forked from OSchip/llvm-project
InstCombine: add comment explaining malloc deletion. NFC.
I tried to change this, not quite realising the logic behind what we were doing. Hopefully this comment will help the next person to come along. llvm-svn: 347653
This commit is contained in:
parent
8577dcc533
commit
81bff5e6ea
|
@ -2244,9 +2244,16 @@ static bool isAllocSiteRemovable(Instruction *AI,
|
|||
}
|
||||
|
||||
Instruction *InstCombiner::visitAllocSite(Instruction &MI) {
|
||||
// If we have a malloc call which is only used in any amount of comparisons
|
||||
// to null and free calls, delete the calls and replace the comparisons with
|
||||
// true or false as appropriate.
|
||||
// If we have a malloc call which is only used in any amount of comparisons to
|
||||
// null and free calls, delete the calls and replace the comparisons with true
|
||||
// or false as appropriate.
|
||||
|
||||
// This is based on the principle that we can substitute our own allocation
|
||||
// function (which will never return null) rather than knowledge of the
|
||||
// specific function being called. In some sense this can change the permitted
|
||||
// outputs of a program (when we convert a malloc to an alloca, the fact that
|
||||
// the allocation is now on the stack is potentially visible, for example),
|
||||
// but we believe in a permissible manner.
|
||||
SmallVector<WeakTrackingVH, 64> Users;
|
||||
|
||||
// If we are removing an alloca with a dbg.declare, insert dbg.value calls
|
||||
|
|
Loading…
Reference in New Issue