[LegalizeTypes] Add a simple expansion for SMULO when a libcall isn't available.

[craig.topper]

Summary

This isn't optimal, but prevents crashing when the libcall isn't
available. It just calculates the full product and makes sure the high bits
match the sign of the low half. Each of the pieces should go through their own
type legalization.

This can make D107420 unnecessary.

Needs tests, but I wanted to start discussion about D107420.

[lebedev.ri]

Tests?

[craig.topper]

Add tests. Disable i128 libcall for 32-bit x86.

[pengfei]

llvm/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp

4063

Seems Lo and Hi are not used?

[craig.topper]

llvm/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp

4063

They are output references passed to this function see line 3969.

[pengfei]

llvm/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp

4063

Oh, I saw them in the function arguments. Sorry for the noise.

[FreddyYe]

I haven't taken a look into gcc's generated code. Do you think gcc implements i256 signed mul overflow check in this same way? Hope you know...

[FreddyYe]

LGTM.

[craig.topper]

In D107581#2930184, @FreddyYe wrote:

I haven't taken a look into gcc's generated code. Do you think gcc implements i256 signed mul overflow check in this same way? Hope you know...

I'm not sure if gcc can generate an i256 overflow check. But I can tell you the i128 code this patch generates does not match gcc. gcc checks whether the upper half of the inputs matches the sign of the lower half and dispatches to 4 different cases. There are two cases where one input is large and one is small that share the same code by commuting the inputs. SelectionDAG can't create branches so it's difficult to do exactly the same thing.

llvm/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp

void DAGTypeLegalizer::ExpandIntRes_XMULO(SDNode *N,
   // Replace this with a libcall that will check overflow.
   RTLIB::Libcall LC = RTLIB::UNKNOWN_LIBCALL;
   if (VT == MVT::i32)
     LC = RTLIB::MULO_I32;
   else if (VT == MVT::i64)
     LC = RTLIB::MULO_I64;
   else if (VT == MVT::i128)
     LC = RTLIB::MULO_I128;
-  assert(LC != RTLIB::UNKNOWN_LIBCALL && "Unsupported XMULO!");
+
+  if (LC == RTLIB::UNKNOWN_LIBCALL || !TLI.getLibcallName(LC)) {
+    // FIXME: This is not an optimal expansion, but better than crashing.
+    EVT WideVT =
+        EVT::getIntegerVT(*DAG.getContext(), VT.getScalarSizeInBits() * 2);
+    SDValue LHS = DAG.getNode(ISD::SIGN_EXTEND, dl, WideVT, N->getOperand(0));
+    SDValue RHS = DAG.getNode(ISD::SIGN_EXTEND, dl, WideVT, N->getOperand(1));
+    SDValue Mul = DAG.getNode(ISD::MUL, dl, WideVT, LHS, RHS);
+    SDValue MulLo, MulHi;
+    SplitInteger(Mul, MulLo, MulHi);
+    SDValue SRA =
+        DAG.getNode(ISD::SRA, dl, VT, MulLo,
+                    DAG.getConstant(VT.getScalarSizeInBits() - 1, dl, VT));
+    SDValue Overflow =
+        DAG.getSetCC(dl, N->getValueType(1), MulHi, SRA, ISD::SETNE);
+    SplitInteger(MulLo, Lo, Hi);
+    ReplaceValueWith(SDValue(N, 1), Overflow);
+    return;
+  }
 
   SDValue Temp = DAG.CreateStackTemporary(PtrVT);
   // Temporary for the overflow value, default it to zero.
   SDValue Chain =
       DAG.getStore(DAG.getEntryNode(), dl, DAG.getConstant(0, dl, PtrVT), Temp,
                    MachinePointerInfo());
 
   TargetLowering::ArgListTy Args;

llvm/lib/Target/X86/X86ISelLowering.cpp

   }
 
   if (!Subtarget.is64Bit()) {
     // These libcalls are not available in 32-bit.
     setLibcallName(RTLIB::SHL_I128, nullptr);
     setLibcallName(RTLIB::SRL_I128, nullptr);
     setLibcallName(RTLIB::SRA_I128, nullptr);
     setLibcallName(RTLIB::MUL_I128, nullptr);
+    setLibcallName(RTLIB::MULO_I128, nullptr);
   }
 
   // Combine sin / cos into _sincos_stret if it is available.
   if (getLibcallName(RTLIB::SINCOS_STRET_F32) != nullptr &&
       getLibcallName(RTLIB::SINCOS_STRET_F64) != nullptr) {
     setOperationAction(ISD::FSINCOS, MVT::f64, Custom);
     setOperationAction(ISD::FSINCOS, MVT::f32, Custom);
   }

