NVIDIA's GeForce GTX TITAN X Becomes First 12GB Consumer Graphics Card

Deathspawner writes: When NVIDIA announced its GeForce GTX TITAN X at GTC, no one was surprised that it'd be faster than the company's previous top-end card, the GTX 980. But what did impress many is that the company said the card would sport a staggering 12GB of VRAM. As Techgage found, pushing that 12GB is an exercise in patience — you really have to go out of your way to come even close. Additional reviews available at PC Perspective and AnandTech. The latter notes, "...from a technical perspective, the GTX Titan X and GM200 GPU represent an interesting shift in high-end GPU design goals for NVIDIA, one whose ramifications I’m not sure we fully understand yet. By building what’s essentially a bigger version of GM204, heavy on graphics and light on FP64 compute, NVIDIA has been able to drive up performance without a GM204-like increase in die size. At 601mm2 GM200 is still NVIDIA’s largest GPU to date, but by producing their purist graphics GPU in quite some time, it has allowed NVIDIA to pack more graphics horsepower than ever before into a 28nm GPU. What remains to be seen then is whether this graphics/FP32-centric design is a one-off occurrence for 28nm, or if this is the start of a permanent shift in NVIDIA GPU design."

Comments

purist != purest

[Anonymous Coward]

:)

12Gig

[Nightshade72]

You sure it's 12Gb and not 11.5? ;-)

Re:12Gig

[Anonymous Coward]

topkek!

Re:12Gig

[Anonymous Coward]

11.5GB?
Why not 11.18GB (rounded) or did you guess at the conversion rate it's (1000^3)/(1024^3) which is approximately 0.9313.
0.9313*12 is approximately 11.18.

Re:12Gig

[Thraxy]

Congratz! You win one internet!

Re:12Gig

[Anonymous Coward]

You sure it's 12Gb and not 11.5? ;-)

It's only a matter of time when systems are offered with more memory on the graphics card than on the motherboard.

Re:12Gig

[Anonymous Coward]

Whoosh.

Re:12Gig

[Anonymous Coward]

It is not the GB / GiB conversion, but a GTX970 "4GB" scandal from earlier this year.

Re:12Gig

[Anonymous Coward]

If you took the time to do a little research you'd find the only misstated piece of the specs(970) was the L2 cache size by 256k IIRC.

Either way on top that's not priced too horribly. I was fully expecting it to be near $2k.

Now to dig up some benchmarks.

Re:12Gig

[Shirley Marquez]

Still a little while to go, however. Anybody buying that card is going to have at LEAST 16GB on the motherboard, more likely 32GB or more.

To Quote Darth Vader...

[Scarletdown]

Impressive! Most impressive.

What portion of the memory is usable this time?

[Anonymous Coward]

So, is this a 12GB card or "12"GB card? Will it have 2GB of fast RAM and 10GB of crap behind a I2C bus which only exists for marketing reasons?

Re:What portion of the memory is usable this time?

[Fire_Wraith]

It's certainly a legitimate question.

On the other hand, as I remarked to a friend when discussing graphics cards the other day, it seems to me that none of the numbers on the cards really matter - RAM, Clock Speed, etc. There are so many variables that you might as well say that it has 12 GigaDrawing Cores and 256 SuperShaders with a 1.5 TeraTransit Hop Interval. What really matters is the final performance, using the universal standard measure of FoC(3), aka "Frames (per second) of Crysis3".

Honestly, when I look at graphics cards (and I'm currently doing so for my next system), that's what matters to me most in comparing them - looking at benchmark results among all the major games. Certainly Nvidia should be telling us up front how the architecture works, and that you have 3.5GB of main/fast memory or whatever, but benchmark statistics from 3rd parties seem to me to not only be more important, but not exactly (or at least not easily) fakeable.

That said, it's interesting to me that the benchmarks I've seen for this card mark it as inferior to the 295X2, which is not only almost a year older, but significantly cheaper. I'm personally hesitant to go with AMD, as my current experience with AMD drivers on my desktop has been downright horrible, compared to a relatively painless experience with my current laptop running an Nvidia card, but I have to wonder what's going on when Nvidia comes out with something like this, a year later, and at seemingly worse performance.

Re:What portion of the memory is usable this time?

[Anonymous Coward]

What really matters is the final performance, using the universal standard measure of FoC(3), aka "Frames (per second) of Crysis3".

Except it's not. Not even close. Some of us have never even played a Crysis game.

Re:What portion of the memory is usable this time?

[rudy_wayne]

What really matters is the final performance, using the universal standard measure of FoC(3), aka "Frames (per second) of Crysis3".

Except it's not. Not even close. Some of us have never even played a Crysis game.

