Overclock.net › Forums › Industry News › Rumors and Unconfirmed Articles › [tweaktown] AMD Radeon R9 Fury X2 should see 12 TFLOPS of compute performance
New Posts  All Forums:Forum Nav:

[tweaktown] AMD Radeon R9 Fury X2 should see 12 TFLOPS of compute performance - Page 2

post #11 of 80
Quote:
Originally Posted by Gilles3000 View Post

Yes, I do. Same die, different power delivery/management.
(also, allegedly, binned differently)

What I was implying is that its probably going to be closer to crossfired Nano's than Fury X's.

Yeah. Pretty obvious when they state 375w power consumption biggrin.gif That's LOW.
post #12 of 80
Quote:
Originally Posted by xxdarkreap3rxx View Post

You know it's the same die, right?


If they are using nanos, the performance is a bit of a let down. 12tflops means the nanos are clocked at 750mhz. That's an extremely low clock. nanos clocked that speed are somewhere around gtx 970 in performance. I was expecting AMD to clock these cards at atleast 900mhz to 1000mhz because of the water cooling. At 750mhz, air should get the job done. Something tell me these micro itx builds from vendor have 400 watt ps which is limiting AMD ability to clock these cards high.

This is gonna hurt reviews for the card, if this thing costs 1k+ and it's barely any faster than 295x2. What it also means is, 16nm cards should be faster than this thing. Not the big monolithics chips either, the midsized gp204 and the midsized AMD equivalent.

I hope AMD Roy is just trolling because at that speed, it's not going to sell well.
Edited by tajoh111 - 2/1/16 at 1:36pm
post #13 of 80
maybe theyre clocking low at the factory to appease low power users and overclockers?
post #14 of 80
Quote:
Originally Posted by tweezlednutball View Post

maybe theyre clocking low at the factory to appease low power users and overclockers?


I think they did it to appeal to the wants of vendors. Those micro builds generally have below average power supplies. Considering that the water cooler dumps heat outside the case, AMD should have gone with a dual power solution(power brick that plugs in the back) option for power users that want these things clocked at fury x speeds.

At fury X speeds in CF, even at 1k, these sell pretty well. At +5% over a 295x2, these things collect dust at 1k.

Low clocks isn't appeasing any overclockers, particularly with the fury series overclocking fiasco.

Review performance is everything since AMD is doing too little marketing, it needs to give the best impression off the bat for this card and at those clocks, that impression is going to be overpriced and wait for 16nm cards.
post #15 of 80
If this is true... AMD fails. 2 R9 Nano would be much faster at less power consumption... This thing will perform max 20% better than 980 Ti in games so if price is anywhere above $700 it fails. But that is impossible because AMD just lowered price from $650 to $500 of ONE Fiji GPU.
post #16 of 80
Quote:
Originally Posted by tajoh111 View Post

If they are using nanos, the performance is a bit of a let down. 12tflops means the nanos are clocked at 750mhz. That's an extremely low clock. nanos clocked that speed are somewhere around gtx 970 in performance. I was expecting AMD to clock these cards at atleast 900mhz to 1000mhz because of the water cooling. At 750mhz, air should get the job done. Something tell me these micro itx builds from vendor have 400 watt ps which is limiting AMD ability to clock these cards high.

This is gonna hurt reviews for the card, if this thing costs 1k+ and it's barely any faster than 295x2. What it also means is, 16nm cards should be faster than this thing. Not the big monolithics chips either, the midsized gp204 and the midsized AMD equivalent.

I hope AMD Roy is just trolling because at that speed, it's not going to sell well.

