Tesla M2090 and P104-100 - video card comparison
Tesla M2090
P104-100
Architecture
Fermi 2.0 (2010−2014)
Pascal (2016−2021)
GPU code name
GF110
GP104
Market segment
Workstation
Desktop
Release date
July 2011
December 2017
Interface
PCIe 2.0 x16
PCIe 3.0 x16
Supplementary power connectors
1x 6-pin + 1x 8-pin
1x 8-pin
Boost clock speed
-
1733 MHz
Core clock speed
651 MHz
1607 MHz
Floating-point performance
1,331.2 gflops
8,873 gflops
Manufacturing process technology
40 nm
16 nm
Number of transistors
3,000 million
7,200 million
Pipelines / CUDA cores
512
1920
Power consumption (TDP)
250 Watt
-
Texture fill rate
41.66
208.0
Memory type
GDDR5
GDDR5X
Maximum RAM amount
6 GB
4 GB
Memory bus width
384 Bit
256 Bit
Memory clock speed
3696 MHz
10008 MHz
Memory bandwidth
177.4 GB/s
320.3 GB/s
Display Connectors
No outputs
No outputs
DirectX
12 (11_0)
12 (12_1)
CUDA
2.0
6.1
OpenCL
1.1
1.2
OpenGL
4.6
4.6
Shader Model
5.1
6.4
Vulkan
N/A
1.2.131