If you’ve followed NVIDIA’s video card launches over the last few years, then there’s a pretty clear pattern to the company’s release schedule. If the company starts things off with a cut-down Titan, as they did with the Kepler and Pascal generations, then a full-fledged Titan is sure to follow. And sure enough, with the recent launch of the GeForce GTX 1080 Ti – which effectively put the original Titan X Pascal out to pasture – NVIDIA is back again to launch their full-fledged Titan for this generation: the NVIDIA Titan Xp.

As a sort of mid-cycle replacement for the original NVIDIA Titan X (Pascal), this is a bit more of a low-key launch for the company. There’s nothing new to talk about as far as the design goes, the market positioning, etc. Instead what we have is simply a fully-enabled GP102 GPU coming to an NVIDIA prosumer card, making it the most powerful video card NVIDIA offers.

NVIDIA GPU Specification Comparison
  NVIDIA Titan Xp GTX 1080 Ti NVIDIA Titan X
GTX Titan X
CUDA Cores 3840 3584 3584 3072
Texture Units 240 224 224 192
ROPs 96 88 96 96
Core Clock 1481MHz? 1481MHz 1417MHz 1000MHz
Boost Clock 1582MHz 1582MHz 1531MHz 1075MHz
TFLOPs (FMA) 12.1 TFLOPs 11.3 TFLOPs 11 TFLOPs 6.1 TFLOPs
Memory Clock 11.4Gbps GDDR5X 11Gbps GDDR5X 10Gbps GDDR5X 7Gbps GDDR5
Memory Bus Width 384-bit 352-bit 384-bit 384-bit
VRAM 12GB 11GB 12GB 12GB
FP64 1/32 1/32 1/32 1/32
FP16 (Native) 1/64 1/64 1/64 N/A
INT8 4:1 4:1 4:1 N/A
TDP 250W 250W 250W 250W
GPU GP102 GP102 GP102 GM200
Transistor Count 12B 12B 12B 8B
Die Size 471mm2 471mm2 471mm2 601mm2
Manufacturing Process TSMC 16nm TSMC 16nm TSMC 16nm TSMC 28nm
Launch Date 04/06/2017 03/10/2017 08/02/2016 03/17/2015
Launch Price $1200 $699 $1200 $999

Relative to the previous (and now discontinued) Titan, things are pretty straightforward. The last 2 SMs have been enabled, and both the GPU and memory clockspeeds have seen a minor bump as well.

Perhaps more meaningful is to compare the Titan Xp to its only real competition on the market, the GTX 1080 Ti. What does a Titan get you over a Ti for this generation? Okay, it gets you about the same thing: the last 2 SMs are unlocked, and the memory clockspeed has seen a very small bump. However reflecting how NVIDIA opted to hobble the GTX 1080 Ti just a little bit to leave room for the inevitable Titan, NVIDIA’s prosumer card gets a bit more memory and a bit more memory bandwidth, thanks to the re-enabling of the full 384-bit memory bus.

Bringing back the last 32-bit memory channel and its associated GDDR5X chip gives the Titan Xp a total of 547.2GB/sec of memory bandwidth, 13% more than its lower-tier sibling. Otherwise on the GPU performance front, we’re looking at 7% more shader/texture/geometry throughput and 9% more ROP throughput. Or to compare it the last-generation flagship GTX Titan X (Maxwell), from flagship-to-flagship NVIDIA has improved GPU performance by 84%, ROP throughput by 47%, and memory bandwidth by 63%.

As for power and other design considerations, this hasn’t changed. The Titan Xp is still a 250W card, and it’s still designed like the last Titan X, clad in black with NVIDIA’s current-generation heatsink and shroud design. Simply put, if you’re a regular NVIDIA high-end customer, then NVIDIA has made it very easy to pull out your GTX 780Ti/980Ti/Titan and replace it with the new Titan Xp.

