REBASED

Final cleanup.
MISched0, with -misched-gprloads.
Simplified and refined.
Remove previous versions.
-tiny-region
Disable pre-ra scheduling.
Revert "Disable pre-ra scheduling."
Try TinyRegion=10 without extra checks.
Revert "Try TinyRegion=10 without extra checks."
Try TinyRegion=10 with some exclusions.
Tiny10Lat without chainpreds and hazard
Was c0f4354

Author: JonPsson

llvm/include/llvm/CodeGen/MachineScheduler.h

@@ -1087,6 +1087,7 @@ class GenericSchedulerBase : public MachineSchedStrategy {
     NoCand,
     Only1,
     PhysReg,
+    LivenessReduce,
     RegExcess,
     RegCritical,
     Stall,
@@ -1218,6 +1219,7 @@ class GenericSchedulerBase : public MachineSchedStrategy {
 };
 
 // Utility functions used by heuristics in tryCandidate().
+unsigned computeRemLatency(SchedBoundary &CurrZone);
 bool tryLess(int TryVal, int CandVal,
              GenericSchedulerBase::SchedCandidate &TryCand,
              GenericSchedulerBase::SchedCandidate &Cand,

llvm/lib/CodeGen/MachineScheduler.cpp

@@ -3168,31 +3168,6 @@ initResourceDelta(const ScheduleDAGMI *DAG,
   }
 }
 
-/// Compute remaining latency. We need this both to determine whether the
-/// overall schedule has become latency-limited and whether the instructions
-/// outside this zone are resource or latency limited.
-///
-/// The "dependent" latency is updated incrementally during scheduling as the
-/// max height/depth of scheduled nodes minus the cycles since it was
-/// scheduled:
-///   DLat = max (N.depth - (CurrCycle - N.ReadyCycle) for N in Zone
-///
-/// The "independent" latency is the max ready queue depth:
-///   ILat = max N.depth for N in Available|Pending
-///
-/// RemainingLatency is the greater of independent and dependent latency.
-///
-/// These computations are expensive, especially in DAGs with many edges, so
-/// only do them if necessary.
-static unsigned computeRemLatency(SchedBoundary &CurrZone) {
-  unsigned RemLatency = CurrZone.getDependentLatency();
-  RemLatency = std::max(RemLatency,
-                        CurrZone.findMaxLatency(CurrZone.Available.elements()));
-  RemLatency = std::max(RemLatency,
-                        CurrZone.findMaxLatency(CurrZone.Pending.elements()));
-  return RemLatency;
-}
-
 /// Returns true if the current cycle plus remaning latency is greater than
 /// the critical path in the scheduling region.
 bool GenericSchedulerBase::shouldReduceLatency(const CandPolicy &Policy,
@@ -3278,6 +3253,7 @@ const char *GenericSchedulerBase::getReasonStr(
   case NoCand:         return "NOCAND    ";
   case Only1:          return "ONLY1     ";
   case PhysReg:        return "PHYS-REG  ";
+  case LivenessReduce: return "LIVE-REDUC";
   case RegExcess:      return "REG-EXCESS";
   case RegCritical:    return "REG-CRIT  ";
   case Stall:          return "STALL     ";
@@ -3351,6 +3327,31 @@ void GenericSchedulerBase::traceCandidate(const SchedCandidate &Cand) {
 #endif
 
