The AMD R9 Fury X, Fury, and Nano have all been released, but a dual-GPU Fiji XT card could be on the way soon according to a new report.
Back in June at AMD's E3 event we were shown Project Quantum, AMD's concept for a powerful dual-GPU system in a very small form-factor. It was speculated that the system was actually housing an unreleased dual-GPU graphic card, which would have made sense given the very small size of the system (and mini-ITX motherboard therein). Now a report from WCCFtech is pointing to a manifest that just might be a shipment of this new dual-GPU card, and the code-name is Gemini.
"Gemini is the code-name AMD has previously used in the past for dual GPU variants and surprisingly, the manifest also contains another phrase: ‘Tobermory’. Now this could simply be a reference to the port that the card shipped from…or it could be the actual codename of the card, with Gemini just being the class itself."
The manifest also indicates a Cooler Master cooler for the card, the maker of the liquid cooling solution for the Fury X. As the Fury X has had its share of criticism for pump whine issues it would be interesting to see how a dual-GPU cooling solution would fare in that department, though we could be seeing an entirely new generation of the pump as well. Of course speculation on an unreleased product like this could be incorrect, and verifiable hard details aren't available yet. Still, of the dual-GPU card is based on a pair of full Fiji XT cores the specs could be very impressive to say the least:
- Core: Fiji XT x2
- Stream Processors: 8192
- GCN Compute Units: 128
- ROPs: 128
- TMUs: 512
- Memory: 8 GB (4GB per GPU)
- Memory Interface: 4096-bit x2
- Memory Bandwidth: 1024 GB/s
In addition to the specifics above the report also discussed the possibility of 17.2 TFLOPS of performance based on 2x the performance of Fury X, which would make the Gemini product one of the most powerful single-card GPU solutions in the world. The card seems close enough to the final stage that we should expect to hear something official soon, but for now it's fun to speculate – unless of course the speculation concerns a high initial retail price, and unfortunately something at or above $1000 is quite likely. We shall see.
Anything above 1000 will mean
Anything above 1000 will mean its D.O.A.
Save you dosh for pascal next year.
Hello Nvidia fanboy. How is
Hello Nvidia fanboy. How is that lovely Titan X doing at $1000?
He is right though. And does
He is right though. And does this 2x Fiji card have frame pacing or will it still give you worse performance than ia single GPU in ALL DX9 GAMES?
Did AMD ever add software frame pacing for DX9?
To be fair, anything near
To be fair, anything near $1000 is very niche, and even anything over $300 is still pretty niche to the point where it won’t affect a company’s bottom line as much as say, a $200 card.
Since GPU’s are a low-margin high volume product, this stuff is mostly for ultra-enthusiasts rather than most consumers, who generally get like stuff in the 960/380 to 970/390 range.
That said, if the price every drops to $999 or even a little less, I can see this product being a great bang/buck, like the 295×2, which eventually became a killer deal considering the massive amount of power it offered, and honestly, still offers today.
I’m sure they have a pretty
I’m sure they have a pretty good idea how many people on a consumer level want a card like this, It’s probably gona be a very limited run, perhaps even numbered like the ARES/MARS lines.
I just saw something talking
I just saw something talking about a possible new dual Nvidia card also. I suspect it will contain the same high binned part that Nvidia is selling as a mobile 980 Ti at around 150 W (?).
Nvidia only has GM204-based
Nvidia only has GM204-based Geforce 980s (non-Ti) @150W for the “mobile” market, and two GM204s are so old and boring (not to mention slower than two Fiji XTs) that I truly hope that’s not what’s being launched.
Same process, even if it is a
Same process, even if it is a different die; they just use only the highest binned die that can run at lower voltage and power consumption. There isn’t really any market for a high binned 980 die in the desktop segment. The fully functional mobile 980 is somewhat dubious as it is. That will still be a lot of power for a laptop. Given that they got the 980 down low enough to even consider running it at full speed in a laptop may mean that they can make a dual 980 Ti with a reasonable amount of power consumption. AMD doesn’t really do the process with only using the highest binned, “cherry picked” parts. With the 295×2 they just used standard binned parts, and took the hit for not being standards compliant. I think AMD made the better choice, since they made the 295×2 a high-end, but still somewhat reasonable part. The Nvidia dual cards were priced so high, that there really was no point in buying them. Considering what AMD was able to do with the nano, they should be able to make an excellent dual card. Nvidia has good power consumption so they may be able to make a good dual card also. We may have an actual good fight with these products, except only for those buyers in the $1000 price range.
But who cares about any of
But who cares about any of these when a single GP100 will be more powerful?
Looks interesting, and seems
Looks interesting, and seems like it’ll be good for 1-card 4K (like the 295×2 before it) but this is out of my price range. For $1000, I could build a whole computer with a good GPU, or buy multiple consoles/handhelds, which is what I prefer to do because my gaming PC is good enough for at least 1-2 more years.
The ironic part is that if I buy consoles, I’ll be buying AMD no matter what I get. Not that console players generally know this. Fanboys are busy arguing over PS4 vs. Xbox One without realizing they’re highly similar AMD APU’s at the core.
Sebastion…You have PEAKED
Sebastion…You have PEAKED my interest here…
HA! thanks for coming out
HA! thanks for coming out ladies and germs, dont forget to tip your waitress.
Not sure why, but I was
Not sure why, but I was thinking if I had this I would underclock it in crossfire and have a quite efficient but super powerful setup to last a long time. When the underclocking stops maxing my 1440p I can bump it up. This would last me a very long time in that scenario as I still think 4k is a bit silly.
Ehh Ill probably just run my R9 290 into the ground..Who am I kidding.
Has Fiji cross fire been
Has Fiji cross fire been played with yet here? How does it scale, pretty much like always or is there a difference up or down?
It probably will not scale
It probably will not scale much better than previous generations under DX11, but it could be different under DX12. I would expect that a lot of asynchronous compute would help with multi-gpu by definition, independently of the new multi-gpu features in DX12. Asynchronous compute jobs should not really care which gpu they are scheduled on. I wouldn’t mind getting the opinion of someone who knows more about graphics processing though.
This would be perfect in my
This would be perfect in my custom build mini gaming pc, easy to carry to grandmas house.