Introduction

ASUS TUF Gaming GeForce RTX 4070 Ti SUPER is a premium custom-design rendition of the new RTX 4070 Ti SUPER that ASUS confirmed it's selling at the NVIDIA MSRP of $800. This card combines ASUS's premium custom PCB engineering with the company's TUF Gaming cooler that it used with cards such as the TUF Gaming RTX 4080—it's very capable and well tuned. The TUF Gaming RTX 4070 Ti SUPER sticks to NVIDIA reference clock speeds, which is how it's able to position this as an MSRP card. With cards at RTX 4070 Ti tier or above that having their TGP set to 285 W, such as this one, NVIDIA lacks a DUAL series custom-design, which makes the TUF Gaming their baseline. There's also the TUF Gaming OC, which could be offered at a slight premium. A segment above this would be the ROG Strix series.



The new NVIDIA GeForce RTX 4070 Ti SUPER is part of a constellation of three brisk new GPU launches NVIDIA is pulling off this January, which seek to refresh the company's higher-end product stack. The RTX 4070 Ti gets replaced with the new RTX 4070 Ti SUPER at its $800 MSRP, and is retired from the lineup. NVIDIA continues to recommend this for the 1440p resolution, with an ideal pairing being some of those 144 Hz or 165 Hz 1440p displays that are becoming affordable; although we've consistently found GPUs in the RTX 4070 series to be capable of 4K Ultra HD resolutions—even the RTX 4070 is, which means the RTX 4070 Ti Super should only do this better. As part of the refresh, NVIDIA gives each of the three SKUs more performance at existing or lower price points. For the RTX 4070 Ti SUPER, it's all about the memory.

Having maxed out the AD104 silicon that drives the RTX 4070, RTX 4070 SUPER, and RTX 4070 Ti with the latter; the only way NVIDIA could create the RTX 4070 Ti SUPER is by tapping into the larger AD103 silicon which drives the RTX 4080 and the upcoming RTX 4080 SUPER. The biggest benefit of the switch is the memory, and you now get 16 GB of it with the RTX 4070 Ti SUPER, across a 256-bit memory interface—this is a 33% gain in both memory size and bandwidth. Besides this, NVIDIA has increased the shaders by 10%, and ROP count by 20%—both fairly significant improvements in terms of specs.

NVIDIA carved the RTX 4070 Ti SUPER out of the AD103 silicon by enabling 66 out of 80 available SM. That's 6 more SM than the 60 physically present on the AD104. It hence has 8,448 CUDA cores, 264 Tensor cores, 66 RT cores, and 264 TMUs. Out of the 112 ROPs present on the AD103, NVIDIA enabled 96, which is 16 more than the 80 ROPs on the RTX 4070 Ti. From the 64 MB of on-die L2 cache, though, NVIDIA only enabled 48 MB, which is the same as the 48 MB of the RTX 4070 Ti. The GPU runs at up to 2610 MHz boost, and the memory at 21 Gbps. With the 256-bit memory bus, this yields 672 GB/s of memory bandwidth. The total graphics power (TGP) or the de facto power limit for the RTX 4070 Ti Super is set at 285 W, or the same as the RTX 4070 Ti. This is lower than the 320 W of the RTX 4080, but not by much.

The ASUS TUF Gaming RTX 4070 Ti SUPER features a large 4-slot cooling solution that uses a trio of Axial Tech fans; ventilating a large heatsink array. There's minimal RGB lighting—just a small LED strip near the tail end of the card; but you get some useful features such as dual-BIOS. Both the two BIOS ROMs run the card at the same 2610 MHz reference speeds, but the Quiet BIOS (Q-BIOS) lets you lower the fan speeds for slightly higher temperatures (which shouldn't affect performance at these reference speeds). Another unique feature with this card is that unlike most other RTX 4070 Ti SUPER cards, it gives you a total of 5 display outputs—two HDMI and three DisplayPorts; with the second HDMI coming in handy if you use a VR headset while you have an HDMI display connected.

