Tesla K80 and CMP 50HX - video card comparison
Tesla K80
CMP 50HX
Architecture
Kepler 2.0 (2013−2015)
Turing (2018−2021)
GPU code name
GK210
TU102
Market segment
Workstation
Desktop
Release date
November 2014
June 2021
Interface
PCIe 3.0 x16
PCIe 3.0 x16
Supplementary power connectors
1x 8-pin
2x 8-pin
Boost clock speed
824 MHz
1545 MHz
Core clock speed
562 MHz
-
Manufacturing process technology
28 nm
12 nm
Number of transistors
7,100 million
18,600 million
Pipelines / CUDA cores
2496
3584
Power consumption (TDP)
300 Watt
250 Watt
Texture fill rate
171.4
296.6
Memory type
GDDR5
GDDR6
Maximum RAM amount
12 GB
10 GB
Memory bus width
384 Bit
320 Bit
Memory clock speed
5012 MHz
14 GB/s
Memory bandwidth
240.6 GB/s
560.0 GB/s
Display Connectors
No outputs
No outputs
DirectX
12 (11_1)
12 Ultimate (12_2)
CUDA
3.7
7.5
OpenCL
1.2
3.0
OpenGL
4.6
4.6
Shader Model
5.1
6.6
Vulkan
1.1.126
1.2