llvm/test/CodeGen/X86/smulo-128-legalisation-lowering.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=x86_64-darwin-unknown < %s | FileCheck %s --check-prefix=X64
+; RUN: llc -mtriple=i686-darwin-unknown < %s | FileCheck %s --check-prefix=X86
+
+define zeroext i1 @smuloi128(i128 %v1, i128 %v2, i128* %res) {
+; X64-LABEL: smuloi128:
+; X64:       ## %bb.0:
+; X64-NEXT:    pushq %rbx
+; X64-NEXT:    .cfi_def_cfa_offset 16
+; X64-NEXT:    subq $16, %rsp
+; X64-NEXT:    .cfi_def_cfa_offset 32
+; X64-NEXT:    .cfi_offset %rbx, -16
+; X64-NEXT:    movq %r8, %rbx
+; X64-NEXT:    movq $0, {{[0-9]+}}(%rsp)
+; X64-NEXT:    leaq {{[0-9]+}}(%rsp), %r8
+; X64-NEXT:    callq ___muloti4
+; X64-NEXT:    cmpq $0, {{[0-9]+}}(%rsp)
+; X64-NEXT:    setne %cl
+; X64-NEXT:    movq %rdx, 8(%rbx)
+; X64-NEXT:    movq %rax, (%rbx)
+; X64-NEXT:    movl %ecx, %eax
+; X64-NEXT:    addq $16, %rsp
+; X64-NEXT:    popq %rbx
+; X64-NEXT:    retq
+;
+; X86-LABEL: smuloi128:
+; X86:       ## %bb.0:
+; X86-NEXT:    pushl %ebp
+; X86-NEXT:    .cfi_def_cfa_offset 8
+; X86-NEXT:    pushl %ebx
+; X86-NEXT:    .cfi_def_cfa_offset 12
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    .cfi_def_cfa_offset 16
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    .cfi_def_cfa_offset 20
+; X86-NEXT:    subl $52, %esp
+; X86-NEXT:    .cfi_def_cfa_offset 72
+; X86-NEXT:    .cfi_offset %esi, -20
+; X86-NEXT:    .cfi_offset %edi, -16
+; X86-NEXT:    .cfi_offset %ebx, -12
+; X86-NEXT:    .cfi_offset %ebp, -8
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    movl %edi, %eax
+; X86-NEXT:    mull %ebx
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    mull %ebx
+; X86-NEXT:    movl %ebx, %esi
+; X86-NEXT:    movl %edx, %ebx
+; X86-NEXT:    movl %eax, %ebp
+; X86-NEXT:    addl %ecx, %ebp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    adcl $0, %ebx
+; X86-NEXT:    movl %edi, %eax
+; X86-NEXT:    mull %ecx
+; X86-NEXT:    movl %ecx, %edi
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    addl %ebp, %eax
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl %ebx, %ecx
+; X86-NEXT:    setb %bl
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull %edi
+; X86-NEXT:    addl %ecx, %eax
+; X86-NEXT:    movl %eax, (%esp) ## 4-byte Spill
+; X86-NEXT:    movzbl %bl, %eax
+; X86-NEXT:    adcl %eax, %edx
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, %eax
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %edx, %ebx
+; X86-NEXT:    movl %eax, %ebp
+; X86-NEXT:    addl %ecx, %ebp
+; X86-NEXT:    adcl $0, %ebx
+; X86-NEXT:    movl %edi, %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %edx, %edi
+; X86-NEXT:    addl %ebp, %eax
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl %ebx, %edi
+; X86-NEXT:    setb %cl
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT:    movl %ebp, %eax
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %eax, %ebx
+; X86-NEXT:    addl %edi, %ebx
+; X86-NEXT:    movzbl %cl, %eax
+; X86-NEXT:    adcl %eax, %edx
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx ## 4-byte Folded Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx ## 4-byte Folded Reload
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl $0, (%esp) ## 4-byte Folded Spill
+; X86-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Folded Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl %ecx, %eax
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %edx, %edi
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl %ebp, %eax
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %edx, %ebp
+; X86-NEXT:    movl %eax, %esi
+; X86-NEXT:    addl %edi, %esi
+; X86-NEXT:    adcl $0, %ebp
+; X86-NEXT:    movl %ecx, %eax
+; X86-NEXT:    mull {{[0-9]+}}(%esp)
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    addl %esi, %eax
+; X86-NEXT:    movl %eax, %edi
+; X86-NEXT:    adcl %ebp, %ecx
+; X86-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) ## 1-byte Folded Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull {{[0-9]+}}(%esp)
+; X86-NEXT:    movl %edx, %ebp
+; X86-NEXT:    movl %eax, %esi
+; X86-NEXT:    addl %ecx, %esi
+; X86-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 1-byte Folded Reload
+; X86-NEXT:    adcl %eax, %ebp
+; X86-NEXT:    addl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Folded Spill
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi ## 4-byte Folded Reload
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl $0, %esi
+; X86-NEXT:    adcl $0, %ebp
+; X86-NEXT:    addl (%esp), %esi ## 4-byte Folded Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp ## 4-byte Folded Reload
+; X86-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) ## 1-byte Folded Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    mull %ecx
+; X86-NEXT:    movl %edx, (%esp) ## 4-byte Spill
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull %ecx
+; X86-NEXT:    movl %edx, %ebx
+; X86-NEXT:    movl %eax, %ecx
+; X86-NEXT:    addl (%esp), %ecx ## 4-byte Folded Reload
+; X86-NEXT:    adcl $0, %ebx
+; X86-NEXT:    movl %edi, %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    mull %edx
+; X86-NEXT:    movl %edx, %edi
+; X86-NEXT:    addl %ecx, %eax
+; X86-NEXT:    movl %eax, %ecx
+; X86-NEXT:    adcl %ebx, %edi
+; X86-NEXT:    setb %bl
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull {{[0-9]+}}(%esp)
+; X86-NEXT:    addl %edi, %eax
+; X86-NEXT:    movl %eax, %edi
+; X86-NEXT:    movzbl %bl, %eax
+; X86-NEXT:    adcl %eax, %edx
+; X86-NEXT:    addl %esi, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Folded Spill
+; X86-NEXT:    adcl %ebp, %ecx
+; X86-NEXT:    movl %ecx, (%esp) ## 4-byte Spill
+; X86-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 1-byte Folded Reload
+; X86-NEXT:    adcl %eax, %edi
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl $0, %edx
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    sarl $31, %ebx
+; X86-NEXT:    movl %ebx, %ecx
+; X86-NEXT:    imull {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl %ebx, %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    addl %ecx, %edx
+; X86-NEXT:    imull %ebx, %esi
+; X86-NEXT:    addl %edx, %esi
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl %ebx, %ecx
+; X86-NEXT:    imull {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl %ebx, %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    mull %edi
+; X86-NEXT:    movl %eax, %esi
+; X86-NEXT:    addl %ecx, %edx
+; X86-NEXT:    movl %ebx, %ebp
+; X86-NEXT:    imull %edi, %ebp
+; X86-NEXT:    addl %edx, %ebp
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi ## 4-byte Folded Reload
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp ## 4-byte Folded Reload
+; X86-NEXT:    movl %edi, %eax
+; X86-NEXT:    mull %ebx
+; X86-NEXT:    movl %edx, %edi
+; X86-NEXT:    movl %eax, %ecx
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull %ebx
+; X86-NEXT:    movl %edx, %esi
+; X86-NEXT:    movl %eax, %ebx
+; X86-NEXT:    addl %edi, %ebx
+; X86-NEXT:    adcl $0, %edx
+; X86-NEXT:    addl %ecx, %ebx
+; X86-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl %edi, %edx
+; X86-NEXT:    setb %cl
+; X86-NEXT:    addl %eax, %edx
+; X86-NEXT:    movzbl %cl, %eax
+; X86-NEXT:    adcl %esi, %eax
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx ## 4-byte Folded Reload
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl %ebp, %eax
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    sarl $31, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl %eax, %edi
+; X86-NEXT:    imull %ecx, %edi
+; X86-NEXT:    mull %ecx
+; X86-NEXT:    movl %eax, %ebx
+; X86-NEXT:    addl %edi, %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    imull %ecx, %edi
+; X86-NEXT:    addl %edx, %edi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl %eax, %ebp
+; X86-NEXT:    imull %ecx, %ebp
+; X86-NEXT:    mull %ecx
+; X86-NEXT:    movl %eax, %esi
+; X86-NEXT:    addl %ebp, %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    imull %ecx, %eax