But it's still a good benchmark even if you never play any of the Crysis games.

If the card gives a good performance in "Frames (per second) of Crysis3" then that's a reasonably good indicator that you'll get good performance in other applications -- it's at least better than AMD or Nvidia's meaningless marketing doublespeak.

Re:What portion of the memory is usable this time?

[AK Marc]

Except it is. Because if you never play a game, why are you buying a gaming card? And games that care about FPS are more alike than the artificial tests that measure the pipeline bandwidth, or refresh speed in a way that doesn't correlate with actual game play. Whether you are playing CS or something else doesn't matter that it's a useful standard. And I've not seen any tests that correlate better with actual gameplay across cards, makers, and different games than FoC.

Re:What portion of the memory is usable this time?

[Anonymous Coward]

On the other hand, as I remarked to a friend when discussing graphics cards the other day, it seems to me that none of the numbers on the cards really matter - RAM, Clock Speed, etc. There are so many variables that you might as well say that it has 12 GigaDrawing Cores and 256 SuperShaders with a 1.5 TeraTransit Hop Interval.

Now you did it. Don't you remember that NDA you signed?

Re:What portion of the memory is usable this time?

[hairyfeet]

Hell you can't even use Crysis 3 by itself as its been shown to run better than it should on some cards, worse on others. That is what happens when you run a poorly optimized game.

Frankly I wish more would do like Tek Syndicate (of course they aren't taking money in the form of ad contracts while many of them are getting huge checks from at least one) where they choose a half a dozen popular games that require some muscle and then see what you get, as IMHO this is a hell of a lot closer to what one would get IRL than "run one benchmark, run BF4" like the others tend to do.

But is there even a point in having 12GB of VRAM at this time? Most games aren't even hitting 4GB and by the time you have games hitting 12GB the GPU is gonna be so out of date it might as well be an FX5900, since its lousy FP means the CUDA guys aren't gonna want this,. So other than "look at my massive ePeen" is there a real use for 12GB now?

Re:What portion of the memory is usable this time?

[Shinobi]

Yes, there is a point in having 12GiB RAM on the card: There are people who can make use of it, even with existing applications. It's also a good way of driving development. This also ties in with your cluelessness about Compute performance: while DP is low, not all Compute tasks need DP. Signal processing for example is a field where DP is a waste. Take music for example. Softsynths that do physical modelling require a lot of resources, both in terms of processing and RAM, but you only need single precision(Until the end, when it's converted over to integer). Now, with this Titan card, you have massive SP compute performance, AND lots of RAM to work within.

There's also real-time simulations, where this card with all that RAM and the Universal Physics Solver will enable to run high frame-rate sims at decent resolutions and decent detail, with a good approximization of the physics involved, which is useful during design phases for example. And since it's a single GPU, development becomes easier.

Re:What portion of the memory is usable this time?

[rahvin112]

Trivial to fake. They put things into the drivers that if it recognizes a benchmark game it turns down or disables certain features to boost frame rates, even where the driver and/or game claims different settings.

Both AMD and Nvidia have been shown to do this.

Re:What portion of the memory is usable this time?

[Anonymous Coward]

Because if you never play a game, why are you buying a gaming card?

Some reasons.

Re:What portion of the memory is usable this time?

[ShanghaiBill]

But it's still a good benchmark even if you never play any of the Crysis games.

It may be a good benchmark for graphics performance. But many of us use GPUs as compute servers. If you are using it for cryptanalysis, than raw performance is important, and memory performance and I/O is not important. If you are using it for neural net training, then memory and raw FLOPS are important. Nvidia's CEO specifically mentioned neural nets as a potential big market for these devices.

Re:What portion of the memory is usable this time?

[viperidaenz]

So unless you're a GPGPU developer, you should buy the card that the application you use was designed for, since the variance in performance is huge, with some GPGPU video encoders performing worse than CPU implementations.

Re:What portion of the memory is usable this time?

[Anonymous Coward]

Not for me, who doesn't need a card that does well in Crysis 3, but better in other things.

What if there are two cards with the exact same price but their performance is 10% or more different? How can I be sure which one does better for my needs?

Can I rely on one game doing the same thing as other games?

Re:What portion of the memory is usable this time?

[hairyfeet]

Actually it shows YOU are fucking clueless to the CUDA scene since page after page on any CUDA forum is dedicated to "Which cards have the best DP" since..surprise surprise, a LOT of HPC tasks require....drumroll...DP!

If you wanna shill (driving development, really? You wanna trot out vertical synergy for a buzzword bingo?) go right ahead, just don't piss on us and tell us its raining, as the major apps that need large memory sets? Yeah kinda need DP and games haven't even hit 4GB other than non official third party high res textures.

