Fury XT and Pro prices

Page 4 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

selni

Senior member
Oct 24, 2013
249
0
41
Doesn't DX12 solve that memory problem?
Two 4gb cards = 8gb of vram with DX12?

Can't imagine DX anything changing that - it's an architectural issue.

Eg a single Fury X has ~500GB/s bandwidth to it's local memory, but to access anything in a different card's memory, you're going over PCI-E, which is vastly slower. So you want everything each card uses stored locally if possible for performance. If you're doing AFR that still means 2x4GB ~= 4GB. If you're doing something else, it depends on the scheme but it's hard to imagine there not being a ton of shared assets required to be loaded by all cards.
 

SimianR

Senior member
Mar 10, 2011
609
16
81
I think anyone looking to get double or even close to double their VRAM out of their SLI/CF setup is going to be disappointed. Just googling the possibility of this brings up a ton of hurdles to overcome. I just don't see this feature being taken advantage of personally.

I agree. I don't think DX12 is going to work miracles - but it might be a step in the right direction from where we are now.
 

2is

Diamond Member
Apr 8, 2012
4,281
131
106
A right step indeed. The reduced CPU overhead and increased draw calls alone are huge.
 

Erenhardt

Diamond Member
Dec 1, 2012
3,251
105
101
Why am I not surprised when I saw your name as the most recent post, I know it would be something... Lets just say, not smart and just blind defense.

I'm sure you'd like to think that, but I'm talking about CF on it's own merits. You don't want to compare SLI vs CF support... It's not a battle you're going to win. Take solace in the fact that when CF is supported, it usually scales pretty well.

I'm quite used to the piles of crap that sit in the white box next to "2is" word. Not even bothering to read it most of the time. Feel Humbled I actually bothered this time.

Quite often sli doesn't even work with games that nv was involved in development - that just says alot about their incompetence.

And when it works, it is far behind amd crossfire. But I know the smoothness/$ is so yesterday, now its all about fps/W and inchPCB/$ is next big thing
 

2is

Diamond Member
Apr 8, 2012
4,281
131
106
I'm quite used to the piles of crap that sit in the white box next to "2is" word. Not even bothering to read it most of the time. Feel Humbled I actually bothered this time.

Quite often sli doesn't even work with games that nv was involved in development - that just says alot about their incompetence.

And when it works, it is far behind amd crossfire. But I know the smoothness/$ is so yesterday, now its all about fps/W and inchPCB/$ is next big thing

You can at least try to be original with your come backs. Curious If you think SLI is broken "quite often" how would you describe CF that's broken far more often? Or do you play the ignorance card and pretend those cases don't exist? It's really more of a rhetorical question than anything. I already know the answer. Pretty sure you do too.
 

LTC8K6

Lifer
Mar 10, 2004
28,520
1,575
126
Ultimately the point is that gamers believe that two 4GB cards can’t possibly give you the 8GB of useful memory. That may have been true for the last 25 years of PC gaming, but thats not true with Mantle and its not true with the low overhead APIs that follow in Mantle’s footsteps. – @Thracks (Robert Hallock, AMD)
 
Feb 19, 2009
10,457
10
76
2is is right though. Crossfire doesn't always work. Still doesn't work in The Witcher 3, what I'm assuming is a AAA GOTY contender, for example. So what should really be said is "for just $100 more when going Fury CF, when it works". Same for SLI, but it's the truth.

It works. Which is a shocker for a GameWorks title!

But you do need to tweak the .ini file to get CF to behave with the customized FXAA/TXAA hybrid implementation. Find the entry, TemporalAA and disable it. I don't notice any IQ change, and there's no performance impact.

I do agree, Witcher 3 is definitely GOTY contender, but it will have strong competition from latter titles this year, Fallout 4 especially and Battlefront.

http://www.techspot.com/review/1011-nvidia-geforce-gtx-980-ti/page6.html

 

chimaxi83

Diamond Member
May 18, 2003
5,456
61
101
It works. Which is a shocker for a GameWorks title!

But you do need to tweak the .ini file to get CF to behave with the customized FXAA/TXAA hybrid implementation. Find the entry, TemporalAA and disable it. I don't notice any IQ change, and there's no performance impact.

