diff --git a/lib/Target/Mips/MipsISelLowering.cpp b/lib/Target/Mips/MipsISelLowering.cpp
index 224569b2503..1d7a1c0ae8c 100644
--- a/lib/Target/Mips/MipsISelLowering.cpp
+++ b/lib/Target/Mips/MipsISelLowering.cpp
@@ -179,11 +179,11 @@ unsigned MipsTargetLowering::getFunctionAlignment(const Function *) const {
 //  (addc multLo, Lo0), (adde multHi, Hi0),
 // where,
 //  multHi/Lo: product of multiplication
-//  Lo0: initial value of Lo register     
-//  Hi0: initial value of Hi register     
+//  Lo0: initial value of Lo register
+//  Hi0: initial value of Hi register
 // Return true if mattern matching was successful.
 static bool SelectMadd(SDNode* ADDENode, SelectionDAG* CurDAG) {
-  // ADDENode's second operand must be a flag output of an ADDC node in order 
+  // ADDENode's second operand must be a flag output of an ADDC node in order
   // for the matching to be successful.
   SDNode* ADDCNode = ADDENode->getOperand(2).getNode();
 
@@ -192,7 +192,7 @@ static bool SelectMadd(SDNode* ADDENode, SelectionDAG* CurDAG) {
 
   SDValue MultHi = ADDENode->getOperand(0);
   SDValue MultLo = ADDCNode->getOperand(0);
-  SDNode* MultNode = MultHi.getNode(); 
+  SDNode* MultNode = MultHi.getNode();
   unsigned MultOpc = MultHi.getOpcode();
 
   // MultHi and MultLo must be generated by the same node,
@@ -202,39 +202,39 @@ static bool SelectMadd(SDNode* ADDENode, SelectionDAG* CurDAG) {
   // and it must be a multiplication.
   if (MultOpc != ISD::SMUL_LOHI && MultOpc != ISD::UMUL_LOHI)
     return false;
-  
-  // MultLo amd MultHi must be the first and second output of MultNode 
-  // respectively.  
+
+  // MultLo amd MultHi must be the first and second output of MultNode
+  // respectively.
   if (MultHi.getResNo() != 1 || MultLo.getResNo() != 0)
     return false;
 
-  // Transform this to a MADD only if ADDENode and ADDCNode are the only users 
+  // Transform this to a MADD only if ADDENode and ADDCNode are the only users
   // of the values of MultNode, in which case MultNode will be removed in later
   // phases.
   // If there exist users other than ADDENode or ADDCNode, this function returns
-  // here, which will result in MultNode being mapped to a single MULT 
-  // instruction node rather than a pair of MULT and MADD instructions being 
+  // here, which will result in MultNode being mapped to a single MULT
+  // instruction node rather than a pair of MULT and MADD instructions being
   // produced.
   if (!MultHi.hasOneUse() || !MultLo.hasOneUse())
     return false;
 
-  SDValue Chain = CurDAG->getEntryNode(); 
+  SDValue Chain = CurDAG->getEntryNode();
   DebugLoc dl = ADDENode->getDebugLoc();
 
   // create MipsMAdd(u) node
   MultOpc = MultOpc == ISD::UMUL_LOHI ? MipsISD::MAddu : MipsISD::MAdd;
-  
+
   SDValue MAdd = CurDAG->getNode(MultOpc, dl,
                                  MVT::Glue,
                                  MultNode->getOperand(0),// Factor 0
                                  MultNode->getOperand(1),// Factor 1
-                                 ADDCNode->getOperand(1),// Lo0 
+                                 ADDCNode->getOperand(1),// Lo0
                                  ADDENode->getOperand(1));// Hi0
 
   // create CopyFromReg nodes
   SDValue CopyFromLo = CurDAG->getCopyFromReg(Chain, dl, Mips::LO, MVT::i32,
                                               MAdd);
-  SDValue CopyFromHi = CurDAG->getCopyFromReg(CopyFromLo.getValue(1), dl, 
+  SDValue CopyFromHi = CurDAG->getCopyFromReg(CopyFromLo.getValue(1), dl,
                                               Mips::HI, MVT::i32,
                                               CopyFromLo.getValue(2));
 
