NVIDIA GeForce RTX 4080 Super Graphics Cards

GeForce RTX 4080 Super Graphics Card for High-End Gamers

The AD103 graphics processor is used as the graphics chip of the RTX 4080 Super. The AD103-400, like all GPUs of the RTX 4000 generation, is based on NVIDIA's Ada Lovelace architecture and the 4 nm manufacturing process. This offers 3rd generation RT cores and 4th generation tensor cores, streaming multiprocessors for the most realistic ray tracing graphics, and the latest AI features.

Extremely High Frame Rates with NVIDIA DLSS 3

NVIDIA's DLSS 3 (Deep Learning Super Sampling) uses the tensor cores of the RTX 4080 Super to maximize performance with uncompromising image quality thanks to AI computation. With NVIDIA's frame generation technology based on DLSS 3, you can experience story games smoother than ever before. Immerse yourself completely in immersive game worlds with fascinating graphics.

NVIDIA Reflex: Speed Wins

NVIDIA Reflex gives you the decisive competitive advantage thanks to low input latencies and minimizes your hardware's reaction times.

NVIDIA Gaming Graphics Card for 4K Resolution

With 10,240 shader ALUs, 16 GB graphics memory, and a 256-bit memory interface at a fast 23 Gbps bandwidth, the NVIDIA GeForce RTX 4080 Super is made for gaming at 4K resolution with maximum graphics settings.

Adobe Creative Cloud with the RTX 4080 Super

With the NVIDIA GeForce RTX 4080 Super, Adobe Creative Cloud tools are faster than ever before. Whether you are a digital artist, professional photographer, editor, or motion graphics specialist, with NVIDIA you benefit from the best features and strongest performance of the Creative Cloud.

AV1 Support: Better Quality for Your Live Stream

NVIDIA's NVENC encoder is an independent part of the GeForce RTX 4080 Super GPU. It is used to encode videos and relieve the CPU. This allows your system to free up resources for games while streaming simultaneously, so you can focus on what matters most: a truly stunning transmission. The new RTX 4000 graphics cards use two NVENC encoders with AV1. This allows you to stream 1440p content with the same performance as H.264, but in 1080p. Additionally, the encoder with ShadowPlay allows you to record in 8K60 and HDR.

Performance Data of the NVIDIA GeForce RTX 4080 Super Graphics Card (Reference Model):

• Compute Performance (FP32): approx. 52.2 TFLOPS
• CUDA Cores: 10,240
• RT Cores: 80
• Tensor Cores: 320
• GPU Base Clock: 2,295 MHz
• GPU Boost Clock: 2,550 MHz
• Graphics Memory: 16 GB GDDR6X
• Memory Clock: 2,875 MHz (effective 23,000 MHz)
• Memory Interface: 256-bit
• Memory Bandwidth: 736 GB/s
• TDP: 320 watts
• Power Connector: 1x 16-pin PCIe 5.0 (12VHPWR)
• Video Outputs: DP 1.4, HDMI 2.1

GeForce RTX 4080 Super: The Ada Lovelace GPU Architecture

The Ada GPU architecture offers some optimizations over Ampere. The number of CUDA cores per SM (Streaming Multiprocessors) has increased from 84 to 128. Depending on the workload, an ADA Lovelace SM can perform either 128 FP32 or 64 FP32 and 64 INT32 computations. Each SM thus consists of four blocks with 16 FP32 ALUs and FP32/INT32 ALUs each. As with Ampere, each SM has a ray tracing computation core.

With 80 SMs, the RTX 4080 Super thus has 10,240 CUDA cores (5,120 FP32 and FP32/INT32 ALUs each) and 80 ray tracing cores. The 80 SMs are divided into 7 GPCs (Graphics Processing Clusters) in the RTX 4080 Super, and each SM has 4 tensor cores. However, the tensor cores in version 4 on the Ada GPUs are much more powerful than on Ampere.

Ray Tracing Performance of the RTX 4080 Super

Ada GPUs are equipped with a new technology called Shader Execution Reordering (SER), which can increase the ray tracing performance by up to three times compared to the Ampere generation. Command workloads are sorted more efficiently. This can increase in-game FPS by up to 25%.

Ray tracing (RT) enables realistic lighting by simulating the physical properties and behavior of light. RT is the calculation of the color of individual pixels during the path that light takes from the user's eye through a 3D landscape. The light traverses the 3D scenery and is reflected or creates reflections from objects. At the same time, shadows, transparent, or semi-transparent objects are created. This creates refractions or distortions.

Ray tracing combines all these effects to represent the final color of a pixel on the monitor. Previously, ray tracing was primarily used in movies to create special effects. Render farms are often used for these scenes, and calculating complex 3D animations and special effects for movies can take several weeks. Due to the complexity of ray tracing, PC applications such as computer games have typically been filled with 3D objects based on a raster model. In rasterization, 3D objects are modeled from a network of triangles or polygons. In the rendering pipeline, these triangles of the 3D model are individually converted into pixels on a 2D screen. The pixels can then be further processed ("shaded").

Tensor & DLSS 3