+; X86-NEXT:    addl %edx, %eax
+; X86-NEXT:    addl %ebx, %esi
+; X86-NEXT:    movl %esi, %ebx
+; X86-NEXT:    adcl %edi, %eax
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl %ecx, %eax
+; X86-NEXT:    mull {{[0-9]+}}(%esp)
+; X86-NEXT:    movl %edx, %ebp
+; X86-NEXT:    movl %eax, %edi
+; X86-NEXT:    movl %eax, %esi
+; X86-NEXT:    addl %edx, %esi
+; X86-NEXT:    adcl $0, %ebp
+; X86-NEXT:    movl %ecx, %eax
+; X86-NEXT:    mull {{[0-9]+}}(%esp)
+; X86-NEXT:    addl %eax, %esi
+; X86-NEXT:    adcl %edx, %ebp
+; X86-NEXT:    setb %cl
+; X86-NEXT:    addl %eax, %ebp
+; X86-NEXT:    movzbl %cl, %eax
+; X86-NEXT:    adcl %edx, %eax
+; X86-NEXT:    addl %ebx, %ebp
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Folded Reload
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi ## 4-byte Folded Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi ## 4-byte Folded Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp ## 4-byte Folded Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Folded Reload
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi ## 4-byte Folded Reload
+; X86-NEXT:    adcl (%esp), %esi ## 4-byte Folded Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp ## 4-byte Folded Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Folded Reload
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx ## 4-byte Reload
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    sarl $31, %ecx
+; X86-NEXT:    xorl %ecx, %eax
+; X86-NEXT:    xorl %ecx, %esi
+; X86-NEXT:    orl %eax, %esi
+; X86-NEXT:    xorl %ecx, %ebp
+; X86-NEXT:    xorl %edi, %ecx
+; X86-NEXT:    orl %ebp, %ecx
+; X86-NEXT:    orl %esi, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl %edx, 12(%eax)
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 4-byte Reload
+; X86-NEXT:    movl %ecx, (%eax)
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 4-byte Reload
+; X86-NEXT:    movl %ecx, 4(%eax)
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 4-byte Reload
+; X86-NEXT:    movl %ecx, 8(%eax)
+; X86-NEXT:    setne %al
+; X86-NEXT:    addl $52, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    popl %ebx
+; X86-NEXT:    popl %ebp
+; X86-NEXT:    retl
+  %t = call {i128, i1} @llvm.smul.with.overflow.i128(i128 %v1, i128 %v2)
+  %val = extractvalue {i128, i1} %t, 0
+  %obit = extractvalue {i128, i1} %t, 1
+  store i128 %val, i128* %res
+  ret i1 %obit
+}
+
+define zeroext i1 @smuloi256(i256 %v1, i256 %v2, i256* %res) {
+; X64-LABEL: smuloi256:
+; X64:       ## %bb.0:
+; X64-NEXT:    pushq %rbp
+; X64-NEXT:    .cfi_def_cfa_offset 16
+; X64-NEXT:    pushq %r15
+; X64-NEXT:    .cfi_def_cfa_offset 24
+; X64-NEXT:    pushq %r14
+; X64-NEXT:    .cfi_def_cfa_offset 32
+; X64-NEXT:    pushq %r13
+; X64-NEXT:    .cfi_def_cfa_offset 40
+; X64-NEXT:    pushq %r12
+; X64-NEXT:    .cfi_def_cfa_offset 48
+; X64-NEXT:    pushq %rbx
+; X64-NEXT:    .cfi_def_cfa_offset 56
+; X64-NEXT:    .cfi_offset %rbx, -56
+; X64-NEXT:    .cfi_offset %r12, -48
+; X64-NEXT:    .cfi_offset %r13, -40
+; X64-NEXT:    .cfi_offset %r14, -32
+; X64-NEXT:    .cfi_offset %r15, -24
+; X64-NEXT:    .cfi_offset %rbp, -16
+; X64-NEXT:    movq %rcx, %r15
+; X64-NEXT:    movq %rdx, %r11
+; X64-NEXT:    movq %rdx, %rax
+; X64-NEXT:    movq %rdx, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rdx, %r10
+; X64-NEXT:    movq %rax, %r14
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    movq %rcx, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rdx, %rbx
+; X64-NEXT:    movq %rax, %rbp
+; X64-NEXT:    addq %r10, %rbp
+; X64-NEXT:    adcq $0, %rbx
+; X64-NEXT:    movq %r11, %rax
+; X64-NEXT:    mulq %r9
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    movq %rax, %r11
+; X64-NEXT:    addq %rbp, %r11
+; X64-NEXT:    adcq %rbx, %rcx
+; X64-NEXT:    setb %al
+; X64-NEXT:    movzbl %al, %ebp
+; X64-NEXT:    movq %r15, %rax
+; X64-NEXT:    mulq %r9
+; X64-NEXT:    movq %r9, %r15
+; X64-NEXT:    movq %rdx, %r12
+; X64-NEXT:    movq %rax, %r10
+; X64-NEXT:    addq %rcx, %r10
+; X64-NEXT:    adcq %rbp, %r12
+; X64-NEXT:    movq %rdi, %r9
+; X64-NEXT:    movq %rdi, %rax
+; X64-NEXT:    movq %r8, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rdx, %rbp
+; X64-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; X64-NEXT:    movq %rsi, %rcx
+; X64-NEXT:    movq %rsi, %rax
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rdx, %rbx
+; X64-NEXT:    movq %rax, %rsi
+; X64-NEXT:    addq %rbp, %rsi
+; X64-NEXT:    adcq $0, %rbx
+; X64-NEXT:    movq %rdi, %rax
+; X64-NEXT:    movq %r15, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; X64-NEXT:    mulq %r15
+; X64-NEXT:    movq %rdx, %rbp
+; X64-NEXT:    addq %rsi, %rax
+; X64-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; X64-NEXT:    adcq %rbx, %rbp
+; X64-NEXT:    setb %bl
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    movq %rcx, %rdi
+; X64-NEXT:    mulq %r15
+; X64-NEXT:    movq %rdx, %r15
+; X64-NEXT:    movq %rax, %rcx
+; X64-NEXT:    addq %rbp, %rcx
+; X64-NEXT:    movzbl %bl, %eax
+; X64-NEXT:    adcq %rax, %r15
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %r8
+; X64-NEXT:    addq %r14, %rcx
+; X64-NEXT:    adcq %r11, %r15
+; X64-NEXT:    adcq $0, %r10
+; X64-NEXT:    adcq $0, %r12
+; X64-NEXT:    movq %r9, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; X64-NEXT:    movq %r9, %rax
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rdx, %rsi
+; X64-NEXT:    movq %rax, %r11
+; X64-NEXT:    movq %rdi, %rax
+; X64-NEXT:    movq %rdi, %r14
+; X64-NEXT:    movq %rdi, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rdx, %rbp
+; X64-NEXT:    movq %rax, %rdi
+; X64-NEXT:    addq %rsi, %rdi
+; X64-NEXT:    adcq $0, %rbp
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rsi
+; X64-NEXT:    movq %r9, %rax
+; X64-NEXT:    mulq %rsi
+; X64-NEXT:    movq %rdx, %rbx
+; X64-NEXT:    addq %rdi, %rax
+; X64-NEXT:    movq %rax, %rdi
+; X64-NEXT:    adcq %rbp, %rbx
+; X64-NEXT:    setb %r9b
+; X64-NEXT:    movq %r14, %rax
+; X64-NEXT:    mulq %rsi
+; X64-NEXT:    movq %rdx, %r13
+; X64-NEXT:    movq %rax, %r14
+; X64-NEXT:    addq %rbx, %r14
+; X64-NEXT:    movzbl %r9b, %eax
+; X64-NEXT:    adcq %rax, %r13
+; X64-NEXT:    addq %rcx, %r11
+; X64-NEXT:    movq %r11, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; X64-NEXT:    adcq %r15, %rdi
+; X64-NEXT:    movq %rdi, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; X64-NEXT:    adcq $0, %r14
+; X64-NEXT:    adcq $0, %r13
+; X64-NEXT:    addq %r10, %r14
+; X64-NEXT:    adcq %r12, %r13
+; X64-NEXT:    setb %r9b
+; X64-NEXT:    movq {{[-0-9]+}}(%r{{[sb]}}p), %rbp ## 8-byte Reload
+; X64-NEXT:    movq %rbp, %rax
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    movq %rax, %r10
+; X64-NEXT:    movq {{[-0-9]+}}(%r{{[sb]}}p), %r12 ## 8-byte Reload
+; X64-NEXT:    movq %r12, %rax
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rdx, %rdi
+; X64-NEXT:    movq %rax, %rbx
+; X64-NEXT:    addq %rcx, %rbx
+; X64-NEXT:    adcq $0, %rdi
+; X64-NEXT:    movq %rbp, %rax
+; X64-NEXT:    mulq %rsi
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    addq %rbx, %rax
+; X64-NEXT:    movq %rax, %rbp
+; X64-NEXT:    adcq %rdi, %rcx
+; X64-NEXT:    setb %bl
+; X64-NEXT:    movq %r12, %rax
+; X64-NEXT:    mulq %rsi
+; X64-NEXT:    movq %rax, %r11
+; X64-NEXT:    addq %rcx, %r11
+; X64-NEXT:    movzbl %bl, %eax
+; X64-NEXT:    adcq %rax, %rdx
+; X64-NEXT:    addq %r14, %r10
+; X64-NEXT:    movq %r10, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; X64-NEXT:    adcq %r13, %rbp
+; X64-NEXT:    movq %rbp, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; X64-NEXT:    movzbl %r9b, %eax
+; X64-NEXT:    adcq %rax, %r11
+; X64-NEXT:    adcq $0, %rdx
+; X64-NEXT:    movq %rdx, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; X64-NEXT:    movq %r12, %rdi
+; X64-NEXT:    sarq $63, %rdi
+; X64-NEXT:    movq %rdi, %rcx
