AMD Radeon R9 Fury X Review
Manufacturer: AMD
UK price (as reviewed): Approx. £510 (inc VAT)
US price (as reviewed): MSRP $649 (ex Tax)
With it having been almost two years since a new flagship graphics card from AMD, and with Nvidia having launched both the GTX Titan X and GTX 980 Ti in the last few months, it was only a matter of time before AMD responded. Today, it’s doing exactly that with the Radeon R9 Fury X. With a brand-new GPU, an entirely new memory system and an onboard liquid cooler, there’s plenty to discuss, so without further ado…
Click to enlarge
The R9 Fury X uses the new AMD Fiji GPU, which bears a similar relationship to the R9 290X’s Hawaii chip as the GM200 (used in GTX Titan X and GTX 980 Ti) does to the GM204 (GTX 980) in that the underlying architecture and layout is very familiar; there’s just more of it. What this means is that Fiji uses AMD’s latest Graphics Core Next architecture. As with Hawaii, there’s a single main Graphics Command Processor and eight Asynchronous Compute Engines (ACEs) at the front end for dividing up work, which is split again between four Shader Engines, each with its own geometry processor and rasteriser. For Fiji, however, the Compute Unit count has been increased from 11 per Shader Engine to 16, for a total of 64. Remember, each Compute Unit contains four SIMD engines, which in turn have four texture units and 16 processors each, taking these totals to 256 to 4,096; a theoretical 45 percent increase in raw processing power. That said, the Render Back-End units have remained at 16 (four per Shader Engine), which keeps the ROP count at 64 compared to 96 on the GTX 980 Ti. The L2 cache jumps up to 2MB, as well. The card is clocked at up to 1,050MHz (it will stay at this speed provided it’s within its thermal, power and fan speed limits).
Click to enlarge — The R9 Fury X block diagram
The more interesting change with Fiji is a move to High Bandwidth Memory (HBM) from GDDR5.
If you want more detail on HBM and why it’s being moved to, you can read our in-depth article here. Essentially, however, HBM allows for the stacking of individual DRAM dies, much closer proximity between the GPU and DRAM and a much wider interface. The result is significantly lowered power consumption and space requirements and much higher memory bandwidth.
In its present form, HBM is limited to 1GB per DRAM stack, which limits Fiji, with its four stacks, to 4GB. This is the same as the R9 290X and 2GB less than the GTX 980 Ti, but AMD is confident that this will not limit Fury X, even at 4K with high details. In fact, it is this resolution the card is specifically designed for. With a massive 4096-bit-wide interface achieved through eight 512-bit memory controllers (two per HBM stack) and a 1Gbps effective speed (500MHz clock with double data rate), the Fury X has a total available memory bandwidth of 512GB/sec. This truly is massive; 60 percent over the R9 290X and 52 percent over the GTX 980 Ti.
It’s also said to offer four times the bandwidth per watt of the R9 290X thanks to the efficiency gains.
As expected, Fury X supports CrossFire XDMA, which enables bridge-less CrossFire set-ups – it’s all handled over the PCI-E 3.0 bus. Fury X is also a TrueAudio-enabled GPU.
The added processing power has increased the transistor count to 8.9 billion and the die size to a hefty 596mm2 – it’s built on the same 28nm TSMC process. Despite this, the PCB is much smaller than the R9 290X – down from almost 11.5in to 7.5in. This has been achieved first through a roughly threefold reduction in PCB footprint for the GPU and memory, since with HBM they are now placed on the same ASIC, which is 1,011mm2 in this instance. Second, the new liquid cooling solution removes the need for a bulky, long cooler atop the core hardware.
