AMD Radeon Pro Vega 16 vs NVIDIA Tesla K20m

Comparative analysis of AMD Radeon Pro Vega 16 and NVIDIA Tesla K20m 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: GFXBench 4.0 - Car Chase Offscreen (Frames), GFXBench 4.0 - Car Chase Offscreen (Fps), GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - T-Rex (Fps), Geekbench - OpenCL, PassMark - G2D Mark, PassMark - G3D Mark, 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).

AMD Radeon Pro Vega 16

NVIDIA Tesla K20m

Differences

Reasons to consider the AMD Radeon Pro Vega 16

Videocard is newer: launch date 5 year(s) 10 month(s) later
A newer manufacturing process allows for a more powerful, yet cooler running videocard: 14 nm vs 28 nm
3x lower typical power consumption: 75 Watt vs 225 Watt
Around 7% better performance in GFXBench 4.0 - Car Chase Offscreen (Frames): 8870 vs 8319
Around 7% better performance in GFXBench 4.0 - Car Chase Offscreen (Fps): 8870 vs 8319
Around 55% better performance in Geekbench - OpenCL: 22421 vs 14510
2.8x better performance in PassMark - G2D Mark: 585 vs 210
Around 9% better performance in PassMark - G3D Mark: 4809 vs 4432

Specifications (specs)
Launch date	14 November 2018 vs 5 January 2013
Manufacturing process technology	14 nm vs 28 nm
Thermal Design Power (TDP)	75 Watt vs 225 Watt
Benchmarks
GFXBench 4.0 - Car Chase Offscreen (Frames)	8870 vs 8319
GFXBench 4.0 - Car Chase Offscreen (Fps)	8870 vs 8319
Geekbench - OpenCL	22421 vs 14510
PassMark - G2D Mark	585 vs 210
PassMark - G3D Mark	4809 vs 4432

Reasons to consider the NVIDIA Tesla K20m

2.4x more core clock speed: 706 MHz vs 300 MHz
2.2x more memory clock speed: 5200 MHz vs 2400 MHz
2x better performance in GFXBench 4.0 - Manhattan (Frames): 7337 vs 3586
2x better performance in GFXBench 4.0 - Manhattan (Fps): 7337 vs 3586
3.2x better performance in GFXBench 4.0 - T-Rex (Frames): 10873 vs 3359
3.2x better performance in GFXBench 4.0 - T-Rex (Fps): 10873 vs 3359

Specifications (specs)
Core clock speed	706 MHz vs 300 MHz
Memory clock speed	5200 MHz vs 2400 MHz
Benchmarks
GFXBench 4.0 - Manhattan (Frames)	7337 vs 3586
GFXBench 4.0 - Manhattan (Fps)	7337 vs 3586
GFXBench 4.0 - T-Rex (Frames)	10873 vs 3359
GFXBench 4.0 - T-Rex (Fps)	10873 vs 3359

Compare benchmarks

GPU 1: AMD Radeon Pro Vega 16
GPU 2: NVIDIA Tesla K20m

GFXBench 4.0 - Car Chase Offscreen (Frames)

GPU 1

GPU 2

8870

8319

GFXBench 4.0 - Car Chase Offscreen (Fps)

GPU 1

GPU 2

8870

8319

GFXBench 4.0 - Manhattan (Frames)

GPU 1

GPU 2

3586

7337

GFXBench 4.0 - Manhattan (Fps)

GPU 1

GPU 2

3586

7337

GFXBench 4.0 - T-Rex (Frames)

GPU 1

GPU 2

3359

10873

GFXBench 4.0 - T-Rex (Fps)

GPU 1

GPU 2

3359

10873

Geekbench - OpenCL

GPU 1

GPU 2

22421

14510

PassMark - G2D Mark

GPU 1

GPU 2

585

210

PassMark - G3D Mark

GPU 1

GPU 2

4809

4432

Name	AMD Radeon Pro Vega 16	NVIDIA Tesla K20m
GFXBench 4.0 - Car Chase Offscreen (Frames)	8870	8319
GFXBench 4.0 - Car Chase Offscreen (Fps)	8870	8319
GFXBench 4.0 - Manhattan (Frames)	3586	7337
GFXBench 4.0 - Manhattan (Fps)	3586	7337
GFXBench 4.0 - T-Rex (Frames)	3359	10873
GFXBench 4.0 - T-Rex (Fps)	3359	10873
Geekbench - OpenCL	22421	14510
PassMark - G2D Mark	585	210
PassMark - G3D Mark	4809	4432
CompuBench 1.5 Desktop - Face Detection (mPixels/s)		54.89
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)		1414.755
CompuBench 1.5 Desktop - T-Rex (Frames/s)		5.303
CompuBench 1.5 Desktop - Video Composition (Frames/s)		83.807
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)		250.291

Compare specifications (specs)

	AMD Radeon Pro Vega 16	NVIDIA Tesla K20m
Essentials
Architecture	GCN 5.0	Kepler
Code name	Vega 12	GK110
Launch date	14 November 2018	5 January 2013
Place in performance rating	360	408
Type	Workstation	Workstation
Launch price (MSRP)		$3,199
Technical info
Boost clock speed	1190 MHz
Core clock speed	300 MHz	706 MHz
Manufacturing process technology	14 nm	28 nm
Thermal Design Power (TDP)	75 Watt	225 Watt
Floating-point performance		3,524 gflops
Pipelines		2496
Texture fill rate		146.8 GTexel / s
Transistor count		7,080 million
Video outputs and ports
Display Connectors	No outputs	No outputs
Compatibility, dimensions and requirements
Interface	PCIe 3.0 x16	PCIe 2.0 x16
Length		267 mm
Supplementary power connectors		1x 6-pin + 1x 8-pin
API support
DirectX	12.0 (12_1)	12.0 (11_0)
OpenGL	4.6	4.6
Memory
Memory clock speed	2400 MHz	5200 MHz
Maximum RAM amount		5 GB
Memory bandwidth		208.0 GB / s
Memory bus width		320 Bit
Memory type		GDDR5