[Power9] Implement new vsx instructions: insert, extract, test data class, min/max, reverse, permute, splat

This change implements the following vsx instructions: - Scalar Insert/Extract xsiexpdp xsiexpqp xsxexpdp xsxsigdp xsxexpqp xsxsigqp - Vector Insert/Extract xviexpdp xviexpsp xvxexpdp xvxexpsp xvxsigdp xvxsigsp xxextractuw xxinsertw - Scalar/Vector Test Data Class xststdcdp xststdcsp xststdcqp xvtstdcdp xvtstdcsp - Maximum/Minimum xsmaxcdp xsmaxjdp xsmincdp xsminjdp - Vector Byte-Reverse/Permute/Splat xxbrd xxbrh xxbrq xxbrw xxperm xxpermr xxspltib 30 instructions Thanks Nemanja for invaluable discussion! Thanks Kit's great help! Reviewers: hal, nemanja, kbarton, tjablin, amehsan http://reviews.llvm.org/D16842 llvm-svn: 264567
2024-11-24 03:33:20 +01:00 · 2016-03-28 08:34:28 +00:00 · 2016-03-28 08:34:28 +00:00 · 86334cecad
commit 86334cecad
parent 9018ddedab
9 changed files with 555 additions and 0 deletions
--- a/lib/Target/PowerPC/AsmParser/PPCAsmParser.cpp
+++ b/lib/Target/PowerPC/AsmParser/PPCAsmParser.cpp
@ -458,9 +458,11 @@ public:
  bool isU6ImmX2() const { return Kind == Immediate &&
                                  isUInt<6>(getImm()) &&
                                  (getImm() & 1) == 0; }
+  bool isU7Imm() const { return Kind == Immediate && isUInt<7>(getImm()); }
  bool isU7ImmX4() const { return Kind == Immediate &&
                                  isUInt<7>(getImm()) &&
                                  (getImm() & 3) == 0; }
+  bool isU8Imm() const { return Kind == Immediate && isUInt<8>(getImm()); }
  bool isU8ImmX8() const { return Kind == Immediate &&
                                  isUInt<8>(getImm()) &&
                                  (getImm() & 7) == 0; }
--- a/lib/Target/PowerPC/InstPrinter/PPCInstPrinter.cpp
+++ b/lib/Target/PowerPC/InstPrinter/PPCInstPrinter.cpp
@ -299,6 +299,20 @@ void PPCInstPrinter::printU6ImmOperand(const MCInst *MI, unsigned OpNo,
  O << (unsigned int)Value;
 }

+void PPCInstPrinter::printU7ImmOperand(const MCInst *MI, unsigned OpNo,
+                                       raw_ostream &O) {
+  unsigned int Value = MI->getOperand(OpNo).getImm();
+  assert(Value <= 127 && "Invalid u7imm argument!");
+  O << (unsigned int)Value;
+}
+
+void PPCInstPrinter::printU8ImmOperand(const MCInst *MI, unsigned OpNo,
+                                       raw_ostream &O) {
+  unsigned int Value = MI->getOperand(OpNo).getImm();
+  assert(Value <= 255 && "Invalid u8imm argument!");
+  O << (unsigned int)Value;
+}
+
 void PPCInstPrinter::printU10ImmOperand(const MCInst *MI, unsigned OpNo,
                                        raw_ostream &O) {
  unsigned short Value = MI->getOperand(OpNo).getImm();
--- a/lib/Target/PowerPC/InstPrinter/PPCInstPrinter.h
+++ b/lib/Target/PowerPC/InstPrinter/PPCInstPrinter.h
@ -53,6 +53,8 @@ public:
  void printS5ImmOperand(const MCInst *MI, unsigned OpNo, raw_ostream &O);
  void printU5ImmOperand(const MCInst *MI, unsigned OpNo, raw_ostream &O);
  void printU6ImmOperand(const MCInst *MI, unsigned OpNo, raw_ostream &O);
+  void printU7ImmOperand(const MCInst *MI, unsigned OpNo, raw_ostream &O);
+  void printU8ImmOperand(const MCInst *MI, unsigned OpNo, raw_ostream &O);
  void printU10ImmOperand(const MCInst *MI, unsigned OpNo, raw_ostream &O);
  void printU12ImmOperand(const MCInst *MI, unsigned OpNo, raw_ostream &O);
