GeForce GTX 780 and Tesla K80 - video card comparison
Passmark - benchmark score GeForce GTX 780 vs Tesla K80
GeForce GTX 780
8247
Tesla K80
6028
GeForce GTX 780
Tesla K80
Architecture
Kepler (2012−2018)
Kepler 2.0 (2013−2015)
GPU code name
GK110
GK210
Market segment
Desktop
Workstation
Release date
May 2013
November 2014
Bus support
PCI Express 3.0
-
Interface
PCIe 3.0 x16
PCIe 3.0 x16
Minimum recommended system power
600 Watt
-
Supplementary power connectors
One 8-pin and one 6-pin
1x 8-pin
Boost clock speed
900 MHz
824 MHz
Core clock speed
863 MHz
562 MHz
CUDA cores
2304
-
Floating-point performance
4,156 gflops
-
Manufacturing process technology
28 nm
28 nm
Number of transistors
7,080 million
7,100 million
Pipelines / CUDA cores
2304
2496
Power consumption (TDP)
250 Watt
300 Watt
Maximum GPU temperature
95 °C
-
Texture fill rate
160.5 billion/sec
171.4
Memory type
GDDR5
GDDR5
Maximum RAM amount
3 GB
12 GB
Memory bus width
384 Bit
384 Bit
Memory clock speed
6008 MHz
5012 MHz
Memory bandwidth
288.4 GB/s
240.6 GB/s
Display Connectors
One Dual Link DVI-I, One Dual Link DVI-D, One HDMI, One DisplayPort
No outputs
Multi monitor support
4 displays
-
HDMI
+
-
HDCP
+
-
Maximum VGA resolution
2048x1536
-
Audio input for HDMI
Internal
-
DirectX
12 (11_0)
12 (11_1)
CUDA
+
3.7
OpenCL
1.2
1.2
OpenGL
4.3
4.6
Shader Model
5.1
5.1
Vulkan
1.1.126
1.1.126
3D Gaming
+
-
3D Vision
+
-
3D Vision Live
+
-
Blu Ray 3D
+
-
PhysX
+
-