GeForce GTX 650 Ti and Radeon HD 3850 - video card comparison
Passmark - benchmark score GeForce GTX 650 Ti vs Radeon HD 3850
GeForce GTX 650 Ti
2598
Radeon HD 3850
404
GeForce GTX 650 Ti
Radeon HD 3850
Architecture
Kepler (2012−2018)
TeraScale (2005−2013)
GPU code name
GK106
RV670
Market segment
Desktop
Desktop
Release date
October 2012
November 2007
Bus support
PCI Express 3.0
-
Interface
PCIe 3.0 x16
PCIe 2.0 x16
Supplementary power connectors
One 6-pin
1x 6-pin
Core clock speed
928 MHz
668 MHz
CUDA cores
768
-
Floating-point performance
1,425 gflops
427.5 gflops
Manufacturing process technology
28 nm
55 nm
Number of transistors
2,540 million
666 million
Pipelines / CUDA cores
768
320
Power consumption (TDP)
110 Watt
75 Watt
Maximum GPU temperature
105 °C
-
Texture fill rate
59.2 billion/sec
10.69
Memory type
GDDR5
GDDR3
Maximum RAM amount
2 GB
1 GB
Memory bus width
128 Bit
256 Bit
Memory clock speed
5.4 GB/s
1660 MHz
Memory bandwidth
86.4 GB/s
53.12 GB/s
Display Connectors
One Dual Link DVI-I, One Dual Link DVI-D, One Mini HDMI
2x DVI, 1x S-Video
Multi monitor support
4 Displays
-
HDMI
+
-
HDCP
+
-
Maximum VGA resolution
2048x1536
-
Audio input for HDMI
Internal
-
DirectX
12 (11_0)
10.1 (10_1)
CUDA
+
-
OpenCL
1.2
N/A
OpenGL
4.3
3.3
Shader Model
5.1
4.1
Vulkan
1.1.126
N/A
3D Blu-Ray
+
-
3D Gaming
+
-
3D Vision
+
-