diff --git a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
--- a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
+++ b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
@@ -3238,7 +3238,7 @@
 
   SDLoc dl(Op);
 
-  if (Subtarget.isPPC64()) {
+  if (Subtarget.isPPC64() || Subtarget.isAIXABI()) {
     // vastart just stores the address of the VarArgsFrameIndex slot into the
     // memory location argument.
     SDValue FR = DAG.getFrameIndex(FuncInfo->getVarArgsFrameIndex(), PtrVT);
@@ -7007,9 +7007,6 @@
           CallConv == CallingConv::Fast) &&
          "Unexpected calling convention!");
 
-  if (isVarArg)
-    report_fatal_error("This call type is unimplemented on AIX.");
-
   if (getTargetMachine().Options.GuaranteedTailCallOpt)
     report_fatal_error("Tail call support is unimplemented on AIX.");
 
@@ -7027,6 +7024,7 @@
   // Assign locations to all of the incoming arguments.
   SmallVector<CCValAssign, 16> ArgLocs;
   MachineFunction &MF = DAG.getMachineFunction();
+  MachineFrameInfo &MFI = MF.getFrameInfo();
   CCState CCInfo(CallConv, isVarArg, MF, ArgLocs, *DAG.getContext());
 
   const EVT PtrVT = getPointerTy(MF.getDataLayout());
@@ -7106,7 +7104,7 @@
       continue;
     }
 
-    if (VA.isRegLoc()) {
+    if (VA.isRegLoc() && !VA.needsCustom()) {
       MVT::SimpleValueType SVT = ValVT.getSimpleVT().SimpleTy;
       unsigned VReg =
           MF.addLiveIn(VA.getLocReg(), getRegClassForSVT(SVT, IsPPC64));
@@ -7119,23 +7117,26 @@
       InVals.push_back(ArgValue);
       continue;
     }
-
-    const unsigned LocSize = LocVT.getStoreSize();
-    const unsigned ValSize = ValVT.getStoreSize();
-    assert((ValSize <= LocSize) && "Object size is larger than size of MemLoc");
-    int CurArgOffset = VA.getLocMemOffset();
-    // Objects are right-justified because AIX is big-endian.
-    if (LocSize > ValSize)
-      CurArgOffset += LocSize - ValSize;
-    MachineFrameInfo &MFI = MF.getFrameInfo();
-    // Potential tail calls could cause overwriting of argument stack slots.
-    const bool IsImmutable =
-        !(getTargetMachine().Options.GuaranteedTailCallOpt &&
-          (CallConv == CallingConv::Fast));
-    int FI = MFI.CreateFixedObject(ValSize, CurArgOffset, IsImmutable);
-    SDValue FIN = DAG.getFrameIndex(FI, PtrVT);
-    SDValue ArgValue = DAG.getLoad(ValVT, dl, Chain, FIN, MachinePointerInfo());
-    InVals.push_back(ArgValue);
+    if (VA.isMemLoc()) {
+      const unsigned LocSize = LocVT.getStoreSize();
+      const unsigned ValSize = ValVT.getStoreSize();
+      assert((ValSize <= LocSize) &&
+             "Object size is larger than size of MemLoc");
+      int CurArgOffset = VA.getLocMemOffset();
+      // Objects are right-justified because AIX is big-endian.
+      if (LocSize > ValSize)
+        CurArgOffset += LocSize - ValSize;
+      // Potential tail calls could cause overwriting of argument stack slots.
+      const bool IsImmutable =
+          !(getTargetMachine().Options.GuaranteedTailCallOpt &&
+            (CallConv == CallingConv::Fast));
+      int FI = MFI.CreateFixedObject(ValSize, CurArgOffset, IsImmutable);
+      SDValue FIN = DAG.getFrameIndex(FI, PtrVT);
+      SDValue ArgValue =
+          DAG.getLoad(ValVT, dl, Chain, FIN, MachinePointerInfo());
+      InVals.push_back(ArgValue);
+      continue;
+    }
   }
 
   // On AIX a minimum of 8 words is saved to the parameter save area.
@@ -7153,6 +7154,39 @@
   PPCFunctionInfo *FuncInfo = MF.getInfo<PPCFunctionInfo>();
   FuncInfo->setMinReservedArea(CallerReservedArea);
 
+  if (isVarArg) {
+    FuncInfo->setVarArgsFrameIndex(
+        MFI.CreateFixedObject(PtrByteSize, CCInfo.getNextStackOffset(), true));
+    SDValue FIN = DAG.getFrameIndex(FuncInfo->getVarArgsFrameIndex(), PtrVT);
+
+    static const MCPhysReg GPR_32[] = {PPC::R3, PPC::R4, PPC::R5, PPC::R6,
+                                       PPC::R7, PPC::R8, PPC::R9, PPC::R10};
+
+    static const MCPhysReg GPR_64[] = {PPC::X3, PPC::X4, PPC::X5, PPC::X6,
+                                       PPC::X7, PPC::X8, PPC::X9, PPC::X10};
+    const unsigned NumGPArgRegs = array_lengthof(IsPPC64 ? GPR_64 : GPR_32);
+
+    // The fixed integer arguments of a variadic function are stored to the
+    // VarArgsFrameIndex on the stack so that they may be loaded by
+    // dereferencing the result of va_next.
+    for (unsigned GPRIndex =
+             (CCInfo.getNextStackOffset() - LinkageSize) / PtrByteSize;
+         GPRIndex < NumGPArgRegs; ++GPRIndex) {
+
+      const unsigned VReg =
+          IsPPC64 ? MF.addLiveIn(GPR_64[GPRIndex], &PPC::G8RCRegClass)
+                  : MF.addLiveIn(GPR_32[GPRIndex], &PPC::GPRCRegClass);
+
+      SDValue Val = DAG.getCopyFromReg(Chain, dl, VReg, PtrVT);
+      SDValue Store =
+          DAG.getStore(Val.getValue(1), dl, Val, FIN, MachinePointerInfo());
+      MemOps.push_back(Store);
+      // Increment the address for the next argument to store.
