Radeon HD 8670D and GeForce GT 610 PCI - video card comparison
Radeon HD 8670D
GeForce GT 610 PCI
Architecture
Terascale 3 (2010−2013)
Fermi 2.0 (2010−2014)
GPU code name
Richland
GF119
Market segment
Desktop
Desktop
Release date
June 2013
April 2012
Interface
IGP
PCI
Supplementary power connectors
-
None
Boost clock speed
950 MHz
-
Core clock speed
844 MHz
810 MHz
Floating-point performance
-
155.5 gflops
Manufacturing process technology
32 nm
40 nm
Number of transistors
1,303 million
292 million
Pipelines / CUDA cores
384
48
Power consumption (TDP)
100 Watt
29 Watt
Texture fill rate
22.80
6.480
Memory type
System Shared
DDR3
Maximum RAM amount
System Shared
512 MB
Memory bus width
System Shared
64 Bit
Memory clock speed
System Shared
1334 MHz
Memory bandwidth
-
10.67 GB/s
Shared memory
+
-
Display Connectors
No outputs
1x DVI, 1x HDMI, 1x VGA
HDMI
-
+
DirectX
11.2 (11_0)
12 (11_0)
CUDA
-
2.1
OpenCL
1.2
1.1
OpenGL
4.4
4.6
Shader Model
5.0
5.1
Vulkan
N/A
N/A