Power Global

Power Global

A central meeting place for IBM Power. Connect, ask questions, share ideas, and explore the full spectrum of Power technologies across workloads, industries, and use cases.


#TechXchangePresenter
#Power

 View Only
Back to discussions
Expand all | Collapse all

lpar_get_info sockets vs iterating over ncores and PROC_MODULEs

  • 1.  lpar_get_info sockets vs iterating over ncores and PROC_MODULEs

    Posted Fri October 08, 2021 12:23 PM
    lpar_get_info with PROC_MODULE_INFO returns an array of processor modules.
    Is it true that one processor module goes in one socket?

    Is it true that if you sum up ncores for each processor module you get total number of cores in the system? For example P9 maxes at 192 cores.
    But what if you just get one proc module (the first module of the array) and multiply sockets by ncores. Woudn't it be the same 192 number?
    So why iterate at all if you want ncores in the system?

    /*  If rc is 0, then buffer contains an array of proc_module_info_t
 *  structures with module_count elements.  For an element of 
 *  index i:
 *       
 *      buffer[i].nsockets is the total number of sockets
 *      buffer[i].nchips   is the number of chips per socket		 
 *      buffer[i].ncores   is the number of cores per chip


    ------------------------------
    philip miloslavsky
    ------------------------------


Related Content