@@ -245,7 +245,7 @@ static bool SelectMadd(SDNode* ADDENode, SelectionDAG* CurDAG) {
   if (!SDValue(ADDENode, 0).use_empty())
     CurDAG->ReplaceAllUsesOfValueWith(SDValue(ADDENode, 0), CopyFromHi);
 
-  return true;  
+  return true;
 }
 
 // SelectMsub -
@@ -253,11 +253,11 @@ static bool SelectMadd(SDNode* ADDENode, SelectionDAG* CurDAG) {
 //  (addc Lo0, multLo), (sube Hi0, multHi),
 // where,
 //  multHi/Lo: product of multiplication
-//  Lo0: initial value of Lo register     
-//  Hi0: initial value of Hi register     
+//  Lo0: initial value of Lo register
+//  Hi0: initial value of Hi register
 // Return true if mattern matching was successful.
 static bool SelectMsub(SDNode* SUBENode, SelectionDAG* CurDAG) {
-  // SUBENode's second operand must be a flag output of an SUBC node in order 
+  // SUBENode's second operand must be a flag output of an SUBC node in order
   // for the matching to be successful.
   SDNode* SUBCNode = SUBENode->getOperand(2).getNode();
 
@@ -266,7 +266,7 @@ static bool SelectMsub(SDNode* SUBENode, SelectionDAG* CurDAG) {
 
   SDValue MultHi = SUBENode->getOperand(1);
   SDValue MultLo = SUBCNode->getOperand(1);
-  SDNode* MultNode = MultHi.getNode(); 
+  SDNode* MultNode = MultHi.getNode();
   unsigned MultOpc = MultHi.getOpcode();
 
   // MultHi and MultLo must be generated by the same node,
@@ -330,9 +330,9 @@ static SDValue PerformADDECombine(SDNode *N, SelectionDAG& DAG,
 
   if (Subtarget->isMips32() && SelectMadd(N, &DAG))
     return SDValue(N, 0);
-  
+
   return SDValue();
-} 		
+}
 
 static SDValue PerformSUBECombine(SDNode *N, SelectionDAG& DAG,
                                   TargetLowering::DAGCombinerInfo &DCI,
@@ -342,11 +342,11 @@ static SDValue PerformSUBECombine(SDNode *N, SelectionDAG& DAG,
 
   if (Subtarget->isMips32() && SelectMsub(N, &DAG))
     return SDValue(N, 0);
-  
-  return SDValue();
-} 		
 
-SDValue  MipsTargetLowering::PerformDAGCombine(SDNode *N, DAGCombinerInfo &DCI) 
+  return SDValue();
+}
+
+SDValue  MipsTargetLowering::PerformDAGCombine(SDNode *N, DAGCombinerInfo &DCI)
   const {
   SelectionDAG &DAG = DCI.DAG;
   unsigned opc = N->getOpcode();
@@ -842,9 +842,15 @@ static bool CC_MipsO32(unsigned ValNo, MVT ValVT,
       Mips::D6, Mips::D7
   };
 
-  unsigned Reg=0;
-  unsigned UnallocIntReg = State.getFirstUnallocated(IntRegs, IntRegsSize);
-  bool IntRegUsed = (IntRegs[UnallocIntReg] != (unsigned (Mips::A0)));
+  unsigned Reg = 0;
+  static bool IntRegUsed = false;
+
+  // This must be the first arg of the call if no regs have been allocated.
+  // Initialize IntRegUsed in that case.
+  if (IntRegs[State.getFirstUnallocated(IntRegs, IntRegsSize)] == Mips::A0 &&
+      F32Regs[State.getFirstUnallocated(F32Regs, FloatRegsSize)] == Mips::F12 &&
+      F64Regs[State.getFirstUnallocated(F64Regs, FloatRegsSize)] == Mips::D6)
+    IntRegUsed = false;
 
