CFD Online Logo CFD Online URL
www.cfd-online.com
[Sponsors]
Home > Forums

Dark side of Amdahl's law. Part III

Register Blogs Members List Search Today's Posts Mark Forums Read

Rate this Entry

Dark side of Amdahl's law. Part III

Posted December 9, 2011 at 12:04 by SergeAS
Tags mpi, parallel

...use a blocking call Sendrecv() instead of a pair of Send() + Recv() slightly improves the performance of the code but does not result to improved scalability




Significantly improves the scalability of the solver, using the Halo ehchanges, the use of non-blocking MPI calls Isend() and Irecv(). This allows data transfer between subdomains is really parallel.

The following figure shows the so-called "efficiency parallelization" calculated as the ratio of real to the ideal speedup as a function of the number of cores involved.

In analyzing the above figures, we see that despite the increase in net performance solver "parallelization efficiency" decreases

to be continued...
Attached Thumbnails
Click image for larger version

Name:	HyperFLOW2D-parallel-factor2.png
Views:	1077
Size:	12.0 KB
ID:	42   Click image for larger version

Name:	HyperFLOW2D-speedup2.png
Views:	1042
Size:	11.4 KB
ID:	43   Click image for larger version

Name:	HyperFLOW2D-speed2.png
Views:	1046
Size:	11.8 KB
ID:	44   Click image for larger version

Name:	HyperFLOW2D-effectivity2.png
Views:	384
Size:	12.6 KB
ID:	45  
Posted in Uncategorized
Views 1209 Comments 0 Edit Tags Email Blog Entry
« Prev     Main     Next »
Total Comments 0

Comments

 

All times are GMT -4. The time now is 08:21.