Radeon HD 6670 and GeForce 840A - video card comparison
Passmark - benchmark score Radeon HD 6670 vs GeForce 840A
Radeon HD 6670
752
GeForce 840A
1214
Radeon HD 6670
GeForce 840A
Architecture
TeraScale 2 (2009−2015)
Maxwell (2014−2018)
GPU code name
Turks
GM108
Market segment
Desktop
Desktop
Release date
April 2011
March 2014
Bus support
PCIe 2.0 x16
-
Interface
PCIe 2.0 x16
PCIe 3.0 x8
Supplementary power connectors
None
-
Boost clock speed
800 MHz
1124 MHz
Core clock speed
-
1029 MHz
Floating-point performance
768.0 gflops
863.2 gflops
Manufacturing process technology
40 nm
28 nm
Number of transistors
716 million
-
Pipelines / CUDA cores
480
384
Power consumption (TDP)
66 Watt
33 Watt
Texture fill rate
19.20
17.98
Memory type
GDDR5
DDR3
Maximum RAM amount
1 GB
2 GB
Memory bus width
128 Bit
64 Bit
Memory clock speed
1050 MHz
2002 MHz
Memory bandwidth
64 GB/s
16.02 GB/s
Display Connectors
1x DVI, 1x HDMI, 1x VGA
No outputs
Eyefinity
1
-
HDMI
+
-
DisplayPort support
-
-
DirectX
DirectX® 11
12 (11_0)
CUDA
-
5.0
Mantle
-
-
OpenCL
1.2
1.2
OpenGL
4.4
4.6
Shader Model
5.0
5.1
Vulkan
-
1.1.126
AppAcceleration
-
-
CrossFire
1
-
Enduro
-
-
HD3D
-
-
PowerTune
-
-
TrueAudio
-
-
ZeroCore
-
-