I do agree, Witcher 3 is definitely GOTY contender, but it will have strong competition from latter titles this year, Fallout 4 especially and Battlefront.

http://www.techspot.com/review/1011-nvidia-geforce-gtx-980-ti/page6.html


Seriously, no more flickering? I'll try this out later today.
 

RussianSensation

Elite Member
Sep 5, 2003
19,458
765
126
Fury might help them a bit but Fury X offers nothing over 980 Ti at that price point.

- At least $100 less than EVGA GTX980Ti Hybrid
- Most likely superior to a reference 980Ti - for the same price it runs cooler and quieter in both overclocked and stock states
- One will be able to create the most powerful small form factor chassis PCs with Fury X or Fury X CF, something that's a lot harder to do with GM200 cards
- 300-600W of heat will be exhausted out of the case at quiet noise levels and low temperatures in stock or overclocked states, something not possible with any air cooled GM200 setup.

Get yourself a CF setup if you don't have one, start buying games on release day. You'll have your own personal database in no time.

Not everyone buys all AAA games on release date, especially when a lot of games have $30+ of DLC which makes a $60 game essentially a $90 game. Batman Arkham Knight is $95 CDN for me with Season pass/DLC on Steam. GOTY edition of this game will be $7.5-10 very quickly given the track record of this franchise. Also, a lot of gamers have a giant backlog of games across GOG, Steam, UPlay, Origin. What that means is with a social life, friends, family, job, sports, the backlog is often a natural occurrence. Another example is Borderlands 2 which I believe was $80-90 for the entire game + DLC but on this Steam sale it was $7.99 for GOTY edition. Just 2 of these games bought at launch would be $180 CDN vs. say $20 if bought later. A lot of gamers here buy 10+ games a year which means buying games at $10 vs. $60-90 results in a massive savings.

If you are the type of gamer who only buys $60-90 games at launch, then you have a point but a lot of PC gamers do not do that. Some games are so broken or are so poorly done (AC Unity or Watch Dogs), that they aren't even worth playing at launch until they receive many patches and several driver updates. Knowing all of this, many gamers might buy some games at launch but wait for many others due to backlog, not to mention that too many games come with DLCs and/or are broken on release which means it's actually better to wait to buy them later once they are fixed. It's not like the old days where if you got a $60 game, it was actually 99.9% complete with very few bugs/glitches and performance was well optimized. Today, you might buy a game that results in a magic developer patch that boost performance 45% months later. If you bought it at launch and your performance was unsatisfactory, you might proceed to buy a $650 videocard when a $300 card would have ran the game just fine.

But that's not even the point since $1100 Fury PRO CF vs. $1000 Titan X takes all of that into account already. When CF doesn't work, performance will be 87-90% as good and when CF works, performance will bury the Titan X. Many modern games work well with CF which means on average the former setup is far superior, especially if one considers the TX more or less requires a cooler swap - so add another $100 to the cost, essentially making them equal. Of course except Grooveriding and a couple other guys, TX owners will continue to defend their purchases but anyone else objective can see how the TX was yet another NV marketing rip-off. Instead of admitting how AMD is about to change the entire $550-650 high-end GPU landscape, the TX owners are in denial phase defending their purchases. No credit is given to AMD where it's actually due, especially from people who were claiming AMD is never going to even match a Titan X and here we are with a possibility it'll beat the Titan X at 4K.

I guess anyone wanting to put 2-3 of these in Crossfire and a couple 4K monitors is out of luck:

Is this a troll post from you?

A great gaming experience on just a single 4K monitor more or less asks for 2x 980Ti/TXs or Fury cards. Not only will 2x4K monitors destroy even Quad Titan SLI since scaling is not great beyond 2 cards but very few gamers play on non-RTS style genres on just 2 monitors because you end up with 2 bezels staring right at the gamer's face. Dual monitor gaming is probably the worst option possible between 1 large screen/projector and triple monitor gaming.

Your very point contradicts your next example below:

"The GeForce GTX TITAN X SLI at 4K was by far the most amazing experience in GTA V. However, to run with "Ultra" grass it looks like a third TITAN X would be needed in a 3-Way SLI configuration. That is a lot of GPU performance to push GTA V fully at 4K"

Ya, so HardOCP states they needed 3x Titans in SLI to run GTA V on a single 4K monitor, what gaming is anyone doing on 2x 4K monitors with modern cards?

