// 
// sub_180005520 from 0x180005520 to 0x180005e7e (2398 bytes)
// 
// 5 xrefs:
// > sub_180003D30 @ 0x180003e52
// > <???> @ 0x18017d730
// > <???> @ 0x18017d75c
// > <???> @ 0x18017d76c
// > <???> @ 0x1801f62dc
// 
// This function is hookable on this platform!
// 
// Using BromaIDA 8.0.0 @ https://github.com/Stazzical/BromaIDA
// Using bindings at commit ba9f177b at Thu Jul 16 22:52:06 2026 from https://github.com/geode-sdk/bindings
// 

__int64 __fastcall sub_180005520(
        __int64 a1,
        float *a2,
        __int64 a3,
        _OWORD *a4,
        int a5,
        int a6,
        int a7,
        int a8,
        int a9,
        int a10,
        int a11)
{
  int v20; // esi
  __int64 v22; // r9
  __int64 v23; // r10
  __int64 result; // rax
  char v26; // r14
  int v27; // eax
  int v28; // r15d
  int v29; // r8d
  __int64 v30; // rdx
  __int64 v31; // r15
  int v32; // r14d
  int i; // r14d
  int v54; // r8d
  int *v55; // rdx
  int v56; // eax
  char v57; // r13
  int v58; // r12d
  int v59; // edx
  __int64 v60; // rax
  int v63; // r15d
  __int64 v65; // rdi
  __int64 v66; // rsi
  __int64 v69; // r13
  int j; // r13d
  int v96; // r8d
  __int64 v97; // rax
  __int64 v98; // rdx
  char v101; // r14
  int v103; // r8d
  __int64 v104; // rdx
  int v107; // r15d
  __int64 v108; // r8
  __int64 v111; // r14
  int v136; // r14d
  __int64 v138; // r9
  int v140; // r8d
  char *v142; // rdx
  int v145; // r15d
  int v147; // edx
  int v148; // r8d
  __int64 v150; // rdx
  int v171; // r14d
  int v173; // ecx
  __int64 v176; // [rsp+20h] [rbp-B8h]
  __int64 v177; // [rsp+28h] [rbp-B0h]
  __int64 v178; // [rsp+30h] [rbp-A8h]
  __int64 v179; // [rsp+60h] [rbp-78h]
  __int64 v180; // [rsp+60h] [rbp-78h]
  __int64 v181; // [rsp+68h] [rbp-70h]
  __int64 v182; // [rsp+70h] [rbp-68h]
  int v186; // [rsp+E0h] [rbp+8h]
  int v187; // [rsp+E0h] [rbp+8h]
  __int64 v188; // [rsp+F0h] [rbp+18h]
  int v189; // [rsp+100h] [rbp+28h]
  int v190; // [rsp+100h] [rbp+28h]
  int v191; // [rsp+100h] [rbp+28h]
  int v192; // [rsp+108h] [rbp+30h]

  _R11 = a2;
  _RBX = a4;
  v20 = a7;
  _RDI = a3;
  v22 = *(_QWORD *)(a1 + 16) + 4LL * a5;
  v23 = *(_QWORD *)(a1 + 8) + 4LL * a6;
  v179 = v23;
  if ( a7 == 1 )
  {
    result = sub_180005E80((_DWORD)a2, a3, (_DWORD)_RBX, v22, v23, a8, a9, a10, a11);
    __asm { vzeroupper }
  }
  else if ( a7 == 2 )
  {
    result = sub_180006070((_DWORD)a2, a3, (_DWORD)_RBX, v22, v22 + 2048, v23, v23 + 4096, a8, a9, a10, a11);
    __asm { vzeroupper }
  }
  else if ( (a7 & 3) != 0 || (((unsigned __int8)(*(_BYTE *)(a1 + 16) + 4 * a5) | (unsigned __int8)v23) & 0x1F) != 0 )
  {
    LODWORD(v178) = a7;
    LODWORD(v177) = a6;
    LODWORD(v176) = a5;
    result = sub_180004520(a1, a2, a3, _RBX, v176, v177, v178, a8, a9, a10, a11);
    __asm { vzeroupper }
  }
  else
  {
    _RCX = a7;
    v26 = a8;
    v27 = a8 >> 3;
    v28 = 8 * a7;
    __asm { vmovaps [rsp+0D8h+var_38], xmm6 }
    v189 = a8 >> 3;
    v192 = 8 * a7;
