6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-07-08 18:30:04 +00:00
Code Issues Projects Releases Wiki Activity

Fix 9216 - Endless loop in InstCombine pass.

Browse Source 
The pattern "A&(A^B) -> A & ~B" recreated itself because ~B is
actually a xor -1.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@125557 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Nadav Rotem 2011-02-15 07:13:48 +00:00
parent 326d976eb2
commit d9e087bbc3
2 changed files with 24 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
lib/Transforms/InstCombine/InstCombineAndOrXor.cpp
View File

@ -1140,7 +1140,11 @@ Instruction *InstCombiner::visitAnd(BinaryOperator &I) {
cast<BinaryOperator>(Op1)->swapOperands();
std::swap(A, B);
}
if (A == Op0) // A&(A^B) -> A & ~B
// Notice that the patten (A&(~B)) is actually (A&(-1^B)), so if
// A is originally -1 (or a vector of -1 and undefs), then we enter
// an endless loop. By checking that A is non-constant we ensure that
// we will never get to the loop.
if (A == Op0 && !isa<Constant>(A)) // A&(A^B) -> A & ~B
return BinaryOperator::CreateAnd(A, Builder->CreateNot(B, "tmp"));
}

19
test/Transforms/InstCombine/2011-02-14-InfLoop.ll Normal file
View File

@ -0,0 +1,19 @@
; This testcase causes an infinite loop in the instruction combiner,
; because it changes a pattern and the original pattern is almost
; identical to the newly-generated pattern.
; RUN: opt < %s -instcombine -disable-output
;PR PR9216
target triple = "x86_64-unknown-linux-gnu"
define <4 x float> @m_387(i8* noalias nocapture %A, i8* nocapture %B, <4 x i1> %C) nounwind {
entry:
%movcsext20 = sext <4 x i1> %C to <4 x i32>
%tmp2389 = xor <4 x i32> %movcsext20, <i32 -1, i32 -1, i32 -1, i32 -1>
%movcand25 = and <4 x i32> %tmp2389, <i32 undef, i32 undef, i32 undef, i32 -1>
%movcor26 = or <4 x i32> %movcand25, zeroinitializer
%L2 = bitcast <4 x i32> %movcor26 to <4 x float>
%L3 = shufflevector <4 x float> zeroinitializer, <4 x float> %L2, <4 x i32> <i32 0, i32 1, i32 2, i32 7>
ret <4 x float> %L3
}