L40 CNX and RTX A400 - video card comparison

L40 CNX

RTX A400

Architecture

Ada Lovelace

Ampere (2020−2022)

GPU code name

AD102

GA107

Market segment

Desktop

Desktop

Release date

October 2022

April 2024

Interface

PCIe 4.0 x16

PCIe 4.0 x8

Supplementary power connectors

1x 16-pin

None

Boost clock speed

2475 MHz

1762 MHz

Manufacturing process technology

4 nm

8 nm

Number of transistors

76,300 million

8,700 million

Pipelines / CUDA cores

18176

768

Power consumption (TDP)

300 Watt

50 Watt

Texture fill rate

1,406

42.29

Memory type

GDDR6

GDDR6

Maximum RAM amount

24 GB

4 GB

Memory bus width

384 Bit

64 Bit

Memory clock speed

18 GB/s

12 GB/s

Memory bandwidth

864.0 GB/s

96 GB/s

Display Connectors

1x HDMI 2.1, 3x DisplayPort 1.4a

4x mini-DisplayPort 1.4a

HDMI

+

-

DirectX

12 Ultimate (12_2)

12 Ultimate (12_2)

CUDA

8.9

8.6

OpenCL

3.0

3.0

OpenGL

4.6

4.6

Shader Model

6.7

6.7

Vulkan

1.3

1.3