IfConverter: Use TargetSchedule for instruction latencies

For targets that have instruction itineraries this means no change. Targets
that move over to the new schedule model will use be able the new schedule
module for instruction latencies in the if-converter (the logic is such that if
there is no itineary we will use the new sched model for the latencies).

Before, we queried "TTI->getInstructionLatency()" for the instruction latency
and the extra prediction cost. Now, we query the TargetSchedule abstraction for
the instruction latency and TargetInstrInfo for the extra predictation cost. The
TargetSchedule abstraction will internally call "TTI->getInstructionLatency" if
an itinerary exists, otherwise it will use the new schedule model.

ATTENTION: Out of tree targets!

(I will also send out an email later to LLVMDev)

This means, if your target implements

 unsigned getInstrLatency(const InstrItineraryData *ItinData,
                          const MachineInstr *MI,
                          unsigned *PredCost);

and returns a value for "PredCost", you now also need to implement

 unsigned getPredictationCost(const MachineInstr *MI);

(if your target uses the IfConversion.cpp pass)

radar://15077010

llvm-svn: 191671

llvm/include/llvm/CodeGen/TargetSchedule.h

@@ -152,7 +152,13 @@ public:
   /// Compute and return the expected latency of this instruction independent of
   /// a particular use. computeOperandLatency is the prefered API, but this is
   /// occasionally useful to help estimate instruction cost.
-  unsigned computeInstrLatency(const MachineInstr *MI) const;
+  ///
+  /// If UseDefaultDefLatency is false and no new machine sched model is
+  /// present this method falls back to TII->getInstrLatency with an empty
+  /// instruction itinerary (this is so we preserve the previous behavior of the
+  /// if converter after moving it to TargetSchedModel).
+  unsigned computeInstrLatency(const MachineInstr *MI,
+                               bool UseDefaultDefLatency = true) const;
 
   /// \brief Output dependency latency of a pair of defs of the same register.
   ///

llvm/include/llvm/Target/TargetInstrInfo.h

@@ -823,6 +823,8 @@ public:
                                    const MachineInstr *MI,
                                    unsigned *PredCost = 0) const;
 
+  virtual unsigned getPredicationCost(const MachineInstr *MI) const;
+
   virtual int getInstrLatency(const InstrItineraryData *ItinData,
                               SDNode *Node) const;
 

llvm/lib/CodeGen/IfConversion.cpp

@@ -22,6 +22,7 @@
 #include "llvm/CodeGen/MachineInstrBuilder.h"
 #include "llvm/CodeGen/MachineModuleInfo.h"
 #include "llvm/CodeGen/MachineRegisterInfo.h"
+#include "llvm/CodeGen/TargetSchedule.h"
 #include "llvm/MC/MCInstrItineraries.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Debug.h"
@@ -31,6 +32,8 @@
 #include "llvm/Target/TargetLowering.h"
 #include "llvm/Target/TargetMachine.h"
 #include "llvm/Target/TargetRegisterInfo.h"
+#include "llvm/Target/TargetSubtargetInfo.h"
+
 using namespace llvm;
 
 // Hidden options for help debugging.
@@ -150,11 +153,11 @@ namespace {
     /// BBAnalysis - Results of if-conversion feasibility analysis indexed by
     /// basic block number.
     std::vector<BBInfo> BBAnalysis;
+    TargetSchedModel SchedModel;
 
     const TargetLoweringBase *TLI;
     const TargetInstrInfo *TII;
     const TargetRegisterInfo *TRI;
-    const InstrItineraryData *InstrItins;
     const MachineBranchProbabilityInfo *MBPI;
     MachineRegisterInfo *MRI;
 
@@ -267,7 +270,11 @@ bool IfConverter::runOnMachineFunction(MachineFunction &MF) {
   TRI = MF.getTarget().getRegisterInfo();
   MBPI = &getAnalysis<MachineBranchProbabilityInfo>();
   MRI = &MF.getRegInfo();
-  InstrItins = MF.getTarget().getInstrItineraryData();
+
+  const TargetSubtargetInfo &ST =
+    MF.getTarget().getSubtarget<TargetSubtargetInfo>();
+  SchedModel.init(*ST.getSchedModel(), &ST, TII);
+
   if (!TII) return false;
 
