Radeon RX 580 and GeForce GTX 680 - video card comparison
Passmark - benchmark score Radeon RX 580 vs GeForce GTX 680
Radeon RX 580
9140
GeForce GTX 680
5721
Radeon RX 580
GeForce GTX 680
Architecture
Polaris (2016−2019)
Kepler (2012−2018)
GPU code name
Polaris 20
GK104
Market segment
Desktop
Desktop
Release date
April 2017
March 2012
Bus support
-
PCI Express 3.0
Interface
PCIe 3.0 x16
PCIe 3.0 x16
Supplementary power connectors
1x 8-pin
Two 6-pin
SLI options
-
+
Boost clock speed
1340 MHz
1058 MHz
Core clock speed
1257 MHz
1006 MHz
CUDA cores
-
1536
Floating-point performance
6,175 gflops
3,090.4 gflops
Manufacturing process technology
14 nm
28 nm
Number of transistors
5,700 million
3,540 million
Pipelines / CUDA cores
2304
1536
Power consumption (TDP)
185 Watt
195 Watt
Texture fill rate
193.0
128.8 billion/sec
Memory type
GDDR5
GDDR5
Maximum RAM amount
8 GB
2048 MB
Memory bus width
256 Bit
256-bit GDDR5
Memory clock speed
8000 MHz
6000 MHz
Memory bandwidth
256.0 GB/s
192.2 GB/s
Shared memory
-
-
Display Connectors
1x HDMI, 3x DisplayPort
One Dual Link DVI-I, One Dual Link DVI-D, One HDMI, One DisplayPort
Multi monitor support
-
4 displays
HDMI
+
+
HDCP
-
+
Maximum VGA resolution
-
2048x1536
Audio input for HDMI
-
Internal
DirectX
12 (12_0)
12 (11_0)
CUDA
-
+
OpenCL
2.0
1.2
OpenGL
4.6
4.2
Shader Model
6.4
5.1
Vulkan
1.2.131
1.1.126