Add early if-conversion support to X86.

Implement the TII hooks needed by EarlyIfConversion to create cmov
instructions and estimate their latency.

Early if-conversion is still not enabled by default.

llvm-svn: 159695

lib/Target/X86/X86InstrInfo.cpp

@@ -2295,6 +2295,37 @@ X86::CondCode X86::GetOppositeBranchCondition(X86::CondCode CC) {
   }
 }
 
+/// getCMovFromCond - Return a cmov(rr) opcode for the given condition and
+/// register size in bytes.
+static unsigned getCMovFromCond(X86::CondCode CC, unsigned RegBytes) {
+  static const unsigned Opc[16][3] = {
+    { X86::CMOVA16rr,  X86::CMOVA32rr,  X86::CMOVA64rr  },
+    { X86::CMOVAE16rr, X86::CMOVAE32rr, X86::CMOVAE64rr },
+    { X86::CMOVB16rr,  X86::CMOVB32rr,  X86::CMOVB64rr  },
+    { X86::CMOVBE16rr, X86::CMOVBE32rr, X86::CMOVBE64rr },
+    { X86::CMOVE16rr,  X86::CMOVE32rr,  X86::CMOVE64rr  },
+    { X86::CMOVG16rr,  X86::CMOVG32rr,  X86::CMOVG64rr  },
+    { X86::CMOVGE16rr, X86::CMOVGE32rr, X86::CMOVGE64rr },
+    { X86::CMOVL16rr,  X86::CMOVL32rr,  X86::CMOVL64rr  },
+    { X86::CMOVLE16rr, X86::CMOVLE32rr, X86::CMOVLE64rr },
+    { X86::CMOVNE16rr, X86::CMOVNE32rr, X86::CMOVNE64rr },
+    { X86::CMOVNO16rr, X86::CMOVNO32rr, X86::CMOVNO64rr },
+    { X86::CMOVNP16rr, X86::CMOVNP32rr, X86::CMOVNP64rr },
+    { X86::CMOVNS16rr, X86::CMOVNS32rr, X86::CMOVNS64rr },
+    { X86::CMOVO16rr,  X86::CMOVO32rr,  X86::CMOVO64rr  },
+    { X86::CMOVP16rr,  X86::CMOVP32rr,  X86::CMOVP64rr  },
+    { X86::CMOVS16rr,  X86::CMOVS32rr,  X86::CMOVS64rr  }
+  };
+
+  assert(CC < 16 && "Can only handle standard cond codes");
+  switch(RegBytes) {
+  default: llvm_unreachable("Illegal register size!");
+  case 2: return Opc[CC][0];
+  case 4: return Opc[CC][1];
+  case 8: return Opc[CC][2];
+  }
+}
+
 bool X86InstrInfo::isUnpredicatedTerminator(const MachineInstr *MI) const {
   if (!MI->isTerminator()) return false;
 
@@ -2519,6 +2550,55 @@ X86InstrInfo::InsertBranch(MachineBasicBlock &MBB, MachineBasicBlock *TBB,
   return Count;
 }
 
+bool X86InstrInfo::
+canInsertSelect(const MachineBasicBlock &MBB,
+                const SmallVectorImpl<MachineOperand> &Cond,
+                unsigned TrueReg, unsigned FalseReg,
+                int &CondCycles, int &TrueCycles, int &FalseCycles) const {
+  // Not all subtargets have cmov instructions.
+  if (!TM.getSubtarget<X86Subtarget>().hasCMov())
+    return false;
+  if (Cond.size() != 1)
+    return false;
+  // We cannot do the composite conditions, at least not in SSA form.
+  if ((X86::CondCode)Cond[0].getImm() > X86::COND_S)
+    return false;
+
+  // Check register classes.
+  const MachineRegisterInfo &MRI = MBB.getParent()->getRegInfo();
+  const TargetRegisterClass *RC =
+    RI.getCommonSubClass(MRI.getRegClass(TrueReg), MRI.getRegClass(FalseReg));
+  if (!RC)
+    return false;
+
+  // We have cmov instructions for 16, 32, and 64 bit general purpose registers.
+  if (X86::GR16RegClass.hasSubClassEq(RC) ||
+      X86::GR32RegClass.hasSubClassEq(RC) ||
+      X86::GR64RegClass.hasSubClassEq(RC)) {
+    // This latency applies to Pentium M, Merom, Wolfdale, Nehalem, and Sandy
+    // Bridge. Probably Ivy Bridge as well.
+    CondCycles = 2;
+    TrueCycles = 2;
+    FalseCycles = 2;
+    return true;
+  }
+
+  // Can't do vectors.
+  return false;
+}
+
+void X86InstrInfo::insertSelect(MachineBasicBlock &MBB,
+                                MachineBasicBlock::iterator I, DebugLoc DL,
+                                unsigned DstReg,
+                                const SmallVectorImpl<MachineOperand> &Cond,
+                                unsigned TrueReg, unsigned FalseReg) const {
+   MachineRegisterInfo &MRI = MBB.getParent()->getRegInfo();
+   assert(Cond.size() == 1 && "Invalid Cond array");
+   unsigned Opc = getCMovFromCond((X86::CondCode)Cond[0].getImm(),
+                                  MRI.getRegClass(DstReg)->getSize());
+   BuildMI(MBB, I, DL, get(Opc), DstReg).addReg(FalseReg).addReg(TrueReg);
+}
+
 /// isHReg - Test if the given register is a physical h register.
 static bool isHReg(unsigned Reg) {
   return X86::GR8_ABCD_HRegClass.contains(Reg);

