[Power9] Implement new vsx instructions: load, store instructions for vector and scalar

[cycheng]

Summary

We follow the comments mentioned in http://reviews.llvm.org/D16842#344378 to implement this new patch.

This patch implements the following vsx instructions:

• Vector load/store:
  1. lxv lxvx lxvb16x lxvl lxvll lxvh8x lxvwsx
  2. stxv stxvb16x stxvh8x stxvl stxvll stxvx
• Scalar load/store:
  1. lxsd lxssp lxsibzx lxsihzx
  2. stxsd stxssp stxsibx stxsihx

21 instructions

[cycheng]

Fix issues mentioned in:
http://reviews.llvm.org/D16842#344765
http://reviews.llvm.org/D16842#344908

[kbarton]

LGTM.
Needs to be rebased to current trunk. Once that is done I can commit it.

[cycheng]

Rebase to r262428 (Mar 2 2016) with tiny changes

[kbarton]

Committed r262906

lib/Target/PowerPC/AsmParser/PPCAsmParser.cpp

switch (Kind) {
         return isInt<16>(getImmS16Context());
       default:
         return false;
     }
   }
   bool isS16ImmX4() const { return Kind == Expression ||
                                    (Kind == Immediate && isInt<16>(getImm()) &&
                                     (getImm() & 3) == 0); }
+  bool isS16ImmX16() const { return Kind == Expression ||
+                                    (Kind == Immediate && isInt<16>(getImm()) &&
+                                     (getImm() & 15) == 0); }
   bool isS17Imm() const {
     switch (Kind) {
       case Expression:
         return true;
       case Immediate:
       case ContextImmediate:
         return isInt<17>(getImmS16Context());
       default:

lib/Target/PowerPC/Disassembler/PPCDisassembler.cpp

static DecodeStatus decodeMemRIXOperands(MCInst &Inst, uint64_t Imm,
   else if (Inst.getOpcode() == PPC::STDU)
     Inst.insert(Inst.begin(), MCOperand::createReg(GP0Regs[Base]));
 
   Inst.addOperand(MCOperand::createImm(SignExtend64<16>(Disp << 2)));
   Inst.addOperand(MCOperand::createReg(GP0Regs[Base]));
   return MCDisassembler::Success;
 }
 
+static DecodeStatus decodeMemRIX16Operands(MCInst &Inst, uint64_t Imm,
+                                         int64_t Address, const void *Decoder) {
+  // Decode the memrix16 field (imm, reg), which has the low 12-bits as the
+  // displacement with 16-byte aligned, and the next 5 bits as the register #.
+
+  uint64_t Base = Imm >> 12;
+  uint64_t Disp = Imm & 0xFFF;
+
+  assert(Base < 32 && "Invalid base register");
+
+  Inst.addOperand(MCOperand::createImm(SignExtend64<16>(Disp << 4)));
+  Inst.addOperand(MCOperand::createReg(GP0Regs[Base]));
+  return MCDisassembler::Success;
+}
+
 static DecodeStatus decodeCRBitMOperand(MCInst &Inst, uint64_t Imm,
                                         int64_t Address, const void *Decoder) {
   // The cr bit encoding is 0x80 >> cr_reg_num.
 
   unsigned Zeros = countTrailingZeros(Imm);
   assert(Zeros < 8 && "Invalid CR bit value");
 
   Inst.addOperand(MCOperand::createReg(CRRegs[7 - Zeros]));