+      SDValue PtrOff = DAG.getConstant(PtrByteSize, dl, PtrVT);
+      FIN = DAG.getNode(ISD::ADD, dl, PtrOff.getValueType(), FIN, PtrOff);
+    }
+  }
+
   if (!MemOps.empty())
     Chain = DAG.getNode(ISD::TokenFactor, dl, MVT::Other, MemOps);
 
diff --git a/llvm/test/CodeGen/PowerPC/aix32-cc-abi-vaarg.ll b/llvm/test/CodeGen/PowerPC/aix32-cc-abi-vaarg.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/PowerPC/aix32-cc-abi-vaarg.ll
@@ -0,0 +1,384 @@
+; RUN: llc -O2 -mtriple powerpc-ibm-aix-xcoff -stop-after=machine-cp -verify-machineinstrs < %s | \
+; RUN: FileCheck --check-prefixes=CHECK,32BIT %s
+
+; RUN: llc -O2 -verify-machineinstrs -mcpu=pwr4 -mattr=-altivec \
+; RUN:  -mtriple powerpc-ibm-aix-xcoff < %s | \
+; RUN: FileCheck --check-prefixes=CHECKASM,ASM32 %s
+
+  target datalayout = "E-m:e-p:32:32-i64:64-n32"
+  target triple = "powerpc-ibm-aix-xcoff"
+  
+  define i32 @int_va_arg(i32 %a, ...) local_unnamed_addr  {
+  entry:
+    %arg1 = alloca i8*, align 4
+    %arg2 = alloca i8*, align 4
+    %0 = bitcast i8** %arg1 to i8*
+    call void @llvm.lifetime.start.p0i8(i64 4, i8* nonnull %0)
+    %1 = bitcast i8** %arg2 to i8*
+    call void @llvm.lifetime.start.p0i8(i64 4, i8* nonnull %1)
+    call void @llvm.va_start(i8* nonnull %0)
+    call void @llvm.va_copy(i8* nonnull %1, i8* nonnull %0)
+    %argp.cur = load i8*, i8** %arg1, align 4
+    %argp.next = getelementptr inbounds i8, i8* %argp.cur, i32 4
+    store i8* %argp.next, i8** %arg1, align 4
+    %2 = bitcast i8* %argp.cur to i32*
+    %3 = load i32, i32* %2, align 4
+    %add = add nsw i32 %3, %a
+    %argp.cur2 = load i8*, i8** %arg2, align 4
+    %argp.next3 = getelementptr inbounds i8, i8* %argp.cur2, i32 4
+    store i8* %argp.next3, i8** %arg2, align 4
+    %4 = bitcast i8* %argp.cur2 to i32*
+    %5 = load i32, i32* %4, align 4
+    %mul = shl i32 %5, 1
+    %add4 = add nsw i32 %add, %mul
+    call void @llvm.va_end(i8* nonnull %0)
+    call void @llvm.va_end(i8* nonnull %1)
+    call void @llvm.lifetime.end.p0i8(i64 4, i8* nonnull %1)
+    call void @llvm.lifetime.end.p0i8(i64 4, i8* nonnull %0)
+    ret i32 %add4
+  }
+  
+  declare void @llvm.lifetime.start.p0i8(i64 immarg, i8* nocapture)
+  declare void @llvm.va_start(i8*)
+  declare void @llvm.va_copy(i8*, i8*)
+  declare void @llvm.va_end(i8*)
+  declare void @llvm.lifetime.end.p0i8(i64 immarg, i8* nocapture)
+  
+; 32BIT-LABEL:   name:            int_va_arg
+; 32BIT-LABEL;   liveins:
+; 32BIT-DAG:     - { reg: '$r3', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$r4', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$r5', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$r6', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$r7', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$r8', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$r9', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$r10', virtual-reg: '' }
+
+; 32BIT-LABEL:   fixedStack:
+; 32BIT-DAG:     - { id: 0, type: default, offset: 28, size: 4
+
+; 32BIT-LABEL:   stack:
+; 32BIT-DAG:     - { id: 0, name: arg1, type: default, offset: 0, size: 4
+; 32BIT-DAG:     - { id: 1, name: arg2, type: default, offset: 0, size: 4
+
+; 32BIT-LABEL:   body:             |
+; 32BIT-DAG:     liveins: $r3, $r4, $r5, $r6, $r7, $r8, $r9, $r10
+; 32BIT-DAG:     STW killed renamable $r4, 0, %fixed-stack.0 :: (store 4 into %fixed-stack.0)
+; 32BIT-DAG:     STW killed renamable $r5, 4, %fixed-stack.0 :: (store 4 into %fixed-stack.0 + 4)
+; 32BIT-DAG:     STW killed renamable $r6, 8, %fixed-stack.0 :: (store 4)
+; 32BIT-DAG:     STW killed renamable $r7, 12, %fixed-stack.0 :: (store 4)
+; 32BIT-DAG:     STW killed renamable $r8, 16, %fixed-stack.0 :: (store 4)
+; 32BIT-DAG:     STW killed renamable $r9, 20, %fixed-stack.0 :: (store 4)
+; 32BIT-DAG:     STW killed renamable $r10, 24, %fixed-stack.0 :: (store 4)
+; 32BIT-DAG:     STW killed renamable $r5, 0, %stack.1.arg2 :: (store 4 into %ir.arg2)
+; 32BIT-DAG:     renamable $r5 = ADDI %fixed-stack.0, 4
+; 32BIT-DAG:     STW killed renamable $r4, 0, %stack.1.arg2 :: (store 4 into %ir.1)
+; 32BIT-DAG:     renamable $r4 = ADDI %fixed-stack.0, 0
+; 32BIT-DAG:     STW renamable $r4, 0, %stack.0.arg1 :: (store 4 into %ir.0)
+; 32BIT-DAG:     STW renamable $r5, 0, %stack.0.arg1 :: (store 4 into %ir.arg1)
+; 32BIT-DAG:     renamable $r4 = LWZ 0, %fixed-stack.0 :: (load 4 from %ir.2)
+; 32BIT-DAG:     renamable $r5 = LWZ 0, %fixed-stack.0 :: (load 4 from %ir.4)
+; 32BIT-DAG:     renamable $r3 = nsw ADD4 killed renamable $r4, killed renamable $r3
+; 32BIT-DAG:     renamable $r3 = nsw ADD4 killed renamable $r3, killed renamable $r4
+; 32BIT-DAG:     BLR implicit $lr, implicit $rm, implicit $r3
+
+; ASM32-LABEL:   .int_va_arg:
+; ASM32-DAG:     stw 4, 28(1) ; set up fixed stack frame for incoming va_args r4->r10
+; ASM32-DAG:     stw 5, 32(1)
+; ASM32-DAG:     stw 6, 36(1)
+; ASM32-DAG:     stw 7, 40(1)
+; ASM32-DAG:     stw 8, 44(1)
+; ASM32-DAG:     stw 9, 48(1)
+; ASM32-DAG:     stw 10, 52(1)
+; ASM32-DAG:     stw 4, -4(1) ; stack object for auto local arg1
+; ASM32-DAG:     stw 4, -8(1) ; stack object for auto local arg2
+; ASM32-DAG:     stw 5, -4(1)  
+; ASM32-DAG:     addi 4, 1, 28
+; ASM32-DAG:     addi 5, 1, 32
+; ASM32-DAG:     lwz 4, 28(1)
+; ASM32-DAG:     stw 5, -8(1)
