Radeon HD 8670D and GeForce 210 PCI - video card comparison
Radeon HD 8670D
GeForce 210 PCI
Architecture
Terascale 3 (2010−2013)
Tesla 2.0 (2007−2013)
GPU code name
Richland
GT216
Market segment
Desktop
Desktop
Release date
June 2013
October 2009
Interface
IGP
PCI
Supplementary power connectors
-
None
Boost clock speed
950 MHz
-
Core clock speed
844 MHz
475 MHz
Floating-point performance
-
35.2 gflops
Manufacturing process technology
32 nm
40 nm
Number of transistors
1,303 million
486 million
Pipelines / CUDA cores
384
16
Power consumption (TDP)
100 Watt
31 Watt
Texture fill rate
22.80
3.800
Memory type
System Shared
DDR2
Maximum RAM amount
System Shared
512 MB
Memory bus width
System Shared
64 Bit
Memory clock speed
System Shared
800 MHz
Memory bandwidth
-
6.4 GB/s
Shared memory
+
-
Display Connectors
No outputs
No outputs
DirectX
11.2 (11_0)
11.1 (10_1)
CUDA
-
1.2
OpenCL
1.2
1.1
OpenGL
4.4
3.3
Shader Model
5.0
4.1
Vulkan
N/A
N/A