Probably due to being a business. We get all of these mild speed upgrades KNOWING that the next release will also offer a small speed increase. I'm pretty sure that, if it were not for $$$$$ we'd be far further than we are now with regards to computer tech.
This always irritates me (and is true for AMD as well). You should easily be able to get 1/8th of float MIPS from doubles (1/4 should be possible, but requires designing around doubles. 1/2 means you *really* designed around doubles and at least half the transistors are dark during singles).
I'm also wondering just how bad you have to be at software fp to not be able to beat 1/64th in fp16. I mean, come on! That is 128 instructions for a 16 bit multiply(/add?)? You should be able to do that niavely in 48, and probably under 32. Personally, I'd rather see fp16 as emphasized as int8 and used for HD pixels.
There's a lot more things a GPU should be doing with FP16 than FP64, but it is embarassing just how much they cripple both (worse for AMD when they keep talking about HSA).
You clearly don't understand nvidias architecture shift since Maxwell. They aren't targeting the FP64 crowd anymore. Shifting away from FP64 enabled them to increase TFLOPs with the offset die area. For those special applications that demand FP64 precision there are other high end cards, or just consider something from AMD who still has an architectural providing FP64 in the pro-budget space.
On that note, I still think they've outdone themselves with the 1080Ti. The Xp likely won't sell well in comparison. Including the target market for the Titan. Which is probably OK because nvidia probably doesn't have a lot of fully enabled GP102's to go around. After all, these are "perfect" chips with no die flaws and that is going to be a substantial minority of the wafer.
I did realize Nvidia had some magical power that puts people in a trance and makes them open their wallets buy things on demand. But please name for all of us victims a competitor that offers the range of performance options with the efficiency that Nvidia does.
Surely these cards, with more SMs and higher clocks, are simply released as yields and process improvements makes them possible? I'm guessing the yield of dies with 12 billion microscopic transistors isn't great.
Apparently you don't know what the phrase "sour grapes" means, as it's not an appropriate response. I think you meant, "jealous?".
But I personally believe you anyway, because it totally makes sense that there are people who for whatever reason want to/need to be at the very forefront of GPU performance, and we're only talking about $1,500 or so extra investment here, which really isn't all that much for a hobby or whatever.
However, your initial response was a false dilemma and thus incorrect. Because pricing evaluations are entirely a personally subjective affair, there are many reasons that someone would say that nvidia's pricing is absurd that do not have anything to do with ability to afford the cards.
It's the typical response of someone who tries to impress people by throwing money around. They think anyone who isn't a complete spendthrift like them is "poor". In the end, he'll likely end up broke, while those who were more responsible with their money will be laughing all the way *from* the bank.
500$ more per card for 8% performance advantage?, or 40% more for 8%. You could get 2 1080TI and it would cost you 16% more for 80% more performance. This is no longer a "personally subjective matter", it is foolishness.
Amazingly, I actually bought a Titan Xp this week. I never thought I would, and I didn't even remember having this conversation, but when reading Anandtech's review of the card I discovered this blast from the past.
These days (one year since this discussion started), crytocoin mining has pushed the availability of the high end Nvidia cards down, and consequently, the price way up. It is hard to find a well built 1080ti for less than $1,000 (you can get bottom barrel ones for ~$900, but those are cheaply made with poor quality fans etc). On Nvidia's site the 1080ti is still $699 but is generally always sold out. But they have the Titan Xp for $1,200.
So at this point, your choices are: spend $1,000 for a 1080ti, spend $1,200 for a Titan Xp, or wait around checking Nvidia's site all the time and hope to get lucky and score a $699 1080ti.
My time is valuable, so I'm not going to spend it constantly checking Nvidia's site. So that option is out.
That leaves the $1,000 1080ti or the $1,2000 Titan Xp. The Titan Xp is more than 10% better than the 1080ti, and now at only a 20% price premium. And you can buy the founder's edition straight from Nvidia. Totally worth it.
