summaryrefslogtreecommitdiffstats
path: root/llvm/lib/CodeGen/SelectionDAG
diff options
context:
space:
mode:
authorJohn Brawn <john.brawn@arm.com>2016-11-23 16:05:51 +0000
committerJohn Brawn <john.brawn@arm.com>2016-11-23 16:05:51 +0000
commit150addb45cb425d96bdcb1ccc53e0f9a56b15e8b (patch)
treecf4370a1fbe33960fcd6ef474974dce6517a047e /llvm/lib/CodeGen/SelectionDAG
parent10fc3cfc637695cb1d4ec946a2327c886859b996 (diff)
downloadbcm5719-llvm-150addb45cb425d96bdcb1ccc53e0f9a56b15e8b.tar.gz
bcm5719-llvm-150addb45cb425d96bdcb1ccc53e0f9a56b15e8b.zip
[DAGCombiner] Fix infinite loop in vector mul/shl combining
We have the following DAGCombiner transformations: (mul (shl X, c1), c2) -> (mul X, c2 << c1) (mul (shl X, C), Y) -> (shl (mul X, Y), C) (shl (mul x, c1), c2) -> (mul x, c1 << c2) Usually the constant shift is optimised by SelectionDAG::getNode when it is constructed, by SelectionDAG::FoldConstantArithmetic, but when we're dealing with vectors and one of those vector constants contains an undef element FoldConstantArithmetic does not fold and we enter an infinite loop. Fix this by making FoldConstantArithmetic use getNode to decide how to fold each vector element, the same as FoldConstantVectorArithmetic does, and rather than adding the constant shift to the work list instead only apply the transformation if it's already been folded into a constant, as if it's not we're going to loop endlessly. Additionally add missing NoOpaques to one of those transformations, which I noticed when writing the tests for this. Differential Revision: https://reviews.llvm.org/D26605 llvm-svn: 287766
Diffstat (limited to 'llvm/lib/CodeGen/SelectionDAG')
-rw-r--r--llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp12
-rw-r--r--llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp21
2 files changed, 15 insertions, 18 deletions
diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 4890441e37c..b3813ba82ce 100644
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -2157,11 +2157,11 @@ SDValue DAGCombiner::visitMUL(SDNode *N) {
// (mul (shl X, c1), c2) -> (mul X, c2 << c1)
if (N0.getOpcode() == ISD::SHL &&
- isConstantOrConstantVector(N1) &&
- isConstantOrConstantVector(N0.getOperand(1))) {
+ isConstantOrConstantVector(N1, /* NoOpaques */ true) &&
+ isConstantOrConstantVector(N0.getOperand(1), /* NoOpaques */ true)) {
SDValue C3 = DAG.getNode(ISD::SHL, SDLoc(N), VT, N1, N0.getOperand(1));
- AddToWorklist(C3.getNode());
- return DAG.getNode(ISD::MUL, SDLoc(N), VT, N0.getOperand(0), C3);
+ if (isConstantOrConstantVector(C3))
+ return DAG.getNode(ISD::MUL, SDLoc(N), VT, N0.getOperand(0), C3);
}
// Change (mul (shl X, C), Y) -> (shl (mul X, Y), C) when the shift has one
@@ -4714,8 +4714,8 @@ SDValue DAGCombiner::visitSHL(SDNode *N) {
isConstantOrConstantVector(N1, /* No Opaques */ true) &&
isConstantOrConstantVector(N0.getOperand(1), /* No Opaques */ true)) {
SDValue Shl = DAG.getNode(ISD::SHL, SDLoc(N1), VT, N0.getOperand(1), N1);
- AddToWorklist(Shl.getNode());
- return DAG.getNode(ISD::MUL, SDLoc(N), VT, N0.getOperand(0), Shl);
+ if (isConstantOrConstantVector(Shl))
+ return DAG.getNode(ISD::MUL, SDLoc(N), VT, N0.getOperand(0), Shl);
}
if (N1C && !N1C->isOpaque())
diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
index f2bb3795a2d..71c83ae5c0f 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
@@ -3498,25 +3498,22 @@ SDValue SelectionDAG::FoldConstantArithmetic(unsigned Opcode, const SDLoc &DL,
EVT SVT = VT.getScalarType();
SmallVector<SDValue, 4> Outputs;
for (unsigned I = 0, E = BV1->getNumOperands(); I != E; ++I) {
- ConstantSDNode *V1 = dyn_cast<ConstantSDNode>(BV1->getOperand(I));
- ConstantSDNode *V2 = dyn_cast<ConstantSDNode>(BV2->getOperand(I));
- if (!V1 || !V2) // Not a constant, bail.
- return SDValue();
-
- if (V1->isOpaque() || V2->isOpaque())
- return SDValue();
+ SDValue V1 = BV1->getOperand(I);
+ SDValue V2 = BV2->getOperand(I);
// Avoid BUILD_VECTOR nodes that perform implicit truncation.
- // FIXME: This is valid and could be handled by truncating the APInts.
+ // FIXME: This is valid and could be handled by truncation.
if (V1->getValueType(0) != SVT || V2->getValueType(0) != SVT)
return SDValue();
// Fold one vector element.
- std::pair<APInt, bool> Folded = FoldValue(Opcode, V1->getAPIntValue(),
- V2->getAPIntValue());
- if (!Folded.second)
+ SDValue ScalarResult = getNode(Opcode, DL, SVT, V1, V2);
+
+ // Scalar folding only succeeded if the result is a constant or UNDEF.
+ if (!ScalarResult.isUndef() && ScalarResult.getOpcode() != ISD::Constant &&
+ ScalarResult.getOpcode() != ISD::ConstantFP)
return SDValue();
- Outputs.push_back(getConstant(Folded.first, DL, SVT));
+ Outputs.push_back(ScalarResult);
}
assert(VT.getVectorNumElements() == Outputs.size() &&
OpenPOWER on IntegriCloud