TITAN RTX and Tesla A100 - video card comparison

TITAN RTX

Tesla A100

Architecture

Turing (2018−2021)

Ampere (2020−2022)

GPU code name

TU102

GA100

Market segment

Desktop

Workstation

Release date

December 2018

-

Interface

PCIe 3.0 x16

PCIe 4.0 x16

Supplementary power connectors

2x 8-pin

None

Boost clock speed

1770 MHz

-

Core clock speed

1350 MHz

1110 MHz

Manufacturing process technology

12 nm

7 nm

Number of transistors

18,600 million

38,000 million

Pipelines / CUDA cores

4608

7936

Power consumption (TDP)

280 Watt

260 Watt

Texture fill rate

509.8

550.6

Memory type

GDDR6

HBM2e

Maximum RAM amount

24 GB

32 GB

Memory bus width

384 Bit

4096 Bit

Memory clock speed

14000 MHz

2400 MHz

Memory bandwidth

672.0 GB/s

1,229 GB/s

Display Connectors

1x HDMI, 3x DisplayPort, 1x USB Type-C

No outputs

HDMI

+

-

DirectX

12 Ultimate (12_1)

12 (12_1)

CUDA

7.5

-

OpenCL

2.0

-

OpenGL

4.6

4.6

Shader Model

6.5

-

Vulkan

1.2.131

-