Regarding MPI_Allgather collective calls in MPI Mahendrakar Rao https://conferences.xsede.org/c/message_boards/find_message?p_l_id=&messageId=533616 2013-06-06T01:56:06Z 2013-06-06T01:56:06Z

It has been 2 months since I stopped using this tool. But it must be available. To use this tool, please open a xsede ticket asking the admin to start the tool for you. They also give examples on access and usage of the tool. <br />Hope this helps.

Mahendrakar Rao 2013-06-06T01:56:06Z Mahendrakar Rao https://conferences.xsede.org/c/message_boards/find_message?p_l_id=&messageId=441812 2013-01-20T03:27:39Z 2013-01-19T10:19:04Z

Hi everybody,<br />Just got access to stempede. As most of us know Stampede is having compute nodes with intel MIC coprocessor. Unfortunately I could not find material on &#034;Programming on Intel MIC using MPI&#034;.<br />Please tell me how to compile and run the MPI code on MIC.<br />Could somebody help me in this regard.<br />Thanks alot<img alt="emoticon" src="https://conferences.xsede.orghttps://conferences.xsede.org/xup-alt-theme/images/emoticons/happy.gif" >.

Mahendrakar Rao 2013-01-19T10:19:04Z Mahendrakar Rao https://conferences.xsede.org/c/message_boards/find_message?p_l_id=&messageId=428164 2012-12-15T04:20:10Z 2012-12-15T04:18:07Z

Hi sir,<br />Is there any tool available on SDSC Gordon to get the hop distances between the allocated nodes?. These distances are required for me to create topology graph of allocated nodes. Please help me in this regard. Thanks in advance.

Mahendrakar Rao 2012-12-15T04:18:07Z Mahendrakar Rao https://conferences.xsede.org/c/message_boards/find_message?p_l_id=&messageId=419288 2012-11-27T10:36:21Z 2012-11-27T10:33:51Z

Hi everybody,<br />When I attempted to run mpiexec with 32 processes on two compute nodes (on SDSC gordon) in interactive mode, it prompts me for a password. <br />Enter passphrase for key &#039;/home/srini09/.ssh/id_rsa&#039;: <br /> I do not know which password to enter. When I enter my login password, it is hanging.<br />could somebody help me in this regard. <br />Thanks in advance.<img alt="emoticon" src="https://conferences.xsede.orghttps://conferences.xsede.org/xup-alt-theme/images/emoticons/happy.gif" >

Mahendrakar Rao 2012-11-27T10:33:51Z https://conferences.xsede.org/c/message_boards/find_message?p_l_id=&messageId=416794 2012-11-16T16:06:19Z 2012-11-16T16:06:19Z

The implementation of MPI_Allgather uses different algorithms internally based on the message size and number of processes. For example bruck for short messages, ring for larger messages. Why do they use different implementations? Please explain.

2012-11-16T16:06:19Z