  void printS16ImmOperand(const MCInst *MI, unsigned OpNo, raw_ostream &O);
--- a/lib/Target/PowerPC/PPCInstrFormats.td
+++ b/lib/Target/PowerPC/PPCInstrFormats.td
@ -769,6 +769,37 @@ class X_RD5_XO5_RS5<bits<6> opcode, bits<5> xo2, bits<10> xo, dag OOL, dag IOL,
  let A = xo2;
 }

+class X_BF3_DCMX7_RS5<bits<6> opcode, bits<10> xo, dag OOL, dag IOL,
+                      string asmstr, InstrItinClass itin, list<dag> pattern>
+  : I<opcode, OOL, IOL, asmstr, itin> {
+  bits<3> BF;
+  bits<7> DCMX;
+  bits<5> VB;
+
+  let Pattern = pattern;
+
+  let Inst{6-8}  = BF;
+  let Inst{9-15} = DCMX;
+  let Inst{16-20} = VB;
+  let Inst{21-30} = xo;
+  let Inst{31}    = 0;
+}
+
+class X_RD6_IMM8<bits<6> opcode, bits<10> xo, dag OOL, dag IOL,
+                 string asmstr, InstrItinClass itin, list<dag> pattern>
+  : I<opcode, OOL, IOL, asmstr, itin> {
+  bits<6> XT;
+  bits<8> IMM8;
+
+  let Pattern = pattern;
+
+  let Inst{6-10}  = XT{4-0};
+  let Inst{11-12} = 0;
+  let Inst{13-20} = IMM8;
+  let Inst{21-30} = xo;
+  let Inst{31}    = XT{5};
+}
+
 // XX*-Form (VSX)
 class XX1Form<bits<6> opcode, bits<10> xo, dag OOL, dag IOL, string asmstr, 
              InstrItinClass itin, list<dag> pattern>
@ -842,6 +873,41 @@ class XX2Form_2<bits<6> opcode, bits<9> xo, dag OOL, dag IOL, string asmstr,
  let Inst{31}    = XT{5};
 }

+class XX2_RD6_UIM5_RS6<bits<6> opcode, bits<9> xo, dag OOL, dag IOL,
+                       string asmstr, InstrItinClass itin, list<dag> pattern>
+  : I<opcode, OOL, IOL, asmstr, itin> {
+  bits<6> XT;
+  bits<6> XB;
+  bits<5> UIM5;
+
+  let Pattern = pattern;
+
+  let Inst{6-10}  = XT{4-0};
+  let Inst{11-15} = UIM5;
+  let Inst{16-20} = XB{4-0};
+  let Inst{21-29} = xo;
+  let Inst{30}    = XB{5};
+  let Inst{31}    = XT{5};
+}
+
+// [PO T XO B XO BX /]
+class XX2_RD5_XO5_RS6<bits<6> opcode, bits<5> xo2, bits<9> xo, dag OOL, dag IOL,
+                       string asmstr, InstrItinClass itin, list<dag> pattern>
+  : I<opcode, OOL, IOL, asmstr, itin> {
+  bits<5> RT;
+  bits<6> XB;
+
+  let Pattern = pattern;
+
+  let Inst{6-10}  = RT;
+  let Inst{11-15} = xo2;
+  let Inst{16-20} = XB{4-0};
+  let Inst{21-29} = xo;
+  let Inst{30}    = XB{5};
+  let Inst{31}    = 0;
+}
+
+// [PO T XO B XO BX TX]
 class XX2_RD6_XO5_RS6<bits<6> opcode, bits<5> xo2, bits<9> xo, dag OOL, dag IOL,
                      string asmstr, InstrItinClass itin, list<dag> pattern>
  : I<opcode, OOL, IOL, asmstr, itin> {
@ -858,6 +924,44 @@ class XX2_RD6_XO5_RS6<bits<6> opcode, bits<5> xo2, bits<9> xo, dag OOL, dag IOL,
  let Inst{31}    = XT{5};
 }

+class XX2_BF3_DCMX7_RS6<bits<6> opcode, bits<9> xo, dag OOL, dag IOL,
+                      string asmstr, InstrItinClass itin, list<dag> pattern>
+  : I<opcode, OOL, IOL, asmstr, itin> {
+  bits<3> BF;
+  bits<7> DCMX;
+  bits<6> XB;
+
+  let Pattern = pattern;
+
+  let Inst{6-8}  = BF;
+  let Inst{9-15} = DCMX;
+  let Inst{16-20} = XB{4-0};
+  let Inst{21-29} = xo;
+  let Inst{30}    = XB{5};
+  let Inst{31}    = 0;
+}
+
+class XX2_RD6_DCMX7_RS6<bits<6> opcode, bits<4> xo1, bits<3> xo2,
+                        dag OOL, dag IOL, string asmstr, InstrItinClass itin,
+                        list<dag> pattern>
+  : I<opcode, OOL, IOL, asmstr, itin> {
+  bits<6> XT;
+  bits<7> DCMX;
+  bits<6> XB;
+
+  let Pattern = pattern;
+
