GeForce RTX 3090 and Radeon PRO W7900 - video card comparison
Passmark - benchmark score GeForce RTX 3090 vs Radeon PRO W7900
GeForce RTX 3090
27596
Radeon PRO W7900
30067
GeForce RTX 3090
Radeon PRO W7900
Architecture
Ampere (2020−2022)
RDNA 3.0 (2022)
GPU code name
Ampere GA102
Navi 31
Market segment
Desktop
Workstation
Release date
September 2020
April 2023
Interface
PCIe 4.0 x16
PCIe 4.0 x16
Supplementary power connectors
1x 12-pin
2x 8-pin
Boost clock speed
1700 MHz
2495 MHz
Core clock speed
1400 MHz
-
Manufacturing process technology
8 nm
5 nm
Number of transistors
28,300 million
57,700 million
Pipelines / CUDA cores
10496
6144
Power consumption (TDP)
350 Watt
295 Watt
Texture fill rate
556.0
958.1
Memory type
GDDR6X
GDDR6
Maximum RAM amount
24 GB
48 GB
Memory bus width
384 Bit
384 Bit
Memory clock speed
19500 MHz
18 GB/s
Memory bandwidth
936.2 GB/s
864.0 GB/s
Shared memory
-
-
Display Connectors
1x HDMI, 3x DisplayPort
3x DisplayPort 2.1, 1x mini-DisplayPort 2.1
HDMI
+
-
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
CUDA
8.5
-
OpenCL
2.0
2.2
OpenGL
4.6
4.6
Shader Model
6.5
6.7
Vulkan
1.2
1.3