RTX A40 and GeForce RTX 3090 SUPER - video card comparison
RTX A40
GeForce RTX 3090 SUPER
Architecture
Ampere (2020−2022)
Ampere (2020−2022)
GPU code name
GA102
GA102
Market segment
Desktop
Desktop
Release date
October 2020
-
Interface
PCIe 4.0 x16
PCIe 4.0 x16
Supplementary power connectors
8-pin EPS
1x 12-pin
Boost clock speed
1755 MHz
1695 MHz
Manufacturing process technology
8 nm
8 nm
Number of transistors
28,300 million
28,300 million
Pipelines / CUDA cores
10752
10752
Power consumption (TDP)
300 Watt
400 Watt
Texture fill rate
589.7
569.5
Memory type
GDDR6
GDDR6X
Maximum RAM amount
48 GB
24 GB
Memory bus width
384 Bit
384 Bit
Memory clock speed
14.5 GB/s
21.2 GB/s
Memory bandwidth
695.8 GB/s
1,018 GB/s
Display Connectors
3x DisplayPort
1x HDMI, 3x DisplayPort
HDMI
-
+
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
CUDA
8.6
8.6
OpenCL
2.0
3.0
OpenGL
4.6
4.6
Shader Model
6.5
6.6
Vulkan
1.2
1.2