Radeon Pro VII and CMP 50HX - video card comparison
Radeon Pro VII
CMP 50HX
Architecture
GCN 5.1 (2018−2021)
Turing (2018−2021)
GPU code name
Vega 20
TU102
Market segment
Workstation
Desktop
Release date
May 2020
June 2021
Interface
PCIe 4.0 x16
PCIe 3.0 x16
Supplementary power connectors
1x 6-pin + 1x 8-pin
2x 8-pin
Boost clock speed
1700 MHz
1545 MHz
Manufacturing process technology
7 nm
12 nm
Number of transistors
13,230 million
18,600 million
Pipelines / CUDA cores
3840
3584
Power consumption (TDP)
250 Watt
250 Watt
Texture fill rate
408.0
296.6
Memory type
HBM2
GDDR6
Maximum RAM amount
16 GB
10 GB
Memory bus width
4096 Bit
320 Bit
Memory clock speed
2 GB/s
14 GB/s
Memory bandwidth
1024 GB/s
560.0 GB/s
Display Connectors
6x 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