I wonder how angry Fury X owners will be if they try to run games like GTA V with VSR or 4K + AA and find it hitting their tiny 4GB limit? Hmmm..

Let's wait for benchmarks but considering 980 SLI/R9 295X2 outperform Titan X in 4K, your 4GB VRAM concern for GTA V has already been addressed by professional reviewers.



More so, that bench is without everything maxed out. Once the entire game is maxed out at 4K, Titan X SLI is a slide-show. Essentially no dual cards with single chips on each available today can max out GTA V at 4K with everything on Ultra. Comparing all these setups, they are all unplayable unless someone likes gaming at console level FPS with insane stuttering.



Exactly. 50% faster when using two GPU's and paying more for them isn't exactly a homerun achievement.

You are confused. It's $1100 Fury CF => projected 90% as fast as the TX when CF doesn't work and at least 50% faster when CF works, all for $100 more just 3 months later. In PC gaming, that's called a no brainer and this was discussed 3 months ago why Titan X would be obsoleted by Fury PRO but many NV supporters dismissed this notion. Now they are all quiet focusing in on 4GB HBM...NV took them for a ride where now one will be able to get 90% of TX SLI performance in dual Fury PROs for $900 less. Oh, and the after-market coolers on Fury PRO will ensure the card stays cool and quiet, unlike the Titan X which was a jet engine in overclocked states on a reference cooler. You trying to say that 87-90% of TX SLI performance for $900 less OR having 87-90% of Titan X performance for $450 less while running cool and quiet isn't a good achievement just 3 months later is some statement alright. I am pretty sure 3 months ago you didn't even dream that a $550 Fury card would be this close to a Titan X and recalling your posts, you didn't even seem confident that Fury X would beat a 980Ti at 4K. After all, without even waiting for specs or benchmarks you ordered 980Ti reference cards. Everyone knows you had no intention of buying AMD cards in CF since apparently you intended to keep your cards for 4-5 years anyway which meant 4GB wouldn't be enough for your sub-1440P monitor.

If you want an apples to apples comparison. CF Fury vs SLI 980Ti and you're still slower for the same amount of money.

That's not the point. Obviously with a 980Ti out today at $650-700, the comparison should be in relation to TX as of now. The point was to bring up what happened in the past and how people just ignore what they were told 3 months ago without admitting they were proven wrong:

1) After-market 980Ti would make Titan X irrelevant
2) After-market 980Ti would outperform Titan X out of the box, with 0 overclocking for $300+ less, while running cooler and quieter, with better components too
3) Fury Pro will offer 87-90% of the performance of the Titan X for nearly 1/2 the price (back then we projected $500-550)
4) Fury X has a serious shot of outperforming the Titan X at 4K
5) 980 was an overpriced rip-off for the last 9 months at $550 and for those who want to spend $500+ on a card and aren't in a rush, it's worth waiting for Fury cards.

Most, if not all of these points, were dismissed by a lot of NV fans on this forum and now they are all quiet after being proven wrong.

Looks like most of these things have come true and instead of admitting how many people on this forum called each one of those points despite being told how AMD is done and won't even improve perf/watt on 28nm, certain posters instead are in spin mode about 4GB HBM not sufficient for dual 4K monitor gaming. Let's not even forget the insane BS made up on this very forum about 2x2048 shader Tonga with HBM or Hawaii with HBM and no other improvements. Now AMD has released a card with 1.5X the perf/watt increase over 290X in Fury X and supposedly 2X the improvement in the Fury Nano and people are downplaying this, despite many of the same users spouting crap like Fury might only beat 980 by 20% at best, while using 300-350W of power doing so.
 
Last edited:
Feb 19, 2009
10,457
10
76
Looks like most of these things have come true and instead of admitting how many people on this forum called each one of those points despite being told how AMD is done and won't even improve perf/watt on 28nm, certain posters instead are in spin mode about 4GB HBM not sufficient for dual 4K monitor gaming. Let's not even forget the insane BS made up on this very forum about 2x2048 shader Tonga with HBM or Hawaii with HBM and no other improvements. Now AMD has released a card with 1.5X the perf/watt increase over 290X in Fury X and supposedly 2X the improvement in the Fury Nano and people are downplaying this, despite many of the same users spouting crap like Fury might only beat 980 by 20% at best, while using 300-350W of power doing so.

