good for the market".
OpenGL 2.0 addresses exactly your concerns - a vendor-neutral shader programming language, and this is precisely why you're seeing 3Dlabs pushing hard for it. It seems they will be first to market with a fully programmable graphics pipeline, and they need the software technology to go with it...
DirectX 9 also addresses the same issues and provides a standard shader language (actually DirectX 8.1 has a standard shader language already, but it lacks a certain amount of the programmability that will be present in DirectX 9), but there are a lot of reasons for the graphics card vendors to favour OpenGL over DirectX. For instance:
Hopefully OpenGL 2.0 will see a resurgence in OpenGL use. I don't like the idea of the 3D market being controlled by Microsoft, and I don't think the 3D vendors do either. Kudos to 3DLabs for leading the way!
I think that puts you very squarely into the "fuckwit" category, so the original poster was still right.
Well, it depends on who you ask. According to SGI, it's OpenGL 1.3, but a few companies call it openGL 2.0. OpenGL 1.3 does have some impressive advantages, so it doesn't really matter. Remember, OpenGL isn't just specifications, it's a library, and it works a lot better than directx releases. (i.e. anything can be rendered in software, so you don't need to mess with libraries everytime a game or card is realeased.)
"And we have seen and do testify that the Father sent the Son to be the Savior of the World"
1 John 4:14
If you're willing to spend $900 on a graphics chip, wouldn't it be easier to just get a dual processor motherboard? Why try to co-opt the graphics chip to run sql queries? MySql is multi-threaded and can already use multiple cpu's if they're available.
And what, pray tell, does armed with nasm mean?
What exactly is one sample antialiasing? A blur filter?
And the kernel option of the future is...
Processor type and features
...
Floating point emulation? [y/N]
Floating point acceleration via 3dLabs VPU? [Y/n]
--TheOrangeSquid Is it any wonder things seem so awry? We swim in a sea of confusion and don't have to think to survive
It could also be because of the assets they claimed from 3dfx coming into play... This is the time when we are supposed to start seeing results from the influx of 3dfx tech from them...
we are all invisible unless we choose otherwise
Measuring it exactly is a little wonky. It's definately not 170 billion matrix multiplies. It could be 64+48, but most likely, it is they're counting 48 floating point multiply/accumulate (a mul and an add in one instruction) + 16 multiplies. For some reason, multiply-accumulate is easy enough that they can implement it as an individual instruction.
A deep unwavering belief is a sure sign you're missing something...
I've seen the current generation of High end cards from 3DLabs, and if this
new generation is anything like the current, it's worth the $900 for gamers.
The Wildcats deliver a whooping 9 fps in Quake. That's nine frames per second. I work in 3D animation and I'd love to have a Wildcat, but to play games, no thanks. Let's hope the new processor is a bit more gamer-friendly (like nVidia's Quadro4, for example).
And personally I'd never spend more than 300 on a gaming card (I would - and in fact have - on a professional card if I thought it was a good investment).
RMN
~~~
High end? MySQL? BWAHAHAHA! Good one
I'm pretty sure he meant high level, as in more complicated than.
--
Evan
"$30 for the One True Ring. $10 each additional ring!" -- JRR "Bob" Tolkien
Some programs out there such as Softimage Have been using reatime 3D API's to draw their widgets for as long as realtime 3D API's have been around. It has been using OpenGl to draw the widgets for at least 6 years.
This Wiki Feeds You TV and Anime - vidwiki.org