Index: lib/Target/AArch64/AArch64CallingConvention.td
===================================================================
--- lib/Target/AArch64/AArch64CallingConvention.td
+++ lib/Target/AArch64/AArch64CallingConvention.td
@@ -118,6 +118,13 @@
       CCAssignToReg<[Q0, Q1, Q2, Q3, Q4, Q5, Q6, Q7]>>
 ]>;
 
+// Vararg functions on windows pass floats in integer registers
+def CC_AArch64_Win64_VarArg : CallingConv<[
+  CCIfType<[f16, f32],    CCPromoteToType<f64>>,
+  CCIfType<[f64], CCBitConvertToType<i64>>,
+  CCDelegateTo<CC_AArch64_AAPCS>
+]>;
+
 
 // Darwin uses a calling convention which differs in only two ways
 // from the standard one at this level:
Index: lib/Target/AArch64/AArch64FastISel.cpp
===================================================================
--- lib/Target/AArch64/AArch64FastISel.cpp
+++ lib/Target/AArch64/AArch64FastISel.cpp
@@ -5138,6 +5138,7 @@
   return selectOperator(I, I->getOpcode());
   // Silence warnings.
   (void)&CC_AArch64_DarwinPCS_VarArg;
+  (void)&CC_AArch64_Win64_VarArg;
 }
 
 namespace llvm {
Index: lib/Target/AArch64/AArch64FrameLowering.cpp
===================================================================
--- lib/Target/AArch64/AArch64FrameLowering.cpp
+++ lib/Target/AArch64/AArch64FrameLowering.cpp
@@ -41,6 +41,10 @@
 // |                                   |
 // |-----------------------------------|
 // |                                   |
+// | (Win64 only) varargs from reg     |
+// |                                   |
+// |-----------------------------------|
+// |                                   |
 // | prev_fp, prev_lr                  |
 // | (a.k.a. "frame record")           |
 // |-----------------------------------| <- fp(=x29)
@@ -463,6 +467,7 @@
   AArch64FunctionInfo *AFI = MF.getInfo<AArch64FunctionInfo>();
   bool needsFrameMoves = MMI.hasDebugInfo() || Fn->needsUnwindTableEntry();
   bool HasFP = hasFP(MF);
+  unsigned GPRSaveSize = alignTo(AFI->getVarArgsGPRSize(), 16);
 
   // Debug location must be unknown since the first debug location is used
   // to determine the end of the prologue.
@@ -473,6 +478,10 @@
   if (MF.getFunction()->getCallingConv() == CallingConv::GHC)
     return;
 
+  if (GPRSaveSize && Subtarget.isTargetWindows())
+    emitFrameOffset(MBB, MBBI, DL, AArch64::SP, AArch64::SP, -GPRSaveSize, TII,
+                    MachineInstr::FrameSetup);
+
   int NumBytes = (int)MFI.getStackSize();
   if (!AFI->hasStackFrame()) {
     assert(!HasFP && "unexpected function without stack frame but with FP");
@@ -728,6 +737,9 @@
     ArgumentPopSize = AFI->getArgumentStackToRestore();
   }
 
+  if (Subtarget.isTargetWindows())
+    ArgumentPopSize += alignTo(AFI->getVarArgsGPRSize(), 16);
+
   // The stack frame should be like below,
   //
   //      ----------------------                     ---
Index: lib/Target/AArch64/AArch64ISelLowering.h
===================================================================
--- lib/Target/AArch64/AArch64ISelLowering.h
+++ lib/Target/AArch64/AArch64ISelLowering.h
@@ -541,6 +541,7 @@
   SDValue LowerBlockAddress(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerAAPCS_VASTART(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerDarwin_VASTART(SDValue Op, SelectionDAG &DAG) const;
+  SDValue LowerWin64_VASTART(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerVASTART(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerVACOPY(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerVAARG(SDValue Op, SelectionDAG &DAG) const;
Index: lib/Target/AArch64/AArch64ISelLowering.cpp
===================================================================
--- lib/Target/AArch64/AArch64ISelLowering.cpp
+++ lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -2650,6 +2650,8 @@
   case CallingConv::PreserveMost:
   case CallingConv::CXX_FAST_TLS:
   case CallingConv::Swift:
+    if (Subtarget->isTargetWindows() && IsVarArg)
+      return CC_AArch64_Win64_VarArg;
     if (!Subtarget->isTargetDarwin())
       return CC_AArch64_AAPCS;
     return IsVarArg ? CC_AArch64_DarwinPCS_VarArg : CC_AArch64_DarwinPCS;
@@ -2828,6 +2830,8 @@
       // The AAPCS variadic function ABI is identical to the non-variadic
       // one. As a result there may be more arguments in registers and we should
       // save them for future reference.
+      // For Win64 variadic functions, all float arguments are passed in integer
+      // registers.
       saveVarArgRegisters(CCInfo, DAG, DL, Chain);
     }
 