+  let Inst{6-10}  = XT{4-0};
+  let Inst{11-15} = DCMX{4-0};
+  let Inst{16-20} = XB{4-0};
+  let Inst{21-24} = xo1;
+  let Inst{25}    = DCMX{5};
+  let Inst{26-28} = xo2;
+  let Inst{29}    = DCMX{6};
+  let Inst{30}    = XB{5};
+  let Inst{31}    = XT{5};
+}
+
 class XX3Form<bits<6> opcode, bits<8> xo, dag OOL, dag IOL, string asmstr, 
              InstrItinClass itin, list<dag> pattern>
  : I<opcode, OOL, IOL, asmstr, itin> {
--- a/lib/Target/PowerPC/PPCInstrInfo.td
+++ b/lib/Target/PowerPC/PPCInstrInfo.td
@ -507,6 +507,24 @@ def u6imm   : Operand<i32> {
  let ParserMatchClass = PPCU6ImmAsmOperand;
  let DecoderMethod = "decodeUImmOperand<6>";
 }
+def PPCU7ImmAsmOperand : AsmOperandClass {
+  let Name = "U7Imm"; let PredicateMethod = "isU7Imm";
+  let RenderMethod = "addImmOperands";
+}
+def u7imm   : Operand<i32> {
+  let PrintMethod = "printU7ImmOperand";
+  let ParserMatchClass = PPCU7ImmAsmOperand;
+  let DecoderMethod = "decodeUImmOperand<7>";
+}
+def PPCU8ImmAsmOperand : AsmOperandClass {
+  let Name = "U8Imm"; let PredicateMethod = "isU8Imm";
+  let RenderMethod = "addImmOperands";
+}
+def u8imm   : Operand<i32> {
+  let PrintMethod = "printU8ImmOperand";
+  let ParserMatchClass = PPCU8ImmAsmOperand;
+  let DecoderMethod = "decodeUImmOperand<8>";
+}
 def PPCU10ImmAsmOperand : AsmOperandClass {
  let Name = "U10Imm"; let PredicateMethod = "isU10Imm";
  let RenderMethod = "addImmOperands";
--- a/lib/Target/PowerPC/PPCInstrVSX.td
+++ b/lib/Target/PowerPC/PPCInstrVSX.td
@ -1806,6 +1806,12 @@ let Predicates = [HasP9Vector] in {
    : X_RD5_XO5_RS5<opcode, xo2, xo, (outs vrrc:$vT), (ins vbtype:$vB),
                    !strconcat(opc, " $vT, $vB"), IIC_VecFP, pattern>;

+  // [PO T XO B XO BX /]
+  class XX2_RT5_XO5_XB6<bits<6> opcode, bits<5> xo2, bits<9> xo, string opc,
+                        list<dag> pattern>
+    : XX2_RD5_XO5_RS6<opcode, xo2, xo, (outs g8rc:$rT), (ins vsfrc:$XB),
+                      !strconcat(opc, " $rT, $XB"), IIC_VecFP, pattern>;
+
  // [PO T XO B XO BX TX]
  class XX2_XT6_XO5_XB6<bits<6> opcode, bits<5> xo2, bits<9> xo, string opc,
                        RegisterOperand vtype, list<dag> pattern>
@ -1967,6 +1973,99 @@ let Predicates = [HasP9Vector] in {
  // Round Quad-Precision to Double-Extended Precision (fp80)
  def XSRQPXP  : Z23_VT5_R1_VB5_RMC2_EX1<63, 37, 0, "xsrqpxp", []>;

+  //===--------------------------------------------------------------------===//
+  // Insert/Extract Instructions
+
+  // Insert Exponent DP/QP
+  // XT NOTE: XT.dword[1] = 0xUUUU_UUUU_UUUU_UUUU
+  def XSIEXPDP : XX1Form <60, 918, (outs vsrc:$XT), (ins g8rc:$rA, g8rc:$rB),
+                          "xsiexpdp $XT, $rA, $rB", IIC_VecFP, []>;
+  // vB NOTE: only vB.dword[0] is used, that's why we don't use
+  //          X_VT5_VA5_VB5 form
+  def XSIEXPQP : XForm_18<63, 868, (outs vrrc:$vT), (ins vrrc:$vA, vsfrc:$vB),
+                          "xsiexpqp $vT, $vA, $vB", IIC_VecFP, []>;
+
+  // Extract Exponent/Significand DP/QP
+  def XSXEXPDP : XX2_RT5_XO5_XB6<60,  0, 347, "xsxexpdp", []>;
+  def XSXSIGDP : XX2_RT5_XO5_XB6<60,  1, 347, "xsxsigdp", []>;
+  def XSXEXPQP : X_VT5_XO5_VB5  <63,  2, 804, "xsxexpqp", []>;
+  def XSXSIGQP : X_VT5_XO5_VB5  <63, 18, 804, "xsxsigqp", []>;
+
+  // Vector Insert Word
+  // XB NOTE: Only XB.dword[1] is used, but we use vsrc on XB.
