Vendor import of llvm release_39 branch r288513:vendor/llvm/llvm-release_39-r288513

https://llvm.org/svn/llvm-project/llvm/branches/release_39@288513

17 files changed, 7403 insertions, 37 deletions

diff --git a/include/llvm/Support/Threading.h b/include/llvm/Support/Threading.h
index 09b96dfb4c1c..fe407b725314 100644
--- a/include/llvm/Support/Threading.h
+++ b/include/llvm/Support/Threading.h
@@ -20,11 +20,11 @@
 #include <ciso646> // So we can check the C++ standard lib macros.
 #include <functional>
 
-// We use std::call_once on all Unix platforms except for NetBSD with
-// libstdc++. That platform has a bug they are working to fix, and they'll
-// remove the NetBSD checks once fixed.
-#if defined(LLVM_ON_UNIX) &&                                                   \
-    !(defined(__NetBSD__) && !defined(_LIBCPP_VERSION)) && !defined(__ppc__)
+// std::call_once from libc++ is used on all Unix platforms. Other
+// implementations like libstdc++ are known to have problems on NetBSD,
+// OpenBSD and PowerPC.
+#if defined(LLVM_ON_UNIX) && (defined(_LIBCPP_VERSION) ||                      \
+    !(defined(__NetBSD__) || defined(__OpenBSD__) || defined(__ppc__)))
 #define LLVM_THREADING_USE_STD_CALL_ONCE 1
 #else
 #define LLVM_THREADING_USE_STD_CALL_ONCE 0
diff --git a/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp b/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp
index 3ab9459c8af7..9a18943291c8 100644
--- a/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp
+++ b/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp
@@ -2185,24 +2185,29 @@ void DAGTypeLegalizer::ExpandIntRes_MUL(SDNode *N,
     // options. This is a trivially-generalized version of the code from
     // Hacker's Delight (itself derived from Knuth's Algorithm M from section
     // 4.3.1).
-    SDValue Mask =
-      DAG.getConstant(APInt::getLowBitsSet(NVT.getSizeInBits(),
-                                           NVT.getSizeInBits() >> 1), dl, NVT);
+    unsigned Bits = NVT.getSizeInBits();
+    unsigned HalfBits = Bits >> 1;
+    SDValue Mask = DAG.getConstant(APInt::getLowBitsSet(Bits, HalfBits), dl,
+                                   NVT);
     SDValue LLL = DAG.getNode(ISD::AND, dl, NVT, LL, Mask);
     SDValue RLL = DAG.getNode(ISD::AND, dl, NVT, RL, Mask);
 
     SDValue T = DAG.getNode(ISD::MUL, dl, NVT, LLL, RLL);
     SDValue TL = DAG.getNode(ISD::AND, dl, NVT, T, Mask);
 
-    SDValue Shift =
-      DAG.getConstant(NVT.getSizeInBits() >> 1, dl,
-                      TLI.getShiftAmountTy(NVT, DAG.getDataLayout()));
+    EVT ShiftAmtTy = TLI.getShiftAmountTy(NVT, DAG.getDataLayout());
+    if (APInt::getMaxValue(ShiftAmtTy.getSizeInBits()).ult(HalfBits)) {
+      // The type from TLI is too small to fit the shift amount we want.
+      // Override it with i32. The shift will have to be legalized.
+      ShiftAmtTy = MVT::i32;
+    }
+    SDValue Shift = DAG.getConstant(HalfBits, dl, ShiftAmtTy);
     SDValue TH = DAG.getNode(ISD::SRL, dl, NVT, T, Shift);
     SDValue LLH = DAG.getNode(ISD::SRL, dl, NVT, LL, Shift);
     SDValue RLH = DAG.getNode(ISD::SRL, dl, NVT, RL, Shift);
 
     SDValue U = DAG.getNode(ISD::ADD, dl, NVT,
-                            DAG.getNode(ISD::MUL, dl, NVT, LLH, RLL), TL);
+                            DAG.getNode(ISD::MUL, dl, NVT, LLH, RLL), TH);
     SDValue UL = DAG.getNode(ISD::AND, dl, NVT, U, Mask);
     SDValue UH = DAG.getNode(ISD::SRL, dl, NVT, U, Shift);
 
@@ -2211,14 +2216,14 @@ void DAGTypeLegalizer::ExpandIntRes_MUL(SDNode *N,
     SDValue VH = DAG.getNode(ISD::SRL, dl, NVT, V, Shift);
 
     SDValue W = DAG.getNode(ISD::ADD, dl, NVT,
-                            DAG.getNode(ISD::MUL, dl, NVT, LL, RL),
+                            DAG.getNode(ISD::MUL, dl, NVT, LLH, RLH),
                             DAG.getNode(ISD::ADD, dl, NVT, UH, VH));
-    Lo = DAG.getNode(ISD::ADD, dl, NVT, TH,
+    Lo = DAG.getNode(ISD::ADD, dl, NVT, TL,
                      DAG.getNode(ISD::SHL, dl, NVT, V, Shift));
 
     Hi = DAG.getNode(ISD::ADD, dl, NVT, W,
                      DAG.getNode(ISD::ADD, dl, NVT,
-                                 DAG.getNode(ISD::MUL, dl, NVT, RH, LL), 
+                                 DAG.getNode(ISD::MUL, dl, NVT, RH, LL),
                                  DAG.getNode(ISD::MUL, dl, NVT, RL, LH)));
     return;
   }
diff --git a/lib/Target/AMDGPU/SIInstrInfo.cpp b/lib/Target/AMDGPU/SIInstrInfo.cpp
index 5cc6a4e0e83e..919081902a9c 100644
--- a/lib/Target/AMDGPU/SIInstrInfo.cpp
+++ b/lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -2203,7 +2203,8 @@ void SIInstrInfo::legalizeOperandsSMRD(MachineRegisterInfo &MRI,
 }
 
 void SIInstrInfo::legalizeOperands(MachineInstr &MI) const {
-  MachineRegisterInfo &MRI = MI.getParent()->getParent()->getRegInfo();
+  MachineFunction &MF = *MI.getParent()->getParent();
+  MachineRegisterInfo &MRI = MF.getRegInfo();
 
   // Legalize VOP2
   if (isVOP2(MI) || isVOPC(MI)) {
@@ -2321,8 +2322,14 @@ void SIInstrInfo::legalizeOperands(MachineInstr &MI) const {
     return;
   }
 
-  // Legalize MIMG
-  if (isMIMG(MI)) {
+  // Legalize MIMG and MUBUF/MTBUF for shaders.
+  //
+  // Shaders only generate MUBUF/MTBUF instructions via intrinsics or via
+  // scratch memory access. In both cases, the legalization never involves
+  // conversion to the addr64 form.
+  if (isMIMG(MI) ||
+      (AMDGPU::isShader(MF.getFunction()->getCallingConv()) &&
+       (isMUBUF(MI) || isMTBUF(MI)))) {
     MachineOperand *SRsrc = getNamedOperand(MI, AMDGPU::OpName::srsrc);
     if (SRsrc && !RI.isSGPRClass(MRI.getRegClass(SRsrc->getReg()))) {
       unsigned SGPR = readlaneVGPRToSGPR(SRsrc->getReg(), MI, MRI);
@@ -2337,9 +2344,10 @@ void SIInstrInfo::legalizeOperands(MachineInstr &MI) const {
     return;
   }
 
-  // Legalize MUBUF* instructions
+  // Legalize MUBUF* instructions by converting to addr64 form.
   // FIXME: If we start using the non-addr64 instructions for compute, we
-  // may need to legalize them here.
+  // may need to legalize them as above. This especially applies to the
+  // buffer_load_format_* variants and variants with idxen (or bothen).
   int SRsrcIdx =
       AMDGPU::getNamedOperandIdx(MI.getOpcode(), AMDGPU::OpName::srsrc);
   if (SRsrcIdx != -1) {
diff --git a/lib/Target/AMDGPU/SIInstructions.td b/lib/Target/AMDGPU/SIInstructions.td
index 18b7d5d62efe..dde5f2fc6b40 100644
--- a/lib/Target/AMDGPU/SIInstructions.td
+++ b/lib/Target/AMDGPU/SIInstructions.td
@@ -2029,6 +2029,7 @@ def SI_RETURN : PseudoInstSI <
   let hasSideEffects = 1;
   let SALU = 1;
   let hasNoSchedulingInfo = 1;
+  let DisableWQM = 1;
 }
 
 let Uses = [EXEC], Defs = [EXEC, VCC, M0],
diff --git a/lib/Target/AMDGPU/SIWholeQuadMode.cpp b/lib/Target/AMDGPU/SIWholeQuadMode.cpp
index b200c153df0b..1534d5825696 100644
--- a/lib/Target/AMDGPU/SIWholeQuadMode.cpp
+++ b/lib/Target/AMDGPU/SIWholeQuadMode.cpp
@@ -219,13 +219,6 @@ char SIWholeQuadMode::scanInstructions(MachineFunction &MF,
       markInstruction(MI, Flags, Worklist);
       GlobalFlags |= Flags;
     }
-
-    if (WQMOutputs && MBB.succ_empty()) {
-      // This is a prolog shader. Make sure we go back to exact mode at the end.
-      Blocks[&MBB].OutNeeds = StateExact;
-      Worklist.push_back(&MBB);
-      GlobalFlags |= StateExact;
-    }
   }
 
   return GlobalFlags;
diff --git a/lib/Transforms/InstCombine/InstCombineCompares.cpp b/lib/Transforms/InstCombine/InstCombineCompares.cpp
index bfd73f4bbac5..961497fe3c2d 100644
--- a/lib/Transforms/InstCombine/InstCombineCompares.cpp
+++ b/lib/Transforms/InstCombine/InstCombineCompares.cpp
@@ -634,7 +634,7 @@ static bool canRewriteGEPAsOffset(Value *Start, Value *Base,
       }
 
       if (!isa<IntToPtrInst>(V) && !isa<PtrToIntInst>(V) &&
-          !isa<GEPOperator>(V) && !isa<PHINode>(V))
+          !isa<GetElementPtrInst>(V) && !isa<PHINode>(V))
         // We've found some value that we can't explore which is different from
         // the base. Therefore we can't do this transformation.
         return false;
diff --git a/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp b/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp
index d312983ed51b..d88456ee4adc 100644
--- a/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp
+++ b/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp
@@ -579,6 +579,13 @@ static Instruction *unpackLoadToAggregate(InstCombiner &IC, LoadInst &LI) {
         UndefValue::get(T), NewLoad, 0, Name));
     }
 
+    // Bail out if the array is too large. Ideally we would like to optimize
+    // arrays of arbitrary size but this has a terrible impact on compile time.
+    // The threshold here is chosen arbitrarily, maybe needs a little bit of
+    // tuning.
+    if (NumElements > 1024)
+      return nullptr;
+
     const DataLayout &DL = IC.getDataLayout();
     auto EltSize = DL.getTypeAllocSize(ET);
     auto Align = LI.getAlignment();
@@ -1081,6 +1088,13 @@ static bool unpackStoreToAggregate(InstCombiner &IC, StoreInst &SI) {
       return true;
     }
 
+    // Bail out if the array is too large. Ideally we would like to optimize
+    // arrays of arbitrary size but this has a terrible impact on compile time.
+    // The threshold here is chosen arbitrarily, maybe needs a little bit of
+    // tuning.
+    if (NumElements > 1024)
+      return false;
+
     const DataLayout &DL = IC.getDataLayout();
     auto EltSize = DL.getTypeAllocSize(AT->getElementType());
     auto Align = SI.getAlignment();
diff --git a/lib/Transforms/Utils/SimplifyCFG.cpp b/lib/Transforms/Utils/SimplifyCFG.cpp
index 0504646c304e..c197317ac771 100644
--- a/lib/Transforms/Utils/SimplifyCFG.cpp
+++ b/lib/Transforms/Utils/SimplifyCFG.cpp
@@ -2024,14 +2024,20 @@ static bool FoldTwoEntryPHINode(PHINode *PN, const TargetTransformInfo &TTI,
 
   // Move all 'aggressive' instructions, which are defined in the
   // conditional parts of the if's up to the dominating block.
-  if (IfBlock1)
+  if (IfBlock1) {
+    for (auto &I : *IfBlock1)
+      I.dropUnknownNonDebugMetadata();
     DomBlock->getInstList().splice(InsertPt->getIterator(),
                                    IfBlock1->getInstList(), IfBlock1->begin(),
                                    IfBlock1->getTerminator()->getIterator());
-  if (IfBlock2)
+  }
+  if (IfBlock2) {
+    for (auto &I : *IfBlock2)
+      I.dropUnknownNonDebugMetadata();
     DomBlock->getInstList().splice(InsertPt->getIterator(),
                                    IfBlock2->getInstList(), IfBlock2->begin(),
                                    IfBlock2->getTerminator()->getIterator());
+  }
 
   while (PHINode *PN = dyn_cast<PHINode>(BB->begin())) {
     // Change the PHI node into a select instruction.
diff --git a/test/CodeGen/AMDGPU/mubuf-shader-vgpr.ll b/test/CodeGen/AMDGPU/mubuf-shader-vgpr.ll
new file mode 100644
index 000000000000..b528577a7eaa
--- /dev/null
+++ b/test/CodeGen/AMDGPU/mubuf-shader-vgpr.ll
@@ -0,0 +1,49 @@
+;RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck %s -check-prefix=CHECK
+;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s -check-prefix=CHECK
+
+; Test that buffer_load_format with VGPR resource descriptor is properly
+; legalized.
+
+; CHECK-LABEL: {{^}}test_none:
+; CHECK: buffer_load_format_x v0, off, {{s\[[0-9]+:[0-9]+\]}}, 0{{$}}
+define amdgpu_vs float @test_none(<4 x i32> addrspace(2)* inreg %base, i32 %i) {
+main_body:
+  %ptr = getelementptr <4 x i32>, <4 x i32> addrspace(2)* %base, i32 %i
+  %tmp2 = load <4 x i32>, <4 x i32> addrspace(2)* %ptr, align 32
+  %tmp7 = call float @llvm.amdgcn.buffer.load.format.f32(<4 x i32> %tmp2, i32 0, i32 0, i1 0, i1 0)
+  ret float %tmp7
+}
+
+; CHECK-LABEL: {{^}}test_idxen:
+; CHECK: buffer_load_format_x v0, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 idxen{{$}}
+define amdgpu_vs float @test_idxen(<4 x i32> addrspace(2)* inreg %base, i32 %i) {
+main_body:
+  %ptr = getelementptr <4 x i32>, <4 x i32> addrspace(2)* %base, i32 %i
+  %tmp2 = load <4 x i32>, <4 x i32> addrspace(2)* %ptr, align 32
+  %tmp7 = call float @llvm.amdgcn.buffer.load.format.f32(<4 x i32> %tmp2, i32 undef, i32 0, i1 0, i1 0)
+  ret float %tmp7
+}
+
+; CHECK-LABEL: {{^}}test_offen:
+; CHECK: buffer_load_format_x v0, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen{{$}}
+define amdgpu_vs float @test_offen(<4 x i32> addrspace(2)* inreg %base, i32 %i) {
+main_body:
+  %ptr = getelementptr <4 x i32>, <4 x i32> addrspace(2)* %base, i32 %i
+  %tmp2 = load <4 x i32>, <4 x i32> addrspace(2)* %ptr, align 32
+  %tmp7 = call float @llvm.amdgcn.buffer.load.format.f32(<4 x i32> %tmp2, i32 0, i32 undef, i1 0, i1 0)
+  ret float %tmp7
+}
+
+; CHECK-LABEL: {{^}}test_both:
+; CHECK: buffer_load_format_x v0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0 idxen offen{{$}}
+define amdgpu_vs float @test_both(<4 x i32> addrspace(2)* inreg %base, i32 %i) {
+main_body:
+  %ptr = getelementptr <4 x i32>, <4 x i32> addrspace(2)* %base, i32 %i
+  %tmp2 = load <4 x i32>, <4 x i32> addrspace(2)* %ptr, align 32
+  %tmp7 = call float @llvm.amdgcn.buffer.load.format.f32(<4 x i32> %tmp2, i32 undef, i32 undef, i1 0, i1 0)
+  ret float %tmp7
+}
+
+declare float @llvm.amdgcn.buffer.load.format.f32(<4 x i32>, i32, i32, i1, i1) nounwind readonly
+
+attributes #0 = { nounwind readnone }
diff --git a/test/CodeGen/AMDGPU/wqm.ll b/test/CodeGen/AMDGPU/wqm.ll
index 809a7ba9b826..41e426457889 100644
--- a/test/CodeGen/AMDGPU/wqm.ll
+++ b/test/CodeGen/AMDGPU/wqm.ll
@@ -17,17 +17,18 @@ main_body:
 ;CHECK-LABEL: {{^}}test2:
 ;CHECK-NEXT: ; %main_body
 ;CHECK-NEXT: s_wqm_b64 exec, exec
-;CHECK: image_sample
 ;CHECK-NOT: exec
-;CHECK: _load_dword v0,
-define amdgpu_ps float @test2(<8 x i32> inreg %rsrc, <4 x i32> inreg %sampler, float addrspace(1)* inreg %ptr, <4 x i32> %c) {
+define amdgpu_ps void @test2(<8 x i32> inreg %rsrc, <4 x i32> inreg %sampler, float addrspace(1)* inreg %ptr, <4 x i32> %c) {
 main_body:
   %c.1 = call <4 x float> @llvm.SI.image.sample.v4i32(<4 x i32> %c, <8 x i32> %rsrc, <4 x i32> %sampler, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
   %c.2 = bitcast <4 x float> %c.1 to <4 x i32>
   %c.3 = extractelement <4 x i32> %c.2, i32 0
   %gep = getelementptr float, float addrspace(1)* %ptr, i32 %c.3
   %data = load float, float addrspace(1)* %gep
-  ret float %data
+
+  call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %data, float undef, float undef, float undef)
+
+  ret void
 }
 
