Index: lib/Target/Mips/MipsFastISel.cpp
===================================================================
--- lib/Target/Mips/MipsFastISel.cpp
+++ lib/Target/Mips/MipsFastISel.cpp
@@ -4,6 +4,7 @@
 #include "llvm/CodeGen/FunctionLoweringInfo.h"
 #include "llvm/CodeGen/FastISel.h"
 #include "llvm/CodeGen/MachineInstrBuilder.h"
+#include "llvm/CodeGen/MachineConstantPool.h"
 #include "llvm/IR/GlobalAlias.h"
 #include "llvm/IR/GlobalVariable.h"
 #include "llvm/Target/TargetInstrInfo.h"
@@ -12,6 +13,7 @@
 #include "MipsISelLowering.h"
 #include "MipsMachineFunction.h"
 #include "MipsSubtarget.h"
+#include "MipsTargetMachine.h"
 
 using namespace llvm;
 
@@ -36,11 +38,11 @@
 
   /// Subtarget - Keep a pointer to the MipsSubtarget around so that we can
   /// make the right decision when generating code for different targets.
-  const MipsSubtarget *Subtarget;
   Module &M;
   const TargetMachine &TM;
   const TargetInstrInfo &TII;
   const TargetLowering &TLI;
+  const MipsSubtarget &Subtarget;
   MipsFunctionInfo *MFI;
 
   // Convenience variables to avoid some queries.
@@ -54,12 +56,12 @@
       : FastISel(funcInfo, libInfo),
         M(const_cast<Module &>(*funcInfo.Fn->getParent())),
         TM(funcInfo.MF->getTarget()), TII(*TM.getInstrInfo()),
-        TLI(*TM.getTargetLowering()) {
-    Subtarget = &TM.getSubtarget<MipsSubtarget>();
+        TLI(*TM.getTargetLowering()),
+        Subtarget(TM.getSubtarget<MipsSubtarget>()) {
     MFI = funcInfo.MF->getInfo<MipsFunctionInfo>();
     Context = &funcInfo.Fn->getContext();
-    TargetSupported = ((Subtarget->getRelocationModel() == Reloc::PIC_) &&
-                       (Subtarget->hasMips32r2() && (Subtarget->isABI_O32())));
+    TargetSupported = ((Subtarget.getRelocationModel() == Reloc::PIC_) &&
+                       (Subtarget.hasMips32r2() && (Subtarget.isABI_O32())));
   }
 
   bool TargetSelectInstruction(const Instruction *I) override;
@@ -70,6 +72,10 @@
 private:
   bool EmitStore(MVT VT, unsigned SrcReg, Address &Addr,
                  unsigned Alignment = 0);
+
+  bool EmitLoad(MVT VT, unsigned &ResultReg, Address &Addr,  unsigned Alignment=0, bool IsZExt = true);
+
+  bool SelectLoad(const Instruction *I);
   bool SelectRet(const Instruction *I);
   bool SelectStore(const Instruction *I);
 
@@ -80,6 +86,30 @@
   unsigned MaterializeGV(const GlobalValue *GV, MVT VT);
   unsigned MaterializeInt(const Constant *C, MVT VT);
   unsigned Materialize32BitInt(int64_t Imm, const TargetRegisterClass *RC);
+
+  unsigned FastEmitInst_riir(uint64_t inst, const TargetRegisterClass *RC,
+                             unsigned Op0, bool Op0IsKill, uint64_t imm1,
+                             uint64_t imm2, unsigned Op3, bool Op3IsKill) {
+    return 0;
+  }
+
+  MachineInstrBuilder EmitInst(unsigned Opc) {
+    return BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(Opc));
+  }
+
+  MachineInstrBuilder EmitInst(unsigned Opc, unsigned DstReg) {
+    return BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(Opc), DstReg);
+  }
+
+  MachineInstrBuilder EmitInstStore(unsigned Opc, unsigned SrcReg, unsigned MemReg , int64_t MemOffset) {
+    return EmitInst(Opc).addReg(SrcReg).addReg(MemReg).addImm(MemOffset);
+  }
+
+  MachineInstrBuilder EmitInstLoadMem(unsigned Opc, unsigned DstReg, unsigned MemReg , int64_t MemOffset) {
+    return EmitInst(Opc, DstReg).addReg(MemReg).addImm(MemOffset);
+  }
+
+#include "MipsGenFastISel.inc"
 };
 
 bool MipsFastISel::isTypeLegal(Type *Ty, MVT &VT) {
@@ -100,6 +130,8 @@
   // We will extend this in a later patch:
   //   If this is a type than can be sign or zero-extended to a basic operation
   //   go ahead and accept it now.
+  if (VT == MVT::i8 || VT == MVT::i16)
+    return true;
   return false;
 }
 