lib/Target/X86/X86InstrInfo.h

@@ -219,6 +219,14 @@ public:
                                 MachineBasicBlock *FBB,
                                 const SmallVectorImpl<MachineOperand> &Cond,
                                 DebugLoc DL) const;
+  virtual bool canInsertSelect(const MachineBasicBlock&,
+                               const SmallVectorImpl<MachineOperand> &Cond,
+                               unsigned, unsigned, int&, int&, int&) const;
+  virtual void insertSelect(MachineBasicBlock &MBB,
+                            MachineBasicBlock::iterator MI, DebugLoc DL,
+                            unsigned DstReg,
+                            const SmallVectorImpl<MachineOperand> &Cond,
+                            unsigned TrueReg, unsigned FalseReg) const;
   virtual void copyPhysReg(MachineBasicBlock &MBB,
                            MachineBasicBlock::iterator MI, DebugLoc DL,
                            unsigned DestReg, unsigned SrcReg,

lib/Target/X86/X86TargetMachine.cpp

@@ -140,7 +140,12 @@ public:
 } // namespace
 
 TargetPassConfig *X86TargetMachine::createPassConfig(PassManagerBase &PM) {
-  return new X86PassConfig(this, PM);
+  X86PassConfig *PC = new X86PassConfig(this, PM);
+
+  if (Subtarget.hasCMov())
+    PC->enablePass(&EarlyIfConverterID);
+
+  return PC;
 }
 
 bool X86PassConfig::addInstSelector() {

test/CodeGen/X86/early-ifcvt.ll

@@ -0,0 +1,39 @@
+; RUN: llc < %s -enable-early-ifcvt -stress-early-ifcvt | FileCheck %s
+target triple = "x86_64-apple-macosx10.8.0"
+
+; CHECK: mm2
+define i32 @mm2(i32* nocapture %p, i32 %n) nounwind uwtable readonly ssp {
+entry:
+  br label %do.body
+
+; CHECK: do.body
+; Loop body has no branches before the backedge.
+; CHECK-NOT: LBB
+do.body:
+  %max.0 = phi i32 [ 0, %entry ], [ %max.1, %do.cond ]
+  %min.0 = phi i32 [ 0, %entry ], [ %min.1, %do.cond ]
+  %n.addr.0 = phi i32 [ %n, %entry ], [ %dec, %do.cond ]
+  %p.addr.0 = phi i32* [ %p, %entry ], [ %incdec.ptr, %do.cond ]
+  %incdec.ptr = getelementptr inbounds i32* %p.addr.0, i64 1
+  %0 = load i32* %p.addr.0, align 4
+  %cmp = icmp sgt i32 %0, %max.0
+  br i1 %cmp, label %do.cond, label %if.else
+
+if.else:
+  %cmp1 = icmp slt i32 %0, %min.0
+  %.min.0 = select i1 %cmp1, i32 %0, i32 %min.0
+  br label %do.cond
+
+do.cond:
+  %max.1 = phi i32 [ %0, %do.body ], [ %max.0, %if.else ]
+  %min.1 = phi i32 [ %min.0, %do.body ], [ %.min.0, %if.else ]
+; CHECK: decl %esi
+; CHECK: jne LBB
+  %dec = add i32 %n.addr.0, -1
+  %tobool = icmp eq i32 %dec, 0
+  br i1 %tobool, label %do.end, label %do.body
+
+do.end:
+  %sub = sub nsw i32 %max.1, %min.1
+  ret i32 %sub
+}