+; ASM32-DAG:     lwz 5, 28(1) ; va_copy load
+; ASM32-DAG:     add 3, 4, 3
+; ASM32-DAG:     add 3, 3, 5
+; ASM32-DAG:     blr
+
+  define i32 @int_stack_va_arg(i32 %one, i32 %two, i32 %three, i32 %four, i32 %five, i32 %six, i32 %seven, i32 %eight, ...) local_unnamed_addr {
+  entry:
+    %arg1 = alloca i8*, align 4
+    %arg2 = alloca i8*, align 4
+    %0 = bitcast i8** %arg1 to i8*
+    call void @llvm.lifetime.start.p0i8(i64 4, i8* nonnull %0)
+    %1 = bitcast i8** %arg2 to i8*
+    call void @llvm.lifetime.start.p0i8(i64 4, i8* nonnull %1) 
+    call void @llvm.va_start(i8* nonnull %0)
+    call void @llvm.va_copy(i8* nonnull %1, i8* nonnull %0)
+    %add = add nsw i32 %two, %one
+    %add2 = add nsw i32 %add, %three
+    %add3 = add nsw i32 %add2, %four
+    %add4 = add nsw i32 %add3, %five
+    %add5 = add nsw i32 %add4, %six
+    %add6 = add nsw i32 %add5, %seven
+    %add7 = add nsw i32 %add6, %eight
+    %argp.cur = load i8*, i8** %arg1, align 4
+    %argp.next = getelementptr inbounds i8, i8* %argp.cur, i32 4
+    store i8* %argp.next, i8** %arg1, align 4
+    %2 = bitcast i8* %argp.cur to i32*
+    %3 = load i32, i32* %2, align 4
+    %add8 = add nsw i32 %add7, %3
+    %argp.cur9 = load i8*, i8** %arg2, align 4
+    %argp.next10 = getelementptr inbounds i8, i8* %argp.cur9, i32 4
+    store i8* %argp.next10, i8** %arg2, align 4
+    %4 = bitcast i8* %argp.cur9 to i32*
+    %5 = load i32, i32* %4, align 4
+    %mul = shl i32 %5, 1
+    %add11 = add nsw i32 %add8, %mul
+    call void @llvm.va_end(i8* nonnull %0)
+    call void @llvm.va_end(i8* nonnull %1)
+    call void @llvm.lifetime.end.p0i8(i64 4, i8* nonnull %1) 
+    call void @llvm.lifetime.end.p0i8(i64 4, i8* nonnull %0) 
+    ret i32 %add11
+  }
+  
+; 32BIT-LABEL:   name:            int_stack_va_arg
+; 32BIT-LABEL:   liveins:
+; 32BIT-DAG:     - { reg: '$r3', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$r4', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$r5', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$r6', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$r7', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$r8', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$r9', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$r10', virtual-reg: '' }
+
+; 32BIT-LABEL:   fixedStack:
+; 32BIT-DAG:     - { id: 0, type: default, offset: 56, size: 4
+
+; 32BIT-LABEL:   stack:
+; 32BIT-DAG:     - { id: 0, name: arg1, type: default, offset: 0, size: 4
+; 32BIT-DAG:     - { id: 1, name: arg2, type: default, offset: 0, size: 4 
+
+; 32BIT-LABEL:   body:             |
+; 32BIT-DAG:     liveins: $r3, $r4, $r5, $r6, $r7, $r8, $r9, $r10
+; 32BIT-DAG:     renamable $r3 = nsw ADD4 killed renamable $r3, killed renamable $r4
+; 32BIT-DAG:     renamable $r3 = nsw ADD4 killed renamable $r3, killed renamable $r5
+; 32BIT-DAG:     renamable $r3 = nsw ADD4 killed renamable $r3, killed renamable $r6
+; 32BIT-DAG:     renamable $r3 = nsw ADD4 killed renamable $r3, killed renamable $r7
+; 32BIT-DAG:     renamable $r3 = nsw ADD4 killed renamable $r3, killed renamable $r8
+; 32BIT-DAG:     renamable $r3 = nsw ADD4 killed renamable $r3, killed renamable $r9
+; 32BIT-DAG:     renamable $r3 = nsw ADD4 killed renamable $r3, killed renamable $r10
+; 32BIT-DAG:     renamable $r3 = nsw ADD4 killed renamable $r4, killed renamable $r3
+; 32BIT-DAG:     renamable $r4 = ADDI %fixed-stack.0, 0
+; 32BIT-DAG:     STW killed renamable $r4, 0, %stack.0.arg1 :: (store 4 into %ir.arg1)
+; 32BIT-DAG:     renamable $r3 = nsw ADD4 killed renamable $r3, renamable $r4
+; 32BIT-DAG:     renamable $r4 = LWZ 0, %fixed-stack.0 :: (load 4 from %ir.4, align 8)
+; 32BIT-DAG:     renamable $r11 = LI 4
+; 32BIT-DAG:     BLR implicit $lr, implicit $rm, implicit $r3
+
+; ASM32-LABEL:   .int_stack_va_arg:
+; ASM32-DAG:     add 3, 4, 3
+; ASM32-DAG:     add 3, 3, 5
+; ASM32-DAG:     add 3, 3, 6
+; ASM32-DAG:     add 3, 3, 7
+; ASM32-DAG:     add 3, 3, 8
+; ASM32-DAG:     add 3, 3, 9
+; ASM32-DAG:     add 3, 3, 10
+; ASM32-DAG:     addi 4, 1, 56
+; ASM32-DAG:     lwz 4, 56(1)
+; ASM32-DAG:     stw 4, -4(1)
+; ASM32-DAG:     li 11, 4
+; ASM32-DAG:     rlwimi 4, 11, 0, 29, 29
+; ASM32-DAG:     add 3, 3, 4
+; ASM32-DAG:     add 3, 3, 4
+; ASM32-DAG:     blr
+
+  define double @double_va_arg(double %a, ...) local_unnamed_addr  {
+  entry:
+    %arg1 = alloca i8*, align 4
+    %arg2 = alloca i8*, align 4
+    %0 = bitcast i8** %arg1 to i8*
+    call void @llvm.lifetime.start.p0i8(i64 4, i8* nonnull %0) 
+    %1 = bitcast i8** %arg2 to i8*
+    call void @llvm.lifetime.start.p0i8(i64 4, i8* nonnull %1) 
+    call void @llvm.va_start(i8* nonnull %0)
+    call void @llvm.va_copy(i8* nonnull %1, i8* nonnull %0)
+    %argp.cur = load i8*, i8** %arg1, align 4
+    %argp.next = getelementptr inbounds i8, i8* %argp.cur, i32 8
+    store i8* %argp.next, i8** %arg1, align 4
+    %2 = bitcast i8* %argp.cur to double*
+    %3 = load double, double* %2, align 4
+    %add = fadd double %3, %a
+    %argp.cur2 = load i8*, i8** %arg2, align 4
+    %argp.next3 = getelementptr inbounds i8, i8* %argp.cur2, i32 8
+    store i8* %argp.next3, i8** %arg2, align 4
+    %4 = bitcast i8* %argp.cur2 to double*
+    %5 = load double, double* %4, align 4
+    %mul = fmul double %5, 2.000000e+00