+  def XXINSERTW   : XX2_RD6_UIM5_RS6<60, 181,
+                                  (outs vsrc:$XT), (ins u4imm:$UIMM, vsrc:$XB),
+                                  "xxinsertw $XT, $XB, $UIMM", IIC_VecFP, []>;
+
+  // Vector Extract Unsigned Word
+  def XXEXTRACTUW : XX2_RD6_UIM5_RS6<60, 165,
+                                  (outs vsrc:$XT), (ins u4imm:$UIMM, vsrc:$XB),
+                                  "xxextractuw $XT, $XB, $UIMM", IIC_VecFP, []>;
+
+  // Vector Insert Exponent DP/SP
+  def XVIEXPDP : XX3_XT5_XA5_XB5<60, 248, "xviexpdp", vsrc, vsrc, vsrc,
+                                 IIC_VecFP, []>;
+  def XVIEXPSP : XX3_XT5_XA5_XB5<60, 216, "xviexpsp", vsrc, vsrc, vsrc,
+                                 IIC_VecFP, []>;
+
+  // Vector Extract Exponent/Significand DP/SP
+  def XVXEXPDP : XX2_XT6_XO5_XB6<60,  0, 475, "xvxexpdp", vsrc, []>;
+  def XVXEXPSP : XX2_XT6_XO5_XB6<60,  8, 475, "xvxexpsp", vsrc, []>;
+  def XVXSIGDP : XX2_XT6_XO5_XB6<60,  1, 475, "xvxsigdp", vsrc, []>;
+  def XVXSIGSP : XX2_XT6_XO5_XB6<60,  9, 475, "xvxsigsp", vsrc, []>;
+
+  //===--------------------------------------------------------------------===//
+
+  // Test Data Class SP/DP/QP
+  def XSTSTDCSP : XX2_BF3_DCMX7_RS6<60, 298,
+                              (outs crrc:$BF), (ins u7imm:$DCMX, vsfrc:$XB),
+                              "xststdcsp $BF, $XB, $DCMX", IIC_VecFP, []>;
+  def XSTSTDCDP : XX2_BF3_DCMX7_RS6<60, 362,
+                              (outs crrc:$BF), (ins u7imm:$DCMX, vsfrc:$XB),
+                              "xststdcdp $BF, $XB, $DCMX", IIC_VecFP, []>;
+  def XSTSTDCQP : X_BF3_DCMX7_RS5  <63, 708,
+                              (outs crrc:$BF), (ins u7imm:$DCMX, vrrc:$vB),
+                              "xststdcqp $BF, $vB, $DCMX", IIC_VecFP, []>;
+
+  // Vector Test Data Class SP/DP
+  def XVTSTDCSP : XX2_RD6_DCMX7_RS6<60, 13, 5,
+                              (outs vsrc:$XT), (ins u7imm:$DCMX, vsrc:$XB),
+                              "xvtstdcsp $XT, $XB, $DCMX", IIC_VecFP, []>;
+  def XVTSTDCDP : XX2_RD6_DCMX7_RS6<60, 15, 5,
+                              (outs vsrc:$XT), (ins u7imm:$DCMX, vsrc:$XB),
+                              "xvtstdcdp $XT, $XB, $DCMX", IIC_VecFP, []>;
+
+  //===--------------------------------------------------------------------===//
+
+  // Maximum/Minimum Type-C/Type-J DP
+  // XT.dword[1] = 0xUUUU_UUUU_UUUU_UUUU, so we use vsrc for XT
+  def XSMAXCDP : XX3_XT5_XA5_XB5<60, 128, "xsmaxcdp", vsrc, vsfrc, vsfrc,
+                                 IIC_VecFP, []>;
+  def XSMAXJDP : XX3_XT5_XA5_XB5<60, 144, "xsmaxjdp", vsrc, vsfrc, vsfrc,
+                                 IIC_VecFP, []>;
+  def XSMINCDP : XX3_XT5_XA5_XB5<60, 136, "xsmincdp", vsrc, vsfrc, vsfrc,
+                                 IIC_VecFP, []>;
+  def XSMINJDP : XX3_XT5_XA5_XB5<60, 152, "xsminjdp", vsrc, vsfrc, vsfrc,
+                                 IIC_VecFP, []>;
+
+  //===--------------------------------------------------------------------===//
+
+  // Vector Byte-Reverse H/W/D/Q Word
+  def XXBRH : XX2_XT6_XO5_XB6<60,  7, 475, "xxbrh", vsrc, []>;
+  def XXBRW : XX2_XT6_XO5_XB6<60, 15, 475, "xxbrw", vsrc, []>;
+  def XXBRD : XX2_XT6_XO5_XB6<60, 23, 475, "xxbrd", vsrc, []>;
+  def XXBRQ : XX2_XT6_XO5_XB6<60, 31, 475, "xxbrq", vsrc, []>;
+
+  // Vector Permute
+  def XXPERM  : XX3_XT5_XA5_XB5<60, 26, "xxperm" , vsrc, vsrc, vsrc,
+                                IIC_VecPerm, []>;
+  def XXPERMR : XX3_XT5_XA5_XB5<60, 58, "xxpermr", vsrc, vsrc, vsrc,
+                                IIC_VecPerm, []>;
+
+  // Vector Splat Immediate Byte
+  def XXSPLTIB : X_RD6_IMM8<60, 360, (outs vsrc:$XT), (ins u8imm:$IMM8),
+                            "xxspltib $XT, $IMM8", IIC_VecPerm, []>;
+
  //===--------------------------------------------------------------------===//
  // Vector/Scalar Load/Store Instructions

--- a/lib/Target/PowerPC/README_P9.txt
+++ b/lib/Target/PowerPC/README_P9.txt
@ -343,6 +343,112 @@ VSX:
  . Provide builtin?
