Radeon Pro 580 and GeForce RTX 4090 Ti - video card comparison

Radeon Pro 580

GeForce RTX 4090 Ti

Architecture

GCN 4.0 (2016−2020)

Ada Lovelace

GPU code name

Polaris 20

AD102

Market segment

Mobile workstation

Desktop

Release date

June 2017

2023

Interface

PCIe 3.0 x16

PCIe 4.0 x16

Supplementary power connectors

None

2x 16-pin

Boost clock speed

1200 MHz

2565 MHz

Core clock speed

1100 MHz

Floating-point performance

6,175 gflops

Manufacturing process technology

14 nm

5 nm

Number of transistors

5,700 million

76,300 million

Pipelines / CUDA cores

2304

18176

Power consumption (TDP)

150 Watt

600 Watt

Texture fill rate

172.8

1,457

Memory type

GDDR5

GDDR6X

Maximum RAM amount

8 GB

24 GB

Memory bus width

256 Bit

384 Bit

Memory clock speed

6780 MHz

24 GB/s

Memory bandwidth

217.0 GB/s

1,152 GB/s

Display Connectors

No outputs

1x HDMI 2.1, 3x DisplayPort 1.4a

HDMI

DirectX

12 (12_0)

12 Ultimate (12_2)

CUDA

8.9

OpenCL

2.0

3.0

OpenGL

4.6

Shader Model

6.4

6.7

Vulkan

1.2.131

1.3