Tesla M2090 and Tesla T4 - video card comparison
Tesla M2090
Tesla T4
Architecture
Fermi 2.0 (2010−2014)
Turing (2018−2021)
GPU code name
GF110
TU104
Market segment
Workstation
Workstation
Release date
July 2011
September 2018
Interface
PCIe 2.0 x16
PCIe 3.0 x16
Supplementary power connectors
1x 6-pin + 1x 8-pin
None
Boost clock speed
-
1590 MHz
Core clock speed
651 MHz
585 MHz
Floating-point performance
1,331.2 gflops
-
Manufacturing process technology
40 nm
12 nm
Number of transistors
3,000 million
13,600 million
Pipelines / CUDA cores
512
2560
Power consumption (TDP)
250 Watt
70 Watt
Texture fill rate
41.66
254.4
Memory type
GDDR5
GDDR6
Maximum RAM amount
6 GB
16 GB
Memory bus width
384 Bit
256 Bit
Memory clock speed
3696 MHz
10000 MHz
Memory bandwidth
177.4 GB/s
320.0 GB/s
Display Connectors
No outputs
No outputs
DirectX
12 (11_0)
12 Ultimate (12_1)
CUDA
2.0
7.5
OpenCL
1.1
1.2
OpenGL
4.6
4.6
Shader Model
5.1
6.5
Vulkan
N/A
1.2.131