It separates the shills from those who actually have logic.
 

2is

Diamond Member
Apr 8, 2012
4,281
131
106
Looks like most of these things have come true and instead of admitting how many people on this forum called each one of those points despite being told how AMD is done and won't even improve perf/watt on 28nm, certain posters instead are in spin mode about 4GB HBM not sufficient for dual 4K monitor gaming. Let's not even forget the insane BS made up on this very forum about 2x2048 shader Tonga with HBM or Hawaii with HBM and no other improvements. Now AMD has released a card with 1.5X the perf/watt increase over 290X in Fury X and supposedly 2X the improvement in the Fury Nano and people are downplaying this, despite many of the same users spouting crap like Fury might only beat 980 by 20% at best, while using 300-350W of power doing so.

I don't see anyone down playing anything really. You compared price/performance to Titan when it's really the 980Ti it should be compared to. You can't expect not to be countered when you paint that sort of picture. People who bought titan aren't worried about saving money on GPU's, that's why they bought Titans. The have the money and to them the instant gratification is wroth the price of admission. They are not wrong for feeling this way, it's one of their enjoyments in life. Everyone knew a 980Ti was coming before Titan was even released. They didn't care, they bought it anyway. Why does that hurt your feelings?
 

5150Joker

Diamond Member
Feb 6, 2002
5,549
0
71
www.techinferno.com
Baasha ran these on 3x Titans on a single 5K display. If the above leaked graph is true with Fury X choking at resolutions above 4K, it's gonna be a disappointment for those that opt for such a setup but with 3x Fury (and there are many out there that can easily afford it):




A top tier card shouldn't be limited to certain resolutions and settings in fear of choking on it's minuscule vram. So it has AIO, great, but what good is that if it chokes by not having enough vram? Guess we'll find out when AMD finally lets reviewers put out benchmarks and then we'll see how many of them really put it to the test. I am more curious to see how Nano will stack up against 970 and what it's price will be. Maybe AMD will finally have a viable part to compete against the 970 even if it's a year late.
 
Last edited:

VulgarDisplay

Diamond Member
Apr 3, 2009
6,188
2
76
Baasha ran these on 3x Titans on a single 5K display. If the above leaked graph is true with Fury X choking at resolutions above 4K, it's gonna be a disappointment for those that opt for such a setup but with 3x Fury (and there are many out there that can easily afford it):




A top tier card shouldn't be limited to certain resolutions and settings in fear of choking on it's minuscule vram. So it has AIO, great, but what good is that if it chokes by not having enough vram? Guess we'll find out when AMD finally lets reviewers put out benchmarks and then we'll see how many of them really put it to the test. I am more curious to see how Nano will stack up against 970 and what it's price will be. Maybe AMD will finally have a viable part to compete against the 970 even if it's a year late.
You do realize that games use the vram that is available to them right? That is in no way a guarantee that the gpu's performance is hindered at all.

Stop spreading blatant misinformation about this.
 

3DVagabond

Lifer
Aug 10, 2009
11,951
204
106
Fiji Pro at the same clocks should only be 14% slower than Fury X. 980 stands 0 chance. It's going to be HD7950 OC vs. 7970 OC situation as long as AMD keeps 64 ROPs and the entire 4096-bit bus.

Looks like some of us where right where we predicted Fury Pro to offer 87-90% of Titan X performance for $500-550. Also, this means > 50% faster performance than Titan X for just $100 more when going Fury CF. It's interesting how this exact scenario was being projected 3 months ago but Titan X owners would hear none of it.

980 will probably end up in no man's land in the hands of overclockers because based on rough specs of the Vanilla Fury, it should absolutely cream the 980 at high rez considering 980 will barely beat a 390X.

Also, you are using $469 price after rebates but it's not as if AMD's AiBs can't include rebates too. As far as the market goes it'll be $499 980 vs. $549 Fury Pro. NV will need a game bundle or another price drop.

