The R9 Fury is AMD’s best card in years, but just who is it for?

What a few months it's been for AMD. Hope sprang eternal after AMD began to drop details on its latest GPU architecture update, named Fiji, which features an all-new, much-hyped technology called High Bandwidth Memory (HBM). After years of playing second-fiddle to Nvidia in raw performance and power consumption, the promised power savings and huge bandwidth of HBM was to be AMD's saving grace, and a turning point for a company in sore need of a win after a string of multi-million dollar losses.

Unfortunately for AMD, the GPU that emerged, the R9 Fury X, didn't quite cut the mustard. Nvidia's pre-emptive strike with the GTX 980 Ti, which was undoubtedly driven by the imminent launch of the Fury X, put a dampener on AMD's bleeding-edge tech. The Fury X cost the same as a 980 Ti, but it wasn't faster, had less memory, and consumed more power—even if its excellent watercooling system kept temperatures under control. Team Red, it seemed, was in trouble once again.

While the flagship R9 Fury X hogged the hardware headlines, however, the release of its little brother—the R9 Fury—a couple of weeks later was far more interesting. At £450 ($560), the R9 Fury is priced below the £550 ($650) of the Fury X and the GTX 980 Ti, but above the £400 ($520) of the GTX 980, and the £350 ($430) of the R9 390X. That puts it, and AMD, in a slightly odd position: if you can get the Fury (and that tasty HBM) for £450, is there any point in stepping up to the Fury X? And on the other hand, if the Fury is only a smidgen better than a 980 or 390X, why bother spending the extra cash?

Specs at a glance	R9 Fury X	R9 Fury	R9 390X	R9 290X
Stream Processors	4096	3584	2816	2816
Texture Units	256	224	176	176
ROPs	64	64	64	64
Boost Clock	1050MHz	1000MHz	1050MHz	1000MHz
Memory Bus Width	4096-bit	4096-bit	512-bit	512-bit
Memory Clock	1GHz	1GHz	6GHz	5GHz
Memory Bandwidth	512GB/s	512GB/s	384GB/s	320GB/s
Memory Size	4GB HBM	4GB HBM	8GB GDDR5	4GB GDDR5
Typical Board Power	275W	275W	250W	250W

Like the Fury X, the Fury is based on AMD's Fiji architecture, which pairs a huge 8.9-billion-transistor, 596-square-millimetre chip built on a 28nm process with 4GB of stacked HBM. We've covered HBM previously in depth, but to recap: HBM uses stacked memory chips along with a silicon interposer and through-silicon-vias (an interconnect that runs through the chip from top to bottom) in order to move the DRAM closer to the GPU. This shortens the traces, allowing for increased bandwidth and lower power consumption. As an added bonus, the PCB itself is much smaller as well.

However, this being a first-generation design, there a few compromises. For starters, the Fury (as well as its bigger brother the Fury X) is limited to 4GB of memory. AMD might well say that 4GB is more than enough even for 4K gaming, but it's telling that the substantially cheaper 390X ships with 8GB of GDDR5 memory, while Nvidia's 980 Ti ships with 6GB.

Maybe the 390X's 8GB of VRAM is simply AMD's way of covering up the fact that, except for the RAM, the card is virtually identical to the 290X (which had the same GPU but only 4GB of RAM). In any case, while it's currently difficult to completely fill 4GB, that smaller pool of memory is likely to become a problem before it's economical to upgrade.

To be fair to AMD, Nvidia's GTX 980 will face that problem too, even if that card has the benefit of being older, and a wee bit cheaper. On paper, the Fury should be notably faster than the 980, though. Compared to the Fury X, the Fury's Fiji chip cuts the compute units down from 64 to 56, which brings down the total stream processor count from 4096 to 3584. The clock speed also drops slightly to 1000MHz, a five percent reduction from the Fury X. That's all there is for cuts, with the number of geometry units and ROPs remaining unchanged. That should place the Fury's performance squarely between that of the Fury X and 980 Ti, and the 980 and 390X.

In our own testing of an Asus Strix version of the R9 Fury (some of which are shown below), as well as a quick look at other benchmarks reported by other sites, the Fury is indeed faster than a 390X and 980, but slower than a Fury X and 980 Ti. But that doesn't tell the whole story.

Given the Fury's odd price positioning, the key is how much faster or slower it is than its competitors. In Anandtech's comparison tests with the Fury X (unfortunately, Ars does not have access to a Fury X to conduct its own tests), they saw an average performance difference of around seven percent in favour of the Fury X. Given that there's around a 20 percent difference in price between the two cards (14 percent for those in the US), you have to wonder if the Fury X is really worth it.

Flagship cards are rarely good value for money, of course. Nvidia fares a little better with the GTX 980 Ti, which costs around 30 percent more than a 980 for around a 30 percent performance improvement. But it's worth comparing to the 970 too, which gets you similar performance to the 980, with the 980 Ti costing a whopping 70 percent more.