NVIDIA Tesla K80m vs NVIDIA Tesla K20Xm

Comparative analysis of NVIDIA Tesla K80m and NVIDIA Tesla K20Xm 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: Geekbench - OpenCL, CompuBench 1.5 Desktop - Face Detection (mPixels/s), CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s), CompuBench 1.5 Desktop - Video Composition (Frames/s), CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s), CompuBench 1.5 Desktop - T-Rex (Frames/s), PassMark - G3D Mark, PassMark - G2D Mark, GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Fps).

NVIDIA Tesla K80m

NVIDIA Tesla K20Xm

Differences

Reasons to consider the NVIDIA Tesla K80m

Videocard is newer: launch date 2 year(s) 0 month(s) later
13.3x more texture fill rate: 2x 182.2 GTexel / s billion / sec vs 164.0 GTexel / s
Around 86% higher pipelines: 2x 2496 vs 2688
2.2x better floating-point performance: 2x 4,373 gflops vs 3,935 gflops
4x more maximum memory size: 2x 12 GB vs 6 GB
Around 11% better performance in Geekbench - OpenCL: 18416 vs 16664
Around 27% better performance in CompuBench 1.5 Desktop - Face Detection (mPixels/s): 62.651 vs 49.455
Around 18% better performance in CompuBench 1.5 Desktop - T-Rex (Frames/s): 6.882 vs 5.836

Specifications (specs)
Launch date	17 November 2014 vs 12 November 2012
Texture fill rate	2x 182.2 GTexel / s billion / sec vs 164.0 GTexel / s
Pipelines	2x 2496 vs 2688
Floating-point performance	2x 4,373 gflops vs 3,935 gflops
Maximum memory size	2x 12 GB vs 6 GB
Benchmarks
Geekbench - OpenCL	18416 vs 16664
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	62.651 vs 49.455
CompuBench 1.5 Desktop - T-Rex (Frames/s)	6.882 vs 5.836

Reasons to consider the NVIDIA Tesla K20Xm

Around 30% higher core clock speed: 732 MHz vs 562 MHz
Around 28% lower typical power consumption: 235 Watt vs 300 Watt
Around 4% higher memory clock speed: 5200 MHz vs 5012 MHz
Around 1% better performance in CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s): 1666.354 vs 1653.567
Around 6% better performance in CompuBench 1.5 Desktop - Video Composition (Frames/s): 92.472 vs 86.984
Around 7% better performance in CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 275.229 vs 258.278

Specifications (specs)
Core clock speed	732 MHz vs 562 MHz
Thermal Design Power (TDP)	235 Watt vs 300 Watt
Memory clock speed	5200 MHz vs 5012 MHz
Benchmarks
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	1666.354 vs 1653.567
CompuBench 1.5 Desktop - Video Composition (Frames/s)	92.472 vs 86.984
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	275.229 vs 258.278

Compare benchmarks

GPU 1: NVIDIA Tesla K80m
GPU 2: NVIDIA Tesla K20Xm

Geekbench - OpenCL

GPU 1

GPU 2

18416

16664

CompuBench 1.5 Desktop - Face Detection (mPixels/s)

GPU 1

GPU 2

62.651

49.455

CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)

GPU 1

GPU 2

1653.567

1666.354

CompuBench 1.5 Desktop - Video Composition (Frames/s)

GPU 1

GPU 2

86.984

92.472

CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)

GPU 1

GPU 2

258.278

275.229

CompuBench 1.5 Desktop - T-Rex (Frames/s)

GPU 1

GPU 2

6.882

5.836

Name	NVIDIA Tesla K80m	NVIDIA Tesla K20Xm
Geekbench - OpenCL	18416	16664
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	62.651	49.455
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	1653.567	1666.354
CompuBench 1.5 Desktop - Video Composition (Frames/s)	86.984	92.472
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	258.278	275.229
CompuBench 1.5 Desktop - T-Rex (Frames/s)	6.882	5.836
PassMark - G3D Mark		4403
PassMark - G2D Mark		198
GFXBench 4.0 - Manhattan (Frames)		1032
GFXBench 4.0 - T-Rex (Frames)		7038
GFXBench 4.0 - Manhattan (Fps)		1032
GFXBench 4.0 - T-Rex (Fps)		7038

Compare specifications (specs)

	NVIDIA Tesla K80m	NVIDIA Tesla K20Xm
Essentials
Architecture	Kepler 2.0	Kepler
Code name	GK210	GK110
Launch date	17 November 2014	12 November 2012
Place in performance rating	733	746
Type	Workstation	Workstation
Launch price (MSRP)		$7,699
Technical info
Boost clock speed	876 MHz
Core clock speed	562 MHz	732 MHz
Floating-point performance	2x 4,373 gflops	3,935 gflops
Manufacturing process technology	28 nm	28 nm
Pipelines	2x 2496	2688
Texture fill rate	2x 182.2 GTexel / s billion / sec	164.0 GTexel / s
Thermal Design Power (TDP)	300 Watt	235 Watt
Transistor count	7,080 million	7,080 million
Video outputs and ports
Display Connectors	No outputs	No outputs
Compatibility, dimensions and requirements
Interface	PCIe 3.0 x16	PCIe 3.0 x16
Length	267 mm	267 mm
Supplementary power connectors	1x 8-pin
API support
DirectX	12.0 (11_1)	12.0 (11_0)
OpenGL	4.6	4.6
Memory
Maximum RAM amount	2x 12 GB	6 GB
Memory bandwidth	2x 240.6 GB / s	249.6 GB / s
Memory bus width	2x 384 Bit	384 Bit
Memory clock speed	5012 MHz	5200 MHz
Memory type	GDDR5	GDDR5