parallelize when processing data

haizhou0410 · February 5, 2021, 10:09

Hi everyone,
I am wondering how to parallelize in Tecplot when it is processing data for instance smoothing data or interpolating data. Since the grids number is large, it takes quite a long time to process and when I check the CPU utilization I found it is quite low. It seems it uses only one core to process the data. Could anyone tell me how to improve the speed such as parallelize? Thank you very much in advance.

wsfowler · February 11, 2021, 19:54

Linear Interpolation and Inverse Distance interpolations are both parallel operations - so you should be seeing good CPU utilization with those operations.

Kriging and Smoothing are not parallel, but some data that these operations need to fetch (like cell face neighbors) are parallel - so you'll see some concurrency.

If you have multiple data files you need to Smooth you could try using Python's multiprocessing module. We did a webinar on this subject here:
https://www.tecplot.com/2019/09/13/a...-times-faster/

If you need additional assistance I'd suggest you contact our support staff at support@tecplot.com (USA) or support-eu@tecplot.com (Europe).

Scott

February 5, 2021, 10:09	parallelize when processing data	#1
haizhou0410 New Member Jim Join Date: Aug 2019 Posts: 13 Rep Power: 6	Hi everyone, I am wondering how to parallelize in Tecplot when it is processing data for instance smoothing data or interpolating data. Since the grids number is large, it takes quite a long time to process and when I check the CPU utilization I found it is quite low. It seems it uses only one core to process the data. Could anyone tell me how to improve the speed such as parallelize? Thank you very much in advance.

Similar Threads
Thread	Thread Starter	Forum	Replies	Last Post
Rewriting UDF For Parallel Processing	m_ridzon	Fluent UDF and Scheme Programming	9	January 10, 2019 13:42
Different results between parallel and serial processing	Sarah_Fluent	FLUENT	5	March 6, 2018 11:42
[OpenFOAM] is parallel processing available in parafoam for post processing?	sachinlb	ParaView	1	August 14, 2012 09:52
NO model vs post processing in coal combustion,CFX	sakalido	CFX	1	April 15, 2011 14:07
Post Processing in FEM	Abhijit Tilak	Main CFD Forum	0	April 26, 2004 11:59

February 11, 2021, 19:54		#2
wsfowler Senior Member Scott Fowler Join Date: May 2009 Posts: 112 Rep Power: 16	Linear Interpolation and Inverse Distance interpolations are both parallel operations - so you should be seeing good CPU utilization with those operations. Kriging and Smoothing are not parallel, but some data that these operations need to fetch (like cell face neighbors) are parallel - so you'll see some concurrency. If you have multiple data files you need to Smooth you could try using Python's multiprocessing module. We did a webinar on this subject here: https://www.tecplot.com/2019/09/13/a...-times-faster/ If you need additional assistance I'd suggest you contact our support staff at support@tecplot.com (USA) or support-eu@tecplot.com (Europe). Scott