@@ -136,17 +168,93 @@
   return 0;
 }
 
+bool MipsFastISel::EmitLoad(MVT VT, unsigned &ResultReg, Address &Addr, unsigned Alignment, bool IsZExt) {
+  //
+  // more cases will be handled here in following patches.
+  //
+  if (!IsZExt)
+    return false; // this is not needed yet.
+  unsigned Opc;
+  switch (VT.SimpleTy) {
+  case MVT::i32: {
+    ResultReg = createResultReg(&Mips::GPR32RegClass);
+    Opc = Mips::LW;
+    break;
+    }
+  case MVT::i16: {
+    ResultReg = createResultReg(&Mips::GPR32RegClass);
+    Opc = Mips::LH;
+    break;
+  }
+  case MVT::i8: {
+    ResultReg = createResultReg(&Mips::GPR32RegClass);
+    Opc = Mips::LB;
+    break;
+  }
+  case MVT::f32: {
+    ResultReg = createResultReg(&Mips::FGR32RegClass);
+    Opc = Mips::LWC1;
+    break;
+  }
+  case MVT::f64: {
+    ResultReg = createResultReg(&Mips::FGR32RegClass);
+    Opc = Mips::LDC1;
+    break;
+  }
+  default:
+    return false;
+  }
+  EmitInstLoadMem(Opc, ResultReg, Addr.Base.Reg, Addr.Offset);
+  return true;
+}
+
 bool MipsFastISel::EmitStore(MVT VT, unsigned SrcReg, Address &Addr,
                              unsigned Alignment) {
   //
   // more cases will be handled here in following patches.
   //
-  if (VT != MVT::i32)
+  unsigned Opc;
+  switch (VT.SimpleTy) {
+  case MVT::i8:
+    Opc=Mips::SB;
+    break;
+  case MVT::i16:
+    Opc=Mips::SH;
+    break;
+  case MVT::i32:
+    Opc=Mips::SW;
+    break;
+  case MVT::f32:
+    Opc=Mips::SWC1;
+    break;
+  case MVT::f64:
+    Opc=Mips::SDC1;
+    break;
+  default:
     return false;
-  BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(Mips::SW))
-      .addReg(SrcReg)
-      .addReg(Addr.Base.Reg)
-      .addImm(Addr.Offset);
+  }
+  EmitInstStore(Opc, SrcReg, Addr.Base.Reg, Addr.Offset);
+  return true;
+}
+
+bool MipsFastISel::SelectLoad(const Instruction *I) {
+  // Atomic loads need special handling.
+  if (cast<LoadInst>(I)->isAtomic())
+    return false;
+
+  // Verify we have a legal type before going any further.
+  MVT VT;
+  if (!isLoadTypeLegal(I->getType(), VT))
+    return false;
+
+  // See if we can handle this address.
+  Address Addr;
+  if (!ComputeAddress(I->getOperand(0), Addr)) return false;
+
+  unsigned ResultReg;
+  if (!EmitLoad(VT, ResultReg, Addr, cast<LoadInst>(I)->getAlignment()))
+    return false;
+  UpdateValueMap(I, ResultReg);
   return true;
 }
 
@@ -186,8 +294,7 @@
   if (Ret->getNumOperands() > 0) {
     return false;
   }
-  unsigned RetOpc = Mips::RetRA;
-  BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(RetOpc));
+  EmitInst(Mips::RetRA);
   return true;
 }
 
