Tesla K80m and Tesla T40 24 GB - video card comparison

Tesla K80m

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

-

Floating-point performance

2x 4,373 gflops

-

Manufacturing process technology

28 nm

12 nm

Number of transistors

7,100 million

18,600 million

Pipelines / CUDA cores

2x 2496

4608

Power consumption (TDP)

300 Watt

260 Watt

Texture fill rate

2x 182.2 billion/sec

449.3

Memory type

GDDR5

GDDR6

Maximum RAM amount

2x 12 GB

24 GB

Memory bus width

2x 384 Bit

384 Bit

Memory clock speed

5012 MHz

13 GB/s

Memory bandwidth

2x 240.6 GB/s

624.0 GB/s

Display Connectors

No outputs

No outputs

DirectX

12.0 (11_1)

12 Ultimate (12_2)

CUDA

-

7.5

OpenCL

-

3.0

OpenGL

4.6

4.6

Shader Model

-

6.7

Vulkan

-

1.3