Hex-Rays v1.2 vs. v1.1 Decompiler Comparison Page

Below you will find side-by-side comparisons of v1.1 and v1.2 decompilations. Please maximize the window too see both columns simultaneously.

The following examples are displayed on this page:

NOTE: these are just some selected examples that can be illustrated as a side-by-side difference. Hex-Rays Decompiler v1.2 includes are many other improvements and new features that are not mentioned on this page - simply because there was nothing to compare them with. Also, some improvements have already been illustrated in the previous comparisons. We continue to improve 64-bit arithmetics and inline function recognition, but the examples would somewhat repeat older stuff, so we did not include them. Please refer to the news page for more details.

Intrinsic functions

Intrinsic functions are generally superior to inline assembly and the above text shows it.

return _InterlockedIncrement(a1);

Scalar SSE floating point instructions

The decompiler can handle SSE scalar floating point instructions directly, without any need of intrinsic functions. Mac OS X users will appreciate this improvement very much because short SSE scalar sequences are very popular in Mach-O files.

int __cdecl sub_578C(int _30, double arg4)
{
  int varC; // [sp+1Ch] [bp-Ch]@1

  varC = 0;
  tclStubsPtr->tcl_CreateTimerHandler((signed int)floor(arg4 * 1000.0),
                  (Tcl_TimerProc *)sub_54CB, &varC);
  while ( !varC )
    tclStubsPtr->tcl_DoOneEvent(0);
  return 0;
}

int __cdecl sub_578C(int a1, __int64 a2)
{
  void *v3; // ST08_4@1
  Tcl_TimerProc *v4; // ST04_4@1
  int v7; // [sp+1Ch] [bp-Ch]@1

  _EBX = 22425;
  __asm { movsd   xmm0, [ebp+arg_4] }
  v7 = 0;
  v3 = &v7;
  v4 = (Tcl_TimerProc *)sub_54CB;
  __asm
  {
    mulsd   xmm0, ds:(qword_19FC8 - 5799h)[ebx]
    cvttsd2si eax, xmm0
  }
  tclStubsPtr->tcl_CreateTimerHandler(_EAX, v4, v3);
  while ( !v7 )
    tclStubsPtr->tcl_DoOneEvent(0);
  return 0;
}

SSE intrinsic functions

While operations on packed values are difficult to decipher with and without intrinsic functions, there is still a side effect: the decompiler has more information about the data flows and unknown assembly instructions do not disrupt the analysis. See how the v6 temporary variable disappears.

    xmm0_3 = _mm_sub_pd(
               (__m128d)_mm_unpacklo_epi32(
                          _mm_unpacklo_epi32(_mm_cvtsi32_si128(eax0->fC),
                                             _mm_cvtsi32_si128(eax0->f8)),
                          (__m128i)xmmword_C1E0),
               (__m128d)xmmword_C1F0);
    result = printf("\t%s: %.*f(%sbytes)",
                    edx0,
                    0,
                    *(_OWORD *)&_mm_hadd_pd(xmm0_3, xmm0_3),
                    &unk_B36C);

    v6 = &unk_B36C;
    _EAX = *(_DWORD *)(a1 + 8);
    _EDX = *(_DWORD *)(v2 + 12);
    __asm
    {
      movd    xmm1, eax
      movd    xmm0, edx
      punpckldq xmm0, xmm1
      punpckldq xmm0, ds:(xmmword_C1E0 - 42D6h)[ebx]
      subpd   xmm0, ds:(xmmword_C1F0 - 42D6h)[ebx]
      haddpd  xmm0, xmm0
      movapd  [ebp+var_18], xmm0
    }
    v12 = _FT0;
    result = printf("\t%s: %.*f(%sbytes)", v4, 0, v12, v6);

SSE scalar operations - 2

The old version was producing a page of code, the new version - just one line. Always a pleasure to have a shorter text: no intermediary variables, no inline assembly, just straightforward code.

signed int __cdecl casual(signed int arg0, int arg4)
{
  return (signed int)floor((double)arg0 
       + (double)(random() & 0x7FFFFFFF) / 2147483647.0
         * (double)(arg4 - arg0));
}

int __cdecl casual(int a1, int a2)
{
  int result; // eax@1

  _EBX = 31521;
  _EDI = a1;
  __asm { cvtsi2sd xmm2, edi }
  _EAX = random() & 0x7FFFFFFF;
  __asm
  {
    cvtsi2sd xmm0, eax
    divsd   xmm0, ds:(qword_9FD0 - 7B21h)[ebx]
  }
  _ESI = a2 - a1;
  __asm
  {
    cvtsi2sd xmm1, esi
    mulsd   xmm0, xmm1
    addsd   xmm2, xmm0
    cvttsd2si eax, xmm2
  }
  return result;
}

SSE scalar operations - 3

The decompiler could recognize an unsigned conversion and represented in concisely. It looks surprising but the line on the right side is identical to the long text on the right side.

long double __cdecl auto_time_interval(__int64 arg0, __int64 arg8)
{
  return (double)(unsigned __int64)(arg0 - arg8) / 1000000.0;
}

long double __cdecl auto_time_interval(__int64 a1, __int64 a2)
{
  long double v3; // fst7@1
  long double result; // fst7@2
  double v5; // [sp+0h] [bp-10h]@2

  _ECX = -1866029031;
  v3 = (long double)(a1 - a2);
  if ( (signed int)((unsigned __int64)(a1 - a2) >> 32) < 0 )
  {
    v5 = v3 + flt_90C78FEC;
    __asm
    {
      movsd   xmm0, [ebp+var_10]
      divsd   xmm0, ds:(qword_90C78FF0 - 90C6A819h)[ecx]
      movsd   [ebp+var_10], xmm0
    }
    result = v5;
  }
  else
  {
    v5 = v3;
    __asm
    {
      movsd   xmm0, [ebp+var_10]
      divsd   xmm0, ds:(qword_90C78FF0 - 90C6A819h)[ecx]
      movsd   [ebp+var_10], xmm0
    }
    result = v5;
  }
  return result;
}

Better ternary operations

Yet another common compiler idiom is recognized and the output becomes better.

 v36 = sub_804CF6C(v20, v40 < 1 ? 2 : 35);

Better recognition of inlined functions

More inlined string functions are recognized.

if ( strcmp(a2[1], "1234567") )
   result = 0;
 else
   result = 6;

v4 = "1234567";
v3 = a2[1];
while ( 1 )
 {
   v5 = *v3 < (unsigned __int8)*v4;
   if ( *v3 != *v4 )
     break;
   if ( !*v3 )
     return 6;
   v6 = v3[1];
   v5 = v6 < v4[1];
   if ( v6 != v4[1] )
     break;
   v3 += 2;
   v4 += 2;
   if ( !v6 )
     return 6;
 }
result = (-(-v5 != v5 - 1) & 0xFFFFFFFA) + 6;

Recognition of signed power2 modulos

One more common compiler idiom. There are many others, we chose only one sample.

result = (v4 + a1) % 4;

Last updated 1 month ago

Was this helpful?