The concept is simple (at least on paper): lay down a flat heat pipe on a large sink and, as an option, send water through to dissipate thermal energy from a flagship-class GPU. By adding water-cooling, you can either complement a capable heat sink and fan solution or replace it entirely.
It's certainly possible that such a hybrid may work quite well. There's no denying that Asus designed its ROG Poseidon GeForce GTX 1080 Ti 11GB Platinum Edition for flexibility though, so its performance, especially when it comes to water-cooling, does have its limits.
Since the actual performance of any third-party card depends on the GPU Boost frequency it can sustain, and thus on cooling, power limits, and processor quality, any review that relies on bar charts is little more than a snapshot of a single specimen. That's why we're putting our emphasis on the actual implementation of each model. To that end, a lot of equipment goes into thoroughly documenting a graphics card's behaviors. If you'd like a peek at what goes into such an evaluation, check out our Nvidia GeForce GTX 1080 Ti 11GB Review. It makes for a good baseline on which Asus builds.
This card is massive; it makes a bold visual appearance based on both size and lighting. Just remember that the ROG Poseidon is a 2.5-slot card, meaning it'll occupy three expansion slots in your case.
Asus does take care to make a good first impression. Still, the entire front cover is made of simple plastics. The only highlights are the RGB lighting effects on the top and back, along with visible bits of the cooler (including the water-cooling fittings).
A GPU-Z screenshot provides the most pertinent technical information, even if the GPU Boost values we observed were much higher than Asus' official specifications.
GTX 1080 Ti FE
GTX 1080 Ti
GTX 1080 FE
GTX 980 Ti
|Base Frequency||1417 MHz||1480 MHz||1594 MHz||1607 MHz||1000 MHz|
|Boost Frequency||1531 MHz+||1582 MHz+||1708 MHz||1733 MHz+||1076 MHz+|
|Memory Size & Type||12GB GDDR5X||11GB GDDR5X||11GB GDDR5X||8GB GDDR5X||6GB GDDR5|
|Die Size||471 mm²||471 mm²||471 mm²||314 mm²||601 mm²|
|Transistors||12 billion||12 billion ||12 billion||7.2 billion||8 billion|
|Streaming Multiprocessors (SM)||28||28||28||20||22|
|GFLOPS (Base Clock)||10,157||10,609||11,426||8228||5632|
|Texture Fill Rate||317.4 GT/s||331.5 GT/s||357.1 GT/s||257.1 GT/s||214 GT/s|
|Pixel Fill Rate||136 GPix/s||130.24 GPix/s||140.3 GPix/s||114,2 GPix/s||116.7 GPix/s|
|Memory Data Rate||10 Gb/s||11 Gb/s||11 Gb/s||10 Gb/s||7 Gb/s|
|Memory Bandwidth||480 GB/s||484.4 GB/s||484.4 GB/s||320 GB/s||336 GB/s|
|L2 Cache||3 MB||2816KB||2816KB||2MB||3MB|
We explained our test system and methodology in How We Test Graphics Cards. If you want to learn more about the procedures we're using in today's review, have a look at that story. In the time since it was published, we also upgraded our CPU and cooling system to rule out any possible host processing bottlenecks.
A short summary in table-form to provide a quick overview:
|System||Intel Core i7-6900K @ 4.3 GHz|
MSI X99S XPower Gaming Titanium
Corsair Vengeance DDR4-3200
1x 1TB Toshiba OCZ RD400 (M.2, System SSD)
2x 960GB Toshiba OCZ TR150 (Storage, Images)
be quiet Dark Power Pro 11, 850W PSU
Windows 10 Pro (All Updates)
|Alphacool Eisblock XPX|
Alphacool Eiszeit 2000 Chiller
2x be quiet! Silent Wings 3 PWM (Closed Case Simulation)
Thermal Grizzly Kryonaut (Used when Switching Coolers)
|Case||Lian Li PC-T70 with Extension Kit and Mods|
Configurations: Open Benchtable, Closed Case
|Power Intake||Contact-free DC Measurement at PCIe Slot (Using a Riser Card)|
Contact-free DC Measurement at External Auxiliary Power Supply Cable
Direct Voltage Measurement at Power Supply
2x Rohde & Schwarz HMO 3054, 500MHz Digital Multi-Channel Oscilloscope with Storage Function
4x Rohde & Schwarz HZO50 Current Probe (1mA - 30A, 100kHz, DC)
4x Rohde & Schwarz HZ355 (10:1 Probes, 500MHz)
1x Rohde & Schwarz HMC 8012 Digital Multimeter with Storage Function
|Thermography||1x Optris PI640 80Hz Infrared Camera + PI Connect|
Real-Time Infrared Monitoring and Recording
|Acoustics||NTI Audio M2211 (with Calibration File, Low Cut at 50Hz)|
Steinberg UR12 (with Phantom Power for Microphones)
Creative X7, Smaart v.7
Custom-Made Proprietary Measurement Chamber, 3.5 x 1.8 x 2.2m (L x D x H)
Perpendicular to Center of Noise Source(s), Measurement Distance of 50cm
Noise Level in dB(A) (Slow), Real-time Frequency Analyzer (RTA)
Graphical Frequency Spectrum of Noise
MORE: Best Graphics Cards
MORE: All Graphics Content