diff --git a/llvm/include/llvm/CodeGen/MachineScheduler.h b/llvm/include/llvm/CodeGen/MachineScheduler.h
index bc00d0b4ff852..8a819051f069a 100644
--- a/llvm/include/llvm/CodeGen/MachineScheduler.h
+++ b/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,
diff --git a/llvm/lib/CodeGen/MachineScheduler.cpp b/llvm/lib/CodeGen/MachineScheduler.cpp
index 97f27277aface..579f787b0af9b 100644
--- a/llvm/lib/CodeGen/MachineScheduler.cpp
+++ b/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.
diff --git a/llvm/lib/Target/SystemZ/SystemZElimCompare.cpp b/llvm/lib/Target/SystemZ/SystemZElimCompare.cpp
index 81f0014dd83f2..149a7b2f451d5 100644
--- a/llvm/lib/Target/SystemZ/SystemZElimCompare.cpp
+++ b/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;
diff --git a/llvm/lib/Target/SystemZ/SystemZInstrInfo.cpp b/llvm/lib/Target/SystemZ/SystemZInstrInfo.cpp
index 91a4aa9c73010..54a2adcc46198 100644
--- a/llvm/lib/Target/SystemZ/SystemZInstrInfo.cpp
+++ b/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() &&
diff --git a/llvm/lib/Target/SystemZ/SystemZInstrInfo.h b/llvm/lib/Target/SystemZ/SystemZInstrInfo.h
index 8b82af61e669a..2030d52becc0e 100644
--- a/llvm/lib/Target/SystemZ/SystemZInstrInfo.h
+++ b/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
diff --git a/llvm/lib/Target/SystemZ/SystemZMachineScheduler.cpp b/llvm/lib/Target/SystemZ/SystemZMachineScheduler.cpp
index 5e2365f1dc513..85376ec70edc5 100644
--- a/llvm/lib/Target/SystemZ/SystemZMachineScheduler.cpp
+++ b/llvm/lib/Target/SystemZ/SystemZMachineScheduler.cpp
@@ -5,22 +5,421 @@
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
-//
-// -------------------------- Post RA scheduling ---------------------------- //
-// SystemZPostRASchedStrategy is a scheduling strategy which is plugged into
-// the MachineScheduler. It has a sorted Available set of SUs and a pickNode()
-// implementation that looks to optimize decoder grouping and balance the
-// usage of processor resources. Scheduler states are saved for the end
-// region of each MBB, so that a successor block can learn from it.
-//===----------------------------------------------------------------------===//
 
 #include "SystemZMachineScheduler.h"
+#include "llvm/CodeGen/LiveInterval.h"
+#include "llvm/CodeGen/LiveIntervals.h"
 #include "llvm/CodeGen/MachineLoopInfo.h"
 
 using namespace llvm;
 
 #define DEBUG_TYPE "machine-scheduler"
 
