Introduction

ZOTAC GeForce RTX 4080 AMP Extreme AIRO is the company's most premium air-cooled custom-design RTX 4080 "Ada" graphics card, which is debuting today alongside a large selection of graphics cards we're reviewing for you. The RTX 4080 is designed to consolidate NVIDIA in the high-end segment, by offering a product that does many of the same things as the $1,600 RTX 4090—4K Ultra HD AAA gaming with ray tracing—at a lower price-point of $1,200 (NVIDIA starting MSRP), pushing the RTX 4090 to be an enthusiast product meant for overclockers climbing leaderboards. The ZOTAC AMP Extreme AIRO adds to this with a nifty factory-overclock, and a heavily noise-optimized cooling solution designed to maximize airflow and heat dissipation.



NVIDIA designed the GeForce RTX 4080 "Ada" with an intelligent set of manufacturing choices. It knows this SKU will push higher volumes than the RTX 4090, and too many AD102 dies will be spent carving its lower shader counts from, and so it innovated the new AD103 silicon that's positioned halfway between the large AD102 and the AD104, on which the future 70-series products will be based. The RTX 4080 is endowed with 16 GB of memory, which is higher than those of the RTX 3080, of 10 GB and 12 GB, but over a narrower 256-bit wide memory bus (which means fewer numbers of memory chips per board). It compensated for the bandwidth shortfall with faster memory speeds of 22.4 Gbps, and larger 64 MB on-die caches.

The RTX 4080 is endowed with 9,728 CUDA cores, 304 Tensor cores, 76 RT cores, and 112 ROPs. The 16 GB memory interface is across a 256-bit wide memory bus. The GPU ticks at 2.50 GHz boost, which ZOTAC overclocked to 2.565 GHz, while leaving the memory untouched at 22.4 Gbps. The AMP Extreme AIRO features the same airy, aerodynamic custom cooler design as the RTX 4090 AMP Extreme, designed to maximize airflow to the large aluminium fin-stack heatsink. It also has a sleek, subtle execution of RGB illumination. ZOTAC is pricing the card at $1,400, a $200 premium over the NVIDIA baseline.

Architecture

The Ada graphics architecture heralds the third generation of the NVIDIA RTX technology, an effort toward increasing the realism in game visuals by leveraging real-time ray tracing, without the enormous amount of compute power required to draw purely ray-traced 3D graphics. This is done by blending conventional raster graphics with ray traced elements such as reflections, lighting, and global illumination, to name a few. The 3rd generation of RTX heralds the new higher IPC "Ada" CUDA core, 3rd generation RT core, 4th generation Tensor core, and the new Optical Flow Processor, a component that plays a key role in generating new frames without involving the GPU's main graphics rendering pipeline.


The GeForce Ada graphics architecture driving the RTX 4080 leverages the TSMC 5 nm EUV foundry process to increase transistor counts. At the heart of the RTX 4080 is the new AD103 silicon, which has a reasonably large transistor count of 45.9 billion, which is still nearly 60% higher than that of the previous-generation flagship GA102. The GPU features a PCI-Express 4.0 x16 host interface, and a 256-bit wide GDDR6X memory bus, which on the RTX 4080 wires out to 16 GB of memory. With NVIDIA cancelling the 12 GB variant, this is the only RTX 4080 there is, for now. The Optical Flow Accelerator (OFA) is an independent top-level component. The chip features two NVENC and one NVDEC units in the GeForce RTX 40-series.

