<div dir="ltr">Dear MPICH2.<div>I use Intel processor with NUMA technology.</div><div>All processes are multi-threaded.</div><div>Processes distributed between computers by mpiexec.hydra.</div><div>I"m interested to separate processes by memory usage. Each process use it's local memory only, as result�bound�to single socket (but not core). But I"m interested in leaving maximum freedom to OS in choosing cores to achieve maximum performance. As result,�I"m interested in binding to CPU:socket but not core.</div>
<div><br></div><div>For example:�</div><div>I have computer with 2 CPUs,� each CPU has 4 cores.</div><div>*) I try to execute 2 processes on this computer.</div><div>� � I"d like to bind 1-st process to cores 0-3 (OS decides where it will be executed each time-slot) and <br>
� � 2-on one on cores 4-7.</div><div>*) I try to execute 4 processes on this computer.</div><div>� � Processes 1&2 I want to bind to CPU:Socket 1 (cores 0-3), processes 3&4 I want to bind to <br>� � CPU:Socket 2 (cores 4-7). OS will resolve conflicts.</div>
<div><br></div><div>According to manual, each strategy performs binding to specific single core, which calculated using user selected algorithm.</div><div>1) May you please suggest any technique to achieve expected binding (not to single core), using mpiexec.hydra?</div>
<div>2) Can I perform process binding to local memory per CPU:Socket?</div><div><br></div><div>Thank you,</div><div>Anatoly.</div><div><br></div><div><br></div></div>