Malloc() under UNICOS

[Mike Pritchard]

refson at castle.ed.ac.uk (Keith Refson) writes:

>Now comes the curious part.  To see what was actually going on I
>replaced the calloc() call with malloc() and memset() (in my interface
>function which handles all memory allocation).  The time spent in
>memory allocation (malloc()+memset()) decreased by a factor of 3
>compared with calloc()!   Now surely calloc() should be entirely
>equivalent to calling malloc()+memset().  Is there some gross
>inefficiency in Cray's implementation of calloc() ?  I am using C
>version 5.0, but I don't know the library version.

This is a problem with the X-MP calloc().  It clears the memory
out in a big for loop instead of using memset().  Calloc() is implemented
as a malloc() and memset() call on the Cray-2.  I just filed a problem
report on this, so Cray should fix this in the next release.

-Mike
--
Mike Pritchard
Internet: mpp at msc.umn.edu  
"Go that way.  Really fast.  If something gets in your way -- turn."