GeForce RTX 2080 Ti and GeForce RTX 3090 SUPER - video card comparison

GeForce RTX 2080 Ti

GeForce RTX 3090 SUPER

Architecture

Turing (2018−2021)

Ampere (2020−2022)

GPU code name

Turing TU102

GA102

Market segment

Desktop

Release date

August 2018

Interface

PCIe 3.0 x16

PCIe 4.0 x16

Supplementary power connectors

2x 8-pin

1x 12-pin

Boost clock speed

1545 MHz

1695 MHz

Core clock speed

1350 MHz

Manufacturing process technology

12 nm

8 nm

Number of transistors

18,600 million

28,300 million

Pipelines / CUDA cores

4352

10752

Power consumption (TDP)

270 Watt

400 Watt

Texture fill rate

420.2

569.5

Memory type

GDDR6

GDDR6X

Maximum RAM amount

11 GB

24 GB

Memory bus width

352 Bit

384 Bit

Memory clock speed

14000 MHz

21.2 GB/s

Memory bandwidth

616.0 GB/s

1,018 GB/s

Shared memory

Display Connectors

1x HDMI, 3x DisplayPort, 1x USB Type-C

1x HDMI, 3x DisplayPort

HDMI

G-SYNC support

DirectX

12 Ultimate (12_1)

12 Ultimate (12_2)

CUDA

7.5

8.6

OpenCL

2.0

3.0

OpenGL

4.6

Shader Model

6.5

6.6

Vulkan

1.2.131

1.2

VR Ready