    if ( a8 >> 3 )
    {
      v29 = a7 >> 2;
      v30 = 4LL * v28;
      v181 = v30;
      do
      {
        v22 -= 32;
        v31 = 0;
        v32 = v29;
        if ( v29 )
        {
          _RDX = &_R11[3 * a7];
          _R12 = -(__int64)a7;
          _R8 = v22 + 4096;
          _R13 = 2LL * a7;
          _RSI = 3LL * a7;
          _R10 = -12LL * a7;
          do
          {
            _RAX = v31 + a7;
            _RDX += 4;
            v31 += 4;
            __asm
            {
              vmovups ymm0, ymmword ptr [r8-800h]
              vmovups ymm4, ymmword ptr [r8]
              vmovups ymm3, ymmword ptr [r8+800h]
              vmovups ymm1, ymmword ptr [r8-1000h]
            }
            _R8 += 0x2000;
            __asm
            {
              vshufps ymm5, ymm1, ymm0, 44h ; 'D'
              vshufps ymm1, ymm1, ymm0, 0EEh
              vshufps ymm2, ymm4, ymm3, 44h ; 'D'
              vshufps ymm0, ymm4, ymm3, 0EEh
              vshufps ymm6, ymm5, ymm2, 88h
              vshufps ymm4, ymm5, ymm2, 0DDh
              vshufps ymm2, ymm1, ymm0, 0DDh
              vextractf128 xmmword ptr [r10+rdx-10h], ymm2, 1
              vshufps ymm3, ymm1, ymm0, 88h
              vextractf128 xmm1, ymm3, 1
              vmovups xmmword ptr [r11+rax*4], xmm1
              vextractf128 xmmword ptr [rdx+r12*4-10h], ymm4, 1
              vextractf128 xmmword ptr [rdx-10h], ymm6, 1
              vmovups xmmword ptr [rdx+rcx*4-10h], xmm2
              vmovups xmmword ptr [rdx+rcx*8-10h], xmm3
              vmovups xmmword ptr [rdx+rsi*4-10h], xmm4
              vmovups xmmword ptr [rdx+r13*8-10h], xmm6
            }
            --v32;
          }
          while ( v32 );
          v27 = v189;
          v30 = v181;
          v29 = a7 >> 2;
        }
        _R11 = (float *)((char *)_R11 + v30);
        v189 = --v27;
      }
      while ( v27 );
      v23 = v179;
      v20 = a7;
      v26 = a8;
      v28 = 8 * a7;
    }
    for ( i = v26 & 7; i; --i )
    {
      v22 -= 4;
      v54 = v20;
      if ( v20 )
      {
        v55 = (int *)v22;
        do
        {
          v56 = *v55;
          v55 += 512;
          *(_DWORD *)_R11++ = v56;
          --v54;
        }
        while ( v54 );
      }
    }
    v57 = a9;
    v58 = a9 >> 3;
    __asm
    {
      vmovaps [rsp+0D8h+var_48], xmm7
      vmovaps [rsp+0D8h+var_58], xmm8
    }
    v190 = a9 >> 3;
    if ( a9 >> 3 )
    {
      v59 = v20 >> 2;
      v60 = 4LL * v28;
      v182 = v60;
      v186 = v20 >> 2;
      do
      {
        __asm
        {
          vmovups ymm6, ymmword ptr [rdi-20h]
          vmovups ymm7, ymmword ptr [rbx]
        }
        _RDI -= 32;
        v22 -= 32;
        v188 = _RDI;
        v63 = v59;
        if ( v59 )
        {
          __asm { vmovdqu ymm8, cs:ymmword_1801446A0 }
          v65 = 0;
          v66 = v23 + 0x2000;
          _RDX = &_R11[3 * a7];
          _R8 = -(__int64)a7;
          v69 = v22 + 4096;
          _R14 = 2LL * a7;
          _R10 = 3LL * a7;
