####
#### BMI2 instructions
####


:BZHI Reg32, rm32, vexVVVV_r32 is $(VEX_NDS) & $(VEX_LZ) & $(VEX_PRE_NONE) & $(VEX_0F38) & $(VEX_W0) & vexVVVV_r32; byte=0xf5; Reg32 ... & check_Reg32_dest ... & rm32
{
  indexTmp:1 = vexVVVV_r32:1;

  # saturate index amount to 32; operand size or higher does not clear any bits
  shift:1 = (indexTmp <= 32) * (32 - indexTmp);

  # clear the upper bits
  Reg32 = (rm32 << shift) >> shift;
  build check_Reg32_dest;

  ZF = (Reg32 == 0);
  SF = (Reg32 s< 0);
  CF = indexTmp > 31;
  OF = 0;
  # AF and PF are undefined
}

@ifdef IA64
:BZHI Reg64, rm64, vexVVVV_r64 is $(LONGMODE_ON) & $(VEX_NDS) & $(VEX_LZ) & $(VEX_PRE_NONE) & $(VEX_0F38) & $(VEX_W1) & vexVVVV_r64; byte=0xf5; Reg64 ... & rm64
{
  indexTmp:1 = vexVVVV_r64:1;

  # saturate index amount to 64; operand size or higher does not clear any bits
  shift:1 = (indexTmp <= 64) * (64 - indexTmp);

  # clear the upper bits
  Reg64 = (rm64 << shift) >> shift;

  ZF = (Reg64 == 0);
  SF = (Reg64 s< 0);
  CF = indexTmp > 63;
  OF = 0;
  # AF and PF are undefined
}
@endif


:MULX Reg32, vexVVVV_r32, rm32 is $(VEX_NDD) & $(VEX_LZ) & $(VEX_PRE_F2) & $(VEX_0F38) & $(VEX_W0) & vexVVVV_r32; byte=0xf6; Reg32 ... & check_Reg32_dest ... &  check_vexVVVV_r32_dest ... & rm32
{
  temp:8 = zext(EDX) * zext(rm32);

  vexVVVV_r32 = temp:4;
  build check_vexVVVV_r32_dest;
  Reg32 = temp(4);
  build check_Reg32_dest;
}

@ifdef IA64
:MULX Reg64, vexVVVV_r64, rm64 is $(LONGMODE_ON) & $(VEX_NDD) & $(VEX_LZ) & $(VEX_PRE_F2) & $(VEX_0F38) & $(VEX_W1) & vexVVVV_r64; byte=0xf6; Reg64 ... & rm64
{
  temp:16 = zext(RDX) * zext(rm64);

  vexVVVV_r64 = temp:8;
  Reg64 = temp(8);
}
@endif


:PDEP Reg32, vexVVVV_r32, rm32 is $(VEX_NDS) & $(VEX_LZ) & $(VEX_PRE_F2) & $(VEX_0F38) & $(VEX_W0) & vexVVVV_r32; byte=0xf5; Reg32 ... & check_Reg32_dest ... & rm32
{
  sourceTmp:4 = vexVVVV_r32;

  indexTmp:4 = 1;
  resultTmp:4 = 0;

 <loop>
  maskBit:4 = rm32 & indexTmp;

  if (maskBit == 0) goto <nextMaskBit>;
  resultTmp = resultTmp | (maskBit * (sourceTmp & 1));
  sourceTmp = sourceTmp >> 1;

 <nextMaskBit>
  indexTmp = indexTmp << 1;
  if (indexTmp != 0) goto <loop>;

  Reg32 = resultTmp;
  build check_Reg32_dest;
}

@ifdef IA64
:PDEP Reg64, vexVVVV_r64, rm64 is $(LONGMODE_ON) & $(VEX_NDS) & $(VEX_LZ) & $(VEX_PRE_F2) & $(VEX_0F38) & $(VEX_W1) & vexVVVV_r64; byte=0xf5; Reg64 ... & rm64
{
  sourceTmp:8 = vexVVVV_r64;

  indexTmp:8 = 1;
  resultTmp:8 = 0;

 <loop>
  maskBit:8 = rm64 & indexTmp;

  if (maskBit == 0) goto <nextMaskBit>;
  resultTmp = resultTmp | (maskBit * (sourceTmp & 1));
  sourceTmp = sourceTmp >> 1;

 <nextMaskBit>
  indexTmp = indexTmp << 1;
  if (indexTmp != 0) goto <loop>;

  Reg64 = resultTmp;
}
@endif


:PEXT Reg32, vexVVVV_r32, rm32 is $(VEX_NDS) & $(VEX_LZ) & $(VEX_PRE_F3) & $(VEX_0F38) & $(VEX_W0) & vexVVVV_r32; byte=0xf5; Reg32 ... & check_Reg32_dest ... & rm32
{
  indexTmp:4 = 0x80000000;
  resultTmp:4 = 0;

