Radeon R5 Graphics and GeForce RTX 4070 - video card comparison
Radeon R5 Graphics
GeForce RTX 4070
Architecture
GCN 2.0 (2013−2017)
Ada Lovelace
GPU code name
Spectre SL
AD104
Market segment
Desktop
Desktop
Release date
September 2014
April 2023
Interface
IGP
PCIe 4.0 x16
Supplementary power connectors
-
1x 16-pin
Boost clock speed
720 MHz
2475 MHz
Core clock speed
497 MHz
1920 MHz
Floating-point performance
388.1 gflops
-
Manufacturing process technology
28 nm
5 nm
Number of transistors
2,410 million
35,800 million
Pipelines / CUDA cores
256
5888
Power consumption (TDP)
15 Watt
200 Watt
Texture fill rate
7.952
455.4
Memory type
System Shared
GDDR6X
Maximum RAM amount
System Shared
12 GB
Memory bus width
System Shared
192 Bit
Memory clock speed
System Shared
21000 MHz
Memory bandwidth
-
504.2 GB/s
Shared memory
-
-
Display Connectors
No outputs
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
6.0
6.7
Vulkan
1.2.131
1.3