Radeon RX 580 and GeForce RTX 5090 - video card comparison

Radeon RX 580

GeForce RTX 5090

Architecture

Polaris (2016−2019)

Blackwell 2.0

GPU code name

Polaris 20

GB202

Market segment

Desktop

Desktop

Release date

April 2017

2025 (recently)

Interface

PCIe 3.0 x16

PCIe 5.0 x16

Supplementary power connectors

1x 8-pin

1x 16-pin

Boost clock speed

1340 MHz

2520 MHz

Core clock speed

1257 MHz

-

Floating-point performance

6,175 gflops

-

Manufacturing process technology

14 nm

0 nm

Number of transistors

5,700 million

-

Pipelines / CUDA cores

2304

20480

Power consumption (TDP)

185 Watt

500 Watt

Texture fill rate

193.0

1,613

Memory type

GDDR5

GDDR7

Maximum RAM amount

8 GB

28 GB

Memory bus width

256 Bit

448 Bit

Memory clock speed

8000 MHz

5 GB/s

Memory bandwidth

256.0 GB/s

280.0 GB/s

Display Connectors

1x HDMI, 3x DisplayPort

1x HDMI 2.1, 3x DisplayPort 1.4a

HDMI

+

+

DirectX

12 (12_0)

12 Ultimate (12_2)

CUDA

-

9.1

OpenCL

2.0

3.0

OpenGL

4.6

4.6

Shader Model

6.4

6.7

Vulkan

1.2.131

1.3