+/// Pre-RA scheduling ///
+
+static cl::opt<unsigned> TinyRegionLim(
+    "tiny-region-lim", cl::Hidden, cl::init(10),
+    cl::desc("Run limited pre-ra scheduling on regions of this size or "
+             "smaller. Mainly for testing."));
+
+static bool isRegDef(const MachineOperand &MO) {
+  return MO.isReg() && MO.isDef();
+}
+
+static bool isVirtRegDef(const MachineOperand &MO) {
+  return isRegDef(MO) && MO.getReg().isVirtual();
+}
+
+static bool isPhysRegDef(const MachineOperand &MO) {
+  return isRegDef(MO) && MO.getReg().isPhysical();
+}
+
+static bool isVirtRegUse(const MachineOperand &MO) {
+  return MO.isReg() && MO.isUse() && MO.readsReg() && MO.getReg().isVirtual();
+}
+
+void SystemZPreRASchedStrategy::initializePrioRegClasses(
+    const TargetRegisterInfo *TRI) {
+  for (const TargetRegisterClass *RC : TRI->regclasses()) {
+    for (MVT VT : MVT::fp_valuetypes())
+      if (TRI->isTypeLegalForClass(*RC, VT)) {
+        PrioRegClasses.insert(RC->getID());
+        break;
+      }
+
+    // On SystemZ vector and FP registers overlap: add any vector RC.
+    if (!PrioRegClasses.count(RC->getID()))
+      for (MVT VT : MVT::fp_fixedlen_vector_valuetypes())
+        if (TRI->isTypeLegalForClass(*RC, VT)) {
+          PrioRegClasses.insert(RC->getID());
+          break;
+        }
+  }
+}
+
+void SystemZPreRASchedStrategy::VRegSet::dump(std::string Msg) {
+  dbgs() << Msg.c_str();
+  bool First = true;
+  for (auto R : *this) {
+    if (!First)
+      dbgs() << ", ";
+    else
+      First = false;
+    dbgs() << "%" << R.virtRegIndex();
+  }
+  dbgs() << "\n";
+}
+
+unsigned SystemZPreRASchedStrategy::getRemLat(SchedBoundary *Zone) const {
+  if (RemLat == ~0U)
+    RemLat = computeRemLatency(*Zone);
+  return RemLat;
+}
+
+void SystemZPreRASchedStrategy::initializeStoresGroup() {
+  StoresGroup.clear();
+  FirstStoreInGroupScheduled = false;
+
+  unsigned CurrMaxDepth = 0;
+  for (unsigned Idx = DAG->SUnits.size() - 1; Idx + 1 != 0; --Idx) {
+    const SUnit *SU = &DAG->SUnits[Idx];
+    const MachineInstr *MI = SU->getInstr();
+    if (!MI->getNumOperands() || MI->isCopy())
+      continue;
+
+    bool HasVirtDef = false;
+    bool HasVirtUse = false;
+    for (unsigned I = 0; I < MI->getDesc().getNumOperands(); ++I) {
+      const MachineOperand &MO = MI->getOperand(I);
+      if (isVirtRegDef(MO) && !MO.isDead())
+        HasVirtDef = true;
+      else if (isVirtRegUse(MO) &&
+               MI->getDesc().operands()[I].OperandType != MCOI::OPERAND_MEMORY)
+        HasVirtUse = true;
+    }
+    bool IsStore = !HasVirtDef && HasVirtUse;
+
+    // Find a group of stores that all are at the bottom while avoiding
+    // regions with any additional group of lesser depth.
+    if (SU->getDepth() > CurrMaxDepth) {
+      CurrMaxDepth = SU->getDepth();
+      bool PrevGroup = StoresGroup.size() > 1;
+      StoresGroup.clear();
+      if (PrevGroup)
+        return;
+      if (IsStore)
+        StoresGroup.insert(SU);
+    }
+    else if (IsStore && !StoresGroup.empty() && SU->getDepth() == CurrMaxDepth) {
+      // The group members should all have the same opcode.
+      if ((*StoresGroup.begin())->getInstr()->getOpcode() != MI->getOpcode()) {
+        StoresGroup.clear();
+        return;
+      }
+      StoresGroup.insert(SU);
+    }
+  }
+
+  // Value of 8 handles a known regression (with group of 20).
+  // TODO: Would some other value be better?
+  if (StoresGroup.size() < 8)
+    StoresGroup.clear();
+}
+
+static int biasPhysRegExtra(const SUnit *SU) {
+  if (int Res = biasPhysReg(SU, /*isTop=*/false))
+    return Res;
+
+  // Also recognize Load Address of stack slot. There are (at least
+  // currently) no instructions here defining a physreg that uses a vreg.
+  const MachineInstr *MI = SU->getInstr();
+  if (MI->getNumOperands() && !MI->isCopy()) {
+    const MachineOperand &DefMO = MI->getOperand(0);
+    if (isPhysRegDef(DefMO))
+      return 1;
+  }
+
+  return 0;
+}
+
+int SystemZPreRASchedStrategy::
+computeSULivenessScore(SchedCandidate &C, ScheduleDAGMILive *DAG,
+                       SchedBoundary *Zone) const {
+  // Not all data deps are modelled around the SUnit - some data edges near
+  // boundaries are missing: Look directly at the MI operands instead.
+  const SUnit *SU = C.SU;
+  const MachineInstr *MI = SU->getInstr();
+  if (!MI->getNumOperands() || MI->isCopy())
+    return 0;
+
+  // Find uses of registers that are not already live (kills).
+  bool PrioKill = false;
+  bool GPRKill = false;
+  bool AddrKill = false;
+  bool HasPrioUse = false;
+  for (unsigned I = 0; I < MI->getDesc().getNumOperands(); ++I) {