 ; ... but disabled for stores (and, in this simple case, not re-enabled).
@@ -414,6 +415,46 @@ entry:
   ret void
 }
 
+; Must return to exact at the end of a non-void returning shader,
+; otherwise the EXEC mask exported by the epilog will be wrong. This is true
+; even if the shader has no kills, because a kill could have happened in a
+; previous shader fragment.
+;
+; CHECK-LABEL: {{^}}test_nonvoid_return:
+; CHECK: s_mov_b64 [[LIVE:s\[[0-9]+:[0-9]+\]]], exec
+; CHECK: s_wqm_b64 exec, exec
+;
+; CHECK: s_and_b64 exec, exec, [[LIVE]]
+; CHECK-NOT: exec
+define amdgpu_ps <4 x float> @test_nonvoid_return() nounwind {
+  %tex = call <4 x float> @llvm.SI.image.sample.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
+  %tex.i = bitcast <4 x float> %tex to <4 x i32>
+  %dtex = call <4 x float> @llvm.SI.image.sample.v4i32(<4 x i32> %tex.i, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
+  ret <4 x float> %dtex
+}
+
+; CHECK-LABEL: {{^}}test_nonvoid_return_unreachable:
+; CHECK: s_mov_b64 [[LIVE:s\[[0-9]+:[0-9]+\]]], exec
+; CHECK: s_wqm_b64 exec, exec
+;
+; CHECK: s_and_b64 exec, exec, [[LIVE]]
+; CHECK-NOT: exec
+define amdgpu_ps <4 x float> @test_nonvoid_return_unreachable(i32 inreg %c) nounwind {
+entry:
+  %tex = call <4 x float> @llvm.SI.image.sample.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
+  %tex.i = bitcast <4 x float> %tex to <4 x i32>
+  %dtex = call <4 x float> @llvm.SI.image.sample.v4i32(<4 x i32> %tex.i, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
+
+  %cc = icmp sgt i32 %c, 0
+  br i1 %cc, label %if, label %else
+
+if:
+  store volatile <4 x float> %dtex, <4 x float>* undef
+  unreachable
+
+else:
+  ret <4 x float> %dtex
+}
 
