Radeon Pro V320 and CMP 50HX - video card comparison

Radeon Pro V320

CMP 50HX

Architecture

GCN 5.0 (2017−2020)

Turing (2018−2021)

GPU code name

Vega 10

TU102

Market segment

Workstation

Desktop

Release date

June 2017

June 2021

Interface

PCIe 3.0 x16

PCIe 3.0 x16

Supplementary power connectors

2x 8-pin

2x 8-pin

Boost clock speed

1500 MHz

1545 MHz

Core clock speed

852 MHz

-

Manufacturing process technology

14 nm

12 nm

Number of transistors

12,500 million

18,600 million

Pipelines / CUDA cores

3584

3584

Power consumption (TDP)

230 Watt

250 Watt

Texture fill rate

336.0

296.6

Memory type

HBM2

GDDR6

Maximum RAM amount

8 GB

10 GB

Memory bus width

2048 Bit

320 Bit

Memory clock speed

1890 MBps

14 GB/s

Memory bandwidth

483.8 GB/s

560.0 GB/s

Display Connectors

4x mini-DisplayPort 1.4a

No outputs

DirectX

12 (12_1)

12 Ultimate (12_2)

CUDA

-

7.5

OpenCL

2.1

3.0

OpenGL

4.6

4.6

Shader Model

6.7

6.6

Vulkan

1.3

1.2