Radeon HD 5870 and GeForce GT 620 - video card comparison
Passmark - benchmark score Radeon HD 5870 vs GeForce GT 620
Radeon HD 5870
2282
GeForce GT 620
388
Radeon HD 5870
GeForce GT 620
Architecture
TeraScale 2 (2009−2015)
Fermi (2010−2014)
GPU code name
Cypress
GF108
Market segment
Desktop
Desktop
Release date
September 2009
May 2012
Bus support
-
PCI Express 2.0
Interface
PCIe 2.0 x16
PCIe 2.0 x16
Supplementary power connectors
2x 6-pin
None
Core clock speed
850 MHz
700 MHz
CUDA cores
-
96
Floating-point performance
2,720.0 gflops
268.8 gflops
Manufacturing process technology
40 nm
40 nm
Number of transistors
2,154 million
585 million
Pipelines / CUDA cores
1600
96
Power consumption (TDP)
188 Watt
49 Watt
Maximum GPU temperature
-
98 °C
Texture fill rate
68.00
11.2 billion/sec
Memory type
GDDR5
DDR3
Maximum RAM amount
1 GB
1 GB
Memory bus width
256 Bit
64 Bit
Memory clock speed
4800 MHz
1.8 GB/s
Memory bandwidth
153.6 GB/s
14.4 GB/s
Display Connectors
2x DVI, 1x HDMI, 1x DisplayPort
Dual Link DVI-I, HDMI, VGA
Multi monitor support
-
+
HDMI
+
+
HDCP
-
+
Maximum VGA resolution
-
2048x1536
Audio input for HDMI
-
Internal
DirectX
11.2 (11_0)
12 (11_0)
CUDA
-
+
OpenCL
1.2
1.1
OpenGL
4.4
4.2
Shader Model
5.0
5.1
Vulkan
N/A
N/A
3D Blu-Ray
-
+