
Radeon Pro W6900X and GeForce RTX 3090 SUPER - video card comparison
Radeon Pro W6900X
GeForce RTX 3090 SUPER
Architecture
RDNA 2.0 (2020−2022)
Ampere (2020−2022)
GPU code name
Navi 21
GA102
Market segment
Workstation
Desktop
Release date
August 2021
-
Interface
PCIe 4.0 x16
PCIe 4.0 x16
Supplementary power connectors
None
1x 12-pin
Boost clock speed
2150 MHz
1695 MHz
Manufacturing process technology
7 nm
8 nm
Number of transistors
26,800 million
28,300 million
Pipelines / CUDA cores
5120
10752
Power consumption (TDP)
300 Watt
400 Watt
Texture fill rate
688.0
569.5
Memory type
GDDR6
GDDR6X
Maximum RAM amount
32 GB
24 GB
Memory bus width
256 Bit
384 Bit
Memory clock speed
16 GB/s
21.2 GB/s
Memory bandwidth
512.0 GB/s
1,018 GB/s
Display Connectors
1x HDMI, 4x Thunderbolt
1x HDMI, 3x DisplayPort
HDMI
+
+
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
CUDA
-
8.6
OpenCL
2.1
3.0
OpenGL
4.6
4.6
Shader Model
6.5
6.6
Vulkan
1.2
1.2