[PowerPC] Enable MachinePipeliner for P9 with -ppc-enable-pipeliner

Implement necessary target hooks to enable MachinePipeliner for P9 only.
The pass is off by default, can be enabled with -ppc-enable-pipeliner for P9.

Differential Revision: https://reviews.llvm.org/D62164

llvm-svn: 363085

7 files changed, 128 insertions, 10 deletions

diff --git a/llvm/lib/Target/Hexagon/HexagonInstrInfo.cpp b/llvm/lib/Target/Hexagon/HexagonInstrInfo.cpp
index d525baa0301..a156de5ba12 100644
--- a/llvm/lib/Target/Hexagon/HexagonInstrInfo.cpp
+++ b/llvm/lib/Target/Hexagon/HexagonInstrInfo.cpp
@@ -697,11 +697,11 @@ bool HexagonInstrInfo::analyzeLoop(MachineLoop &L,
 /// Generate code to reduce the loop iteration by one and check if the loop is
 /// finished. Return the value/register of the new loop count. this function
 /// assumes the nth iteration is peeled first.
-unsigned HexagonInstrInfo::reduceLoopCount(MachineBasicBlock &MBB,
-      MachineInstr *IndVar, MachineInstr &Cmp,
-      SmallVectorImpl<MachineOperand> &Cond,
-      SmallVectorImpl<MachineInstr *> &PrevInsts,
-      unsigned Iter, unsigned MaxIter) const {
+unsigned HexagonInstrInfo::reduceLoopCount(
+    MachineBasicBlock &MBB, MachineBasicBlock &PreHeader, MachineInstr *IndVar,
+    MachineInstr &Cmp, SmallVectorImpl<MachineOperand> &Cond,
+    SmallVectorImpl<MachineInstr *> &PrevInsts, unsigned Iter,
+    unsigned MaxIter) const {
   // We expect a hardware loop currently. This means that IndVar is set
   // to null, and the compare is the ENDLOOP instruction.
   assert((!IndVar) && isEndLoopN(Cmp.getOpcode())
diff --git a/llvm/lib/Target/Hexagon/HexagonInstrInfo.h b/llvm/lib/Target/Hexagon/HexagonInstrInfo.h
index 6c4dbfedb31..e0a999d0f4c 100644
--- a/llvm/lib/Target/Hexagon/HexagonInstrInfo.h
+++ b/llvm/lib/Target/Hexagon/HexagonInstrInfo.h
@@ -139,7 +139,7 @@ public:
   /// is finished.  Return the value/register of the new loop count.  We need
   /// this function when peeling off one or more iterations of a loop. This
   /// function assumes the nth iteration is peeled first.
-  unsigned reduceLoopCount(MachineBasicBlock &MBB,
+  unsigned reduceLoopCount(MachineBasicBlock &MBB, MachineBasicBlock &PreHeader,
                            MachineInstr *IndVar, MachineInstr &Cmp,
                            SmallVectorImpl<MachineOperand> &Cond,
                            SmallVectorImpl<MachineInstr *> &PrevInsts,
diff --git a/llvm/lib/Target/PowerPC/PPCInstrInfo.cpp b/llvm/lib/Target/PowerPC/PPCInstrInfo.cpp
index 0799c4281e3..7aede06b73d 100644
--- a/llvm/lib/Target/PowerPC/PPCInstrInfo.cpp
+++ b/llvm/lib/Target/PowerPC/PPCInstrInfo.cpp
@@ -3922,3 +3922,77 @@ PPCInstrInfo::isSignOrZeroExtended(const MachineInstr &MI, bool SignExt,
   }
   return false;
 }
+
+bool PPCInstrInfo::isBDNZ(unsigned Opcode) const {
+  return (Opcode == (Subtarget.isPPC64() ? PPC::BDNZ8 : PPC::BDNZ));
+}
+
+bool PPCInstrInfo::analyzeLoop(MachineLoop &L, MachineInstr *&IndVarInst,
+                               MachineInstr *&CmpInst) const {
+  MachineBasicBlock *LoopEnd = L.getBottomBlock();
+  MachineBasicBlock::iterator I = LoopEnd->getFirstTerminator();
+  // We really "analyze" only CTR loops right now.
+  if (I != LoopEnd->end() && isBDNZ(I->getOpcode())) {
+    IndVarInst = nullptr;
+    CmpInst = &*I;
+    return false;
+  }
+  return true;
+}
+
+MachineInstr *
+PPCInstrInfo::findLoopInstr(MachineBasicBlock &PreHeader) const {
+
+  unsigned LOOPi = (Subtarget.isPPC64() ? PPC::MTCTR8loop : PPC::MTCTRloop);
+
+  // The loop set-up instruction should be in preheader
+  for (auto &I : PreHeader.instrs())
+    if (I.getOpcode() == LOOPi)
+      return &I;
+  return nullptr;
+}
+
+unsigned PPCInstrInfo::reduceLoopCount(
