[AMDGPU] Add VerifyScheduling support.

[foad]

Summary

This is cut and pasted from the corresponding GenericScheduler
functions.

[vpykhtin]

LGTM.

llvm/trunk/include/llvm/CodeGen/MachineScheduler.h

 #include <memory>
 #include <string>
 #include <vector>
 
 namespace llvm {
 
 extern cl::opt<bool> ForceTopDown;
 extern cl::opt<bool> ForceBottomUp;
+extern cl::opt<bool> VerifyScheduling;
 
 class LiveIntervals;
 class MachineDominatorTree;
 class MachineFunction;
 class MachineInstr;
 class MachineLoopInfo;
 class RegisterClassInfo;
 class SchedDFSResult;

llvm/trunk/lib/CodeGen/MachineScheduler.cpp

 cl::opt<bool> ForceTopDown("misched-topdown", cl::Hidden,
                            cl::desc("Force top-down list scheduling"));
 cl::opt<bool> ForceBottomUp("misched-bottomup", cl::Hidden,
                             cl::desc("Force bottom-up list scheduling"));
 cl::opt<bool>
 DumpCriticalPathLength("misched-dcpl", cl::Hidden,
                        cl::desc("Print critical path length to stdout"));
 
+cl::opt<bool> VerifyScheduling(
+    "verify-misched", cl::Hidden,
+    cl::desc("Verify machine instrs before and after machine scheduling"));
+
 } // end namespace llvm
 
 #ifndef NDEBUG
 static cl::opt<bool> ViewMISchedDAGs("view-misched-dags", cl::Hidden,
   cl::desc("Pop up a window to show MISched dags after they are processed"));
 
 /// In some situations a few uninteresting nodes depend on nearly all other
 /// nodes in the graph, provide a cutoff to hide them.

 
 static cl::opt<bool> EnableCyclicPath("misched-cyclicpath", cl::Hidden,
   cl::desc("Enable cyclic critical path analysis."), cl::init(true));
 
 static cl::opt<bool> EnableMemOpCluster("misched-cluster", cl::Hidden,
                                         cl::desc("Enable memop clustering."),
                                         cl::init(true));
 
-static cl::opt<bool> VerifyScheduling("verify-misched", cl::Hidden,
-  cl::desc("Verify machine instrs before and after machine scheduling"));
-
 // DAG subtrees must have at least this many nodes.
 static const unsigned MinSubtreeSize = 8;
 
 // Pin the vtables to this file.
 void MachineSchedStrategy::anchor() {}
 
 void ScheduleDAGMutation::anchor() {}
 

llvm/trunk/lib/Target/AMDGPU/GCNSchedStrategy.cpp

SUnit *GCNMaxOccupancySchedStrategy::pickNodeBidirectional(bool &IsTopNode) {
   LLVM_DEBUG(dbgs() << "Picking from Bot:\n");
   if (!BotCand.isValid() || BotCand.SU->isScheduled ||
       BotCand.Policy != BotPolicy) {
     BotCand.reset(CandPolicy());
     pickNodeFromQueue(Bot, BotPolicy, DAG->getBotRPTracker(), BotCand);
     assert(BotCand.Reason != NoCand && "failed to find the first candidate");
   } else {
     LLVM_DEBUG(traceCandidate(BotCand));
+#ifndef NDEBUG
+    if (VerifyScheduling) {
+      SchedCandidate TCand;
+      TCand.reset(CandPolicy());
+      pickNodeFromQueue(Bot, BotPolicy, DAG->getBotRPTracker(), TCand);
+      assert(TCand.SU == BotCand.SU &&
+             "Last pick result should correspond to re-picking right now");
+    }
+#endif
   }
 
   // Check if the top Q has a better candidate.
   LLVM_DEBUG(dbgs() << "Picking from Top:\n");
   if (!TopCand.isValid() || TopCand.SU->isScheduled ||
       TopCand.Policy != TopPolicy) {
     TopCand.reset(CandPolicy());
     pickNodeFromQueue(Top, TopPolicy, DAG->getTopRPTracker(), TopCand);
     assert(TopCand.Reason != NoCand && "failed to find the first candidate");
   } else {
     LLVM_DEBUG(traceCandidate(TopCand));
+#ifndef NDEBUG
+    if (VerifyScheduling) {
+      SchedCandidate TCand;
+      TCand.reset(CandPolicy());
+      pickNodeFromQueue(Top, TopPolicy, DAG->getTopRPTracker(), TCand);
+      assert(TCand.SU == TopCand.SU &&
+           "Last pick result should correspond to re-picking right now");
+    }
+#endif
   }
 
   // Pick best from BotCand and TopCand.
   LLVM_DEBUG(dbgs() << "Top Cand: "; traceCandidate(TopCand);
              dbgs() << "Bot Cand: "; traceCandidate(BotCand););
   SchedCandidate Cand;
   if (TopCand.Reason == BotCand.Reason) {
     Cand = BotCand;