+; X64-NEXT:    imulq %rsi, %rcx
+; X64-NEXT:    movq %rdi, %rax
+; X64-NEXT:    mulq %r8
+; X64-NEXT:    movq %rax, %r9
+; X64-NEXT:    addq %rcx, %rdx
+; X64-NEXT:    imulq %rdi, %r8
+; X64-NEXT:    addq %rdx, %r8
+; X64-NEXT:    movq %rdi, %rbp
+; X64-NEXT:    movq {{[-0-9]+}}(%r{{[sb]}}p), %r10 ## 8-byte Reload
+; X64-NEXT:    imulq %r10, %rbp
+; X64-NEXT:    movq %rdi, %rax
+; X64-NEXT:    movq {{[-0-9]+}}(%r{{[sb]}}p), %rbx ## 8-byte Reload
+; X64-NEXT:    mulq %rbx
+; X64-NEXT:    movq %rax, %r13
+; X64-NEXT:    addq %rbp, %rdx
+; X64-NEXT:    movq %rdi, %rcx
+; X64-NEXT:    imulq %rbx, %rcx
+; X64-NEXT:    movq %rbx, %rax
+; X64-NEXT:    addq %rdx, %rcx
+; X64-NEXT:    addq %r9, %r13
+; X64-NEXT:    adcq %r8, %rcx
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rdx, %rbx
+; X64-NEXT:    movq %rax, %r14
+; X64-NEXT:    movq %r10, %rax
+; X64-NEXT:    mulq %rdi
+; X64-NEXT:    movq %rax, %r8
+; X64-NEXT:    addq %rbx, %r8
+; X64-NEXT:    movq %rdx, %rbp
+; X64-NEXT:    adcq $0, %rbp
+; X64-NEXT:    addq %r14, %r8
+; X64-NEXT:    adcq %rbx, %rbp
+; X64-NEXT:    setb %bl
+; X64-NEXT:    addq %rax, %rbp
+; X64-NEXT:    movzbl %bl, %r15d
+; X64-NEXT:    adcq %rdx, %r15
+; X64-NEXT:    addq %r13, %rbp
+; X64-NEXT:    adcq %rcx, %r15
+; X64-NEXT:    sarq $63, %rsi
+; X64-NEXT:    movq {{[-0-9]+}}(%r{{[sb]}}p), %r10 ## 8-byte Reload
+; X64-NEXT:    movq %r10, %rcx
+; X64-NEXT:    imulq %rsi, %rcx
+; X64-NEXT:    movq %r10, %rax
+; X64-NEXT:    mulq %rsi
+; X64-NEXT:    movq %rax, %rdi
+; X64-NEXT:    addq %rcx, %rdx
+; X64-NEXT:    movq {{[-0-9]+}}(%r{{[sb]}}p), %r9 ## 8-byte Reload
+; X64-NEXT:    movq %r9, %rcx
+; X64-NEXT:    imulq %rsi, %rcx
+; X64-NEXT:    addq %rdx, %rcx
+; X64-NEXT:    movq {{[-0-9]+}}(%r{{[sb]}}p), %rax ## 8-byte Reload
+; X64-NEXT:    movq %rax, %rbx
+; X64-NEXT:    imulq %rsi, %rbx
+; X64-NEXT:    mulq %rsi
+; X64-NEXT:    movq %rax, %r13
+; X64-NEXT:    addq %rbx, %rdx
+; X64-NEXT:    movq %r12, %rax
+; X64-NEXT:    imulq %rsi, %rax
+; X64-NEXT:    addq %rdx, %rax
+; X64-NEXT:    addq %rdi, %r13
+; X64-NEXT:    adcq %rcx, %rax
+; X64-NEXT:    movq %rax, %r12
+; X64-NEXT:    movq %rsi, %rax
+; X64-NEXT:    mulq %r10
+; X64-NEXT:    movq %rdx, %rbx
+; X64-NEXT:    movq %rax, %rcx
+; X64-NEXT:    movq %rax, %rdi
+; X64-NEXT:    addq %rdx, %rdi
+; X64-NEXT:    adcq $0, %rbx
+; X64-NEXT:    movq %rsi, %rax
+; X64-NEXT:    mulq %r9
+; X64-NEXT:    addq %rax, %rdi
+; X64-NEXT:    adcq %rdx, %rbx
+; X64-NEXT:    setb %sil
+; X64-NEXT:    addq %rax, %rbx
+; X64-NEXT:    movzbl %sil, %eax
+; X64-NEXT:    adcq %rdx, %rax
+; X64-NEXT:    addq %r13, %rbx
+; X64-NEXT:    adcq %r12, %rax
+; X64-NEXT:    addq %r14, %rcx
+; X64-NEXT:    adcq %r8, %rdi
+; X64-NEXT:    adcq %rbp, %rbx
+; X64-NEXT:    adcq %r15, %rax
+; X64-NEXT:    addq {{[-0-9]+}}(%r{{[sb]}}p), %rcx ## 8-byte Folded Reload
+; X64-NEXT:    adcq {{[-0-9]+}}(%r{{[sb]}}p), %rdi ## 8-byte Folded Reload
+; X64-NEXT:    adcq %r11, %rbx
+; X64-NEXT:    adcq {{[-0-9]+}}(%r{{[sb]}}p), %rax ## 8-byte Folded Reload
+; X64-NEXT:    movq {{[-0-9]+}}(%r{{[sb]}}p), %rsi ## 8-byte Reload
+; X64-NEXT:    movq %rsi, %rdx
+; X64-NEXT:    sarq $63, %rdx
+; X64-NEXT:    xorq %rdx, %rax
+; X64-NEXT:    xorq %rdx, %rdi
+; X64-NEXT:    orq %rax, %rdi
+; X64-NEXT:    xorq %rdx, %rbx
+; X64-NEXT:    xorq %rcx, %rdx
+; X64-NEXT:    orq %rbx, %rdx
+; X64-NEXT:    orq %rdi, %rdx
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %rax
+; X64-NEXT:    movq %rsi, 24(%rax)
+; X64-NEXT:    movq {{[-0-9]+}}(%r{{[sb]}}p), %rcx ## 8-byte Reload
+; X64-NEXT:    movq %rcx, (%rax)
+; X64-NEXT:    movq {{[-0-9]+}}(%r{{[sb]}}p), %rcx ## 8-byte Reload
+; X64-NEXT:    movq %rcx, 8(%rax)
+; X64-NEXT:    movq {{[-0-9]+}}(%r{{[sb]}}p), %rcx ## 8-byte Reload
+; X64-NEXT:    movq %rcx, 16(%rax)
+; X64-NEXT:    setne %al
+; 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
+;
+; X86-LABEL: smuloi256:
+; X86:       ## %bb.0:
+; X86-NEXT:    pushl %ebp
+; X86-NEXT:    .cfi_def_cfa_offset 8
+; X86-NEXT:    pushl %ebx
+; X86-NEXT:    .cfi_def_cfa_offset 12
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    .cfi_def_cfa_offset 16
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    .cfi_def_cfa_offset 20
+; X86-NEXT:    subl $152, %esp
+; X86-NEXT:    .cfi_def_cfa_offset 172
+; X86-NEXT:    .cfi_offset %esi, -20
+; X86-NEXT:    .cfi_offset %edi, -16
+; X86-NEXT:    .cfi_offset %ebx, -12
+; X86-NEXT:    .cfi_offset %ebp, -8
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %ebx, %eax
+; X86-NEXT:    mull %edi
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    movl %eax, (%esp) ## 4-byte Spill
+; X86-NEXT:    movl %ebp, %eax
+; X86-NEXT:    mull %edi
+; X86-NEXT:    movl %edx, %esi
+; X86-NEXT:    movl %eax, %edi
+; X86-NEXT:    addl %ecx, %edi
+; X86-NEXT:    adcl $0, %esi
+; X86-NEXT:    movl %ebx, %eax
+; X86-NEXT:    mull {{[0-9]+}}(%esp)
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    addl %edi, %eax
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl %esi, %ecx
+; X86-NEXT:    setb %bl
+; X86-NEXT:    movl %ebp, %eax
+; X86-NEXT:    mull {{[0-9]+}}(%esp)
+; X86-NEXT:    movl %eax, %edi
+; X86-NEXT:    addl %ecx, %edi
+; X86-NEXT:    movzbl %bl, %eax
+; X86-NEXT:    adcl %eax, %edx
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl %edx, %ebx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %edx, %esi
+; X86-NEXT:    movl %eax, %ebp
+; X86-NEXT:    addl %ebx, %ebp
+; X86-NEXT:    adcl $0, %esi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull {{[0-9]+}}(%esp)
+; X86-NEXT:    movl %edx, %ebx
+; X86-NEXT:    addl %ebp, %eax
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl %esi, %ebx
+; X86-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) ## 1-byte Folded Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT:    movl %ebp, %eax
+; X86-NEXT:    mull {{[0-9]+}}(%esp)
+; X86-NEXT:    movl %eax, %esi
+; X86-NEXT:    addl %ebx, %esi
+; X86-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 1-byte Folded Reload
+; X86-NEXT:    adcl %eax, %edx
+; X86-NEXT:    addl (%esp), %esi ## 4-byte Folded Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx ## 4-byte Folded Reload
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl $0, %edi
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl $0, %ecx
+; X86-NEXT:    movl %ecx, (%esp) ## 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl %ecx, %eax
+; X86-NEXT:    mull %edi
+; X86-NEXT:    movl %edx, %ebx
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl %ebp, %eax
+; X86-NEXT:    mull %edi
+; X86-NEXT:    movl %edx, %ebp
+; X86-NEXT:    movl %eax, %edi
+; X86-NEXT:    addl %ebx, %edi
+; X86-NEXT:    adcl $0, %ebp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    movl %ecx, %eax
+; X86-NEXT:    mull %ebx
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    addl %edi, %eax
+; X86-NEXT:    movl %eax, %edi
+; X86-NEXT:    adcl %ebp, %ecx
+; X86-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) ## 1-byte Folded Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull %ebx
+; X86-NEXT:    movl %edx, %ebx
+; X86-NEXT:    movl %eax, %ebp
+; X86-NEXT:    addl %ecx, %ebp
+; X86-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 1-byte Folded Reload
+; X86-NEXT:    adcl %eax, %ebx
+; X86-NEXT:    addl %esi, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Folded Spill
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi ## 4-byte Folded Reload
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl $0, %ebp
+; X86-NEXT:    adcl $0, %ebx
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp ## 4-byte Folded Reload
+; X86-NEXT:    adcl (%esp), %ebx ## 4-byte Folded Reload
+; X86-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) ## 1-byte Folded Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    movl %eax, (%esp) ## 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %edx, %esi
+; X86-NEXT:    movl %eax, %edi
+; X86-NEXT:    addl %ecx, %edi
