RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-12-25 13:08:00 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Allow scalarrepl to treat an all-zero GEP just as bitcast.

Browse Source 
This includes not marking a GEP involving a vector as unsafe, but only when it
has all zero indices. This allows scalarrepl to work in a few more cases.

llvm-svn: 57177
This commit is contained in:
Matthijs Kooijman 2008-10-06 16:23:31 +00:00
parent dcc1048912
commit 12cd5d041d
2 changed files with 52 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
lib/Transforms/Scalar/ScalarReplAggregates.cpp
View File

@ -530,7 +530,8 @@ void SROA::isSafeUseOfAllocation(Instruction *User, AllocationInst *AI,
return MarkUnsafe(Info);
}
}
bool hasVector = false;
// Walk through the GEP type indices, checking the types that this indexes
// into.
@ -539,22 +540,30 @@ void SROA::isSafeUseOfAllocation(Instruction *User, AllocationInst *AI,
if (isa<StructType>(*I))
continue;
// Don't SROA pointers into vectors.
if (isa<VectorType>(*I))
return MarkUnsafe(Info);
// Otherwise, we must have an index into an array type. Verify that this is
// an in-range constant integer. Specifically, consider A[0][i]. We
// cannot know that the user isn't doing invalid things like allowing i to
// index an out-of-range subscript that accesses A[1]. Because of this, we
// have to reject SROA of any accesses into structs where any of the
// components are variables.
ConstantInt *IdxVal = dyn_cast<ConstantInt>(I.getOperand());
if (!IdxVal) return MarkUnsafe(Info);
if (IdxVal->getZExtValue() >= cast<ArrayType>(*I)->getNumElements())
return MarkUnsafe(Info);
// Are all indices still zero?
IsAllZeroIndices &= IdxVal->isZero();
if (const ArrayType *AT = dyn_cast<ArrayType>(*I)) {
// This GEP indexes an array. Verify that this is an in-range constant
// integer. Specifically, consider A[0][i]. We cannot know that the user
// isn't doing invalid things like allowing i to index an out-of-range
// subscript that accesses A[1]. Because of this, we have to reject SROA
// of any accesses into structs where any of the components are variables.
if (IdxVal->getZExtValue() >= AT->getNumElements())
return MarkUnsafe(Info);
}
// Note if we've seen a vector type yet
hasVector |= isa<VectorType>(*I);
// Don't SROA pointers into vectors, unless all indices are zero. When all
// indices are zero, we only consider this GEP as a bitcast, but will still
// not consider breaking up the vector.
if (hasVector && !IsAllZeroIndices)
return MarkUnsafe(Info);
}
// If there are any non-simple uses of this getelementptr, make sure to reject
@ -661,6 +670,11 @@ void SROA::RewriteBitCastUserOfAlloca(Instruction *BCInst, AllocationInst *AI,
// It is likely that OtherPtr is a bitcast, if so, remove it.
if (BitCastInst *BC = dyn_cast<BitCastInst>(OtherPtr))
OtherPtr = BC->getOperand(0);
// All zero GEPs are effectively casts
if (GetElementPtrInst *GEP = dyn_cast<GetElementPtrInst>(OtherPtr))
if (GEP->hasAllZeroIndices())
OtherPtr = GEP->getOperand(0);
if (ConstantExpr *BCE = dyn_cast<ConstantExpr>(OtherPtr))
if (BCE->getOpcode() == Instruction::BitCast)
OtherPtr = BCE->getOperand(0);

24
test/Transforms/ScalarRepl/2008-09-22-vector-gep.ll Normal file
View File

@ -0,0 +1,24 @@
; This test checks to see if scalarrepl also works when a gep with all zeroes is
; used instead of a bitcast to prepare a memmove pointer argument. Previously,
; this would not work when there was a vector involved in the struct, preventing
; scalarrepl from removing the alloca below.
; RUN: llvm-as < %s | opt -scalarrepl | llvm-dis > %t
; RUN: cat %t | not grep alloca
%struct.two = type <{ < 2 x i8 >, i16 }>
define void @main(%struct.two* %D, i16 %V) {
entry:
%S = alloca %struct.two
%S.2 = getelementptr %struct.two* %S, i32 0, i32 1
store i16 %V, i16* %S.2
; This gep is effectively a bitcast to i8*, but is sometimes generated
; because the type of the first element in %struct.two is i8.
%tmpS = getelementptr %struct.two* %S, i32 0, i32 0, i32 0
%tmpD = bitcast %struct.two* %D to i8*
call void @llvm.memmove.i32(i8* %tmpD, i8* %tmpS, i32 4, i32 1)
ret void
}
declare void @llvm.memmove.i32(i8*, i8*, i32, i32) nounwind