 declare void @llvm.amdgcn.image.store.v4i32(<4 x float>, <4 x i32>, <8 x i32>, i32, i1, i1, i1, i1) #1
 declare void @llvm.amdgcn.buffer.store.f32(float, <4 x i32>, i32, i32, i1, i1) #1
diff --git a/test/CodeGen/X86/mul-i1024.ll b/test/CodeGen/X86/mul-i1024.ll
new file mode 100644
index 000000000000..60933b1e1fa1
--- /dev/null
+++ b/test/CodeGen/X86/mul-i1024.ll
@@ -0,0 +1,5938 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=i386-unknown | FileCheck %s --check-prefix=X32
+; RUN: llc < %s -mtriple=x86_64-unknown | FileCheck %s --check-prefix=X64
+
+define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
+; X32-LABEL: test_1024:
+; X32:       # BB#0:
+; X32-NEXT:    pushl %ebp
+; X32-NEXT:    movl %esp, %ebp
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    andl $-8, %esp
+; X32-NEXT:    subl $2640, %esp # imm = 0xA50
+; X32-NEXT:    movl 8(%ebp), %eax
+; X32-NEXT:    movl 64(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 68(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 72(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 76(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 80(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 84(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 88(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 92(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 96(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 100(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 104(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 108(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 112(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 116(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 120(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 124(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl (%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 4(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 8(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 12(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 16(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 20(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 24(%eax), %ecx
+; X32-NEXT:    movl %ecx, (%esp) # 4-byte Spill
+; X32-NEXT:    movl 28(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 32(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 36(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 40(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 44(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 48(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 52(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 56(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 60(%eax), %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 12(%ebp), %eax
+; X32-NEXT:    movl 48(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 52(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 56(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 60(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 32(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 36(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 40(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 44(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 16(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 20(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 24(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 28(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 8(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 12(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 112(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 116(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 120(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 124(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 96(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 100(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 104(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 108(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 80(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 84(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 88(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 92(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 64(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 68(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 72(%eax), %edi
+; X32-NEXT:    movl 76(%eax), %esi
+; X32-NEXT:    movl (%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 4(%eax), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edx
+; X32-NEXT:    pushl %ecx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl %esi, %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    pushl %ecx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl %ebx, %esi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl %edi, %ebx
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    movl %ebx, %esi
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl %edi, %ebx
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl %esi, %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    addl %edi, %ecx
+; X32-NEXT:    movl %edx, %eax
+; X32-NEXT:    adcl %esi, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, (%esp) # 4-byte Spill
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    addl %edx, %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %ecx, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    adcl %esi, %edi
+; X32-NEXT:    movl $0, %ebx
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    sbbl %ecx, %ecx
+; X32-NEXT:    andl $1, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    adcl (%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, (%esp) # 4-byte Spill
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl %ecx, %edx
+; X32-NEXT:    addl %eax, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl %ecx, %esi
+; X32-NEXT:    adcl %eax, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %eax, %ecx
+; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %ebx, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl (%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, (%esp) # 4-byte Spill
+; X32-NEXT:    adcl %ecx, %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    addl %edx, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %edx, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl %edi, %esi
+; X32-NEXT:    adcl %ebx, %ecx
+; X32-NEXT:    movl $0, %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    sbbl %eax, %eax
+; X32-NEXT:    andl $1, %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    adcl (%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    addl %edi, %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %edi, %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %edi, %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %edi, %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    addl %esi, %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    adcl %ecx, %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    adcl %edx, %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %eax, %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    adcl %edx, %ecx
+; X32-NEXT:    movl $0, %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    sbbl %esi, %esi
+; X32-NEXT:    andl $1, %esi
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    addl %eax, %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %ecx, %ebx
+; X32-NEXT:    movl %ebx, (%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl %esi, %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl %edx, %esi
+; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    sbbl %edx, %edx
+; X32-NEXT:    andl $1, %edx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    adcl %ecx, %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, (%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl %eax, %edx
+; X32-NEXT:    adcl %ecx, %esi
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    sbbl %ecx, %ecx
+; X32-NEXT:    andl $1, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    addl %edx, %eax
+; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl %edx, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl %edx, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl (%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, (%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    sbbl %eax, %eax
+; X32-NEXT:    andl $1, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl %eax, %edx
+; X32-NEXT:    adcl %ecx, %esi
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    sbbl %ecx, %ecx
+; X32-NEXT:    andl $1, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    addl %edx, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl %edi, %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl (%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    addl %esi, %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %edx, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl %ebx, (%esp) # 4-byte Spill
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    addl %edi, %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %ecx, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    addl %ebx, %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl $0, %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    sbbl %eax, %eax
+; X32-NEXT:    andl $1, %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    adcl (%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, (%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %ebx, %edi
+; X32-NEXT:    movl %edi, %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %ecx, %eax
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %ecx, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    addl %esi, %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %edx, %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl %edi, %edx
+; X32-NEXT:    adcl (%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl %ecx, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl %ebx, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl %edx, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl %esi, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl %eax, %edx
+; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    movl $0, %edi
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    sbbl %eax, %eax
+; X32-NEXT:    andl $1, %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, (%esp) # 4-byte Spill
+; X32-NEXT:    movl (%esp), %esi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, (%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    addl %edx, %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %ecx, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %edi, (%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl %eax, %edx
+; X32-NEXT:    adcl %ecx, %esi
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    sbbl %ecx, %ecx
+; X32-NEXT:    andl $1, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    addl %edx, %eax
+; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, (%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl %eax, %edx
+; X32-NEXT:    adcl %ecx, %esi
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    sbbl %ecx, %ecx
+; X32-NEXT:    andl $1, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    addl %edx, %ecx
+; X32-NEXT:    adcl %esi, %edi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl %edx, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl (%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, (%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    sbbl %eax, %eax
+; X32-NEXT:    andl $1, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl %eax, %edx
+; X32-NEXT:    adcl %ecx, %esi
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    sbbl %ecx, %ecx
+; X32-NEXT:    andl $1, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    addl %edx, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl (%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, (%esp) # 4-byte Spill
+; X32-NEXT:    addl %eax, %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %esi, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    addl %eax, %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %eax, %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    movl %eax, %edx
+; X32-NEXT:    adcl %edi, %esi
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    sbbl %ecx, %ecx
+; X32-NEXT:    andl $1, %ecx
+; X32-NEXT:    addl (%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl %ecx, %ebx
+; X32-NEXT:    addl %eax, %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, (%esp) # 4-byte Spill
+; X32-NEXT:    movl %ecx, %edi
+; X32-NEXT:    adcl %eax, %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %ecx, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    adcl %edx, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %esi, %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl %ebx, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl %edi, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl %esi, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl %ecx, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl %edx, %eax
+; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    movl $0, %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    sbbl %esi, %esi
+; X32-NEXT:    andl $1, %esi
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    adcl (%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    addl %eax, %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %ecx, %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl %esi, %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl %eax, %edx
+; X32-NEXT:    adcl %ecx, %esi
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    sbbl %ecx, %ecx
+; X32-NEXT:    andl $1, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    adcl (%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    addl %edx, %eax
+; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl %eax, %edx
+; X32-NEXT:    adcl %ecx, %esi
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    sbbl %ecx, %ecx
+; X32-NEXT:    andl $1, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    addl %edx, %ecx
+; X32-NEXT:    adcl %esi, %edi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl %edx, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    sbbl %eax, %eax
+; X32-NEXT:    andl $1, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl %eax, %edx
+; X32-NEXT:    adcl %ecx, %esi
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    sbbl %ecx, %ecx
+; X32-NEXT:    andl $1, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    addl %edx, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl %edi, %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, %edx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    sbbl %eax, %eax
+; X32-NEXT:    andl $1, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl %edi, %edx
+; X32-NEXT:    adcl %eax, %ecx
+; X32-NEXT:    movl $0, %ebx
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    sbbl %eax, %eax
+; X32-NEXT:    andl $1, %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl (%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    addl %edx, %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %ecx, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %ebx, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl %eax, %edx
+; X32-NEXT:    adcl %ecx, %esi
+; X32-NEXT:    movl $0, %edi
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    sbbl %ebx, %ebx
+; X32-NEXT:    andl $1, %ebx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl (%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, (%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    addl %edx, %ecx
+; X32-NEXT:    movl (%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl %esi, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    adcl %edi, %esi
+; X32-NEXT:    adcl %ebx, %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, (%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl %eax, %edx
+; X32-NEXT:    adcl %ecx, %esi
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    sbbl %ecx, %ecx
+; X32-NEXT:    andl $1, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    addl %edx, %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl %esi, %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    adcl %ecx, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl (%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, (%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl %edx, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl %esi, %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    sbbl %eax, %eax
+; X32-NEXT:    andl $1, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl %edi, %edx
+; X32-NEXT:    adcl %ebx, %esi
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    sbbl %ebx, %ebx
+; X32-NEXT:    andl $1, %ebx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl %edi, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl %edi, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    addl %edx, %eax
+; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    adcl %ebx, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl %edi, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    adcl %ebx, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, (%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl %eax, %edi
+; X32-NEXT:    adcl %ecx, %esi
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    sbbl %ecx, %ecx
+; X32-NEXT:    andl $1, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    addl %eax, %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %ecx, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    adcl %edx, %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    addl %edi, %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %esi, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl %eax, %edx
+; X32-NEXT:    adcl %ecx, %esi
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    sbbl %ecx, %ecx
+; X32-NEXT:    andl $1, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    addl %edx, %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl %esi, %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl %eax, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %ecx, %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl %eax, %edx
+; X32-NEXT:    adcl %ecx, %esi
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    sbbl %ebx, %ebx
+; X32-NEXT:    andl $1, %ebx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %ecx, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl %edi, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    addl %edx, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl %esi, %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl %ebx, %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    adcl %ecx, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    adcl %ecx, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    movl %esi, %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl %edi, %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    sbbl %eax, %eax
+; X32-NEXT:    andl $1, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl %edi, %edx
+; X32-NEXT:    adcl %ebx, %ecx
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    sbbl %ebx, %ebx
+; X32-NEXT:    andl $1, %ebx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl %edi, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl %edi, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    addl %edx, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    adcl %ecx, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl %ebx, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    adcl %esi, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    adcl %esi, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    adcl %esi, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl %edi, %edx
+; X32-NEXT:    adcl %ebx, %esi
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    sbbl %ecx, %ecx
+; X32-NEXT:    andl $1, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    addl %edx, %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %esi, %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl %edx, %eax
+; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    movl $0, %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    sbbl %esi, %esi
+; X32-NEXT:    andl $1, %esi
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    addl %eax, %edx
+; X32-NEXT:    adcl %ecx, %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl %edx, %eax
+; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    movl $0, %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    sbbl %esi, %esi
+; X32-NEXT:    andl $1, %esi
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl %edi, %ebx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    addl %eax, %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %ecx, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl %edx, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl %esi, %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl %eax, %edx
+; X32-NEXT:    adcl %ecx, %esi
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    sbbl %ebx, %ebx
+; X32-NEXT:    andl $1, %ebx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %ecx, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl %edi, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    addl %edx, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl %esi, %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    adcl %ebx, %esi
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl %eax, %edx
+; X32-NEXT:    adcl %ecx, %esi
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    sbbl %ebx, %ebx
+; X32-NEXT:    andl $1, %ebx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    addl %edx, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, %esi
+; X32-NEXT:    adcl %ebx, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    sbbl %eax, %eax
+; X32-NEXT:    andl $1, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl %edx, %eax
+; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    movl $0, %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    sbbl %esi, %esi
+; X32-NEXT:    andl $1, %esi
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    addl %eax, %ebx
+; X32-NEXT:    adcl %ecx, %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl %edx, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl %edx, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl %edi, %edx
+; X32-NEXT:    adcl %ebx, %esi
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    sbbl %ecx, %ecx
+; X32-NEXT:    andl $1, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    addl %edx, %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %esi, %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    addl %ecx, %ebx
+; X32-NEXT:    adcl %edx, %eax
+; X32-NEXT:    movl $0, %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    sbbl %edi, %edi
+; X32-NEXT:    andl $1, %edi
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    addl %ebx, %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    adcl %eax, %ebx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    adcl %edi, %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl (%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl 16(%ebp), %ebx
+; X32-NEXT:    movl %ecx, 4(%ebx)
+; X32-NEXT:    movl 16(%ebp), %ecx
+; X32-NEXT:    movl %eax, (%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 8(%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 12(%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 16(%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 20(%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 24(%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 28(%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 32(%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 36(%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 40(%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 44(%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 48(%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 52(%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 56(%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 60(%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 64(%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 68(%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 72(%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 76(%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 80(%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 84(%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 88(%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 92(%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 96(%ecx)
+; X32-NEXT:    movl %edx, 100(%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 104(%ecx)
+; X32-NEXT:    movl %esi, 108(%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 112(%ecx)
+; X32-NEXT:    movl %edi, 116(%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 120(%ecx)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, 124(%ecx)
+; X32-NEXT:    leal -12(%ebp), %esp
+; X32-NEXT:    popl %esi
+; X32-NEXT:    popl %edi
+; X32-NEXT:    popl %ebx
+; X32-NEXT:    popl %ebp
+; X32-NEXT:    retl
+;
+; X64-LABEL: test_1024:
+; X64:       # BB#0:
+; X64-NEXT:    pushq %rbp
+; X64-NEXT:    pushq %r15
+; X64-NEXT:    pushq %r14
+; X64-NEXT:    pushq %r13
+; X64-NEXT:    pushq %r12
+; X64-NEXT:    pushq %rbx
+; X64-NEXT:    subq $360, %rsp # imm = 0x168
+; X64-NEXT:    movq %rdx, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq 48(%rdi), %r9
+; X64-NEXT:    movq %r9, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq 40(%rdi), %rcx
+; X64-NEXT:    movq %rcx, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq 32(%rdi), %rax
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rdi, %r10
+; X64-NEXT:    xorl %r8d, %r8d
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rdx, %rdi
+; X64-NEXT:    movq %rax, %r11
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rax, %rcx
+; X64-NEXT:    addq %rdi, %rcx
+; X64-NEXT:    movq %rdx, %rbx
+; X64-NEXT:    adcq $0, %rbx
+; X64-NEXT:    addq %r11, %rcx
+; X64-NEXT:    movq %rcx, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rdi, %rbp
+; X64-NEXT:    adcq $0, %rbp
+; X64-NEXT:    addq %rbx, %rbp
+; X64-NEXT:    sbbq %rbx, %rbx
+; X64-NEXT:    andl $1, %ebx
+; X64-NEXT:    addq %rax, %rbp
+; X64-NEXT:    adcq %rdx, %rbx
+; X64-NEXT:    movq %r9, %rax
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rdx, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %r11, %r13
+; X64-NEXT:    addq %rax, %r13
+; X64-NEXT:    movq %rdi, %rax
+; X64-NEXT:    movq %rdi, %r15
+; X64-NEXT:    movq %r15, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq %rdx, %rax
+; X64-NEXT:    addq %rbp, %r13
+; X64-NEXT:    movq %r13, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq %rbx, %rax
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rsi, %r8
+; X64-NEXT:    movq (%r8), %rax
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    xorl %ebp, %ebp
+; X64-NEXT:    mulq %rbp
+; X64-NEXT:    movq %rax, %r14
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    movq 8(%r8), %rax
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    mulq %rbp
+; X64-NEXT:    xorl %r9d, %r9d