@@ -197,6 +304,8 @@
   switch (I->getOpcode()) {
   default:
     break;
+  case Instruction::Load:
+    return SelectLoad(I);
   case Instruction::Store:
     return SelectStore(I);
   case Instruction::Ret:
@@ -207,6 +316,22 @@
 }
 
 unsigned MipsFastISel::MaterializeFP(const ConstantFP *CFP, MVT VT) {
+  int64_t Imm = CFP->getValueAPF().bitcastToAPInt().getZExtValue();
+  if (VT == MVT::f32) {
+    const TargetRegisterClass *RC = &Mips::FGR32RegClass;
+    unsigned DestReg = createResultReg(RC);
+    unsigned TempReg = Materialize32BitInt(Imm, &Mips::GPR32RegClass);
+    EmitInst(Mips::MTC1, DestReg).addReg(TempReg);
+    return DestReg;
+  } else if (VT == MVT::f64) {
+    const TargetRegisterClass *RC = &Mips::AFGR64RegClass;
+    unsigned DestReg = createResultReg(RC);
+    unsigned TempReg1 = Materialize32BitInt(Imm >> 32, &Mips::GPR32RegClass);
+    unsigned TempReg2 =
+        Materialize32BitInt(Imm & 0xFFFFFFFF, &Mips::GPR32RegClass);
+    EmitInst(Mips::BuildPairF64, DestReg).addReg(TempReg2).addReg(TempReg1);
+    return DestReg;
+  }
   return 0;
 }
 
@@ -221,8 +346,7 @@
   // TLS not supported at this time.
   if (IsThreadLocal)
     return 0;
-  BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(Mips::LW), DestReg)
-      .addReg(MFI->getGlobalBaseReg())
+  EmitInst(Mips::LW, DestReg).addReg(MFI->getGlobalBaseReg())
       .addGlobalAddress(GV, 0, MipsII::MO_GOT);
   return DestReg;
 }
@@ -245,15 +369,10 @@
 
   if (isInt<16>(Imm)) {
     unsigned Opc = Mips::ADDiu;
-    BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(Opc), ResultReg)
-        .addReg(Mips::ZERO)
-        .addImm(Imm);
+    EmitInst(Opc, ResultReg).addReg(Mips::ZERO).addImm(Imm);
     return ResultReg;
   } else if (isUInt<16>(Imm)) {
-    BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(Mips::ORi),
-            ResultReg)
-        .addReg(Mips::ZERO)
-        .addImm(Imm);
+    EmitInst(Mips::ORi, ResultReg).addReg(Mips::ZERO).addImm(Imm);
     return ResultReg;
   }
   unsigned Lo = Imm & 0xFFFF;
@@ -261,16 +380,11 @@
   if (Lo) {
     // Both Lo and Hi have nonzero bits.
     unsigned TmpReg = createResultReg(RC);
-    BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(Mips::LUi),
-            TmpReg).addImm(Hi);
-    BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(Mips::ORi),
-            ResultReg)
-        .addReg(TmpReg)
-        .addImm(Lo);
+    EmitInst(Mips::LUi, TmpReg).addImm(Hi);
+    EmitInst(Mips::ORi, ResultReg).addReg(TmpReg).addImm(Lo);
 