Re:What portion of the memory is usable this time?

[Fire_Wraith]

Yes, and the reviews I've been looking at included a number of games, including Crysis 3, Bioshock Infinite, BF4, the latest Tomb Raider, etc, because you need to see a wider range to get a general idea of the performance. I've actually never played Crysis or any of its sequels, but it's sort of infamous as being a massive graphics power hog, to the point that "My system gets X frames per second of Crysis" became something of a bragging point of how powerful your gaming machine is, hence why I used that as the example in my post.

Re:What portion of the memory is usable this time?

[BlueBlade]

RAM is very important if you use high resolutions. If you game in 1080p, then yeah this won't tell you much. If you have a 4k monitor though, 3GB isn't enough so you can at least look at the RAM to narrow your selection, then look at benchmarks.

Re:What portion of the memory is usable this time?

[Anonymous Coward]

But is there even a point in having 12GB of VRAM at this time?

Off the top of my head right now..
Video screen capture / recording with 0 delay
Raycasting
High resolution procedural textures

Re:What portion of the memory is usable this time?

[Anonymous Coward]

Not really. CryEngine is horribly optimised.

Re:What portion of the memory is usable this time?

[Anonymous Coward]

You're trying to make a argument for nVidia... but in your statement, you're comparing your experience of a unnamed laptop GPU to a unnamed AMD GPU..

You also didn't state any of the other computer stats of either system. You know it doesn't matter if you have a $2000 GPU if the rest of your system components are crap. For all we know your AMD setup could have been using a ATA100 with 256 MB SDRAM and a CPU to match. Since the nVidia card you're referring to is in your laptop, it is clear you didn't have a similar spec'd AMD card in the same laptop.

If you're going to use your experiences to make a argument for one or the other, you should at least provide all of the information instead of just blank statements with no information to back it up.

Re:What portion of the memory is usable this time?

[drkim]

You are talking about game benchmarks.

For people editing, doing F/X and CG work, having all those CUDA cores helps (Photoshop, Adobe Premier, Avid, and AfterEffects all can use the CUDA cores for crazy fast rendering).

And, all that VRAM helps when working with HD and 4K video, especially multiple layers of video.

AMD doesn't yet offer CUDA processing.

Re:What portion of the memory is usable this time?

[Luckyo]

12GB card apparently, because this seems to be upsized 980 rather than 970.

But if they were to ever make Tital Z LE or similar cut down version to utilize their not fully operational dies, one would have to look very hard into just how much of real memory and how much "marketing memory" such a card would have.

Re:What portion of the memory is usable this time?

[PPalmgren]

I'm personally hesitant to go with AMD, as my current experience with AMD drivers on my desktop has been downright horrible, compared to a relatively painless experience with my current laptop running an Nvidia card, but I have to wonder what's going on when Nvidia comes out with something like this, a year later, and at seemingly worse performance.

I've actually found the reverse case lately, for my usage. I have a R9 290 in my HTPC and a Geforce 770x. Every time I update my 770x driver, it moves my taskbar to the other screen and resets window sizes, incredibly frustrating and something that shouldn't happen in 2014. Its been a problem for at least 4 years through multiple OSes and different installs. I had this problem on a GF 250, and I've reported the bug multiple times. I also experienced CTDs in Battlefield 3 and about 3 other games, usually associated with driver crashes, plus a lighting bug in FarCry 4 where the lighting lingered after moving, making the game unplayable. Then there's AC Unity which was a trainwreck.

My big nitpick with the AMD driver is an annoying cursor bug I've experienced in dota 2 which happens on multi-monitor setups, not sure if they took care of that yet because the AMD card is now in the HTPC. Every once in a while the cursor icon would screw up and look either grainy or sometimes look like a black comb or something, a visual bug. Other than that, I haven't had any issues with AMD drivers.

Re:What portion of the memory is usable this time?

[Anonymous Coward]

So, since Shinobi's point is that some people can make use of it, and your counter point is that he's wrong, you are saying that NOONE can make use of it. I'd like to see proof of that, please. Go away troll.

Re:What portion of the memory is usable this time?

[Anonymous Coward]

The possible issue with the 295X2 is that with a multi-GPU solution, you rely on SLI/Crossfire profiles in order to get that performance. Like with Far Cry 4, where AMD users waited 4 months to get a profile. In the meantime, your performance is closer to that of a single R290X.

Re:What portion of the memory is usable this time?

