RTX A40 and CMP 40HX - video card comparison
RTX A40
CMP 40HX
Architecture
Ampere (2020−2022)
Turing (2018−2021)
GPU code name
GA102
TU106
Market segment
Desktop
Desktop
Release date
October 2020
February 2021
Interface
PCIe 4.0 x16
PCIe 3.0 x16
Supplementary power connectors
8-pin EPS
1x 8-pin
Boost clock speed
1755 MHz
1650 MHz
Manufacturing process technology
8 nm
12 nm
Number of transistors
28,300 million
10,800 million
Pipelines / CUDA cores
10752
2304
Power consumption (TDP)
300 Watt
185 Watt
Texture fill rate
589.7
237.6
Memory type
GDDR6
GDDR6
Maximum RAM amount
48 GB
8 GB
Memory bus width
384 Bit
256 Bit
Memory clock speed
14.5 GB/s
14 GB/s
Memory bandwidth
695.8 GB/s
448.0 GB/s
Display Connectors
3x DisplayPort
No outputs
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
CUDA
8.6
7.5
OpenCL
2.0
3.0
OpenGL
4.6
4.6
Shader Model
6.5
6.6
Vulkan
1.2
1.2