+; X64-NEXT:    movq %rax, %r12
+; X64-NEXT:    addq %rcx, %r12
+; X64-NEXT:    movq %rdx, %rbp
+; X64-NEXT:    adcq $0, %rbp
+; X64-NEXT:    addq %r14, %r12
+; X64-NEXT:    movq %rcx, %rbx
+; X64-NEXT:    movq %rcx, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq $0, %rbx
+; X64-NEXT:    addq %rbp, %rbx
+; X64-NEXT:    sbbq %rbp, %rbp
+; X64-NEXT:    andl $1, %ebp
+; X64-NEXT:    addq %rax, %rbx
+; X64-NEXT:    adcq %rdx, %rbp
+; X64-NEXT:    movq 16(%r8), %rax
+; X64-NEXT:    movq %r8, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    mulq %r9
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rdx, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %r14, %rdi
+; X64-NEXT:    movq %rdi, %r9
+; X64-NEXT:    addq %rax, %r9
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    adcq %rdx, %rax
+; X64-NEXT:    addq %rbx, %r9
+; X64-NEXT:    adcq %rbp, %rax
+; X64-NEXT:    movq %rax, %rbp
+; X64-NEXT:    movq %r11, %rax
+; X64-NEXT:    movq %r11, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    addq %rdi, %rax
+; X64-NEXT:    adcq %rcx, %r15
+; X64-NEXT:    movq %r15, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq (%r10), %rax
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    xorl %r15d, %r15d
+; X64-NEXT:    mulq %r15
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    movq %rax, %r14
+; X64-NEXT:    addq %rdi, %rax
+; X64-NEXT:    movq %rsi, %rax
+; X64-NEXT:    adcq %rcx, %rax
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq 32(%r8), %rax
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    mulq %r15
+; X64-NEXT:    xorl %r8d, %r8d
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rdx, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %r14, %rcx
+; X64-NEXT:    addq %rax, %rcx
+; X64-NEXT:    movq %rsi, %rax
+; X64-NEXT:    adcq %rdx, %rax
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    addq %rdi, %r11
+; X64-NEXT:    movq %r11, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rdi, %r11
+; X64-NEXT:    movq %r11, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; X64-NEXT:    adcq %r12, %rax
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq %r9, %r13
+; X64-NEXT:    movq %r13, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %r9, %rdi
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; X64-NEXT:    adcq %rbp, %rax
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rbp, %r9
+; X64-NEXT:    movq 8(%r10), %rax
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %r10, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    xorl %ecx, %ecx
+; X64-NEXT:    movq %rax, %r15
+; X64-NEXT:    addq %rsi, %r15
+; X64-NEXT:    movq %rdx, %rbx
+; X64-NEXT:    adcq $0, %rbx
+; X64-NEXT:    addq %r14, %r15
+; X64-NEXT:    movq %rsi, %rbp
+; X64-NEXT:    movq %rsi, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq $0, %rbp
+; X64-NEXT:    addq %rbx, %rbp
+; X64-NEXT:    sbbq %r8, %r8
+; X64-NEXT:    andl $1, %r8d
+; X64-NEXT:    addq %rax, %rbp
+; X64-NEXT:    adcq %rdx, %r8
+; X64-NEXT:    movq 16(%r10), %rax
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    mulq %rcx
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rdx, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %r14, %rbx
+; X64-NEXT:    addq %rax, %rbx
+; X64-NEXT:    movq %rsi, %r10
+; X64-NEXT:    adcq %rdx, %r10
+; X64-NEXT:    addq %rbp, %rbx
+; X64-NEXT:    adcq %r8, %r10
+; X64-NEXT:    movq %r14, %rax
+; X64-NEXT:    movq %r14, (%rsp) # 8-byte Spill
+; X64-NEXT:    addq %r11, %rax
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %r15, %rcx
+; X64-NEXT:    adcq %rcx, %r12
+; X64-NEXT:    movq %r12, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq %rbx, %rdi
+; X64-NEXT:    movq %rdi, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rbx, %r8
+; X64-NEXT:    adcq %r10, %r9
+; X64-NEXT:    movq %r9, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %r13 # 8-byte Reload
+; X64-NEXT:    movq 40(%r13), %rax
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    xorl %edx, %edx
+; X64-NEXT:    mulq %rdx
+; X64-NEXT:    xorl %r11d, %r11d
+; X64-NEXT:    movq %rax, %rsi
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %r9 # 8-byte Reload
+; X64-NEXT:    addq %r9, %rsi
+; X64-NEXT:    movq %rdx, %rbx
+; X64-NEXT:    adcq $0, %rbx
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    addq %rdi, %rsi
+; X64-NEXT:    movq %r9, %rbp
+; X64-NEXT:    adcq $0, %rbp
+; X64-NEXT:    addq %rbx, %rbp
+; X64-NEXT:    sbbq %rbx, %rbx
+; X64-NEXT:    andl $1, %ebx
+; X64-NEXT:    addq %rax, %rbp
+; X64-NEXT:    adcq %rdx, %rbx
+; X64-NEXT:    movq 48(%r13), %rax
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    mulq %r11
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rdx, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rdi, %r15
+; X64-NEXT:    movq %rdi, %r11
+; X64-NEXT:    addq %rax, %r15
+; X64-NEXT:    movq %r9, %rdi
+; X64-NEXT:    adcq %rdx, %rdi
+; X64-NEXT:    addq %rbp, %r15
+; X64-NEXT:    adcq %rbx, %rdi
+; X64-NEXT:    addq %r11, %r14
+; X64-NEXT:    movq %r14, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq %rsi, %rcx
+; X64-NEXT:    movq %rcx, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq %r15, %r8
+; X64-NEXT:    movq %r8, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq %rdi, %r10
+; X64-NEXT:    movq %r10, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %r14 # 8-byte Reload
+; X64-NEXT:    movq %r14, %rax
+; X64-NEXT:    addq %r11, %rax
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; X64-NEXT:    adcq %r9, %rax
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %r14, %rax
+; X64-NEXT:    addq %r11, %rax
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %rsi # 8-byte Folded Reload
+; X64-NEXT:    movq %rsi, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %r15 # 8-byte Folded Reload
+; X64-NEXT:    movq %r15, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %rdi # 8-byte Folded Reload
+; X64-NEXT:    movq %rdi, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rax, %r9
+; X64-NEXT:    movq %rdx, %rbx
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; X64-NEXT:    movq 56(%rax), %rax
+; X64-NEXT:    movq %rax, %rsi
+; X64-NEXT:    movq %rsi, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rdi, %r10
+; X64-NEXT:    movq %rdx, %rdi
+; X64-NEXT:    movq %rax, %rbp
+; X64-NEXT:    addq %rbx, %rbp
+; X64-NEXT:    adcq $0, %rdi
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    mulq %rcx
+; X64-NEXT:    movq %rdx, %rbx
+; X64-NEXT:    movq %rax, %r8
+; X64-NEXT:    addq %rbp, %r8
+; X64-NEXT:    adcq $0, %rbx
+; X64-NEXT:    addq %rdi, %rbx
+; X64-NEXT:    sbbq %rdi, %rdi
+; X64-NEXT:    andl $1, %edi
+; X64-NEXT:    movq %rsi, %rax
+; X64-NEXT:    mulq %rcx
+; X64-NEXT:    movq %rcx, %r11
+; X64-NEXT:    addq %rbx, %rax
+; X64-NEXT:    adcq %rdi, %rdx
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %r15 # 8-byte Reload
+; X64-NEXT:    addq -{{[0-9]+}}(%rsp), %r15 # 8-byte Folded Reload
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %r12 # 8-byte Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %r12 # 8-byte Folded Reload
+; X64-NEXT:    addq %rax, %r15
+; X64-NEXT:    adcq %rdx, %r12
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    movq %rdi, %rax
+; X64-NEXT:    movq %r10, %rsi
+; X64-NEXT:    mulq %rsi
+; X64-NEXT:    movq %rdx, %r10
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    mulq %rsi
+; X64-NEXT:    movq %rdx, %rbp
+; X64-NEXT:    movq %rax, %rbx
+; X64-NEXT:    addq %r10, %rbx
+; X64-NEXT:    adcq $0, %rbp
+; X64-NEXT:    movq %rdi, %rax
+; X64-NEXT:    movq %rdi, %r10
+; X64-NEXT:    mulq %r11
+; X64-NEXT:    movq %rdx, %rdi
+; X64-NEXT:    addq %rbx, %rax
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq $0, %rdi
+; X64-NEXT:    addq %rbp, %rdi
+; X64-NEXT:    sbbq %rbp, %rbp
+; X64-NEXT:    andl $1, %ebp
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    movq %rcx, %rsi
+; X64-NEXT:    mulq %r11
+; X64-NEXT:    movq %rdx, %r13
+; X64-NEXT:    movq %rax, %rbx
+; X64-NEXT:    addq %rdi, %rbx
+; X64-NEXT:    adcq %rbp, %r13
+; X64-NEXT:    addq {{[0-9]+}}(%rsp), %rbx # 8-byte Folded Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %r13 # 8-byte Folded Reload
+; X64-NEXT:    addq %r9, %rbx
+; X64-NEXT:    adcq %r8, %r13
+; X64-NEXT:    adcq $0, %r15
+; X64-NEXT:    adcq $0, %r12
+; X64-NEXT:    movq %r10, %rbp
+; X64-NEXT:    movq %rbp, %rax
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    movq %rax, %r9
+; X64-NEXT:    movq %rsi, %rax
+; X64-NEXT:    movq %rsi, %r8
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    movq %rax, %rdi
+; X64-NEXT:    addq %rcx, %rdi
+; X64-NEXT:    adcq $0, %rsi
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; X64-NEXT:    movq 24(%rax), %r14
+; X64-NEXT:    movq %rbp, %rax
+; X64-NEXT:    mulq %r14
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    addq %rdi, %rax
+; X64-NEXT:    movq %rax, %rdi
+; X64-NEXT:    adcq $0, %rcx
+; X64-NEXT:    addq %rsi, %rcx
+; X64-NEXT:    sbbq %rsi, %rsi
+; X64-NEXT:    andl $1, %esi
+; X64-NEXT:    movq %r8, %rax
+; X64-NEXT:    mulq %r14
+; X64-NEXT:    addq %rcx, %rax
+; X64-NEXT:    adcq %rsi, %rdx
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rbp # 8-byte Reload
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %r11 # 8-byte Reload
+; X64-NEXT:    addq %r11, %rbp
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rsi # 8-byte Reload
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %rsi # 8-byte Folded Reload
+; X64-NEXT:    addq %rax, %rbp
+; X64-NEXT:    adcq %rdx, %rsi
+; X64-NEXT:    addq %rbx, %r9
+; X64-NEXT:    movq %r9, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq %r13, %rdi
+; X64-NEXT:    movq %rdi, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq $0, %rbp
+; X64-NEXT:    adcq $0, %rsi
+; X64-NEXT:    addq %r15, %rbp
+; X64-NEXT:    adcq %r12, %rsi
+; X64-NEXT:    movl $0, %r10d
+; X64-NEXT:    adcq $0, %r10
+; X64-NEXT:    sbbq %r15, %r15
+; X64-NEXT:    andl $1, %r15d
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rdx, %r12
+; X64-NEXT:    movq %rax, %r13
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %r8 # 8-byte Reload
+; X64-NEXT:    movq %r8, %rax
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rdx, %rbx
+; X64-NEXT:    movq %rax, %rdi
+; X64-NEXT:    addq %r12, %rdi
+; X64-NEXT:    adcq $0, %rbx
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    mulq %r14
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    movq %rax, %r9
+; X64-NEXT:    addq %rdi, %r9
+; X64-NEXT:    adcq $0, %rcx
+; X64-NEXT:    addq %rbx, %rcx
+; X64-NEXT:    sbbq %rdi, %rdi
+; X64-NEXT:    andl $1, %edi
+; X64-NEXT:    movq %r8, %rax
+; X64-NEXT:    mulq %r14
+; X64-NEXT:    movq %r14, %r12
+; X64-NEXT:    addq %rcx, %rax
+; X64-NEXT:    adcq %rdi, %rdx
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    addq %r11, %rcx
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %rdi # 8-byte Folded Reload
+; X64-NEXT:    addq %rax, %rcx
+; X64-NEXT:    adcq %rdx, %rdi
+; X64-NEXT:    addq %rbp, %r13
+; X64-NEXT:    adcq %rsi, %r9
+; X64-NEXT:    adcq %r10, %rcx
+; X64-NEXT:    adcq %r15, %rdi
+; X64-NEXT:    addq {{[0-9]+}}(%rsp), %r13 # 8-byte Folded Reload
+; X64-NEXT:    movq %r13, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %r9 # 8-byte Folded Reload
+; X64-NEXT:    movq %r9, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %rcx # 8-byte Folded Reload
+; X64-NEXT:    movq %rcx, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %rdi # 8-byte Folded Reload
+; X64-NEXT:    movq %rdi, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rsi # 8-byte Reload
+; X64-NEXT:    movq %rsi, %rax
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rax, %r11
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; X64-NEXT:    movq 24(%rax), %rax
+; X64-NEXT:    movq %rax, %r8
+; X64-NEXT:    movq %r8, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rdi, %r13
+; X64-NEXT:    movq %rdx, %rdi
+; X64-NEXT:    movq %rax, %rbx
+; X64-NEXT:    addq %rcx, %rbx
+; X64-NEXT:    adcq $0, %rdi
+; X64-NEXT:    movq %rsi, %rax
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rbp # 8-byte Reload
+; X64-NEXT:    mulq %rbp
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    movq %rax, %r15
+; X64-NEXT:    addq %rbx, %r15
+; X64-NEXT:    adcq $0, %rcx
+; X64-NEXT:    addq %rdi, %rcx
+; X64-NEXT:    sbbq %rsi, %rsi
+; X64-NEXT:    andl $1, %esi
+; X64-NEXT:    movq %r8, %rax
+; X64-NEXT:    mulq %rbp
+; X64-NEXT:    movq %rbp, %r14
+; X64-NEXT:    addq %rcx, %rax
+; X64-NEXT:    adcq %rsi, %rdx
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %r8 # 8-byte Reload
+; X64-NEXT:    addq -{{[0-9]+}}(%rsp), %r8 # 8-byte Folded Reload
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %r10 # 8-byte Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %r10 # 8-byte Folded Reload
+; X64-NEXT:    addq %rax, %r8
+; X64-NEXT:    adcq %rdx, %r10
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rsi # 8-byte Reload
+; X64-NEXT:    movq %rsi, %rax
+; X64-NEXT:    mulq %r13
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rbp # 8-byte Reload
+; X64-NEXT:    movq %rbp, %rax
+; X64-NEXT:    mulq %r13
+; X64-NEXT:    movq %rdx, %rdi
+; X64-NEXT:    movq %rax, %rbx
+; X64-NEXT:    addq %rcx, %rbx
+; X64-NEXT:    adcq $0, %rdi
+; X64-NEXT:    movq %rsi, %rax
+; X64-NEXT:    movq %rsi, %r9
+; X64-NEXT:    mulq %r14
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    addq %rbx, %rax
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq $0, %rsi
+; X64-NEXT:    addq %rdi, %rsi
+; X64-NEXT:    sbbq %rdi, %rdi
+; X64-NEXT:    andl $1, %edi
+; X64-NEXT:    movq %rbp, %rax
+; X64-NEXT:    mulq %r14
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    movq %rax, %rbx
+; X64-NEXT:    addq %rsi, %rbx
+; X64-NEXT:    adcq %rdi, %rcx
+; X64-NEXT:    addq -{{[0-9]+}}(%rsp), %rbx # 8-byte Folded Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %rcx # 8-byte Folded Reload
+; X64-NEXT:    addq %r11, %rbx
+; X64-NEXT:    adcq %r15, %rcx
+; X64-NEXT:    adcq $0, %r8
+; X64-NEXT:    adcq $0, %r10
+; X64-NEXT:    movq %r9, %rsi
+; X64-NEXT:    movq %rsi, %rax
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rdx, %r9
+; X64-NEXT:    movq %rax, %r11
+; X64-NEXT:    movq %rbp, %r14
+; X64-NEXT:    movq %r14, %rax
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rdi, %r13
+; X64-NEXT:    movq %rdx, %rdi
+; X64-NEXT:    movq %rax, %rbp
+; X64-NEXT:    addq %r9, %rbp
+; X64-NEXT:    adcq $0, %rdi
+; X64-NEXT:    movq %rsi, %rax
+; X64-NEXT:    mulq %r12
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    addq %rbp, %rax
+; X64-NEXT:    movq %rax, %r15
+; X64-NEXT:    adcq $0, %rsi
+; X64-NEXT:    addq %rdi, %rsi
+; X64-NEXT:    sbbq %rdi, %rdi
+; X64-NEXT:    andl $1, %edi
+; X64-NEXT:    movq %r14, %rax
+; X64-NEXT:    mulq %r12
+; X64-NEXT:    addq %rsi, %rax
+; X64-NEXT:    adcq %rdi, %rdx
+; X64-NEXT:    movq (%rsp), %rsi # 8-byte Reload
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %r14 # 8-byte Reload
+; X64-NEXT:    addq %r14, %rsi
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rbp # 8-byte Reload
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %rbp # 8-byte Folded Reload
+; X64-NEXT:    addq %rax, %rsi
+; X64-NEXT:    adcq %rdx, %rbp
+; X64-NEXT:    addq %rbx, %r11
+; X64-NEXT:    movq %r11, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq %rcx, %r15
+; X64-NEXT:    movq %r15, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq $0, %rsi
+; X64-NEXT:    adcq $0, %rbp
+; X64-NEXT:    addq %r8, %rsi
+; X64-NEXT:    adcq %r10, %rbp
+; X64-NEXT:    movl $0, %r10d
+; X64-NEXT:    adcq $0, %r10
+; X64-NEXT:    sbbq %r15, %r15
+; X64-NEXT:    andl $1, %r15d
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    mulq %r13
+; X64-NEXT:    movq %rdx, %r9
+; X64-NEXT:    movq %rax, %r11
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %r8 # 8-byte Reload
+; X64-NEXT:    movq %r8, %rax
+; X64-NEXT:    mulq %r13
+; X64-NEXT:    movq %rdx, %rdi
+; X64-NEXT:    movq %rax, %rbx
+; X64-NEXT:    addq %r9, %rbx
+; X64-NEXT:    adcq $0, %rdi
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    movq %r12, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    mulq %r12
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    movq %rax, %r9
+; X64-NEXT:    addq %rbx, %r9
+; X64-NEXT:    adcq $0, %rcx
+; X64-NEXT:    addq %rdi, %rcx
+; X64-NEXT:    sbbq %rdi, %rdi
+; X64-NEXT:    andl $1, %edi
+; X64-NEXT:    movq %r8, %rax
+; X64-NEXT:    mulq %r12
+; X64-NEXT:    addq %rcx, %rax
+; X64-NEXT:    adcq %rdi, %rdx
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    addq %r14, %rcx
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %r12 # 8-byte Reload
+; X64-NEXT:    movq %r12, %r13
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %r13 # 8-byte Folded Reload
+; X64-NEXT:    addq %rax, %rcx
+; X64-NEXT:    adcq %rdx, %r13
+; X64-NEXT:    addq %rsi, %r11
+; X64-NEXT:    adcq %rbp, %r9
+; X64-NEXT:    adcq %r10, %rcx
+; X64-NEXT:    adcq %r15, %r13
+; X64-NEXT:    addq -{{[0-9]+}}(%rsp), %r11 # 8-byte Folded Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %r9 # 8-byte Folded Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %rcx # 8-byte Folded Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %r13 # 8-byte Folded Reload
+; X64-NEXT:    addq -{{[0-9]+}}(%rsp), %r11 # 8-byte Folded Reload
+; X64-NEXT:    movq %r11, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %r9 # 8-byte Folded Reload
+; X64-NEXT:    movq %r9, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %rcx # 8-byte Folded Reload
+; X64-NEXT:    movq %rcx, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %r13 # 8-byte Folded Reload
+; X64-NEXT:    adcq $0, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; X64-NEXT:    adcq $0, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; X64-NEXT:    adcq $0, {{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; X64-NEXT:    adcq $0, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rsi # 8-byte Reload
+; X64-NEXT:    movq %rsi, %rax
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    mulq %rcx
+; X64-NEXT:    movq %rdx, %rdi
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %r8, %rax
+; X64-NEXT:    mulq %rcx
+; X64-NEXT:    movq %rcx, %r11
+; X64-NEXT:    movq %rdx, %rbx
+; X64-NEXT:    movq %rax, %rbp
+; X64-NEXT:    addq %rdi, %rbp
+; X64-NEXT:    adcq $0, %rbx
+; X64-NEXT:    movq %rsi, %rax
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    movq %rax, %r10
+; X64-NEXT:    addq %rbp, %r10
+; X64-NEXT:    adcq $0, %rcx
+; X64-NEXT:    addq %rbx, %rcx
+; X64-NEXT:    sbbq %rsi, %rsi
+; X64-NEXT:    andl $1, %esi
+; X64-NEXT:    movq %r8, %rax
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rdi, %r14
+; X64-NEXT:    addq %rcx, %rax
+; X64-NEXT:    adcq %rsi, %rdx
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %r9 # 8-byte Reload
+; X64-NEXT:    addq {{[0-9]+}}(%rsp), %r9 # 8-byte Folded Reload
+; X64-NEXT:    movq %r12, %r15
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %r15 # 8-byte Folded Reload
+; X64-NEXT:    addq %rax, %r9
+; X64-NEXT:    adcq %rdx, %r15
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    movq %r11, %rdi
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rdx, %r8
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rsi # 8-byte Reload
+; X64-NEXT:    movq %rsi, %rax
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rdx, %rbx
+; X64-NEXT:    movq %rax, %rbp
+; X64-NEXT:    addq %r8, %rbp
+; X64-NEXT:    adcq $0, %rbx
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    movq %rcx, %r8
+; X64-NEXT:    mulq %r14
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    addq %rbp, %rax
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq $0, %rcx
+; X64-NEXT:    addq %rbx, %rcx
+; X64-NEXT:    sbbq %rbp, %rbp
+; X64-NEXT:    andl $1, %ebp
+; X64-NEXT:    movq %rsi, %rax
+; X64-NEXT:    movq %rsi, %rdi
+; X64-NEXT:    mulq %r14
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    movq %rax, %rbx
+; X64-NEXT:    addq %rcx, %rbx
+; X64-NEXT:    adcq %rbp, %rsi
+; X64-NEXT:    addq {{[0-9]+}}(%rsp), %rbx # 8-byte Folded Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %rsi # 8-byte Folded Reload
+; X64-NEXT:    addq -{{[0-9]+}}(%rsp), %rbx # 8-byte Folded Reload
+; X64-NEXT:    adcq %r10, %rsi
+; X64-NEXT:    adcq $0, %r9
+; X64-NEXT:    adcq $0, %r15
+; X64-NEXT:    movq %r8, %rbp
+; X64-NEXT:    movq %rbp, %rax
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    mulq %rcx
+; X64-NEXT:    movq %rdx, %r14
+; X64-NEXT:    movq %rax, %r8
+; X64-NEXT:    movq %rdi, %rax
+; X64-NEXT:    movq %rdi, %r11
+; X64-NEXT:    mulq %rcx
+; X64-NEXT:    movq %rdx, %r12
+; X64-NEXT:    movq %rax, %rcx
+; X64-NEXT:    addq %r14, %rcx
+; X64-NEXT:    adcq $0, %r12
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; X64-NEXT:    movq 56(%rax), %rdi
+; X64-NEXT:    movq %rbp, %rax
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rdi, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rdx, %rbp
+; X64-NEXT:    addq %rcx, %rax
+; X64-NEXT:    movq %rax, %r10
+; X64-NEXT:    adcq $0, %rbp
+; X64-NEXT:    addq %r12, %rbp
+; X64-NEXT:    sbbq %rcx, %rcx
+; X64-NEXT:    andl $1, %ecx
+; X64-NEXT:    movq %r11, %rax
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    addq %rbp, %rax
+; X64-NEXT:    adcq %rcx, %rdx
+; X64-NEXT:    movq (%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %r11 # 8-byte Reload
+; X64-NEXT:    addq %r11, %rcx
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %r12 # 8-byte Reload
+; X64-NEXT:    adcq %r12, %rdi
+; X64-NEXT:    addq %rax, %rcx
+; X64-NEXT:    adcq %rdx, %rdi
+; X64-NEXT:    addq %rbx, %r8
+; X64-NEXT:    movq %r8, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq %rsi, %r10
+; X64-NEXT:    movq %r10, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq $0, %rcx
+; X64-NEXT:    adcq $0, %rdi
+; X64-NEXT:    addq %r9, %rcx
+; X64-NEXT:    adcq %r15, %rdi
+; X64-NEXT:    movl $0, %r8d
+; X64-NEXT:    adcq $0, %r8
+; X64-NEXT:    sbbq %r9, %r9
+; X64-NEXT:    andl $1, %r9d
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rsi # 8-byte Reload
+; X64-NEXT:    movq %rsi, %rax
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rbx # 8-byte Reload
+; X64-NEXT:    mulq %rbx
+; X64-NEXT:    movq %rdx, %r10
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %r14 # 8-byte Reload
+; X64-NEXT:    movq %r14, %rax
+; X64-NEXT:    mulq %rbx
+; X64-NEXT:    movq %rdx, %rbx
+; X64-NEXT:    movq %rax, %rbp
+; X64-NEXT:    addq %r10, %rbp
+; X64-NEXT:    adcq $0, %rbx
+; X64-NEXT:    movq %rsi, %rax
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %r10 # 8-byte Reload
+; X64-NEXT:    mulq %r10
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    movq %rax, %r15
+; X64-NEXT:    addq %rbp, %r15
+; X64-NEXT:    adcq $0, %rsi
+; X64-NEXT:    addq %rbx, %rsi
+; X64-NEXT:    sbbq %rbp, %rbp
+; X64-NEXT:    andl $1, %ebp
+; X64-NEXT:    movq %r14, %rax
+; X64-NEXT:    mulq %r10
+; X64-NEXT:    addq %rsi, %rax
+; X64-NEXT:    adcq %rbp, %rdx
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %r10 # 8-byte Reload
+; X64-NEXT:    addq %r11, %r10
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %r14 # 8-byte Reload
+; X64-NEXT:    adcq %r12, %r14
+; X64-NEXT:    addq %rax, %r10
+; X64-NEXT:    adcq %rdx, %r14
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; X64-NEXT:    addq %rcx, %rax
+; X64-NEXT:    adcq %rdi, %r15
+; X64-NEXT:    adcq %r8, %r10
+; X64-NEXT:    adcq %r9, %r14
+; X64-NEXT:    addq {{[0-9]+}}(%rsp), %rax # 8-byte Folded Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %r15 # 8-byte Folded Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %r10 # 8-byte Folded Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %r14 # 8-byte Folded Reload
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    addq %rcx, {{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    adcq %rcx, {{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    adcq %rcx, {{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; X64-NEXT:    adcq %r13, {{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; X64-NEXT:    adcq $0, %rax
+; X64-NEXT:    adcq $0, %r15
+; X64-NEXT:    adcq $0, %r10
+; X64-NEXT:    adcq $0, %r14
+; X64-NEXT:    addq -{{[0-9]+}}(%rsp), %rax # 8-byte Folded Reload
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %r15 # 8-byte Folded Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %r10 # 8-byte Folded Reload
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %r14 # 8-byte Folded Reload
+; X64-NEXT:    movl $0, %eax
+; X64-NEXT:    adcq $0, %rax
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movl $0, %eax
+; X64-NEXT:    adcq $0, %rax
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movl $0, %eax
+; X64-NEXT:    adcq $0, %rax
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    sbbq %rax, %rax
+; X64-NEXT:    andl $1, %eax
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    movq %rdi, %rax
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    mulq %rcx
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rbp # 8-byte Reload
+; X64-NEXT:    movq %rbp, %rax
+; X64-NEXT:    mulq %rcx
+; X64-NEXT:    movq %rcx, %r9
+; X64-NEXT:    movq %rdx, %rbx
+; X64-NEXT:    movq %rax, %rcx
+; X64-NEXT:    addq %rsi, %rcx
+; X64-NEXT:    adcq $0, %rbx
+; X64-NEXT:    movq %rdi, %rax
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    movq %rax, %r13
+; X64-NEXT:    addq %rcx, %r13
+; X64-NEXT:    adcq $0, %rsi
+; X64-NEXT:    addq %rbx, %rsi
+; X64-NEXT:    sbbq %rcx, %rcx
+; X64-NEXT:    andl $1, %ecx
+; X64-NEXT:    movq %rbp, %rax
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rdi, %r11
+; X64-NEXT:    addq %rsi, %rax
+; X64-NEXT:    adcq %rcx, %rdx
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %r12 # 8-byte Reload
+; X64-NEXT:    addq {{[0-9]+}}(%rsp), %r12 # 8-byte Folded Reload
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %r8 # 8-byte Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %r8 # 8-byte Folded Reload
+; X64-NEXT:    addq %rax, %r12
+; X64-NEXT:    adcq %rdx, %r8
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    movq %rdi, %rax
+; X64-NEXT:    mulq %r9
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rbp # 8-byte Reload
+; X64-NEXT:    movq %rbp, %rax
+; X64-NEXT:    mulq %r9
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    movq %rax, %rbx
+; X64-NEXT:    addq %rcx, %rbx
+; X64-NEXT:    adcq $0, %rsi
+; X64-NEXT:    movq %rdi, %rax
+; X64-NEXT:    movq %rdi, %r9
+; X64-NEXT:    mulq %r11
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    addq %rbx, %rax
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq $0, %rcx
+; X64-NEXT:    addq %rsi, %rcx
+; X64-NEXT:    sbbq %rdi, %rdi
+; X64-NEXT:    andl $1, %edi
+; X64-NEXT:    movq %rbp, %rbx
+; X64-NEXT:    movq %rbx, %rax
+; X64-NEXT:    mulq %r11
+; X64-NEXT:    movq %rdx, %r11
+; X64-NEXT:    movq %rax, %rsi
+; X64-NEXT:    addq %rcx, %rsi
+; X64-NEXT:    adcq %rdi, %r11
+; X64-NEXT:    addq {{[0-9]+}}(%rsp), %rsi # 8-byte Folded Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %r11 # 8-byte Folded Reload
+; X64-NEXT:    addq -{{[0-9]+}}(%rsp), %rsi # 8-byte Folded Reload
+; X64-NEXT:    adcq %r13, %r11
+; X64-NEXT:    adcq $0, %r12
+; X64-NEXT:    adcq $0, %r8
+; X64-NEXT:    movq %r8, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %r9, %rdi
+; X64-NEXT:    movq %rdi, %rax
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    mulq %rcx
+; X64-NEXT:    movq %rdx, %r8
+; X64-NEXT:    movq %rax, %r13
