NVIDIA Tesla K80m vs AMD Radeon HD 8970 OEM

Comparative analysis of NVIDIA Tesla K80m and AMD Radeon HD 8970 OEM 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), GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - T-Rex (Fps).

NVIDIA Tesla K80m

AMD Radeon HD 8970 OEM

Differences

Reasons to consider the NVIDIA Tesla K80m

Videocard is newer: launch date 1 year(s) 10 month(s) later
18.4x more texture fill rate: 2x 182.2 GTexel / s billion / sec vs 118.4 GTexel / s
2.4x more pipelines: 2x 2496 vs 2048
2.3x better floating-point performance: 2x 4,373 gflops vs 3,789 gflops
8x more maximum memory size: 2x 12 GB vs 3 GB

Launch date	17 November 2014 vs 8 January 2013
Texture fill rate	2x 182.2 GTexel / s billion / sec vs 118.4 GTexel / s
Pipelines	2x 2496 vs 2048
Floating-point performance	2x 4,373 gflops vs 3,789 gflops
Maximum memory size	2x 12 GB vs 3 GB

Reasons to consider the AMD Radeon HD 8970 OEM

Around 65% higher core clock speed: 925 MHz vs 562 MHz
Around 20% lower typical power consumption: 250 Watt vs 300 Watt
Around 10% higher memory clock speed: 5500 MHz vs 5012 MHz

Core clock speed	925 MHz vs 562 MHz
Thermal Design Power (TDP)	250 Watt vs 300 Watt
Memory clock speed	5500 MHz vs 5012 MHz

Compare benchmarks

GPU 1: NVIDIA Tesla K80m
GPU 2: AMD Radeon HD 8970 OEM

Name	NVIDIA Tesla K80m	AMD Radeon HD 8970 OEM
Geekbench - OpenCL	18310
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	62.651
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	1653.567
CompuBench 1.5 Desktop - Video Composition (Frames/s)	86.984
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	258.278
CompuBench 1.5 Desktop - T-Rex (Frames/s)	6.882
GFXBench 4.0 - Manhattan (Frames)		3583
GFXBench 4.0 - Manhattan (Fps)		3583
GFXBench 4.0 - T-Rex (Frames)		3339
GFXBench 4.0 - T-Rex (Fps)		3339

Compare specifications (specs)

	NVIDIA Tesla K80m	AMD Radeon HD 8970 OEM
Essentials
Architecture	Kepler 2.0	GCN 1.0
Code name	GK210	Tahiti
Launch date	17 November 2014	8 January 2013
Place in performance rating	754	756
Type	Workstation	Desktop
Technical info
Boost clock speed	876 MHz
Core clock speed	562 MHz	925 MHz
Floating-point performance	2x 4,373 gflops	3,789 gflops
Manufacturing process technology	28 nm	28 nm
Pipelines	2x 2496	2048
Texture fill rate	2x 182.2 GTexel / s billion / sec	118.4 GTexel / s
Thermal Design Power (TDP)	300 Watt	250 Watt
Transistor count	7,080 million	4,313 million
Video outputs and ports
Display Connectors	No outputs	1x DVI, 1x HDMI, 2x mini-DisplayPort
Compatibility, dimensions and requirements
Interface	PCIe 3.0 x16	PCIe 3.0 x16
Length	267 mm	274 mm
Supplementary power connectors	1x 8-pin	1x 6-pin + 1x 8-pin
API support
DirectX	12.0 (11_1)	12.0
OpenGL	4.6	4.5
Memory
Maximum RAM amount	2x 12 GB	3 GB
Memory bandwidth	2x 240.6 GB / s	264.0 GB / s
Memory bus width	2x 384 Bit	384 Bit
Memory clock speed	5012 MHz	5500 MHz
Memory type	GDDR5	GDDR5