 namespace llvm {
+/// Compute remaining latency. We need this both to determine whether the
+/// overall schedule has become latency-limited and whether the instructions
+/// outside this zone are resource or latency limited.
+///
+/// The "dependent" latency is updated incrementally during scheduling as the
+/// max height/depth of scheduled nodes minus the cycles since it was
+/// scheduled:
+///   DLat = max (N.depth - (CurrCycle - N.ReadyCycle) for N in Zone
+///
+/// The "independent" latency is the max ready queue depth:
+///   ILat = max N.depth for N in Available|Pending
+///
+/// RemainingLatency is the greater of independent and dependent latency.
+///
+/// These computations are expensive, especially in DAGs with many edges, so
+/// only do them if necessary.
+unsigned computeRemLatency(SchedBoundary &CurrZone) {
+  unsigned RemLatency = CurrZone.getDependentLatency();
+  RemLatency = std::max(RemLatency,
+                        CurrZone.findMaxLatency(CurrZone.Available.elements()));
+  RemLatency = std::max(RemLatency,
+                        CurrZone.findMaxLatency(CurrZone.Pending.elements()));
+  return RemLatency;
+}
+
 /// Return true if this heuristic determines order.
 /// TODO: Consider refactor return type of these functions as integer or enum,
 /// as we may need to differentiate whether TryCand is better than Cand.

llvm/lib/Target/SystemZ/SystemZElimCompare.cpp

@@ -151,30 +151,6 @@ Reference SystemZElimCompare::getRegReferences(MachineInstr &MI, unsigned Reg) {
   return Ref;
 }
 
-// Return true if this is a load and test which can be optimized the
-// same way as compare instruction.
-static bool isLoadAndTestAsCmp(MachineInstr &MI) {
-  // If we during isel used a load-and-test as a compare with 0, the
-  // def operand is dead.
-  return (MI.getOpcode() == SystemZ::LTEBR ||
-          MI.getOpcode() == SystemZ::LTDBR ||
-          MI.getOpcode() == SystemZ::LTXBR) &&
-         MI.getOperand(0).isDead();
-}
-
-// Return the source register of Compare, which is the unknown value
-// being tested.
-static unsigned getCompareSourceReg(MachineInstr &Compare) {
-  unsigned reg = 0;
-  if (Compare.isCompare())
-    reg = Compare.getOperand(0).getReg();
-  else if (isLoadAndTestAsCmp(Compare))
-    reg = Compare.getOperand(1).getReg();
-  assert(reg);
-
-  return reg;
-}
-
 // Compare compares the result of MI against zero.  If MI is an addition
 // of -1 and if CCUsers is a single branch on nonzero, eliminate the addition
 // and convert the branch to a BRCT(G) or BRCTH.  Return true on success.
@@ -207,7 +183,7 @@ bool SystemZElimCompare::convertToBRCT(
   // We already know that there are no references to the register between
   // MI and Compare.  Make sure that there are also no references between
   // Compare and Branch.
-  unsigned SrcReg = getCompareSourceReg(Compare);
+  unsigned SrcReg = TII->getCompareSourceReg(Compare);
   MachineBasicBlock::iterator MBBI = Compare, MBBE = Branch;
   for (++MBBI; MBBI != MBBE; ++MBBI)
     if (getRegReferences(*MBBI, SrcReg))
@@ -254,7 +230,7 @@ bool SystemZElimCompare::convertToLoadAndTrap(
   // We already know that there are no references to the register between
   // MI and Compare.  Make sure that there are also no references between
   // Compare and Branch.
-  unsigned SrcReg = getCompareSourceReg(Compare);
+  unsigned SrcReg = TII->getCompareSourceReg(Compare);
   MachineBasicBlock::iterator MBBI = Compare, MBBE = Branch;
   for (++MBBI; MBBI != MBBE; ++MBBI)
     if (getRegReferences(*MBBI, SrcReg))
@@ -495,25 +471,17 @@ bool SystemZElimCompare::adjustCCMasksForInstr(
   return true;
 }
 
-// Return true if Compare is a comparison against zero.
-static bool isCompareZero(MachineInstr &Compare) {
-  if (isLoadAndTestAsCmp(Compare))
-    return true;
-  return Compare.getNumExplicitOperands() == 2 &&
-    Compare.getOperand(1).isImm() && Compare.getOperand(1).getImm() == 0;
-}
-
 // Try to optimize cases where comparison instruction Compare is testing
 // a value against zero.  Return true on success and if Compare should be
 // deleted as dead.  CCUsers is the list of instructions that use the CC
 // value produced by Compare.
 bool SystemZElimCompare::optimizeCompareZero(
     MachineInstr &Compare, SmallVectorImpl<MachineInstr *> &CCUsers) {
-  if (!isCompareZero(Compare))
+  if (!TII->isCompareZero(Compare))
     return false;
 
