Introduction

NVIDIA's GeForce RTX 20 Super series launch in two phases across July is topped off by the new GeForce RTX 2080 Super. Designed to displace the RTX 2080 from the company's product stack at $700, the RTX 2080 Super not just maxes out the 12 nm "TU104" Turing silicon, but also comes with higher GPU clock speeds and faster 15.5 Gbps GDDR6 memory. NVIDIA's reason to launch the RTX 2080 Super may have been necessitated by, of all things, the $399 Radeon RX 5700 XT.

AMD's Radeon RX 5700-series "Navi" launch destabilized NVIDIA's lineup. The RX 5700 XT outperformed the RTX 2070, and the RX 5700 beat the RTX 2060, forcing NVIDIA to launch the RTX 2060 Super and RTX 2070 Super to recapture the $399 and $499 price points. This had a ripple effect on the RTX 2080 because the RTX 2070 Super was carved out from the same "TU104" silicon and since the original RTX 2070 maxed out the "TU106." The RTX 2070 Super performs within 6-8 percent of the RTX 2080 while being $200 cheaper. Custom-design, factory-overclocked RTX 2070 Super cards narrow the performance gap to as little as 3-4 percent. NVIDIA would need to refresh the RTX 2080 lest it gets cannibalized by the RTX 2070 Super. We hence have the new RTX 2080 Super.



NVIDIA's objectives with the RTX 2080 Super are to increase the performance gap with the RTX 2070 Super, so it can justify selling it at a $200 premium, at $700 and avoid tapping into the larger "TU102" silicon, which would escalate costs. The company's approach hence is to supercharge the "TU104". For starters, all 3,072 CUDA cores physically present on the chip are enabled. The original RTX 2080 only features 2,944 of them. Secondly, the GPU Boost frequency is dialed up by a further 100 MHz, to 1815 MHz (up 6 percent). Lastly, the company increased the memory bandwidth by 11 percent by dialing memory clock speeds up to 15.5 Gbps using fast 16 Gbps-rated memory chips.

NVIDIA is also allowing its add-in card (AIC) partners to innovate custom-design RTX 2080 Super graphics cards with generous factory-overclocked speeds and meaty cooling solutions. With prices starting at $700, NVIDIA partners have $200 to mark up prices of their premium offerings because beyond $900, you should aim for the RTX 2080 Ti.

In this review, we're testing the ZOTAC GeForce RTX 2080 Super AMP Extreme, the company's top-dog offering based on the RTX 2080 Super. ZOTAC dialed GPU Boost frequencies up to 1875 MHz (65 MHz above stock), while leaving the memory untouched at 15.5 Gbps. ZOTAC's innovation is concentrated with the physical board design, which has a massive 16+4 phase VRM that draws power from two 8-pin PCIe power connectors, and a multi-phase tantalum capacitor for additional power filtering across the vGPU phases. The massive Ice Storm 2.0 triple-slot cooling solution features three fans with independent speed control, idle fan-stop, and five 8 mm-thick copper heat pipes. ZOTAC is pricing the RTX 2080 Super AMP Extreme at $780, a $80 premium over the $700 baseline price.

Packaging and Contents

You will receive:

• Graphics card
• Documentation
• 2x Molex to PCIe adapter cable

The Card

Visually, the RTX 2080 Super AMP Extreme looks identical to the company's RTX 2080 non-Super AMP Extreme, which of course makes a lot of economical sense. On the back, you'll find a high-quality metal backplate. Dimensions of the card are 32.0 x 13.5 cm.


Installation requires three slots in your system.


Display connectivity options include three standard DisplayPort 1.4a, one HDMI 2.0b, and a VirtualLink connector, which is basically USB-C with DisplayPort routing and USB-PD, so a single cable can power, display, and take input from your VR HMD.

NVIDIA has updated their display engine with the Turing microarchitecture, which now supports DisplayPort 1.4a with support for VESA's nearly lossless Display Stream Compression (DSC). Combined, this enables support for 8K@30Hz with a single cable or 8K@60Hz when DSC is turned on. For context, DisplayPort 1.4a is the latest version of the standard that was published in April, 2018.

At CES 2019, NVIDIA announced that all their graphics cards will now support VESA Adaptive Sync (aka FreeSync). While only a small number of FreeSync monitors have been fully qualified with G-SYNC, users can enable the feature in NVIDIA's control panel regardless of whether the monitor is certified or not.


The board uses two 8-pin power connectors. This input configuration is specified for up to 375 watts of power draw.


With Turing, NVIDIA is using NVLink as a physical layer for its next-generation SLI technology. NVLink provides sufficient bandwidth for multi-GPU rendering at 8K 60 Hz, 4K 120 Hz, and other such bandwidth-heavy display resolutions. It's a point-to-point link between your GPUs, so latencies will be lower compared to pushing data through the PCI-Express bus.

Disassembly

Zotac is using six heatpipes and a copper base on their cooler.


Once the main heatsink is removed, a black baseplate becomes visible, which provides cooling for the VRM circuitry.


The backplate is made out of metal and protects the card against damage during handling and installation. Note how the backplate actually partially wraps around the card for added protection and improved looks.

On the next page, we dive deep into the PCB layout and VRM configuration.

High-resolution PCB Pictures

These pictures are for the convenience of volt-modders and people who would like to see all the finer details on the PCB. Feel free to link back to us and use them in your articles or forum posts.



High-res versions are also available (front, back).