Radeon Pro Duo and GeForce RTX 4090 - video card comparison
Passmark - benchmark score Radeon Pro Duo vs GeForce RTX 4090
Radeon Pro Duo
8409
GeForce RTX 4090
39777
Radeon Pro Duo
GeForce RTX 4090
Architecture
GCN 3.0 (2014−2017)
Ada Lovelace
GPU code name
Capsaicin
AD102-300-A1
Market segment
Workstation
Desktop
Release date
April 2016
September 2022
Bus support
PCIe 3.0
-
Interface
PCIe 3.0 x16
PCIe 4.0 x16
Supplementary power connectors
3x 8-pin
1x 16-pin
Boost clock speed
1000 MHz
2520 MHz
Compute units
128
-
Core clock speed
-
2235 MHz
Floating-point performance
2x 8,192 gflops
-
Manufacturing process technology
28 nm
5 nm
Number of transistors
8,900 million
76,300 million
Pipelines / CUDA cores
4096
16384
Power consumption (TDP)
350 Watt
450 Watt
Texture fill rate
256.0
1,290
Memory type
High Bandwidth Memory (HBM)
GDDR6X
Maximum RAM amount
8 GB
24 GB
Memory bus width
4096 Bit
384 Bit
Memory clock speed
500 MHz
21000 MHz
Memory bandwidth
512 GB/s
1,008 GB/s
Shared memory
-
-
Display Connectors
1x HDMI, 3x DisplayPort
1x HDMI 2.1, 3x DisplayPort 1.4a
Eyefinity
1
-
Number of Eyefinity displays
6
-
HDMI
+
+
DisplayPort support
+
-
DirectX
DirectX® 12
12 Ultimate (12_2)
CUDA
-
8.9
Mantle
+
-
OpenCL
2.0
3.0
OpenGL
4.5
4.6
Shader Model
6.0
6.6
Vulkan
+
1.3
AppAcceleration
+
-
CrossFire
1
-
Enduro
+
-
FreeSync
1
-
FRTC
1
-
HD3D
+
-
LiquidVR
1
-
PowerTune
+
-
TressFX
1
-
TrueAudio
+
-
UVD
+
-
VCE
+
-
ZeroCore
+
-