Charm++ parallel programming system

[Fernando Stump <fstump2 AT illinois.edu>]

Hi,

Chengbin: Thanks for helping with the compilation. Just to let you know I 
manage to compile by using cmake instead of autotools, and thus avoid the 
libtools call.
 
Anyone willing to help: 

I have a C++ code which I compiled with charmc -language parfum. The 
standalone version of the code is running, but when I use charmrun for some 
reason the connection time out. The example (simple2D) from which I based my 
code is running fine with charmrun on this machine

Below, there is the standalone call and then with charmrun.

Any clue on where the issue may be


Fernando-Stumps-MacBook-Pro:yafeq fstump2$ ./pfem
Charm++: standalone mode (not using charmrun)
Charm++: scheduler running in netpoll mode.
Charm++> Running on 1 unique compute nodes (4-way SMP).
Charm++> Cpu topology info:
PE to node map: 0 
Node to PE map:
Chip #0: 0 
Charm++> cpu topology info is gathered in 0.003 seconds.
init started
Reading node coordinates from xxx.1.node
Reading elements from xxx.1.ele
Passing node coords to framework
Passing elements to framework
Finished with init (Reading took 0 s)
Entering timeloop
1 0.000083 sec for loop 0 
1 0.000015 sec for loop 64 
1 0.000016 sec for loop 128 
1 0.000016 sec for loop 192 
1 0.000015 sec for loop 256 
1 0.000015 sec for loop 320 
1 0.000016 sec for loop 384 
1 0.000016 sec for loop 448 
1 0.000016 sec for loop 512 
1 0.000016 sec for loop 576 
1 0.000015 sec for loop 640 
1 0.000015 sec for loop 704 
1 0.000017 sec for loop 768 
1 0.000015 sec for loop 832 
1 0.000015 sec for loop 896 
1 0.000019 sec for loop 960 
1 0.000016 sec for loop 1024 
1 0.000015 sec for loop 1088 
1 0.000015 sec for loop 1152 
1 0.000015 sec for loop 1216 
1 0.000015 sec for loop 1280 
1 0.000015 sec for loop 1344 
1 0.000015 sec for loop 1408 
1 0.000015 sec for loop 1472 
1 0.000023 sec for loop 1536 
1 0.000015 sec for loop 1600 
1 0.000015 sec for loop 1664 
1 0.000015 sec for loop 1728 
1 0.000016 sec for loop 1792 
1 0.000017 sec for loop 1856 
1 0.000015 sec for loop 1920 
1 0.000015 sec for loop 1984 
1 0.000015 sec for loop 2048 
1 0.000015 sec for loop 2112 
1 0.000015 sec for loop 2176 
1 0.000015 sec for loop 2240 
1 0.000015 sec for loop 2304 
1 0.000015 sec for loop 2368 
1 0.000015 sec for loop 2432 
1 0.000015 sec for loop 2496 
1 0.000015 sec for loop 2560 
1 0.000015 sec for loop 2624 
1 0.000016 sec for loop 2688 
1 0.000019 sec for loop 2752 
1 0.000015 sec for loop 2816 
1 0.000015 sec for loop 2880 
1 0.000016 sec for loop 2944 
1 0.000015 sec for loop 3008 
1 0.000015 sec for loop 3072 
1 0.000015 sec for loop 3136 
1 0.000015 sec for loop 3200 
1 0.000015 sec for loop 3264 
1 0.000015 sec for loop 3328 
1 0.000016 sec for loop 3392 
1 0.000015 sec for loop 3456 
1 0.000015 sec for loop 3520 
1 0.000015 sec for loop 3584 
1 0.000015 sec for loop 3648 
1 0.000015 sec for loop 3712 
1 0.000015 sec for loop 3776 
1 0.000015 sec for loop 3840 
1 0.000016 sec for loop 3904 
1 0.000017 sec for loop 3968 
1 0.000020 sec for loop 4032 
1 0.000016 sec for loop 4096 
1 0.000015 sec for loop 4160 
1 0.000015 sec for loop 4224 
1 0.000016 sec for loop 4288 
1 0.000015 sec for loop 4352 
1 0.000016 sec for loop 4416 
1 0.000015 sec for loop 4480 
1 0.000016 sec for loop 4544 
1 0.000016 sec for loop 4608 
1 0.000015 sec for loop 4672 
1 0.000015 sec for loop 4736 
1 0.000015 sec for loop 4800 
1 0.000015 sec for loop 4864 
1 0.000015 sec for loop 4928 
1 0.000015 sec for loop 4992 
Driver finished: average 0.000499 s/step
Program finished.