   // Promote i8 and i16
   if (LocVT == MVT::i8 || LocVT == MVT::i16) {
@@ -857,30 +863,48 @@ static bool CC_MipsO32(unsigned ValNo, MVT ValVT,
       LocInfo = CCValAssign::AExt;
   }
 
-  if (ValVT == MVT::i32 || (ValVT == MVT::f32 && IntRegUsed)) {
+  if (ValVT == MVT::i32) {
     Reg = State.AllocateReg(IntRegs, IntRegsSize);
     IntRegUsed = true;
-    LocVT = MVT::i32;
-  }
+  } else if (ValVT == MVT::f32) {
+    // An int reg has to be marked allocated regardless of whether or not
+    // IntRegUsed is true.
+    Reg = State.AllocateReg(IntRegs, IntRegsSize);
 
-  if (ValVT.isFloatingPoint() && !IntRegUsed) {
-    if (ValVT == MVT::f32)
-      Reg = State.AllocateReg(F32Regs, FloatRegsSize);
-    else
-      Reg = State.AllocateReg(F64Regs, FloatRegsSize);
-  }
-
-  if (ValVT == MVT::f64 && IntRegUsed) {
-    if (UnallocIntReg != IntRegsSize) {
-      // If we hit register A3 as the first not allocated, we must
-      // mark it as allocated (shadow) and use the stack instead.
-      if (IntRegs[UnallocIntReg] != (unsigned (Mips::A3)))
-        Reg = Mips::A2;
-      for (;UnallocIntReg < IntRegsSize; ++UnallocIntReg)
-        State.AllocateReg(UnallocIntReg);
+    if (IntRegUsed) {
+      if (Reg) // Int reg is available
+        LocVT = MVT::i32;
+    } else {
+      unsigned FReg = State.AllocateReg(F32Regs, FloatRegsSize);
+      if (FReg) // F32 reg is available
+        Reg = FReg;
+      else if (Reg) // No F32 regs are available, but an int reg is available.
+        LocVT = MVT::i32;
     }
-    LocVT = MVT::i32;
-  }
+  } else if (ValVT == MVT::f64) {
+    // Int regs have to be marked allocated regardless of whether or not
+    // IntRegUsed is true.
+    Reg = State.AllocateReg(IntRegs, IntRegsSize);
+    if (Reg == Mips::A1)
+      Reg = State.AllocateReg(IntRegs, IntRegsSize);
+    else if (Reg == Mips::A3)
+      Reg = 0;
+    State.AllocateReg(IntRegs, IntRegsSize);
+
+    // At this point, Reg is A0, A2 or 0, and all the unavailable integer regs
+    // are marked as allocated.
+    if (IntRegUsed) {
+      if (Reg)// if int reg is available
+        LocVT = MVT::i32;
+    } else {
+      unsigned FReg = State.AllocateReg(F64Regs, FloatRegsSize);
+      if (FReg) // F64 reg is available.
+        Reg = FReg;
+      else if (Reg) // No F64 regs are available, but an int reg is available.
+        LocVT = MVT::i32;
+    }
+  } else
+    assert(false && "cannot handle this ValVT");
 