 <loop>
  maskBit:4 = rm32 & indexTmp;

  if (maskBit == 0) goto <nextMaskBit>;
  resultTmp = (resultTmp << 1) | zext((maskBit & vexVVVV_r32) != 0);

 <nextMaskBit>
  indexTmp = indexTmp >> 1;
  if (indexTmp != 0) goto <loop>;

  build check_Reg32_dest;
  Reg32 = resultTmp;
}

@ifdef IA64
:PEXT Reg64, vexVVVV_r64, rm64 is $(LONGMODE_ON) & $(VEX_NDS) & $(VEX_LZ) & $(VEX_PRE_F3) & $(VEX_0F38) & $(VEX_W1) & vexVVVV_r64; byte=0xf5; Reg64 ... & rm64
{
  indexTmp:8 = 0x8000000000000000;
  resultTmp:8 = 0;

 <loop>
  maskBit:8 = rm64 & indexTmp;

  if (maskBit == 0) goto <nextMaskBit>;
  resultTmp = (resultTmp << 1) | zext((maskBit & vexVVVV_r64) != 0);

 <nextMaskBit>
  indexTmp = indexTmp >> 1;
  if (indexTmp != 0) goto <loop>;

  Reg64 = resultTmp;
}
@endif


:RORX Reg32, rm32, imm8 is $(VEX_NONE) & $(VEX_LZ) & $(VEX_PRE_F2) & $(VEX_0F3A) & $(VEX_W0); byte=0xf0; Reg32 ... & check_Reg32_dest ... & rm32; imm8
{
  shiftTmp:1 = (imm8:1 & 0x1F);

  Reg32 = (rm32 >> shiftTmp) | ( rm32 << (32 - shiftTmp));
  build check_Reg32_dest;
}

@ifdef IA64
:RORX Reg64, rm64, imm8 is $(LONGMODE_ON) & $(VEX_NONE) & $(VEX_LZ) & $(VEX_PRE_F2) & $(VEX_0F3A) & $(VEX_W1); byte=0xf0; Reg64 ... & rm64; imm8
{
  shiftTmp:1 = (imm8:1 & 0x3F);

  Reg64 = (rm64 >> shiftTmp) | ( rm64 << (64 - shiftTmp));
}
@endif


:SARX Reg32, rm32, vexVVVV_r32 is $(VEX_NDS) & $(VEX_LZ) & $(VEX_PRE_F3) & $(VEX_0F38) & $(VEX_W0) & vexVVVV_r32; byte=0xf7; Reg32 ... & check_Reg32_dest ... & rm32
{
  Reg32 = rm32 s>> (vexVVVV_r32 & 0x0000001F);
  build check_Reg32_dest;
}

@ifdef IA64
:SARX Reg64, rm64, vexVVVV_r64 is $(LONGMODE_ON) & $(VEX_NDS) & $(VEX_LZ) & $(VEX_PRE_F3) & $(VEX_0F38) & $(VEX_W1) & vexVVVV_r64; byte=0xf7; Reg64 ... & rm64
{
  Reg64 = rm64 s>> (vexVVVV_r64 & 0x000000000000003F);
}
@endif


:SHLX Reg32, rm32, vexVVVV_r32 is $(VEX_NDS) & $(VEX_LZ) & $(VEX_PRE_66) & $(VEX_0F38) & $(VEX_W0) & vexVVVV_r32; byte=0xf7; Reg32 ... & check_Reg32_dest ... & rm32
{
  Reg32 = rm32 << (vexVVVV_r32 & 0x0000001F);
  build check_Reg32_dest;
}

@ifdef IA64
:SHLX Reg64, rm64, vexVVVV_r64 is $(LONGMODE_ON) & $(VEX_NDS) & $(VEX_LZ) & $(VEX_PRE_66) & $(VEX_0F38) & $(VEX_W1) & vexVVVV_r64; byte=0xf7; Reg64 ... & rm64
{
  Reg64 = rm64 << (vexVVVV_r64 & 0x000000000000003F);
}
@endif


:SHRX Reg32, rm32, vexVVVV_r32 is $(VEX_NDS) & $(VEX_LZ) & $(VEX_PRE_F2) & $(VEX_0F38) & $(VEX_W0) & vexVVVV_r32; byte=0xf7; Reg32 ... & check_Reg32_dest ... & rm32
{
  Reg32 = rm32 >> (vexVVVV_r32 & 0x0000001F);
  build check_Reg32_dest;
}

@ifdef IA64
:SHRX Reg64, rm64, vexVVVV_r64 is $(LONGMODE_ON) & $(VEX_NDS) & $(VEX_LZ) & $(VEX_PRE_F2) & $(VEX_0F38) & $(VEX_W1) & vexVVVV_r64; byte=0xf7; Reg64 ... & rm64
{
  Reg64 = rm64 >> (vexVVVV_r64 & 0x000000000000003F);
}
@endif