          _R12 = -12LL * a7;
          do
          {
            _RAX = v65 + a7;
            _RDX += 4;
            v65 += 4;
            __asm { vmulps  ymm0, ymm6, ymmword ptr [r13-1000h] }
            v69 += 0x2000;
            v66 += 0x4000;
            __asm
            {
              vpermps ymm5, ymm8, ymm0
              vfmadd231ps ymm5, ymm7, ymmword ptr [rsi-6000h]
              vmulps  ymm0, ymm6, ymmword ptr [r13-2800h]
              vpermps ymm3, ymm8, ymm0
              vfmadd231ps ymm3, ymm7, ymmword ptr [rsi-5000h]
              vmulps  ymm0, ymm6, ymmword ptr [r13-2000h]
              vshufps ymm2, ymm5, ymm3, 44h ; 'D'
              vpermps ymm4, ymm8, ymm0
              vfmadd231ps ymm4, ymm7, ymmword ptr [rsi-4000h]
              vmulps  ymm0, ymm6, ymmword ptr [r13-1800h]
              vshufps ymm3, ymm5, ymm3, 0EEh
              vpermps ymm1, ymm8, ymm0
              vfmadd231ps ymm1, ymm7, ymmword ptr [rsi-3000h]
              vshufps ymm0, ymm4, ymm1, 44h ; 'D'
              vshufps ymm5, ymm2, ymm0, 88h
              vmovups xmmword ptr [rdx+r12-10h], xmm5
              vshufps ymm1, ymm4, ymm1, 0EEh
              vshufps ymm4, ymm2, ymm0, 0DDh
              vmovups xmmword ptr [r11+rax*4], xmm4
              vshufps ymm2, ymm3, ymm1, 88h
              vmovups xmmword ptr [rdx+r8*4-10h], xmm2
              vshufps ymm3, ymm3, ymm1, 0DDh
              vmovups xmmword ptr [rdx-10h], xmm3
              vextractf128 xmmword ptr [rdx+rcx*4-10h], ymm5, 1
              vextractf128 xmmword ptr [rdx+rcx*8-10h], ymm4, 1
              vextractf128 xmmword ptr [rdx+r10*4-10h], ymm2, 1
              vextractf128 xmmword ptr [rdx+r14*8-10h], ymm3, 1
            }
            --v63;
          }
          while ( v63 );
          v23 = v179;
          _RDI = v188;
          v58 = v190;
          v60 = v182;
          v59 = v186;
        }
        v23 += 32;
        _R11 = (float *)((char *)_R11 + v60);
        _RBX += 2;
        v179 = v23;
        v190 = --v58;
      }
      while ( v58 );
      v20 = a7;
      v57 = a9;
    }
    for ( j = v57 & 7; j; --j )
    {
      __asm
      {
        vmovss  xmm1, dword ptr [rdi-4]
        vmovss  xmm2, dword ptr [rbx]
      }
      _RDI -= 4;
      v22 -= 4;
      v96 = v20;
      if ( v20 )
      {
        v97 = v22;
        v98 = v23;
        do
        {
          __asm
          {
            vmulss  xmm0, xmm1, dword ptr [rax]
            vfmadd231ss xmm0, xmm2, dword ptr [rdx]
            vmovss  dword ptr [r11], xmm0
          }
          ++_R11;
          v98 += 4096;
          v97 += 2048;
          --v96;
        }
        while ( v96 );
      }
      v23 += 4;
      _RBX = (_OWORD *)((char *)_RBX + 4);
    }
    v101 = a10;
    result = (unsigned int)(a10 >> 3);
    v191 = result;
    if ( (_DWORD)result )
    {
      __asm { vmovdqu ymm6, cs:ymmword_1801446A0 }
      v103 = v20 >> 2;
      v104 = 4LL * v192;
      v187 = v20 >> 2;
      do
      {
        __asm
        {