I never thought I'd buy a $1,200 GPU, but with the way cryptomining is driving prices up, I am not sure when if ever the prices are going to coime down. So I'll just enjoy this Titan Xp in my VR rig for a few years ...
haha, NV strategy: First - cheating, sell Geforce rebranded as Titan for high price, while collecting real Titan chips Second - normalization, sell Geforce as Geforce, and Titan as Titan Most loyal clients, as best victims to drain their pockets :)
Anyone who willingly buys something is not a victim, except in the rare case of the buyer being under duress for some reason and having no alternative -- and this is CERTAINLY not a case of that.
People still harp on about that today as if it ever really meant anything, all the while ignoring the fact that the 970's memory design had hardly any affect on gaming at all. I said often that those playing games which would end up using close to 4GB RAM would likely want a GPU with more raw power than a 970 anyway, so indeed it was a non-issue from the start. People do seem to love to wallow in the FUD though.
Yes, when you're bigger and on top there's pretty not much you can do about it. Might as well lie back and enjoy it. Now, getting back to what he was saying... we (as consumers) need Vega badly. If anything just to offer up competition.
Makes as much sense as saying Porsche is running the train on its customers every WHICH way they want because they charge an arm and a leg for their high end cars. It isn't meant to be a value proposition. Is it a decent value comparatively to the Ti? Of course not. So what. No one is forcing anyone to buy any of this. Now, does it make the Ti look like a great value now? Yes it does. That's the point.
No the last Titan was $1200. You are correct if you go back ONE MORE titan at $999 (maxwell). Just look at the chart in this article. R&D costs money, quit complaining about your paycheck and get a better one if you can't afford the best toys. ;) Richer people laugh at this price and love the bragging rights. Even if you have zero interest in this card, you should at least appreciate the fact that having people who DO pay for it (and for the most part don't care about price) pave the way for cheaper cards with even more perf later. IE the last titan's income helps us get a 1080TI right?
One more point, this card is really not aimed at gamers (buy a 1080ti for that). It's aimed at people who can't afford P6000's prices (or just don't want to pay it) but still want the perf & maybe some extra memory without the need for support that pro cards get. For these people, Titan's have always had laughably awesome pricing which is why many buy more than one. Heck you can afford 4 for the price of 1 P6000. Again, from their perspective your comment is silly and even $1500 would be cheap (you could still buy 3 for the price of 1 p6000). That's a LOT of power on the cheap if you're a dev etc on a budget. Great gaming is just a bonus to these people if they're using it in a home/work PC.
So even if a GAMER calls it expensive, quite a lot of others think it's dirt cheap. You can thank Vega coming for getting a 1080ti that is so close to Titan this round. Of course if Vega sucks, expect them to spread again next round...LOL. You don't seem to understand a CEO's job is to charge the maximum they can get for all products at any time. That's the whole point of business. Charge exactly what the market will handle. That isn't to say they get it right all the time, but NV wouldn't be charging $1200 AGAIN if they weren't flying off the shelves and setting record quarters one after another. Clearly, some of us have decent wages and cash to throw away again and again. :) Thank god too, or R&D would slow to a crawl and we'd have 2-3yrs between new cards instead of yearly+refresh. One only has to look at AMD for the last 5yrs to see what a lack of cash produces (no cpus, gpu's always hot or higher watts, less perf etc), 30% engineer layoffs etc etc. Note until Ryzen, AMD had no cpu over $150 for years. Now hopefully that will change for a few years so they can recover some much needed cash for R&D, paying down debt etc.
I have about no hope Vega will change much in gpus (NV already answered twice before it's launch), but the cpu side has a shot at making some REAL cash as soon as all the server chips hit, zen is in apus and rev2 of the desktop hits (which hopefully fixes all the gaming issues, already are claiming this). Good they launched desktop first and have a chance to fix the cpu stuff before server and apu chips hit. People who build their own desktops have a much better tolerance for issues than server or even laptop types (lump in retail desktop pc buyers too I guess, dell etc). If you built it, you probably follow some hardware sites, and most likely know what a bios flash is etc.
