<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>