GeForce GTX 680 and Tesla P40 - video card comparison
Passmark - benchmark score GeForce GTX 680 vs Tesla P40
GeForce GTX 680
5721
Tesla P40
12873
GeForce GTX 680
Tesla P40
Architecture
Kepler (2012−2018)
Pascal (2016−2021)
GPU code name
GK104
GP102
Market segment
Desktop
Workstation
Release date
March 2012
September 2016
Bus support
PCI Express 3.0
-
Interface
PCIe 3.0 x16
PCIe 3.0 x16
Supplementary power connectors
Two 6-pin
8-pin EPS
SLI options
+
-
Boost clock speed
1058 MHz
1531 MHz
Core clock speed
1006 MHz
1303 MHz
CUDA cores
1536
-
Floating-point performance
3,090.4 gflops
11,758 gflops
Manufacturing process technology
28 nm
16 nm
Number of transistors
3,540 million
11,800 million
Pipelines / CUDA cores
1536
3840
Power consumption (TDP)
195 Watt
250 Watt
Texture fill rate
128.8 billion/sec
367.4
Memory type
GDDR5
GDDR5
Maximum RAM amount
2048 MB
24 GB
Memory bus width
256-bit GDDR5
384 Bit
Memory clock speed
6000 MHz
7.2 GB/s
Memory bandwidth
192.2 GB/s
347.1 GB/s
Shared memory
-
-
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 (12_1)
CUDA
+
6.1
OpenCL
1.2
3.0
OpenGL
4.2
4.6
Shader Model
5.1
6.7
Vulkan
1.1.126
1.3