I wouldn't mind fixing issues myself (on ryzen and really want an 8core for handbrake) but I don't think rev1 is going to get fixed much for gamers as pcper and AMD themselves have hinted already (they point to rev2). Intel charges up to $7K for top server chips (24core) so I can't wait for AMD to get in that market with 16/32 cores and hopefully CHARGE what they are worth. No discount if they are great at certain server loads vs. Intel. Until they're stuck on shelves CHARGE $7K while you can vs. an Intel 24core if you're winning benchmarks for many server loads. Maybe you sell a 32core for $6500 if you're smacking around the 24core Intel, but for crying out loud, don't charge $3500 if that is the case...ROFL. Intel already has an answer coming too (32core announced) so get cash while you can. Intel can't really cut all their chips in half and have happy shareholders so there is a limit to their price war that is surely coming. For AMD even a price war at server chips prices would net huge profits though :) Business 101 AMD, learn from Intel/NV pricing.
Presumably this is Nvidia's spoiler announcement, just like Intel's Coffee Lake announcement ahead of Ryzen (which didn't work at all, being completely forgotten in days).
Really? People are complaining that nVidia has released a new halo card? Like you all would have TOTALLY bought this $1200, but you already bought a 1080 Ti, so now nVidia is just trying to rip you off!
I'm not going to defend this is a purely sensible strategy by nVidia, but this makes absolutely zero difference in any meaningful way.
I think this card isn't meant to sell but to merely to make the Ti @ $699 more palatable. The avg for the highend has traditionally $500-$600. Nvidia having no competition has been bumping the price up every release bc they can.
I don't think any 1080 Ti owner would be complaining about this. It just reinforces that 1080Ti is a good buy... At least relative to both the Titan X as well as the XP: "At $1200 it’s 71% more expensive than the GTX Titan Ti, all for one last GB of memory and 5-10% more performance."
Yup, NV is moving away from SLI, and companies aren't bothering with the same level of coding support anymore. In the days of the 400 series, SLI was an excellent technology which worked very well, but it depends too much on dev support. Makes more sense now to get a single good card and thus have fewer stuttering issues aswell.
The original Titan did make sense: it had the FP64 performance but without the support behind Tesla or Quadro.
The newer Titans (maxwell,pascal) are not that intereseting. You are better off with 2x1080 Ti to do HPC for an additional $200 against only 1 Titan Xp.
This card is just "oh look, I have the most powerful card with 0 resell value". Because there are no differences in drivers, it uses GeForce drivers without any additional capability.
I bought 4 Pascal Titan X cards, and feel pretty good, because I've been using them almost 24/7 for about 8 months now. When Nvidia releases something that is at least 50% faster at the same price, I will consider upgrading. To be honest, I hoped this new Titan will offer good FP16 performance, but it doesn't, I have no interest.
Good technique for flooding the news with Nvidia products and meaningless upgrades to eclipse any news regarding AMD and VEGA and thus keep their market-share tightly controlled.
In the other side, this could be considered a tech marvel to see that they have matured their process so much. They can sell fully defectless versions of their giant chip.
Seems like what happened here was that the 1080 Ti came out, people stopped buying the Titan Pascal. So nVidia needed to upgrade it just a bit, to make it faster again, so they can continue collecting the price premium from people willing to pay $1,200 for a slightly faster graphics card.
Except you got it backwards, they released the 1080Ti knowing a new Titan king of performance will come next. I bet my 60k car that they wouldn't have released the 1080Ti otherwise.
I suspect original Pascal Titan X being a virtue of necessity... They had fresh, far from being mature process, huge chip and virtually no Titan in their hands and they wanted to keep their face... So the original crippled titan came, limited to nVidia selling only due to heavily limited supplies. Now the process matured, they can afford start selling real Pascal Titan.
Plus ofc, they show something to grab a bit of a market before VEGA comes.
I love the people who are honestly surprised by this release strategy. It seems few people read the articles speaking about how yields work with new processes, and even fewer people understand the division between gamers and professional users.
I wish NVIDIA would understand that the many people that wouldn't buy a super-expensive, high-end video card *without* HBM in 2016 would surely not buy one in 2017, and the longer they wait the more likely it is that we buy AMD.
It's absurd, really, that we're not seeing HBM as standard on these ridiculously expensive flagship products. Fury X came out almost *two* years ago, featured HBM and cost $650; not to mention the non-X Fury that cost $550 and also had HBM. The performance impact doesn't matter - a premium product should have the latest technologies.
They get more Profit by using gddr5 memory, and it is selling good enough. Same as with Intel. Why make big improvements is small improvements give more Profit... We need more competition to get better products.