[hairyfeet]

But it is soooo poorly optimized (BTW its Crysis 1, Crysis 2 and 3 can actually run on netbooks, just FYI) its like bragging "My truck can drag a boat anchor better than yours"....oookay, why would I WANT to drag a boat anchor? Hell Crysis is so much of a bad joke there are guys with HD7970s (something like 10 times more powerful than max spec) that have to use the low res hack for the last level just to make the damned thing load!

Nope I would still argue the best way to handle it is what Tek Syndicate does, which is take a handful of the top 20 games that really push a GPU, Skyrim on HD, Metro Last Light HD remix, BF 4, etc and then show you what the average run is, because there are plenty of cards that can run one game decently but run others like ass.

Re:What portion of the memory is usable this time?

[Anonymous Coward]

Yes, this exactly. The problem with benchmarks that try to rank performance on a linear scale is they can only measure a specific use-case, or do a weighted average of different use-cases. If a particular benchmark became the industry standard way to compare performance of cards, then they would just start optimizing everything for that benchmark, which isn't a good outcome. There is no way to boil it down to a single number. There ought to be a small number of somewhat orthogonal performance measurements that are industry standard. Seems like a really hard problem to get everyone to agree on what to measure and how though.

Re:What portion of the memory is usable this time?

[Anonymous Coward]

driving development, really? You wanna trot out vertical synergy for a buzzword bingo?

I can see how that might sound like buzzword bullshit, that's really how it works. Many games are developed to the highest spec'd consumer cards available, knowing that by the time the game is finished that kind of card will be common. Development is driven both ways. If it wasn't for that, there would be a catch-22 where game developers aren't going to write a game that requires hardware that isn't available, and hardware makers aren't going to produce cards that no existing game can take advantage of.

Plus, games aren't the only market for GPUs these days.

Sigh

[ledow]

So basically the card is overspecced for no sensible reason and you can't fill that amount of VRAM even at 8K with 8xFSAA (and when you do that, you get 9fps). Even SLI'ing 4 of those together won't get you 40fps at those res.

So the extra VRAM is entirely, completely pointless and they could have just supplied it with 8Gb (or less!), reduce the price slightly and had done with it and nobody would have noticed any difference.

Selling point of our product: "We've put in useless shit that you'll never be able to use anyway! And charged you a premium for it!"

Re:Sigh

[Anonymous Coward]

i dunno, i could probably use up that 12GB pretty quickly with CUDA.

wait, were you talking about Modern Gears of Halo or something? people still play those silly things?

Re:Sigh

[demachina]

Deep Neural Nets will use it, at least the very big, wide, deep ones will.

Re:Sigh

[wickedsteve]

Fuckin 9fps? But, I need at least 120fps for my 3D Vision!

Re:Sigh

[Goragoth]

In case people are confused it is important to point out that the Titan cards aren't aimed at gamers. They are partly a PR stunt for Nvidia (look, we make the biggest, baddest GPU out there), and partly of interest to developers working in graphics research (either developing tech for next gen games, GPGPU research, fluid simulations, and other projects). When you are raycasting massive voxel scenes for example, the 12GB can look rather attractive.

At the end of the day it is very much a niche product, and calling it a "consumer card" is perhaps a bit of a misnomer. If all you are looking to do is to consume content (i.e. play games) this isn't the card for you, just SLI as many GTX980's as you can afford together and be done with it.

Re:Sigh

[gman003]

Compute might use it. The Titan was traditionally both the top-tier graphics card, as well as the entry-level compute card. They've slashed FP64 performance with this iteration, but FP32 performance is still sky-high, and they're pushing situations like that for using this as a compute card.

Re:Sigh

[Shinobi]

I know some people who are drooling all over this card for various real-time simulations. The Unified Physics Solver and 12GiB RAM on the card will allow them to push a combination of good graphics and good enough physics, at decent frame rates in real-time, all on a single card. It also makes it easier to develop sim solutions.

Re:Sigh

[retchdog]

it's not a bad strategy for the gaming market either (not great, but not bad). it's a developer gateway to including physics simulations in games. rather than cramming in even more pixels (at the point where most people won't even notice them) or cosmetic effects, even adding fluid simulation can create a more significant market differentiation than more anti-aliasing. pushing these cards on the "early-adopter" (read: sucker) crowd opens that door.

Re:Sigh

[dugancent]

Titan cards aren't aimed at gamers

Correct. They are aimed at suckers.

Re:Sigh

[Kjella]

So basically the card is overspecced for no sensible reason and you can't fill that amount of VRAM even at 8K with 8xFSAA (and when you do that, you get 9fps). Even SLI'ing 4 of those together won't get you 40fps at those res.

