
Radeon Pro Duo Polaris and GeForce RTX 4070 - video card comparison
Radeon Pro Duo Polaris
GeForce RTX 4070
Architecture
GCN 4.0 (2016−2020)
Ada Lovelace
GPU code name
Ellesmere
AD104
Market segment
Workstation
Desktop
Release date
April 2017
April 2023
Interface
PCIe 3.0 x16
PCIe 4.0 x16
Supplementary power connectors
1x 6-pin + 1x 8-pin
1x 16-pin
Boost clock speed
-
2475 MHz
Core clock speed
1243 MHz
1920 MHz
Floating-point performance
2x 5,728 gflops
-
Manufacturing process technology
14 nm
5 nm
Number of transistors
5,700 million
35,800 million
Pipelines / CUDA cores
2304
5888
Power consumption (TDP)
250 Watt
200 Watt
Texture fill rate
179.0
455.4
Memory type
GDDR5
GDDR6X
Maximum RAM amount
16 GB
12 GB
Memory bus width
256 Bit
192 Bit
Memory clock speed
7000 MHz
21000 MHz
Memory bandwidth
224.0 GB/s
504.2 GB/s
Shared memory
-
-
Display Connectors
1x HDMI, 3x DisplayPort
1x HDMI 2.1, 3x DisplayPort 1.4a
HDMI
+
+
DirectX
12 (12_0)
12 Ultimate (12_2)
CUDA
-
8.9
OpenCL
2.0
3.0
OpenGL
4.6
4.6
Shader Model
6.4
6.7
Vulkan
1.2.131
1.3