Short 10-Minute Video Comparing 10x RTX 4070 Ti Super

Our goal with the videos is to create short summaries, not go into all the details and test results, which can be found in our written reviews.

Architecture

The Ada graphics architecture heralds the third generation of the NVIDIA RTX technology, an effort toward increasing the realism of 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 introduces 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 4070 SUPER leverages the TSMC 5 nm EUV foundry process to increase transistor counts.



The GeForce RTX 4070 Ti SUPER gets a significant memory sub-system uplift over the original RTX 4070 Ti, besides an increase in shaders and other on-die components. Since NVIDIA maxed out AD104 to create the RTX 4070 Ti, the only way it could go about creating the RTX 4070 Ti SUPER is by tapping into the larger AD103 that powers the RTX 4080 and the upcoming RTX 4080 SUPER. The biggest perks of the switch to AD103 is its wider 256-bit memory bus, which allowed NVIDIA to increase the memory from 12 GB to 16 GB.

The AD103 is built on the 5 nm EUV foundry process, with a die size of 379 mm² and 45.9 billion transistors. The chip features a PCI-Express 4.0 x16 host interface along with support for PCI resizable BAR; and its 256-bit wide GDDR6X memory interface. The GigaThread Engine serves as the main workflow controller for the GPU, dispatching work among the GPU's seven graphics processing clusters (GPCs). Each GPC shares a Raster Engine and render backends among six texture processing clusters (TPCs), the indivisible subunit of the GPU. 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. One of the seven GPCs on the AD103 physically only has four TPCs.

With a total of 40 TPCs, or 80 SM, the AD103 physically features 10,240 CUDA cores, 320 Tensor cores, 80 RT cores, and 320 TMUs; along with 64 MB of on-die L2 cache, and 112 ROPs. NVIDIA carved the RTX 4070 Ti SUPER out of the AD103 by enabling 66 out of 80 SM, 48 MB out of the 64 MB of L2 cache present; and 96 ROPs out of the 112 present. This results in 8,448 CUDA cores, 264 Tensor cores, 66 RT cores, 264 TMUs, 96 ROPs, and 48 MB of L2 cache. NVIDIA also disabled a few NVDEC units, giving this the same exact video acceleration configuration as the RTX 4070 Ti, with two NVENC and one NVDEC units. The 256-bit memory interface drives 16 GB of memory, however the memory runs at 21 Gbps, compared to the 22.5 Gbps of the RTX 4080, and 23 Gbps of the upcoming RTX 4080 SUPER. Even with 21 Gbps, the memory bandwidth on tap is an impressive 672 GB/s, a 33% increase over that of the original RTX 4070 Ti.

3rd Gen RT Core and Ray Tracing

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. 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 also 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

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 Frame Generation

DLSS 3 introduces a revolutionary new feature that promises a doubling in frame-rate at comparable quality, it's called AI frame-generation. Building on 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, it's also possible to enable frame generation at native resolution without upscaling. Later in the article, we will show you DLSS 3 in action.


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 latency with DLSS 3 enabled is at an acceptable level. 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

The ASUS RTX 4070 TUF is instantly recognizable, thanks to its bulky look that's a feature of the TUF series. On the other side you'll find a metal backplate that has a cutout for air to flow through.


Dimensions of the card are 30 x 14 cm, and it weighs 1316 g.


Installation requires three slots in your system. We measured the card's width to be 65 mm.


Display connectivity includes three standard DisplayPort 1.4a ports and two HDMI 2.1a (same as Ampere and same as non-Super Ada).

NVIDIA introduced the concept of dual NVDEC and NVENC Codecs with the Ada Lovelace 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. While the RTX 4070 Ti Super features dual units, the RTX 4070 Super and RTX 4070 come with only one of them. 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.


All GeForce RTX 4070 Ti Super graphics cards use the 12+4 pin ATX 12VHPWR connector, an adapter cable is included in the box.


Right next the power input is a dual BIOS switch, which lets you switch to a secondary "quiet" BIOS, which runs at a more relaxed fan curve.