I'm not sure what you mean. To my understanding, the Nano and Fury X both use the Fiji XT die and the differences are in the PCBs and BIOS (to lower the stock clocks). It does seem these are clocked very low judging by the numbers they've given us: 12 TFLOPS (single-precision) & 375w consumption. Hopefully the PCB is beastly and can support a hefty OC because I agree with you, barely faster than a 295x2 @ $1000 and not being able to OC well is crap.
post #17 of 80
Quote:
Originally Posted by xxdarkreap3rxx View Post

I'm not sure what you mean. To my understanding, the Nano and Fury X both use the Fiji XT die and the differences are in the PCBs and BIOS (to lower the stock clocks). It does seem these are clocked very low judging by the numbers they've given us: 12 TFLOPS (single-precision) & 375w consumption. Hopefully the PCB is beastly and can support a hefty OC because I agree with you, barely faster than a 295x2 @ $1000 and not being able to OC well is crap.

It going to be tough to overclock well even with the best components on board. Power supplies in these machines are simply too small. The only advantage and niche fury x and x2 have is its size. However for the x2, it will consume too much power for the ultra small itx builds if it is clocked like a fury x. If it had say a 200-300 watt powerbrick, that would open up the x2 to the very smallest class of machines. That way you get the best of both word. The Gemini at 12TF is just a compromises card. At 1050mhz, it's over a 17tf card. That's 40% faster. It might consume 500 -550watts of power, but the enthusiast don't mind that power consumption if it's the very fastest card, particularly with a 30-40% advantage over the next fastest card.
post #18 of 80
This thing was suppose to come out late Q3 of last year, then moved to Q4 of last year, then end of 2015, then Q1 of 2016, and will probably get pushed to end of Q2 2016 which will coincide with polaris release (which may just be low end to midrange for the initial release) and Nvidia will probably release something that beats this, whether marginally or with a big lead. I don't get how long AMD can hype something.
ArmourMK2
(14 items)
 
  
CPUMotherboardGraphicsRAM
Core i7 5820K MSI X99 SLi Plus EVGA GTX 970 Crucial DDR4 
Hard DriveOptical DriveOSMonitor
Sandisk Ultra II  None Windows 8.1 Dell Ultrasharp U3415W 
MonitorKeyboardPowerCase
Dell Ultrasharp U2311h KBC Poker II MX Blue w/ White LED Corsair AX850 Lian-Li Armorsuit PC-P60b 
MouseMouse Pad
Razer Deathadder Chroma XtracPads Ripper XXL 
  hide details  
Reply
ArmourMK2
(14 items)
 
  
CPUMotherboardGraphicsRAM
Core i7 5820K MSI X99 SLi Plus EVGA GTX 970 Crucial DDR4 
Hard DriveOptical DriveOSMonitor
Sandisk Ultra II  None Windows 8.1 Dell Ultrasharp U3415W 
MonitorKeyboardPowerCase
Dell Ultrasharp U2311h KBC Poker II MX Blue w/ White LED Corsair AX850 Lian-Li Armorsuit PC-P60b 
MouseMouse Pad
Razer Deathadder Chroma XtracPads Ripper XXL 
  hide details  
Reply
post #19 of 80
what is the performance per inch?
LEGION
(15 items)
 
  
CPUMotherboardGraphicsRAM
I7 6700K ASUS Maximus VIII Impact EVGA GTX TITAN X G.skill 16gb 3200 ddr4 
Hard DriveHard DriveHard DriveCooling
Samsung 840 pro 250gb Samsung 840 evo 250gb Samsung 840 evo 250gb Ice kings magic. 
OSMonitorKeyboardPower
WIN 10 Wasabi Mango 42" 4k Corsair k70 EVGA 1000w P2 
CaseMouseAudio
Caselabs Mercury S3 Razer naga :( sennheiser HD 558 
  hide details  
Reply
LEGION
(15 items)
 
  
CPUMotherboardGraphicsRAM
I7 6700K ASUS Maximus VIII Impact EVGA GTX TITAN X G.skill 16gb 3200 ddr4 
Hard DriveHard DriveHard DriveCooling
Samsung 840 pro 250gb Samsung 840 evo 250gb Samsung 840 evo 250gb Ice kings magic. 
OSMonitorKeyboardPower
WIN 10 Wasabi Mango 42" 4k Corsair k70 EVGA 1000w P2 
CaseMouseAudio
Caselabs Mercury S3 Razer naga :( sennheiser HD 558 
  hide details  
Reply
post #20 of 80
Quote:
Originally Posted by szeged View Post

what is the performance per inch?