| AMD Radeon R9 Fury X 4GB | AMD Radeon R9 390X 8GB | AMD Radeon R9 290X 4GB | |
| GPU | |||
| Architecture | Graphics Core Next | Graphics Core Next | Graphics Core Next |
| Codename | Fiji | Hawaii XT | Hawaii XT |
| Core Clock | Up to 1,050MHz | Up to 1,050MHz | Up to 1GHz |
| Stream Processors | 4,096 | 2,816 | 2,816 |
| Layout | 4 SEs, 64 CUs | 4 SEs, 44CUs | 4 SEs, 44CUs |
| Texture Units | 256 | 176 | 176 |
| Rasterisers | 4 | 4 | 4 |
| Tesselation Units | 4 | 4 | 4 |
| ROPs | 64 | 64 | 64 |
| Transistors | 8. 9 billion |
6.2 billion | 6.2 billion |
| Die Size | 596mm2 | 438mm2 | 438mm2 |
| Process Node | 28nm | 28nm | 28nm |
| Memory | |||
| Amount | 4GB HBM | 8GB GDDR5 | 4GB GDDR5 |
| Frequency | 500MHz (1GHz effective) | 1.5GHz (6GHz effective) | 1.25GHz (5GHz effective) |
| Interface | 4,096-bit | 512-bit | 512-bit |
| Bandwidth | 512GB/sec | 384GB/sec | 320GB/sec |
| Card Specifications | |||
| Power Connectors | 2 x 8-pin | 1 x 8-pin, 1 x 6-pin | 1 x 8-pin, 1 x 6-pin |
| Stock Card Length | 195mm | N/A | 278mm |
| TDP | 275W | 275W | 275W |
In terms of APIs, the R9 Fury X supports DirectX 12, as well as Vulcan and Mantle.
AMD dodged the question on the exact DX12 feature level, but we do know that Tiled Resources are supported, suggesting feature level 12_0, compared to 12_1 for the GTX 980 Ti. AMD did draw attention to three key features of DirectX 12, however. First, Async Shaders, which allows work to be broken up into smaller tasks that can be processed at the same time. This will be managed by the dedicated ACE units, and is particularly useful for applying certain compute-based postprocessing effects with minimum impact on performance. DirectX 12 also has native multi-GPU support for the first time, enabling split-frame rendering for lower latency as well as combined, rather than mirrored, memory pools. Finally, there are also big improvements to efficiency when using multi-core CPUs – something that is practically universal now.
Click to enlarge — DirectX 12 Async Shaders
Other features include Virtual Super Resolution, a game-agnostic means of achieving supersampling anti-aliasing (SSAA) for the whole image.
This is similar to Nvidia’s Dynamic Super Resolution, allowing games to be rendered at a higher resolution than a panel’s maximum, before being scaled down again to achieve greater detail and smooth edges. There is also Frame Rate Target Control, where you can limit the frame rate in DirectX 10 or 11 games to between 55 and 95fps for power, heat and noise savings. This is being introduced to the whole R9 300 series range; it’s not really relevant for a super-high-end, liquid-cooled card like Fury X.
One final word concerns FreeSync. It has previously been criticised for having a lower refresh rate limit of 40Hz, meaning if you drop below 40fps you lose the smoothness. However, we’re starting to see this change with the introduction of new screens, three of which are of note: the Asus MG279Q (27in IPS, 1440p, 35-90Hz dynamic refresh rate range), the Acer XR341CK (34in curved IPS, 3,440 x 1,440 UltraWide, 30-75Hz) and the Nixeus NX-VUE24 (24in TN, 1080p, 30-144Hz). The fact that FreeSync can work down to 30Hz is good news – it may not work below this, but 30fps should be your minimum target in games anyway.
1 — AMD Radeon R9 Fury X Review2 — AMD Radeon R9 Fury X Review — The Card3 — AMD Radeon R9 Fury X Review — Test Setup4 — AMD Radeon R9 Fury X Review — Alien: Isolation Performance5 — AMD Radeon R9 Fury X Review — Battlefield 4 Performance6 — AMD Radeon R9 Fury X Review — Crysis 3 Performance7 — AMD Radeon R9 Fury X Review — Grand Theft Auto V Performance8 — AMD Radeon R9 Fury X Review — Middle Earth: Shadow of Mordor Performance9 — AMD Radeon R9 Fury X Review — The Witcher 3: Wild Hunt Performance10 — AMD Radeon R9 Fury X Review — Unigine Valley 1.011 — AMD Radeon R9 Fury X Review — Power and Thermals12 — AMD Radeon R9 Fury X Review — Overclocking13 — AMD Radeon R9 Fury X Review — Performance Analysis14 — AMD Radeon R9 Fury X Review — Conclusion
The R9 Fury is AMD’s best card in years, but just who is it for?
Tech —
Jul 25, 2015 11:15 am UTC
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?
Advertisement
| 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.
Advertisement
-
The R9 Fury is equipped with three Display Ports, one HDMI 1.4 port, and one DVI-D port.
-
The Asus version of the R9 Fury has a very nice (and sturdy) backplate.
-
The R9 Fury is a substantially bigger card than Nvidia’s reference Titan X.