If a 32db card with HBM that's faster isn't worth $80 more, then I don't know what is. You would just have to be completely opposed to buying AMD not to think it's better value.
 

3DVagabond

Lifer
Aug 10, 2009
11,951
204
106
Can't imagine DX anything changing that - it's an architectural issue.

Eg a single Fury X has ~500GB/s bandwidth to it's local memory, but to access anything in a different card's memory, you're going over PCI-E, which is vastly slower. So you want everything each card uses stored locally if possible for performance. If you're doing AFR that still means 2x4GB ~= 4GB. If you're doing something else, it depends on the scheme but it's hard to imagine there not being a ton of shared assets required to be loaded by all cards.

They don't share memory. They just don't have to duplicate it. Each card only uses memory for the rendering it's doing. You can do split frame rendering, but you can also just allocate different aspects to different cards. Kind of like a separate card can do just PhysX now. They will be able toy do that with different parts of the rendering pipeline.
 

gamervivek

Senior member
Jan 17, 2011
490
53
91
cp'ing my b3d posts,

Far Cry 4 seems to be the best case scenario, where the 290X is equal or slightly faster than 980.

And now crossfire works rather well with the game after the patching up. Smacks the GM200 cards by 70% in TR's review.

www.techreport.com/review/28356/nvidia-geforce-gtx-980-ti-graphics-card-reviewed/7



Anyway, the numbers from the "leaked" slides during Titan X's launch had far cry 4 as the best game against Titan X.

Titan X faster than 290X in far cry 4 by (TS?)29.1% TP - 31.5% TR- 25%

And 390X(now Fury, thanks moor?) faster than 290X by 55% , so 20.1% , 17.8% and 24% faster than Titan X respectively. Would be hard for 980Ti to catch up even with overclocking.

The other would be alien isolation where it's 18% or so faster, while BF4 and Tomb Raider had them at parity.


Expreview have the slide in question, but their logo covers up the *.

http://img.expreview.com/news/2015/06/17/AMD_Radeon_FuryX_20.jpg
 

Erenhardt

Diamond Member
Dec 1, 2012
3,251
105
101
cp'ing my b3d posts,

Far Cry 4 seems to be the best case scenario, where the 290X is equal or slightly faster than 980.

And now crossfire works rather well with the game after the patching up. Smacks the GM200 cards by 70% in TR's review.

www.techreport.com/review/28356/nvidia-geforce-gtx-980-ti-graphics-card-reviewed/7



Anyway, the numbers from the "leaked" slides during Titan X's launch had far cry 4 as the best game against Titan X.

Titan X faster than 290X in far cry 4 by (TS?)29.1% TP - 31.5% TR- 25%

And 390X(now Fury, thanks moor?) faster than 290X by 55% , so 20.1% , 17.8% and 24% faster than Titan X respectively. Would be hard for 980Ti to catch up even with overclocking.

The other would be alien isolation where it's 18% or so faster, while BF4 and Tomb Raider had them at parity.


Expreview have the slide in question, but their logo covers up the *.

http://img.expreview.com/news/2015/06/17/AMD_Radeon_FuryX_20.jpg

Where did you get the numbers for Fury from? I didn't see any official benchmark against 290X...
 

Zstream

Diamond Member
Oct 24, 2005
3,395
277
136
I don't see anyone down playing anything really. You compared price/performance to Titan when it's really the 980Ti it should be compared to. You can't expect not to be countered when you paint that sort of picture. People who bought titan aren't worried about saving money on GPU's, that's why they bought Titans. The have the money and to them the instant gratification is wroth the price of admission. They are not wrong for feeling this way, it's one of their enjoyments in life. Everyone knew a 980Ti was coming before Titan was even released. They didn't care, they bought it anyway. Why does that hurt your feelings?



We get it. You won't ever buy an AMD card for whatever reason. I'm not sure why some posters need to go round and round when it's clear they wont but the product. I'm really happy about fury and the features you get with the card. I won't be getting it on release bit from am enthusiast pov, you have to be excited about the product.
 

LTC8K6

Lifer
Mar 10, 2004
28,520
1,575
126
cp'ing my b3d posts,

Far Cry 4 seems to be the best case scenario, where the 290X is equal or slightly faster than 980.

