GRID A100A and Tesla X2070 - video card comparison
GRID A100A
Tesla X2070
Architecture
Ampere (2020−2022)
Fermi 2.0 (2010−2014)
GPU code name
GA100
GF110
Market segment
Workstation
Workstation
Release date
May 2020
July 2011
Interface
PCIe 4.0 x16
PCIe 2.0 x16
Supplementary power connectors
None
-
Boost clock speed
1005 MHz
-
Core clock speed
-
651 MHz
Floating-point performance
-
1,331.2 gflops
Manufacturing process technology
7 nm
40 nm
Number of transistors
54,200 million
3,000 million
Pipelines / CUDA cores
6912
512
Power consumption (TDP)
400 Watt
225 Watt
Texture fill rate
434.2
41.66
Memory type
HBM2e
GDDR5
Maximum RAM amount
48 GB
6 GB
Memory bus width
6144 Bit
384 Bit
Memory clock speed
2.4 GB/s
3696 MHz
Memory bandwidth
1,866 GB/s
177.4 GB/s
Display Connectors
No outputs
No outputs
DirectX
12 Ultimate (12_2)
12 (11_0)
CUDA
8.0
2.0
OpenCL
2.0
1.1
OpenGL
4.6
4.6
Shader Model
6.5
5.1
Vulkan
1.2
N/A