Tesla K80 and Radeon Pro WX 8100 - video card comparison
Tesla K80
Radeon Pro WX 8100
Architecture
Kepler 2.0 (2013−2015)
GCN 5.0 (2017−2020)
GPU code name
GK210
Vega 10
Market segment
Workstation
Workstation
Release date
November 2014
December 2017
Interface
PCIe 3.0 x16
PCIe 3.0 x16
Supplementary power connectors
1x 8-pin
1x 6-pin + 1x 8-pin
Boost clock speed
824 MHz
1500 MHz
Core clock speed
562 MHz
1200 MHz
Manufacturing process technology
28 nm
14 nm
Number of transistors
7,100 million
12,500 million
Pipelines / CUDA cores
2496
3584
Power consumption (TDP)
300 Watt
230 Watt
Texture fill rate
171.4
336.0
Memory type
GDDR5
HBM2
Maximum RAM amount
12 GB
8 GB
Memory bus width
384 Bit
2048 Bit
Memory clock speed
5012 MHz
2000 MHz
Memory bandwidth
240.6 GB/s
512.0 GB/s
Display Connectors
No outputs
6x mini-DisplayPort
DirectX
12 (11_1)
12 (12_1)
CUDA
3.7
-
OpenCL
1.2
2.0
OpenGL
4.6
4.6
Shader Model
5.1
6.4
Vulkan
1.1.126
1.1.125