forked from OSchip/llvm-project
Add a note about a potential PIC optimization.
llvm-svn: 52663
This commit is contained in:
parent
76600aa35c
commit
02a2aaf2e7
|
@ -1709,3 +1709,10 @@ _test:
|
|||
it would be better to codegen as: x+~y (notl+addl)
|
||||
|
||||
//===---------------------------------------------------------------------===//
|
||||
|
||||
We should consider using __i686.get_pc_thunk.bx for MOVPC32r (used for PIC)
|
||||
on targets that support it, such as Linux and similar targets, in place of
|
||||
the call-a-label trick. It's said to be friendlier to branch-prediction
|
||||
hardware because it pairs a ret with the call.
|
||||
|
||||
//===---------------------------------------------------------------------===//
|
||||
|
|
Loading…
Reference in New Issue