+    const MachineOperand &MO = MI->getOperand(I);
+    if (!isVirtRegUse(MO))
+      continue;
+    HasPrioUse |= isPrioVirtReg(MO.getReg(), &DAG->MRI);
+    if (LiveRegs.count(MO.getReg()))
+      continue;
+    if (isPrioVirtReg(MO.getReg(), &DAG->MRI))
+      PrioKill = true;
+    else if (MI->getDesc().operands()[I].OperandType != MCOI::OPERAND_MEMORY)
+      GPRKill = true;
+    else
+      AddrKill = true;
+  }
+
+  // Find the interesting properties.
+  const MachineOperand &DefMO = MI->getOperand(0);
+  assert(!isPhysRegDef(DefMO) && "Did not expect physreg def!");
+  bool IsLoad =
+      isRegDef(DefMO) && !DefMO.isDead() && !IsRedefining[SU->NodeNum];
+  bool IsStore = (!isRegDef(DefMO) || DefMO.isDead());
+  // Prioritize FP: Ignore GPR/Addr kills with an FP def.
+  bool UsesLivePrio =
+      IsLoad && !PrioKill &&
+      (isPrioVirtReg(DefMO.getReg(), &DAG->MRI) || (!GPRKill && !AddrKill));
+  bool UsesLiveAll = !PrioKill && !GPRKill && !AddrKill;
+  bool PreservesSchedLat = SU->getHeight() <= Zone->getScheduledLatency();
+  const unsigned Cycles = 2;
+  unsigned Margin = SchedModel->getIssueWidth() * (Cycles + SU->Latency - 1);
+  bool HasDistToTop = NumLeft > Margin;
+
+  // Pull down a defining SU if it preserves the scheduled latency while not
+  // causing any (prioritized) register uses to become live. If however there
+  // will be relatively many SUs scheduled above this one and all uses are
+  // already live it should not be a problem to increase the scheduled
+  // latency given the OOO execution.
+  // TODO: Try schedulling small (DFSResult) subtrees as a unit.
+  bool SchedLow = IsLoad && ((PreservesSchedLat && UsesLivePrio) ||
+                             (HasDistToTop && UsesLiveAll));
+
+  // This handles regions with many chained stores of the same depth at the
+  // bottom in the input order (cactus). Push them upwards during scheduling.
+  bool SchedHigh = IsStore && FirstStoreInGroupScheduled &&
+                   StoresGroup.count(SU) &&
+                   (PrioKill || (!HasPrioUse && GPRKill));
+
+  if (SchedLow)
+    return -1;
+  if (SchedHigh)
+    return 1;
+  return 0;
+}
+
+bool SystemZPreRASchedStrategy::tryCandidate(SchedCandidate &Cand,
+                                             SchedCandidate &TryCand,
+                                             SchedBoundary *Zone) const {
+  assert(Zone && !Zone->isTop() && "Bottom-Up scheduling only.");
+
+  // Initialize the candidate if needed.
+  if (!Cand.isValid()) {
+    TryCand.Reason = FirstValid;
+    return true;
+  }
+
+  // Bias physreg defs and copies to their uses and definitions respectively.
+  int TryCandPRegBias = biasPhysRegExtra(TryCand.SU);
+  int CandPRegBias = biasPhysRegExtra(Cand.SU);
+  if (tryGreater(TryCandPRegBias, CandPRegBias, TryCand, Cand, PhysReg))
+    return TryCand.Reason != NoCand;
+  if (TryCandPRegBias && CandPRegBias) {
+    // Both biased same way.
+    tryGreater(TryCand.SU->NodeNum, Cand.SU->NodeNum, TryCand, Cand, NodeOrder);
+    return TryCand.Reason != NoCand;
+  }
+
+  if (TinyRegion) {
+    // Prioritize instructions that read unbuffered resources by stall cycles.
+    // TODO: Try this in bigger regions as well.
+    if (tryLess(Zone->getLatencyStallCycles(TryCand.SU),
+                Zone->getLatencyStallCycles(Cand.SU), TryCand, Cand, Stall))
+      return TryCand.Reason != NoCand;
+  } else {
+    // Look for an opportunity to reduce register liveness.
+    int TryCandScore = computeSULivenessScore(TryCand, DAG, Zone);
+    int CandScore = computeSULivenessScore(Cand, DAG, Zone);
+    if (tryLess(TryCandScore, CandScore, TryCand, Cand, LivenessReduce))
+      return TryCand.Reason != NoCand;
+
+    // Don't extend the scheduled latency.
+    if (ShouldReduceLatency && TryC...
[truncated]

diff --git a/llvm/lib/Target/SystemZ/SystemZMachineScheduler.cpp b/llvm/lib/Target/SystemZ/SystemZMachineScheduler.cpp
index fc47578dd..c8da1d711 100644
--- a/llvm/lib/Target/SystemZ/SystemZMachineScheduler.cpp
+++ b/llvm/lib/Target/SystemZ/SystemZMachineScheduler.cpp
@@ -331,7 +331,7 @@ bool SystemZPreRASchedStrategy::tryCandidate(SchedCandidate &Cand,
             : TryCand.SU->getHeight() < Cand.SU->getHeight() ? Cand.SU
                                                              : nullptr) {
       if (HigherSU->getHeight() > Zone->getScheduledLatency() &&
-          HigherSU->getDepth()  < getRemLat(Zone)) {
+          HigherSU->getDepth() < getRemLat(Zone)) {
         tryLess(TryCand.SU->getHeight(), Cand.SU->getHeight(), TryCand, Cand,
                 GenericSchedulerBase::BotHeightReduce);
         return TryCand.Reason != NoCand;