They should absolutely start pulling names for Titan cards from the Greek mythology. This is so obvious I'm not sure why they haven't already done it except Marketing probably decided it would be too nerdy to try to sell something called a Mnemosyne.
--[I think this card isn't meant to sell but to merely to make the Ti @ $699 more palatable.]--
This psychological effect (forget its name but something about pricing being comparative rather than absolute) has actually been studied and shown to work. Just placing an overpriced item at the top end will make people more likely to think the next one down is reasonably priced.
Those complaining don't understand the nature of the work being done by those who would find the newer product attractive. In many cases a 9% productivity improvement would more than offset the higher cost.
We’ve updated our terms. By continuing to use the site and/or by logging into your account, you agree to the Site’s updated Terms of Use and Privacy Policy.
Facebook
Twitter
RSS
70 Comments
Back to Article
osxandwindows - Friday, April 7, 2017 - link
Why does Nvidia insist on milking customers for gimped GPus, anyway?damianrobertjones - Friday, April 7, 2017 - link
Probably due to being a business. We get all of these mild speed upgrades KNOWING that the next release will also offer a small speed increase. I'm pretty sure that, if it were not for $$$$$ we'd be far further than we are now with regards to computer tech.ImSpartacus - Friday, April 7, 2017 - link
If not for $$$$, we'd see less r&d spending and be noticeably behind in overall computer tech.grant3 - Friday, April 7, 2017 - link
Tell us more about this modern technology which was designed without any money.nathanddrews - Friday, April 7, 2017 - link
Milking? Gimped? This is a full chip at 1/5th the price of the P6000...SharpEars - Friday, April 7, 2017 - link
Look at the FP64 performance of all of the cards in the table - Gimped!wumpus - Friday, April 7, 2017 - link
This always irritates me (and is true for AMD as well). You should easily be able to get 1/8th of float MIPS from doubles (1/4 should be possible, but requires designing around doubles. 1/2 means you *really* designed around doubles and at least half the transistors are dark during singles).I'm also wondering just how bad you have to be at software fp to not be able to beat 1/64th in fp16. I mean, come on! That is 128 instructions for a 16 bit multiply(/add?)? You should be able to do that niavely in 48, and probably under 32. Personally, I'd rather see fp16 as emphasized as int8 and used for HD pixels.
There's a lot more things a GPU should be doing with FP16 than FP64, but it is embarassing just how much they cripple both (worse for AMD when they keep talking about HSA).
nathanddrews - Friday, April 7, 2017 - link
Ah, gimped for compute. I was thinking only about games.Samus - Saturday, April 8, 2017 - link
You clearly don't understand nvidias architecture shift since Maxwell. They aren't targeting the FP64 crowd anymore. Shifting away from FP64 enabled them to increase TFLOPs with the offset die area. For those special applications that demand FP64 precision there are other high end cards, or just consider something from AMD who still has an architectural providing FP64 in the pro-budget space.On that note, I still think they've outdone themselves with the 1080Ti. The Xp likely won't sell well in comparison. Including the target market for the Titan. Which is probably OK because nvidia probably doesn't have a lot of fully enabled GP102's to go around. After all, these are "perfect" chips with no die flaws and that is going to be a substantial minority of the wafer.
osxandwindows - Friday, April 7, 2017 - link
They sold the same crapp in 2016 for the same price.Chaser - Friday, April 7, 2017 - link
I did realize Nvidia had some magical power that puts people in a trance and makes them open their wallets buy things on demand. But please name for all of us victims a competitor that offers the range of performance options with the efficiency that Nvidia does.Meteor2 - Friday, April 7, 2017 - link
Surely these cards, with more SMs and higher clocks, are simply released as yields and process improvements makes them possible? I'm guessing the yield of dies with 12 billion microscopic transistors isn't great.zerosandones - Sunday, April 9, 2017 - link
why does apple insist on milking customer for gimped PC's, anyway?you see how stupid that questions sounds too!
