Charm++ parallel programming system

["Van Der Wijngaart, Rob F" <rob.f.van.der.wijngaart AT intel.com>]

Excellent, thanks, Phil!

 

Rob

 

From: Phil Miller [mailto:unmobile AT gmail.com]
Sent: Monday, December 05, 2016 10:36 AM
To: Van Der Wijngaart, Rob F <rob.f.van.der.wijngaart AT intel.com>
Cc: Chandrasekar, Kavitha <kchndrs2 AT illinois.edu>; White, Samuel T <white67 AT illinois.edu>; Totoni, Ehsan <ehsan.totoni AT intel.com>; Langer, Akhil <akhil.langer AT intel.com>; Harshitha Menon <harshitha.menon AT gmail.com>; charm AT cs.uiuc.edu
Subject: Re: [charm] When to migrate

 

 

On Mon, Dec 5, 2016 at 12:27 PM, Van Der Wijngaart, Rob F <rob.f.van.der.wijngaart AT intel.com> wrote:

One last question. If I have an AMPI code that I have linked with commonLB and that I run with a valid +balancer argument, but I do not call AMPI_Migrate anywhere in the code, does the runtime still collect load balance information? If so, is there a charmrun command that I can give that prevents the runtime from doing that? I know I could use these functions:

AMPI_Load_stop_measure(void)

AMPI_Load_start_measure(void)

but I prefer to specify it on the command line (otherwise I need to supply yet another input parameter and parse it in the code). Thanks!

 

 

If you run the program with +LBOff, instrumentation will be initially disabled. It will be as if Load_stop_measure() were called at the beginning of execution.