+; X64-NEXT:    movq %rbx, %rax
+; X64-NEXT:    movq %rbx, %r9
+; X64-NEXT:    mulq %rcx
+; X64-NEXT:    movq %rdx, %rbp
+; X64-NEXT:    movq %rax, %rcx
+; X64-NEXT:    addq %r8, %rcx
+; X64-NEXT:    adcq $0, %rbp
+; X64-NEXT:    movq %rdi, %rax
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rdx, %rbx
+; X64-NEXT:    addq %rcx, %rax
+; X64-NEXT:    movq %rax, %r8
+; X64-NEXT:    adcq $0, %rbx
+; X64-NEXT:    addq %rbp, %rbx
+; X64-NEXT:    sbbq %rcx, %rcx
+; X64-NEXT:    andl $1, %ecx
+; X64-NEXT:    movq %r9, %rax
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    addq %rbx, %rax
+; X64-NEXT:    adcq %rcx, %rdx
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    addq {{[0-9]+}}(%rsp), %rdi # 8-byte Folded Reload
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %rcx # 8-byte Folded Reload
+; X64-NEXT:    addq %rax, %rdi
+; X64-NEXT:    adcq %rdx, %rcx
+; X64-NEXT:    addq %rsi, %r13
+; X64-NEXT:    adcq %r11, %r8
+; X64-NEXT:    movq %r8, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq $0, %rdi
+; X64-NEXT:    adcq $0, %rcx
+; X64-NEXT:    addq %r12, %rdi
+; X64-NEXT:    movq %rdi, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %rcx # 8-byte Folded Reload
+; X64-NEXT:    movq %rcx, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movl $0, %r12d
+; X64-NEXT:    adcq $0, %r12
+; X64-NEXT:    sbbq %r9, %r9
+; X64-NEXT:    andl $1, %r9d
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rbx # 8-byte Reload
+; X64-NEXT:    movq %rbx, %rax
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rsi # 8-byte Reload
+; X64-NEXT:    mulq %rsi
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    movq %rax, %r11
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %r8 # 8-byte Reload
+; X64-NEXT:    movq %r8, %rax
+; X64-NEXT:    mulq %rsi
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    movq %rax, %rbp
+; X64-NEXT:    addq %rcx, %rbp
+; X64-NEXT:    adcq $0, %rsi
+; X64-NEXT:    movq %rbx, %rax
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    movq %rax, %rbx
+; X64-NEXT:    addq %rbp, %rbx
+; X64-NEXT:    adcq $0, %rcx
+; X64-NEXT:    addq %rsi, %rcx
+; X64-NEXT:    sbbq %rsi, %rsi
+; X64-NEXT:    andl $1, %esi
+; X64-NEXT:    movq %r8, %rax
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    addq %rcx, %rax
+; X64-NEXT:    adcq %rsi, %rdx
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rsi # 8-byte Reload
+; X64-NEXT:    addq {{[0-9]+}}(%rsp), %rsi # 8-byte Folded Reload
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %rcx # 8-byte Folded Reload
+; X64-NEXT:    addq %rax, %rsi
+; X64-NEXT:    adcq %rdx, %rcx
+; X64-NEXT:    addq -{{[0-9]+}}(%rsp), %r11 # 8-byte Folded Reload
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %rbx # 8-byte Folded Reload
+; X64-NEXT:    adcq %r12, %rsi
+; X64-NEXT:    adcq %r9, %rcx
+; X64-NEXT:    addq {{[0-9]+}}(%rsp), %r11 # 8-byte Folded Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %rbx # 8-byte Folded Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %rsi # 8-byte Folded Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %rcx # 8-byte Folded Reload
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; X64-NEXT:    addq %rax, {{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; X64-NEXT:    adcq %r15, {{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; X64-NEXT:    adcq %r10, %r13
+; X64-NEXT:    movq %r13, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq %r14, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %r11 # 8-byte Folded Reload
+; X64-NEXT:    movq %r11, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %rbx # 8-byte Folded Reload
+; X64-NEXT:    movq %rbx, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %rsi # 8-byte Folded Reload
+; X64-NEXT:    movq %rsi, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %rcx # 8-byte Folded Reload
+; X64-NEXT:    movq %rcx, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rsi # 8-byte Reload
+; X64-NEXT:    movq 64(%rsi), %r14
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rbp # 8-byte Reload
+; X64-NEXT:    movq %rbp, %rax
+; X64-NEXT:    mulq %r14
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %r8 # 8-byte Reload
+; X64-NEXT:    movq %r8, %rax
+; X64-NEXT:    mulq %r14
+; X64-NEXT:    movq %rdx, %rdi
+; X64-NEXT:    movq %rax, %rbx
+; X64-NEXT:    addq %rcx, %rbx
+; X64-NEXT:    adcq $0, %rdi
+; X64-NEXT:    movq 72(%rsi), %rcx
+; X64-NEXT:    movq %rsi, %r13
+; X64-NEXT:    movq %rbp, %rax
+; X64-NEXT:    mulq %rcx
+; X64-NEXT:    movq %rcx, %rsi
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    movq %rax, %r10
+; X64-NEXT:    addq %rbx, %r10
+; X64-NEXT:    adcq $0, %rcx
+; X64-NEXT:    addq %rdi, %rcx
+; X64-NEXT:    sbbq %rdi, %rdi
+; X64-NEXT:    andl $1, %edi
+; X64-NEXT:    movq %r8, %rax
+; X64-NEXT:    mulq %rsi
+; X64-NEXT:    movq %rsi, %r8
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    movq %rax, %rbp
+; X64-NEXT:    addq %rcx, %rbp
+; X64-NEXT:    adcq %rdi, %rsi
+; X64-NEXT:    movq %r14, %rax
+; X64-NEXT:    xorl %ecx, %ecx
+; X64-NEXT:    mulq %rcx
+; X64-NEXT:    movq %rax, %rbx
+; X64-NEXT:    movq %rdx, %r11
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %r15 # 8-byte Reload
+; X64-NEXT:    addq %rbx, %r15
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %r12 # 8-byte Reload
+; X64-NEXT:    adcq %r11, %r12
+; X64-NEXT:    addq %rbp, %r15
+; X64-NEXT:    adcq %rsi, %r12
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    movq %r14, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    mulq %r14
+; X64-NEXT:    movq %rdx, %r9
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    movq %rdi, %rax
+; X64-NEXT:    mulq %r14
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    movq %rax, %rbp
+; X64-NEXT:    addq %r9, %rbp
+; X64-NEXT:    adcq $0, %rsi
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    movq %rcx, %r14
+; X64-NEXT:    movq %r8, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    addq %rbp, %rax
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq $0, %rcx
+; X64-NEXT:    addq %rsi, %rcx
+; X64-NEXT:    sbbq %rsi, %rsi
+; X64-NEXT:    andl $1, %esi
+; X64-NEXT:    movq %rdi, %rax
+; X64-NEXT:    movq %rdi, %r9
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    addq %rcx, %rax
+; X64-NEXT:    adcq %rsi, %rdx
+; X64-NEXT:    addq -{{[0-9]+}}(%rsp), %rbx # 8-byte Folded Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %r11 # 8-byte Folded Reload
+; X64-NEXT:    addq %rax, %rbx
+; X64-NEXT:    adcq %rdx, %r11
+; X64-NEXT:    addq -{{[0-9]+}}(%rsp), %rbx # 8-byte Folded Reload
+; X64-NEXT:    adcq %r10, %r11
+; X64-NEXT:    adcq $0, %r15
+; X64-NEXT:    adcq $0, %r12
+; X64-NEXT:    movq 80(%r13), %rbp
+; X64-NEXT:    movq %r14, %rsi
+; X64-NEXT:    movq %rsi, %rax
+; X64-NEXT:    mulq %rbp
+; X64-NEXT:    movq %rdx, %r8
+; X64-NEXT:    movq %rax, %r14
+; X64-NEXT:    movq %r9, %rax
+; X64-NEXT:    mulq %rbp
+; X64-NEXT:    movq %rdx, %r10
+; X64-NEXT:    movq %rax, %rcx
+; X64-NEXT:    addq %r8, %rcx
+; X64-NEXT:    adcq $0, %r10
+; X64-NEXT:    movq 88(%r13), %r13
+; X64-NEXT:    movq %rsi, %rax
+; X64-NEXT:    mulq %r13
+; X64-NEXT:    movq %rdx, %rdi
+; X64-NEXT:    movq %rax, %r8
+; X64-NEXT:    addq %rcx, %r8
+; X64-NEXT:    adcq $0, %rdi
+; X64-NEXT:    addq %r10, %rdi
+; X64-NEXT:    sbbq %rsi, %rsi
+; X64-NEXT:    andl $1, %esi
+; X64-NEXT:    movq %r9, %rax
+; X64-NEXT:    mulq %r13
+; X64-NEXT:    movq %rdx, %r10
+; X64-NEXT:    movq %rax, %rcx
+; X64-NEXT:    addq %rdi, %rcx
+; X64-NEXT:    adcq %rsi, %r10
+; X64-NEXT:    movq %rbp, %rax
+; X64-NEXT:    xorl %edx, %edx
+; X64-NEXT:    mulq %rdx
+; X64-NEXT:    movq %rdx, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rax, %rdi
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rsi # 8-byte Reload
+; X64-NEXT:    addq %rdi, %rsi
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; X64-NEXT:    adcq %rdx, %rax
+; X64-NEXT:    addq %rcx, %rsi
+; X64-NEXT:    adcq %r10, %rax
+; X64-NEXT:    addq %rbx, %r14
+; X64-NEXT:    movq %r14, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq %r11, %r8
+; X64-NEXT:    movq %r8, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq $0, %rsi
+; X64-NEXT:    adcq $0, %rax
+; X64-NEXT:    addq %r15, %rsi
+; X64-NEXT:    movq %rsi, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq %r12, %rax
+; X64-NEXT:    movq %rax, %r10
+; X64-NEXT:    movl $0, %r15d
+; X64-NEXT:    adcq $0, %r15
+; X64-NEXT:    sbbq %r12, %r12
+; X64-NEXT:    andl $1, %r12d
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    mulq %rbp
+; X64-NEXT:    movq %rdx, %r8
+; X64-NEXT:    movq %rax, %r14
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %r11 # 8-byte Reload
+; X64-NEXT:    movq %r11, %rax
+; X64-NEXT:    mulq %rbp
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    movq %rax, %rbx
+; X64-NEXT:    addq %r8, %rbx
+; X64-NEXT:    adcq $0, %rsi
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    mulq %r13
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    addq %rbx, %rax
+; X64-NEXT:    movq %rax, %rbx
+; X64-NEXT:    adcq $0, %rcx
+; X64-NEXT:    addq %rsi, %rcx
+; X64-NEXT:    sbbq %rsi, %rsi
+; X64-NEXT:    andl $1, %esi
+; X64-NEXT:    movq %r11, %rax
+; X64-NEXT:    mulq %r13
+; X64-NEXT:    addq %rcx, %rax
+; X64-NEXT:    adcq %rsi, %rdx
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rsi # 8-byte Reload
+; X64-NEXT:    addq %rdi, %rsi
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %rcx # 8-byte Folded Reload
+; X64-NEXT:    addq %rax, %rsi
+; X64-NEXT:    adcq %rdx, %rcx
+; X64-NEXT:    addq -{{[0-9]+}}(%rsp), %r14 # 8-byte Folded Reload
+; X64-NEXT:    movq %r14, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq %r10, %rbx
+; X64-NEXT:    movq %rbx, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq %r15, %rsi
+; X64-NEXT:    movq %rsi, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq %r12, %rcx
+; X64-NEXT:    movq %rcx, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; X64-NEXT:    imulq %rax, %r13
+; X64-NEXT:    movq %rax, %r8
+; X64-NEXT:    mulq %rbp
+; X64-NEXT:    movq %rax, %r9
+; X64-NEXT:    addq %r13, %rdx
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    imulq %rdi, %rbp
+; X64-NEXT:    addq %rdx, %rbp
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; X64-NEXT:    movq %rax, %rsi
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rbx # 8-byte Reload
+; X64-NEXT:    imulq %rbx, %rsi
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    mulq %rcx
+; X64-NEXT:    movq %rax, %r10
+; X64-NEXT:    addq %rsi, %rdx
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; X64-NEXT:    imulq %rcx, %rax
+; X64-NEXT:    addq %rdx, %rax
+; X64-NEXT:    addq %r9, %r10
+; X64-NEXT:    adcq %rbp, %rax
+; X64-NEXT:    movq %rax, %r9
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    movq %rcx, %rbp
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rbx, %rax
+; X64-NEXT:    movq %rbx, %r12
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    movq %rax, %rbx
+; X64-NEXT:    addq %rcx, %rbx
+; X64-NEXT:    adcq $0, %rsi
+; X64-NEXT:    movq %rbp, %rax
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rdx, %rbp
+; X64-NEXT:    movq %rax, %r14
+; X64-NEXT:    addq %rbx, %r14
+; X64-NEXT:    adcq $0, %rbp
+; X64-NEXT:    addq %rsi, %rbp
+; X64-NEXT:    sbbq %rcx, %rcx
+; X64-NEXT:    andl $1, %ecx
+; X64-NEXT:    movq %r12, %rax
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rdx, %r12
+; X64-NEXT:    movq %rax, %r8
+; X64-NEXT:    addq %rbp, %r8
+; X64-NEXT:    adcq %rcx, %r12
+; X64-NEXT:    addq %r10, %r8
+; X64-NEXT:    adcq %r9, %r12
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rdx # 8-byte Reload
+; X64-NEXT:    movq 120(%rdx), %rcx
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %r9 # 8-byte Reload
+; X64-NEXT:    imulq %r9, %rcx
+; X64-NEXT:    movq 112(%rdx), %rsi
+; X64-NEXT:    movq %rdx, %rdi
+; X64-NEXT:    movq %r9, %rax
+; X64-NEXT:    mulq %rsi
+; X64-NEXT:    movq %rax, %r15
+; X64-NEXT:    addq %rcx, %rdx
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %r10 # 8-byte Reload
+; X64-NEXT:    imulq %r10, %rsi
+; X64-NEXT:    addq %rdx, %rsi
+; X64-NEXT:    movq 96(%rdi), %rbp
+; X64-NEXT:    movq 104(%rdi), %rbx
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; X64-NEXT:    movq %rax, %rcx
+; X64-NEXT:    imulq %rbx, %rcx
+; X64-NEXT:    mulq %rbp
+; X64-NEXT:    movq %rax, %r13
+; X64-NEXT:    addq %rcx, %rdx
+; X64-NEXT:    imulq %rbp, %r11
+; X64-NEXT:    addq %rdx, %r11
+; X64-NEXT:    addq %r15, %r13
+; X64-NEXT:    adcq %rsi, %r11
+; X64-NEXT:    movq %r11, %r15
+; X64-NEXT:    movq %rbp, %rax
+; X64-NEXT:    mulq %r9
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    movq %rax, %r11
+; X64-NEXT:    movq %rbx, %rax
+; X64-NEXT:    mulq %r9
+; X64-NEXT:    movq %rdx, %rdi
+; X64-NEXT:    movq %rax, %rcx
+; X64-NEXT:    addq %rsi, %rcx
+; X64-NEXT:    adcq $0, %rdi
+; X64-NEXT:    movq %rbp, %rax
+; X64-NEXT:    mulq %r10
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    movq %rax, %rbp
+; X64-NEXT:    addq %rcx, %rbp
+; X64-NEXT:    adcq $0, %rsi
+; X64-NEXT:    addq %rdi, %rsi
+; X64-NEXT:    sbbq %rcx, %rcx
+; X64-NEXT:    andl $1, %ecx
+; X64-NEXT:    movq %rbx, %rax
+; X64-NEXT:    mulq %r10
+; X64-NEXT:    addq %rsi, %rax
+; X64-NEXT:    adcq %rcx, %rdx
+; X64-NEXT:    addq %r13, %rax
+; X64-NEXT:    adcq %r15, %rdx
+; X64-NEXT:    addq -{{[0-9]+}}(%rsp), %r11 # 8-byte Folded Reload
+; X64-NEXT:    adcq %r14, %rbp
+; X64-NEXT:    adcq %r8, %rax
+; X64-NEXT:    adcq %r12, %rdx
+; X64-NEXT:    addq -{{[0-9]+}}(%rsp), %r11 # 8-byte Folded Reload
+; X64-NEXT:    movq %r11, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %rbp # 8-byte Folded Reload
+; X64-NEXT:    movq %rbp, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %rax # 8-byte Folded Reload
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %rdx # 8-byte Folded Reload
+; X64-NEXT:    movq %rdx, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rsi # 8-byte Reload
+; X64-NEXT:    movq 80(%rsi), %rax
+; X64-NEXT:    movq %rax, %rbp
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    movq 88(%rsi), %rax
+; X64-NEXT:    movq %rsi, %r11
+; X64-NEXT:    movq %rax, %r8
+; X64-NEXT:    movq %r8, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rdi, %rbx
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    movq %rax, %rdi
+; X64-NEXT:    addq %rcx, %rdi
+; X64-NEXT:    adcq $0, %rsi
+; X64-NEXT:    movq %rbp, %rax
+; X64-NEXT:    movq %rbp, %r9
+; X64-NEXT:    movq %r9, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %r15 # 8-byte Reload
+; X64-NEXT:    mulq %r15
+; X64-NEXT:    movq %rdx, %rbp
+; X64-NEXT:    movq %rax, %r14
+; X64-NEXT:    addq %rdi, %r14
+; X64-NEXT:    adcq $0, %rbp
+; X64-NEXT:    addq %rsi, %rbp
+; X64-NEXT:    sbbq %rdi, %rdi
+; X64-NEXT:    andl $1, %edi
+; X64-NEXT:    movq %r8, %rax
+; X64-NEXT:    mulq %r15
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    movq %rax, %rcx
+; X64-NEXT:    addq %rbp, %rcx
+; X64-NEXT:    adcq %rdi, %rsi
+; X64-NEXT:    movq %r9, %rax
+; X64-NEXT:    xorl %r13d, %r13d
+; X64-NEXT:    mulq %r13
+; X64-NEXT:    movq %rdx, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rax, %r12
+; X64-NEXT:    movq (%rsp), %r10 # 8-byte Reload
+; X64-NEXT:    addq %r10, %r12
+; X64-NEXT:    movq %rdx, %r8
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %r9 # 8-byte Reload
+; X64-NEXT:    adcq %r9, %r8
+; X64-NEXT:    addq %rcx, %r12
+; X64-NEXT:    adcq %rsi, %r8
+; X64-NEXT:    movq %r11, %rsi
+; X64-NEXT:    movq 64(%rsi), %rax
+; X64-NEXT:    movq %rax, %r11
+; X64-NEXT:    movq %rbx, %rdi
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    movq 72(%rsi), %rbx
+; X64-NEXT:    movq %rbx, %rax
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    movq %rax, %rbp
+; X64-NEXT:    addq %rcx, %rbp
+; X64-NEXT:    adcq $0, %rsi
+; X64-NEXT:    movq %r11, %rax
+; X64-NEXT:    mulq %r15
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    addq %rbp, %rax
+; X64-NEXT:    movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq $0, %rcx
+; X64-NEXT:    addq %rsi, %rcx
+; X64-NEXT:    sbbq %rdi, %rdi
+; X64-NEXT:    andl $1, %edi
+; X64-NEXT:    movq %rbx, %rax
+; X64-NEXT:    mulq %r15
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    movq %rax, %rbp
+; X64-NEXT:    addq %rcx, %rbp
+; X64-NEXT:    adcq %rdi, %rsi
+; X64-NEXT:    movq %r11, %rdi
+; X64-NEXT:    movq %rdi, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rdi, %rax
+; X64-NEXT:    mulq %r13
+; X64-NEXT:    movq %rdx, %r11
+; X64-NEXT:    movq %rax, %r13
+; X64-NEXT:    addq %r13, %r10
+; X64-NEXT:    adcq %r11, %r9
+; X64-NEXT:    addq %rbp, %r10
+; X64-NEXT:    adcq %rsi, %r9
+; X64-NEXT:    addq {{[0-9]+}}(%rsp), %r10 # 8-byte Folded Reload
+; X64-NEXT:    movq %r10, (%rsp) # 8-byte Spill
+; X64-NEXT:    adcq %r14, %r9
+; X64-NEXT:    movq %r9, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq $0, %r12
+; X64-NEXT:    adcq $0, %r8
+; X64-NEXT:    movq %rdi, %rax
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    mulq %rcx
+; X64-NEXT:    movq %rdx, %r9
+; X64-NEXT:    movq %rax, %r15
+; X64-NEXT:    movq %rbx, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rbx, %rax
+; X64-NEXT:    mulq %rcx
+; X64-NEXT:    movq %rdx, %rbp
+; X64-NEXT:    movq %rax, %rsi
+; X64-NEXT:    addq %r9, %rsi
+; X64-NEXT:    adcq $0, %rbp
+; X64-NEXT:    movq %rdi, %rax
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %r10 # 8-byte Reload
+; X64-NEXT:    mulq %r10
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    movq %rax, %rdi
+; X64-NEXT:    addq %rsi, %rdi
+; X64-NEXT:    adcq $0, %rcx
+; X64-NEXT:    addq %rbp, %rcx
+; X64-NEXT:    sbbq %rsi, %rsi
+; X64-NEXT:    andl $1, %esi
+; X64-NEXT:    movq %rbx, %rax
+; X64-NEXT:    mulq %r10
+; X64-NEXT:    addq %rcx, %rax
+; X64-NEXT:    adcq %rsi, %rdx
+; X64-NEXT:    addq -{{[0-9]+}}(%rsp), %r13 # 8-byte Folded Reload
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %r14 # 8-byte Reload
+; X64-NEXT:    adcq %r14, %r11
+; X64-NEXT:    addq %rax, %r13
+; X64-NEXT:    adcq %rdx, %r11
+; X64-NEXT:    addq (%rsp), %r15 # 8-byte Folded Reload
+; X64-NEXT:    movq %r15, (%rsp) # 8-byte Spill
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %rdi # 8-byte Folded Reload
+; X64-NEXT:    movq %rdi, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq $0, %r13
+; X64-NEXT:    adcq $0, %r11
+; X64-NEXT:    addq %r12, %r13
+; X64-NEXT:    adcq %r8, %r11
+; X64-NEXT:    movl $0, %r8d
+; X64-NEXT:    adcq $0, %r8
+; X64-NEXT:    sbbq %r9, %r9
+; X64-NEXT:    andl $1, %r9d
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %r15 # 8-byte Reload
+; X64-NEXT:    mulq %r15
+; X64-NEXT:    movq %rdx, %r12
+; X64-NEXT:    movq %rax, %rdi
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rbx # 8-byte Reload
+; X64-NEXT:    movq %rbx, %rax
+; X64-NEXT:    mulq %r15
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    movq %rax, %rbp
+; X64-NEXT:    addq %r12, %rbp
+; X64-NEXT:    adcq $0, %rsi
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    mulq %r10
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    addq %rbp, %rax
+; X64-NEXT:    movq %rax, %rbp
+; X64-NEXT:    adcq $0, %rcx
+; X64-NEXT:    addq %rsi, %rcx
+; X64-NEXT:    sbbq %rsi, %rsi
+; X64-NEXT:    andl $1, %esi
+; X64-NEXT:    movq %rbx, %rax
+; X64-NEXT:    mulq %r10
+; X64-NEXT:    addq %rcx, %rax
+; X64-NEXT:    adcq %rsi, %rdx
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rsi # 8-byte Reload
+; X64-NEXT:    addq -{{[0-9]+}}(%rsp), %rsi # 8-byte Folded Reload
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    adcq %r14, %rcx
+; X64-NEXT:    addq %rax, %rsi
+; X64-NEXT:    adcq %rdx, %rcx
+; X64-NEXT:    addq %r13, %rdi
+; X64-NEXT:    movq %rdi, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq %r11, %rbp
+; X64-NEXT:    movq %rbp, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq %r8, %rsi
+; X64-NEXT:    movq %rsi, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq %r9, %rcx
+; X64-NEXT:    movq %rcx, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rbp # 8-byte Reload
+; X64-NEXT:    movq 96(%rbp), %rcx
+; X64-NEXT:    imulq %rcx, %r10
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    mulq %r15
+; X64-NEXT:    movq %rax, %r9
+; X64-NEXT:    addq %r10, %rdx
+; X64-NEXT:    movq 104(%rbp), %r8
+; X64-NEXT:    imulq %r8, %r15
+; X64-NEXT:    addq %rdx, %r15
+; X64-NEXT:    movq 112(%rbp), %rax
+; X64-NEXT:    movq %rbp, %rdi
+; X64-NEXT:    movq %rax, %rsi
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rbx # 8-byte Reload
+; X64-NEXT:    imulq %rbx, %rsi
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rbp # 8-byte Reload
+; X64-NEXT:    mulq %rbp
+; X64-NEXT:    movq %rax, %r13
+; X64-NEXT:    addq %rsi, %rdx
+; X64-NEXT:    movq 120(%rdi), %rdi
+; X64-NEXT:    imulq %rbp, %rdi
+; X64-NEXT:    addq %rdx, %rdi
+; X64-NEXT:    addq %r9, %r13
+; X64-NEXT:    adcq %r15, %rdi
+; X64-NEXT:    movq %rbp, %rax
+; X64-NEXT:    movq %rbp, %r9
+; X64-NEXT:    mulq %rcx
+; X64-NEXT:    movq %rdx, %rbp
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rbx, %rax
+; X64-NEXT:    mulq %rcx
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    movq %rax, %rsi
+; X64-NEXT:    addq %rbp, %rsi
+; X64-NEXT:    adcq $0, %rcx
+; X64-NEXT:    movq %r9, %rax
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rdx, %rbp
+; X64-NEXT:    movq %rax, %r12
+; X64-NEXT:    addq %rsi, %r12
+; X64-NEXT:    adcq $0, %rbp
+; X64-NEXT:    addq %rcx, %rbp
+; X64-NEXT:    sbbq %rcx, %rcx
+; X64-NEXT:    andl $1, %ecx
+; X64-NEXT:    movq %rbx, %rax
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rdx, %r8
+; X64-NEXT:    movq %rax, %r9
+; X64-NEXT:    addq %rbp, %r9
+; X64-NEXT:    adcq %rcx, %r8
+; X64-NEXT:    addq %r13, %r9
+; X64-NEXT:    adcq %rdi, %r8
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rsi # 8-byte Reload
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rbx # 8-byte Reload
+; X64-NEXT:    imulq %rbx, %rsi
+; X64-NEXT:    movq %rbx, %rax
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    mulq %rcx
+; X64-NEXT:    movq %rax, %r10
+; X64-NEXT:    addq %rsi, %rdx
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %r11 # 8-byte Reload
+; X64-NEXT:    imulq %r11, %rcx
+; X64-NEXT:    addq %rdx, %rcx
+; X64-NEXT:    movq %rcx, %rsi
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; X64-NEXT:    movq %rax, %rcx
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %r14 # 8-byte Reload
+; X64-NEXT:    imulq %r14, %rcx
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rbp # 8-byte Reload
+; X64-NEXT:    mulq %rbp
+; X64-NEXT:    movq %rax, %r13
+; X64-NEXT:    addq %rcx, %rdx
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; X64-NEXT:    imulq %rbp, %rax
+; X64-NEXT:    addq %rdx, %rax
+; X64-NEXT:    addq %r10, %r13
+; X64-NEXT:    adcq %rsi, %rax
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rbp, %rax
+; X64-NEXT:    movq %rbp, %r10
+; X64-NEXT:    mulq %rbx
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    movq %rax, %rbp
+; X64-NEXT:    movq %r14, %rax
+; X64-NEXT:    mulq %rbx
+; X64-NEXT:    movq %rdx, %rdi
+; X64-NEXT:    movq %rax, %rcx
+; X64-NEXT:    addq %rsi, %rcx
+; X64-NEXT:    adcq $0, %rdi
+; X64-NEXT:    movq %r10, %rax
+; X64-NEXT:    mulq %r11
+; X64-NEXT:    movq %rdx, %r15
+; X64-NEXT:    movq %rax, %r10
+; X64-NEXT:    addq %rcx, %r10
+; X64-NEXT:    adcq $0, %r15
+; X64-NEXT:    addq %rdi, %r15
+; X64-NEXT:    sbbq %rcx, %rcx
+; X64-NEXT:    andl $1, %ecx
+; X64-NEXT:    movq %r14, %rax
+; X64-NEXT:    mulq %r11
+; X64-NEXT:    addq %r15, %rax
+; X64-NEXT:    adcq %rcx, %rdx
+; X64-NEXT:    addq %r13, %rax
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %rdx # 8-byte Folded Reload
+; X64-NEXT:    addq -{{[0-9]+}}(%rsp), %rbp # 8-byte Folded Reload
+; X64-NEXT:    adcq %r12, %r10
+; X64-NEXT:    adcq %r9, %rax
+; X64-NEXT:    adcq %r8, %rdx
+; X64-NEXT:    addq -{{[0-9]+}}(%rsp), %rbp # 8-byte Folded Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %r10 # 8-byte Folded Reload
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %rax # 8-byte Folded Reload
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %rdx # 8-byte Folded Reload
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    addq {{[0-9]+}}(%rsp), %rcx # 8-byte Folded Reload
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %rdi # 8-byte Folded Reload
+; X64-NEXT:    movq (%rsp), %rbx # 8-byte Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %rbx # 8-byte Folded Reload
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rsi # 8-byte Reload
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %rsi # 8-byte Folded Reload
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %rbp # 8-byte Folded Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %r10 # 8-byte Folded Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %rax # 8-byte Folded Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %rdx # 8-byte Folded Reload
+; X64-NEXT:    addq {{[0-9]+}}(%rsp), %rcx # 8-byte Folded Reload
+; X64-NEXT:    movq %rcx, %r8
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %rdi # 8-byte Folded Reload
+; X64-NEXT:    movq %rdi, %r9
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %rbx # 8-byte Folded Reload
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %rsi # 8-byte Folded Reload
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %rbp # 8-byte Folded Reload
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %r10 # 8-byte Folded Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %rax # 8-byte Folded Reload
+; X64-NEXT:    adcq {{[0-9]+}}(%rsp), %rdx # 8-byte Folded Reload
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    movq %rdi, (%rcx)
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    movq %rdi, 8(%rcx)
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    movq %rdi, 16(%rcx)
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    movq %rdi, 24(%rcx)
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    movq %rdi, 32(%rcx)
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    movq %rdi, 40(%rcx)
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    movq %rdi, 48(%rcx)
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; X64-NEXT:    movq %rdi, 56(%rcx)
+; X64-NEXT:    movq %r8, 64(%rcx)
+; X64-NEXT:    movq %r9, 72(%rcx)
+; X64-NEXT:    movq %rbx, 80(%rcx)
+; X64-NEXT:    movq %rsi, 88(%rcx)
+; X64-NEXT:    movq %rbp, 96(%rcx)
+; X64-NEXT:    movq %r10, 104(%rcx)
+; X64-NEXT:    movq %rax, 112(%rcx)
+; X64-NEXT:    movq %rdx, 120(%rcx)
+; X64-NEXT:    addq $360, %rsp # imm = 0x168
+; X64-NEXT:    popq %rbx
+; X64-NEXT:    popq %r12
+; X64-NEXT:    popq %r13
+; X64-NEXT:    popq %r14
+; X64-NEXT:    popq %r15
+; X64-NEXT:    popq %rbp
+; X64-NEXT:    retq
+  %av = load i1024, i1024* %a
+  %bv = load i1024, i1024* %b
+  %r = mul i1024 %av, %bv
+  store i1024 %r, i1024* %out
+  ret void
+}
diff --git a/test/CodeGen/X86/mul-i256.ll b/test/CodeGen/X86/mul-i256.ll
index 8b8b10aa1790..8f207b8dd086 100644
--- a/test/CodeGen/X86/mul-i256.ll
+++ b/test/CodeGen/X86/mul-i256.ll
@@ -15,12 +15,17 @@ entry:
 ; There is a lot of inter-register motion, and so matching the instruction
 ; sequence will be fragile. There should be 6 underlying multiplications.
 ; CHECK: imulq
+; CHECK: mulq
 ; CHECK: imulq
 ; CHECK: imulq
+; CHECK: mulq
 ; CHECK: imulq
-; CHECK: imulq
-; CHECK: imulq
+; CHECK: mulq
+; CHECK: mulq
+; CHECK: mulq
+; CHECK: mulq
 ; CHECK-NOT: imulq
+; CHECK-NOT: mulq
 ; CHECK: retq
 