+    %add4 = fadd double %add, %mul
+    call void @llvm.va_end(i8* nonnull %0)
+    call void @llvm.va_end(i8* nonnull %1)
+    call void @llvm.lifetime.end.p0i8(i64 4, i8* nonnull %1) 
+    call void @llvm.lifetime.end.p0i8(i64 4, i8* nonnull %0) 
+    ret double %add4
+  }
+  
+; 32BIT-LABEL:   name:            double_va_arg
+; 32BIT-LABEL:   liveins:
+; 32BIT-DAG:     - { reg: '$f1', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$r5', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$r6', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$r7', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$r8', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$r9', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$r10', virtual-reg: '' }
+
+; 32BIT-LABEL:   fixedStack:
+; 32BIT-DAG:     - { id: 0, type: default, offset: 32, size: 4 
+
+; 32BIT-LABEL:   stack:
+; 32BIT-DAG:     - { id: 0, name: arg1, type: default, offset: 0, size: 4
+; 32BIT-DAG:     - { id: 1, name: arg2, type: default, offset: 0, size: 4
+
+; 32BIT-LABEL:   body:             |
+; 32BIT-DAG:     liveins: $f1, $r5, $r6, $r7, $r8, $r9, $r10
+; 32BIT-DAG:     renamable $r3 = ADDI %fixed-stack.0, 0
+; 32BIT-DAG:     STW renamable $r5, 0, %fixed-stack.0 :: (store 4 into %fixed-stack.0, align 16)
+; 32BIT-DAG:     STW renamable $r6, 4, %fixed-stack.0 :: (store 4 into %fixed-stack.0 + 4)
+; 32BIT-DAG:     STW killed renamable $r7, 8, %fixed-stack.0 :: (store 4 into %fixed-stack.0 + 8, align 8)
+; 32BIT-DAG:     STW killed renamable $r8, 12, %fixed-stack.0 :: (store 4)
+; 32BIT-DAG:     STW killed renamable $r9, 16, %fixed-stack.0 :: (store 4 into %fixed-stack.0 + 16, align 16)
+; 32BIT-DAG:     STW killed renamable $r10, 20, %fixed-stack.0 :: (store 4)
+; 32BIT-DAG:     STW renamable $r3, 0, %stack.0.arg1 :: (store 4 into %ir.0)
+; 32BIT-DAG:     STW killed renamable $r3, 0, %stack.1.arg2 :: (store 4 into %ir.1)
+; 32BIT-DAG:     BLR implicit $lr, implicit $rm, implicit $f1
+
+; ASM32-LABEL:  .double_va_arg:
+; ASM32-DAG:    stw 5, 32(1)
+; ASM32-DAG:    stw 6, 36(1)
+; ASM32-DAG:    stw 7, 40(1)
+; ASM32-DAG:    stw 8, 44(1)
+; ASM32-DAG:    stw 9, 48(1)
+; ASM32-DAG:    stw 10, 52(1)
+; ASM32-DAG:    addi 3, 1, 32
+; ASM32-DAG:    lfd 0, -16(1)
+; ASM32-DAG:    lfd 2, -24(1)
+; ASM32-DAG:    fadd 0, 0, 1
+; ASM32-DAG:    fadd 1, 0, 2
+; ASM32-DAG:    blr
+
+  define double @double_stack_va_arg(double %one, double %two, double %three, double %four, double %five, double %six, double %seven, double %eight, double %nine, double %ten, double %eleven, double %twelve, double %thirteen, ...) local_unnamed_addr  {
+  entry:
+    %arg1 = alloca i8*, align 4
+    %arg2 = alloca i8*, align 4
+    %0 = bitcast i8** %arg1 to i8*
+    call void @llvm.lifetime.start.p0i8(i64 4, i8* nonnull %0) 
+    %1 = bitcast i8** %arg2 to i8*
+    call void @llvm.lifetime.start.p0i8(i64 4, i8* nonnull %1) 
+    call void @llvm.va_start(i8* nonnull %0)
+    call void @llvm.va_copy(i8* nonnull %1, i8* nonnull %0)
+    %add = fadd double %one, %two
+    %add2 = fadd double %add, %three
+    %add3 = fadd double %add2, %four
+    %add4 = fadd double %add3, %five
+    %add5 = fadd double %add4, %six
+    %add6 = fadd double %add5, %seven
+    %add7 = fadd double %add6, %eight
+    %add8 = fadd double %add7, %nine
+    %add9 = fadd double %add8, %ten
+    %add10 = fadd double %add9, %eleven
+    %add11 = fadd double %add10, %twelve
+    %add12 = fadd double %add11, %thirteen
+    %2 = bitcast i8** %arg1 to double**
+    %argp.cur1 = load double*, double** %2, align 4
+    %3 = load double, double* %argp.cur1, align 4
+    %add13 = fadd double %add12, %3
+    %4 = bitcast i8** %arg2 to double**
+    %argp.cur142 = load double*, double** %4, align 4
+    %5 = load double, double* %argp.cur142, align 4
+    %mul = fmul double %5, 2.000000e+00
+    %add16 = fadd double %add13, %mul
+    call void @llvm.lifetime.end.p0i8(i64 4, i8* nonnull %1) 
+    call void @llvm.lifetime.end.p0i8(i64 4, i8* nonnull %0) 
+    ret double %add16
+  }
+  
+; 32BIT-LABEL:   name:            double_stack_va_arg
+; 32BIT-LABEL:   liveins:
+; 32BIT-DAG:     - { reg: '$f1', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$f2', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$f3', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$f4', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$f5', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$f6', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$f7', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$f8', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$f9', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$f10', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$f11', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$f12', virtual-reg: '' }
+; 32BIT-DAG:     - { reg: '$f13', virtual-reg: '' }
+
+; 32BIT-LABEL:   fixedStack:
+; 32BIT-DAG:     - { id: 0, type: default, offset: 128, size: 4
+
+; 32BIT-LABEL:   stack:
+; 32BIT-DAG:     - { id: 0, name: arg1, type: default, offset: 0, size: 4, alignment: 4, 
+; 32BIT-DAG:  - { id: 1, name: arg2, type: default, offset: 0, size: 4, alignment: 4, 
+; 32BIT-DAG:  - { id: 2, name: '', type: default, offset: 0, size: 8, alignment: 8, 
