AMD Radeon E8950 vs NVIDIA Tesla K80m

Comparative analysis of AMD Radeon E8950 and NVIDIA Tesla K80m 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: 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), Geekbench - OpenCL.

AMD Radeon E8950

NVIDIA Tesla K80m

Differences

Reasons to consider the AMD Radeon E8950

Videocard is newer: launch date 10 month(s) later
Around 31% higher core clock speed: 735 MHz vs 562 MHz
Around 14% higher boost clock speed: 1000 MHz vs 876 MHz
3.2x lower typical power consumption: 95 Watt vs 300 Watt
Around 20% higher memory clock speed: 6000 MHz vs 5012 MHz
Around 7% better performance in CompuBench 1.5 Desktop - Face Detection (mPixels/s): 66.837 vs 62.651
Around 26% better performance in CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 326.391 vs 258.278

Specifications (specs)
Launch date	29 September 2015 vs 17 November 2014
Core clock speed	735 MHz vs 562 MHz
Boost clock speed	1000 MHz vs 876 MHz
Thermal Design Power (TDP)	95 Watt vs 300 Watt
Memory clock speed	6000 MHz vs 5012 MHz
Benchmarks
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	66.837 vs 62.651
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	326.391 vs 258.278

Reasons to consider the NVIDIA Tesla K80m

17x more texture fill rate: 2x 182.2 GTexel / s billion / sec vs 128.0 GTexel / s
2.4x more pipelines: 2x 2496 vs 2048
2.1x better floating-point performance: 2x 4,373 gflops vs 4,096 gflops
3x more maximum memory size: 2x 12 GB vs 8 GB
Around 21% better performance in CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s): 1653.567 vs 1369.722
Around 4% better performance in CompuBench 1.5 Desktop - T-Rex (Frames/s): 6.882 vs 6.633
Around 32% better performance in CompuBench 1.5 Desktop - Video Composition (Frames/s): 86.984 vs 65.836

Specifications (specs)
Texture fill rate	2x 182.2 GTexel / s billion / sec vs 128.0 GTexel / s
Pipelines	2x 2496 vs 2048
Floating-point performance	2x 4,373 gflops vs 4,096 gflops
Maximum memory size	2x 12 GB vs 8 GB
Benchmarks
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	1653.567 vs 1369.722
CompuBench 1.5 Desktop - T-Rex (Frames/s)	6.882 vs 6.633
CompuBench 1.5 Desktop - Video Composition (Frames/s)	86.984 vs 65.836

Compare benchmarks

GPU 1: AMD Radeon E8950
GPU 2: NVIDIA Tesla K80m

CompuBench 1.5 Desktop - Face Detection (mPixels/s)

GPU 1

GPU 2

66.837

62.651

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

GPU 1

GPU 2

1369.722

1653.567

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

GPU 1

GPU 2

6.633

6.882

CompuBench 1.5 Desktop - Video Composition (Frames/s)

GPU 1

GPU 2

65.836

86.984

CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)

GPU 1

GPU 2

326.391

258.278

Name	AMD Radeon E8950	NVIDIA Tesla K80m
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	66.837	62.651
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	1369.722	1653.567
CompuBench 1.5 Desktop - T-Rex (Frames/s)	6.633	6.882
CompuBench 1.5 Desktop - Video Composition (Frames/s)	65.836	86.984
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	326.391	258.278
Geekbench - OpenCL		18475

Compare specifications (specs)

	AMD Radeon E8950	NVIDIA Tesla K80m
Essentials
Architecture	GCN 3.0	Kepler 2.0
Code name	Amethyst	GK210
Launch date	29 September 2015	17 November 2014
Place in performance rating	724	725
Type	Desktop	Workstation
Technical info
Boost clock speed	1000 MHz	876 MHz
Core clock speed	735 MHz	562 MHz
Floating-point performance	4,096 gflops	2x 4,373 gflops
Manufacturing process technology	28 nm	28 nm
Pipelines	2048	2x 2496
Texture fill rate	128.0 GTexel / s	2x 182.2 GTexel / s billion / sec
Thermal Design Power (TDP)	95 Watt	300 Watt
Transistor count	5,000 million	7,080 million
Video outputs and ports
Display Connectors	No outputs	No outputs
Compatibility, dimensions and requirements
Interface	MXM-B (3.0)	PCIe 3.0 x16
Supplementary power connectors	None	1x 8-pin
Length		267 mm
API support
DirectX	12.0 (12_0)	12.0 (11_1)
OpenGL	4.5	4.6
Memory
Maximum RAM amount	8 GB	2x 12 GB
Memory bandwidth	192.0 GB / s	2x 240.6 GB / s
Memory bus width	256 Bit	2x 384 Bit
Memory clock speed	6000 MHz	5012 MHz
Memory type	GDDR5	GDDR5