And now crossfire works rather well with the game after the patching up. Smacks the GM200 cards by 70% in TR's review.

www.techreport.com/review/28356/nvidia-geforce-gtx-980-ti-graphics-card-reviewed/7



Anyway, the numbers from the "leaked" slides during Titan X's launch had far cry 4 as the best game against Titan X.

Titan X faster than 290X in far cry 4 by (TS?)29.1% TP - 31.5% TR- 25%

And 390X(now Fury, thanks moor?) faster than 290X by 55% , so 20.1% , 17.8% and 24% faster than Titan X respectively. Would be hard for 980Ti to catch up even with overclocking.

The other would be alien isolation where it's 18% or so faster, while BF4 and Tomb Raider had them at parity.


Expreview have the slide in question, but their logo covers up the *.

http://img.expreview.com/news/2015/06/17/AMD_Radeon_FuryX_20.jpg

It says "For system info refer to system #18 in the footnotes".
 

guskline

Diamond Member
Apr 17, 2006
5,338
476
126
5150Joker Comparing a $649 Fury X with a TitanX (@$999) is a comparison but NOT of equal cards. Running 3 Titan X's is @$3000 vs $1950 for 3 Fury X's.

I suspect AMD could not get an 8G card ready or decided to wait for HBM2 to release such a high resolution card. Tough when you are releasing a new model that you want to run well. No doubt their highest end consumer card, for now, is limited to 4G Vram, HBM1.

If you have followed the releases from AMD, and especially Joe Macri, he recently (last few weeks) acknowledged this limitation and said he addressed it by assigning engineers specifically to better utilize the Vram. Only extensive testing will see if his efforts bore fruit.

The real battle appears to be between the GTX980 TI and the Fury X. The price is comparable, though the GTX980 TI has more Vram.

Only when reviewers get these cards and run them at 4k and multiple 4k monitors with various games will we see the results.
 
Last edited:
sale-70-410-exam    | Exam-200-125-pdf    | we-sale-70-410-exam    | hot-sale-70-410-exam    | Latest-exam-700-603-Dumps    | Dumps-98-363-exams-date    | Certs-200-125-date    | Dumps-300-075-exams-date    | hot-sale-book-C8010-726-book    | Hot-Sale-200-310-Exam    | Exam-Description-200-310-dumps?    | hot-sale-book-200-125-book    | Latest-Updated-300-209-Exam    | Dumps-210-260-exams-date    | Download-200-125-Exam-PDF    | Exam-Description-300-101-dumps    | Certs-300-101-date    | Hot-Sale-300-075-Exam    | Latest-exam-200-125-Dumps    | Exam-Description-200-125-dumps    | Latest-Updated-300-075-Exam    | hot-sale-book-210-260-book    | Dumps-200-901-exams-date    | Certs-200-901-date    | Latest-exam-1Z0-062-Dumps    | Hot-Sale-1Z0-062-Exam    | Certs-CSSLP-date    | 100%-Pass-70-383-Exams    | Latest-JN0-360-real-exam-questions    | 100%-Pass-4A0-100-Real-Exam-Questions    | Dumps-300-135-exams-date    | Passed-200-105-Tech-Exams    | Latest-Updated-200-310-Exam    | Download-300-070-Exam-PDF    | Hot-Sale-JN0-360-Exam    | 100%-Pass-JN0-360-Exams    | 100%-Pass-JN0-360-Real-Exam-Questions    | Dumps-JN0-360-exams-date    | Exam-Description-1Z0-876-dumps    | Latest-exam-1Z0-876-Dumps    | Dumps-HPE0-Y53-exams-date    | 2017-Latest-HPE0-Y53-Exam    | 100%-Pass-HPE0-Y53-Real-Exam-Questions    | Pass-4A0-100-Exam    | Latest-4A0-100-Questions    | Dumps-98-365-exams-date    | 2017-Latest-98-365-Exam    | 100%-Pass-VCS-254-Exams    | 2017-Latest-VCS-273-Exam    | Dumps-200-355-exams-date    | 2017-Latest-300-320-Exam    | Pass-300-101-Exam    | 100%-Pass-300-115-Exams    |
http://www.portvapes.co.uk/    | http://www.portvapes.co.uk/    |