          vpermps ymm7, ymm6, ymmword ptr [rdi-20h]
          vmovups ymm8, ymmword ptr [rbx]
        }
        _RDI -= 32;
        v23 -= 32;
        v180 = v23;
        v107 = v103;
        if ( v103 )
        {
          v108 = v23 + 0x2000;
          _RAX = &_R11[2 * a7];
          _RDX = -(__int64)a7;
          v111 = v22 + 4096;
          _R12 = 2LL * a7;
          _RSI = 3LL * a7;
          _R10 = 5LL * a7;
          _R13 = _RDX;
          do
          {
            _RAX += 4;
            v111 += 0x2000;
            __asm { vpermps ymm0, ymm6, ymmword ptr [r8-2000h] }
            v108 += 0x4000;
            __asm
            {
              vmulps  ymm5, ymm0, ymm8
              vfmsub231ps ymm5, ymm7, ymmword ptr [r14-3000h]
              vpermps ymm0, ymm6, ymmword ptr [r8-5000h]
              vmulps  ymm3, ymm0, ymm8
              vfmsub231ps ymm3, ymm7, ymmword ptr [r14-2800h]
              vpermps ymm0, ymm6, ymmword ptr [r8-4000h]
              vshufps ymm2, ymm5, ymm3, 44h ; 'D'
              vmulps  ymm4, ymm0, ymm8
              vfmsub231ps ymm4, ymm7, ymmword ptr [r14-2000h]
              vpermps ymm0, ymm6, ymmword ptr [r8-3000h]
              vshufps ymm3, ymm5, ymm3, 0EEh
              vmulps  ymm1, ymm0, ymm8
              vfmsub231ps ymm1, ymm7, ymmword ptr [r14-1800h]
              vshufps ymm0, ymm4, ymm1, 44h ; 'D'
              vshufps ymm5, ymm2, ymm0, 88h
              vmovups xmmword ptr [rax+r13*8-10h], xmm5
              vshufps ymm1, ymm4, ymm1, 0EEh
              vshufps ymm4, ymm2, ymm0, 0DDh
              vmovups xmmword ptr [rax+rdx*4-10h], xmm4
              vshufps ymm2, ymm3, ymm1, 88h
              vmovups xmmword ptr [rax-10h], xmm2
              vshufps ymm3, ymm3, ymm1, 0DDh
              vmovups xmmword ptr [rax+rcx*4-10h], xmm3
              vextractf128 xmmword ptr [rax+rcx*8-10h], ymm5, 1
              vextractf128 xmmword ptr [rax+rsi*4-10h], ymm4, 1
              vextractf128 xmmword ptr [rax+r12*8-10h], ymm2, 1
              vextractf128 xmmword ptr [rax+r10*4-10h], ymm3, 1
            }
            --v107;
          }
          while ( v107 );
          v23 = v180;
          LODWORD(result) = v191;
          v104 = 4LL * v192;
          v103 = v187;
        }
        _R11 = (float *)((char *)_R11 + v104);
        v22 += 32;
        _RBX += 2;
        result = (unsigned int)(result - 1);
        v191 = result;
      }
      while ( (_DWORD)result );
      v20 = a7;
      v101 = a10;
    }
    v136 = v101 & 7;
    if ( v136 )
    {
      _RDI = _RDI - v23;
      v138 = v22 - (_QWORD)_RBX;
      do
      {
        __asm { vmovss  xmm2, dword ptr [rbx] }
        result = v23;
        v140 = v20;
        v23 -= 4;
        __asm { vmovss  xmm1, dword ptr [rax+rdi-4] }
        if ( v20 )
        {
          result = v23;
          v142 = (char *)_RBX + v138;
          do
          {
            __asm
            {
              vmulss  xmm0, xmm2, dword ptr [rax]