lib/Target/PowerPC/MCTargetDesc/PPCMCCodeEmitter.cpp

unsigned getImm16Encoding(const MCInst &MI, unsigned OpNo,
                              SmallVectorImpl<MCFixup> &Fixups,
                              const MCSubtargetInfo &STI) const;
   unsigned getMemRIEncoding(const MCInst &MI, unsigned OpNo,
                             SmallVectorImpl<MCFixup> &Fixups,
                             const MCSubtargetInfo &STI) const;
   unsigned getMemRIXEncoding(const MCInst &MI, unsigned OpNo,
                              SmallVectorImpl<MCFixup> &Fixups,
                              const MCSubtargetInfo &STI) const;
+  unsigned getMemRIX16Encoding(const MCInst &MI, unsigned OpNo,
+                               SmallVectorImpl<MCFixup> &Fixups,
+                               const MCSubtargetInfo &STI) const;
   unsigned getSPE8DisEncoding(const MCInst &MI, unsigned OpNo,
                               SmallVectorImpl<MCFixup> &Fixups,
                               const MCSubtargetInfo &STI) const;
   unsigned getSPE4DisEncoding(const MCInst &MI, unsigned OpNo,
                               SmallVectorImpl<MCFixup> &Fixups,
                               const MCSubtargetInfo &STI) const;
   unsigned getSPE2DisEncoding(const MCInst &MI, unsigned OpNo,
                               SmallVectorImpl<MCFixup> &Fixups,
if (MO.isImm())
     return ((getMachineOpValue(MI, MO, Fixups, STI) >> 2) & 0x3FFF) | RegBits;
   
   // Add a fixup for the displacement field.
   Fixups.push_back(MCFixup::create(IsLittleEndian? 0 : 2, MO.getExpr(),
                                    (MCFixupKind)PPC::fixup_ppc_half16ds));
   return RegBits;
 }
 
+unsigned PPCMCCodeEmitter::getMemRIX16Encoding(const MCInst &MI, unsigned OpNo,
+                                       SmallVectorImpl<MCFixup> &Fixups,
+                                       const MCSubtargetInfo &STI) const {
+  // Encode (imm, reg) as a memrix16, which has the low 12-bits as the
+  // displacement and the next 5 bits as the register #.
+  assert(MI.getOperand(OpNo+1).isReg());
+  unsigned RegBits = getMachineOpValue(MI, MI.getOperand(OpNo+1), Fixups, STI) << 12;
+
+  const MCOperand &MO = MI.getOperand(OpNo);
+  assert(MO.isImm());
+
+  return ((getMachineOpValue(MI, MO, Fixups, STI) >> 4) & 0xFFF) | RegBits;
+}
 
 unsigned PPCMCCodeEmitter::getSPE8DisEncoding(const MCInst &MI, unsigned OpNo,
                                               SmallVectorImpl<MCFixup> &Fixups,
                                               const MCSubtargetInfo &STI)
                                               const {
   // Encode (imm, reg) as a spe8dis, which has the low 5-bits of (imm / 8)
   // as the displacement and the next 5 bits as the register #.
   assert(MI.getOperand(OpNo+1).isReg());

lib/Target/PowerPC/PPCInstrFormats.td

class DSForm_1<bits<6> opcode, bits<2> xo, dag OOL, dag IOL, string asmstr,
   let Pattern = pattern;
   
   let Inst{6-10}  = RST;
   let Inst{11-15} = DS_RA{18-14};  // Register #
   let Inst{16-29} = DS_RA{13-0};   // Displacement.
   let Inst{30-31} = xo;
 }
 
+// DQ-Form: [PO T RA DQ TX XO] or [PO S RA DQ SX XO]
+class DQ_RD6_RS5_DQ12<bits<6> opcode, bits<3> xo, dag OOL, dag IOL,
+                      string asmstr, InstrItinClass itin, list<dag> pattern>
+  : I<opcode, OOL, IOL, asmstr, itin> {
+  bits<6>  XT;
+  bits<17> DS_RA;
+
+  let Pattern = pattern;
+
+  let Inst{6-10}  = XT{4-0};
+  let Inst{11-15} = DS_RA{16-12};  // Register #
+  let Inst{16-27} = DS_RA{11-0};   // Displacement.
+  let Inst{28}    = XT{5};
+  let Inst{29-31} = xo;
+}
 
