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

Add some comments clarifying that the GEP analysis for vector GEPs is 

deeply suspicious and likely to go away eventually. Also fix a bogus
comment about one of the checks in the vector GEP analysis. Based on
review from Duncan.

llvm-svn: 163894
This commit is contained in:
Chandler Carruth 2012-09-14 10:30:40 +00:00
parent 19450da9e6
commit dd3cea898f
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
llvm/lib/Transforms/Scalar/SROA.cpp
View File

@ -1300,10 +1300,13 @@ static Value *getNaturalGEPRecursively(IRBuilder<> &IRB, const TargetData &TD,
if (Ty->isPointerTy())
return 0;
// We try to analyze GEPs over vectors here, but note that these GEPs are
// extremely poorly defined currently. The long-term goal is to remove GEPing
// over a vector from the IR completely.
if (VectorType *VecTy = dyn_cast<VectorType>(Ty)) {
unsigned ElementSizeInBits = VecTy->getScalarSizeInBits();
if (ElementSizeInBits % 8)
return 0; // GEPs over multiple of 8 size vector elements are invalid.
return 0; // GEPs over non-multiple of 8 size vector elements are invalid.
APInt ElementSize(Offset.getBitWidth(), ElementSizeInBits / 8);
APInt NumSkippedElements = Offset.udiv(ElementSize);
if (NumSkippedElements.ugt(VecTy->getNumElements()))