+; X86-NEXT:    adcl $0, %esi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    mull %ecx
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    addl %edi, %eax
+; X86-NEXT:    movl %eax, %edi
+; X86-NEXT:    adcl %esi, %ecx
+; X86-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) ## 1-byte Folded Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull {{[0-9]+}}(%esp)
+; X86-NEXT:    addl %ecx, %eax
+; X86-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 1-byte Folded Reload
+; X86-NEXT:    adcl %ecx, %edx
+; X86-NEXT:    addl %ebp, (%esp) ## 4-byte Folded Spill
+; X86-NEXT:    adcl %ebx, %edi
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 1-byte Folded Reload
+; X86-NEXT:    adcl %ecx, %eax
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl $0, %edx
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    movl %ebx, %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %edx, %esi
+; X86-NEXT:    movl %eax, %edi
+; X86-NEXT:    addl %ecx, %edi
+; X86-NEXT:    adcl $0, %esi
+; X86-NEXT:    movl %ebx, %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT:    mull %ebp
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    addl %edi, %eax
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl %esi, %ecx
+; X86-NEXT:    setb %bl
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull %ebp
+; X86-NEXT:    addl %ecx, %eax
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movzbl %bl, %eax
+; X86-NEXT:    adcl %eax, %edx
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT:    movl %ebp, %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl %edx, %edi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %edx, %esi
+; X86-NEXT:    movl %eax, %ebx
+; X86-NEXT:    addl %edi, %ebx
+; X86-NEXT:    adcl $0, %esi
+; X86-NEXT:    movl %ebp, %eax
+; X86-NEXT:    movl %ebp, %edi
+; X86-NEXT:    mull {{[0-9]+}}(%esp)
+; X86-NEXT:    movl %edx, %ebp
+; X86-NEXT:    addl %ebx, %eax
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl %esi, %ebp
+; X86-NEXT:    setb %bl
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull {{[0-9]+}}(%esp)
+; X86-NEXT:    movl %eax, %esi
+; X86-NEXT:    addl %ebp, %esi
+; X86-NEXT:    movzbl %bl, %eax
+; X86-NEXT:    adcl %eax, %edx
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi ## 4-byte Folded Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx ## 4-byte Folded Reload
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Folded Spill
+; X86-NEXT:    adcl $0, %ecx
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl %edi, %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    mull %ecx
+; X86-NEXT:    movl %edx, %ebx
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull %ecx
+; X86-NEXT:    movl %edx, %ebp
+; X86-NEXT:    movl %eax, %edi
+; X86-NEXT:    addl %ebx, %edi
+; X86-NEXT:    adcl $0, %ebp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    mull %ebx
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    addl %edi, %eax
+; X86-NEXT:    movl %eax, %edi
+; X86-NEXT:    adcl %ebp, %ecx
+; X86-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) ## 1-byte Folded Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull %ebx
+; X86-NEXT:    movl %edx, %ebx
+; X86-NEXT:    movl %eax, %ebp
+; X86-NEXT:    addl %ecx, %ebp
+; X86-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 1-byte Folded Reload
+; X86-NEXT:    adcl %eax, %ebx
+; X86-NEXT:    addl %esi, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Folded Spill
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi ## 4-byte Folded Reload
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl $0, %ebp
+; X86-NEXT:    adcl $0, %ebx
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp ## 4-byte Folded Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx ## 4-byte Folded Reload
+; X86-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) ## 1-byte Folded Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %edx, %esi
+; X86-NEXT:    movl %eax, %edi
+; X86-NEXT:    addl %ecx, %edi
+; X86-NEXT:    adcl $0, %esi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    mull %ecx
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    addl %edi, %eax
+; X86-NEXT:    movl %eax, %edi
+; X86-NEXT:    adcl %esi, %ecx
+; X86-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) ## 1-byte Folded Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull {{[0-9]+}}(%esp)
+; X86-NEXT:    addl %ecx, %eax
+; X86-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 1-byte Folded Reload
+; X86-NEXT:    adcl %ecx, %edx
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 4-byte Reload
+; X86-NEXT:    addl %ebp, %ecx
+; X86-NEXT:    movl %edi, %esi
+; X86-NEXT:    adcl %ebx, %esi
+; X86-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %edi ## 1-byte Folded Reload
+; X86-NEXT:    adcl %edi, %eax
+; X86-NEXT:    adcl $0, %edx
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 4-byte Folded Reload
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi ## 4-byte Folded Reload
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Folded Reload
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx ## 4-byte Folded Reload
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl $0, (%esp) ## 4-byte Folded Spill
+; X86-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Folded Spill
+; X86-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Folded Spill
+; X86-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Folded Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    movl %ebx, %eax
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT:    movl %ebp, %eax
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %edx, %esi
+; X86-NEXT:    movl %eax, %edi
+; X86-NEXT:    addl %ecx, %edi
+; X86-NEXT:    adcl $0, %esi
+; X86-NEXT:    movl %ebx, %eax
+; X86-NEXT:    mull {{[0-9]+}}(%esp)
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    addl %edi, %eax
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl %esi, %ecx
+; X86-NEXT:    setb %bl
+; X86-NEXT:    movl %ebp, %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    mull %edi
+; X86-NEXT:    addl %ecx, %eax
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movzbl %bl, %eax
+; X86-NEXT:    adcl %eax, %edx
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    movl %ebx, %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %edx, %esi
+; X86-NEXT:    movl %eax, %ebp
+; X86-NEXT:    addl %ecx, %ebp
+; X86-NEXT:    adcl $0, %esi
+; X86-NEXT:    movl %ebx, %eax
+; X86-NEXT:    mull %edi
+; X86-NEXT:    movl %edx, %ebx
+; X86-NEXT:    addl %ebp, %eax
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl %esi, %ebx
+; X86-NEXT:    setb %cl
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl %eax, %ebp
+; X86-NEXT:    mull %edi
+; X86-NEXT:    movl %eax, %esi
+; X86-NEXT:    addl %ebx, %esi
+; X86-NEXT:    movzbl %cl, %eax
+; X86-NEXT:    adcl %eax, %edx
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi ## 4-byte Folded Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx ## 4-byte Folded Reload
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Folded Spill
+; X86-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Folded Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl %ecx, %eax
+; X86-NEXT:    mull %edi
+; X86-NEXT:    movl %edx, %ebx
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl %ebp, %eax
+; X86-NEXT:    mull %edi
+; X86-NEXT:    movl %edx, %ebp
+; X86-NEXT:    movl %eax, %edi
+; X86-NEXT:    addl %ebx, %edi
+; X86-NEXT:    adcl $0, %ebp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    movl %ecx, %eax
+; X86-NEXT:    mull %ebx
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    addl %edi, %eax
+; X86-NEXT:    movl %eax, %edi
+; X86-NEXT:    adcl %ebp, %ecx
+; X86-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) ## 1-byte Folded Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull %ebx
+; X86-NEXT:    movl %edx, %ebp
+; X86-NEXT:    movl %eax, %ebx