    (set f128:$vT, (int_ppc_vsx_xsrqpxp f128:$vB))

+- Insert Exponent DP/QP: xsiexpdp xsiexpqp
+  . Use intrinsic?
+  . xsiexpdp:
+    // Note: rA and rB are the unsigned integer value.
+    (set f128:$XT, (int_ppc_vsx_xsiexpdp i64:$rA, i64:$rB))
+
+  . xsiexpqp:
+    (set f128:$vT, (int_ppc_vsx_xsiexpqp f128:$vA, f64:$vB))
+
+- Extract Exponent/Significand DP/QP: xsxexpdp xsxsigdp xsxexpqp xsxsigqp
+  . Use intrinsic?
+  . (set i64:$rT, (int_ppc_vsx_xsxexpdp f64$XB))    // xsxexpdp
+    (set i64:$rT, (int_ppc_vsx_xsxsigdp f64$XB))    // xsxsigdp
+    (set f128:$vT, (int_ppc_vsx_xsxexpqp f128$vB))  // xsxexpqp
+    (set f128:$vT, (int_ppc_vsx_xsxsigqp f128$vB))  // xsxsigqp
+
+- Vector Insert Word: xxinsertw
+  . Note: llvm has insertelem in "Vector Operations"
+    ; yields <n x <ty>>
+    <result> = insertelement <n x <ty>> <val>, <ty> <elt>, <ty2> <idx>
+
+    But how to map to it??
+    [(set v1f128:$XT, (insertelement v1f128:$XTi, f128:$XB, i4:$UIMM))]>,
+    RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
+
+  . Or use intrinsic?
+    (set v1f128:$XT, (int_ppc_vsx_xxinsertw v1f128:$XTi, f128:$XB, i4:$UIMM))
+
+- Vector Extract Unsigned Word: xxextractuw
+  . Note: llvm has extractelement in "Vector Operations"
+    ; yields <ty>
+    <result> = extractelement <n x <ty>> <val>, <ty2> <idx>
+
+    How to map to it??
+    [(set f128:$XT, (extractelement v1f128:$XB, i4:$UIMM))]
+
+  . Or use intrinsic?
+    (set f128:$XT, (int_ppc_vsx_xxextractuw v1f128:$XB, i4:$UIMM))
+
+- Vector Insert Exponent DP/SP: xviexpdp xviexpsp
+  . Use intrinsic
+    (set v2f64:$XT, (int_ppc_vsx_xviexpdp v2f64:$XA, v2f64:$XB))
+    (set v4f32:$XT, (int_ppc_vsx_xviexpsp v4f32:$XA, v4f32:$XB))
+
+- Vector Extract Exponent/Significand DP/SP: xvxexpdp xvxexpsp xvxsigdp xvxsigsp
+  . Use intrinsic
+    (set v2f64:$XT, (int_ppc_vsx_xvxexpdp v2f64:$XB))
+    (set v4f32:$XT, (int_ppc_vsx_xvxexpsp v4f32:$XB))
+    (set v2f64:$XT, (int_ppc_vsx_xvxsigdp v2f64:$XB))
+    (set v4f32:$XT, (int_ppc_vsx_xvxsigsp v4f32:$XB))
+
+- Test Data Class SP/DP/QP: xststdcsp xststdcdp xststdcqp
+  . No SDAG, intrinsic, builtin are required?
+    Because it seems that we have no way to map BF field?
+
+    Instruction Form: [PO T XO B XO BX TX]
+    Asm: xststd* BF,XB,DCMX
+
+    BF is an index to CR register field.
+
+- Vector Test Data Class SP/DP: xvtstdcsp xvtstdcdp
+  . Use intrinsic
+    (set v4f32:$XT, (int_ppc_vsx_xvtstdcsp v4f32:$XB, i7:$DCMX))
+    (set v2f64:$XT, (int_ppc_vsx_xvtstdcdp v2f64:$XB, i7:$DCMX))
+
+- Maximum/Minimum Type-C/Type-J DP: xsmaxcdp xsmaxjdp xsmincdp xsminjdp
+  . PowerISA_V3.0:
+    "xsmaxcdp can be used to implement the C/C++/Java conditional operation
+     (x>y)?x:y for single-precision and double-precision arguments."
