Re: Allocation sinking in git HEAD

  • From: Geoff Leyland <geoff_leyland@xxxxxxxxxxx>
  • To: luajit@xxxxxxxxxxxxx
  • Date: Wed, 4 Jul 2012 10:54:45 +1200

On 4/07/2012, at 10:42 AM, David Given wrote:

> For example, passing the object to a leaf function vs passing it to a
> non-leaf function

I imagine it's more a case of whether the object is contained within a single 
trace than about functions.  Presumably some objects are materialized just 
before trace exits.  Are then then un-materialised if the side trace's use of 
the object later proves tractable to the optimization?

> passing it to an FFI function…

If you ask for a pointer, a pointer has to be provided.  As I understand it, 
this is about moving structure fields from the heap to local variables, not 
whole structures from the heap to the stack.


Other related posts: