GeForce GTX 580 and Radeon HD 8670D - video card comparison
Passmark - benchmark score GeForce GTX 580 vs Radeon HD 8670D
GeForce GTX 580
4702
Radeon HD 8670D
545
GeForce GTX 580
Radeon HD 8670D
Architecture
Fermi (2010−2014)
Terascale 3 (2010−2013)
GPU code name
GF110
Richland
Market segment
Desktop
Desktop
Release date
November 2010
June 2013
Bus support
PCI-E 2.0 x 16
-
Interface
PCIe 2.0 x16
IGP
Supplementary power connectors
One 6-pin and One 8-pin
-
SLI options
+
-
Boost clock speed
-
950 MHz
Core clock speed
772 MHz
844 MHz
CUDA cores
512
-
Floating-point performance
1,581.1 gflops
-
Manufacturing process technology
40 nm
32 nm
Number of transistors
3,000 million
1,303 million
Pipelines / CUDA cores
512
384
Power consumption (TDP)
244 Watt
100 Watt
Maximum GPU temperature
97 °C
-
Texture fill rate
49.4 billion/sec
22.80
Memory type
GDDR5
System Shared
Maximum RAM amount
1536 MB
System Shared
Memory bus width
384 Bit
System Shared
Memory clock speed
2004 MHz (4008 data rate)
System Shared
Memory bandwidth
192.4 GB/s
-
Shared memory
-
+
Display Connectors
Mini HDMITwo Dual Link DVI
No outputs
Multi monitor support
+
-
HDMI
+
-
Maximum VGA resolution
2048x1536
-
Audio input for HDMI
Internal
-
DirectX
12 (11_0)
11.2 (11_0)
CUDA
+
-
OpenCL
1.1
1.2
OpenGL
4.2
4.4
Shader Model
5.1
5.0
Vulkan
+
N/A