A40 PCIe and Radeon PRO W7900 - video card comparison

A40 PCIe

Radeon PRO W7900

Architecture

Ampere (2020−2022)

RDNA 3.0 (2022)

GPU code name

GA102

Navi 31

Market segment

Desktop

Workstation

Release date

October 2020

April 2023

Interface

PCIe 4.0 x16

PCIe 4.0 x16

Supplementary power connectors

8-pin EPS

2x 8-pin

Boost clock speed

1755 MHz

2495 MHz

Manufacturing process technology

8 nm

5 nm

Number of transistors

28,300 million

57,700 million

Pipelines / CUDA cores

10752

6144

Power consumption (TDP)

300 Watt

295 Watt

Texture fill rate

589.7

958.1

Memory type

GDDR6

GDDR6

Maximum RAM amount

48 GB

48 GB

Memory bus width

384 Bit

384 Bit

Memory clock speed

14.5 GB/s

18 GB/s

Memory bandwidth

695.8 GB/s

864.0 GB/s

Display Connectors

3x DisplayPort

3x DisplayPort 2.1, 1x mini-DisplayPort 2.1

DirectX

12 Ultimate (12_2)

12 Ultimate (12_2)

CUDA

8.6

-

OpenCL

2.0

2.2

OpenGL

4.6

4.6

Shader Model

6.5

6.7

Vulkan

1.2

1.3