You do realize that 8K @ 12GB is the same as 4K (25% the pixels) @ 3GB? Are you claiming the GTX970/980 is equally overspecced at 4GB(-ish)? I don't think we have 8K monitors yet but make a triple UHD monitor setup and I think you'll make quad-Titan X sweat.

Re:Sigh

[Anonymous Coward]

Very much correct, 12gb is absolutely useless for gaming, they could've cut it down to half that without a noticeable performance loss on any game out today. But as a PR stunt it's effective, people will buy it not knowing any better regardless and say they have "12gb of ram!" Just like they'll buy 32gb of DDR4 3600 ram and then use it for nothing other than playing Call of Duty, even though 8gb of DDR1600 ram would give them the same performance.

Re:Sigh

[sexconker]

You're not doing anything useful on a 12 GB Titan that couldn't do on 8 GB or 6 GB.

If you've bought some integrated solution that requires/prefers CUDA / nVidia cards you buy nVidia and piss the money away on Quadros.
Otherwise you go with AMD for compute.
Nvidia's double precision performance on their workstation cards is a joke (and almost completely absent on the Titans). There's a reason Bitcoin mining was done on AMD GPUs.

Re:Sigh

[sexconker]

The Titan cards ARE aimed at gamers.
Have you seen the reviews? Did you see the presentation today? Did you see the double precision compute performance? This is not a compute card.
Quadro = Workstation
GTX = Gamer
Titan = Gamer with more money than sense

Re:Sigh

[rudy_wayne]

"We've put in useless shit that you'll never be able to use anyway! And charged you a premium for it!"

That's called Marketing.

Re:Sigh

[sexconker]

For compute, multiple GTX cards gets you more performance/$ than the Titan, with the same "LOL DOUBLE PRECISION NOT GONNA WORK" caveat.
If you're not stuck with CUDA, AMD's offerings are a better choice.

This isn't a compute card - it's an idiot card. For both games and compute, both Nvidia's and AMD's standard "gamer" cards are a better value.
The only thing novel about the Titan X is 12 GB accessible by 1 GPU.

Re:Sigh

[UnknownSoldier]

Just because you don't understand the difference between the Titan's FP64 (float64) = 1/3 FP32 (float32) performance versus the FP64 = 1/24 FP32 performance of regular cards doesn't imply that everyone who buys Titan cards is clueless.

Re:Sigh

[plcurechax]

In case people are confused it is important to point out that the Titan cards aren't aimed at gamers.

Yes, the Titan series is an odd bridge between consumer price/ performance, and professional reliability (ECC RAM) and unhampered double precision performance at painfully professional level prices of the CUDA / GPGPU oriented Quadro and Telsa cards. (Telsa K20 to K80 cost $3500 - $5000 USD approx AFAIK)

So they are great alternatives for CUDA aware 3D graphics application users who traditionally can't afford a Quadro or Telsa card (are not professional movie / video-game studio artists or CAD designers), and students and researchers looking for low(er)-cost prototypes for developing CUDA / GPGPU software / experience. I assume any graduate CS/EE student studying parallelism / many-core hardware or software wants a Titan as an affordable alternative to the tuition-like pricing of the Quadro and Telsa cards.

I had considering putting the Titan X on my own personal wish list, until I read that the FP64 isn't in line with performance improvements over previous generation Titans.

Re:Sigh

[Kjella]

Actually that's exactly what this card is not, they've dropped FP64 performance and basically made a bigger, more badass gaming card. If there's any others who can use it, that's because they don't really need the compute features. This is like Intel's "Extreme Edition" CPUs, the performance/dollar is abysmal but it's not an Xeon. Neither is this a Tesla. This is for the "I can drop $3k on a gaming rig" market. I know people with more expensive hobbies than computers.

Re:Sigh

[Anonymous Coward]

Hey, 9fps is enough for Tetris. Hell, it is an extra f.

I want my block-stacking at the top-of-the-line ultra-smooth high-res, total immersion, realer than real.
And you better believe I will sell my kidneys, all 7 of them.

Re:Sigh

[Shinobi]

The reason Bitcoin was done on AMD GPU's was because AMD had a bitshift instruction, and that due to how simple Bitcoin is, AMD's rather retarded memory handling didn't cause any choking. Double precision had absolutely zero to do with Bitcoin running well on AMD.

AMD's memory handling means that the actual Double Precision performance you get out of a given card is extremely different from the theoretical maximum. In fact, for many real-world tasks, Nvidia+CUDA delivers better DP performance than the AMD paper tigers, especially per watt, and so the HPC world heavily leans towards Nvidia, even with DP heavy tasks. For tasks that doesn't need SP, like many forms of signal analysis etc? Forget AMD, not worth the bother of shitty drivers, piss-poor memory handling, worse performance per watt.