The essential component hierarchy is similar to past generations of NVIDIA GPUs. The AD103 silicon features 7 Graphics Processing Clusters (GPCs), each of these has all the SIMD and graphics rendering machinery, and is a small GPU in its own right. Each GPC shares a raster engine (geometry processing components) and two ROP partitions (each with eight ROP units). The GPC of the AD102 contains six Texture Processing Clusters (TPCs), the main number-crunching machinery. Each of these has two Streaming Multiprocessors (SM), and a Polymorph unit. Each SM contains 128 CUDA cores across four partitions. Half of these CUDA cores are pure-FP32; while the other half is capable of FP32 or INT32. The SM retains concurrent FP32+INT32 math processing capability. The SM also contains a 3rd generation RT core, four 4th generation Tensor cores, some cache memory, and four TMUs. There are 12 SM per GPC, so 1,536 CUDA cores, 48 Tensor cores, and 12 RT cores; per GPC. There are seven such GPCs, which add up to 10,240 CUDA cores, 320 TMUs, 320 Tensor Cores, 80 RT cores. Each GPC contributes 16 ROPs, so there are 112 ROPs on the silicon. NVIDIA carved the RTX 4080 out of the AD103 by disabling four SMs.


The 3rd generation RT core accelerates the most math-intensive aspects of real-time ray tracing, including BVH traversal. Displaced micro-mesh engine is a revolutionary feature introduced with the new 3rd generation RT core, which accelerates the displaced micro-mesh feature. Just as mesh shaders and tessellation have had a profound impact on improving performance with complex raster geometry, allowing game developers to significantly increase geometric complexity; DMMs is a method to reduce the complexity of the bounding-volume hierarchy (BVH) data-structure, which is used to determine where a ray hits geometry. Previously the BVH had to capture even the smallest details to properly determine the intersection point. Ada's ray tracing architecture receives a major performance uplift from Shader Execution Reordering (SER), a software-defined feature that requires awareness from game-engines, to help the GPU reorganize and optimize worker threads associated with ray tracing.


The BVH now needn't have data for every single triangle on an object, but can represent objects with complex geometry as a coarse mesh of base triangles, which greatly simplifies the BVH data structure. A simpler BVH means less memory consumed and helps to greatly reduce ray tracing CPU load, because the CPU only has to generate a smaller structure. With older "Ampere" and "Turing" RT cores, each triangle on an object had to be sampled at high overhead, so the RT core could precisely calculate ray intersection for each triangle. With Ada, the simpler BVH, plus the displacement maps can be sent to the RT core, which is now able to figure out the exact hit point on its own. NVIDIA has seen 11:1 to 28:1 compression in total triangle counts. This reduces BVH compile times by 7.6x to over 15x, in comparison to the older RT core; and reducing its storage footprint by anywhere between 6.5 to 20 times. DMMs could reduce disk- and memory bandwidth utilization, utilization of the PCIe bus, as well as reduce CPU utilization. NVIDIA worked with Simplygon and Adobe to add DMM support for their tool chains.


Opacity Micro Meshes (OMM) is a new feature introduced with Ada to improve rasterization performance, particularly with objects that have alpha (transparency data). Most low-priority objects in a 3D scene, such as leaves on a tree, are essentially rectangles with textures on the leaves where the transparency (alpha) creates the shape of the leaf. RT cores have a hard time intersecting rays with such objects, because they're not really in the shape that they appear (they're really just rectangles with textures that give you the illusion of shape). Previous-generation RT cores had to have multiple interactions with the rendering stage to figure out the shape of a transparent object, because they couldn't test for alpha by themselves.


This has been solved by using OMMs. Just as DMMs simplify geometry by creating meshes of micro-triangles; OMMs create meshes of rectangular textures that align with parts of the texture that aren't alpha, so the RT core has a better understanding of the geometry of the object, and can correctly calculate ray intersections. This has a significant performance impact on shading performance in non-RT applications, too. Practical applications of OMMs aren't just low-priority objects such as vegetation, but also smoke-sprites and localized fog. Traditionally there was a lot of overdraw for such effects, because they layered multiple textures on top of each other, that all had to be fully processed by the shaders. Now only the non-opaque pixels get executed—OMMs provide a 30 percent speedup with graphics buffer fill-rates, and a 10 percent impact on frame-rates.


DLSS 3 introduces a revolutionary new feature that promises a doubling in frame-rate at comparable quality, it's called AI frame-generation. While it has all the features of DLSS 2 and its AI super-resolution (scaling up a lower-resolution frame to native resolution with minimal quality loss); DLSS 3 can generate entire frames simply using AI, without involving the graphics rendering pipeline.