+; 32BIT-DAG:  - { id: 3, name: '', type: default, offset: 0, size: 8, alignment: 8, 
+
+; 32BIT-LABEL:   body:             |
+; 32BIT-DAG:     liveins: $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10, $f11, $f12, $f13
+; 32BIT-DAG:     renamable $f0 = FADD killed renamable $f1, killed renamable $f2, implicit $rm
+; 32BIT-DAG:     renamable $f0 = FADD killed renamable $f0, killed renamable $f3, implicit $rm
+; 32BIT-DAG:     renamable $f0 = FADD killed renamable $f0, killed renamable $f4, implicit $rm
+; 32BIT-DAG:     renamable $f0 = FADD killed renamable $f0, killed renamable $f5, implicit $rm
+; 32BIT-DAG:     renamable $f0 = FADD killed renamable $f0, killed renamable $f6, implicit $rm
+; 32BIT-DAG:     renamable $f0 = FADD killed renamable $f0, killed renamable $f7, implicit $rm
+; 32BIT-DAG:     renamable $f0 = FADD killed renamable $f0, killed renamable $f8, implicit $rm
+; 32BIT-DAG:     renamable $f0 = FADD killed renamable $f0, killed renamable $f9, implicit $rm
+; 32BIT-DAG:     renamable $f0 = FADD killed renamable $f0, killed renamable $f10, implicit $rm
+; 32BIT-DAG:     STW killed renamable $r3, 0, %stack.3 :: (store 4 into %stack.3, align 8)
+; 32BIT-DAG:     STW killed renamable $r4, 4, %stack.3 :: (store 4 into %stack.3 + 4)
+; 32BIT-DAG:     renamable $f0 = FADD killed renamable $f0, killed renamable $f11, implicit $rm
+; 32BIT-DAG:     renamable $f1 = LFD 0, %stack.2 :: (load 8 from %stack.2)
+; 32BIT-DAG:     renamable $f2 = LFD 0, %stack.3 :: (load 8 from %stack.3)
+; 32BIT-DAG:     renamable $f0 = FADD killed renamable $f0, killed renamable $f12, implicit $rm
+; 32BIT-DAG:     renamable $f0 = FADD killed renamable $f0, killed renamable $f13, implicit $rm
+; 32BIT-DAG:     renamable $r3 = ADDI %fixed-stack.0, 0
+; 32BIT-DAG:     STW killed renamable $r3, 0, %stack.0.arg1 :: (store 4 into %ir.0)
+; 32BIT-DAG:     renamable $r3 = LWZ 0, %fixed-stack.0 :: (load 4 from %ir.argp.cur142, align 16)
+; 32BIT-DAG:     STW renamable $r4, 4, %stack.2 :: (store 4 into %stack.2 + 4)
+; 32BIT-DAG:     STW renamable $r3, 0, %stack.2 :: (store 4 into %stack.2, align 8)
+; 32BIT-DAG:     renamable $r4 = LWZ 4, %fixed-stack.0 :: (load 4 from %ir.argp.cur1 + 4)
+; 32BIT-DAG:     renamable $f0 = FADD killed renamable $f0, killed renamable $f1, implicit $rm
+; 32BIT-DAG:     renamable $f1 = FADD killed renamable $f2, renamable $f2, implicit $rm
+; 32BIT-DAG:     renamable $f1 = FADD killed renamable $f0, killed renamable $f1, implicit $rm
+; 32BIT-DAG:     BLR implicit $lr, implicit $rm, implicit $f1
+
+; ASM32-LABEL:  .double_stack_va_arg:
+; ASM32-DAG:    fadd 0, 1, 2
+; ASM32-DAG:    fadd 0, 0, 3
+; ASM32-DAG:    addi 3, 1, 128
+; ASM32-DAG:    fadd 0, 0, 4
+; ASM32-DAG:    stw 3, -4(1)
+; ASM32-DAG:    fadd 0, 0, 5
+; ASM32-DAG:    lwz 3, 128(1)
+; ASM32-DAG:    lwz 4, 132(1)
+; ASM32-DAG:    fadd 0, 0, 6
+; ASM32-DAG:    fadd 0, 0, 7
+; ASM32-DAG:    fadd 0, 0, 8
+; ASM32-DAG:    stw 3, -16(1)
+; ASM32-DAG:    stw 4, -12(1)
+; ASM32-DAG:    fadd 0, 0, 9
+; ASM32-DAG:    lfd 1, -16(1)
+; ASM32-DAG:    fadd 0, 0, 10
+; ASM32-DAG:    stw 3, -24(1)
+; ASM32-DAG:    stw 4, -20(1)
+; ASM32-DAG:    fadd 0, 0, 11
+; ASM32-DAG:    lfd 2, -24(1)
+; ASM32-DAG:    fadd 0, 0, 12
+; ASM32-DAG:    fadd 0, 0, 13
+; ASM32-DAG:    fadd 0, 0, 1
+; ASM32-DAG:    fadd 1, 0, 2
+; ASM32-DAG:    blr
diff --git a/llvm/test/CodeGen/PowerPC/aix64-cc-abi-vaarg.ll b/llvm/test/CodeGen/PowerPC/aix64-cc-abi-vaarg.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/PowerPC/aix64-cc-abi-vaarg.ll
@@ -0,0 +1,366 @@
+; RUN: llc -O2 -mtriple powerpc-ibm-aix-xcoff -stop-after=machine-cp -verify-machineinstrs < %s | \
+; RUN: FileCheck --check-prefixes=CHECK,32BIT %s
+
+; RUN: llc -O2 -verify-machineinstrs -mcpu=pwr4 -mattr=-altivec \
+; RUN:  -mtriple powerpc-ibm-aix-xcoff < %s | \
+; RUN: FileCheck --check-prefixes=CHECKASM,ASM32 %s
+
+  target datalayout = "E-m:e-i64:64-n32:64"
+  target triple = "powerpc64-ibm-aix-xcoff"
+  
+  define i32 @int_va_arg(i32 %a, ...) local_unnamed_addr  {
+  entry:
+    %arg1 = alloca i8*, align 8
+    %arg2 = alloca i8*, align 8
+    %0 = bitcast i8** %arg1 to i8*
+    call void @llvm.lifetime.start.p0i8(i64 8, i8* nonnull %0) 
+    %1 = bitcast i8** %arg2 to i8*
+    call void @llvm.lifetime.start.p0i8(i64 8, i8* nonnull %1)
+    call void @llvm.va_start(i8* nonnull %0)
+    call void @llvm.va_copy(i8* nonnull %1, i8* nonnull %0)
+    %2 = va_arg i8** %arg1, i32
+    %add = add nsw i32 %2, %a
+    %3 = va_arg i8** %arg2, i32
+    %mul = shl i32 %3, 1
+    %add3 = add nsw i32 %add, %mul
+    call void @llvm.va_end(i8* nonnull %0)
+    call void @llvm.va_end(i8* nonnull %1)
+    call void @llvm.lifetime.end.p0i8(i64 8, i8* nonnull %1) 
+    call void @llvm.lifetime.end.p0i8(i64 8, i8* nonnull %0) 
+    ret i32 %add3
+  }
+
+  declare void @llvm.lifetime.start.p0i8(i64 immarg, i8* nocapture) 
+  declare void @llvm.va_start(i8*) 
+  declare void @llvm.va_copy(i8*, i8*) 
+  declare void @llvm.va_end(i8*) 
+  declare void @llvm.lifetime.end.p0i8(i64 immarg, i8* nocapture) 
+  
+; 64BIT-LABEL:   name:            int_va_arg
+; 64BIT-LABEL:   liveins:
+; 64BIT-DAG:     - { reg: '$x3', virtual-reg: '' }
+; 64BIT-DAG:     - { reg: '$x4', virtual-reg: '' }
+; 64BIT-DAG:     - { reg: '$x5', virtual-reg: '' }
+; 64BIT-DAG:     - { reg: '$x6', virtual-reg: '' }