+    MachineBasicBlock &MBB, MachineBasicBlock &PreHeader, MachineInstr *IndVar,
+    MachineInstr &Cmp, SmallVectorImpl<MachineOperand> &Cond,
+    SmallVectorImpl<MachineInstr *> &PrevInsts, unsigned Iter,
+    unsigned MaxIter) const {
+  // We expect a hardware loop currently. This means that IndVar is set
+  // to null, and the compare is the ENDLOOP instruction.
+  assert((!IndVar) && isBDNZ(Cmp.getOpcode()) && "Expecting a CTR loop");
+  MachineFunction *MF = MBB.getParent();
+  DebugLoc DL = Cmp.getDebugLoc();
+  MachineInstr *Loop = findLoopInstr(PreHeader);
+  if (!Loop)
+    return 0;
+  unsigned LoopCountReg = Loop->getOperand(0).getReg();
+  MachineRegisterInfo &MRI = MF->getRegInfo();
+  MachineInstr *LoopCount = MRI.getUniqueVRegDef(LoopCountReg);
+
+  if (!LoopCount)
+    return 0;
+  // If the loop trip count is a compile-time value, then just change the
+  // value.
+  if (LoopCount->getOpcode() == PPC::LI8 || LoopCount->getOpcode() == PPC::LI) {
+    int64_t Offset = LoopCount->getOperand(1).getImm();
+    if (Offset <= 1) {
+      LoopCount->eraseFromParent();
+      Loop->eraseFromParent();
+      return 0;
+    }
+    LoopCount->getOperand(1).setImm(Offset - 1);
+    return Offset - 1;
+  }
+
+  // The loop trip count is a run-time value.
+  // We need to subtract one from the trip count,
+  // and insert branch later to check if we're done with the loop.
+
+  // Since BDZ/BDZ8 that we will insert will also decrease the ctr by 1,
+  // so we don't need to generate any thing here.
+  Cond.push_back(MachineOperand::CreateImm(0));
+  Cond.push_back(MachineOperand::CreateReg(
+      Subtarget.isPPC64() ? PPC::CTR8 : PPC::CTR, true));
+  return LoopCountReg;
+}
+
diff --git a/llvm/lib/Target/PowerPC/PPCInstrInfo.h b/llvm/lib/Target/PowerPC/PPCInstrInfo.h
index da34e70989d..78b04c2c1ca 100644
--- a/llvm/lib/Target/PowerPC/PPCInstrInfo.h
+++ b/llvm/lib/Target/PowerPC/PPCInstrInfo.h
@@ -457,6 +457,34 @@ public:
     }
     return Reg;
   }
+
+  /// Check \p Opcode is BDNZ (Decrement CTR and branch if it is still nonzero).
+  bool isBDNZ(unsigned Opcode) const;
+
+  /// Find the hardware loop instruction used to set-up the specified loop.
+  /// On PPC, we have two instructions used to set-up the hardware loop
+  /// (MTCTRloop, MTCTR8loop) with corresponding endloop (BDNZ, BDNZ8)
+  /// instructions to indicate the end of a loop.
+  MachineInstr *findLoopInstr(MachineBasicBlock &PreHeader) const;
+
+  /// Analyze the loop code to find the loop induction variable and compare used
+  /// to compute the number of iterations. Currently, we analyze loop that are
+  /// controlled using hardware loops.  In this case, the induction variable
+  /// instruction is null.  For all other cases, this function returns true,
+  /// which means we're unable to analyze it. \p IndVarInst and \p CmpInst will
+  /// return new values when we can analyze the readonly loop \p L, otherwise,
+  /// nothing got changed
+  bool analyzeLoop(MachineLoop &L, MachineInstr *&IndVarInst,
+                   MachineInstr *&CmpInst) const override;
+  /// Generate code to reduce the loop iteration by one and check if the loop
+  /// is finished.  Return the value/register of the new loop count.  We need
+  /// this function when peeling off one or more iterations of a loop. This
+  /// function assumes the last iteration is peeled first.
+  unsigned reduceLoopCount(MachineBasicBlock &MBB, MachineBasicBlock &PreHeader,
+                           MachineInstr *IndVar, MachineInstr &Cmp,
+                           SmallVectorImpl<MachineOperand> &Cond,
+                           SmallVectorImpl<MachineInstr *> &PrevInsts,
+                           unsigned Iter, unsigned MaxIter) const override;
 };
 