+; X86-NEXT:    addl %ecx, %ebx
+; X86-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 1-byte Folded Reload
+; X86-NEXT:    adcl %eax, %ebp
+; X86-NEXT:    addl %esi, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Folded Spill
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi ## 4-byte Folded Reload
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl $0, %ebx
+; X86-NEXT:    adcl $0, %ebp
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx ## 4-byte Folded Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp ## 4-byte Folded Reload
+; X86-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) ## 1-byte Folded Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %edx, %esi
+; X86-NEXT:    movl %eax, %edi
+; X86-NEXT:    addl %ecx, %edi
+; X86-NEXT:    adcl $0, %esi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    mull %ecx
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    addl %edi, %eax
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl %esi, %ecx
+; X86-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) ## 1-byte Folded Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull {{[0-9]+}}(%esp)
+; X86-NEXT:    addl %ecx, %eax
+; X86-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 1-byte Folded Reload
+; X86-NEXT:    adcl %ecx, %edx
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi ## 4-byte Reload
+; X86-NEXT:    addl %ebx, %edi
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx ## 4-byte Reload
+; X86-NEXT:    adcl %ebp, %ebx
+; X86-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 1-byte Folded Reload
+; X86-NEXT:    adcl %ecx, %eax
+; X86-NEXT:    adcl $0, %edx
+; X86-NEXT:    movl %edx, %esi
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 4-byte Reload
+; X86-NEXT:    addl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Folded Spill
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 4-byte Reload
+; X86-NEXT:    adcl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Folded Spill
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 4-byte Reload
+; X86-NEXT:    adcl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Folded Spill
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 4-byte Reload
+; X86-NEXT:    adcl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Folded Spill
+; X86-NEXT:    movl %edi, %edx
+; X86-NEXT:    adcl $0, %edx
+; X86-NEXT:    movl %ebx, %ecx
+; X86-NEXT:    adcl $0, %ecx
+; X86-NEXT:    adcl $0, %eax
+; X86-NEXT:    adcl $0, %esi
+; X86-NEXT:    addl (%esp), %edx ## 4-byte Folded Reload
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 4-byte Folded Reload
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Folded Reload
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi ## 4-byte Folded Reload
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) ## 1-byte Folded Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT:    movl %ebp, %eax
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %edx, %esi
+; X86-NEXT:    movl %eax, %ebx
+; X86-NEXT:    addl %ecx, %ebx
+; X86-NEXT:    adcl $0, %esi
+; X86-NEXT:    movl %edi, %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    mull %edi
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    addl %ebx, %eax
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl %esi, %ecx
+; X86-NEXT:    setb %bl
+; X86-NEXT:    movl %ebp, %eax
+; X86-NEXT:    mull %edi
+; X86-NEXT:    addl %ecx, %eax
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movzbl %bl, %eax
+; X86-NEXT:    adcl %eax, %edx
+; X86-NEXT:    movl %edx, (%esp) ## 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    mull %ebx
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull %ebx
+; X86-NEXT:    movl %edx, %ebx
+; X86-NEXT:    movl %eax, %ebp
+; X86-NEXT:    addl %ecx, %ebp
+; X86-NEXT:    adcl $0, %ebx
+; X86-NEXT:    movl %edi, %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %edx, %edi
+; X86-NEXT:    addl %ebp, %eax
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl %ebx, %edi
+; X86-NEXT:    setb %cl
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl %eax, %ebx
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %eax, %ebp
+; X86-NEXT:    addl %edi, %ebp
+; X86-NEXT:    movzbl %cl, %eax
+; X86-NEXT:    adcl %eax, %edx
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp ## 4-byte Folded Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx ## 4-byte Folded Reload
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Folded Spill
+; X86-NEXT:    adcl $0, (%esp) ## 4-byte Folded Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl %ecx, %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %edx, %edi
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl %ebx, %eax
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %edx, %ebx
+; X86-NEXT:    movl %eax, %esi
+; X86-NEXT:    addl %edi, %esi
+; X86-NEXT:    adcl $0, %ebx
+; X86-NEXT:    movl %ecx, %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    mull %edi
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    addl %esi, %eax
+; X86-NEXT:    movl %eax, %esi
+; X86-NEXT:    adcl %ebx, %ecx
+; X86-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) ## 1-byte Folded Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull %edi
+; X86-NEXT:    movl %edx, %ebx
+; X86-NEXT:    movl %eax, %edi
+; X86-NEXT:    addl %ecx, %edi
+; X86-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 1-byte Folded Reload
+; X86-NEXT:    adcl %eax, %ebx
+; X86-NEXT:    addl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Folded Spill
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi ## 4-byte Folded Reload
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl $0, %edi
+; X86-NEXT:    adcl $0, %ebx
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi ## 4-byte Folded Reload
+; X86-NEXT:    adcl (%esp), %ebx ## 4-byte Folded Reload
+; X86-NEXT:    setb (%esp) ## 1-byte Folded Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull %esi
+; X86-NEXT:    movl %edx, %esi
+; X86-NEXT:    movl %eax, %ebp
+; X86-NEXT:    addl %ecx, %ebp
+; X86-NEXT:    adcl $0, %esi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    mull %ecx
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    addl %ebp, %eax
+; X86-NEXT:    movl %eax, %ebp
+; X86-NEXT:    adcl %esi, %ecx
+; X86-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) ## 1-byte Folded Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull {{[0-9]+}}(%esp)
+; X86-NEXT:    movl %eax, %esi
+; X86-NEXT:    addl %ecx, %esi
+; X86-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 1-byte Folded Reload
+; X86-NEXT:    adcl %eax, %edx
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 4-byte Reload
+; X86-NEXT:    addl %edi, %ecx
+; X86-NEXT:    adcl %ebx, %ebp
+; X86-NEXT:    movzbl (%esp), %eax ## 1-byte Folded Reload
+; X86-NEXT:    adcl %eax, %esi
+; X86-NEXT:    adcl $0, %edx
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Reload
+; X86-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Folded Spill
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Reload
+; X86-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Folded Spill
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Reload
+; X86-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Folded Spill
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Reload
+; X86-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Folded Spill
+; X86-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 1-byte Folded Reload
+; X86-NEXT:    adcl %eax, %ecx
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl $0, %ebp
+; X86-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl $0, %esi
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl $0, %edx
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    sarl $31, %ebx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull %ebx
+; X86-NEXT:    movl %edx, %esi
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl %eax, %ecx