 attributes #0 = { norecurse nounwind uwtable "target-cpu"="x86-64" "target-features"="+fxsr,+mmx,+sse,+sse2,+x87" }
diff --git a/test/CodeGen/X86/mul-i512.ll b/test/CodeGen/X86/mul-i512.ll
new file mode 100644
index 000000000000..f9cea6d2ba32
--- /dev/null
+++ b/test/CodeGen/X86/mul-i512.ll
@@ -0,0 +1,1238 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=i386-unknown | FileCheck %s --check-prefix=X32
+; RUN: llc < %s -mtriple=x86_64-unknown | FileCheck %s --check-prefix=X64
+
+define void @test_512(i512* %a, i512* %b, i512* %out) nounwind {
+; X32-LABEL: test_512:
+; X32:       # BB#0:
+; X32-NEXT:    pushl %ebp
+; X32-NEXT:    movl %esp, %ebp
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    andl $-8, %esp
+; X32-NEXT:    subl $656, %esp # imm = 0x290
+; X32-NEXT:    movl 8(%ebp), %eax
+; X32-NEXT:    movl 48(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 52(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 56(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 60(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 40(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 44(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 32(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 36(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl (%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 4(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 16(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 20(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 8(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 12(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 24(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 28(%eax), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 12(%ebp), %eax
+; X32-NEXT:    movl 48(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 52(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 56(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 60(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 32(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 36(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 40(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 44(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl (%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 4(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 8(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 12(%eax), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl 16(%eax), %esi
+; X32-NEXT:    movl 20(%eax), %edi
+; X32-NEXT:    movl 24(%eax), %ebx
+; X32-NEXT:    movl 28(%eax), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl $0
+; X32-NEXT:    pushl %edi
+; X32-NEXT:    pushl %esi
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    adcl %edx, %ecx
+; X32-NEXT:    movl $0, %edi
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    sbbl %edx, %edx
+; X32-NEXT:    andl $1, %edx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    addl %edx, %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %esi, %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %esi, %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %esi, %edx
+; X32-NEXT:    addl %eax, %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %ecx, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl %edi, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl %edx, %eax
+; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    movl $0, %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    sbbl %esi, %esi
+; X32-NEXT:    andl $1, %esi
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    addl %edi, %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %edi, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %edi, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %edi, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    addl %eax, %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl %ecx, %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %edx, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl %edi, %edx
+; X32-NEXT:    adcl %ebx, %esi
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    sbbl %ebx, %ebx
+; X32-NEXT:    andl $1, %ebx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %edi, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    addl %edx, %eax
+; X32-NEXT:    movl %eax, %edx
+; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    adcl %ebx, %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl %edx, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    movl %esi, %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl %edi, %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    sbbl %eax, %eax
+; X32-NEXT:    andl $1, %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl %edx, %eax
+; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    movl $0, %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    sbbl %esi, %esi
+; X32-NEXT:    andl $1, %esi
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl %edx, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl %edx, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    addl %eax, %edi
+; X32-NEXT:    adcl %ecx, %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx # 4-byte Reload
+; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl %edx, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx # 4-byte Reload
+; X32-NEXT:    adcl %edx, {{[0-9]+}}(%esp) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl %edi, %edx
+; X32-NEXT:    adcl %ebx, %esi
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    sbbl %ecx, %ecx
+; X32-NEXT:    andl $1, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    addl %edx, %edi
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl %esi, %ebx
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    addl %eax, %esi
+; X32-NEXT:    adcl %ecx, %edi
+; X32-NEXT:    movl $0, %eax
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    sbbl %ecx, %ecx
+; X32-NEXT:    andl $1, %ecx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl %eax, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl {{[0-9]+}}(%esp) # 4-byte Folded Reload
+; X32-NEXT:    pushl %eax
+; X32-NEXT:    calll __multi3
+; X32-NEXT:    addl $32, %esp
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    addl %esi, %ebx
+; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %ecx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl 16(%ebp), %edi
+; X32-NEXT:    movl %esi, 4(%edi)
+; X32-NEXT:    movl 16(%ebp), %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, (%esi)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, 8(%esi)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, 12(%esi)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, 16(%esi)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, 20(%esi)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, 24(%esi)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, 28(%esi)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, 32(%esi)
+; X32-NEXT:    movl %ebx, 36(%esi)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, 40(%esi)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, 44(%esi)
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, 48(%esi)
+; X32-NEXT:    movl %ecx, 52(%esi)
+; X32-NEXT:    movl %edx, 56(%esi)
+; X32-NEXT:    movl %eax, 60(%esi)
+; X32-NEXT:    leal -12(%ebp), %esp
+; X32-NEXT:    popl %esi
+; X32-NEXT:    popl %edi
+; X32-NEXT:    popl %ebx
+; X32-NEXT:    popl %ebp
+; X32-NEXT:    retl
+;
+; X64-LABEL: test_512:
+; X64:       # BB#0:
+; X64-NEXT:    pushq %rbp
+; X64-NEXT:    pushq %r15
+; X64-NEXT:    pushq %r14
+; X64-NEXT:    pushq %r13
+; X64-NEXT:    pushq %r12
+; X64-NEXT:    pushq %rbx
+; X64-NEXT:    pushq %rax
+; X64-NEXT:    movq %rdx, (%rsp) # 8-byte Spill
+; X64-NEXT:    movq 24(%rdi), %rbp
+; X64-NEXT:    movq 16(%rdi), %rcx
+; X64-NEXT:    movq %rsi, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq (%rsi), %rdx
+; X64-NEXT:    movq 8(%rsi), %r8
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    mulq %rsi
+; X64-NEXT:    movq %rdx, %r10
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rbp, %rax
+; X64-NEXT:    movq %rbp, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    mulq %rsi
+; X64-NEXT:    movq %rsi, %r9
+; X64-NEXT:    movq %rdx, %rbx
+; X64-NEXT:    movq %rax, %rsi
+; X64-NEXT:    addq %r10, %rsi
+; X64-NEXT:    adcq $0, %rbx
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    movq %rcx, %r11
+; X64-NEXT:    movq %r11, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    movq %rax, %r12
+; X64-NEXT:    addq %rsi, %r12
+; X64-NEXT:    adcq $0, %rcx
+; X64-NEXT:    addq %rbx, %rcx
+; X64-NEXT:    sbbq %rbx, %rbx
+; X64-NEXT:    andl $1, %ebx
+; X64-NEXT:    movq %rbp, %rax
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    movq %rax, %rbp
+; X64-NEXT:    addq %rcx, %rbp
+; X64-NEXT:    adcq %rbx, %rsi
+; X64-NEXT:    xorl %ecx, %ecx
+; X64-NEXT:    movq %r9, %rbx
+; X64-NEXT:    movq %rbx, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rbx, %rax
+; X64-NEXT:    mulq %rcx
+; X64-NEXT:    movq %rdx, %r13
+; X64-NEXT:    movq %rax, %r10
+; X64-NEXT:    movq %r11, %rax
+; X64-NEXT:    mulq %rcx
+; X64-NEXT:    movq %rdx, %r9
+; X64-NEXT:    movq %r9, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rax, %r15
+; X64-NEXT:    movq %r15, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    addq %r10, %r15
+; X64-NEXT:    adcq %r13, %r9
+; X64-NEXT:    addq %rbp, %r15
+; X64-NEXT:    adcq %rsi, %r9
+; X64-NEXT:    movq %rdi, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq (%rdi), %rax
+; X64-NEXT:    movq %rax, %r14
+; X64-NEXT:    mulq %rbx
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rdx, %r11
+; X64-NEXT:    movq 8(%rdi), %rax
+; X64-NEXT:    movq %rax, %rcx
+; X64-NEXT:    movq %rcx, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    mulq %rbx
+; X64-NEXT:    movq %rdx, %rbp
+; X64-NEXT:    movq %rax, %rsi
+; X64-NEXT:    addq %r11, %rsi
+; X64-NEXT:    adcq $0, %rbp
+; X64-NEXT:    movq %r14, %rax
+; X64-NEXT:    movq %r8, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rdx, %rbx
+; X64-NEXT:    addq %rsi, %rax
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq $0, %rbx
+; X64-NEXT:    addq %rbp, %rbx
+; X64-NEXT:    sbbq %rdi, %rdi
+; X64-NEXT:    andl $1, %edi
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    movq %rax, %rbp
+; X64-NEXT:    addq %rbx, %rbp
+; X64-NEXT:    adcq %rdi, %rsi
+; X64-NEXT:    movq %r14, %rcx
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    xorl %edx, %edx
+; X64-NEXT:    mulq %rdx
+; X64-NEXT:    movq %rdx, %r14
+; X64-NEXT:    movq %rax, %r11
+; X64-NEXT:    addq %r11, %r10
+; X64-NEXT:    adcq %r14, %r13
+; X64-NEXT:    addq %rbp, %r10
+; X64-NEXT:    adcq %rsi, %r13
+; X64-NEXT:    addq -{{[0-9]+}}(%rsp), %r10 # 8-byte Folded Reload
+; X64-NEXT:    adcq %r12, %r13
+; X64-NEXT:    adcq $0, %r15
+; X64-NEXT:    adcq $0, %r9
+; X64-NEXT:    movq %r9, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rsi # 8-byte Reload
+; X64-NEXT:    movq 16(%rsi), %r8
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    movq %rcx, %r9
+; X64-NEXT:    movq %r9, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rdx, %rdi
+; X64-NEXT:    movq %rax, %r12
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rdx, %rbx
+; X64-NEXT:    movq %rax, %rbp
+; X64-NEXT:    addq %rdi, %rbp
+; X64-NEXT:    adcq $0, %rbx
+; X64-NEXT:    movq 24(%rsi), %rdi
+; X64-NEXT:    movq %r9, %rax
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    addq %rbp, %rax
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq $0, %rsi
+; X64-NEXT:    addq %rbx, %rsi
+; X64-NEXT:    sbbq %rbp, %rbp
+; X64-NEXT:    andl $1, %ebp
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rdx, %rbx
+; X64-NEXT:    movq %rax, %r9
+; X64-NEXT:    addq %rsi, %r9
+; X64-NEXT:    adcq %rbp, %rbx
+; X64-NEXT:    movq %r8, %rax
+; X64-NEXT:    xorl %ecx, %ecx
+; X64-NEXT:    mulq %rcx
+; X64-NEXT:    movq %rdx, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rax, %rbp
+; X64-NEXT:    addq %rbp, %r11
+; X64-NEXT:    adcq %rdx, %r14
+; X64-NEXT:    addq %r9, %r11
+; X64-NEXT:    adcq %rbx, %r14
+; X64-NEXT:    addq %r10, %r12
+; X64-NEXT:    movq %r12, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq %r13, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; X64-NEXT:    adcq $0, %r11
+; X64-NEXT:    adcq $0, %r14
+; X64-NEXT:    addq %r15, %r11
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %r14 # 8-byte Folded Reload
+; X64-NEXT:    adcq $0, %rcx
+; X64-NEXT:    movq %rcx, %r13
+; X64-NEXT:    sbbq %r9, %r9
+; X64-NEXT:    andl $1, %r9d
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rdx, %r15
+; X64-NEXT:    movq %rax, %r12
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %r10 # 8-byte Reload
+; X64-NEXT:    movq %r10, %rax
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    movq %rax, %rbx
+; X64-NEXT:    addq %r15, %rbx
+; X64-NEXT:    adcq $0, %rsi
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    addq %rbx, %rax
+; X64-NEXT:    movq %rax, %rbx
+; X64-NEXT:    adcq $0, %rcx
+; X64-NEXT:    addq %rsi, %rcx
+; X64-NEXT:    sbbq %rsi, %rsi
+; X64-NEXT:    andl $1, %esi
+; X64-NEXT:    movq %r10, %rax
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    addq %rcx, %rax
+; X64-NEXT:    adcq %rsi, %rdx
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rsi # 8-byte Reload
+; X64-NEXT:    addq %rbp, %rsi
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %rcx # 8-byte Folded Reload
+; X64-NEXT:    addq %rax, %rsi
+; X64-NEXT:    adcq %rdx, %rcx
+; X64-NEXT:    addq %r11, %r12
+; X64-NEXT:    movq %r12, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq %r14, %rbx
+; X64-NEXT:    movq %rbx, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq %r13, %rsi
+; X64-NEXT:    movq %rsi, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    adcq %r9, %rcx
+; X64-NEXT:    movq %rcx, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    movq 32(%rcx), %rsi
+; X64-NEXT:    imulq %rsi, %rdi
+; X64-NEXT:    movq %rsi, %rax
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rax, %r11
+; X64-NEXT:    addq %rdi, %rdx
+; X64-NEXT:    movq 40(%rcx), %r9
+; X64-NEXT:    imulq %r9, %r8
+; X64-NEXT:    addq %rdx, %r8
+; X64-NEXT:    movq 48(%rcx), %rax
+; X64-NEXT:    movq %rcx, %rbx
+; X64-NEXT:    movq %rax, %rdi
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    imulq %rcx, %rdi
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rbp # 8-byte Reload
+; X64-NEXT:    mulq %rbp
+; X64-NEXT:    movq %rax, %r12
+; X64-NEXT:    addq %rdi, %rdx
+; X64-NEXT:    movq 56(%rbx), %rbx
+; X64-NEXT:    imulq %rbp, %rbx
+; X64-NEXT:    addq %rdx, %rbx
+; X64-NEXT:    addq %r11, %r12
+; X64-NEXT:    adcq %r8, %rbx
+; X64-NEXT:    movq %rbp, %rax
+; X64-NEXT:    movq %rbp, %r8
+; X64-NEXT:    mulq %rsi
+; X64-NEXT:    movq %rdx, %rdi
+; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    mulq %rsi
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    movq %rax, %rbp
+; X64-NEXT:    addq %rdi, %rbp
+; X64-NEXT:    adcq $0, %rsi
+; X64-NEXT:    movq %r8, %rax
+; X64-NEXT:    mulq %r9
+; X64-NEXT:    movq %rdx, %rdi
+; X64-NEXT:    movq %rax, %r11
+; X64-NEXT:    addq %rbp, %r11
+; X64-NEXT:    adcq $0, %rdi
+; X64-NEXT:    addq %rsi, %rdi
+; X64-NEXT:    sbbq %rsi, %rsi
+; X64-NEXT:    andl $1, %esi
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    mulq %r9
+; X64-NEXT:    movq %rdx, %r14
+; X64-NEXT:    movq %rax, %r15
+; X64-NEXT:    addq %rdi, %r15
+; X64-NEXT:    adcq %rsi, %r14
+; X64-NEXT:    addq %r12, %r15
+; X64-NEXT:    adcq %rbx, %r14
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rdx # 8-byte Reload
+; X64-NEXT:    movq 56(%rdx), %rcx
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %r8 # 8-byte Reload
+; X64-NEXT:    imulq %r8, %rcx
+; X64-NEXT:    movq 48(%rdx), %rbp
+; X64-NEXT:    movq %rdx, %rbx
+; X64-NEXT:    movq %r8, %rax
+; X64-NEXT:    mulq %rbp
+; X64-NEXT:    movq %rax, %rsi
+; X64-NEXT:    addq %rcx, %rdx
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %r10 # 8-byte Reload
+; X64-NEXT:    imulq %r10, %rbp
+; X64-NEXT:    addq %rdx, %rbp
+; X64-NEXT:    movq 32(%rbx), %rdi
+; X64-NEXT:    movq 40(%rbx), %r12
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; X64-NEXT:    movq %rax, %rcx
+; X64-NEXT:    imulq %r12, %rcx
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rax, %r9
+; X64-NEXT:    addq %rcx, %rdx
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %r13 # 8-byte Reload
+; X64-NEXT:    imulq %rdi, %r13
+; X64-NEXT:    addq %rdx, %r13
+; X64-NEXT:    addq %rsi, %r9
+; X64-NEXT:    adcq %rbp, %r13
+; X64-NEXT:    movq %rdi, %rax
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    movq %rax, %rsi
+; X64-NEXT:    movq %r12, %rax
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rdx, %rbx
+; X64-NEXT:    movq %rax, %rbp
+; X64-NEXT:    addq %rcx, %rbp
+; X64-NEXT:    adcq $0, %rbx
+; X64-NEXT:    movq %rdi, %rax
+; X64-NEXT:    mulq %r10
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    movq %rax, %rdi
+; X64-NEXT:    addq %rbp, %rdi
+; X64-NEXT:    adcq $0, %rcx
+; X64-NEXT:    addq %rbx, %rcx
+; X64-NEXT:    sbbq %rbp, %rbp
+; X64-NEXT:    andl $1, %ebp
+; X64-NEXT:    movq %r12, %rax
+; X64-NEXT:    mulq %r10
+; X64-NEXT:    addq %rcx, %rax
+; X64-NEXT:    adcq %rbp, %rdx
+; X64-NEXT:    addq %r9, %rax
+; X64-NEXT:    adcq %r13, %rdx
+; X64-NEXT:    addq -{{[0-9]+}}(%rsp), %rsi # 8-byte Folded Reload
+; X64-NEXT:    adcq %r11, %rdi
+; X64-NEXT:    adcq %r15, %rax
+; X64-NEXT:    adcq %r14, %rdx
+; X64-NEXT:    addq -{{[0-9]+}}(%rsp), %rsi # 8-byte Folded Reload
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %rdi # 8-byte Folded Reload
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %rax # 8-byte Folded Reload
+; X64-NEXT:    adcq -{{[0-9]+}}(%rsp), %rdx # 8-byte Folded Reload
+; X64-NEXT:    movq (%rsp), %rcx # 8-byte Reload
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rbp # 8-byte Reload
+; X64-NEXT:    movq %rbp, (%rcx)
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rbp # 8-byte Reload
+; X64-NEXT:    movq %rbp, 8(%rcx)
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rbp # 8-byte Reload
+; X64-NEXT:    movq %rbp, 16(%rcx)
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rbp # 8-byte Reload
+; X64-NEXT:    movq %rbp, 24(%rcx)
+; X64-NEXT:    movq %rsi, 32(%rcx)
+; X64-NEXT:    movq %rdi, 40(%rcx)
+; X64-NEXT:    movq %rax, 48(%rcx)
+; X64-NEXT:    movq %rdx, 56(%rcx)
+; X64-NEXT:    addq $8, %rsp
+; X64-NEXT:    popq %rbx
+; X64-NEXT:    popq %r12
+; X64-NEXT:    popq %r13
+; X64-NEXT:    popq %r14
+; X64-NEXT:    popq %r15
+; X64-NEXT:    popq %rbp
+; X64-NEXT:    retq
+  %av = load i512, i512* %a
+  %bv = load i512, i512* %b
+  %r = mul i512 %av, %bv
+  store i512 %r, i512* %out
+  ret void
+}
diff --git a/test/LTO/X86/type-mapping-bug.ll b/test/LTO/X86/type-mapping-bug.ll
index 3a1891234c86..c2aeb8817ec5 100644
--- a/test/LTO/X86/type-mapping-bug.ll
+++ b/test/LTO/X86/type-mapping-bug.ll
@@ -1,6 +1,6 @@
 ; RUN: llvm-as -o %t.dst.bc %s
 ; RUN: llvm-as -o %t.src.bc %S/Inputs/type-mapping-src.ll
-; RUN: llvm-lto %t.dst.bc %t.src.bc -o=/dev/null
+; RUN: llvm-lto %t.dst.bc %t.src.bc -o=%t.lto.bc
 
