NVIDIA Tesla V100 PCIe vs NVIDIA Tesla P40

Comparative analysis of NVIDIA Tesla V100 PCIe and NVIDIA Tesla P40 videocards for all known characteristics in the following categories: Essentials, Technical info, Video outputs and ports, Compatibility, dimensions and requirements, Memory, Technologies, 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).

NVIDIA Tesla V100 PCIe

NVIDIA Tesla P40

Differences

Reasons to consider the NVIDIA Tesla V100 PCIe

Videocard is newer: launch date 9 month(s) later
Around 20% higher texture fill rate: 441.6 GTexel / s vs 367.4 GTexel / s
Around 33% higher pipelines: 5120 vs 3840
Around 20% better floating-point performance: 14,131 gflops vs 11,758 gflops
A newer manufacturing process allows for a more powerful, yet cooler running videocard: 12 nm vs 16 nm

Launch date	21 June 2017 vs 13 September 2016
Texture fill rate	441.6 GTexel / s vs 367.4 GTexel / s
Pipelines	5120 vs 3840
Floating-point performance	14,131 gflops vs 11,758 gflops
Manufacturing process technology	12 nm vs 16 nm

Reasons to consider the NVIDIA Tesla P40

Around 5% higher core clock speed: 1303 MHz vs 1246 MHz
Around 11% higher boost clock speed: 1531 MHz vs 1380 MHz
Around 50% higher maximum memory size: 24 GB vs 16 GB
5.7x more memory clock speed: 10008 MHz vs 1758 MHz

Core clock speed	1303 MHz vs 1246 MHz
Boost clock speed	1531 MHz vs 1380 MHz
Maximum memory size	24 GB vs 16 GB
Memory clock speed	10008 MHz vs 1758 MHz

Compare benchmarks

GPU 1: NVIDIA Tesla V100 PCIe
GPU 2: NVIDIA Tesla P40

Name	NVIDIA Tesla V100 PCIe	NVIDIA Tesla P40
PassMark - G3D Mark		12499
PassMark - G2D Mark		434
Geekbench - OpenCL		54934
CompuBench 1.5 Desktop - Face Detection (mPixels/s)		300.355
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)		3559.383
CompuBench 1.5 Desktop - T-Rex (Frames/s)		19.757
CompuBench 1.5 Desktop - Video Composition (Frames/s)		204.32
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)		1214.142
GFXBench 4.0 - Car Chase Offscreen (Frames)		9538
GFXBench 4.0 - Manhattan (Frames)		3699
GFXBench 4.0 - T-Rex (Frames)		3340
GFXBench 4.0 - Car Chase Offscreen (Fps)		9538
GFXBench 4.0 - Manhattan (Fps)		3699
GFXBench 4.0 - T-Rex (Fps)		3340

Compare specifications (specs)

	NVIDIA Tesla V100 PCIe	NVIDIA Tesla P40
Essentials
Architecture	Volta	Pascal
Code name	GV100	GP102
Launch date	21 June 2017	13 September 2016
Place in performance rating	not rated	247
Type	Desktop	Workstation
Launch price (MSRP)		$5,699
Technical info
Boost clock speed	1380 MHz	1531 MHz
Core clock speed	1246 MHz	1303 MHz
Floating-point performance	14,131 gflops	11,758 gflops
Manufacturing process technology	12 nm	16 nm
Pipelines	5120	3840
Texture fill rate	441.6 GTexel / s	367.4 GTexel / s
Thermal Design Power (TDP)	250 Watt	250 Watt
Transistor count	21,100 million	11,800 million
Video outputs and ports
Display Connectors	No outputs	No outputs
Compatibility, dimensions and requirements
Interface	PCIe 3.0 x16	PCIe 3.0 x16
Supplementary power connectors	2x 8-pin	1x 6-pin + 1x 8-pin
Length		267 mm
Memory
Maximum RAM amount	16 GB	24 GB
Memory bandwidth	900.1 GB / s	480.4 GB / s
Memory bus width	4096 Bit	384 Bit
Memory clock speed	1758 MHz	10008 MHz
Memory type	HBM2	GDDR5X
Technologies
CUDA
API support
DirectX		12.0 (12_1)
OpenGL		4.6