Fury Nano: First results in!

Page 8 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.
Status
Not open for further replies.
Feb 19, 2009
10,457
10
76
Yup. NV has been slapping marketing TDP for years. It's about time AMD plays the same game. I would just put a 150-175W TDP on a 225-250W card. The same people who think TDP = power usage wouldn't know any better since it's not like they read reviews/pay attention to proper power consumption testing.

With nearly the same specs as the Fury X and 100W less TDP, AMD is getting smarter when it comes to the marketing game.


Well I guess they finally caught on that NV under-assign the TDP and have gotten away with it for years so they should match the same. Just for the typical uninformed buyer.

Still, up to 1Ghz is a very impressive feat at the rumored 150W gaming load, I guess it confirms Zlatan saying the clock speed is 4 digits and performance is very close to Fury X.

If its their best bin chips, full dies... yeah the price won't be cheap.
 

casiofx

Senior member
Mar 24, 2015
369
36
61
The truth that your full of numbers and information but you hardly ever have nothing good to say about .............. like a walking AMD billboared and that mabe the Nano is delayed.
What a blatant hypocrite you are!
Where's your rebuttal other than personal attack?
RS's argument is valid backed up with data, yours is personal comment without support.
If you didn't know better, RS is agnostic user, he gives both companies their credits, just like when Nvidia is doing better on their cards.
Learn to read more of his comments in other threads and stop thread crapping.
 

LTC8K6

Lifer
Mar 10, 2004
28,520
1,575
126
I don't understand why Nano was not released first. It looks like it's possibly the star of the AMD show.
 

bystander36

Diamond Member
Apr 1, 2013
5,154
132
106
I don't understand why Nano was not released first. It looks like it's possibly the star of the AMD show.

If they are binned, they likely had to slowly stock pile them before release, and let's be honest, most people are more concerned with performance than performance per watt.
 

shady28

Platinum Member
Apr 11, 2004
2,520
397
126
From a marketing / merchandising standpoint -

TDP in and of itself really isn't relevant in the marketplace.

It's a question of which broad group does it fall into as far as who will buy it -

No 6-pin
Single 6-pin
Dual 6-pin (or single 8-pin)
6+8 pin
8+8 pin

Every time you move down the ladder above, your potential market shrinks. I would bet that the first 3 of that list makes up 90%+ of potential dGPU market.

And before it starts lets dispense with the 'but you can change the PSU' etc. As soon as we start talking about that, we're not talking about the broad market anymore.

The 970 is in the dual 6-pin / single 8-pin category, so that's the Nano's main competitor in terms of what its potential market is. It's quite a bit larger than the 980 / 290 / 390 market.

I would think a Nano with ~GTX 980 performance (assumption) would sell very well provided it's priced to compete with the 980. It addresses the biggest issues with 980 / 290 / 390 type cards - big power requirements, big heat output, and big size - without compromising performance.
 

tential

Diamond Member
May 13, 2008
7,348
642
121
Well I guess they finally caught on that NV under-assign the TDP and have gotten away with it for years so they should match the same. Just for the typical uninformed buyer.

Still, up to 1Ghz is a very impressive feat at the rumored 150W gaming load, I guess it confirms Zlatan saying the clock speed is 4 digits and performance is very close to Fury X.

If its their best bin chips, full dies... yeah the price won't be cheap.

NV would have put a 150W TDP.... Maybe even 125W Not 175W for a 150W gaming load.

Do you not know NV?
 

Abwx

Lifer
Apr 2, 2011
11,536
4,323
136
If they are binned, they likely had to slowly stock pile them before release, and let's be honest, most people are more concerned with performance than performance per watt.

Quite possible that there s extreme binning, but still, the numbers are above what is generaly possible and it s not like 28nm wasnt already mature.

As for perf/watt we ll see if this debate will keep being important in the coming times, if Nano perform well i predict that the new holy grail will be extreme overclocking, power be damned...
 

LTC8K6

Lifer
Mar 10, 2004
28,520
1,575
126
I would think a Nano with ~GTX 980 performance (assumption) would sell very well

I think it would have been a great release right around the time of the 980Ti release.

A hand grenade tossed gently into NV's campfire.
 

casiofx

Senior member
Mar 24, 2015
369
36
61
From a marketing / merchandising standpoint -

TDP in and of itself really isn't relevant in the marketplace.