 }
diff --git a/llvm/lib/Target/PowerPC/PPCSubtarget.cpp b/llvm/lib/Target/PowerPC/PPCSubtarget.cpp
index e3bc305be7a..0d2786e8443 100644
--- a/llvm/lib/Target/PowerPC/PPCSubtarget.cpp
+++ b/llvm/lib/Target/PowerPC/PPCSubtarget.cpp
@@ -39,6 +39,11 @@ static cl::opt<bool> QPXStackUnaligned("qpx-stack-unaligned",
   cl::desc("Even when QPX is enabled the stack is not 32-byte aligned"),
   cl::Hidden);
 
+static cl::opt<bool>
+    EnableMachinePipeliner("ppc-enable-pipeliner",
+                           cl::desc("Enable Machine Pipeliner for PPC"),
+                           cl::init(false), cl::Hidden);
+
 PPCSubtarget &PPCSubtarget::initializeSubtargetDependencies(StringRef CPU,
                                                             StringRef FS) {
   initializeEnvironment();
@@ -181,10 +186,14 @@ bool PPCSubtarget::hasLazyResolverStub(const GlobalValue *GV) const {
   return false;
 }
 
-bool PPCSubtarget::enableMachineScheduler() const {
-  return true;
+bool PPCSubtarget::enableMachineScheduler() const { return true; }
+
+bool PPCSubtarget::enableMachinePipeliner() const {
+  return (DarwinDirective == PPC::DIR_PWR9) && EnableMachinePipeliner;
 }
 
+bool PPCSubtarget::useDFAforSMS() const { return false; }
+
 // This overrides the PostRAScheduler bit in the SchedModel for each CPU.
 bool PPCSubtarget::enablePostRAScheduler() const { return true; }
 
diff --git a/llvm/lib/Target/PowerPC/PPCSubtarget.h b/llvm/lib/Target/PowerPC/PPCSubtarget.h
index e1f4a9680da..a59cbd60618 100644
--- a/llvm/lib/Target/PowerPC/PPCSubtarget.h
+++ b/llvm/lib/Target/PowerPC/PPCSubtarget.h
@@ -322,9 +322,13 @@ public:
   /// but may expand the ISEL instruction later.
   bool enableEarlyIfConversion() const override { return true; }
 
-  // Scheduling customization.
+  /// Scheduling customization.
   bool enableMachineScheduler() const override;
-  // This overrides the PostRAScheduler bit in the SchedModel for each CPU.
+  /// Pipeliner customization.
+  bool enableMachinePipeliner() const override;
+  /// Machine Pipeliner customization
+  bool useDFAforSMS() const override;
+  /// This overrides the PostRAScheduler bit in the SchedModel for each CPU.
   bool enablePostRAScheduler() const override;
   AntiDepBreakMode getAntiDepBreakMode() const override;
   void getCriticalPathRCs(RegClassVector &CriticalPathRCs) const override;
diff --git a/llvm/lib/Target/PowerPC/PPCTargetMachine.cpp b/llvm/lib/Target/PowerPC/PPCTargetMachine.cpp
index da1121bac9c..fcaf7d6e3ee 100644
--- a/llvm/lib/Target/PowerPC/PPCTargetMachine.cpp
+++ b/llvm/lib/Target/PowerPC/PPCTargetMachine.cpp
@@ -488,6 +488,9 @@ void PPCPassConfig::addPreRegAlloc() {
   }
   if (EnableExtraTOCRegDeps)
     addPass(createPPCTOCRegDepsPass());
+
+  if (getOptLevel() != CodeGenOpt::None)
+    addPass(&MachinePipelinerID);
 }
 
 void PPCPassConfig::addPreSched2() {