GeForce RTX 2080 Super and A100 PCIe - video card comparison
GeForce RTX 2080 Super
A100 PCIe
Architecture
Turing (2018−2021)
Ampere (2020−2022)
GPU code name
Turing TU104
GA100
Market segment
Desktop
Desktop
Release date
July 2019
June 2020
Interface
PCIe 3.0 x16
PCIe 4.0 x16
Supplementary power connectors
1x 6-pin + 1x 8-pin
1x 8-pin
Boost clock speed
1815 MHz
-
Core clock speed
1650 MHz
1410 MHz
Manufacturing process technology
12 nm
7 nm
Number of transistors
13,600 million
54,200 million
Pipelines / CUDA cores
3072
6912
Power consumption (TDP)
250 Watt
250 Watt
Texture fill rate
348.5
609.1
Memory type
GDDR6
HBM2e
Maximum RAM amount
8 GB
40 GB
Memory bus width
256 Bit
5120 Bit
Memory clock speed
15500 MHz
2.4 GB/s
Memory bandwidth
495.9 GB/s
1,555 GB/s
Shared memory
-
-
Display Connectors
1x HDMI, 3x DisplayPort, 1x USB Type-C
No outputs
HDMI
+
-
G-SYNC support
+
-
DirectX
12 Ultimate (12_1)
12 Ultimate (12_2)
CUDA
7.5
8.0
OpenCL
1.2
2.0
OpenGL
4.6
4.6
Shader Model
6.5
6.5
Vulkan
1.2.131
1.2
VR Ready
+
-