It's a question of which broad group does it fall into as far as who will buy it -

No 6-pin
Single 6-pin
Dual 6-pin (or single 8-pin)
6+8 pin
8+8 pin

Every time you move down the ladder above, your potential market shrinks. I would bet that the first 3 of that list makes up 90%+ of potential dGPU market.

And before it starts lets dispense with the 'but you can change the PSU' etc. As soon as we start talking about that, we're not talking about the broad market anymore.

The 970 is in the dual 6-pin / single 8-pin category, so that's the Nano's main competitor in terms of what its potential market is. It's quite a bit larger than the 980 / 290 / 390 market.

I would think a Nano with ~GTX 980 performance (assumption) would sell very well provided it's priced to compete with the 980. It addresses the biggest issues with 980 / 290 / 390 type cards - big power requirements, big heat output, and big size - without compromising performance.
And it is dual slot, fits into small case easily and can be powered by smaller PSUs.
Much like a mainstream high end card.
 

railven

Diamond Member
Mar 25, 2010
6,604
561
126
So...anyone else getting that weird hype vibe again? Fury X was talked up and (in my opinion) it under delivered in just about every aspect.

Fury (non-Pro) got literally no fanfare around here (at least I didn't think it did) and it released beautiful.

What I'm trying to say is, it feels like Nano is getting built up too much. If Nano is the secret sauce, and it delivers to some of these expectations, AMD literally may have cannibalized all the other SKUs.

27'th can't get here fast enough if it is the official launch date.
 
Feb 19, 2009
10,457
10
76
They wont cannibalize other SKUs if they price it $600.

Still, I would have preferred a 850mhz core clock $449 part, with room for manual OC to 1ghz, cheaper for gamers!
 

RampantAndroid

Diamond Member
Jun 27, 2004
6,591
3
81
So...anyone else getting that weird hype vibe again? Fury X was talked up and (in my opinion) it under delivered in just about every aspect.

Fury (non-Pro) got literally no fanfare around here (at least I didn't think it did) and it released beautiful.

What I'm trying to say is, it feels like Nano is getting built up too much. If Nano is the secret sauce, and it delivers to some of these expectations, AMD literally may have cannibalized all the other SKUs.

27'th can't get here fast enough if it is the official launch date.

Bolded is what I find odd, really. If everything is true about this card (all of the rumors and consumption numbers) then this card will totally blow even the Fury out of the water...
 

iiiankiii

Senior member
Apr 4, 2008
759
47
91
I wonder what a FIJI HBM derivative would do for power consumption on a mid to low tier card like the GTX 960/750TI. I hope somebody grab a Nano and downclock/undervolt it to match the performance of the GTX 960/750ti to get an idea of the power consumption.
 

tential

Diamond Member
May 13, 2008
7,348
642
121
So...anyone else getting that weird hype vibe again? Fury X was talked up and (in my opinion) it under delivered in just about every aspect.

Fury (non-Pro) got literally no fanfare around here (at least I didn't think it did) and it released beautiful.

What I'm trying to say is, it feels like Nano is getting built up too much. If Nano is the secret sauce, and it delivers to some of these expectations, AMD literally may have cannibalized all the other SKUs.

27'th can't get here fast enough if it is the official launch date.

I'm getting that "Surely you can't underdeliver three times in a row" vibe....
 

bystander36

Diamond Member
Apr 1, 2013
5,154
132
106
So...anyone else getting that weird hype vibe again? Fury X was talked up and (in my opinion) it under delivered in just about every aspect.

Fury (non-Pro) got literally no fanfare around here (at least I didn't think it did) and it released beautiful.

What I'm trying to say is, it feels like Nano is getting built up too much. If Nano is the secret sauce, and it delivers to some of these expectations, AMD literally may have cannibalized all the other SKUs.

27'th can't get here fast enough if it is the official launch date.

To me, Nano is for a niche market and I don't think AMD thinks otherwise. I'm sure the average user around here will think it's underwhelming, but it wasn't meant for them.
 

SolMiester

Diamond Member
Dec 19, 2004
5,330
17
76
What a blatant hypocrite you are!
Where's your rebuttal other than personal attack?
RS's argument is valid backed up with data, yours is personal comment without support.
If you didn't know better, RS is agnostic user, he gives both companies their credits, just like when Nvidia is doing better on their cards.
Learn to read more of his comments in other threads and stop thread crapping.

