Tesla K80 and Tesla T40 24 GB - video card comparison

Tesla K80

Tesla T40 24 GB

Architecture

Kepler 2.0 (2013−2015)

Turing (2018−2021)

GPU code name

GK210

TU102

Market segment

Workstation

Workstation

Release date

November 2014

-

Interface

PCIe 3.0 x16

PCIe 3.0 x16

Supplementary power connectors

1x 8-pin

1x 6-pin + 1x 8-pin

Boost clock speed

824 MHz

1560 MHz

Core clock speed

562 MHz

-

Manufacturing process technology

28 nm

12 nm

Number of transistors

7,100 million

18,600 million

Pipelines / CUDA cores

2496

4608

Power consumption (TDP)

300 Watt

260 Watt

Texture fill rate

171.4

449.3

Memory type

GDDR5

GDDR6

Maximum RAM amount

12 GB

24 GB

Memory bus width

384 Bit

384 Bit

Memory clock speed

5012 MHz

13 GB/s

Memory bandwidth

240.6 GB/s

624.0 GB/s

Display Connectors

No outputs

No outputs

DirectX

12 (11_1)

12 Ultimate (12_2)

CUDA

3.7

7.5

OpenCL

1.2

3.0

OpenGL

4.6

4.6

Shader Model

5.1

6.7

Vulkan

1.1.126

1.3