GeForce RTX 3080 Ti and Tesla M2050 - video card comparison

GeForce RTX 3080 Ti

Tesla M2050

Architecture

Ampere (2020−2022)

Fermi (2010−2014)

GPU code name

Ampere GA102

GF100

Market segment

Desktop

Workstation

Release date

September 2020

July 2011

Interface

PCIe 4.0 x16

PCIe 2.0 x16

Supplementary power connectors

1x 12-pin

1x 6-pin + 1x 8-pin

Boost clock speed

1667 MHz

-

Core clock speed

1370 MHz

575 MHz

Floating-point performance

-

1,030.4 gflops

Manufacturing process technology

8 nm

40 nm

Number of transistors

28,300 million

3,100 million

Pipelines / CUDA cores

10240

448

Power consumption (TDP)

350 Watt

225 Watt

Texture fill rate

532.8

32.20

Memory type

GDDR6X

GDDR5

Maximum RAM amount

12 GB

3 GB

Memory bus width

384 Bit

384 Bit

Memory clock speed

19000 MHz

3092 MHz

Memory bandwidth

912.4 GB/s

148.4 GB/s

Shared memory

-

-

Display Connectors

1x HDMI, 3x DisplayPort

No outputs

HDMI

+

-

DirectX

12 Ultimate (12_2)

12 (11_0)

CUDA

8.6

2.0

OpenCL

3.0

1.1

OpenGL

4.6

4.6

Shader Model

6.6

5.1

Vulkan

1.2

N/A