TBH, I stopped reading RS's posts a long time ago, when I got tired of the cut and paste wall of text as I couldnt be bothered trying to got clarify his numbers, but hey, lap it up mate!
 
Feb 19, 2009
10,457
10
76
Stop thread crapping. If you don't wanna read someone's post then don't. The personal attacks are getting out of hand, where's the mods?
 

raghu78

Diamond Member
Aug 23, 2012
4,093
1,475
136
There goes the hope of a price of USD 450 for R9 Nano. If its a fully enabled Fiji there is no way AMD are going to price this card at anything less than USD 500-550. USD 500 would be ok if it can match ref 980. Whats going to be interesting is how does the stock cooler handle overclocking (noise/temps) and whats the perf gain from OC.

Stop thread crapping. If you don't wanna read someone's post then don't. The personal attacks are getting out of hand, where's the mods?

report the post.
 

SimianR

Senior member
Mar 10, 2011
609
16
81
Where's the $600 number coming from? Just because the cost of something is the same doesn't mean it necessarily gets priced the same. I'm hoping for a $449 price point but I can see them pricing it at $500. Anything more than that to me just seems crazy, even if it is a specialty, niche card. Keep in mind they save the cost of the AIO water cooler here. I have a feeling AMD priced the fury and fury X at those price points because they just don't have the supply to meet demand right now, so they know they can get slightly more for them in the mean time. Once the supply ramps up I wouldn't doubt it if we see price cuts on the all the Fiji based GPUs.
 

RussianSensation

Elite Member
Sep 5, 2003
19,458
765
126
The truth that your full of numbers and information

I'll take that as a compliment. Yes, I believe it's better to be as informed as possible to actually have data backing up what I state vs. often baseless opinions posted by various posters. I still remember how you were dead wrong on bitcoin mining for 5 years straight despite all the data provided to you by myself and various posters. Ever since, it's been very clear to me you do not like it when people prove you wrong with hard data which I suppose is why you don't like to see data being used to undermine your position on any GPU recommendations.

but you hardly ever have nothing good to say about ..............

That's your opinion. If you do not like what I say, put me on ignore. In any event, instead of addressing my post, you discuss me as a person and bring AMD billboard cheer-leading into the discussion when I specifically provided evidence of how the current rumors were discussing the Nano's reveal dates.

like a walking AMD billboared

I am pretty sure I've recommended more NV cards and posted way more deals on NV cards since I've joined this forum that you ever have. I would take any bet on that. But at the same time I've recommended people great ATI/AMD cards over the years and bitcoin mining which hopefully got them a superior product and made them some $. I have both NV and AMD GPUs in my desktop PCs. But keep on believing in some crazy mantra that I am a walking AMD billboard whenever you do not like when I speak the truth about bad products like GTX750Ti/950/960 (as well as 285/380/Fury X from AMD, etc.). Of course you never see me criticize both camps or recommend both camps depending on which products are worth buying.

that mabe the Nano is delayed.

Please do tell us when AMD announced an official launch date for the Nano? For Nano to be delayed, AMD would have needed to commit to a certain date. Using this logic, I'll just go ahead and claim that GTX780Ti was delayed by nearly a year and GTX980Ti was delayed by at least 8 months. Funny how 'delays' work in your world.

Rebuttal enough?

When your snide remarks on XFX's current lack of knowledge on Nano's hard launch were addressed with announcement date =! hard launch, you ignored those comments. Furthermore, depending on the availability, not all AIBs may get dibs on the Nano. Only Asus and Sapphire are currently allowed to sell the Fury cards. In that case I guess XFX would also to this date have no idea when the Fury is launching, right?

is this his other account or are you his mommy?

Yet another disrespectful comment to another forum member, instead of you actually addressing the topic at hand.

TBH, I stopped reading RS's posts a long time ago, when I got tired of the cut and paste wall of text as I couldnt be bothered trying to got clarify his numbers, but hey, lap it up mate!

I didn't expect you to pay attention to my posts after I started criticizing NV's poor price/performance and pricing mid-range cards at high-end. When I was praising and recommending GeForce 3, 4, 6, 8, GTX200 and 400 series, I sure do remember you agreeing with me. The reason you stopped reading my posts have little to do with you trying to clarify the information I post. We know what the real answer is.