   if (!Reg) {
     unsigned SizeInBytes = ValVT.getSizeInBits() >> 3;
diff --git a/test/CodeGen/Mips/o32-cc.ll b/test/CodeGen/Mips/o32-cc.ll
new file mode 100644
index 00000000000..3fd97ce729a
--- /dev/null
+++ b/test/CodeGen/Mips/o32-cc.ll
@@ -0,0 +1,321 @@
+; RUN: llc -march=mips -mcpu=4ke < %s | FileCheck %s
+
+; $f12, $f14
+; CHECK: ldc1 $f12, %lo($CPI0_0)($2)
+; CHECK: ldc1 $f14, %lo($CPI0_1)($3)
+define void @testlowercall0() nounwind {
+entry:
+  tail call void @f0(double 5.000000e+00, double 6.000000e+00) nounwind
+  ret void
+}
+
+declare void @f0(double, double)
+
+; $f12, $f14
+; CHECK: lwc1 $f12, %lo($CPI1_0)($2)
+; CHECK: lwc1 $f14, %lo($CPI1_1)($3)
+define void @testlowercall1() nounwind {
+entry:
+  tail call void @f1(float 8.000000e+00, float 9.000000e+00) nounwind
+  ret void
+}
+
+declare void @f1(float, float)
+
+; $f12, $f14
+; CHECK: lwc1 $f12, %lo($CPI2_0)($2)
+; CHECK: ldc1 $f14, %lo($CPI2_1)($3)
+define void @testlowercall2() nounwind {
+entry:
+  tail call void @f2(float 8.000000e+00, double 6.000000e+00) nounwind
+  ret void
+}
+
+declare void @f2(float, double)
+
+; $f12, $f14
+; CHECK: ldc1 $f12, %lo($CPI3_0)($2)
+; CHECK: lwc1 $f14, %lo($CPI3_1)($3)
+define void @testlowercall3() nounwind {
+entry:
+  tail call void @f3(double 5.000000e+00, float 9.000000e+00) nounwind
+  ret void
+}
+
+declare void @f3(double, float)
+
+; $4, $5, $6, $7
+; CHECK: addiu $4, $zero, 12
+; CHECK: addiu $5, $zero, 13
+; CHECK: addiu $6, $zero, 14
+; CHECK: addiu $7, $zero, 15
+define void @testlowercall4() nounwind {
+entry:
+  tail call void @f4(i32 12, i32 13, i32 14, i32 15) nounwind
+  ret void
+}
+
+declare void @f4(i32, i32, i32, i32)
+
+; $f12, $6, stack
+; CHECK: sw  $2, 16($sp)
+; CHECK: sw  $zero, 20($sp)
+; CHECK: ldc1 $f12, %lo($CPI5_0)($3)
+; CHECK: addiu $6, $zero, 23
+define void @testlowercall5() nounwind {
+entry:
+  tail call void @f5(double 1.500000e+01, i32 23, double 1.700000e+01) nounwind
+  ret void
+}
+
+declare void @f5(double, i32, double)
+
+; $f12, $6, $7
+; CHECK: ldc1 $f12, %lo($CPI6_0)($2)
+; CHECK: addiu $6, $zero, 33
+; CHECK: addiu $7, $zero, 24
+define void @testlowercall6() nounwind {
+entry:
+  tail call void @f6(double 2.500000e+01, i32 33, i32 24) nounwind
+  ret void
+}
+
+declare void @f6(double, i32, i32)
+
+; $f12, $5, $6
+; CHECK: lwc1 $f12, %lo($CPI7_0)($2)
+; CHECK: addiu $5, $zero, 43
+; CHECK: addiu $6, $zero, 34
+define void @testlowercall7() nounwind {
+entry:
+  tail call void @f7(float 1.800000e+01, i32 43, i32 34) nounwind
+  ret void
+}
+
+declare void @f7(float, i32, i32)
+
+; $4, $5, $6, stack
+; CHECK: sw  $2, 16($sp)
+; CHECK: sw  $zero, 20($sp)
+; CHECK: addiu $4, $zero, 22
+; CHECK: addiu $5, $zero, 53
+; CHECK: addiu $6, $zero, 44
+define void @testlowercall8() nounwind {
+entry:
