Good point. That particular call to memalign, however, is part of a
series of OMPI memory hook tests. The memory allocated by that
memalign call is promptly freed (opal/mca/memory/ptmalloc2/
opal_ptmalloc2_component.c : line 111). The change is to silence
TotalView's memory alignment error when memory debugging is enabled.
Samuel K. Gutierrez
Los Alamos National Laboratory
On Oct 1, 2009, at 12:56 PM, Ashley Pittman wrote:
> Simple malloc() returns pointers that are at least eight byte aligned
> anyway, I'm not sure what the reason for calling memalign() with a
> of four would be be anyway.
> On Thu, 2009-10-01 at 20:19 +0200, Åke Sandgren wrote:
>> No it didn't. And memalign is obsolete according to the manpage.
>> posix_memalign is the one to use.
> Ashley Pittman, Bath, UK.
> Padb - A parallel job inspection tool for cluster computing
> users mailing list