There goes the hope of a price of USD 450 for R9 Nano. If its a fully enabled Fiji there is no way AMD are going to price this card at anything less than USD 500-550. USD 500 would be ok if it can match ref 980. Whats going to be interesting is how does the stock cooler handle overclocking (noise/temps) and whats the perf gain from OC.

Well we don't know for sure. Logically you are correct but then again AMD has surprised us in the past with HD5850, HD6950 and R9 290 and even the Fury non-X. All of those 2nd tier cards made the high-end card seem not really worth it. Something isn't adding up though -- if the Nano is an up to 1Ghz Fury X in a 175W power envelope, it's either the best binned Fiji chip they have in their line-up or the 175W is just a marketing TDP. Otherwise, if AMD prices it at $450, get a $50 CLC and you basically have a Fury X for $150 less. There seems to be some missing information.

The standard Fury X layout for a full chip has 8 ACEs for compute:



AMD clearly lists Fury X as having 8 Asynchronous Compute Engines (0-7):



The supposedly leaked Nano slides have 4 ACEs on the diagram as well as in the description:



I am not sure if this is an error or a fake slide or the Nano does have some flawed/disabled ACE parts other than the traditional shaders, TMUs and ROPs. Otherwise, it's hard to explain how a fully unlocked 1Ghz Nano is only 5-10% faster than a 290X.
 
Last edited:
Reactions: Grazick

SimianR

Senior member
Mar 10, 2011
609
16
81
Some of the better pictures let you see that the nano actually has quite a thick heatsink despite being a short card. From what the AMD rep stated during the Fury X launch, the nano's clock speed is going to be determined by powertune and I'm betting in most situations will not be operating at 1000mhz. I'm guessing it will fluctuate between 800mhz-1000mhz and do what it has to do to maintain it's tdp as well as whatever temperature target it has.
 
Feb 19, 2009
10,457
10
76
Interesting find on the block diagram @RS.

Looks like a different design, built for efficiency? Would be WOW if true.
They cut out 4 ACE for 2 additional HWS (Hardware Scheduler?)... hmm. Interesting!

Edit: If that block diagram is true it means AMD made 2 different Fiji designs. One focused for raw perf with extra compute power and one focused on raw efficiency (less idle ACEs, 2 additional schedulers to maximize shader efficiency!).
 
Last edited:

RussianSensation

Elite Member
Sep 5, 2003
19,458
765
126
Some of the better pictures let you see that the nano actually has quite a thick heatsink despite being a short card. From what the AMD rep stated during the Fury X launch, the nano's clock speed is going to be determined by powertune and I'm betting in most situations will not be operating at 1000mhz. I'm guessing it will fluctuate between 800mhz-1000mhz and do what it has to do to maintain it's tdp as well as whatever temperature target it has.

If true, that also means 2 things:

1) If AMD can tame a 175W GPU with such a small heatsink (sure it's thick but it's not a large heatsink like one on the Sapphire Fury, Asus Strix Fury/980Ti cards or Zotac AMP! 980Ti's cooler), then it's very disappointing that AMD didn't use such a heatsink for HD5870 and above. I guess it's better late than never....

2) If it's a fully unlocked chip, it could be possible to just buy an after-market CLC and overclock this card beyond Fury/Fury X. In that case, if the Nano is $500 or lower, it will cannibalize the sales of both the Fury and Fury X for many enthusiasts. However, it'll be interesting to see how much of a power limitation that 8-pin power connector becomes in a scenario where the Nano is running above 1Ghz.

Interesting find on the block diagram @RS.

Looks like a different design, built for efficiency? Would be WOW if true.
They cut out 4 ACE for 2 additional HWS (Hardware Scheduler?)... hmm. Interesting!

It's just rumours of course. I found it on here.

It also shows that AMD already had manufactured samples of HBM GPUs in late 2013 with interposer ~ 800mm2 and by mid-2014 they had manufactured over 5000 samples of 592mm2 HBM1 28nm GPUs with > 1000mm2 interposer! Looks like the road to HBM1 was incredibly tough and likely very expensive/R&D intensive.

 
Last edited:
Status
Not open for further replies.
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/    |