GeForce RTX 3090 and Tesla T40 24 GB - video card comparison

GeForce RTX 3090

Tesla T40 24 GB

Architecture

Ampere (2020−2022)

Turing (2018−2021)

GPU code name

Ampere GA102

TU102

Market segment

Desktop

Workstation

Release date

September 2020

Interface

PCIe 4.0 x16

PCIe 3.0 x16

Supplementary power connectors

1x 12-pin

1x 6-pin + 1x 8-pin

Boost clock speed

1700 MHz

1560 MHz

Core clock speed

1400 MHz

Manufacturing process technology

8 nm

12 nm

Number of transistors

28,300 million

18,600 million

Pipelines / CUDA cores

10496

4608

Power consumption (TDP)

350 Watt

260 Watt

Texture fill rate

556.0

449.3

Memory type

GDDR6X

GDDR6

Maximum RAM amount

24 GB

Memory bus width

384 Bit

Memory clock speed

19500 MHz

13 GB/s

Memory bandwidth

936.2 GB/s

624.0 GB/s

Shared memory

Display Connectors

1x HDMI, 3x DisplayPort

No outputs

HDMI

DirectX

12 Ultimate (12_2)

CUDA

8.5

7.5

OpenCL

2.0

3.0

OpenGL

4.6

Shader Model

6.5

6.7

Vulkan

1.2

1.3