As for RAM, there are things it's useful for, especially since the Titan also has its Universal Physics Solver, meaning that together with the RAM amount, you can put together very detailed sims at decent resolutions and framerates, all on a single card.

Re:Sigh

[Jax Omen]

Too bad the Titan X the article is about has the same 1/32 FP64 as the GTX 980, and NOT the 1/3 FP64 of the previous Titan cards. Source: http://www.anandtech.com/show/... GP is correct. This card is for suckers. People who want to play at 4k will be far better served by SLI/CF still, everyone else shouldn't be looking at either option, and instead getting the far-less-expensive-and-more-than-adequate-at-2560x1440 R9 290, R9 290x, GTX 970, or GTX980 single cards instead.

Re:Sigh

[Shinobi]

Just to correct a misunderstanding many people have:

Not everyone who does compute needs double precision. Many tasks within signal processing only need single precision, for example.

Re: Sigh

[Anonymous Coward]

amd fanbois alert

Re:Sigh

[retchdog]

640k is enough for anyone, right? lol

there is a LOT you can do with 32-bit operations, and oftentimes it's better to push more data through than to get precision you don't need anyway. don't mistake your pedantic ignorance for insight.

Re:Sigh

[Anonymous Coward]

There will _always_ be a "small penis, fastest chip on the block" market for these things. NVIDIA is not stupid. They know, that no matter how expensive their top-of-the-line GPU is, someone will buy it simply because it's the best that can be bought.

It makes no difference if you get 105% of the performance for 400% of the price. This market doesn't care.

Re:Sigh

[evilbessie]

They should have kept the price at $1000 and only put on 8GB, keep the money for profit, it's not like the people who buy them care or make sensible price/performance decisions.

Re:Sigh

[Shinobi]

And that was supposed to be "For tasks that don't need DP, like many forms of signal analysis etc?"

Re:Sigh

[BevanFindlay]

I do wonder if ridiculous amounts of VRAM may end up being useful in game engines that are currently only on the horizon - for example, Outerra's 1:1 scale planet engine renders mostly in GPU. One wonders too about RAM demand of something like Euclideon's "unlimited detail" engine (assuming it isn't vapourware). If we're moving to games that do more in the GPU, then maybe stupid amounts of VRAM might actually get used? Then again, I expect if that were to happen (using complex GPU-based world generators), the compute performance is going to matter too...

I can still remember when I couldn't understand how you'd ever fill a 2GB hard drive... (this was before video on computers was a serious thing, obviously). 12GB VRAM is just bonkers.

Re:Sigh

[UnknownSoldier]

Yeah I noticed that nVidia is playing games with the FP64 with the Titan X. :-(

Conflating high end gamers using Titan X with the scientific performance of the previous Titan Black and Titan is rather dodgy.

Re:Sigh

[Nemyst]

There is such a thing as FP32 compute workload. In fact, graphics research is largely concerned about this, since the goal is often to eventually release the research to the mass market, who're going to be using consumer cards.

Re: Sigh

[Anonymous Coward]

As opposed to all the other nvidia fanbois posting?

Re:Sigh

[Anonymous Coward]

Yay, a market of 6 people.

Re:Sigh

[Anonymous Coward]

sorry, this one has no double precision FP64 and its much more squarely aimed at consumer graphics.... RTFA pls

Re:Sigh

[NemoinSpace]

Just because you can't afford one doesn't mean I'm not better than you. Plenty of people are going to buy this card and then probably have sex with your girlfriend.
You don't have a girlfriend either do you? See how this works? Believe me, you want this card, you need this card. This card separates the winners from the losers. I'm getting one. If you don't have less than a thousand dollars to blow on a video card, what are you gonna do when you have to spend real money?

Re:Sigh

[spauldo]

Blender would find it useful.

It doesn't need double floats for rendering, and it has to load the data for the whole pass into the video RAM to use CUDA. That puts a limit on your scene complexity.

There are various issues using monolithic kernels on AMD cards. Until Blender's GPU renderer (Cycles) is redesigned to use microkernels (work is in progress, but it'll take a while), NVidia is where it's at.

I just do the stuff as a hobby, but if I were a professional, I'd have a couple of Titans in my machine right now, largely for the 6GB vRAM.

Re:Sigh

[UnknownSoldier]

Intel has been doing the exact same thing for the past 20+ years ...

nVidia finally started taking lessons. :-/

Re:Sigh

[Anonymous Coward]

Someone who buys a Titan X (the Titan Z is still like $2000, so Titan X will be a lot more), isn't going to be using Blender. They'll be using production quality, professional modelling software like Maya, 3ds Max and Mudbox.