+
+    Note! c type and j type have different behavior when:
+    1. Either input is NaN
+    2. Both input are +-Infinity, +-Zero
+
+  . dtype map to llvm fmaxnum/fminnum
+    jtype use intrinsic
+
+  . xsmaxcdp xsmincdp
+    (set f64:$XT, (fmaxnum f64:$XA, f64:$XB))
+    (set f64:$XT, (fminnum f64:$XA, f64:$XB))
+
+  . xsmaxjdp xsminjdp
+    (set f64:$XT, (int_ppc_vsx_xsmaxjdp f64:$XA, f64:$XB))
+    (set f64:$XT, (int_ppc_vsx_xsminjdp f64:$XA, f64:$XB))
+
+- Vector Byte-Reverse H/W/D/Q Word: xxbrh xxbrw xxbrd xxbrq
+  . Use intrinsic
+    (set v8i16:$XT, (int_ppc_vsx_xxbrh v8i16:$XB))
+    (set v4i32:$XT, (int_ppc_vsx_xxbrw v4i32:$XB))
+    (set v2i64:$XT, (int_ppc_vsx_xxbrd v2i64:$XB))
+    (set v1i128:$XT, (int_ppc_vsx_xxbrq v1i128:$XB))
+
+- Vector Permute: xxperm xxpermr
+  . I have checked "PPCxxswapd" in PPCInstrVSX.td, but they are different
+  . Use intrinsic
+    (set v16i8:$XT, (int_ppc_vsx_xxperm v16i8:$XA, v16i8:$XB))
+    (set v16i8:$XT, (int_ppc_vsx_xxpermr v16i8:$XA, v16i8:$XB))
+
+- Vector Splat Immediate Byte: xxspltib
+  . Similar to XXSPLTW:
+      def XXSPLTW : XX2Form_2<60, 164,
+                           (outs vsrc:$XT), (ins vsrc:$XB, u2imm:$UIM),
+                           "xxspltw $XT, $XB, $UIM", IIC_VecPerm, []>;
+
+  . No SDAG, intrinsic, builtin are required?
+
 - Load/Store Vector: lxv stxv
  . Has likely SDAG match:
    (set v?:$XT, (load ix16addr:$src))
--- a/test/MC/Disassembler/PowerPC/vsx.txt
+++ b/test/MC/Disassembler/PowerPC/vsx.txt
@ -692,6 +692,99 @@
 # CHECK: xsrqpxp 1, 7, 27, 2
 0xfc 0xe1 0xdc 0x4a

+# CHECK: xsiexpdp 63, 3, 4
+0xf3 0xe3 0x27 0x2d
+
+# CHECK: xsiexpqp 7, 31, 27
+0xfc 0xff 0xde 0xc8
+
+# CHECK: xviexpdp 7, 63, 27
+0xf0 0xff 0xdf 0xc4
+
+# CHECK: xviexpsp 7, 63, 27
+0xf0 0xff 0xde 0xc4
+
+# CHECK: xxextractuw 7, 63, 15
+0xf0 0xef 0xfa 0x96
+
+# CHECK: xxinsertw 7, 63, 15
+0xf0 0xef 0xfa 0xd6
+
+# CHECK: xsxexpdp 7, 63
+0xf0 0xe0 0xfd 0x6e
+
+# CHECK: xsxsigdp 7, 63
+0xf0 0xe1 0xfd 0x6e
+
+# CHECK: xsxexpqp 7, 31
+0xfc 0xe2 0xfe 0x48
+
+# CHECK: xsxsigqp 7, 31
+0xfc 0xf2 0xfe 0x48
+
+# CHECK: xvxexpdp 7, 63
+0xf0 0xe0 0xff 0x6e
+
+# CHECK: xvxexpsp 7, 63
+0xf0 0xe8 0xff 0x6e
+
+# CHECK: xvxsigdp 7, 63
+0xf0 0xe1 0xff 0x6e
+
+# CHECK: xvxsigsp 7, 63
+0xf0 0xe9 0xff 0x6e
+
+# CHECK: xststdcsp 7, 63, 127
+0xf3 0xff 0xfc 0xaa
+
+# CHECK: xststdcdp 7, 63, 127
+0xf3 0xff 0xfd 0xaa
+
+# CHECK: xststdcqp 7, 31, 127
+0xff 0xff 0xfd 0x88
+
+# CHECK: xststdcsp 7, 63, 127
+0xf3 0xff 0xfc 0xaa
+
+# CHECK: xststdcdp 7, 63, 127
+0xf3 0xff 0xfd 0xaa
+
+# CHECK: xststdcqp 7, 31, 127
+0xff 0xff 0xfd 0x88
+
+# CHECK: xsmaxcdp 7, 63, 27
+0xf0 0xff 0xdc 0x04
+
+# CHECK: xsmaxjdp 7, 63, 27
+0xf0 0xff 0xdc 0x84
+
+# CHECK: xsmincdp 7, 63, 27
+0xf0 0xff 0xdc 0x44
+
+# CHECK: xsminjdp 7, 63, 27
+0xf0 0xff 0xdc 0xc4
+
+# CHECK: xxbrh 7, 63
+0xf0 0xe7 0xff 0x6e
+
+# CHECK: xxbrw 7, 63
+0xf0 0xef 0xff 0x6e
+
+# CHECK: xxbrd 7, 63
+0xf0 0xf7 0xff 0x6e
+
+# CHECK: xxbrq 7, 63
+0xf0 0xff 0xff 0x6e
+
+# CHECK: xxperm 7, 63, 27
+0xf0 0xff 0xd8 0xd4
+
+# CHECK: xxpermr 7, 63, 27
+0xf0 0xff 0xd9 0xd4
+
+# CHECK: xxspltib 63, 255
+0xf3 0xe7 0xfa 0xd1
+
 # CHECK: lxv 61, 32752(31)
 0xf7 0xbf 0x7f 0xf9

--- a/test/MC/PowerPC/vsx.s
+++ b/test/MC/PowerPC/vsx.s
@ -732,6 +732,123 @@