Gich - Friday, April 7, 2017 - link
This is a bit insulting...jordanclock - Friday, April 7, 2017 - link
Because you were totally going to get one instead of a 1080ti, right?vladx - Friday, April 7, 2017 - link
That what people who don't have the cash for it would say, personally I'm gonna sell my 2x1080Ti and get myself a pair of new Titans.cwolf78 - Friday, April 7, 2017 - link
Surrrrre you are.vladx - Friday, April 7, 2017 - link
Lol sour grapesbji - Friday, April 7, 2017 - link
Apparently you don't know what the phrase "sour grapes" means, as it's not an appropriate response. I think you meant, "jealous?".But I personally believe you anyway, because it totally makes sense that there are people who for whatever reason want to/need to be at the very forefront of GPU performance, and we're only talking about $1,500 or so extra investment here, which really isn't all that much for a hobby or whatever.
However, your initial response was a false dilemma and thus incorrect. Because pricing evaluations are entirely a personally subjective affair, there are many reasons that someone would say that nvidia's pricing is absurd that do not have anything to do with ability to afford the cards.
Nagorak - Saturday, April 8, 2017 - link
It's the typical response of someone who tries to impress people by throwing money around. They think anyone who isn't a complete spendthrift like them is "poor". In the end, he'll likely end up broke, while those who were more responsible with their money will be laughing all the way *from* the bank.sharath.naik - Thursday, April 20, 2017 - link
500$ more per card for 8% performance advantage?, or 40% more for 8%. You could get 2 1080TI and it would cost you 16% more for 80% more performance. This is no longer a "personally subjective matter", it is foolishness.bji - Friday, April 13, 2018 - link
Amazingly, I actually bought a Titan Xp this week. I never thought I would, and I didn't even remember having this conversation, but when reading Anandtech's review of the card I discovered this blast from the past.These days (one year since this discussion started), crytocoin mining has pushed the availability of the high end Nvidia cards down, and consequently, the price way up. It is hard to find a well built 1080ti for less than $1,000 (you can get bottom barrel ones for ~$900, but those are cheaply made with poor quality fans etc). On Nvidia's site the 1080ti is still $699 but is generally always sold out. But they have the Titan Xp for $1,200.
So at this point, your choices are: spend $1,000 for a 1080ti, spend $1,200 for a Titan Xp, or wait around checking Nvidia's site all the time and hope to get lucky and score a $699 1080ti.
My time is valuable, so I'm not going to spend it constantly checking Nvidia's site. So that option is out.
That leaves the $1,000 1080ti or the $1,2000 Titan Xp. The Titan Xp is more than 10% better than the 1080ti, and now at only a 20% price premium. And you can buy the founder's edition straight from Nvidia. Totally worth it.
I never thought I'd buy a $1,200 GPU, but with the way cryptomining is driving prices up, I am not sure when if ever the prices are going to coime down. So I'll just enjoy this Titan Xp in my VR rig for a few years ...
Nagorak - Saturday, April 8, 2017 - link
Doesn't impress me.TristanSDX - Friday, April 7, 2017 - link
haha, NV strategy:First - cheating, sell Geforce rebranded as Titan for high price, while collecting real Titan chips
Second - normalization, sell Geforce as Geforce, and Titan as Titan
Most loyal clients, as best victims to drain their pockets :)
bji - Friday, April 7, 2017 - link
Anyone who willingly buys something is not a victim, except in the rare case of the buyer being under duress for some reason and having no alternative -- and this is CERTAINLY not a case of that.tamalero - Friday, April 7, 2017 - link
Misleading is a good tactic for Nvidia. I mean, anyone remembers the debacle of the 970 GTX?edzieba - Friday, April 7, 2017 - link
You mean where it had such good performance that nobody noticed the last 512MB was not full-duplex for months until Nvidia told everybody?mapesdhs - Monday, April 10, 2017 - link
People still harp on about that today as if it ever really meant anything, all the while ignoring the fact that the 970's memory design had hardly any affect on gaming at all. I said often that those playing games which would end up using close to 4GB RAM would likely want a GPU with more raw power than a 970 anyway, so indeed it was a non-issue from the start. People do seem to love to wallow in the FUD though.Cellar Door - Friday, April 7, 2017 - link