Now we are talking.

If this is just a bit faster then 295X2 it will fail bad. My only hopes is that it makes AMD focus on CFX more.
Ishimura
(21 items)
 
Silent Knight
(13 items)
 
 
CPUMotherboardGraphicsRAM
Intel Core i7 3770K @ 4.6GHz ASRock Z77E-ITX eVGA GTX 1080 Ti Hybrid AMD Radeon R9 16GB DDR3-2400MHz  
Hard DriveHard DriveCoolingCooling
SanDisk Ultra II 960GB Toshiba X300 5TB Corsair H100i GTX eVGA Hybrid Water Cooler  
CoolingOSMonitorKeyboard
4x GentleTyphoon AP-15 Windows 10 Pro 64-Bit Philips Brilliance BDM4065UC 4K Razer BlackWidow Chroma  
PowerCaseMouseMouse Pad
eVGA SuperNOVA 750 G3 Define Nano S Logitech G502 Proteus Core PECHAM Gaming Mouse Pad XX-Large 
AudioAudioAudioAudio
Audioengine D1 DAC Mackie CR Series CR3 Audio-Technica ATH-M50 Sennheiser HD 598 
Audio
Sony XB950BT 
CPUMotherboardGraphicsRAM
AMD Phenom II X4 955 @ 4.2GHz ASUS M4A79XTD EVO AMD Radeon HD 7970 3GB @ 1200/1500 2x 4GB G.SKILL Ripjaws X DDR3-1600 
Hard DriveHard DriveHard DriveCooling
OCZ Agility 3 60GB WD Caviar Green 1.5TB 2 x Seagate Barracuda 2TB XSPC Raystorm 
CoolingCoolingOSPower
EK-FC7970 XSPC RS360 Windows 10 Pro 64-Bit Corsair TX750 
Case
NZXT Switch 810  
  hide details  
Reply
Ishimura
(21 items)
 
Silent Knight
(13 items)
 
 
CPUMotherboardGraphicsRAM
Intel Core i7 3770K @ 4.6GHz ASRock Z77E-ITX eVGA GTX 1080 Ti Hybrid AMD Radeon R9 16GB DDR3-2400MHz  
Hard DriveHard DriveCoolingCooling
SanDisk Ultra II 960GB Toshiba X300 5TB Corsair H100i GTX eVGA Hybrid Water Cooler  
CoolingOSMonitorKeyboard
4x GentleTyphoon AP-15 Windows 10 Pro 64-Bit Philips Brilliance BDM4065UC 4K Razer BlackWidow Chroma  
PowerCaseMouseMouse Pad
eVGA SuperNOVA 750 G3 Define Nano S Logitech G502 Proteus Core PECHAM Gaming Mouse Pad XX-Large 
AudioAudioAudioAudio
Audioengine D1 DAC Mackie CR Series CR3 Audio-Technica ATH-M50 Sennheiser HD 598 
Audio
Sony XB950BT 
CPUMotherboardGraphicsRAM
AMD Phenom II X4 955 @ 4.2GHz ASUS M4A79XTD EVO AMD Radeon HD 7970 3GB @ 1200/1500 2x 4GB G.SKILL Ripjaws X DDR3-1600 
Hard DriveHard DriveHard DriveCooling
OCZ Agility 3 60GB WD Caviar Green 1.5TB 2 x Seagate Barracuda 2TB XSPC Raystorm 
CoolingCoolingOSPower
EK-FC7970 XSPC RS360 Windows 10 Pro 64-Bit Corsair TX750 
Case
NZXT Switch 810  
  hide details  
Reply
New Posts  All Forums:Forum Nav:
  Return Home
  Back to Forum: Rumors and Unconfirmed Articles
Overclock.net › Forums › Industry News › Rumors and Unconfirmed Articles › [tweaktown] AMD Radeon R9 Fury X2 should see 12 TFLOPS of compute performance