   PreRegAlloc = MRI->isSSA();
@@ -672,9 +679,8 @@ void IfConverter::ScanInstructions(BBInfo &BBI) {
 
     if (!isPredicated) {
       BBI.NonPredSize++;
-      unsigned ExtraPredCost = 0;
-      unsigned NumCycles = TII->getInstrLatency(InstrItins, &*I,
-                                                &ExtraPredCost);
+      unsigned ExtraPredCost = TII->getPredicationCost(&*I);
+      unsigned NumCycles = SchedModel.computeInstrLatency(&*I, false);
       if (NumCycles > 1)
         BBI.ExtraCost += NumCycles-1;
       BBI.ExtraCost2 += ExtraPredCost;
@@ -1511,8 +1517,8 @@ void IfConverter::CopyAndPredicateBlock(BBInfo &ToBBI, BBInfo &FromBBI,
     MachineInstr *MI = MF.CloneMachineInstr(I);
     ToBBI.BB->insert(ToBBI.BB->end(), MI);
     ToBBI.NonPredSize++;
-    unsigned ExtraPredCost = 0;
-    unsigned NumCycles = TII->getInstrLatency(InstrItins, &*I, &ExtraPredCost);
+    unsigned ExtraPredCost = TII->getPredicationCost(&*I);
+    unsigned NumCycles = SchedModel.computeInstrLatency(&*I, false);
     if (NumCycles > 1)
       ToBBI.ExtraCost += NumCycles-1;
     ToBBI.ExtraCost2 += ExtraPredCost;

llvm/lib/CodeGen/TargetInstrInfo.cpp

@@ -630,6 +630,10 @@ unsigned TargetInstrInfo::defaultDefLatency(const MCSchedModel *SchedModel,
   return 1;
 }
 
+unsigned TargetInstrInfo::getPredicationCost(const MachineInstr *) const {
+  return 0;
+}
+
 unsigned TargetInstrInfo::
 getInstrLatency(const InstrItineraryData *ItinData,
                 const MachineInstr *MI,

llvm/lib/CodeGen/TargetSchedule.cpp

@@ -225,10 +225,13 @@ unsigned TargetSchedModel::computeOperandLatency(
   return DefMI->isTransient() ? 0 : TII->defaultDefLatency(&SchedModel, DefMI);
 }
 
-unsigned TargetSchedModel::computeInstrLatency(const MachineInstr *MI) const {
+unsigned
+TargetSchedModel::computeInstrLatency(const MachineInstr *MI,
+                                      bool UseDefaultDefLatency) const {
   // For the itinerary model, fall back to the old subtarget hook.
   // Allow subtargets to compute Bundle latencies outside the machine model.
-  if (hasInstrItineraries() || MI->isBundle())
+  if (hasInstrItineraries() || MI->isBundle() ||
+      (!hasInstrSchedModel() && !UseDefaultDefLatency))
     return TII->getInstrLatency(&InstrItins, MI);
 
   if (hasInstrSchedModel()) {

llvm/lib/Target/ARM/ARMBaseInstrInfo.cpp

@@ -3669,6 +3669,24 @@ ARMBaseInstrInfo::getOperandLatency(const InstrItineraryData *ItinData,
   return Latency;
 }
 
+unsigned ARMBaseInstrInfo::getPredicationCost(const MachineInstr *MI) const {
+   if (MI->isCopyLike() || MI->isInsertSubreg() ||
+      MI->isRegSequence() || MI->isImplicitDef())
+    return 0;
+
+  if (MI->isBundle())
+    return 0;
+
+  const MCInstrDesc &MCID = MI->getDesc();
+
+  if (MCID.isCall() || MCID.hasImplicitDefOfPhysReg(ARM::CPSR)) {
+    // When predicated, CPSR is an additional source operand for CPSR updating
+    // instructions, this apparently increases their latencies.
+    return 1;
+  }
+  return 0;
+}
+
 unsigned ARMBaseInstrInfo::getInstrLatency(const InstrItineraryData *ItinData,
                                            const MachineInstr *MI,
                                            unsigned *PredCost) const {

llvm/lib/Target/ARM/ARMBaseInstrInfo.h

@@ -264,6 +264,8 @@ private:
                         const MCInstrDesc &UseMCID,
                         unsigned UseIdx, unsigned UseAlign) const;
 
+  unsigned getPredicationCost(const MachineInstr *MI) const;
+
   unsigned getInstrLatency(const InstrItineraryData *ItinData,
                            const MachineInstr *MI,
                            unsigned *PredCost = 0) const;

llvm/lib/Target/R600/R600InstrInfo.cpp

@@ -989,6 +989,10 @@ R600InstrInfo::PredicateInstruction(MachineInstr *MI,
   return false;
 }
 
+unsigned int R600InstrInfo::getPredicationCost(const MachineInstr *) const {
+  return 2;
+}
+
 unsigned int R600InstrInfo::getInstrLatency(const InstrItineraryData *ItinData,
                                             const MachineInstr *MI,
                                             unsigned *PredCost) const {

llvm/lib/Target/R600/R600InstrInfo.h

@@ -181,6 +181,8 @@ namespace llvm {
   bool PredicateInstruction(MachineInstr *MI,
                         const SmallVectorImpl<MachineOperand> &Pred) const;
 
+  unsigned int getPredicationCost(const MachineInstr *) const;
+
   unsigned int getInstrLatency(const InstrItineraryData *ItinData,
                                const MachineInstr *MI,
                                unsigned *PredCost = 0) const;