Tesla M40 and CMP 30HX - video card comparison

Passmark - benchmark score Tesla M40 vs CMP 30HX

Tesla M40

10687

CMP 30HX

8379

Tesla M40

CMP 30HX

Architecture

Maxwell 2.0 (2015−2019)

Turing (2018−2021)

GPU code name

GM200

TU116

Market segment

Workstation

Desktop

Release date

November 2015

February 2021

Interface

PCIe 3.0 x16

PCIe 3.0 x4

Supplementary power connectors

8-pin EPS

1x 8-pin

Boost clock speed

1112 MHz

1785 MHz

Core clock speed

948 MHz

Floating-point performance

6,844 gflops

Manufacturing process technology

28 nm

12 nm

Number of transistors

8,000 million

6,600 million

Pipelines / CUDA cores

3072

1408

Power consumption (TDP)

250 Watt

125 Watt

Texture fill rate

213.5

157.1

Memory type

GDDR5

GDDR6

Maximum RAM amount

12 GB

6 GB

Memory bus width

384 Bit

192 Bit

Memory clock speed

6 GB/s

14 GB/s

Memory bandwidth

288.4 GB/s

336.0 GB/s

Display Connectors

No outputs

DirectX

12 (12_1)

CUDA

5.2

7.5

OpenCL

3.0

OpenGL

4.6

Shader Model

6.7

6.6

Vulkan

1.3

1.2