Re:Sigh

[Anonymous Coward]

I can still remember when I couldn't understand how you'd ever fill a 2GB hard drive... (this was before video on computers was a serious thing, obviously). 12GB VRAM is just bonkers.

You can't even fit newer windows systems on 2GB. No need for video.

Re:Sigh

[Anonymous Coward]

Yeah, because if you're using FOSS you're obviously small fry. That's how things work.

Re:Sigh

[Goragoth]

No matter what Nvidia themselves say this isn't a gamer targeted card. It simply doesn't make sense for a gamer to buy, they are far better off with GTX980's in SLI (which outperforms the Titan X in gaming benchmarks significantly).

Lacking in DP performance does make it less attractive to most GPGPU researchers, but some cases do just fine using SP and most graphics related research certainly does. So let me reiterate: if you are working on research for next generation games and you are working with massive assets that may or may not be compressed down in the future this card is interesting. If you are doing other graphics research in raytracing or voxel cone tracing or the like then this card is interesting.

Of course some of these cards will simply end up in the hands of gamers with more money than sense, but I imagine the majority will find their way into universities in the hands of researchers who need large amounts of onboard memory and high amounts of single-precision performance. Not a big market for sure but I doubt that any of the Titan line of cards are really profitable on their own anyway, they exist primarily as PR for Nvidia (which is why they are always surrounded by big PR events).

Re:Sigh

[Anonymous Coward]

That's retarded to stretch logic into bullshit like you just did.

Re:Sigh

[Mark of the North]

I've worked in Alias Wavefront, Maya, 3DS Max, and Blender. They all have their quirks. All were fairly painful to pick up. But honestly, Blender is nice in that it is a fairly complete program. I'd like to see more consistency in its user interface, but it is comparable to the competition in that sense. Certainly, I'm seeing Blender in production settings a lot lately. Watching the documentary Video Games: The Movie, Blender was all over the place.

Re:Sigh

[MatthiasF]

I completely disagree. The majority of the HPC realm still uses Nvidia only because they know CUDA and not because of any technological advantage. AMD has held the line at not allowing sloppy programming methods into their OpenCL compiler and that has held back a lot of HPC users from jumping ship. You can even see this in many complaints from open source projects, like Blender, where they refuse to produce proper multi-threaded code and rely heavily on the CUDA compiler to do the work for them.

The rest of your complaints, "shitty drivers", "piss-poor memory handling" and "worse performance per watt" are also bogus. I own or manage machines using a large number of Nvidia and AMD video cards, and have seen as many driver issues between the two that neither has come out worse. This is a typical fanboy stereotype that keeps being repeated with no real fact behind it.

Your second complaint is seen a lot in programming forums, but I have never seen anyone do a proper write up of any memory issues with any of AMD's generations and most of the conversations lead me to believe it was an issue of the programmer's personal preference not wanting to learn a second platform with less market share than an actual technical issue. Most of these issues would be alleviate if the programmer would just use a common optimized library and stop trying to redo the work themselves.

Lastly, AMD's offerings have historically produce more performance per watt and their latest offerings continue that trend. This, besides the bit shift ability you mention, is also one reason why AMD was used for Bitcoin mining and supercomputers.

http://www.tomshardware.com/re...
http://www.green500.org/news/g...

Now, my latest personal computer has an Nvidia GeForce GTX 980 inside because I more often need to fix CUDA code and noticed some of the games I wanted to play ran better on it (again, from the game designer's preference and not a technical merit). I personally own eight other video cards across AMD, Nvidia and Matrox (who use AMD GPUs these days) and three generations for testing.

And I am only sticking up for AMD because I admire their push to get people to code for multi-core better. Nvidia has been too conciliatory in the last six years in that respect, which is fine for their revenue stream and market share but not a good thing in the big picture for the broader computer industry. Since Moore's law has begun to slow, we are going to need a massive shift to multi-core optimized applications and we need programmers ready for that day.

AMD seems to be ready with the tough love to get everyone there while Nvidia keeps enabling bad behaviors.

Re:Sigh

[Bob the Super Hamste]

and then probably have sex with your girlfriend.

No one wants to have sex with his hand.

Re:Sigh

[Anonymous Coward]

There are 8k monitors now, just not for the average consumer.

Re:Sigh

[Anonymous Coward]

No professional artist will touch Blender, the UI is a mess and the renderers for it are low quality. The only things I've ever seen done in Blender are small indie projects, such as the one you named.

Re:Sigh

[Anonymous Coward]

It's not as much of a stretch as your asshole gets when it's reamed by big sweaty nigger cocks.

my first thought

[Anonymous Coward]

MUST... BUY... 4 OF,, THOSE...

