Add a note about a potential PIC optimization.

llvm-svn: 52663
This commit is contained in:
Dan Gohman 2008-06-24 00:53:07 +00:00
parent 76600aa35c
commit 02a2aaf2e7
1 changed files with 7 additions and 0 deletions

View File

@ -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.
//===---------------------------------------------------------------------===//