NVIDIA Tesla P100 SXM2 vs AMD Radeon R9 390 X2

Comparative analysis of NVIDIA Tesla P100 SXM2 and AMD Radeon R9 390 X2 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 - T-Rex (Frames/s).

NVIDIA Tesla P100 SXM2

AMD Radeon R9 390 X2

Differences

Reasons to consider the NVIDIA Tesla P100 SXM2

Videocard is newer: launch date 7 month(s) later
Around 33% higher core clock speed: 1328 MHz vs 1000 MHz
Around 4% better floating-point performance: 10,609 gflops vs 2x 5,120 gflops
A newer manufacturing process allows for a more powerful, yet cooler running videocard: 16 nm vs 28 nm
Around 93% lower typical power consumption: 300 Watt vs 580 Watt

Launch date	5 April 2016 vs 3 September 2015
Core clock speed	1328 MHz vs 1000 MHz
Floating-point performance	10,609 gflops vs 2x 5,120 gflops
Manufacturing process technology	16 nm vs 28 nm
Thermal Design Power (TDP)	300 Watt vs 580 Watt

Reasons to consider the AMD Radeon R9 390 X2

6.5x more texture fill rate: 2x 160.0 GTexel / s billion / sec vs 331.5 GTexel / s
Around 43% higher pipelines: 2x 2560 vs 3584
3.8x more memory clock speed: 5400 MHz vs 1408 MHz

Texture fill rate	2x 160.0 GTexel / s billion / sec vs 331.5 GTexel / s
Pipelines	2x 2560 vs 3584
Memory clock speed	5400 MHz vs 1408 MHz

Compare benchmarks

GPU 1: NVIDIA Tesla P100 SXM2
GPU 2: AMD Radeon R9 390 X2

Name	NVIDIA Tesla P100 SXM2	AMD Radeon R9 390 X2
Geekbench - OpenCL	76222
CompuBench 1.5 Desktop - T-Rex (Frames/s)		21.128

Compare specifications (specs)

	NVIDIA Tesla P100 SXM2	AMD Radeon R9 390 X2
Essentials
Architecture	Pascal	GCN 2.0
Code name	GP100	Grenada
Launch date	5 April 2016	3 September 2015
Place in performance rating	255	257
Type	Desktop	Desktop
Launch price (MSRP)		$1,399
Technical info
Boost clock speed	1480 MHz
Core clock speed	1328 MHz	1000 MHz
Floating-point performance	10,609 gflops	2x 5,120 gflops
Manufacturing process technology	16 nm	28 nm
Pipelines	3584	2x 2560
Texture fill rate	331.5 GTexel / s	2x 160.0 GTexel / s billion / sec
Thermal Design Power (TDP)	300 Watt	580 Watt
Transistor count	15,300 million	6,200 million
Video outputs and ports
Display Connectors	No outputs	2x DVI, 1x HDMI, 1x DisplayPort
Compatibility, dimensions and requirements
Interface	PCIe 3.0 x16	PCIe 3.0 x16
Supplementary power connectors	None	4x 8-pin
API support
DirectX	12.0 (12_1)	12.0 (12_0)
OpenGL	4.6	4.5
Memory
Maximum RAM amount	16 GB	2x 8 GB
Memory bandwidth	720.9 GB / s	2x 345.6 GB / s
Memory bus width	4096 Bit	2x 512 Bit
Memory clock speed	1408 MHz	5400 MHz
Memory type	HBM2	GDDR5