 // 1.7.6 X-Form
 class XForm_base_r3xo<bits<6> opcode, bits<10> xo, dag OOL, dag IOL, string asmstr, 
                       InstrItinClass itin, list<dag> pattern>
   : I<opcode, OOL, IOL, asmstr, itin> {
   bits<5> RST;
   bits<5> A;
   bits<5> B;

lib/Target/PowerPC/PPCInstrInfo.td

 }
 def PPCDispRIXOperand : AsmOperandClass {
  let Name = "DispRIX"; let PredicateMethod = "isS16ImmX4";
  let RenderMethod = "addImmOperands";
 }
 def dispRIX : Operand<iPTR> {
   let ParserMatchClass = PPCDispRIXOperand;
 }
+def PPCDispRIX16Operand : AsmOperandClass {
+ let Name = "DispRIX16"; let PredicateMethod = "isS16ImmX16";
+ let RenderMethod = "addImmOperands";
+}
+def dispRIX16 : Operand<iPTR> {
+  let ParserMatchClass = PPCDispRIX16Operand;
+}
 def PPCDispSPE8Operand : AsmOperandClass {
  let Name = "DispSPE8"; let PredicateMethod = "isU8ImmX8";
  let RenderMethod = "addImmOperands";
 }
 def dispSPE8 : Operand<iPTR> {
   let ParserMatchClass = PPCDispSPE8Operand;
 }
 def PPCDispSPE4Operand : AsmOperandClass {
def memrr : Operand<iPTR> {
   let MIOperandInfo = (ops ptr_rc_nor0:$ptrreg, ptr_rc_idx:$offreg);
 }
 def memrix : Operand<iPTR> {   // memri where the imm is 4-aligned.
   let PrintMethod = "printMemRegImm";
   let MIOperandInfo = (ops dispRIX:$imm, ptr_rc_nor0:$reg);
   let EncoderMethod = "getMemRIXEncoding";
   let DecoderMethod = "decodeMemRIXOperands";
 }
+def memrix16 : Operand<iPTR> { // memri, imm is 16-aligned, 12-bit, Inst{16:27}
+  let PrintMethod = "printMemRegImm";
+  let MIOperandInfo = (ops dispRIX16:$imm, ptr_rc_nor0:$reg);
+  let EncoderMethod = "getMemRIX16Encoding";
+  let DecoderMethod = "decodeMemRIX16Operands";
+}
 def spe8dis : Operand<iPTR> {   // SPE displacement where the imm is 8-aligned.
   let PrintMethod = "printMemRegImm";
   let MIOperandInfo = (ops dispSPE8:$imm, ptr_rc_nor0:$reg);
   let EncoderMethod = "getSPE8DisEncoding";
 }
 def spe4dis : Operand<iPTR> {   // SPE displacement where the imm is 4-aligned.
   let PrintMethod = "printMemRegImm";
   let MIOperandInfo = (ops dispSPE4:$imm, ptr_rc_nor0:$reg);

lib/Target/PowerPC/PPCInstrVSX.td

let Predicates = [HasP9Vector] in {
   }
 
   // Round to Quad-Precision Integer [with Inexact]
   def XSRQPI   : Z23_VT5_R1_VB5_RMC2_EX1<63,  5, 0, "xsrqpi" , []>;
   def XSRQPIX  : Z23_VT5_R1_VB5_RMC2_EX1<63,  5, 1, "xsrqpix", []>;
 