The market really needs Vega at this point - it is just silly how Nvidia can run train on their customers every witch way they want.shabby - Friday, April 7, 2017 - link
When you're on top got can do whatever you want, blame amd for not competing first.bigboxes - Friday, April 7, 2017 - link
Yes, when you're bigger and on top there's pretty not much you can do about it. Might as well lie back and enjoy it. Now, getting back to what he was saying... we (as consumers) need Vega badly. If anything just to offer up competition.Manch - Friday, April 7, 2017 - link
Makes as much sense as saying Porsche is running the train on its customers every WHICH way they want because they charge an arm and a leg for their high end cars. It isn't meant to be a value proposition. Is it a decent value comparatively to the Ti? Of course not. So what. No one is forcing anyone to buy any of this. Now, does it make the Ti look like a great value now? Yes it does. That's the point.darckhart - Friday, April 7, 2017 - link
And now they've pushed that top tier an extra $200! as if $1k wasn't good enough. "let's do $1200! people still buy? great! let's do $1500 next time!"bji - Friday, April 7, 2017 - link
If this is surprising to you, I suggest a college course in basic economics. Or maybe just read a book.TheJian - Saturday, April 8, 2017 - link
No the last Titan was $1200. You are correct if you go back ONE MORE titan at $999 (maxwell). Just look at the chart in this article. R&D costs money, quit complaining about your paycheck and get a better one if you can't afford the best toys. ;) Richer people laugh at this price and love the bragging rights. Even if you have zero interest in this card, you should at least appreciate the fact that having people who DO pay for it (and for the most part don't care about price) pave the way for cheaper cards with even more perf later. IE the last titan's income helps us get a 1080TI right?One more point, this card is really not aimed at gamers (buy a 1080ti for that). It's aimed at people who can't afford P6000's prices (or just don't want to pay it) but still want the perf & maybe some extra memory without the need for support that pro cards get. For these people, Titan's have always had laughably awesome pricing which is why many buy more than one. Heck you can afford 4 for the price of 1 P6000. Again, from their perspective your comment is silly and even $1500 would be cheap (you could still buy 3 for the price of 1 p6000). That's a LOT of power on the cheap if you're a dev etc on a budget. Great gaming is just a bonus to these people if they're using it in a home/work PC.
So even if a GAMER calls it expensive, quite a lot of others think it's dirt cheap. You can thank Vega coming for getting a 1080ti that is so close to Titan this round. Of course if Vega sucks, expect them to spread again next round...LOL. You don't seem to understand a CEO's job is to charge the maximum they can get for all products at any time. That's the whole point of business. Charge exactly what the market will handle. That isn't to say they get it right all the time, but NV wouldn't be charging $1200 AGAIN if they weren't flying off the shelves and setting record quarters one after another. Clearly, some of us have decent wages and cash to throw away again and again. :) Thank god too, or R&D would slow to a crawl and we'd have 2-3yrs between new cards instead of yearly+refresh. One only has to look at AMD for the last 5yrs to see what a lack of cash produces (no cpus, gpu's always hot or higher watts, less perf etc), 30% engineer layoffs etc etc. Note until Ryzen, AMD had no cpu over $150 for years. Now hopefully that will change for a few years so they can recover some much needed cash for R&D, paying down debt etc.
I have about no hope Vega will change much in gpus (NV already answered twice before it's launch), but the cpu side has a shot at making some REAL cash as soon as all the server chips hit, zen is in apus and rev2 of the desktop hits (which hopefully fixes all the gaming issues, already are claiming this). Good they launched desktop first and have a chance to fix the cpu stuff before server and apu chips hit. People who build their own desktops have a much better tolerance for issues than server or even laptop types (lump in retail desktop pc buyers too I guess, dell etc). If you built it, you probably follow some hardware sites, and most likely know what a bios flash is etc.
