Radeon RX 580 and RTX A40 - video card comparison

Radeon RX 580

RTX A40

Architecture

Polaris (2016−2019)

Ampere (2020−2022)

GPU code name

Polaris 20

GA102

Market segment

Desktop

Desktop

Release date

April 2017

October 2020

Interface

PCIe 3.0 x16

PCIe 4.0 x16

Supplementary power connectors

1x 8-pin

8-pin EPS

Boost clock speed

1340 MHz

1755 MHz

Core clock speed

1257 MHz

-

Floating-point performance

6,175 gflops

-

Manufacturing process technology

14 nm

8 nm

Number of transistors

5,700 million

28,300 million

Pipelines / CUDA cores

2304

10752

Power consumption (TDP)

185 Watt

300 Watt

Texture fill rate

193.0

589.7

Memory type

GDDR5

GDDR6

Maximum RAM amount

8 GB

48 GB

Memory bus width

256 Bit

384 Bit

Memory clock speed

8000 MHz

14.5 GB/s

Memory bandwidth

256.0 GB/s

695.8 GB/s

Display Connectors

1x HDMI, 3x DisplayPort

3x DisplayPort

HDMI

+

-

DirectX

12 (12_0)

12 Ultimate (12_2)

CUDA

-

8.6

OpenCL

2.0

2.0

OpenGL

4.6

4.6

Shader Model

6.4

6.5

Vulkan

1.2.131

1.2