Radeon Pro SSG and CMP 40HX - video card comparison

Passmark - benchmark score Radeon Pro SSG vs CMP 40HX

Radeon Pro SSG

11300

CMP 40HX

6981

Radeon Pro SSG

CMP 40HX

Architecture

GCN 3.0 (2014−2017)

Turing (2018−2021)

GPU code name

Fiji

TU106

Market segment

Workstation

Desktop

Release date

July 2016

February 2021

Interface

PCIe 3.0 x16

Supplementary power connectors

1x 6-pin + 1x 8-pin

1x 8-pin

Boost clock speed

1050 MHz

1650 MHz

Core clock speed

1440 MHz

Floating-point performance

12,288 gflops

Manufacturing process technology

28 nm

12 nm

Number of transistors

8,900 million

10,800 million

Pipelines / CUDA cores

4096

2304

Power consumption (TDP)

260 Watt

185 Watt

Texture fill rate

268.8

237.6

Memory type

HBM

GDDR6

Maximum RAM amount

4 GB

8 GB

Memory bus width

4096 Bit

256 Bit

Memory clock speed

1000 MBps

14 GB/s

Memory bandwidth

512.0 GB/s

448.0 GB/s

Display Connectors

1x HDMI 1.4a, 3x mini-DisplayPort 1.2

No outputs

HDMI

DirectX

12 (12_0)

12 Ultimate (12_2)

CUDA

7.5

OpenCL

2.1

3.0

OpenGL

4.6

Shader Model

6.5

6.6

Vulkan

1.2.170

1.2