as it is making effectively arbitrary modifications to the CFG and we don't
have a domset/domfrontier implementations that can handle the dynamic updates.
Instead of having a bunch of code that doesn't actually work in practice,
just demote any potentially tricky values to the stack (causing the problem
to go away entirely). Later invocations of mem2reg will rebuild SSA for us.
This fixes all of the major performance regressions with tail duplication
from LLVM 1.1. For example, this loop:
---
int popcount(int x) {
int result = 0;
while (x != 0) {
result = result + (x & 0x1);
x = x >> 1;
}
return result;
}
---
Used to be compiled into:
int %popcount(int %X) {
entry:
br label %loopentry
loopentry: ; preds = %entry, %no_exit
%x.0 = phi int [ %X, %entry ], [ %tmp.9, %no_exit ] ; <int> [#uses=3]
%result.1.0 = phi int [ 0, %entry ], [ %tmp.6, %no_exit ] ; <int> [#uses=2]
%tmp.1 = seteq int %x.0, 0 ; <bool> [#uses=1]
br bool %tmp.1, label %loopexit, label %no_exit
no_exit: ; preds = %loopentry
%tmp.4 = and int %x.0, 1 ; <int> [#uses=1]
%tmp.6 = add int %tmp.4, %result.1.0 ; <int> [#uses=1]
%tmp.9 = shr int %x.0, ubyte 1 ; <int> [#uses=1]
br label %loopentry
loopexit: ; preds = %loopentry
ret int %result.1.0
}
And is now compiled into:
int %popcount(int %X) {
entry:
br label %no_exit
no_exit: ; preds = %entry, %no_exit
%x.0.0 = phi int [ %X, %entry ], [ %tmp.9, %no_exit ] ; <int> [#uses=2]
%result.1.0.0 = phi int [ 0, %entry ], [ %tmp.6, %no_exit ] ; <int> [#uses=1]
%tmp.4 = and int %x.0.0, 1 ; <int> [#uses=1]
%tmp.6 = add int %tmp.4, %result.1.0.0 ; <int> [#uses=2]
%tmp.9 = shr int %x.0.0, ubyte 1 ; <int> [#uses=2]
%tmp.1 = seteq int %tmp.9, 0 ; <bool> [#uses=1]
br bool %tmp.1, label %loopexit, label %no_exit
loopexit: ; preds = %no_exit
ret int %tmp.6
}
llvm-svn: 12457
Note that this is a band-aid put over a band-aid. This just undisables
tail duplication in on very specific case that it seems to work in.
llvm-svn: 11989