Tesla M40 and Tesla M2050 - video card comparison
Tesla M40
Tesla M2050
Architecture
Maxwell 2.0 (2015−2019)
Fermi (2010−2014)
GPU code name
GM200
GF100
Market segment
Workstation
Workstation
Release date
November 2015
July 2011
Interface
PCIe 3.0 x16
PCIe 2.0 x16
Supplementary power connectors
8-pin EPS
1x 6-pin + 1x 8-pin
Boost clock speed
1112 MHz
-
Core clock speed
948 MHz
575 MHz
Floating-point performance
6,844 gflops
1,030.4 gflops
Manufacturing process technology
28 nm
40 nm
Number of transistors
8,000 million
3,100 million
Pipelines / CUDA cores
3072
448
Power consumption (TDP)
250 Watt
225 Watt
Texture fill rate
213.5
32.20
Memory type
GDDR5
GDDR5
Maximum RAM amount
12 GB
3 GB
Memory bus width
384 Bit
384 Bit
Memory clock speed
6 GB/s
3092 MHz
Memory bandwidth
288.4 GB/s
148.4 GB/s
Display Connectors
No outputs
No outputs
DirectX
12 (12_1)
12 (11_0)
CUDA
5.2
2.0
OpenCL
3.0
1.1
OpenGL
4.6
4.6
Shader Model
6.7
5.1
Vulkan
1.3
N/A