+  tail call void @f8(i32 22, i32 53, i32 44, double 4.000000e+00) nounwind
+  ret void
+}
+
+declare void @f8(i32, i32, i32, double)
+
+; $4, $5, $6, $7
+; CHECK: addiu $4, $zero, 32
+; CHECK: addiu $5, $zero, 63
+; CHECK: addiu $6, $zero, 54
+; CHECK: ori $7, $2, 0
+define void @testlowercall9() nounwind {
+entry:
+  tail call void @f9(i32 32, i32 63, i32 54, float 1.100000e+01) nounwind
+  ret void
+}
+
+declare void @f9(i32, i32, i32, float)
+
+; $4, $5, ($6, $7)
+; CHECK: addiu $4, $zero, 42
+; CHECK: addiu $5, $zero, 73
+; CHECK: addiu $6, $zero, 0
+; CHECK: ori $7, $2, 0
+define void @testlowercall10() nounwind {
+entry:
+  tail call void @f10(i32 42, i32 73, double 2.700000e+01) nounwind
+  ret void
+}
+
+declare void @f10(i32, i32, double)
+
+; $4, ($6, $7)
+; CHECK: addiu $4, $zero, 52
+; CHECK: addiu $6, $zero, 0
+; CHECK: ori $7, $2, 0
+define void @testlowercall11() nounwind {
+entry:
+  tail call void @f11(i32 52, double 1.600000e+01) nounwind
+  ret void
+}
+
+declare void @f11(i32, double)
+
+; $f12, $f14, $6, $7
+; CHECK: lwc1 $f12, %lo($CPI12_0)($2)
+; CHECK: lwc1 $f14, %lo($CPI12_1)($3)
+; CHECK: ori $6, $4, 0
+; CHECK: ori $7, $5, 0
+define void @testlowercall12() nounwind {
+entry:
+  tail call void @f12(float 2.800000e+01, float 1.900000e+01, float 1.000000e+01, float 2.100000e+01) nounwind
+  ret void
+}
+
+declare void @f12(float, float, float, float)
+
+; $f12, $5, $6, $7
+; CHECK: lwc1 $f12, %lo($CPI13_0)($2)
+; CHECK: addiu $5, $zero, 83
+; CHECK: ori $6, $3, 0
+; CHECK: addiu $7, $zero, 25
+define void @testlowercall13() nounwind {
+entry:
+  tail call void @f13(float 3.800000e+01, i32 83, float 2.000000e+01, i32 25) nounwind
+  ret void
+}
+
+
+declare void @f13(float, i32, float, i32)
+
+; $f12, $f14, $7
+; CHECK: ldc1 $f12, %lo($CPI14_0)($2)
+; CHECK: lwc1 $f14, %lo($CPI14_1)($3)
+; CHECK: ori $7, $4, 0
+define void @testlowercall14() nounwind {
+entry:
+  tail call void @f14(double 3.500000e+01, float 2.900000e+01, float 3.000000e+01) nounwind
+  ret void
+}
+
+declare void @f14(double, float, float)
+
+; $f12, $f14, ($6, $7)
+; CHECK: lwc1 $f12, %lo($CPI15_0)($2)
+; CHECK: lwc1 $f14, %lo($CPI15_1)($3)
+; CHECK: addiu $6, $zero, 0
+; CHECK: ori $7, $4, 32768
+define void @testlowercall15() nounwind {
+entry:
+  tail call void @f15(float 4.800000e+01, float 3.900000e+01, double 3.700000e+01) nounwind
+  ret void
+}
+
+declare void @f15(float, float, double)
+
+; $4, $5, $6, $7
+; CHECK: addiu $4, $zero, 62
+; CHECK: ori $5, $2, 0
+; CHECK: addiu $6, $zero, 64
+; CHECK: ori $7, $3, 0
+define void @testlowercall16() nounwind {
+entry:
+  tail call void @f16(i32 62, float 4.900000e+01, i32 64, float 3.100000e+01) nounwind
+  ret void
+}
+
+declare void @f16(i32, float, i32, float)
+
+; $4, $5, $6, $7
+; CHECK: addiu $4, $zero, 72
