NVIDIA Lifts Veil On GeForce GTX 1080 Ti Performance Reviews, Which Show Faster Speeds Than Titan X (hothardware.com) 51
MojoKid writes from a report via HotHardware: NVIDIA is officially launching its most powerful gaming graphics card today, the GeForce GTX 1080 Ti. It was announced last week at the Game Developers Conference and pre-orders began shortly thereafter. However, the cards will begin shipping today and NVIDIA has lifted the veil on performance reviews. Though its memory complement and a few blocks within the GPU are reduced versus NVIDIA's previous top-end card, the Titan X, the GeForce GTX 1080 Ti makes up for its shortcomings with a combination of refinement and the brute force of higher memory clocks, based on new and improved Micron GDDR5X memory, faster core clocks and an improved cooler. For gamers, the good news is, the 1080 Ti retails for $699, versus $1200 for the Titan X, and it is in fact faster, for the most part. Throughout a battery of game tests and benchmarks, regardless of the resolution or settings used, the GeForce GTX 1080 Ti performed on par with or slightly faster than the NVIDIA Titan X and roughly 30-35% better than the standard GeForce GTX 1080 Founders Edition. Versus AMD's current flagship GPU, the Radeon R9 Fury X, there is no competition; the GeForce GTX 1080 Ti was nearly 2x faster than the Fury X in some cases.
I still remember the SGI days (Score:3)
How far we've come since the SGI Indigo 2 Max Impact is just phenomenal.
Re: I still remember the SGI days (Score:2)
Moore's Law (Score:5, Insightful)
It's funny how we say Moore's law is dead when it's about the only thing still kicking.
Clock speeds, the x86 architecture, and software design are all more or less stagnant, which means your typical single-threaded business logic is barely running faster year upon year and CPU benchmarks are pretty flat.
But anything parallel and transistor-hungry is improving by leaps and bounds: the 1080Ti is ~70% faster than its predecessor (with 50% more transistors), AMD is offering 8 cores for the price of 4, 32 for their server models, Intel's Phi is at 72... even smartphones are at 8-10 cores. As Moore predicted, dense ICs are packing more transistors every year, and it looks set to continue for the next several years at least.
Re:Moore's Law (Score:4, Interesting)
The benchmarks are quite revealing though. Performance took a big step up in 4k and max settings, but if you only game at 1080p and nearly max settings then a fairly old card is still more than adequate.
I wish reviewers would review cards for non-gaming use too. Will the fans ramp up if I have two 4k displays with browsers and Kicad open?
Re: (Score:2)
The 1080 Ti isn't really pitched at people still playing games at 1080p. The 970, which is a few years old now, is still a pretty solid choice for 1080p gaming and its direct successor, the 1070, is overkill (and just fine for 1440p in many cases). Hell, running a lot of games on a 1080 Ti at 1080p, you will probably only see a modest improvement in performance over older cards before you hit CPU-constraints anyway.
The 1080 Ti is really designed for two things; 4K gaming and VR (and, to some degree, people
Re: (Score:3)
Re: (Score:1)
$150 40" refurb RCA TV 1080p on a gtx1070. Looks great on ultra and high settings.
Re: (Score:2)
Large 1080p tv sets are widely available and very cheap these days...
Re: (Score:2)
The 1080 Ti is really designed for two things; 4K gaming and VR (and, to some degree, people wanting to do 1080p or 1440p gaming at 120Hz).
Yeah, the question for me isn't whether I upgrade from a 1070 to the 1080Ti, it's whether I upgrade from a 1440p screen and a 1070 to a 4k screen and the 1080Ti.
Unless I turn on a lot of anti-aliasing all the games I own run at 1440p and max settings with great framerates already, and a 27" monitor at 1440p doesn't really need AA.
Re: (Score:1)
Are you seriously comparing a PCIe board to a CPU?! WTF are you smoking? Graphics card have a GPU, memory and a transformer on them. Have you never seen a naked graphics card or what? The GPU itself is smaller than any PC CPU. So yes, they are packing more into the same space because a graphics card itself is like a motherboard and even Mini-ITX motherboards are larger.