+; X86-NEXT:    movl %eax, (%esp) ## 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull %ebx
+; X86-NEXT:    movl %eax, %ebp
+; X86-NEXT:    addl %esi, %ebp
+; X86-NEXT:    movl %edx, %edi
+; X86-NEXT:    adcl $0, %edi
+; X86-NEXT:    addl %ecx, %ebp
+; X86-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl %esi, %edi
+; X86-NEXT:    setb %cl
+; X86-NEXT:    addl %eax, %edi
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movzbl %cl, %eax
+; X86-NEXT:    adcl %edx, %eax
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull %ebx
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl %eax, %edi
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull %ebx
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    movl %eax, %ebp
+; X86-NEXT:    movl %eax, %esi
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Reload
+; X86-NEXT:    addl %eax, %esi
+; X86-NEXT:    adcl $0, %edx
+; X86-NEXT:    addl %edi, %esi
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl %eax, %edx
+; X86-NEXT:    setb %al
+; X86-NEXT:    addl %ebp, %edx
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movzbl %al, %esi
+; X86-NEXT:    adcl %ecx, %esi
+; X86-NEXT:    movl (%esp), %ecx ## 4-byte Reload
+; X86-NEXT:    addl %edx, %ecx
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Reload
+; X86-NEXT:    adcl %esi, %eax
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp ## 4-byte Reload
+; X86-NEXT:    adcl $0, %ebp
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx ## 4-byte Reload
+; X86-NEXT:    movl %edx, %edi
+; X86-NEXT:    adcl $0, %edi
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 4-byte Folded Reload
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Folded Reload
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 4-byte Reload
+; X86-NEXT:    adcl $0, %ecx
+; X86-NEXT:    adcl $0, %esi
+; X86-NEXT:    addl %ebp, %ecx
+; X86-NEXT:    adcl %edi, %esi
+; X86-NEXT:    setb %al
+; X86-NEXT:    addl (%esp), %ecx ## 4-byte Folded Reload
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi ## 4-byte Folded Reload
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movzbl %al, %eax
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Folded Reload
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl $0, %edx
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl %eax, %ecx
+; X86-NEXT:    imull %ebx, %ecx
+; X86-NEXT:    mull %ebx
+; X86-NEXT:    movl %eax, %ebp
+; X86-NEXT:    addl %ecx, %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    imull %ebx, %edi
+; X86-NEXT:    addl %edx, %edi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl %eax, %ecx
+; X86-NEXT:    imull %ebx, %ecx
+; X86-NEXT:    mull %ebx
+; X86-NEXT:    movl %eax, %esi
+; X86-NEXT:    addl %ecx, %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    imull %ebx, %ecx
+; X86-NEXT:    addl %edx, %ecx
+; X86-NEXT:    addl %ebp, %esi
+; X86-NEXT:    adcl %edi, %ecx
+; X86-NEXT:    movl %ebx, %eax
+; X86-NEXT:    mull {{[0-9]+}}(%esp)
+; X86-NEXT:    movl %edx, %ebp
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl %eax, %edi
+; X86-NEXT:    addl %edx, %edi
+; X86-NEXT:    adcl $0, %ebp
+; X86-NEXT:    movl %ebx, %eax
+; X86-NEXT:    mull {{[0-9]+}}(%esp)
+; X86-NEXT:    addl %eax, %edi
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl %edx, %ebp
+; X86-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) ## 1-byte Folded Spill
+; X86-NEXT:    addl %eax, %ebp
+; X86-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %edi ## 1-byte Folded Reload
+; X86-NEXT:    adcl %edx, %edi
+; X86-NEXT:    addl %esi, %ebp
+; X86-NEXT:    adcl %ecx, %edi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    imull %ebx, %eax
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Folded Reload
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    imull %ebx, %ecx
+; X86-NEXT:    addl %eax, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    imull %ebx, %eax
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Folded Reload
+; X86-NEXT:    movl %eax, %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    imull %ebx, %eax
+; X86-NEXT:    addl %edx, %eax
+; X86-NEXT:    movl (%esp), %edx ## 4-byte Reload
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx ## 4-byte Folded Reload
+; X86-NEXT:    movl %edx, (%esp) ## 4-byte Spill
+; X86-NEXT:    adcl %ecx, %eax
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl %ebx, %eax
+; X86-NEXT:    mull {{[0-9]+}}(%esp)
+; X86-NEXT:    movl %edx, %esi
+; X86-NEXT:    movl %eax, %ecx
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    addl %edx, %ecx
+; X86-NEXT:    adcl $0, %esi
+; X86-NEXT:    movl %ebx, %eax
+; X86-NEXT:    mull {{[0-9]+}}(%esp)
+; X86-NEXT:    addl %eax, %ecx
+; X86-NEXT:    adcl %edx, %esi
+; X86-NEXT:    setb %bl
+; X86-NEXT:    addl %eax, %esi
+; X86-NEXT:    movzbl %bl, %ebx
+; X86-NEXT:    adcl %edx, %ebx
+; X86-NEXT:    addl (%esp), %esi ## 4-byte Folded Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx ## 4-byte Folded Reload
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Reload
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Folded Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 4-byte Folded Reload
+; X86-NEXT:    adcl %ebp, %esi
+; X86-NEXT:    adcl %edi, %ebx
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Folded Reload
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 4-byte Folded Reload
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi ## 4-byte Folded Reload
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx ## 4-byte Folded Reload
+; X86-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    sarl $31, %eax
+; X86-NEXT:    movl %eax, %ebx
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    mull {{[0-9]+}}(%esp)
+; X86-NEXT:    movl %eax, %ecx
+; X86-NEXT:    movl %eax, %esi
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl %edx, %edi
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    addl %edx, %ecx
+; X86-NEXT:    adcl $0, %edi
+; X86-NEXT:    movl %ebx, %eax
+; X86-NEXT:    mull {{[0-9]+}}(%esp)
+; X86-NEXT:    addl %eax, %ecx
+; X86-NEXT:    movl %ecx, %ebx
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl %edx, %edi
+; X86-NEXT:    setb %cl
+; X86-NEXT:    addl %eax, %edi
+; X86-NEXT:    movzbl %cl, %ebp
+; X86-NEXT:    adcl %edx, %ebp
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    addl %edi, %eax
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl %ebx, %eax
+; X86-NEXT:    adcl %ebp, %eax
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl $0, %edi
+; X86-NEXT:    adcl $0, %ebp
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi ## 4-byte Reload
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    mull {{[0-9]+}}(%esp)
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    movl %eax, %ebx
+; X86-NEXT:    movl %eax, (%esp) ## 4-byte Spill
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    addl %edx, %ebx
+; X86-NEXT:    adcl $0, %ecx
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    mull {{[0-9]+}}(%esp)
+; X86-NEXT:    addl %eax, %ebx
+; X86-NEXT:    adcl %edx, %ecx
+; X86-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) ## 1-byte Folded Spill
+; X86-NEXT:    addl %eax, %ecx
+; X86-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 1-byte Folded Reload
+; X86-NEXT:    adcl %edx, %eax
+; X86-NEXT:    movl (%esp), %edx ## 4-byte Reload
+; X86-NEXT:    addl %edx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Folded Spill
+; X86-NEXT:    adcl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Folded Spill
+; X86-NEXT:    movl %ecx, %edx
+; X86-NEXT:    adcl $0, %edx
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl %eax, %esi
+; X86-NEXT:    movl %eax, %edx
+; X86-NEXT:    adcl $0, %esi
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Reload
+; X86-NEXT:    addl %edi, %eax
+; X86-NEXT:    adcl %ebp, %esi
+; X86-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) ## 1-byte Folded Spill