 # CHECK-LE: xsrqpxp 1, 7, 27, 2                # encoding: [0x4a,0xdc,0xe1,0xfc]
            xsrqpxp 1, 7, 27, 2

+# Insert Exponent DP/QP
+# CHECK-BE: xsiexpdp 63, 3, 4                  # encoding: [0xf3,0xe3,0x27,0x2d]
+# CHECK-LE: xsiexpdp 63, 3, 4                  # encoding: [0x2d,0x27,0xe3,0xf3]
+            xsiexpdp 63, 3, 4
+# CHECK-BE: xsiexpqp 7, 31, 27                 # encoding: [0xfc,0xff,0xde,0xc8]
+# CHECK-LE: xsiexpqp 7, 31, 27                 # encoding: [0xc8,0xde,0xff,0xfc]
+            xsiexpqp 7, 31, 27
+
+# Vector Insert Exponent DP
+# CHECK-BE: xviexpdp 7, 63, 27                 # encoding: [0xf0,0xff,0xdf,0xc4]
+# CHECK-LE: xviexpdp 7, 63, 27                 # encoding: [0xc4,0xdf,0xff,0xf0]
+            xviexpdp 7, 63, 27
+# CHECK-BE: xviexpsp 7, 63, 27                 # encoding: [0xf0,0xff,0xde,0xc4]
+# CHECK-LE: xviexpsp 7, 63, 27                 # encoding: [0xc4,0xde,0xff,0xf0]
+            xviexpsp 7, 63, 27
+
+# Vector Extract Unsigned Word
+# CHECK-BE: xxextractuw 7, 63, 15              # encoding: [0xf0,0xef,0xfa,0x96]
+# CHECK-LE: xxextractuw 7, 63, 15              # encoding: [0x96,0xfa,0xef,0xf0]
+            xxextractuw 7, 63, 15
+
+# Vector Insert Word
+# CHECK-BE: xxinsertw 7, 63, 15                # encoding: [0xf0,0xef,0xfa,0xd6]
+# CHECK-LE: xxinsertw 7, 63, 15                # encoding: [0xd6,0xfa,0xef,0xf0]
+            xxinsertw 7, 63, 15
+
+# Extract Exponent/Significand DP/QP
+# CHECK-BE: xsxexpdp 7, 63                     # encoding: [0xf0,0xe0,0xfd,0x6e]
+# CHECK-LE: xsxexpdp 7, 63                     # encoding: [0x6e,0xfd,0xe0,0xf0]
+            xsxexpdp 7, 63
+# CHECK-BE: xsxsigdp 7, 63                     # encoding: [0xf0,0xe1,0xfd,0x6e]
+# CHECK-LE: xsxsigdp 7, 63                     # encoding: [0x6e,0xfd,0xe1,0xf0]
+            xsxsigdp 7, 63
+# CHECK-BE: xsxexpqp 7, 31                     # encoding: [0xfc,0xe2,0xfe,0x48]
+# CHECK-LE: xsxexpqp 7, 31                     # encoding: [0x48,0xfe,0xe2,0xfc]
+            xsxexpqp 7, 31
+# CHECK-BE: xsxsigqp 7, 31                     # encoding: [0xfc,0xf2,0xfe,0x48]
+# CHECK-LE: xsxsigqp 7, 31                     # encoding: [0x48,0xfe,0xf2,0xfc]
+            xsxsigqp 7, 31
+
+# Vector Extract Exponent/Significand DP
+# CHECK-BE: xvxexpdp 7, 63                     # encoding: [0xf0,0xe0,0xff,0x6e]
+# CHECK-LE: xvxexpdp 7, 63                     # encoding: [0x6e,0xff,0xe0,0xf0]
+            xvxexpdp 7, 63
+# CHECK-BE: xvxexpsp 7, 63                     # encoding: [0xf0,0xe8,0xff,0x6e]
+# CHECK-LE: xvxexpsp 7, 63                     # encoding: [0x6e,0xff,0xe8,0xf0]
+            xvxexpsp 7, 63
+# CHECK-BE: xvxsigdp 7, 63                     # encoding: [0xf0,0xe1,0xff,0x6e]
+# CHECK-LE: xvxsigdp 7, 63                     # encoding: [0x6e,0xff,0xe1,0xf0]
+            xvxsigdp 7, 63
+# CHECK-BE: xvxsigsp 7, 63                     # encoding: [0xf0,0xe9,0xff,0x6e]
+# CHECK-LE: xvxsigsp 7, 63                     # encoding: [0x6e,0xff,0xe9,0xf0]
+            xvxsigsp 7, 63
+
+# Test Data Class SP/DP/QP
+# CHECK-BE: xststdcsp 7, 63, 127               # encoding: [0xf3,0xff,0xfc,0xaa]
+# CHECK-LE: xststdcsp 7, 63, 127               # encoding: [0xaa,0xfc,0xff,0xf3]
+            xststdcsp 7, 63, 127
+# CHECK-BE: xststdcdp 7, 63, 127               # encoding: [0xf3,0xff,0xfd,0xaa]