   // Round Quad-Precision to Double-Extended Precision (fp80)
   def XSRQPXP  : Z23_VT5_R1_VB5_RMC2_EX1<63, 37, 0, "xsrqpxp", []>;
+
+  //===--------------------------------------------------------------------===//
+  // Vector/Scalar Load/Store Instructions
+
+  let mayLoad = 1 in {
+  // Load Vector
+  def LXV : DQ_RD6_RS5_DQ12<61, 1, (outs vsrc:$XT), (ins memrix16:$src),
+                            "lxv $XT, $src", IIC_LdStLFD, []>;
+  // Load DWord
+  def LXSD  : DSForm_1<57, 2, (outs vrrc:$vD), (ins memrix:$src),
+                       "lxsd $vD, $src", IIC_LdStLFD, []>;
+  // Load SP from src, convert it to DP, and place in dword[0]
+  def LXSSP : DSForm_1<57, 3, (outs vrrc:$vD), (ins memrix:$src),
+                       "lxssp $vD, $src", IIC_LdStLFD, []>;
+
+  // [PO T RA RB XO TX] almost equal to [PO S RA RB XO SX], but has different
+  // "out" and "in" dag
+  class X_XT6_RA5_RB5<bits<6> opcode, bits<10> xo, string opc,
+                      RegisterOperand vtype, list<dag> pattern>
+    : XX1Form<opcode, xo, (outs vtype:$XT), (ins memrr:$src),
+              !strconcat(opc, " $XT, $src"), IIC_LdStLFD, pattern>;
+
+  // Load as Integer Byte/Halfword & Zero Indexed
+  def LXSIBZX : X_XT6_RA5_RB5<31, 781, "lxsibzx", vsfrc, []>;
+  def LXSIHZX : X_XT6_RA5_RB5<31, 813, "lxsihzx", vsfrc, []>;
+
+  // Load Vector Halfword*8/Byte*16 Indexed
+  def LXVH8X  : X_XT6_RA5_RB5<31, 812, "lxvh8x" , vsrc, []>;
+  def LXVB16X : X_XT6_RA5_RB5<31, 876, "lxvb16x", vsrc, []>;
+
+  // Load Vector Indexed
+  def LXVX    : X_XT6_RA5_RB5<31, 268, "lxvx"   , vsrc, []>;
+
+  // Load Vector (Left-justified) with Length
+  def LXVL    : X_XT6_RA5_RB5<31, 269, "lxvl"   , vsrc, []>;
+  def LXVLL   : X_XT6_RA5_RB5<31, 301, "lxvll"  , vsrc, []>;
+
+  // Load Vector Word & Splat Indexed
+  def LXVWSX  : X_XT6_RA5_RB5<31, 364, "lxvwsx" , vsrc, []>;
+  } // end mayLoad
+
+  let mayStore = 1 in {
+  // Store Vector
+  def STXV : DQ_RD6_RS5_DQ12<61, 5, (outs), (ins vsrc:$XT, memrix16:$dst),
+                             "stxv $XT, $dst", IIC_LdStSTFD, []>;
+  // Store DWord
+  def STXSD  : DSForm_1<61, 2, (outs), (ins vrrc:$vS, memrix:$dst),
+                        "stxsd $vS, $dst", IIC_LdStSTFD, []>;
+  // Convert DP of dword[0] to SP, and Store to dst
+  def STXSSP : DSForm_1<61, 3, (outs), (ins vrrc:$vS, memrix:$dst),
+                        "stxssp $vS, $dst", IIC_LdStSTFD, []>;
+
+  // [PO S RA RB XO SX]
+  class X_XS6_RA5_RB5<bits<6> opcode, bits<10> xo, string opc,
+                      RegisterOperand vtype, list<dag> pattern>
+    : XX1Form<opcode, xo, (outs), (ins vtype:$XT, memrr:$dst),
+              !strconcat(opc, " $XT, $dst"), IIC_LdStSTFD, pattern>;
+
+  // Store as Integer Byte/Halfword Indexed
+  def STXSIBX  : X_XS6_RA5_RB5<31,  909, "stxsibx" , vsfrc, []>;
+  def STXSIHX  : X_XS6_RA5_RB5<31,  941, "stxsihx" , vsfrc, []>;
+
+  // Store Vector Halfword*8/Byte*16 Indexed
+  def STXVH8X  : X_XS6_RA5_RB5<31,  940, "stxvh8x" , vsrc, []>;
+  def STXVB16X : X_XS6_RA5_RB5<31, 1004, "stxvb16x", vsrc, []>;
+
+  // Store Vector Indexed
+  def STXVX    : X_XS6_RA5_RB5<31,  396, "stxvx"   , vsrc, []>;
+
+  // Store Vector (Left-justified) with Length
+  def STXVL    : X_XS6_RA5_RB5<31,  397, "stxvl"   , vsrc, []>;
+  def STXVLL   : X_XS6_RA5_RB5<31,  429, "stxvll"  , vsrc, []>;
+  } // end mayStore
 } // end HasP9Vector

lib/Target/PowerPC/README_P9.txt

- Round to Quad-Precision Integer: xsrqpi xsrqpix
   . Provide builtin?
     (set f128:$vT, (int_ppc_vsx_xsrqpi f128:$vB))
     (set f128:$vT, (int_ppc_vsx_xsrqpix f128:$vB))
 