I wouldn't mind fixing issues myself (on ryzen and really want an 8core for handbrake) but I don't think rev1 is going to get fixed much for gamers as pcper and AMD themselves have hinted already (they point to rev2). Intel charges up to $7K for top server chips (24core) so I can't wait for AMD to get in that market with 16/32 cores and hopefully CHARGE what they are worth. No discount if they are great at certain server loads vs. Intel. Until they're stuck on shelves CHARGE $7K while you can vs. an Intel 24core if you're winning benchmarks for many server loads. Maybe you sell a 32core for $6500 if you're smacking around the 24core Intel, but for crying out loud, don't charge $3500 if that is the case...ROFL. Intel already has an answer coming too (32core announced) so get cash while you can. Intel can't really cut all their chips in half and have happy shareholders so there is a limit to their price war that is surely coming. For AMD even a price war at server chips prices would net huge profits though :) Business 101 AMD, learn from Intel/NV pricing.
mapesdhs - Monday, April 10, 2017 - link
Thanks TheJian, another good post! 8)Meteor2 - Friday, April 7, 2017 - link
Presumably this is Nvidia's spoiler announcement, just like Intel's Coffee Lake announcement ahead of Ryzen (which didn't work at all, being completely forgotten in days).jordanclock - Friday, April 7, 2017 - link
Really? People are complaining that nVidia has released a new halo card? Like you all would have TOTALLY bought this $1200, but you already bought a 1080 Ti, so now nVidia is just trying to rip you off!I'm not going to defend this is a purely sensible strategy by nVidia, but this makes absolutely zero difference in any meaningful way.
Manch - Friday, April 7, 2017 - link
I think this card isn't meant to sell but to merely to make the Ti @ $699 more palatable. The avg for the highend has traditionally $500-$600. Nvidia having no competition has been bumping the price up every release bc they can.Meteor2 - Friday, April 7, 2017 - link
Exactly like Intel with HEDT CPUs. Thank goodness for AMD.K_Space - Friday, April 7, 2017 - link
I don't think any 1080 Ti owner would be complaining about this. It just reinforces that 1080Ti is a good buy... At least relative to both the Titan X as well as the XP:"At $1200 it’s 71% more expensive than the GTX Titan Ti, all for one last GB of memory and 5-10% more performance."
BurntMyBacon - Monday, April 10, 2017 - link
@K_Space: "At $1200 it’s 71% more expensive than the GTX Titan Ti, all for one last GB of memory and 5-10% more performance."Where can I get this fabled GTX Titan Ti you speak of. Sounds like a killer deal.
SharpEars - Friday, April 7, 2017 - link
FP64 1/32 - You can keep your overpriced garbage!mapesdhs - Monday, April 10, 2017 - link
Get a better job and buy a Quadro. Or just use some old 580s.SharpEars - Friday, April 7, 2017 - link
Buy a Titan Xp or put 2 1080 Tis in SLI for almost the same price, you be the judge on what is faster/better!jordanclock - Friday, April 7, 2017 - link
Probably the Titan Xp because SLI scaling has been kind of crap lately.mapesdhs - Monday, April 10, 2017 - link
Yup, NV is moving away from SLI, and companies aren't bothering with the same level of coding support anymore. In the days of the 400 series, SLI was an excellent technology which worked very well, but it depends too much on dev support. Makes more sense now to get a single good card and thus have fewer stuttering issues aswell.sonicmerlin - Friday, April 14, 2017 - link
What happened to DX 12 multi card support?Filiprino - Friday, April 7, 2017 - link
The original Titan did make sense: it had the FP64 performance but without the support behind Tesla or Quadro.The newer Titans (maxwell,pascal) are not that intereseting. You are better off with 2x1080 Ti to do HPC for an additional $200 against only 1 Titan Xp.
This card is just "oh look, I have the most powerful card with 0 resell value". Because there are no differences in drivers, it uses GeForce drivers without any additional capability.
madwolfa - Friday, April 7, 2017 - link
Titans have pretty good resell value, tbh.britjh22 - Friday, April 7, 2017 - link
Only up until the next xx80 Ti or Titan come out, and then that shit plummets or gets extremely difficult to find a buyer.mapesdhs - Monday, April 10, 2017 - link
Not all pro tasks need FP64. OTOH, some need ECC and thus non-pro cards are of no use anyway (fine for dev work, useless for production environments).Aerodrifting - Friday, April 7, 2017 - link
I wonder how the people who bought Pascal Titan X feel right now, lolp1esk - Friday, April 7, 2017 - link
I bought 4 Pascal Titan X cards, and feel pretty good, because I've been using them almost 24/7 for about 8 months now. When Nvidia releases something that is at least 50% faster at the same price, I will consider upgrading. To be honest, I hoped this new Titan will offer good FP16 performance, but it doesn't, I have no interest.tamalero - Friday, April 7, 2017 - link
Good technique for flooding the news with Nvidia products and meaningless upgrades to eclipse any news regarding AMD and VEGA and thus keep their market-share tightly controlled.In the other side, this could be considered a tech marvel to see that they have matured their process so much. They can sell fully defectless versions of their giant chip.
