AmazonEC2

OpenSees can run Sequentially and in Parallel on the resources provided by Amazon EC2. Amazon EC2 is the largest and most widely used cloud service provider. Once you are set up with Amazon and have installed some software from MIT, the running of the applications is trivial. For example, 6 commands from the terminal and you could be running a parallel application on a remote Aamzon EC2 cluster of a few thousand nodes for a few dollars an hour. And it might not cost you anything, i.e. it could be FREE! as you get free hours through the education program if you are a student or educator. and those in industry get a limted amount of resources for the first 112 months.

The following are the 6 commands you would issue from your terminal window to run the file Example.tcl on a 100 node Amazon Cluster and obtain the results that the scipts created in the results folder back.

starcluser start smallcluster
starcluster put Example.tcl /root
starcluster sshmaster smallcluster
mpiexec -n 100 OpenSees Example.tcl
starcluster get /results /root/results
starcluster terminate smallcluster

The first command starts the cluster. The second command will copy the file Eample.tcl to the remote machine. The third command will cause you to log on to your remote clusters 'master' node. The next command is the command you would issue on the remote machine to run a 100 processor job. The next command retrieves the contents of the /root/results directory. And lastly and an important command (assuming you don't want to use all your free allocation and go into bankruptcy) is the command to terminate the remote cluster.

The operation requires that:

• You log in with a credit card and obtain an Amazon EC2 account.
• You correctly install the StarCluster Software from MIT on your computer.
• Lastly you use the AMI that we have created for you in the StarCluster config file. The Amazon Ec2 AMI to specify is ami-e9ff1182 and is available in the US East Region.

The change to the config file is simply to swap out there ami and replace with ours. The NODE_IMAGE_ID lines should read:

NODE_IMAGE_ID = ami-e9ff1182