+; 64BIT-DAG:     - { reg: '$x7', virtual-reg: '' }
+; 64BIT-DAG:     - { reg: '$x8', virtual-reg: '' }
+; 64BIT-DAG:     - { reg: '$x9', virtual-reg: '' }
+; 64BIT-DAG:     - { reg: '$x10', virtual-reg: '' }
+
+; 64BIT-LABEL:   fixedStack:
+; 64BIT-DAG:     - { id: 0, type: default, offset: 56, size: 8
+
+; 64BIT-LABEL:   stack:
+; 64BIT-DAG:     - { id: 0, name: arg1, type: default, offset: 0, size: 8
+; 64BIT-DAG:     - { id: 1, name: arg2, type: default, offset: 0, size: 8 
+
+; 64BIT-LABEL:   body:             |
+; 64BIT-DAG:     liveins: $x3, $x4, $x5, $x6, $x7, $x8, $x9, $x10
+; 64BIT-DAG:     renamable $x4 = ADDI8 %fixed-stack.0, 0
+; 64BIT-DAG:     STD killed renamable $x4, 0, %fixed-stack.0 :: (store 8 into %fixed-stack.0)
+; 64BIT-DAG:     STD killed renamable $x5, 8, %fixed-stack.0 :: (store 8 into %fixed-stack.0 + 8)
+; 64BIT-DAG:     STD killed renamable $x6, 16, %fixed-stack.0 :: (store 8)
+; 64BIT-DAG:     STD killed renamable $x7, 24, %fixed-stack.0 :: (store 8)
+; 64BIT-DAG:     STD killed renamable $x8, 32, %fixed-stack.0 :: (store 8)
+; 64BIT-DAG:     STD killed renamable $x9, 40, %fixed-stack.0 :: (store 8)
+; 64BIT-DAG:     STD killed renamable $x10, 48, %fixed-stack.0 :: (store 8)
+; 64BIT-DAG:     renamable $r11 = LWZ 0, %fixed-stack.0 :: (load 4 from %fixed-stack.0, align 8)
+; 64BIT-DAG:     STD renamable $x4, 0, %stack.0.arg1 :: (store 8 into %ir.0)
+; 64BIT-DAG:     STD killed renamable $x4, 0, %stack.1.arg2 :: (store 8 into %ir.1)
+; 64BIT-DAG:     renamable $x4 = LD 0, %stack.1.arg2 :: (load 8 from %ir.arg2)
+; 64BIT-DAG:     renamable $x5 = ADDI8 %fixed-stack.0, 4
+; 64BIT-DAG:     STD killed renamable $x5, 0, %stack.0.arg1 :: (store 8 into %ir.arg1)
+; 64BIT-DAG:     renamable $x5 = ADDI8 renamable $x4, 4
+; 64BIT-DAG:     STD killed renamable $x5, 0, %stack.1.arg2 :: (store 8 into %ir.arg2)
+; 64BIT-DAG:     renamable $r4 = LWZ 0, killed renamable $x4 :: (load 4)
+; 64BIT-DAG:     renamable $r3 = nsw ADD4 killed renamable $r11, renamable $r3, implicit killed $x3
+; 64BIT-DAG:     renamable $r4 = RLWINM killed renamable $r4, 1, 0, 30
+; 64BIT-DAG:     renamable $r3 = nsw ADD4 killed renamable $r3, killed renamable $r4, implicit-def $x3
+; 64BIT-DAG:     BLR8 implicit $lr8, implicit $rm, implicit $x3
+
+; ASM64-LABEL:   .int_va_arg:
+; ASM64-LABEL:   std 4, 56(1)
+; ASM64-LABEL:   std 5, 64(1)
+; ASM64-LABEL:   std 6, 72(1)
+; ASM64-LABEL:   std 7, 80(1)
+; ASM64-LABEL:   std 8, 88(1)
+; ASM64-LABEL:   std 9, 96(1)
+; ASM64-LABEL:   std 10, 104(1)
+; ASM64-LABEL:   addi 11, 1, 56
+; ASM64-LABEL:   lwz 4, 56(1)
+; ASM64-LABEL:   lwz 5, 56(1)
+; ASM64-LABEL:   addi 12, 1, 60
+; ASM64-LABEL:   std 11, -8(1)
+; ASM64-LABEL:   std 11, -16(1)
+; ASM64-LABEL:   std 12, -8(1)
+; ASM64-LABEL:   std 12, -16(1)
+; ASM64-LABEL:   add 3, 4, 3
+; ASM64-LABEL:   add 3, 3, 4
+; ASM64-LABEL:   blr
+
+  define i32 @int_stack_va_arg(i32 %one, i32 %two, i32 %three, i32 %four, i32 %five, i32 %six, i32 %seven, i32 %eight, ...) local_unnamed_addr {
+  entry:
+    %arg1 = alloca i8*, align 8
+    %arg2 = alloca i8*, align 8
+    %0 = bitcast i8** %arg1 to i8*
+    call void @llvm.lifetime.start.p0i8(i64 8, i8* nonnull %0) 
+    %1 = bitcast i8** %arg2 to i8*
+    call void @llvm.lifetime.start.p0i8(i64 8, i8* nonnull %1) 
+    call void @llvm.va_start(i8* nonnull %0)
+    call void @llvm.va_copy(i8* nonnull %1, i8* nonnull %0)
+    %add = add nsw i32 %two, %one
+    %add2 = add nsw i32 %add, %three
+    %add3 = add nsw i32 %add2, %four
+    %add4 = add nsw i32 %add3, %five
+    %add5 = add nsw i32 %add4, %six
+    %add6 = add nsw i32 %add5, %seven
+    %add7 = add nsw i32 %add6, %eight
+    %2 = va_arg i8** %arg1, i32
+    %add8 = add nsw i32 %add7, %2
+    %3 = va_arg i8** %arg2, i32
+    %mul = shl i32 %3, 1
+    %add10 = add nsw i32 %add8, %mul
+    call void @llvm.va_end(i8* nonnull %0)
+    call void @llvm.va_end(i8* nonnull %1)
+    call void @llvm.lifetime.end.p0i8(i64 8, i8* nonnull %1) 
+    call void @llvm.lifetime.end.p0i8(i64 8, i8* nonnull %0) 
+    ret i32 %add10
+  }
+  
+; 64BIT-LABEL:    name:            int_stack_va_arg
+; 64BIT-LABEL:    liveins:
+; 64BIT-DAG:       - { reg: '$x3', virtual-reg: '' }
+; 64BIT-DAG:       - { reg: '$x4', virtual-reg: '' }
+; 64BIT-DAG:       - { reg: '$x5', virtual-reg: '' }
+; 64BIT-DAG:       - { reg: '$x6', virtual-reg: '' }
+; 64BIT-DAG:       - { reg: '$x7', virtual-reg: '' }
+; 64BIT-DAG:       - { reg: '$x8', virtual-reg: '' }
+; 64BIT-DAG:       - { reg: '$x9', virtual-reg: '' }
+; 64BIT-DAG:       - { reg: '$x10', virtual-reg: '' }
+
+; 64BIT-LABEL:    fixedStack:
+; 64BIT-DAG:       - { id: 0, type: default, offset: 112, size: 8, alignment: 16, stack-id: default, 
+
+; 64BIT-LABEL:    stack:
+; 64BIT-DAG:       - { id: 0, name: arg1, type: default, offset: 0, size: 8, alignment: 8, 
+; 64BIT-DAG:       - { id: 1, name: arg2, type: default, offset: 0, size: 8, alignment: 8, 
+
+; 64BIT-LABEL:     body:             |
+; 64BIT-DAG:       liveins: $x3, $x4, $x5, $x6, $x7, $x8, $x9, $x10
+; 64BIT-DAG:       renamable $r11 = LWZ 0, %fixed-stack.0 :: (load 4 from %fixed-stack.0, align 16)
+; 64BIT-DAG:       renamable $r3 = nsw ADD4 renamable $r4, renamable $r3, implicit killed $x3, implicit killed $x4