@@ -2881,7 +2885,10 @@
   unsigned GPRSaveSize = 8 * (NumGPRArgRegs - FirstVariadicGPR);
   int GPRIdx = 0;
   if (GPRSaveSize != 0) {
-    GPRIdx = MFI.CreateStackObject(GPRSaveSize, 8, false);
+    if (Subtarget->isTargetWindows())
+      GPRIdx = MFI.CreateFixedObject(GPRSaveSize, GPRSaveSize & 15, false);
+    else
+      GPRIdx = MFI.CreateStackObject(GPRSaveSize, 8, false);
 
     SDValue FIN = DAG.getFrameIndex(GPRIdx, PtrVT);
 
@@ -2890,7 +2897,10 @@
       SDValue Val = DAG.getCopyFromReg(Chain, DL, VReg, MVT::i64);
       SDValue Store = DAG.getStore(
           Val.getValue(1), DL, Val, FIN,
-          MachinePointerInfo::getStack(DAG.getMachineFunction(), i * 8));
+          Subtarget->isTargetWindows()
+              ? MachinePointerInfo::getFixedStack(DAG.getMachineFunction(),
+                                                  GPRIdx, 8)
+              : MachinePointerInfo::getStack(DAG.getMachineFunction(), i * 8));
       MemOps.push_back(Store);
       FIN =
           DAG.getNode(ISD::ADD, DL, PtrVT, FIN, DAG.getConstant(8, DL, PtrVT));
@@ -2899,7 +2909,7 @@
   FuncInfo->setVarArgsGPRIndex(GPRIdx);
   FuncInfo->setVarArgsGPRSize(GPRSaveSize);
 
-  if (Subtarget->hasFPARMv8()) {
+  if (Subtarget->hasFPARMv8() && !Subtarget->isTargetWindows()) {
     static const MCPhysReg FPRArgRegs[] = {
         AArch64::Q0, AArch64::Q1, AArch64::Q2, AArch64::Q3,
         AArch64::Q4, AArch64::Q5, AArch64::Q6, AArch64::Q7};
@@ -4491,6 +4501,19 @@
                       MachinePointerInfo(SV));
 }
 
+SDValue AArch64TargetLowering::LowerWin64_VASTART(SDValue Op,
+                                                  SelectionDAG &DAG) const {
+  AArch64FunctionInfo *FuncInfo =
+      DAG.getMachineFunction().getInfo<AArch64FunctionInfo>();
+
+  SDLoc DL(Op);
+  SDValue FR = DAG.getFrameIndex(FuncInfo->getVarArgsGPRIndex(),
+                                 getPointerTy(DAG.getDataLayout()));
+  const Value *SV = cast<SrcValueSDNode>(Op.getOperand(2))->getValue();
+  return DAG.getStore(Op.getOperand(0), DL, FR, Op.getOperand(1),
+                      MachinePointerInfo(SV));
+}
+
 SDValue AArch64TargetLowering::LowerAAPCS_VASTART(SDValue Op,
                                                 SelectionDAG &DAG) const {
   // The layout of the va_list struct is specified in the AArch64 Procedure Call
@@ -4562,6 +4585,8 @@
 
 SDValue AArch64TargetLowering::LowerVASTART(SDValue Op,
                                             SelectionDAG &DAG) const {
+  if (Subtarget->isTargetWindows())
+    return LowerWin64_VASTART(Op, DAG);
   return Subtarget->isTargetDarwin() ? LowerDarwin_VASTART(Op, DAG)
                                      : LowerAAPCS_VASTART(Op, DAG);
 }
@@ -10783,7 +10808,7 @@
 
 unsigned
 AArch64TargetLowering::getVaListSizeInBits(const DataLayout &DL) const {
-  if (Subtarget->isTargetDarwin())
+  if (Subtarget->isTargetDarwin() || Subtarget->isTargetWindows())
     return getPointerTy(DL).getSizeInBits();
 
   return 3 * getPointerTy(DL).getSizeInBits() + 2 * 32;