However before we get off of the specifications entirely, there’s one aspect of the new Titan Xp that surprises me: the memory capacity. In the previous generations, Titan cards have offered the full memory capacity for their associated GPU, equivalent to NVIDIA’s Tesla and Quadro cards. For the original Titan, this was 6GB, and 12GB for the Titan X (Maxwell). However with the Titan Xp, NVIDIA is still only offering 12GB of VRAM, while the otherwise equivalent Quadro P6000 gets 24GB. This is an interesting departure from the norm for the company.

I have a couple of ideas on why this is, though it’s all speculation. The first is that this is a market reason: NVIDIA needs to enforce better market segmentation between the prosumer Titan and the professional Tesla. Typically this is done via their respective driver sets and what features these cards offer (Tesla not being rigged for workstations, for example). However Titan X (Maxwell) was very popular in the previous generation, and it may be that it did a little too well compared to the Tesla, and NVIDA is concerned that there will be a repeat performance here even though they’ve done a much greater level of feature separation via the differences in the GP100 and GP102 GPUs.

The other theory is that NVIDIA can’t have it all – they can’t both have super-fast GDDR5X, and 24GB of it in clamshell mode at the same time. It’s telling on the memory bandwidth front that NVIDIA has overclocked the Titan Xp’s memory just a bit; 11.4Gbps, even though partner Micron’s GDDR5X tops out at 11Gbps. Granted, 12Gbps is coming, but I think Micron would be announcing that and NVIDIA would just run with 12Gbps. In any case, this compares starkly to the Quadro P6000, which does get 24GB of VRAM, but with its GDDR5X underclocked to 9Gbps. Or to take it one step further, the Tesla P40, which doesn’t get GDDR5X at all and only has GDDR5. NVIDIA and Micron have definitely pushed the envelope with GDDR5X, so given the additional complexities of clamshell mode, it’s not unreasonable to speculate that a 12GB card is for technical reasons along these lines.

In any case, NVIDIA’s handling of the Titan Xp and their intended market hasn’t changed from the previous generation Titan. This means NVIDIA is walking an interesting line with partners and customers in positioning this as a prosumer card. At $1200 it’s 71% more expensive than the GTX 1080 Ti, all for one last GB of memory and 5-10% more performance. That last bit of flagship performance from NVIDIA has always come at a price, and the Titan Xp is no exception.

The expected customer base then is both professionals and consumers, however one that leans more strongly towards professionals than the Maxwell generation. Professionals would just as well work with NVIDIA directly, whereas consumers have (and generally still do) work via NVIDIA’s partners, whom of course won’t be promoting the Titan Xp since they don’t get to sell it. Which is not to say that you can’t buy it and game on it – for those whom money is no object, this will happen – and it’s even conveniently on the GeForce website. But even then, the NVIDIA Titan Xp (remember, this isn’t a GeForce) doesn’t get the same level of promotion with consumers and gamers as past iterations have. The prosumer card is decidedly more professional, especially with the almost-as-good GeForce GTX 1080 Ti right below it.

Meanwhile, on a personal note, I’m entirely nonplussed with the name. NVIDIA named the previous Titan X (Pascal) poorly, and they seem content to continue that trend here. Because the previous Pascal-based Titan was called the “Titan X”, it’s very common to see it informally referred to as the “Titan XP”. Except now we have NVIDIA selling the “Titan Xp”, which is not the same card as the “Titan XP”. I appreciate NVIDIA at least not calling this the “Titan X” yet again – and I assume that all of this started from someone wanting to call it the “Titan X Plus” but they really need to find better names. My suggestion: either pick unique Titan names, or at least go with yearly model numbers like cars and iPads.

Anyhow, for those whose wallets are deep enough to buy NVIDIA’s latest prosumer and budget deep-learning card, the card will set you back $1200. Like the previous Titan, the NVIDA Titan Xp is being sold exclusively through NVIDIA’s website, and has already gone on sale today.

Source: NVIDIA

Comments Locked


View All Comments

  • 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.

Log in

Don't have an account? Sign up now