Re: (Score:2)
Graphics cards are also LARGE. A PCIe board takes up more room than even the largest of processors in the x86 line in all its history.
Are you high?
The GPU is smaller or at most the same size as the CPU.
1080Ti and Titan X Pascal have a die size of 471 square millimeters. That is the largest chip up to date.
Ryzen 1800X has a die size of a little bit over 195 square millimeters. Yes, that's smaller than the GPU die size but really not that big of a difference.
Latest Intel's CPU die size are notoriously difficult to find, I can't be arsed to dig for them but then again, we're comparing small things and small things.
Maybe you included the whol
Re: (Score:3)
High-end GPUs have been larger than CPUs for many, many years now. It's a matter of perspective whether you find 471 mm^2 a significant step up from 195mm^2.
You might e.g. compare https://en.wikipedia.org/wiki/... [wikipedia.org] die sizes and https://en.wikipedia.org/wiki/... [wikipedia.org]
Really old generations aren't listed with die sizes there, but even the first generation that is (geforce 8xxx) includes e.g. the GeForce 8800 GTS (nov 2006) at 484 mm^2
Even a 10-core (modern) broadwell-E chip is around half that (http://hothardware
Re: (Score:2)
Agreed, mathematically it's "almost 2.5 times the surface" but really, at those dimensions there's not much of a difference.
But take a look at transistor count and you'll know why the die difference exists.
Ryzen 1800X has 4.8 billion transistors while GTX 1080 has 7.2 billion transistors. Hence the die size difference (well some of it of course).
Re: (Score:1)
I bet ledow (319597) is high because he smoked all the caps on his motherboard and power supply! X^D
What about drivers? (Score:2)
Are there great Linux drivers? Are they removing features from the Windows version so you have feature parity with Linux? Oh, well, fuck you Nvidia.
Re: What about drivers? (Score:2, Insightful)
There are for FreeBSD, and guess what, we have no problems with binary drivers whatsoever :p By the way, I'll go and tweak my system configuration by editing /etc/rc.conf now, while blasting Megadeth at full volume mixed by a sound system that doesn't require a truckload of daemons to get the job done.
Re: (Score:1)
WTF ? (Score:2)
What do they mean they're launching it today ? I've had a 1080Ti since November - and I had a month-long import delay after ordering in October last year !
Re: (Score:2)
I... rather suspect that you are mixing up which card you have. Either that, or you have an "Nvidya G-Forks 1080Ti" with a suspicious amount of Chinese script on the packaging and curiously disappointing performance.
The GTX 1080 was launched in May 2016. The Titan X (Pascal) in August 2016. You might also be thinking of the lower-end GTX 1050 Ti, which launched in October 2016.
Re: (Score:2)
Yeah, memory failure - it is the 1050 I got, which I got in October when it launched.
I'm not home so couldn't check for myself if the model matched.
Re: (Score:2)
Re: (Score:2)
Faster than the Titan... (Score:5, Interesting)
The "faster than a Titan" thing has been causing a bit of angst. The early reviews and benchmarks do indeed show that the 1080 Ti outperforms the Titan X (Pascal) in many cases. It's not universal; some games and benchmarks still favour the Titan by a tiny margin, but those are a minority.
But the sheer price of the Titan X (which was unprecedented in the Pascal series) has driven a lot of extra discontent this time around, especially as the 1080 Ti came out with a lower price than a lot of observers had been expecting (there were confident predictions from usually-reliable sources that it would be $200 north of where it actually landed). If you need a bit more salt in your diet, take a look at some of the threads over on the Nvidia forums today from disgruntled Titan X owners.
This is, however, pretty much par for the course in the high-end PC game and it's not as though Nvidia haven't slipped into a predictable cycle over their last few generations (at least since the 700-series) that makes clear how things work. If you want to buy a card that is "top of the range", you've basically got three options:
1) Buy the *80 card that arrives with the first wave of consumer cards in each generation. You will get a few months at the top of the tree, until the release of the (massively more expensive) Titan. This is always the cheapest of the three options, but also the most time-limited.