 target triple = "x86_64-pc-windows-msvc18.0.0"
 
diff --git a/test/Transforms/InstCombine/indexed-gep-compares.ll b/test/Transforms/InstCombine/indexed-gep-compares.ll
index 495881549e25..64dff2712976 100644
--- a/test/Transforms/InstCombine/indexed-gep-compares.ll
+++ b/test/Transforms/InstCombine/indexed-gep-compares.ll
@@ -167,4 +167,24 @@ lpad:
 ; CHECK:  ret i32* %[[PTR]]
 }
 
+
+@pr30402 = constant i64 3
+define i1 @test7() {
+entry:
+  br label %bb7
+
+bb7:                                              ; preds = %bb10, %entry-block
+  %phi = phi i64* [ @pr30402, %entry ], [ getelementptr inbounds (i64, i64* @pr30402, i32 1), %bb7 ]
+  %cmp = icmp eq i64* %phi, getelementptr inbounds (i64, i64* @pr30402, i32 1)
+  br i1 %cmp, label %bb10, label %bb7
+
+bb10:
+  ret i1 %cmp
+}
+; CHECK-LABEL: @test7(
+; CHECK:  %[[phi:.*]] = phi i64* [ @pr30402, %entry ], [ getelementptr inbounds (i64, i64* @pr30402, i32 1), %bb7 ]
+; CHECK:  %[[cmp:.*]] = icmp eq i64* %[[phi]], getelementptr inbounds (i64, i64* @pr30402, i32 1)
+; CHECK: ret i1 %[[cmp]]
+
+
 declare i32 @__gxx_personality_v0(...)
diff --git a/test/Transforms/InstCombine/unpack-fca.ll b/test/Transforms/InstCombine/unpack-fca.ll
index 47e747ccc468..3c5e4177d69f 100644
--- a/test/Transforms/InstCombine/unpack-fca.ll
+++ b/test/Transforms/InstCombine/unpack-fca.ll
@@ -49,6 +49,15 @@ define void @storeArrayOfA([1 x %A]* %aa.ptr) {
   ret void
 }
 