+; X86-NEXT:    addl (%esp), %eax ## 4-byte Folded Reload
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl %ebx, %esi
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 1-byte Folded Reload
+; X86-NEXT:    adcl %ecx, %eax
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl $0, %edx
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp ## 4-byte Reload
+; X86-NEXT:    imull %ebp, %eax
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Folded Reload
+; X86-NEXT:    movl %eax, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    imull %ebp, %eax
+; X86-NEXT:    addl %ecx, %eax
+; X86-NEXT:    movl %eax, %ecx
+; X86-NEXT:    movl %ebp, %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    imull %esi, %edx
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx ## 4-byte Folded Reload
+; X86-NEXT:    movl %ebp, %edi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    imull %eax, %edi
+; X86-NEXT:    addl %edx, %edi
+; X86-NEXT:    movl (%esp), %edx ## 4-byte Reload
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx ## 4-byte Folded Reload
+; X86-NEXT:    movl %edx, (%esp) ## 4-byte Spill
+; X86-NEXT:    adcl %ecx, %edi
+; X86-NEXT:    mull %ebp
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    movl %eax, %ebx
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    mull %ebp
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl %eax, %esi
+; X86-NEXT:    addl %ecx, %esi
+; X86-NEXT:    adcl $0, %edx
+; X86-NEXT:    addl %ebx, %esi
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl %ecx, %edx
+; X86-NEXT:    setb %cl
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx ## 4-byte Folded Reload
+; X86-NEXT:    movzbl %cl, %eax
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Folded Reload
+; X86-NEXT:    addl (%esp), %edx ## 4-byte Folded Reload
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl %edi, %eax
+; X86-NEXT:    movl %eax, (%esp) ## 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    imull %ebp, %esi
+; X86-NEXT:    movl %ebp, %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    mull %ecx
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    addl %esi, %edx
+; X86-NEXT:    imull %ebp, %ecx
+; X86-NEXT:    addl %edx, %ecx
+; X86-NEXT:    movl %ecx, %edi
+; X86-NEXT:    movl %ebp, %ecx
+; X86-NEXT:    imull {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl %ebp, %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    mull %ebx
+; X86-NEXT:    addl %ecx, %edx
+; X86-NEXT:    movl %ebp, %esi
+; X86-NEXT:    imull %ebx, %esi
+; X86-NEXT:    addl %edx, %esi
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Folded Reload
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl %edi, %esi
+; X86-NEXT:    movl %ebx, %eax
+; X86-NEXT:    mull %ebp
+; X86-NEXT:    movl %edx, %edi
+; X86-NEXT:    movl %eax, %ebx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    mull %ebp
+; X86-NEXT:    movl %edx, %ebp
+; X86-NEXT:    movl %eax, %ecx
+; X86-NEXT:    addl %edi, %eax
+; X86-NEXT:    adcl $0, %edx
+; X86-NEXT:    addl %ebx, %eax
+; X86-NEXT:    adcl %edi, %edx
+; X86-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) ## 1-byte Folded Spill
+; X86-NEXT:    addl %ecx, %edx
+; X86-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 1-byte Folded Reload
+; X86-NEXT:    adcl %ebp, %ecx
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx ## 4-byte Folded Reload
+; X86-NEXT:    adcl %esi, %ecx
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx ## 4-byte Folded Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Folded Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx ## 4-byte Folded Reload
+; X86-NEXT:    adcl (%esp), %ecx ## 4-byte Folded Reload
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx ## 4-byte Folded Reload
+; X86-NEXT:    movl %ebx, (%esp) ## 4-byte Spill
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Folded Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx ## 4-byte Folded Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 4-byte Folded Reload
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi ## 4-byte Reload
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi ## 4-byte Folded Reload
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp ## 4-byte Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp ## 4-byte Folded Reload
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi ## 4-byte Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi ## 4-byte Folded Reload
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx ## 4-byte Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx ## 4-byte Folded Reload
+; X86-NEXT:    movl (%esp), %esi ## 4-byte Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi ## 4-byte Folded Reload
+; X86-NEXT:    movl %esi, (%esp) ## 4-byte Spill
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Folded Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx ## 4-byte Folded Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 4-byte Folded Reload
+; X86-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi ## 4-byte Folded Reload
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp ## 4-byte Folded Reload
+; X86-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi ## 4-byte Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi ## 4-byte Folded Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx ## 4-byte Folded Reload
+; X86-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
+; X86-NEXT:    movl (%esp), %ebx ## 4-byte Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx ## 4-byte Folded Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Folded Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx ## 4-byte Folded Reload
+; X86-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 4-byte Folded Reload
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp ## 4-byte Reload
+; X86-NEXT:    movl %ebp, %esi
+; X86-NEXT:    sarl $31, %esi
+; X86-NEXT:    xorl %esi, %edi
+; X86-NEXT:    xorl %esi, %edx
+; X86-NEXT:    orl %edi, %edx
+; X86-NEXT:    movl %ebx, %edi
+; X86-NEXT:    xorl %esi, %edi
+; X86-NEXT:    orl %edx, %edi
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx ## 4-byte Reload
+; X86-NEXT:    xorl %esi, %edx
+; X86-NEXT:    orl %edi, %edx
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx ## 4-byte Reload
+; X86-NEXT:    xorl %esi, %ebx
+; X86-NEXT:    xorl %esi, %ecx
+; X86-NEXT:    orl %ebx, %ecx
+; X86-NEXT:    xorl %esi, %eax
+; X86-NEXT:    orl %ecx, %eax
+; X86-NEXT:    xorl {{[-0-9]+}}(%e{{[sb]}}p), %esi ## 4-byte Folded Reload
+; X86-NEXT:    orl %eax, %esi
+; X86-NEXT:    orl %edx, %esi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl %ebp, 28(%eax)
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 4-byte Reload
+; X86-NEXT:    movl %ecx, (%eax)
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 4-byte Reload
+; X86-NEXT:    movl %ecx, 4(%eax)
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 4-byte Reload
+; X86-NEXT:    movl %ecx, 8(%eax)
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 4-byte Reload
+; X86-NEXT:    movl %ecx, 12(%eax)
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 4-byte Reload
+; X86-NEXT:    movl %ecx, 16(%eax)
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 4-byte Reload
+; X86-NEXT:    movl %ecx, 20(%eax)
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx ## 4-byte Reload
+; X86-NEXT:    movl %ecx, 24(%eax)
+; X86-NEXT:    setne %al
+; X86-NEXT:    addl $152, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    popl %ebx
+; X86-NEXT:    popl %ebp
+; X86-NEXT:    retl
+  %t = call {i256, i1} @llvm.smul.with.overflow.i256(i256 %v1, i256 %v2)
+  %val = extractvalue {i256, i1} %t, 0
+  %obit = extractvalue {i256, i1} %t, 1
+  store i256 %val, i256* %res
+  ret i1 %obit
+}
+
+declare {i128, i1} @llvm.smul.with.overflow.i128(i128, i128) nounwind readnone
+declare {i256, i1} @llvm.smul.with.overflow.i256(i256, i256) nounwind readnone