Wake me up, When am app like VR needs this.

[Anonymous Coward]

Like an Oculus rift app, or second life VR, (Once the lag problem is fixed).

Call of Duty VR..........

OK, we get it

[Anonymous Coward]

Hardware has gone to the atoms now, we can get anything we ever wanted in electronics.

Now what?

Do we still cling to the antiquated notion of work and the economy?

is vram relevant compared to internet speed?

[kwoff]

I'm in the Netherlands and UPC (internet provider) once again appears to be taking a big dump, so while peristalsis plays out I can't play anything. What do I care about video cards?

Yay

[Anonymous Coward]

War of the marchitecture once again

Newsworthy today, standard tomorrow

[Anonymous Coward]

obsolete in a month.

OK, maybe not quite a month but we all know how this goes. Smart developers will be figuring out how to make best use of this much grunt right now becasue everyone will have one in the time it takes to bring code to market.

Is it really?

[Anonymous Coward]

Or is it closer to 6GB x2 ?

AMD RADEON R9 390X

[Anonymous Coward]

The AMD RADEON R9 390X will pack in 4096 cores, with 8GB HBM at 2 GB per stack, via Dual-Link. The 28nm GPU will feature 8.6 teraFLOPS of performance, beating Nvidia's GeForce GTX Titan X (which currently offers 6.2 TFLOPS) by a significant amount.

Re:AMD RADEON R9 390X

[epyT-R]

Yeah but will the drivers handle exceptions gracefully

CUDA benchmark?

[Anonymous Coward]

I wish someone would post some benchmarks for 3D rendering via Octane, Iray ect. Not everyone buys expensive Nvidia cards to play games on them. :D

When available as 16nm, yes

[amplesand]

Nvidia GM204 Maxwell GPUs May Jump From 28nm to 16nm, Skip 20nm http://www.eteknix.com/nvidia-... At 601 mm2 the Titan X will never be cheap because of the low yield. At 16nm this would be something.

Re:When available as 16nm, yes

[Cederic]

Yeah, I'm sticking with my GTX780 until the 20 or 26nm chips are out. Hopefully something from that range will support top-end graphic settings with decent frames per second on a 4k screen, in which case I'll consider buying one.

GeForce GTX Titan X - 4k gaming on a single card

[Anonymous Coward]

That is the gist of it. Unless you are all blind.

Oh great

[slashmydots]

Here's all you need to know about a 12Gb graphics card. Most games' entire installations aren't 12G let alone the textures.

Re:Oh great

[Anonymous Coward]

For the last year a 50GB of installation size is not a exception anymore. It is quite a surprise to find 7 DVDs from a game box for the first time.

Damn it

[Whiteox]

It doesn't really help me. I've been contracted to build a high level gaming system with no stutter/jitter etc. I've been delaying the build looking for Nvidia's answer to the AMD 295x2. The Titan X is good, but the vram is ridiculous. I'll need 2x 980's or 970's to beat the performance of the 295x2 and I don't want to go SLI until the game developers write better code (never) and Nvidia sort out their drivers (improbable). Even the 295x2 has minor stutter issues. I just can't wait for the AMD Fiji chip which should have been out by now.

Re:Damn it

[Anonymous Coward]

no one cares about you. just use another card for your lucrative "contract".

Useless for budget scientific computing

[quax]

Which is really a shame, numerical simulations would easily make full use of the memory.

Re:Useless for budget scientific computing

[godrik]

I was at the keynote at GTC this morning and it really depends on what you are doing. If you want to do numerical simulation, it is not very useful because double precision performance is terrible. But if you do data mining, you mostly care about bandwidth and single precision performance. And then 12GB isn't too much. Actually I find it still a bit on the low side. Intel Xeon Phi are featuring 16GB this days. And in the realm of data analysis fitting the data on the accelerator is what make the difference ebetween the accelerator is great and the accelerator is useless.

Re:Useless for budget scientific computing

[quax]

True, when I wrote 'scientific computing' I meant fp64 numerical simulations. Data mining is filed under 'business intelligence' in my mind :-)

Re:Useless for budget scientific computing

[Scott Ransom]

I do lots of scientific computing (radio astronomy signal processing) on consumer-level NVIDIA cards and it is *all* FP32. These kinds of cards (and the 12GB of mem) could be very useful for my work, and others who do DSP-type of *scientific* computing.

Re:Useless for budget scientific computing

[quax]

Glad to hear we have a taker who can make some use of them.

Where do you put the card?

[camperdave]

Question: In a client/server situation, where do you put the graphics card, in the server to do the rendering, or in the client to run the display?