 - Round Quad-Precision to Double-Extended Precision (fp80): xsrqpxp
   . Provide builtin?
     (set f128:$vT, (int_ppc_vsx_xsrqpxp f128:$vB))
 
+- Load/Store Vector: lxv stxv
+  . Has likely SDAG match:
+    (set v?:$XT, (load ix16addr:$src))
+    (set v?:$XT, (store ix16addr:$dst))
+
+  . Need define ix16addr in PPCInstrInfo.td
+    ix16addr: 16-byte aligned, see "def memrix16" in PPCInstrInfo.td
+
+- Load/Store Vector Indexed: lxvx stxvx
+  . Has likely SDAG match:
+    (set v?:$XT, (load xoaddr:$src))
+    (set v?:$XT, (store xoaddr:$dst))
+
+- Load/Store DWord: lxsd stxsd
+  . Similar to lxsdx/stxsdx:
+    def LXSDX : XX1Form<31, 588,
+                        (outs vsfrc:$XT), (ins memrr:$src),
+                        "lxsdx $XT, $src", IIC_LdStLFD,
+                        [(set f64:$XT, (load xoaddr:$src))]>;
+
+  . (set f64:$XT, (load ixaddr:$src))
+    (set f64:$XT, (store ixaddr:$dst))
+
+- Load/Store SP, with conversion from/to DP: lxssp stxssp
+  . Similar to lxsspx/stxsspx:
+    def LXSSPX : XX1Form<31, 524, (outs vssrc:$XT), (ins memrr:$src),
+                         "lxsspx $XT, $src", IIC_LdStLFD,
+                         [(set f32:$XT, (load xoaddr:$src))]>;
+
+  . (set f32:$XT, (load ixaddr:$src))
+    (set f32:$XT, (store ixaddr:$dst))
+
+- Load as Integer Byte/Halfword & Zero Indexed: lxsibzx lxsihzx
+  . Similar to lxsiwzx:
+    def LXSIWZX : XX1Form<31, 12, (outs vsfrc:$XT), (ins memrr:$src),
+                          "lxsiwzx $XT, $src", IIC_LdStLFD,
+                          [(set f64:$XT, (PPClfiwzx xoaddr:$src))]>;
+
+  . (set f64:$XT, (PPClfiwzx xoaddr:$src))
+
+- Store as Integer Byte/Halfword Indexed: stxsibx stxsihx
+  . Similar to stxsiwx:
+    def STXSIWX : XX1Form<31, 140, (outs), (ins vsfrc:$XT, memrr:$dst),
+                          "stxsiwx $XT, $dst", IIC_LdStSTFD,
+                          [(PPCstfiwx f64:$XT, xoaddr:$dst)]>;
+
+  . (PPCstfiwx f64:$XT, xoaddr:$dst)
+
+- Load Vector Halfword*8/Byte*16 Indexed: lxvh8x lxvb16x
+  . Similar to lxvd2x/lxvw4x:
+    def LXVD2X : XX1Form<31, 844,
+                         (outs vsrc:$XT), (ins memrr:$src),
+                         "lxvd2x $XT, $src", IIC_LdStLFD,
+                         [(set v2f64:$XT, (int_ppc_vsx_lxvd2x xoaddr:$src))]>;
+
+  . (set v8i16:$XT, (int_ppc_vsx_lxvh8x xoaddr:$src))
+    (set v16i8:$XT, (int_ppc_vsx_lxvb16x xoaddr:$src))
+
+- Store Vector Halfword*8/Byte*16 Indexed: stxvh8x stxvb16x
+  . Similar to stxvd2x/stxvw4x:
+    def STXVD2X : XX1Form<31, 972,
+                         (outs), (ins vsrc:$XT, memrr:$dst),
+                         "stxvd2x $XT, $dst", IIC_LdStSTFD,
+                         [(store v2f64:$XT, xoaddr:$dst)]>;
+
+  . (store v8i16:$XT, xoaddr:$dst)
+    (store v16i8:$XT, xoaddr:$dst)
+
+- Load/Store Vector (Left-justified) with Length: lxvl lxvll stxvl stxvll
+  . Likely needs an intrinsic
+  . (set v?:$XT, (int_ppc_vsx_lxvl xoaddr:$src))
+    (set v?:$XT, (int_ppc_vsx_lxvll xoaddr:$src))
+
+  . (int_ppc_vsx_stxvl xoaddr:$dst))
+    (int_ppc_vsx_stxvll xoaddr:$dst))
+
+- Load Vector Word & Splat Indexed: lxvwsx
+  . Likely needs an intrinsic
+  . (set v?:$XT, (int_ppc_vsx_lxvwsx xoaddr:$src))

