The new isel was not properly handling patterns that covered
internal nodes with flag results. Record these with a new
OPC_MarkFlagResults opcode and use this to update the interior
nodes' flag results properly. This fixes CodeGen/X86/i256-add.ll
with the new isel.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97021 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/utils/TableGen/DAGISelMatcherGen.cpp b/utils/TableGen/DAGISelMatcherGen.cpp
index 39d5155..9727c5f 100644
--- a/utils/TableGen/DAGISelMatcherGen.cpp
+++ b/utils/TableGen/DAGISelMatcherGen.cpp
@@ -70,6 +70,10 @@
/// MatchedChainNodes - This maintains the position in the recorded nodes
/// array of all of the recorded input nodes that have chains.
SmallVector<unsigned, 2> MatchedChainNodes;
+
+ /// MatchedFlagResultNodes - This maintains the position in the recorded
+ /// nodes array of all of the recorded input nodes that have flag results.
+ SmallVector<unsigned, 2> MatchedFlagResultNodes;
/// PhysRegInputs - List list has an entry for each explicitly specified
/// physreg input to the pattern. The first elt is the Register node, the
@@ -287,6 +291,9 @@
AddMatcherNode(new CheckChainCompatibleMatcherNode(PrevOp));
}
}
+
+ // TODO: Complex patterns can't have output flags, if they did, we'd want
+ // to record them.
return;
}
@@ -416,6 +423,18 @@
AddMatcherNode(new CheckFoldableChainNodeMatcherNode());
}
}
+
+ // If this node has an output flag and isn't the root, remember it.
+ if (N->NodeHasProperty(SDNPOutFlag, CGP) &&
+ N != Pattern.getSrcPattern()) {
+ // TODO: This redundantly records nodes with both flags and chains.
+
+ // Record the node and remember it in our chained nodes list.
+ AddMatcherNode(new RecordMatcherNode("'" + N->getOperator()->getName() +
+ "' flag output node"));
+ // Remember all of the nodes with output flags our pattern will match.
+ MatchedFlagResultNodes.push_back(NextRecordedOperandNo++);
+ }
// If this node is known to have an input flag or if it *might* have an input
// flag, capture it as the flag input of the pattern.
@@ -598,16 +617,16 @@
bool isRoot = N == Pattern.getDstPattern();
- // NodeHasOutFlag - True if this node has a flag.
- bool NodeHasInFlag = false, NodeHasOutFlag = false;
+ // TreeHasOutFlag - True if this tree has a flag.
+ bool TreeHasInFlag = false, TreeHasOutFlag = false;
if (isRoot) {
const TreePatternNode *SrcPat = Pattern.getSrcPattern();
- NodeHasInFlag = SrcPat->TreeHasProperty(SDNPOptInFlag, CGP) ||
+ TreeHasInFlag = SrcPat->TreeHasProperty(SDNPOptInFlag, CGP) ||
SrcPat->TreeHasProperty(SDNPInFlag, CGP);
// FIXME2: this is checking the entire pattern, not just the node in
// question, doing this just for the root seems like a total hack.
- NodeHasOutFlag = SrcPat->TreeHasProperty(SDNPOutFlag, CGP);
+ TreeHasOutFlag = SrcPat->TreeHasProperty(SDNPOutFlag, CGP);
}
// NumResults - This is the number of results produced by the instruction in
@@ -668,7 +687,7 @@
PhysRegInputs[i].first));
// Even if the node has no other flag inputs, the resultant node must be
// flagged to the CopyFromReg nodes we just generated.
- NodeHasInFlag = true;
+ TreeHasInFlag = true;
}
// Result order: node results, chain, flags
@@ -694,7 +713,7 @@
}
if (NodeHasChain)
ResultVTs.push_back(MVT::Other);
- if (NodeHasOutFlag)
+ if (TreeHasOutFlag)
ResultVTs.push_back(MVT::Flag);
// FIXME2: Instead of using the isVariadic flag on the instruction, we should
@@ -727,7 +746,7 @@
AddMatcherNode(new EmitNodeMatcherNode(II.Namespace+"::"+II.TheDef->getName(),
ResultVTs.data(), ResultVTs.size(),
InstOps.data(), InstOps.size(),
- NodeHasChain, NodeHasInFlag,
+ NodeHasChain, TreeHasInFlag,
NodeHasMemRefs,NumFixedArityOperands));
// The non-chain and non-flag results of the newly emitted node get recorded.
@@ -813,6 +832,13 @@
assert(Ops.size() >= NumSrcResults && "Didn't provide enough results");
Ops.resize(NumSrcResults);
#endif
+
+ // If the matched pattern covers nodes which define a flag result, emit a node
+ // that tells the matcher about them so that it can update their results.
+ if (!MatchedFlagResultNodes.empty())
+ AddMatcherNode(new MarkFlagResultsMatcherNode(MatchedFlagResultNodes.data(),
+ MatchedFlagResultNodes.size()));
+
// We know that the resulting pattern has exactly one result/
// FIXME2: why? what about something like (set a,b,c, (complexpat))