Benchmarks

Feature tests are special tests designed to highlight specific techniques, functions or capabilities.

The NVIDIA DLSS feature test is designed to help you test and compare the performance and image quality of DLSS processing.

You can choose to run the NVIDIA DLSS feature test using DLSS 4, DLSS 3, DLSS 2 or DLSS 1. With DLSS 2 or DLSS 3, you can also choose between three image quality modes—Quality, Performance and Ultra Performance. DLSS 4 adds two more modes: Balanced, which sits between Quality and Performance, and DLAA  (Deep Learning Anti-Aliasing). 

The NVIDIA DLSS feature test runs the Port Royal benchmark twice. The first run has DLSS disabled to provide a baseline. The second run uses DLSS processing. The result screen reports the frame rate for each run.

DLSS is a proprietary NVIDIA technology. To run this test, you will need an NVIDIA graphics card with drivers that support DLSS and Microsoft DirectX Raytracing. The NVIDIA DLSS feature test requires an NVIDIA graphics card that supports DLSS. DLSS 3 requires a GeForce RTX 40 Series GPU. DLSS 3 and DLSS 4 Frame Generation require a GeForce RTX 40 or RTX 50 Series GPU and Reflex SDK integration. DLSS 4 with Multi Frame Generation requires a GeForce RTX 50 Series GPU.

What is Deep Learning Super Sampling?

Deep Learning Super Sampling (DLSS) is an NVIDIA RTX technology that uses deep learning and AI to improve game performance while maintaining visual quality.

DLSS uses a deep neural network to extract multidimensional features of the rendered scene and intelligently combine details from multiple frames to construct a high-quality final image. This approach allows NVIDIA RTX GPUs to use fewer samples for rendering and use AI to fill in the information to create the final image. The result is a clear, crisp image of a quality similar to traditional rendering but with higher performance.

DLSS 4 is an improved version of DLSS that aims to deliver more performance and image quality than the previous DLSS versions. 

DLSS Multi Frame Generation

DLSS Multi Frame Generation uses AI to boost frame rates by generating up to three additional frames while optimizing responsiveness with NVIDIA Reflex. It is available for GeForce RTX 50 Series GPUs and laptops. 

DLSS Frame Generation

DLSS Frame Generation uses AI to boost frame rates by generating one additional frame, all while optimising responsiveness with NVIDIA Reflex.  DLSS Frame Generation requires a GeForce RTX 40 Series GPU or higher, as well as a Reflex SDK integration.

DLSS Super Resolution

DLSS Super Resolution uses AI to reconstruct high-resolution frames, rendering fewer pixels and boosting frame rates. This feature is available for all RTX GPUs.

NVIDIA DLAA

NVIDIA DLAA maximises image quality through an AI-based anti-aliasing technique. DLAA uses the same Super Resolution technology developed for DLSS, reconstructing a native resolution image to maximise image quality. This feature is available for all RTX GPUs.

NVIDIA Reflex 2

NVIDIA Reflex 2 helps DLSS Multi Frame Generation and Frame Generation achieve maximum performance at the lowest latency.It accomplishes this by combining NVIDIA Reflex Low Latency technology, which synchronises the CPU frame submission with GPU processing for just-in-time rendering, and NVIDIA Reflex Frame Warp technology, which uses the latest mouse position data and frame warping to deliver even more responsive mouse and camera movements. synchronizes

Aliasing

Aliasing—a distracting jagged line on the edge of an object in a scene—is a common artifact in real-time computer graphics.

Increasing the resolution of the entire image is not always practical so a common way to remove the jagged lines is to increase the number of samples on the line which helps to smooth it. Many techniques have been developed which intelligently blend the colors of the jagged edges with the colors of nearby pixels but most of these can lead to a loss of fine detail.

Temporal Anti-Aliasing

The 3DMark Port Royal benchmark uses Temporal Anti-Aliasing (TAA), a popular anti-aliasing technique used in many games today. TAA solves the aliasing problem by accumulating multiple samples temporally—instead of adding more samples to a single frame, it adds a small jitter to a rendered frame and combines the current samples with matching samples from previous frames. This directly leads to an increased sampling rate. Unfortunately, TAA suffers from flickering and ghosting artifacts. These artifacts are more visible in dynamic scenes.

A deep learning solution to aliasing

To develop Deep Learning Super Sampling, NVIDIA researchers trained a neural network to find jagged edges in an image, determine the best color for each pixel, and then apply proper colors to create smoother edges and improved image quality.

DLSS provides high-quality anti-aliasing with fewer artifacts and better performance than other types of anti-aliasing. Compared with TAA, DLSS produces sharp images that are temporally stable.

Neural network training

The specific details and method of the training is NVIDIA's trade secret since DLSS is a proprietary technology.

The original DLSS version required training the AI network with specific data extracted from each supported title. Newer DLSS version do not require any input from the workload to train the network. It delivers a generalized network that can work across games. With DLSS 4 NVIDIA introduced the new Transformer Model for improved image quality for all GeForce RTX-generations from RTX 20 to RTX 50.