[MachineCombiner] Support local strategy for traces

For in-order cores MachineCombiner makes better decisions when the critical path
is calculated only for the current basic block and does not take into account
other blocks from the trace.

This patch adds a virtual method to TargetInstrInfo to allow each target decide
which strategy to use.

Depends on D140541

Reviewed By: spatel

Differential Revision: https://reviews.llvm.org/D140542

1 files changed, 10 insertions, 5 deletions

diff --git a/llvm/lib/CodeGen/MachineCombiner.cpp b/llvm/lib/CodeGen/MachineCombiner.cpp
index 1ae558b..fd02d1b 100644
--- a/llvm/lib/CodeGen/MachineCombiner.cpp
+++ b/llvm/lib/CodeGen/MachineCombiner.cpp
@@ -95,7 +95,8 @@ private:
   bool isTransientMI(const MachineInstr *MI);
   unsigned getDepth(SmallVectorImpl<MachineInstr *> &InsInstrs,
                     DenseMap<unsigned, unsigned> &InstrIdxForVirtReg,
-                    MachineTraceMetrics::Trace BlockTrace);
+                    MachineTraceMetrics::Trace BlockTrace,
+                    const MachineBasicBlock &MBB);
   unsigned getLatency(MachineInstr *Root, MachineInstr *NewRoot,
                       MachineTraceMetrics::Trace BlockTrace);
   bool
@@ -207,7 +208,8 @@ bool MachineCombiner::isTransientMI(const MachineInstr *MI) {
 unsigned
 MachineCombiner::getDepth(SmallVectorImpl<MachineInstr *> &InsInstrs,
                           DenseMap<unsigned, unsigned> &InstrIdxForVirtReg,
-                          MachineTraceMetrics::Trace BlockTrace) {
+                          MachineTraceMetrics::Trace BlockTrace,
+                          const MachineBasicBlock &MBB) {
   SmallVector<unsigned, 16> InstrDepth;
   // For each instruction in the new sequence compute the depth based on the
   // operands. Use the trace information when possible. For new operands which
@@ -237,7 +239,9 @@ MachineCombiner::getDepth(SmallVectorImpl<MachineInstr *> &InsInstrs,
                                                       InstrPtr, UseIdx);
       } else {
         MachineInstr *DefInstr = getOperandDef(MO);
-        if (DefInstr) {
+        if (DefInstr && (TII->getMachineCombinerTraceStrategy() !=
+                             MachineTraceStrategy::TS_Local ||
+                         DefInstr->getParent() == &MBB)) {
           DepthOp = BlockTrace.getInstrCycles(*DefInstr).Depth;
           if (!isTransientMI(DefInstr))
             LatencyOp = TSchedModel.computeOperandLatency(
@@ -374,7 +378,8 @@ bool MachineCombiner::improvesCriticalPathLen(
     MachineCombinerPattern Pattern,
     bool SlackIsAccurate) {
   // Get depth and latency of NewRoot and Root.
-  unsigned NewRootDepth = getDepth(InsInstrs, InstrIdxForVirtReg, BlockTrace);
+  unsigned NewRootDepth =
+      getDepth(InsInstrs, InstrIdxForVirtReg, BlockTrace, *MBB);
   unsigned RootDepth = BlockTrace.getInstrCycles(*Root).Depth;
 
   LLVM_DEBUG(dbgs() << "  Dependence data for " << *Root << "\tNewRootDepth: "
@@ -574,7 +579,7 @@ bool MachineCombiner::combineInstructions(MachineBasicBlock *MBB) {
   // Check if the block is in a loop.
   const MachineLoop *ML = MLI->getLoopFor(MBB);
   if (!TraceEnsemble)
-    TraceEnsemble = Traces->getEnsemble(MachineTraceStrategy::TS_MinInstrCount);
+    TraceEnsemble = Traces->getEnsemble(TII->getMachineCombinerTraceStrategy());
 
   SparseSet<LiveRegUnit> RegUnits;
   RegUnits.setUniverse(TRI->getNumRegUnits());