+; 64BIT-DAG:       renamable $r3 = nsw ADD4 killed renamable $r3, renamable $r5, implicit killed $x5
+; 64BIT-DAG:       renamable $r3 = nsw ADD4 killed renamable $r3, renamable $r6, implicit killed $x6
+; 64BIT-DAG:       renamable $r3 = nsw ADD4 killed renamable $r3, renamable $r7, implicit killed $x7
+; 64BIT-DAG:       renamable $r3 = nsw ADD4 killed renamable $r3, renamable $r8, implicit killed $x8
+; 64BIT-DAG:       renamable $r3 = nsw ADD4 killed renamable $r3, renamable $r9, implicit killed $x9
+; 64BIT-DAG:       renamable $r3 = nsw ADD4 killed renamable $r3, renamable $r10, implicit killed $x10
+; 64BIT-DAG:       renamable $r3 = nsw ADD4 killed renamable $r3, renamable $r11
+; 64BIT-DAG:       renamable $r3 = nsw ADD4 killed renamable $r3, killed renamable $r4, implicit-def $x3
+; 64BIT-DAG:       BLR8 implicit $lr8, implicit $rm, implicit $x3
+
+; ASM64-DAG:     .int_stack_va_arg:
+; ASM64-DAG:     # %bb.0:                                # %entry
+; ASM64-DAG:     add 3, 4, 3
+; ASM64-DAG:     add 3, 3, 5
+; ASM64-DAG:     add 3, 3, 6
+; ASM64-DAG:     lwz 4, 112(1)
+; ASM64-DAG:     add 3, 3, 7
+; ASM64-DAG:     add 3, 3, 8
+; ASM64-DAG:     add 3, 3, 9
+; ASM64-DAG:     add 3, 3, 10
+; ASM64-DAG:     add 3, 3, 4
+; ASM64-DAG:     slwi 4, 4, 1
+; ASM64-DAG:     addi 11, 1, 116
+; ASM64-DAG:     add 3, 3, 4
+; ASM64-DAG:     std 11, -8(1)
+; ASM64-DAG:     std 11, -16(1)
+; ASM64-DAG:     blr
+
+  define double @double_va_arg(double %a, ...) local_unnamed_addr  {
+  entry:
+    %arg1 = alloca i8*, align 8
+    %arg2 = alloca i8*, align 8
+    %0 = bitcast i8** %arg1 to i8*
+    call void @llvm.lifetime.start.p0i8(i64 8, i8* nonnull %0) 
+    %1 = bitcast i8** %arg2 to i8*
+    call void @llvm.lifetime.start.p0i8(i64 8, i8* nonnull %1) 
+    call void @llvm.va_start(i8* nonnull %0)
+    call void @llvm.va_copy(i8* nonnull %1, i8* nonnull %0)
+    %2 = va_arg i8** %arg1, double
+    %add = fadd double %2, %a
+    %3 = va_arg i8** %arg2, double
+    %mul = fmul double %3, 2.000000e+00
+    %add3 = fadd double %add, %mul
+    call void @llvm.va_end(i8* nonnull %0)
+    call void @llvm.va_end(i8* nonnull %1)
+    call void @llvm.lifetime.end.p0i8(i64 8, i8* nonnull %1) 
+    call void @llvm.lifetime.end.p0i8(i64 8, i8* nonnull %0) 
+    ret double %add3
+  }
+
+; 64BIT-LABEL:   name:            double_va_arg
+; 64BIT-LABEL:   liveins:
+; 64BIT-DAG:     - { reg: '$f1', virtual-reg: '' }
+; 64BIT-DAG:     - { reg: '$x4', virtual-reg: '' }
+; 64BIT-DAG:     - { reg: '$x5', virtual-reg: '' }
+; 64BIT-DAG:     - { reg: '$x6', virtual-reg: '' }
+; 64BIT-DAG:     - { reg: '$x7', virtual-reg: '' }
+; 64BIT-DAG:     - { reg: '$x8', virtual-reg: '' }
+; 64BIT-DAG:     - { reg: '$x9', virtual-reg: '' }
+; 64BIT-DAG:     - { reg: '$x10', virtual-reg: '' }
+
+; 64BIT-LABEL:   fixedStack:
+; 64BIT-DAG:     - { id: 0, type: default, offset: 56, size: 8
+
+; 64BIT-LABEL:   stack:
+; 64BIT-DAG:       - { id: 0, name: arg1, type: default, offset: 0, size: 8 
+; 64BIT-DAG:       - { id: 1, name: arg2, type: default, offset: 0, size: 8 
+
+; 64BIT-LABEL:     body:             |
+; 64BIT-DAG:         liveins: $f1, $x4, $x5, $x6, $x7, $x8, $x9, $x10
+; 64BIT-DAG:         renamable $x3 = ADDI8 %fixed-stack.0, 0
+; 64BIT-DAG:         STD killed renamable $x4, 0, %fixed-stack.0 :: (store 8 into %fixed-stack.0)
+; 64BIT-DAG:         STD killed renamable $x5, 8, %fixed-stack.0 :: (store 8 into %fixed-stack.0 + 8)
+; 64BIT-DAG:         STD killed renamable $x6, 16, %fixed-stack.0 :: (store 8)
+; 64BIT-DAG:         STD killed renamable $x7, 24, %fixed-stack.0 :: (store 8)
+; 64BIT-DAG:         STD killed renamable $x8, 32, %fixed-stack.0 :: (store 8)
+; 64BIT-DAG:         STD killed renamable $x9, 40, %fixed-stack.0 :: (store 8)
+; 64BIT-DAG:         STD killed renamable $x10, 48, %fixed-stack.0 :: (store 8)
+; 64BIT-DAG:         STD renamable $x3, 0, %stack.0.arg1 :: (store 8 into %ir.0)
+; 64BIT-DAG:         STD killed renamable $x3, 0, %stack.1.arg2 :: (store 8 into %ir.1)
+; 64BIT-DAG:         renamable $x3 = ADDI8 %fixed-stack.0, 8
+; 64BIT-DAG:         STD killed renamable $x3, 0, %stack.0.arg1 :: (store 8 into %ir.arg1)
+; 64BIT-DAG:         renamable $x3 = LD 0, %stack.1.arg2 :: (load 8 from %ir.arg2)
+; 64BIT-DAG:         renamable $f0 = LFD 0, %fixed-stack.0 :: (load 8)
+; 64BIT-DAG:         renamable $x4 = ADDI8 renamable $x3, 8
+; 64BIT-DAG:         STD killed renamable $x4, 0, %stack.1.arg2 :: (store 8 into %ir.arg2)
+; 64BIT-DAG:         renamable $f0 = FADD killed renamable $f0, killed renamable $f1, implicit $rm
+; 64BIT-DAG:         renamable $f1 = LFD 0, killed renamable $x3 :: (load 8)
+; 64BIT-DAG:         renamable $f1 = FADD killed renamable $f1, renamable $f1, implicit $rm
+; 64BIT-DAG:         renamable $f1 = FADD killed renamable $f0, killed renamable $f1, implicit $rm
+; 64BIT-DAG:         BLR8 implicit $lr8, implicit $rm, implicit $f1
+
+; ASM64-LABEL:  .double_va_arg:
+; ASM64-DAG:     std 4, 56(1)
+; ASM64-DAG:     std 5, 64(1)
+; ASM64-DAG:     std 6, 72(1)
+; ASM64-DAG:     std 7, 80(1)
+; ASM64-DAG:     std 8, 88(1)
+; ASM64-DAG:     std 9, 96(1)
+; ASM64-DAG:     addi 11, 1, 56
+; ASM64-DAG:     addi 3, 1, 64
+; ASM64-DAG:     std 11, -8(1)
+; ASM64-DAG:     std 11, -16(1)
+; ASM64-DAG:     std 3, -8(1)