Fernando-Stumps-MacBook-Pro:yafeq fstump2$ ./charmrun pfem  +vp4 +p4 ++verbose
Charmrun> charmrun started...
Charmrun> using ./nodelist as nodesfile
Charmrun> adding client 0: "localhost", IP:127.0.0.1
Charmrun> adding client 1: "localhost", IP:127.0.0.1
Charmrun> adding client 2: "localhost", IP:127.0.0.1
Charmrun> adding client 3: "localhost", IP:127.0.0.1
Charmrun> Charmrun = 192.168.1.144, port = 53280
Charmrun> Sending "0 192.168.1.144 53280 9600 0" to client 0.
Charmrun> find the node program 
"/Users/fstump2/Documents/workspace/LibFEM/Soheil_Alejandro/libs/yafeq/build/yafeq/pfem"
 at 
"/Users/fstump2/Documents/workspace/LibFEM/Soheil_Alejandro/libs/yafeq/build/yafeq"
 for 0.
Charmrun> Starting ssh localhost -l fstump2 /bin/sh -f
Charmrun> remote shell (localhost:0) started
Charmrun> Sending "1 192.168.1.144 53280 9600 0" to client 1.
Charmrun> find the node program 
"/Users/fstump2/Documents/workspace/LibFEM/Soheil_Alejandro/libs/yafeq/build/yafeq/pfem"
 at 
"/Users/fstump2/Documents/workspace/LibFEM/Soheil_Alejandro/libs/yafeq/build/yafeq"
 for 1.
Charmrun> Starting ssh localhost -l fstump2 /bin/sh -f
Charmrun> remote shell (localhost:1) started
Charmrun> Sending "2 192.168.1.144 53280 9600 0" to client 2.
Charmrun> find the node program 
"/Users/fstump2/Documents/workspace/LibFEM/Soheil_Alejandro/libs/yafeq/build/yafeq/pfem"
 at 
"/Users/fstump2/Documents/workspace/LibFEM/Soheil_Alejandro/libs/yafeq/build/yafeq"
 for 2.
Charmrun> Starting ssh localhost -l fstump2 /bin/sh -f
Charmrun> remote shell (localhost:2) started
Charmrun> Sending "3 192.168.1.144 53280 9600 0" to client 3.
Charmrun> find the node program 
"/Users/fstump2/Documents/workspace/LibFEM/Soheil_Alejandro/libs/yafeq/build/yafeq/pfem"
 at 
"/Users/fstump2/Documents/workspace/LibFEM/Soheil_Alejandro/libs/yafeq/build/yafeq"
 for 3.
Charmrun> Starting ssh localhost -l fstump2 /bin/sh -f
Charmrun> remote shell (localhost:3) started
Charmrun> node programs all started
Charmrun remote shell(localhost.3)> remote responding...
Charmrun remote shell(localhost.2)> remote responding...
Charmrun remote shell(localhost.0)> remote responding...
Charmrun remote shell(localhost.3)> starting node-program...
Charmrun remote shell(localhost.3)> rsh phase successful.
Charmrun remote shell(localhost.0)> starting node-program...
Charmrun remote shell(localhost.1)> remote responding...
Charmrun remote shell(localhost.2)> starting node-program...
Charmrun remote shell(localhost.0)> rsh phase successful.
Charmrun remote shell(localhost.1)> starting node-program...
Charmrun remote shell(localhost.1)> rsh phase successful.
Charmrun remote shell(localhost.2)> rsh phase successful.
Charmrun> Waiting for 0-th client to connect.
Charmrun> error 0 attaching to node:
Timeout waiting for node-program to connect
Fernando-Stumps-MacBook-Pro:yafeq fstump2$