2) Buy the Titan that comes out a few months after the *80. This will have an absurd price tag - often twice that of the *80. It will be the fastest thing around for, in general, 6-9 months, and even then, the next card may only match it rather than beating it.
3) Buy the *80 Ti that comes out 6-9 months after the Titan. This will generally give you framerates in most games in the +/- 3% range of the Titan, but for a price much closer to the *80. This will hold its place at the top for anywhere from 9 to 15 months, until the release of the next generation of cards. In the next generation, the *80 will outperform the last generation *80 Ti and the *70 will offer broadly comparable (maybe slightly better) performance for around half the price.
I've been going for the *80 Ti route for a while now, on the grounds that the price/performance ratio tends to hold up better over time. I'm seeing complaints at the moment from people who bought a Titan within the last few weeks, which is just bizarre. The 1080 Ti has been known to be close to release since January, so why anybody would take the plunge on a Titan at $1200 under those circumstances is beyond me.
I'm working from home today and waiting for my 1080 Ti to be delivered. I wish I could say I'm not bouncing up and down in my chair going "SQUEEEEEE!!!" like a 12 year old girl at a One Direction concert, but I'm not sure how convincingly I could make that case.
Re: (Score:2)
I think the 10xx series still caught a few people off guard though because 28nm to 16nm gave it a huge boost causing a lot bigger performance difference and caused more impatience than usual. I doubt they'll skip a node like that again and I think the 1080 Ti is tactically priced to make 1080 owners want to sell & upgrade squishing the $500 market they expect Vega will launch in. I mean 30-35% performance increase for 40% higher MSRP is as close to linear as you're likely to get.
Re: (Score:2)
Actually yes there's a saying that 10nm is a crappy node again and GPUs are likely to go straight for 7nm (those nm sizes being creative accounting)
It's a new normal to get two GPU architectures on the same process node, we all expect a 16nm Volta.
Re: (Score:2)
The "faster than a Titan" thing has been causing a bit of angst. The early reviews and benchmarks do indeed show that the 1080 Ti outperforms the Titan X (Pascal) in many cases. It's not universal; some games and benchmarks still favour the Titan by a tiny margin, but those are a minority.
But the sheer price of the Titan X (which was unprecedented in the Pascal series) has driven a lot of extra discontent this time around, especially as the 1080 Ti came out with a lower price than a lot of observers had been expecting (there were confident predictions from usually-reliable sources that it would be $200 north of where it actually landed). If you need a bit more salt in your diet, take a look at some of the threads over on the Nvidia forums today from disgruntled Titan X owners.
This is, however, pretty much par for the course in the high-end PC game and it's not as though Nvidia haven't slipped into a predictable cycle over their last few generations (at least since the 700-series) that makes clear how things work. If you want to buy a card that is "top of the range", you've basically got three options:
1) Buy the *80 card that arrives with the first wave of consumer cards in each generation. You will get a few months at the top of the tree, until the release of the (massively more expensive) Titan. This is always the cheapest of the three options, but also the most time-limited.
2) Buy the Titan that comes out a few months after the *80. This will have an absurd price tag - often twice that of the *80. It will be the fastest thing around for, in general, 6-9 months, and even then, the next card may only match it rather than beating it.
3) Buy the *80 Ti that comes out 6-9 months after the Titan. This will generally give you framerates in most games in the +/- 3% range of the Titan, but for a price much closer to the *80. This will hold its place at the top for anywhere from 9 to 15 months, until the release of the next generation of cards. In the next generation, the *80 will outperform the last generation *80 Ti and the *70 will offer broadly comparable (maybe slightly better) performance for around half the price.
I've been going for the *80 Ti route for a while now, on the grounds that the price/performance ratio tends to hold up better over time. I'm seeing complaints at the moment from people who bought a Titan within the last few weeks, which is just bizarre. The 1080 Ti has been known to be close to release since January, so why anybody would take the plunge on a Titan at $1200 under those circumstances is beyond me.