   } else {
-    BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(Mips::LUi),
-            ResultReg).addImm(Hi);
+    EmitInst(Mips::LUi, ResultReg).addImm(Hi);
   }
   return ResultReg;
 }
Index: test/CodeGen/Mips/Fast-ISel/loadstore2.ll
===================================================================
--- /dev/null
+++ test/CodeGen/Mips/Fast-ISel/loadstore2.ll
@@ -0,0 +1,84 @@
+; ModuleID = 'loadstore2.c'
+target datalayout = "E-m:m-p:32:32-i8:8:32-i16:16:32-i64:64-n32-S64"
+target triple = "mips--linux-gnu"
+
+@c2 = common global i8 0, align 1
+@c1 = common global i8 0, align 1
+; RUN: llc -march=mipsel -relocation-model=pic -O0 -mips-fast-isel -fast-isel-abort -mcpu=mips32r2 \
+; RUN:     < %s | FileCheck %s
+
+@s2 = common global i16 0, align 2
+@s1 = common global i16 0, align 2
+@i2 = common global i32 0, align 4
+@i1 = common global i32 0, align 4
+@f2 = common global float 0.000000e+00, align 4
+@f1 = common global float 0.000000e+00, align 4
+@d2 = common global double 0.000000e+00, align 8
+@d1 = common global double 0.000000e+00, align 8
+
+; Function Attrs: nounwind
+define void @cfoo() #0 {
+entry:
+  %0 = load i8* @c2, align 1
+  store i8 %0, i8* @c1, align 1
+; CHECK:	.ent	cfoo
+; CHECK:	lb	${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:	sb	${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:	.end	cfoo
+
+  ret void
+}
+
+; Function Attrs: nounwind
+define void @sfoo() #0 {
+entry:
+  %0 = load i16* @s2, align 2
+  store i16 %0, i16* @s1, align 2
+; CHECK:	.ent	sfoo
+; CHECK:	lh	${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:	sh	${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:	.end	sfoo
+  ret void
+}
+
+; Function Attrs: nounwind
+define void @ifoo() #0 {
+entry:
+  %0 = load i32* @i2, align 4
+  store i32 %0, i32* @i1, align 4
+; CHECK:	.ent	ifoo
+; CHECK:	lw	${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:	sw	${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:	.end	ifoo
+
+  ret void
+}
+
+; Function Attrs: nounwind
+define void @ffoo() #0 {
+entry:
+  %0 = load float* @f2, align 4
+  store float %0, float* @f1, align 4
+; CHECK:	.ent	ffoo
+; CHECK:	lwc1	$f{{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:	swc1	$f{{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:	.end	ffoo
+
+  ret void
+}
+
+; Function Attrs: nounwind
+define void @dfoo() #0 {
+entry:
+  %0 = load double* @d2, align 8
+  store double %0, double* @d1, align 8
+; CHECK:        .ent    dfoo
+; CHECK:        ldc1    $f{{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:        sdc1    $f{{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:        .end    dfoo
+  ret void
+}
+
+attributes #0 = { nounwind "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
+
+
Index: test/CodeGen/Mips/Fast-ISel/simplestorefp1.ll
===================================================================
--- /dev/null
+++ test/CodeGen/Mips/Fast-ISel/simplestorefp1.ll
@@ -0,0 +1,39 @@
+; RUN: llc -march=mipsel -relocation-model=pic -O0 -mips-fast-isel -fast-isel-abort -mcpu=mips32r2 \
+; RUN:     < %s | FileCheck %s
+
+@f = common global float 0.000000e+00, align 4
+@de = common global double 0.000000e+00, align 8
+
+; Function Attrs: nounwind
+define void @f1() #0 {
+entry:
+  store float 0x3FFA76C8C0000000, float* @f, align 4
+  ret void
+; CHECK:	.ent	f1
+; CHECK:	lui	$[[REG1:[0-9]+]], 16339
+; CHECK:	ori	$[[REG2:[0-9]+]], $[[REG1]], 46662
+; CHECK:	mtc1	$[[REG2]], $f[[REG3:[0-9]+]]
+; CHECK:	lw	$[[REG4:[0-9]+]], %got(f)(${{[0-9]+}})
+; CHECK:	swc1	$f[[REG3]], 0($[[REG4]])
+; CHECK: 	.end	f1
+
+}
+
+; Function Attrs: nounwind
+define void @d1() #0 {
+entry:
+  store double 1.234567e+00, double* @de, align 8
+; CHECK:	.ent	d1
+; CHECK:	lui	$[[REG1a:[0-9]+]], 16371
+; CHECK:	ori	$[[REG2a:[0-9]+]], $[[REG1a]], 49353
+; CHECK:	lui	$[[REG1b:[0-9]+]], 21403
+; CHECK:	ori	$[[REG2b:[0-9]+]], $[[REG1b]], 34951
+; CHECK:	mtc1	$[[REG2b]], $f[[REG3b:[0-9]+]]
+; CHECK:	mtc1	$[[REG2a]], $f[[REG3a:[0-9]+]]
+; CHECK:	sdc1	$f[[REG3b]], 0(${{[0-9]+}})
+; CHECK:	.end	d1
+  ret void
+}
+
+attributes #0 = { nounwind "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
+