+# CHECK-LE: xststdcdp 7, 63, 127               # encoding: [0xaa,0xfd,0xff,0xf3]
+            xststdcdp 7, 63, 127
+# CHECK-BE: xststdcqp 7, 31, 127               # encoding: [0xff,0xff,0xfd,0x88]
+# CHECK-LE: xststdcqp 7, 31, 127               # encoding: [0x88,0xfd,0xff,0xff]
+            xststdcqp 7, 31, 127
+
+# Vector Test Data Class SP/DP
+# CHECK-BE: xststdcsp 7, 63, 127               # encoding: [0xf3,0xff,0xfc,0xaa]
+# CHECK-LE: xststdcsp 7, 63, 127               # encoding: [0xaa,0xfc,0xff,0xf3]
+            xststdcsp 7, 63, 127
+# CHECK-BE: xststdcdp 7, 63, 127               # encoding: [0xf3,0xff,0xfd,0xaa]
+# CHECK-LE: xststdcdp 7, 63, 127               # encoding: [0xaa,0xfd,0xff,0xf3]
+            xststdcdp 7, 63, 127
+# CHECK-BE: xststdcqp 7, 31, 127               # encoding: [0xff,0xff,0xfd,0x88]
+# CHECK-LE: xststdcqp 7, 31, 127               # encoding: [0x88,0xfd,0xff,0xff]
+            xststdcqp 7, 31, 127
+
+# Maximum/Minimum Type-C/Type-J DP
+# CHECK-BE: xsmaxcdp 7, 63, 27                 # encoding: [0xf0,0xff,0xdc,0x04]
+# CHECK-LE: xsmaxcdp 7, 63, 27                 # encoding: [0x04,0xdc,0xff,0xf0]
+            xsmaxcdp 7, 63, 27
+# CHECK-BE: xsmaxjdp 7, 63, 27                 # encoding: [0xf0,0xff,0xdc,0x84]
+# CHECK-LE: xsmaxjdp 7, 63, 27                 # encoding: [0x84,0xdc,0xff,0xf0]
+            xsmaxjdp 7, 63, 27
+# CHECK-BE: xsmincdp 7, 63, 27                 # encoding: [0xf0,0xff,0xdc,0x44]
+# CHECK-LE: xsmincdp 7, 63, 27                 # encoding: [0x44,0xdc,0xff,0xf0]
+            xsmincdp 7, 63, 27
+# CHECK-BE: xsminjdp 7, 63, 27                 # encoding: [0xf0,0xff,0xdc,0xc4]
+# CHECK-LE: xsminjdp 7, 63, 27                 # encoding: [0xc4,0xdc,0xff,0xf0]
+            xsminjdp 7, 63, 27
+
+# Vector Byte-Reverse H/W/D/Q Word
+# CHECK-BE: xxbrh 7, 63                        # encoding: [0xf0,0xe7,0xff,0x6e]
+# CHECK-LE: xxbrh 7, 63                        # encoding: [0x6e,0xff,0xe7,0xf0]
+            xxbrh 7, 63
+# CHECK-BE: xxbrw 7, 63                        # encoding: [0xf0,0xef,0xff,0x6e]
+# CHECK-LE: xxbrw 7, 63                        # encoding: [0x6e,0xff,0xef,0xf0]
+            xxbrw 7, 63
+# CHECK-BE: xxbrd 7, 63                        # encoding: [0xf0,0xf7,0xff,0x6e]
+# CHECK-LE: xxbrd 7, 63                        # encoding: [0x6e,0xff,0xf7,0xf0]
+            xxbrd 7, 63
+# CHECK-BE: xxbrq 7, 63                        # encoding: [0xf0,0xff,0xff,0x6e]
+# CHECK-LE: xxbrq 7, 63                        # encoding: [0x6e,0xff,0xff,0xf0]
+            xxbrq 7, 63
+
+# Vector Permute
+# CHECK-BE: xxperm 7, 63, 27                   # encoding: [0xf0,0xff,0xd8,0xd4]
+# CHECK-LE: xxperm 7, 63, 27                   # encoding: [0xd4,0xd8,0xff,0xf0]
+            xxperm 7, 63, 27
+# CHECK-BE: xxpermr 7, 63, 27                  # encoding: [0xf0,0xff,0xd9,0xd4]
+# CHECK-LE: xxpermr 7, 63, 27                  # encoding: [0xd4,0xd9,0xff,0xf0]
+            xxpermr 7, 63, 27
+
+# Vector Splat Immediate Byte
+# CHECK-BE: xxspltib 63, 255                   # encoding: [0xf3,0xe7,0xfa,0xd1]
+# CHECK-LE: xxspltib 63, 255                   # encoding: [0xd1,0xfa,0xe7,0xf3]
+            xxspltib 63, 255
+
 # 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]