+define void @storeLargeArrayOfA([2000 x %A]* %aa.ptr) {
+; CHECK-LABEL: storeLargeArrayOfA
+; CHECK-NEXT: store [2000 x %A]
+; CHECK-NEXT: ret void
+  %i1 = insertvalue [2000 x %A] undef, %A { %A__vtbl* @A__vtblZ }, 1
+  store [2000 x %A] %i1, [2000 x %A]* %aa.ptr, align 8
+  ret void
+}
+
 define void @storeStructOfArrayOfA({ [1 x %A] }* %saa.ptr) {
 ; CHECK-LABEL: storeStructOfArrayOfA
 ; CHECK-NEXT: [[GEP:%[a-z0-9\.]+]] = getelementptr inbounds { [1 x %A] }, { [1 x %A] }* %saa.ptr, i64 0, i32 0, i64 0, i32 0
@@ -179,6 +188,14 @@ define [2 x %B] @loadArrayOfB([2 x %B]* %ab.ptr) {
   ret [2 x %B] %1
 }
 
+define [2000 x %B] @loadLargeArrayOfB([2000 x %B]* %ab.ptr) {
+; CHECK-LABEL: loadLargeArrayOfB
+; CHECK-NEXT: load [2000 x %B], [2000 x %B]* %ab.ptr, align 8
+; CHECK-NEXT: ret [2000 x %B]
+  %1 = load [2000 x %B], [2000 x %B]* %ab.ptr, align 8
+  ret [2000 x %B] %1
+}
+
 %struct.S = type <{ i8, %struct.T }>
 %struct.T = type { i32, i32 }
 
diff --git a/test/Transforms/SimplifyCFG/PR29163.ll b/test/Transforms/SimplifyCFG/PR29163.ll
new file mode 100644
index 000000000000..65f9090dd135
--- /dev/null
+++ b/test/Transforms/SimplifyCFG/PR29163.ll
@@ -0,0 +1,31 @@
+; RUN: opt -S -simplifycfg < %s | FileCheck %s
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+@GV = external constant i64*
+
+define i64* @test1(i1 %cond, i8* %P) {
+entry:
+  br i1 %cond, label %if, label %then
+
+then:
+  %bc = bitcast i8* %P to i64*
+  br label %join
+
+if:
+  %load = load i64*, i64** @GV, align 8, !dereferenceable !0
+  br label %join
+
+join:
+  %phi = phi i64* [ %bc, %then ], [ %load, %if ]
+  ret i64* %phi
+}
+
+; CHECK-LABEL: define i64* @test1(
+; CHECK: %[[bc:.*]] = bitcast i8* %P to i64*
+; CHECK: %[[load:.*]] = load i64*, i64** @GV, align 8{{$}}
+; CHECK: %[[phi:.*]] = select i1 %cond, i64* %[[load]], i64* %[[bc]]
+; CHECK: ret i64* %[[phi]]
+
+
+!0 = !{i64 8}