Radeon HD 3850 and GeForce GT 430 PCI - video card comparison
Radeon HD 3850
GeForce GT 430 PCI
Architecture
TeraScale (2005−2013)
Fermi (2010−2014)
GPU code name
RV670
GF108
Market segment
Desktop
Desktop
Release date
November 2007
October 2010
Interface
PCIe 2.0 x16
PCIe 2.0 x16
Supplementary power connectors
1x 6-pin
None
Core clock speed
668 MHz
700 MHz
Floating-point performance
427.5 gflops
-
Manufacturing process technology
55 nm
40 nm
Number of transistors
666 million
585 million
Pipelines / CUDA cores
320
96
Power consumption (TDP)
75 Watt
49 Watt
Texture fill rate
10.69
11.20
Memory type
GDDR3
DDR3
Maximum RAM amount
1 GB
512 MB
Memory bus width
256 Bit
64 Bit
Memory clock speed
1660 MHz
1200 MHz
Memory bandwidth
53.12 GB/s
9.6 GB/s
Display Connectors
2x DVI, 1x S-Video
1x DVI, 1x HDMI, 1x VGA
HDMI
-
+
DirectX
10.1 (10_1)
12 (11_0)
CUDA
-
2.1
OpenCL
N/A
1.1
OpenGL
3.3
4.6
Shader Model
4.1
5.1
Vulkan
N/A
N/A