+; ASM64-DAG:     std 3, -16(1)
+; ASM64-DAG:     std 10, 104(1)
+; ASM64-DAG:     ld 4, 56(1)
+; ASM64-DAG:     ld 3, 56(1)
+; ASM64-DAG:     fadd 0, 0, 1
+; ASM64-DAG:     fadd 1, 2, 2
+; ASM64-DAG:     fadd 1, 0, 1
+; ASM64-DAG:     blr
+  
+  define double @double_stack_va_arg(double %one, double %two, double %three, double %four, double %five, double %six, double %seven, double %eight, double %nine, double %ten, double %eleven, double %twelve, double %thirteen, ...) local_unnamed_addr  {
+  entry:
+    %arg1 = alloca i8*, align 8
+    %arg2 = alloca i8*, align 8
+    %0 = bitcast i8** %arg1 to i8*
+    call void @llvm.lifetime.start.p0i8(i64 8, i8* nonnull %0) 
+    %1 = bitcast i8** %arg2 to i8*
+    call void @llvm.lifetime.start.p0i8(i64 8, i8* nonnull %1) 
+    call void @llvm.va_start(i8* nonnull %0)
+    call void @llvm.va_copy(i8* nonnull %1, i8* nonnull %0)
+    %add = fadd double %one, %two
+    %add2 = fadd double %add, %three
+    %add3 = fadd double %add2, %four
+    %add4 = fadd double %add3, %five
+    %add5 = fadd double %add4, %six
+    %add6 = fadd double %add5, %seven
+    %add7 = fadd double %add6, %eight
+    %add8 = fadd double %add7, %nine
+    %add9 = fadd double %add8, %ten
+    %add10 = fadd double %add9, %eleven
+    %add11 = fadd double %add10, %twelve
+    %add12 = fadd double %add11, %thirteen
+    %2 = va_arg i8** %arg1, double
+    %add13 = fadd double %add12, %2
+    %3 = va_arg i8** %arg2, double
+    %mul = fmul double %3, 2.000000e+00
+    %add15 = fadd double %add13, %mul
+    call void @llvm.lifetime.end.p0i8(i64 8, i8* nonnull %1) 
+    call void @llvm.lifetime.end.p0i8(i64 8, i8* nonnull %0) 
+    ret double %add15
+  }
+  
+
+; 64BIT-LABEL:   name:            double_stack_va_arg
+; 64BIT-LABEL:   liveins:
+; 64BIT-DAG:     - { reg: '$f1', virtual-reg: '' }
+; 64BIT-DAG:     - { reg: '$f2', virtual-reg: '' }
+; 64BIT-DAG:     - { reg: '$f3', virtual-reg: '' }
+; 64BIT-DAG:     - { reg: '$f4', virtual-reg: '' }
+; 64BIT-DAG:     - { reg: '$f5', virtual-reg: '' }
+; 64BIT-DAG:     - { reg: '$f6', virtual-reg: '' }
+; 64BIT-DAG:     - { reg: '$f7', virtual-reg: '' }
+; 64BIT-DAG:     - { reg: '$f8', virtual-reg: '' }
+; 64BIT-DAG:     - { reg: '$f9', virtual-reg: '' }
+; 64BIT-DAG:     - { reg: '$f10', virtual-reg: '' }
+; 64BIT-DAG:     - { reg: '$f11', virtual-reg: '' }
+; 64BIT-DAG:     - { reg: '$f12', virtual-reg: '' }
+; 64BIT-DAG:     - { reg: '$f13', virtual-reg: '' }
+
+; 64BIT-LABEL:   fixedStack:
+; 64BIT-DAG:       - { id: 0, type: default, offset: 152, size: 8
+
+; 64BIT-LABEL:   stack:
+; 64BIT-DAG:       - { id: 0, name: arg1, type: default, offset: 0, size: 8
+; 64BIT-DAG:       - { id: 1, name: arg2, type: default, offset: 0, size: 8 
+
+; 64BIT-LABEL:     body:             |
+; 64BIT-DAG:         liveins: $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10, $f11, $f12, $f13
+; 64BIT-DAG:         renamable $f1 = FADD killed renamable $f1, killed renamable $f2, implicit $rm
+; 64BIT-DAG:         renamable $f1 = FADD killed renamable $f1, killed renamable $f3, implicit $rm
+; 64BIT-DAG:         renamable $f1 = FADD killed renamable $f1, killed renamable $f4, implicit $rm
+; 64BIT-DAG:         renamable $f1 = FADD killed renamable $f1, killed renamable $f5, implicit $rm
+; 64BIT-DAG:         renamable $f1 = FADD killed renamable $f1, killed renamable $f6, implicit $rm
+; 64BIT-DAG:         renamable $f1 = FADD killed renamable $f1, killed renamable $f7, implicit $rm
+; 64BIT-DAG:         renamable $f1 = FADD killed renamable $f1, killed renamable $f8, implicit $rm
+; 64BIT-DAG:         renamable $f1 = FADD killed renamable $f1, killed renamable $f9, implicit $rm
+; 64BIT-DAG:         renamable $f1 = FADD killed renamable $f1, killed renamable $f10, implicit $rm
+; 64BIT-DAG:         renamable $f1 = FADD killed renamable $f1, killed renamable $f11, implicit $rm
+; 64BIT-DAG:         renamable $f1 = FADD killed renamable $f1, killed renamable $f12, implicit $rm
+; 64BIT-DAG:         renamable $f1 = FADD killed renamable $f1, killed renamable $f13, implicit $rm
+; 64BIT-DAG:         renamable $f1 = FADD killed renamable $f1, renamable $f0, implicit $rm
+; 64BIT-DAG:         renamable $f0 = LFD 0, %fixed-stack.0 :: (load 8)
+; 64BIT-DAG:         renamable $f0 = FADD killed renamable $f0, renamable $f0, implicit $rm
+; 64BIT-DAG:         renamable $f1 = FADD killed renamable $f1, killed renamable $f0, implicit $rm
+; 64BIT-DAG:         BLR8 implicit $lr8, implicit $rm, implicit $f1
+
+; ASM64-LABEL:   .double_stack_va_arg:
+; ASM64-DAG:     std 3, -8(1)
+; ASM64-DAG:     std 3, -16(1)
+; ASM64-DAG:     addi 3, 1, 152
+; ASM64-DAG:     ld 3, 152(1)
+; ASM64-DAG:     fadd 0, 1, 2
+; ASM64-DAG:     fadd 0, 0, 3
+; ASM64-DAG:     fadd 0, 0, 4
+; ASM64-DAG:     fadd 0, 0, 5
+; ASM64-DAG:     fadd 0, 0, 6
+; ASM64-DAG:     fadd 0, 0, 7
+; ASM64-DAG:     fadd 0, 0, 8
+; ASM64-DAG:     fadd 0, 0, 9
+; ASM64-DAG:     fadd 0, 0, 10
+; ASM64-DAG:     fadd 0, 0, 11
+; ASM64-DAG:     fadd 0, 0, 12
+; ASM64-DAG:     fadd 0, 0, 13
+; ASM64-DAG:     std 3, -32(1)
+; ASM64-DAG:     lfd 1, -32(1)
+; ASM64-DAG:     std 3, -24(1)
+; ASM64-DAG:     lfd 2, -24(1)
+; ASM64-DAG:     fadd 0, 0, 1
+; ASM64-DAG:     fadd 1, 2, 2
+; ASM64-DAG:     fadd 1, 0, 1
+; ASM64-DAG:     blr
+