NVIDIA Tesla V100 SMX2 vs NVIDIA P106-100

Comparative analysis of NVIDIA Tesla V100 SMX2 and NVIDIA P106-100 videocards for all known characteristics in the following categories: Essentials, Technical info, Compatibility, dimensions and requirements, Memory, Technologies, Video outputs and ports, API support. Benchmark videocards performance analysis: PassMark - G3D Mark, PassMark - G2D Mark, Geekbench - OpenCL, 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), GFXBench 4.0 - Car Chase Offscreen (Frames), GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - Car Chase Offscreen (Fps), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Fps), 3DMark Fire Strike - Graphics Score.

NVIDIA Tesla V100 SMX2

NVIDIA P106-100

Differences

Reasons to consider the NVIDIA Tesla V100 SMX2

3.2x more texture fill rate: 438.4 GTexel / s vs 136.7 GTexel / s
4x more pipelines: 5120 vs 1280
3.2x better floating-point performance: 14,029 gflops vs 4,375 gflops
A newer manufacturing process allows for a more powerful, yet cooler running videocard: 12 nm vs 16 nm
2.7x more maximum memory size: 16 GB vs 6 GB

Texture fill rate	438.4 GTexel / s vs 136.7 GTexel / s
Pipelines	5120 vs 1280
Floating-point performance	14,029 gflops vs 4,375 gflops
Manufacturing process technology	12 nm vs 16 nm
Maximum memory size	16 GB vs 6 GB

Reasons to consider the NVIDIA P106-100

Around 10% higher core clock speed: 1506 MHz vs 1370 MHz
2.1x lower typical power consumption: 120 Watt vs 250 Watt
4.6x more memory clock speed: 8008 MHz vs 1758 MHz

Core clock speed	1506 MHz vs 1370 MHz
Thermal Design Power (TDP)	120 Watt vs 250 Watt
Memory clock speed	8008 MHz vs 1758 MHz

Compare benchmarks

GPU 1: NVIDIA Tesla V100 SMX2
GPU 2: NVIDIA P106-100

Name	NVIDIA Tesla V100 SMX2	NVIDIA P106-100
PassMark - G3D Mark		6443
PassMark - G2D Mark		245
Geekbench - OpenCL		36274
CompuBench 1.5 Desktop - Face Detection (mPixels/s)		163.993
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)		1705.321
CompuBench 1.5 Desktop - T-Rex (Frames/s)		9.266
CompuBench 1.5 Desktop - Video Composition (Frames/s)		76.32
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)		448.036
GFXBench 4.0 - Car Chase Offscreen (Frames)		12824
GFXBench 4.0 - Manhattan (Frames)		1860
GFXBench 4.0 - T-Rex (Frames)		1680
GFXBench 4.0 - Car Chase Offscreen (Fps)		12824
GFXBench 4.0 - Manhattan (Fps)		1860
GFXBench 4.0 - T-Rex (Fps)		1680
3DMark Fire Strike - Graphics Score		4072

Compare specifications (specs)

	NVIDIA Tesla V100 SMX2	NVIDIA P106-100
Essentials
Architecture	Volta	Pascal
Code name	GV100	GP106
Launch date	21 June 2017	19 June 2017
Place in performance rating	not rated	435
Type	Workstation	Desktop
Technical info
Core clock speed	1370 MHz	1506 MHz
Floating-point performance	14,029 gflops	4,375 gflops
Manufacturing process technology	12 nm	16 nm
Pipelines	5120	1280
Texture fill rate	438.4 GTexel / s	136.7 GTexel / s
Thermal Design Power (TDP)	250 Watt	120 Watt
Transistor count	21,100 million	4,400 million
Boost clock speed		1709 MHz
Compatibility, dimensions and requirements
Interface	PCIe 3.0 x16	PCIe 3.0 x16
Supplementary power connectors	None	1x 6-pin
Length		250 mm
Memory
Maximum RAM amount	16 GB	6 GB
Memory bandwidth	900.1 GB / s	192.2 GB / s
Memory bus width	4096 Bit	192 Bit
Memory clock speed	1758 MHz	8008 MHz
Memory type	HBM2	GDDR5
Technologies
CUDA
Video outputs and ports
Display Connectors		No outputs
API support
DirectX		12.0 (12_1)
OpenGL		4.6