maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

The optimization a + (-0.0f) -> a was being misapplied to a + (+0.0f) in the vector case (because 

we weren't differntiating floating-point zeroinitializers from other zero-initializers)
which was causing problems for code relying upon a + (+0.0f) to, eg, flush denormals to
0. Make the scalar and vector cases have the same behaviour.

llvm-svn: 177279
This commit is contained in:
David Tweed 2013-03-18 11:54:44 +00:00
parent 15bee188c4
commit 5493feed25
1 changed files with 13 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
llvm/lib/IR/Constants.cpp
View File

@ -47,6 +47,19 @@ bool Constant::isNegativeZeroValue() const {
if (const ConstantFP *CFP = dyn_cast<ConstantFP>(this))
return CFP->isZero() && CFP->isNegative();
// Equivalent for a vector of -0.0's.
if (const ConstantDataVector *CV = dyn_cast<ConstantDataVector>(this))
if (ConstantFP *SplatCFP = dyn_cast_or_null<ConstantFP>(CV->getSplatValue()))
if (SplatCFP && SplatCFP->isZero() && SplatCFP->isNegative())
return true;
// However, vectors of zeroes which are floating point represent +0.0's.
if (const ConstantAggregateZero *CAZ = dyn_cast<ConstantAggregateZero>(this))
if (const VectorType *VT = dyn_cast<VectorType>(CAZ->getType()))
if (VT->getElementType()->isFloatingPointTy())
// As it's a CAZ, we know it's the zero bit-pattern (ie, +0.0) in each element.
return false;
// Otherwise, just use +0.0.
return isNullValue();
}