              vfmsub231ss xmm0, xmm1, dword ptr [rdx]
              vmovss  dword ptr [r11], xmm0
            }
            ++_R11;
            v142 += 2048;
            result += 4096;
            --v140;
          }
          while ( v140 );
        }
        _RBX = (_OWORD *)((char *)_RBX + 4);
        --v136;
      }
      while ( v136 );
    }
    v145 = a11 >> 3;
    if ( a11 >> 3 )
    {
      __asm { vmovups ymm8, cs:ymmword_1801446E0 }
      v147 = v20 >> 2;
      result = 32LL * v20;
      do
      {
        v23 -= 32;
        v148 = v147;
        if ( v147 )
        {
          _RAX = &_R11[2 * a7];
          v150 = v23 + 0x2000;
          _R9 = -(__int64)a7;
          _R12 = 3LL * a7;
          _RBX = 2LL * a7;
          _R13 = 5LL * a7;
          _RDI = _R9;
          do
          {
            _RAX += 4;
            __asm
            {
              vmulps  ymm4, ymm8, ymmword ptr [rdx-2000h]
              vmulps  ymm0, ymm8, ymmword ptr [rdx-1000h]
              vmulps  ymm2, ymm8, ymmword ptr [rdx]
              vmulps  ymm1, ymm8, ymmword ptr [rdx+1000h]
            }
            v150 += 0x4000;
            __asm
            {
              vshufps ymm3, ymm4, ymm0, 44h ; 'D'
              vshufps ymm5, ymm4, ymm0, 0EEh
              vshufps ymm0, ymm2, ymm1, 44h ; 'D'
              vshufps ymm7, ymm3, ymm0, 88h
              vshufps ymm6, ymm3, ymm0, 0DDh
              vshufps ymm2, ymm2, ymm1, 0EEh
              vshufps ymm3, ymm5, ymm2, 0DDh
              vextractf128 xmmword ptr [rax+rdi*8-10h], ymm3, 1
              vshufps ymm4, ymm5, ymm2, 88h
              vextractf128 xmmword ptr [rax+r9*4-10h], ymm4, 1
              vextractf128 xmmword ptr [rax-10h], ymm6, 1
              vextractf128 xmmword ptr [rax+rcx*4-10h], ymm7, 1
              vmovups xmmword ptr [rax+rcx*8-10h], xmm3
              vmovups xmmword ptr [rax+r12*4-10h], xmm4
              vmovups xmmword ptr [rax+rbx*8-10h], xmm6
              vmovups xmmword ptr [rax+r13*4-10h], xmm7
            }
            --v148;
          }
          while ( v148 );
          result = 32LL * v20;
          v147 = v20 >> 2;
        }
        _R11 = (float *)((char *)_R11 + result);
        --v145;
      }
      while ( v145 );
    }
    __asm
    {
      vmovaps xmm8, [rsp+0D8h+var_58]
      vmovaps xmm7, [rsp+0D8h+var_48]
      vmovaps xmm6, [rsp+0D8h+var_38]
    }
    v171 = a11 & 7;
    if ( (a11 & 7) != 0 )
    {
      __asm { vmovss  xmm2, dword ptr cs:xmmword_180144610 }
      do
      {
        v23 -= 4;
        v173 = v20;
        if ( v20 )
        {
          result = v23;
          do
          {
            __asm
            {
              vmovss  xmm0, dword ptr [rax]
              vxorps  xmm1, xmm0, xmm2
              vmovss  dword ptr [r11], xmm1
            }
            ++_R11;
            result += 4096;
            --v173;
          }
          while ( v173 );
        }
        --v171;
      }
      while ( v171 );
    }
    __asm { vzeroupper }
  }
  return result;
}