twtech - Friday, April 7, 2017 - link
Seems like what happened here was that the 1080 Ti came out, people stopped buying the Titan Pascal. So nVidia needed to upgrade it just a bit, to make it faster again, so they can continue collecting the price premium from people willing to pay $1,200 for a slightly faster graphics card.vladx - Sunday, April 9, 2017 - link
Except you got it backwards, they released the 1080Ti knowing a new Titan king of performance will come next. I bet my 60k car that they wouldn't have released the 1080Ti otherwise.HollyDOL - Monday, April 10, 2017 - link
I suspect original Pascal Titan X being a virtue of necessity... They had fresh, far from being mature process, huge chip and virtually no Titan in their hands and they wanted to keep their face... So the original crippled titan came, limited to nVidia selling only due to heavily limited supplies. Now the process matured, they can afford start selling real Pascal Titan.Plus ofc, they show something to grab a bit of a market before VEGA comes.
Dizoja86 - Saturday, April 8, 2017 - link
I love the people who are honestly surprised by this release strategy. It seems few people read the articles speaking about how yields work with new processes, and even fewer people understand the division between gamers and professional users.p1esk - Saturday, April 8, 2017 - link
Do tell how is this card more "professional" than 1080Ti. Very few people will pay 70% premium for a 9% faster card.yhselp - Saturday, April 8, 2017 - link
I wish NVIDIA would understand that the many people that wouldn't buy a super-expensive, high-end video card *without* HBM in 2016 would surely not buy one in 2017, and the longer they wait the more likely it is that we buy AMD.It's absurd, really, that we're not seeing HBM as standard on these ridiculously expensive flagship products. Fury X came out almost *two* years ago, featured HBM and cost $650; not to mention the non-X Fury that cost $550 and also had HBM. The performance impact doesn't matter - a premium product should have the latest technologies.
haukionkannel - Saturday, April 8, 2017 - link
They get more Profit by using gddr5 memory, and it is selling good enough. Same as with Intel. Why make big improvements is small improvements give more Profit...We need more competition to get better products.
dma_nad - Sunday, April 9, 2017 - link
many people wouldn't buy, but many people still buyAshinjuka - Sunday, April 9, 2017 - link
Re: Titan namesThey should absolutely start pulling names for Titan cards from the Greek mythology. This is so obvious I'm not sure why they haven't already done it except Marketing probably decided it would be too nerdy to try to sell something called a Mnemosyne.
https://en.wikipedia.org/wiki/Titan_(mythology)
vladx - Sunday, April 9, 2017 - link
Nice idea, I'd love for the Volta Titan to be called Prometheus instead.mapesdhs - Monday, April 10, 2017 - link
Except the Prometheus movie sucked, so probably not the best choice re word association for marketing. ;Dstephenbrooks - Sunday, April 9, 2017 - link
--[I think this card isn't meant to sell but to merely to make the Ti @ $699 more palatable.]--This psychological effect (forget its name but something about pricing being comparative rather than absolute) has actually been studied and shown to work. Just placing an overpriced item at the top end will make people more likely to think the next one down is reasonably priced.
rtho782 - Monday, April 10, 2017 - link
I don't understand all the complaints about this being so close to the Titan X (p) and 1080ti.Progress happens. Yields have gone up and vram is a little faster, so we have a refreshed Titan Xp.
As I remember, there was only about 3 months between the GeForce 4 Ti4800 and the GeForce FX5900 Ultra.
mapesdhs - Monday, April 10, 2017 - link
Those complaining don't understand the nature of the work being done by those who would find the newer product attractive. In many cases a 9% productivity improvement would more than offset the higher cost.yazeed - Sunday, April 23, 2017 - link
Deep Learning/Gaming Build with NVIDIA Titan Xp and MacBook Pro with Thunderbolt2https://medium.com/@yazeedalrubyli/deep-learning-g...