I'm working from home today and waiting for my 1080 Ti to be delivered. I wish I could say I'm not bouncing up and down in my chair going "SQUEEEEEE!!!" like a 12 year old girl at a One Direction concert, but I'm not sure how convincingly I could make that case.
The "faster than a Titan" thing has been causing a bit of angst. The early reviews and benchmarks do indeed show that the 1080 Ti outperforms the Titan X (Pascal) in many cases. It's not universal; some games and benchmarks still favour the Titan by a tiny margin, but those are a minority.
But the sheer price of the Titan X (which was unprecedented in the Pascal series) has driven a lot of extra discontent this time around, especially as the 1080 Ti came out with a lower price than a lot of observers had been expecting (there were confident predictions from usually-reliable sources that it would be $200 north of where it actually landed). If you need a bit more salt in your diet, take a look at some of the threads over on the Nvidia forums today from disgruntled Titan X owners.
This is, however, pretty much par for the course in the high-end PC game and it's not as though Nvidia haven't slipped into a predictable cycle over their last few generations (at least since the 700-series) that makes clear how things work. If you want to buy a card that is "top of the range", you've basically got three options:
1) Buy the *80 card that arrives with the first wave of consumer cards in each generation. You will get a few months at the top of the tree, until the release of the (massively more expensive) Titan. This is always the cheapest of the three options, but also the most time-limited.
2) Buy the Titan that comes out a few months after the *80. This will have an absurd price tag - often twice that of the *80. It will be the fastest thing around for, in general, 6-9 months, and even then, the next card may only match it rather than beating it.
3) Buy the *80 Ti that comes out 6-9 months after the Titan. This will generally give you framerates in most games in the +/- 3% range of the Titan, but for a price much closer to the *80. This will hold its place at the top for anywhere from 9 to 15 months, until the release of the next generation of cards. In the next generation, the *80 will outperform the last generation *80 Ti and the *70 will offer broadly comparable (maybe slightly better) performance for around half the price.
I've been going for the *80 Ti route for a while now, on the grounds that the price/performance ratio tends to hold up better over time. I'm seeing complaints at the moment from people who bought a Titan within the last few weeks, which is just bizarre. The 1080 Ti has been known to be close to release since January, so why anybody would take the plunge on a Titan at $1200 under those circumstances is beyond me.
I'm working from home today and waiting for my 1080 Ti to be delivered. I wish I could say I'm not bouncing up and down in my chair going "SQUEEEEEE!!!" like a 12 year old girl at a One Direction concert, but I'm not sure how convincingly I could make that case.
Your analysis looks at the market timing, but it makes a lot of sense given how chib fabs run, as well. The *80 chips are likely what they are confident they can produce from the beginning, the Titans are likely the higher-binned parts, and the *80 Ti come out once all the fab issues have been ironed out and more chips are meeting that bin spec. It makes perfect sense that for each generation, the *80 Ti takes time for the fab to mature, but usually would come close to the Titan.
Re: (Score:1)
Biased? (Score:2)
Re: (Score:3)
The real comparison will be with the AMD Vega line, which is expected within the next month or two.
Nvidia is clearly worried that AMD have something good up their sleeves on that front, or we would not have seen a 1080 Ti with these specs at this price point.
Re: (Score:2)
The real comparison will be with the AMD Vega line, which is expected within the next month or two.
Nvidia is clearly worried that AMD have something good up their sleeves on that front, or we would not have seen a 1080 Ti with these specs at this price point.
Or maybe yields are better than expected. Or maybe the market analysis says that this price point results in more profit based on the marginal cost curve. Maybe they just have an aggressive new manager whose bonus is tied to units sold. To say "Nvidia is clearly worried" is putting an awful lot of certainty onto a purely speculative statement.
Re: (Score:2)
The pricing dance is extremely complex, but there's no question here about whether Nvidia's Magic Margin spreadsheet includes a giant column of anticipated AMD price-p
Re: (Score:2)
You're mistaken a bit, Fury X is a single GPU board. The dual GPU one is the Radeon Pro Duo, which is likely very rare.
Re: (Score:2)