Be careful about scheduling nodes above previous calls. It increase usages of
more callee-saved registers and introduce copies. Only allows it if scheduling
a node above calls would end up lessen register pressure.
Call operands also has added ABI restrictions for register allocation, so be
extra careful with hoisting them above calls.
rdar://9329627
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@130245 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/lib/CodeGen/SelectionDAG/ScheduleDAGSDNodes.cpp b/lib/CodeGen/SelectionDAG/ScheduleDAGSDNodes.cpp
index 94b8c2f..9f2f012 100644
--- a/lib/CodeGen/SelectionDAG/ScheduleDAGSDNodes.cpp
+++ b/lib/CodeGen/SelectionDAG/ScheduleDAGSDNodes.cpp
@@ -83,6 +83,7 @@
SU->Latency = Old->Latency;
SU->isVRegCycle = Old->isVRegCycle;
SU->isCall = Old->isCall;
+ SU->isCallOp = Old->isCallOp;
SU->isTwoAddress = Old->isTwoAddress;
SU->isCommutable = Old->isCommutable;
SU->hasPhysRegDefs = Old->hasPhysRegDefs;
@@ -285,6 +286,7 @@
Worklist.push_back(DAG->getRoot().getNode());
Visited.insert(DAG->getRoot().getNode());
+ SmallVector<SUnit*, 8> CallSUnits;
while (!Worklist.empty()) {
SDNode *NI = Worklist.pop_back_val();
@@ -337,6 +339,9 @@
if (!HasGlueUse) break;
}
+ if (NodeSUnit->isCall)
+ CallSUnits.push_back(NodeSUnit);
+
// Schedule zero-latency TokenFactor below any nodes that may increase the
// schedule height. Otherwise, ancestors of the TokenFactor may appear to
// have false stalls.
@@ -356,6 +361,20 @@
// Assign the Latency field of NodeSUnit using target-provided information.
ComputeLatency(NodeSUnit);
}
+
+ // Find all call operands.
+ while (!CallSUnits.empty()) {
+ SUnit *SU = CallSUnits.pop_back_val();
+ for (const SDNode *SUNode = SU->getNode(); SUNode;
+ SUNode = SUNode->getGluedNode()) {
+ if (SUNode->getOpcode() != ISD::CopyToReg)
+ continue;
+ SDNode *SrcN = SUNode->getOperand(2).getNode();
+ if (isPassiveNode(SrcN)) continue; // Not scheduled.
+ SUnit *SrcSU = &SUnits[SrcN->getNodeId()];
+ SrcSU->isCallOp = true;
+ }
+ }
}
void ScheduleDAGSDNodes::AddSchedEdges() {