Tesla K8 and Tesla M2090 - video card comparison
Tesla K8
Tesla M2090
Architecture
Kepler (2012−2018)
Fermi 2.0 (2010−2014)
GPU code name
GK104
GF110
Market segment
Workstation
Workstation
Release date
September 2014
July 2011
Interface
PCIe 2.0 x16
PCIe 2.0 x16
Supplementary power connectors
1x 6-pin
1x 6-pin + 1x 8-pin
Boost clock speed
811 MHz
-
Core clock speed
693 MHz
651 MHz
Floating-point performance
2,491 gflops
1,331.2 gflops
Manufacturing process technology
28 nm
40 nm
Number of transistors
3,540 million
3,000 million
Pipelines / CUDA cores
1536
512
Power consumption (TDP)
100 Watt
250 Watt
Texture fill rate
103.8
41.66
Memory type
GDDR5
GDDR5
Maximum RAM amount
8 GB
6 GB
Memory bus width
256 Bit
384 Bit
Memory clock speed
5000 MHz
3696 MHz
Memory bandwidth
160.0 GB/s
177.4 GB/s
Display Connectors
No outputs
No outputs
DirectX
12 (11_0)
12 (11_0)
CUDA
3.0
2.0
OpenCL
1.2
1.1
OpenGL
4.6
4.6
Shader Model
5.1
5.1
Vulkan
1.1.126
N/A