Radeon HD 3850 and GeForce GT 430 - video card comparison
Passmark - benchmark score Radeon HD 3850 vs GeForce GT 430
Radeon HD 3850
404
GeForce GT 430
618
Radeon HD 3850
GeForce GT 430
Architecture
TeraScale (2005−2013)
Fermi (2010−2014)
GPU code name
RV670
GF108
Market segment
Desktop
Desktop
Release date
November 2007
October 2010
Bus support
-
PCI-E 2.0 x 16
Interface
PCIe 2.0 x16
PCIe 2.0 x16
Supplementary power connectors
1x 6-pin
None
Core clock speed
668 MHz
700 MHz
CUDA cores per GPU
-
96
Floating-point performance
427.5 gflops
268.8 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
Maximum GPU temperature
-
98 °C
Texture fill rate
10.69
11.2 billion/sec
Memory type
GDDR3
GDDR3
Maximum RAM amount
1 GB
1 GB
Memory bus width
256 Bit
128 Bit
Memory clock speed
1660 MHz
800 - 900 MHz (1600 - 1800 data rate)
Memory bandwidth
53.12 GB/s
25.6 - 28.8 GB/s
Display Connectors
2x DVI, 1x S-Video
HDMIVGA (optional)Mini HDMIDual Link DVI
HDMI
-
+
Maximum VGA resolution
-
2048x1536
Audio input for HDMI
-
Internal
DirectX
10.1 (10_1)
12 (11_0)
CUDA
-
+
OpenCL
N/A
1.1
OpenGL
3.3
4.2
Shader Model
4.1
5.1
Vulkan
N/A
N/A