test/MC/Disassembler/PowerPC/vsx.txt

 # CHECK: xsrqpi 1, 7, 27, 2
 0xfc 0xe1 0xdc 0x0a
 
 # CHECK: xsrqpix 1, 7, 27, 2
 0xfc 0xe1 0xdc 0x0b
 
 # CHECK: xsrqpxp 1, 7, 27, 2
 0xfc 0xe1 0xdc 0x4a
+
+# CHECK: lxv 61, 32752(31)
+0xf7 0xbf 0x7f 0xf9
+
+# CHECK: lxv 61, -32768(0)
+0xf7 0xa0 0x80 0x09
+
+# CHECK: stxv 61, 32752(31)
+0xf7 0xbf 0x7f 0xfd
+
+# CHECK: stxv 61, -32768(0)
+0xf7 0xa0 0x80 0x0d
+
+# CHECK: lxsd 31, -32768(0)
+0xe7 0xe0 0x80 0x02
+
+# CHECK: lxsd 31, 32764(12)
+0xe7 0xec 0x7f 0xfe
+
+# CHECK: lxssp 31, -32768(0)
+0xe7 0xe0 0x80 0x03
+
+# CHECK: lxssp 31, 32764(12)
+0xe7 0xec 0x7f 0xff
+
+# CHECK: stxsd 31, 32764(12)
+0xf7 0xec 0x7f 0xfe
+
+# CHECK: stxssp 31, -32768(0)
+0xf7 0xe0 0x80 0x03
+
+# CHECK: lxvx 57, 12, 27
+0x7f 0x2c 0xda 0x19
+
+# CHECK: lxsibzx 57, 12, 27
+0x7f 0x2c 0xde 0x1b
+
+# CHECK: lxsihzx 57, 12, 27
+0x7f 0x2c 0xde 0x5b
+
+# CHECK: lxvb16x 57, 12, 27
+0x7f 0x2c 0xde 0xd9
+
+# CHECK: lxvh8x 57, 12, 27
+0x7f 0x2c 0xde 0x59
+
+# CHECK: lxvl 57, 12, 27
+0x7f 0x2c 0xda 0x1b
+
+# CHECK: lxvll 57, 12, 27
+0x7f 0x2c 0xda 0x5b
+
+# CHECK: lxvwsx 57, 12, 27
+0x7f 0x2c 0xda 0xd9
+
+# CHECK: stxsibx 57, 12, 27
+0x7f 0x2c 0xdf 0x1b
+
+# CHECK: stxsihx 57, 12, 27
+0x7f 0x2c 0xdf 0x5b
+
+# CHECK: stxvh8x 57, 12, 27
+0x7f 0x2c 0xdf 0x59
+
+# CHECK: stxvb16x 57, 12, 27
+0x7f 0x2c 0xdf 0xd9
+
+# CHECK: stxvx 57, 12, 27
+0x7f 0x2c 0xdb 0x19
+
+# CHECK: stxvl 57, 12, 27
+0x7f 0x2c 0xdb 0x1b
+
+# CHECK: stxvll 57, 12, 27
+0x7f 0x2c 0xdb 0x5b

test/MC/PowerPC/vsx.s

 # CHECK-BE: xsrqpix 1, 7, 27, 2                # encoding: [0xfc,0xe1,0xdc,0x0b]
 # CHECK-LE: xsrqpix 1, 7, 27, 2                # encoding: [0x0b,0xdc,0xe1,0xfc]
             xsrqpix 1, 7, 27, 2
 
