A100 PCIe and GeForce RTX 4080 Ti - video card comparison

A100 PCIe

GeForce RTX 4080 Ti

Architecture

Ampere (2020−2022)

Ada Lovelace

GPU code name

GA100

AD102

Market segment

Desktop

Release date

June 2020

2023

Interface

PCIe 4.0 x16

Supplementary power connectors

1x 8-pin

1x 16-pin

Boost clock speed

2610 MHz

Core clock speed

1410 MHz

Manufacturing process technology

7 nm

5 nm

Number of transistors

54,200 million

76,300 million

Pipelines / CUDA cores

6912

14080

Power consumption (TDP)

250 Watt

400 Watt

Texture fill rate

609.1

1,148

Memory type

HBM2e

GDDR6X

Maximum RAM amount

40 GB

16 GB

Memory bus width

5120 Bit

256 Bit

Memory clock speed

2.4 GB/s

21.2 GB/s

Memory bandwidth

1,555 GB/s

678.4 GB/s

Display Connectors

No outputs

1x HDMI 2.1, 3x DisplayPort 1.4a

HDMI

DirectX

12 Ultimate (12_2)

CUDA

8.0

8.9

OpenCL

2.0

3.0

OpenGL

4.6

Shader Model

6.5

6.7

Vulkan

1.2

1.3