+; CHECK: ori $5, $2, 0
+; CHECK: addiu $6, $zero, 74
+; CHECK: addiu $7, $zero, 35
+define void @testlowercall17() nounwind {
+entry:
+  tail call void @f17(i32 72, float 5.900000e+01, i32 74, i32 35) nounwind
+  ret void
+}
+
+declare void @f17(i32, float, i32, i32)
+
+; $4, $5, $6, $7
+; CHECK: addiu $4, $zero, 82
+; CHECK: addiu $5, $zero, 93
+; CHECK: ori $6, $2, 0
+; CHECK: addiu $7, $zero, 45
+define void @testlowercall18() nounwind {
+entry:
+  tail call void @f18(i32 82, i32 93, float 4.000000e+01, i32 45) nounwind
+  ret void
+}
+
+declare void @f18(i32, i32, float, i32)
+
+
+; $4, ($6, $7), stack
+; CHECK: sw  $2, 16($sp)
+; CHECK: sw  $zero, 20($sp)
+; CHECK: addiu $4, $zero, 92
+; CHECK: addiu $6, $zero, 0
+; CHECK: ori $7, $3, 0
+define void @testlowercall20() nounwind {
+entry:
+  tail call void @f20(i32 92, double 2.600000e+01, double 4.700000e+01) nounwind
+  ret void
+}
+
+declare void @f20(i32, double, double)
+
+; $f12, $5
+; CHECK: lwc1 $f12, %lo($CPI20_0)($2)
+; CHECK: addiu $5, $zero, 103
+define void @testlowercall21() nounwind {
+entry:
+  tail call void @f21(float 5.800000e+01, i32 103) nounwind
+  ret void
+}
+
+declare void @f21(float, i32)
+
+; $f12, $5, ($6, $7)
+; CHECK: lwc1 $f12, %lo($CPI21_0)($2)
+; CHECK: addiu $5, $zero, 113
+; CHECK: addiu $6, $zero, 0
+; CHECK: ori $7, $3, 32768
+define void @testlowercall22() nounwind {
+entry:
+  tail call void @f22(float 6.800000e+01, i32 113, double 5.700000e+01) nounwind
+  ret void
+}
+
+declare void @f22(float, i32, double)
+
+; $f12, f6
+; CHECK: ldc1 $f12, %lo($CPI22_0)($2)
+; CHECK: addiu $6, $zero, 123
+define void @testlowercall23() nounwind {
+entry:
+  tail call void @f23(double 4.500000e+01, i32 123) nounwind
+  ret void
+}
+
+declare void @f23(double, i32)
+
+; $f12,$6, stack
+; CHECK: sw  $2, 16($sp)
+; CHECK: sw  $zero, 20($sp)
+; CHECK: ldc1 $f12, %lo($CPI23_0)($3)
+; CHECK: addiu $6, $zero, 133
+define void @testlowercall24() nounwind {
+entry:
+  tail call void @f24(double 5.500000e+01, i32 133, double 6.700000e+01) nounwind
+  ret void
+}
+
+declare void @f24(double, i32, double)
+
+; CHECK: lwc1 $f12, %lo($CPI24_0)($2)
+; CHECK: lwc1 $f14, %lo($CPI24_1)($3)
+; CHECK: ori $6, $4, 0
+; CHECK: ori $7, $5, 0
+; CHECK: lwc1 $f12, %lo($CPI24_2)($2)
+; CHECK: addiu $5, $zero, 83
+; CHECK: ori $6, $3, 0
+; CHECK: addiu $7, $zero, 25
+; CHECK: addiu $4, $zero, 82
+; CHECK: addiu $5, $zero, 93
+; CHECK: ori $6, $2, 0
+; CHECK: addiu $7, $zero, 45
+define void @testlowercall25() nounwind {
+entry:
+  tail call void @f12(float 2.800000e+01, float 1.900000e+01, float 1.000000e+01, float 2.100000e+01) nounwind
+  tail call void @f13(float 3.800000e+01, i32 83, float 2.000000e+01, i32 25) nounwind
+  tail call void @f18(i32 82, i32 93, float 4.000000e+01, i32 45) nounwind
+  ret void
+}