 # Round Quad-Precision to Double-Extended Precision
 # CHECK-BE: xsrqpxp 1, 7, 27, 2                # encoding: [0xfc,0xe1,0xdc,0x4a]
 # CHECK-LE: xsrqpxp 1, 7, 27, 2                # encoding: [0x4a,0xdc,0xe1,0xfc]
             xsrqpxp 1, 7, 27, 2
+
+# Load/Store Vector, test maximum and minimum displacement value
+# CHECK-BE: lxv 61, 32752(31)                  # encoding: [0xf7,0xbf,0x7f,0xf9]
+# CHECK-LE: lxv 61, 32752(31)                  # encoding: [0xf9,0x7f,0xbf,0xf7]
+            lxv 61, 32752(31)
+# CHECK-BE: lxv 61, -32768(0)                  # encoding: [0xf7,0xa0,0x80,0x09]
+# CHECK-LE: lxv 61, -32768(0)                  # encoding: [0x09,0x80,0xa0,0xf7]
+            lxv 61, -32768(0)
+# CHECK-BE: stxv 61, 32752(31)                 # encoding: [0xf7,0xbf,0x7f,0xfd]
+# CHECK-LE: stxv 61, 32752(31)                 # encoding: [0xfd,0x7f,0xbf,0xf7]
+            stxv 61, 32752(31)
+# CHECK-BE: stxv 61, -32768(0)                 # encoding: [0xf7,0xa0,0x80,0x0d]
+# CHECK-LE: stxv 61, -32768(0)                 # encoding: [0x0d,0x80,0xa0,0xf7]
+            stxv 61, -32768(0)
+
+# Load/Store DWord
+# CHECK-BE: lxsd 31, -32768(0)                 # encoding: [0xe7,0xe0,0x80,0x02]
+# CHECK-LE: lxsd 31, -32768(0)                 # encoding: [0x02,0x80,0xe0,0xe7]
+            lxsd 31, -32768(0)
+# CHECK-BE: lxsd 31, 32764(12)                 # encoding: [0xe7,0xec,0x7f,0xfe]
+# CHECK-LE: lxsd 31, 32764(12)                 # encoding: [0xfe,0x7f,0xec,0xe7]
+            lxsd 31, 32764(12)
+# CHECK-BE: stxsd 31, 32764(12)                # encoding: [0xf7,0xec,0x7f,0xfe]
+# CHECK-LE: stxsd 31, 32764(12)                # encoding: [0xfe,0x7f,0xec,0xf7]
+            stxsd 31, 32764(12)
+
+# Load SP from src, convert it to DP, and place in dword[0]
+# CHECK-BE: lxssp 31, -32768(0)                # encoding: [0xe7,0xe0,0x80,0x03]
+# CHECK-LE: lxssp 31, -32768(0)                # encoding: [0x03,0x80,0xe0,0xe7]
+            lxssp 31, -32768(0)
+# CHECK-BE: lxssp 31, 32764(12)                # encoding: [0xe7,0xec,0x7f,0xff]
+# CHECK-LE: lxssp 31, 32764(12)                # encoding: [0xff,0x7f,0xec,0xe7]
+            lxssp 31, 32764(12)
+
+# Convert DP of dword[0] to SP, and Store to dst
+# CHECK-BE: stxssp 31, -32768(0)               # encoding: [0xf7,0xe0,0x80,0x03]
+# CHECK-LE: stxssp 31, -32768(0)               # encoding: [0x03,0x80,0xe0,0xf7]
+            stxssp 31, -32768(0)
+
+# Load as Integer Byte/Halfword & Zero Indexed
+# CHECK-BE: lxsibzx 57, 12, 27                 # encoding: [0x7f,0x2c,0xde,0x1b]
+# CHECK-LE: lxsibzx 57, 12, 27                 # encoding: [0x1b,0xde,0x2c,0x7f]
+            lxsibzx 57, 12, 27
+# CHECK-BE: lxsihzx 57, 12, 27                 # encoding: [0x7f,0x2c,0xde,0x5b]
+# CHECK-LE: lxsihzx 57, 12, 27                 # encoding: [0x5b,0xde,0x2c,0x7f]
+            lxsihzx 57, 12, 27