Every alternating frame with DLSS 3 is hence AI-generated, without being a replica of the previous rendered frame. This is possible only on the Ada graphics architecture, because of a hardware component called the optical flow accelerator (OFA), which assists in predicting what the next frame could look like, by creating what NVIDIA calls an optical flow-field. OFA ensures that the DLSS 3 algorithm isn't confused by static objects in a rapidly-changing 3D scene (such as a race sim). The process heavily relies on the performance uplift introduced by the FP8 math format of the 4th generation Tensor core. A third key ingredient of DLSS 3 is Reflex. By reducing the rendering queue to zero, Reflex plays a vital role in ensuring that frame-times with DLSS 3 are at an acceptable level, and a render-queue doesn't confuse the upscaler. A combination of OFA and the 4th Gen Tensor core is why the Ada architecture is required to use DLSS 3, and why it won't work on older architectures.

Packaging

The Card

Zotac is taking an all-smooth approach with their GeForce RTX 4080 AMP Extreme. The curves on their card are almost female-elegant. On the back you get a high-quality metal backplate, the front cooler shroud is made from plastic.


Zotac's RGB illumination is amazing and mesmerizing. They have integrated a large lighting element along the top edge. There's more lighting at the bottom and an additional illumination zone on the backplate.


Dimensions of the card are 36.0 x 15.0 cm, and it weighs 1962 g.


Installation requires three slots in your system.


Display connectivity includes three standard DisplayPort 1.4a ports and one HDMI 2.1a (same technology as Ampere).

NVIDIA introduced the concept of dual NVDEC and NVENC Codecs with the Ada architecture. This means there are two independent sets of hardware-accelerators; so you can encode and decode two streams of video in parallel or one stream at double the FPS rate. The new 8th Gen NVENC now accelerates AV1 encoding, besides HEVC. You also get an "optical flow accelerator" unit that is able to calculate intermediate frames for videos, to smooth playback. The same hardware unit is used for frame generation in DLSS 3.


The card uses the new 12+4 pin ATX 12VHPWR connector, which is rated for up to 600 W of power draw. An adapter cable from 3x PCIe 8-pin is included (which is rated for up to 450 W). Of course the 4x 8-pin to 16-pin adapter cables from RTX 4090 will also work with the RTX 4080, but the card won't need that much power.

Right next to the power connector you find the dual BIOS switch which lets you toggle between the default performance BIOS and a secondary quiet BIOS. Interestingly, Zotac chose to use a push button instead of a physical switch, which means you can only switch between the two when the card is powered up. Only power is sufficient, no need to go into BIOS or Windows, there's no need to install any software. After pressing the button, the RGB lights will flash red for performance BIOS and blue for quiet BIOS. The setting is saved between reboots and power offs, so no complaints from me.

Teardown

Unlike the Zotac RTX 4090 AMP Extreme AIRO, the RTX 4080 doesn't use a vapor-chamber, but a classic baseplate. There's also nine heatpipes installed to move heat away quickly from the GPU, to the heatsink. The main cooler also provides cooling for the VRM and memory chips.


The backplate is made of metal and protects the card against damage during installation and handling.

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 these in your articles, videos or forum posts.


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

Circuit Board (PCB) Analysis

GPU voltage is a 24-phase design, managed by a UPI uP9512R controller.


Alpha & Omega AOZ5311NQI BLN3 DrMOS components are used for GPU voltage; they are rated for 55 A of current each.


Memory voltage is a three-phase design, managed by a uPI uP9529Q controller.


For memory, Alpha & Omega AOZ5311NQI BLN3 DrMOS with a 55 A rating are used, too.


The GDDR6X memory chips are made by Micron and carry the model number D8BZF, which decodes to MT61K512M32KPA-24. They are specified to run at 1500 MHz (24 Gbps effective).


NVIDIA's AD103 graphics processor is the company's second Ada Lovelace GPU. It is built using a 5 nanometer process at TSMC Taiwan, with a transistor count of 45.9 billion and a die size of 379 mm².