Introduction

PNY GeForce RTX 4070 XLR8 is the company's premium custom-design graphics card based on NVIDIA's most affordable RTX 40-series Ada graphics card to date. The RTX 4070 is gunning to be the best-selling graphics model in the crucial Spring-Summer PC shopping season, where people upgrade their rigs for the break. XLR8 (pronounced "accelerate"), is PNY's premium gamer-focused brand of graphics cards, PC memory, and SSDs. You can expect all the bells and whistles of a high-end graphics card, including RGB LED lighting, a powerful VRM setup with more tuning headroom, and high-end product design in general.

The GeForce RTX 4070 is designed to dominate maxed-out AAA gaming at resolutions of up to 1440p, and high refresh-rate e-sports gameplay up to that resolution. It is very much capable of 4K Ultra HD gaming, but that requires dialing down some eye-candy, or judiciously using DLSS or the newer DLSS 3 Frame Generation feature, something that previous-generation high-end graphics cards being cleared out of stores around the $700-mark, lack. As a performance-segment graphics card, the RTX 4070 is also significantly more power-efficient than previous-gen high-end GPUs.



The GeForce Ada graphics architecture debuts the 3rd generation of NVIDIA RTX, the path breaking consumer graphics technology that combines real-time ray traced elements with conventional raster 3D graphics, to significantly improve gaming realism. Ada introduces significantly faster CUDA cores that run at higher clock speeds; 3rd generation RT cores with even more ray intersection performance that reduces the performance impact of enabling ray tracing; and 4th generation Tensor cores that support newer math formats.

The GeForce RTX 4070 is carved out of the same 5 nm AD104 silicon as the RTX 4070 Ti, but while the Ti maxes it out, the RTX 4070 is significantly cut down, featuring just 46 out of 60 streaming multiprocessors (SM) physically present, which works out to 5,888 CUDA cores, 184 Tensor cores, 46 RT cores, and 184 TMUs. The ROP count has been reduced to 64 from 80, although thankfully, the memory sub-system remains untouched. You get the same 12 GB of 21 Gbps GDDR6X memory across a 192-bit memory bus, which the RTX 4070 Ti has.

The PNY RTX 4070 XLR8 is priced at $650, a $50 premium over the NVIDIA MSRP, which is why it did not feature among yesterday's reviews. The card in this review is the non-OC variant of the RTX 4070 XLR8, which sticks to NVIDIA-reference clock speeds, with the price-premium covering for more features, such as RGB and superior VRM. There is an even pricier XLR8 OC Edition card that's priced slightly higher. With the RTX 4070, NVIDIA allowed its board partners to opt for the legacy 8-pin PCIe power connector instead of the modern 16-pin 12VHPWR. PNY chose the former, which should fit the 200 W typical graphics power (TGP) for the RTX 4070, and even provide the convenience of the more familiar power connector.

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 leverages the TSMC 5 nm EUV foundry process to increase transistor counts. At the heart of this GPU is the new AD104 silicon, which has a fairly high transistor count of 35.8 billion, which is more than double that of the previous-generation GA104. The GPU features a PCI-Express 4.0 x16 host interface, and a 192-bit wide GDDR6X memory bus, which on the RTX 4070 wires out to 12 GB of memory. The Optical Flow Accelerator (OFA) is an independent top-level component. The chip features one NVENC and one NVDEC unit.

The essential component hierarchy is similar to past generations of NVIDIA GPUs. The AD104 silicon features 5 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 AD104 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 five such GPCs, which add up to 7,680 CUDA cores, 240 TMUs, 240 Tensor Cores, and 60 RT cores. Each GPC contributes 16 ROPs, so there are 80 ROPs on the silicon. The RTX 4070 is carved out of the AD104 by disabling an entire GPC worth 6 TPCs, and an additional TPC from one of the remaining GPCs. This yields 5,888 CUDA cores, 184 Tensor cores, 46 RT cores, and 184 TMUs. The ROP count has been reduced from 80 to 64. The on-die L2 cache sees a slight reduction, too, which is now down to 36 MB from the 48 MB present.


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; DMM 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. DMM 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. 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 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

The PNY RTX 4070 XLR8 follows the design theme of the company's other GeForce 40 cards. On the other side you'll find a metal backplate that has a cutout for air to flow through.


PNY has added an RGB lighting zone around the middle fan, and a second area is illuminated, the XLR8 logo near the top.


Dimensions of the card are 30 x 12 cm, and it weighs 850 g.


Installation requires two slots in your system.


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

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 a single 8-pin power connector, which, together with the PCIe slot, is specified for up to 225 W power draw. Some other RTX 4070 cards like the NVIDIA Founders Edition come with the new 16-pin connector, but they are limited to the same power draw levels. NVIDIA has given their partners free choice on what connector they use, and I suspect the classic 8-pin is a little bit cheaper to implement.

Teardown

PNY's heatsink uses four heatpipes to keep the card cool. The main cooler also provides cooling for the memory chips and VRM circuitry.


The metal backplate 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 an eight-phase design, managed by a uPI uP9512R controller.


OnSemi NCP302150 DrMOS components are used for GPU voltage; they are rated for 50 A of current each.


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


For memory, OnSemi NCP302150 DrMOS with a 50 A rating are used again.


The GDDR6X memory chips are made by Micron and carry the model number D8BZC, which decodes to MT61K512M32KPA-21:U. They are specified to run at 1313 MHz (21 Gbps GDDR6 effective).


NVIDIA's AD104 graphics processor is the company's third Ada Lovelace GPU. It is built using a 5 nanometer process at TSMC Taiwan, with a transistor count of 35.8 billion and a die size of 295 mm².