Continue to Site

Welcome to EDAboard.com

Welcome to our site! EDAboard.com is an international Electronics Discussion Forum focused on EDA software, circuits, schematics, books, theory, papers, asic, pld, 8051, DSP, Network, RF, Analog Design, PCB, Service Manuals... and a whole lot more! To participate you need to register. Registration is free. Click here to register now.

HFSS and MPI for use of solver domain (intel MPI or platform MPI)

Status
Not open for further replies.

hassan_k

Newbie level 2
Newbie level 2
Joined
Feb 22, 2014
Messages
2
Helped
0
Reputation
0
Reaction score
0
Trophy points
1
Visit site
Activity points
15
Hello everyone

First i have to provide this information:

1- i have instaled the latest version of Intel MPI and platform MPI of IBM.

2- i have to use one of them through Ansys HFSS 15 x64 which is a EM-software in a GigE network.

3- HFSS dont have any problem with discrit processes (for ex. 15 paralel process in optimetric solution will share trough 3 computer on network correctly)

4- i need to use memory of other computers on the network, so need distribute the RAM usage with enabling "use of solver domain"

5- the error i got every time is "authentication faild" or "unable to create child process in hosts" (see the below)

[error] The attempted launch of solvers via MPI failed while connecting to communication pipes. The probable cause is failure to install the vendor MPI on one or more machines or password authentication failure for MPI during the launch attempt. -- Simulating on machine
[error] Unable to create child process: mpirun. -- Simulating on machine

6- the ansoft RSM on all machins are running and the testing tool on hfss work properly.

now i need help to configure Intel MPI or platform MPI in order to split the matrixes.

i will apreciate that anyone can help me.

with the special regards
 

Hi hassan_k,

I am getting exactly the same error when I am trying to use Domain decomposition method. It works perfectly fine when I use it with just one node,i.e., 16cores and 32GB RAM (all memory shared between 16 cores). If I try to distribute the task over multiple nodes, I get the same error as yours.

Please let me know if you have managed to solved this problem.

Thanks,
 

Status
Not open for further replies.

Part and Inventory Search

Welcome to EDABoard.com

Sponsor

Back
Top