+
+# Load Vector Halfword*8/Byte*16 Indexed
+# CHECK-BE: lxvh8x 57, 12, 27                  # encoding: [0x7f,0x2c,0xde,0x59]
+# CHECK-LE: lxvh8x 57, 12, 27                  # encoding: [0x59,0xde,0x2c,0x7f]
+            lxvh8x 57, 12, 27
+# CHECK-BE: lxvb16x 57, 12, 27                 # encoding: [0x7f,0x2c,0xde,0xd9]
+# CHECK-LE: lxvb16x 57, 12, 27                 # encoding: [0xd9,0xde,0x2c,0x7f]
+            lxvb16x 57, 12, 27
+
+# Load Vector Indexed
+# CHECK-BE: lxvx 57, 12, 27                    # encoding: [0x7f,0x2c,0xda,0x19]
+# CHECK-LE: lxvx 57, 12, 27                    # encoding: [0x19,0xda,0x2c,0x7f]
+            lxvx 57, 12, 27
+
+# Load Vector (Left-justified) with Length
+# CHECK-BE: lxvl 57, 12, 27                    # encoding: [0x7f,0x2c,0xda,0x1b]
+# CHECK-LE: lxvl 57, 12, 27                    # encoding: [0x1b,0xda,0x2c,0x7f]
+            lxvl 57, 12, 27
+# CHECK-BE: lxvll 57, 12, 27                   # encoding: [0x7f,0x2c,0xda,0x5b]
+# CHECK-LE: lxvll 57, 12, 27                   # encoding: [0x5b,0xda,0x2c,0x7f]
+            lxvll 57, 12, 27
+
+# Load Vector Word & Splat Indexed
+# CHECK-BE: lxvwsx 57, 12, 27                  # encoding: [0x7f,0x2c,0xda,0xd9]
+# CHECK-LE: lxvwsx 57, 12, 27                  # encoding: [0xd9,0xda,0x2c,0x7f]
+            lxvwsx 57, 12, 27
+
+# Store as Integer Byte/Halfword Indexed
+# CHECK-BE: stxsibx 57, 12, 27                 # encoding: [0x7f,0x2c,0xdf,0x1b]
+# CHECK-LE: stxsibx 57, 12, 27                 # encoding: [0x1b,0xdf,0x2c,0x7f]
+            stxsibx 57, 12, 27
+# CHECK-BE: stxsihx 57, 12, 27                 # encoding: [0x7f,0x2c,0xdf,0x5b]
+# CHECK-LE: stxsihx 57, 12, 27                 # encoding: [0x5b,0xdf,0x2c,0x7f]
+            stxsihx 57, 12, 27
+
+# Store Vector Halfword*8/Byte*16 Indexed
+# CHECK-BE: stxvh8x 57, 12, 27                 # encoding: [0x7f,0x2c,0xdf,0x59]
+# CHECK-LE: stxvh8x 57, 12, 27                 # encoding: [0x59,0xdf,0x2c,0x7f]
+            stxvh8x 57, 12, 27
+# CHECK-BE: stxvb16x 57, 12, 27                # encoding: [0x7f,0x2c,0xdf,0xd9]
+# CHECK-LE: stxvb16x 57, 12, 27                # encoding: [0xd9,0xdf,0x2c,0x7f]
+            stxvb16x 57, 12, 27
+
+# Store Vector Indexed
+# CHECK-BE: stxvx 57, 12, 27                   # encoding: [0x7f,0x2c,0xdb,0x19]
+# CHECK-LE: stxvx 57, 12, 27                   # encoding: [0x19,0xdb,0x2c,0x7f]
+            stxvx 57, 12, 27
+
+# Store Vector (Left-justified) with Length
+# CHECK-BE: stxvl 57, 12, 27                   # encoding: [0x7f,0x2c,0xdb,0x1b]
+# CHECK-LE: stxvl 57, 12, 27                   # encoding: [0x1b,0xdb,0x2c,0x7f]
+            stxvl 57, 12, 27
+# CHECK-BE: stxvll 57, 12, 27                  # encoding: [0x7f,0x2c,0xdb,0x5b]
+# CHECK-LE: stxvll 57, 12, 27                  # encoding: [0x5b,0xdb,0x2c,0x7f]
+            stxvll 57, 12, 27