   // Search back for CC results that are based on the first operand.
-  unsigned SrcReg = getCompareSourceReg(Compare);
+  unsigned SrcReg = TII->getCompareSourceReg(Compare);
   MachineBasicBlock &MBB = *Compare.getParent();
   Reference CCRefs;
   Reference SrcRefs;
@@ -702,7 +670,7 @@ bool SystemZElimCompare::processBlock(MachineBasicBlock &MBB) {
   MachineBasicBlock::iterator MBBI = MBB.end();
   while (MBBI != MBB.begin()) {
     MachineInstr &MI = *--MBBI;
-    if (CompleteCCUsers && (MI.isCompare() || isLoadAndTestAsCmp(MI)) &&
+    if (CompleteCCUsers && (MI.isCompare() || TII->isLoadAndTestAsCmp(MI)) &&
         (optimizeCompareZero(MI, CCUsers) ||
          fuseCompareOperations(MI, CCUsers))) {
       ++MBBI;

llvm/lib/Target/SystemZ/SystemZInstrInfo.cpp

@@ -2144,6 +2144,34 @@ unsigned SystemZInstrInfo::getFusedCompare(unsigned Opcode,
   return 0;
 }
 
+bool SystemZInstrInfo::isLoadAndTestAsCmp(const MachineInstr &MI) const {
+  // If we during isel used a load-and-test as a compare with 0, the
+  // def operand is dead.
+  return (MI.getOpcode() == SystemZ::LTEBR ||
+          MI.getOpcode() == SystemZ::LTDBR ||
+          MI.getOpcode() == SystemZ::LTXBR) &&
+    MI.getOperand(0).isDead();
+}
+
+bool SystemZInstrInfo::isCompareZero(const MachineInstr &Compare) const {
+  if (isLoadAndTestAsCmp(Compare))
+    return true;
+  return Compare.isCompare() && Compare.getNumExplicitOperands() == 2 &&
+    Compare.getOperand(1).isImm() && Compare.getOperand(1).getImm() == 0;
+}
+
+unsigned SystemZInstrInfo::
+getCompareSourceReg(const MachineInstr &Compare) const {
+  unsigned reg = 0;
+  if (Compare.isCompare())
+    reg = Compare.getOperand(0).getReg();
+  else if (isLoadAndTestAsCmp(Compare))
+    reg = Compare.getOperand(1).getReg();
+  assert(reg);
+
+  return reg;
+}
+
 bool SystemZInstrInfo::
 prepareCompareSwapOperands(MachineBasicBlock::iterator const MBBI) const {
   assert(MBBI->isCompare() && MBBI->getOperand(0).isReg() &&

llvm/lib/Target/SystemZ/SystemZInstrInfo.h

@@ -356,6 +356,17 @@ class SystemZInstrInfo : public SystemZGenInstrInfo {
                            SystemZII::FusedCompareType Type,
                            const MachineInstr *MI = nullptr) const;
 
+  // Return true if this is a load and test which can be optimized the
+  // same way as compare instruction.
+  bool isLoadAndTestAsCmp(const MachineInstr &MI) const;
+
+  // Return true if Compare is a comparison against zero.
+  bool isCompareZero(const MachineInstr &Compare) const;
+
+  // Return the source register of Compare, which is the unknown value
+  // being tested.
+  unsigned getCompareSourceReg(const MachineInstr &Compare) const;
+
   // Try to find all CC users of the compare instruction (MBBI) and update
   // all of them to maintain equivalent behavior after swapping the compare
   // operands. Return false if not all users can be conclusively found and