Tesla K80 and Tesla P6 - video card comparison
Tesla K80
Tesla P6
Architecture
Kepler 2.0 (2013−2015)
Pascal (2016−2021)
GPU code name
GK210
GP104
Market segment
Workstation
Workstation
Release date
November 2014
March 2017
Interface
PCIe 3.0 x16
MXM-B (3.0)
Supplementary power connectors
1x 8-pin
None
Boost clock speed
824 MHz
1506 MHz
Core clock speed
562 MHz
1012 MHz
Floating-point performance
-
6,169 gflops
Manufacturing process technology
28 nm
16 nm
Number of transistors
7,100 million
7,200 million
Pipelines / CUDA cores
2496
2048
Power consumption (TDP)
300 Watt
90 Watt
Texture fill rate
171.4
192.8
Memory type
GDDR5
GDDR5
Maximum RAM amount
12 GB
16 GB
Memory bus width
384 Bit
256 Bit
Memory clock speed
5012 MHz
6008 MHz
Memory bandwidth
240.6 GB/s
192.3 GB/s
Display Connectors
No outputs
No outputs
DirectX
12 (11_1)
12 (12_1)
CUDA
3.7
6.1
OpenCL
1.2
1.2
OpenGL
4.6
4.6
Shader Model
5.1
6.4
Vulkan
1.1.126
1.2.131