Tesla M2070-Q and Tesla K80m - video card comparison

Tesla M2070-Q

Tesla K80m

Architecture

Fermi (2010−2014)

Kepler 2.0 (2013−2015)

GPU code name

GF100

GK210

Market segment

Workstation

Workstation

Release date

July 2011

November 2014

Interface

PCIe 2.0 x16

PCIe 3.0 x16

Supplementary power connectors

1x 6-pin + 1x 8-pin

1x 8-pin

Boost clock speed

-

824 MHz

Core clock speed

574 MHz

562 MHz

Floating-point performance

1,027.7 gflops

2x 4,373 gflops

Manufacturing process technology

40 nm

28 nm

Number of transistors

3,100 million

7,100 million

Pipelines / CUDA cores

448

2x 2496

Power consumption (TDP)

225 Watt

300 Watt

Texture fill rate

32.14

2x 182.2 billion/sec

Memory type

GDDR5

GDDR5

Maximum RAM amount

6 GB

2x 12 GB

Memory bus width

384 Bit

2x 384 Bit

Memory clock speed

3132 MHz

5012 MHz

Memory bandwidth

150.3 GB/s

2x 240.6 GB/s

Display Connectors

No outputs

No outputs

DirectX

12 (11_0)

12.0 (11_1)

CUDA

2.0

-

OpenCL

1.1

-

OpenGL

4.6

4.6

Shader Model

5.1

-

Vulkan

N/A

-