LPEL_FLAGS

This file shows the meaning of LPEL flags

-i <input file>: specify input file

-m <monitoring flag combination>: enable monitoring (for more detail, see LOGFORMAT)

-w <num>: 	specify the number of workers (including master in lpel_hrc, e.g. -w 2 ==> 1 master, 1 worker)
-cw <num>: 	specify the number of cpus used for workers (and master in lpel_hrc)
-co <num>: 	specify the number of cpus used for wrappers
-sosi:    	enable supporting source/sink

Each wrapper/source/sink is mapped separately to its own thread.
Source tasks are tasks of entities starting with "snet_source"
Sink tasks are tasks of entities starting with "snet_sink"

By default: w = #cpus
            cw =# cpus
            co = 0
If co = 0; wrapper/source/sink are executed on the same set of cpus as workers

-np: disable pinned mode. By default, pinned mode is enable, i.e. workers and master are mapped in their set of cpus with round-robin manner. E.g. if there is 3 cpus for master/worker and there are 1 master and 4 workers:  master is mapped to cpu 0, worker 1 is mapped to cpu 1, worker 2 is mapped to cpu 2, worker 3 is mapped to cpu 0, worker 4 is mapped to cpu 1.
When this mode is disable, worker/master are mapped to the set of cpus but not pinned to any specific cpu.


-excl: workers and master are executed on exclusive cpus, i.e. one worker/master has its own cpu
 If this flag is used:
    + pinned mode must be enable
    + co > 0
    + #cpus >= cw + co

For task migration in lpel_decen:
-tm <num>         : mechanims for task migration (1: random-based, 2: waiting-proportion-based)
-threshold <val>  : random threshold used in random-based migration