NVIDIA Tesla K80 vs NVIDIA Tesla P4

Comparative analysis of NVIDIA Tesla K80 and NVIDIA Tesla P4 videocards for all known characteristics in the following categories: Essentials, Technical info, Video outputs and ports, Compatibility, dimensions and requirements, API support, Memory. Benchmark videocards performance analysis: PassMark - G2D Mark, PassMark - G3D Mark, Geekbench - OpenCL, CompuBench 1.5 Desktop - Face Detection (mPixels/s), CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s), CompuBench 1.5 Desktop - T-Rex (Frames/s), CompuBench 1.5 Desktop - Video Composition (Frames/s), CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s), GFXBench 4.0 - Car Chase Offscreen (Frames), GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - Car Chase Offscreen (Fps), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Fps).

NVIDIA Tesla K80

NVIDIA Tesla P4

Differences

Reasons to consider the NVIDIA Tesla K80

1007.6x more texture fill rate: 171.4 GTexel/s vs 170.1 GTexel / s
Around 50% higher maximum memory size: 12 GB vs 8 GB

Texture fill rate	171.4 GTexel/s vs 170.1 GTexel / s
Maximum memory size	12 GB vs 8 GB

Reasons to consider the NVIDIA Tesla P4

Videocard is newer: launch date 1 year(s) 9 month(s) later
Around 44% higher core clock speed: 810 MHz vs 562 MHz
Around 29% higher boost clock speed: 1063 MHz vs 824 MHz
Around 3% higher pipelines: 2560 vs 2496
A newer manufacturing process allows for a more powerful, yet cooler running videocard: 16 nm vs 28 nm
4x lower typical power consumption: 75 Watt vs 300 Watt
4.8x more memory clock speed: 6008 MHz vs 1253 MHz, 5 Gbps effective
Around 40% better performance in PassMark - G2D Mark: 391 vs 280
Around 94% better performance in PassMark - G3D Mark: 9097 vs 4680

Specifications (specs)
Launch date	13 September 2016 vs 17 Nov 2014
Core clock speed	810 MHz vs 562 MHz
Boost clock speed	1063 MHz vs 824 MHz
Pipelines	2560 vs 2496
Manufacturing process technology	16 nm vs 28 nm
Thermal Design Power (TDP)	75 Watt vs 300 Watt
Memory clock speed	6008 MHz vs 1253 MHz, 5 Gbps effective
Benchmarks
PassMark - G2D Mark	391 vs 280
PassMark - G3D Mark	9097 vs 4680

Compare benchmarks

GPU 1: NVIDIA Tesla K80
GPU 2: NVIDIA Tesla P4

PassMark - G2D Mark

GPU 1

GPU 2

280

391

PassMark - G3D Mark

GPU 1

GPU 2

4680

9097

Name	NVIDIA Tesla K80	NVIDIA Tesla P4
PassMark - G2D Mark	280	391
PassMark - G3D Mark	4680	9097
Geekbench - OpenCL		37924
CompuBench 1.5 Desktop - Face Detection (mPixels/s)		147.62
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)		1791.761
CompuBench 1.5 Desktop - T-Rex (Frames/s)		9.457
CompuBench 1.5 Desktop - Video Composition (Frames/s)		99.574
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)		523.29
GFXBench 4.0 - Car Chase Offscreen (Frames)		11409
GFXBench 4.0 - Manhattan (Frames)		3698
GFXBench 4.0 - T-Rex (Frames)		3341
GFXBench 4.0 - Car Chase Offscreen (Fps)		11409
GFXBench 4.0 - Manhattan (Fps)		3698
GFXBench 4.0 - T-Rex (Fps)		3341

Compare specifications (specs)

	NVIDIA Tesla K80	NVIDIA Tesla P4
Essentials
Architecture	Kepler 2.0	Pascal
Code name	GK210	GP104
Launch date	17 Nov 2014	13 September 2016
Place in performance rating	374	349
Type		Workstation
Technical info
Boost clock speed	824 MHz	1063 MHz
Core clock speed	562 MHz	810 MHz
Manufacturing process technology	28 nm	16 nm
Peak Double Precision (FP64) Performance	1,371 GFLOPS (1:3)
Peak Single Precision (FP32) Performance	4.113 TFLOPS
Pipelines	2496	2560
Pixel fill rate	42.85 GPixel/s
Texture fill rate	171.4 GTexel/s	170.1 GTexel / s
Thermal Design Power (TDP)	300 Watt	75 Watt
Transistor count	7100 million	7,200 million
Floating-point performance		5,443 gflops
Video outputs and ports
Display Connectors	No outputs	No outputs
Compatibility, dimensions and requirements
Form factor	Dual-slot
Interface	PCIe 3.0 x16	PCIe 3.0 x16
Length	267 mm, 10.5 inches	267 mm
Recommended system power (PSU)	700 Watt
Supplementary power connectors	1x 8-pin	None
API support
DirectX	12 (11_1)	12.0 (12_1)
OpenCL	3.0
OpenGL	4.6	4.6
Shader Model	6.5 (5.1)
Vulkan
Memory
Maximum RAM amount	12 GB	8 GB
Memory bandwidth	240.6 GB/s	192.3 GB / s
Memory bus width	384 bit	256 Bit
Memory clock speed	1253 MHz, 5 Gbps effective	6008 MHz
Memory type	GDDR5	GDDR5