1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 12:41:49 +01:00

[PowerPC] Remove UseVSXReg

The UseVSXReg flag can be safely removed and the code cleaned up.

Patch By: Yi-Hong Liu

Differential Revision: https://reviews.llvm.org/D58685

llvm-svn: 357028
This commit is contained in:
Stefan Pintilie 2019-03-26 20:28:21 +00:00
parent 244f929f25
commit f062017e37
5 changed files with 102 additions and 126 deletions

View File

@ -168,10 +168,7 @@ void PPCAsmPrinter::printOperand(const MachineInstr *MI, unsigned OpNo,
switch (MO.getType()) {
case MachineOperand::MO_Register: {
// The MI is INLINEASM ONLY and UseVSXReg is always false.
unsigned Reg =
PPCInstrInfo::getRegNumForOperand(MI->getDesc(), MO.getReg(), OpNo);
const char *RegName = PPCInstPrinter::getRegisterName(Reg);
const char *RegName = PPCInstPrinter::getRegisterName(MO.getReg());
// Linux assembler (Others?) does not take register mnemonics.
// FIXME - What about special registers used in mfspr/mtspr?

View File

@ -37,14 +37,6 @@ class I<bits<6> opcode, dag OOL, dag IOL, string asmstr, InstrItinClass itin>
let TSFlags{2} = PPC970_Cracked;
let TSFlags{5-3} = PPC970_Unit;
/// Indicate that the VSX instruction is to use VSX numbering/encoding.
/// Since ISA 3.0, there are scalar instructions that use the upper
/// half of the VSX register set only. Rather than adding further complexity
/// to the register class set, the VSX registers just include the Altivec
/// registers and this flag decides the numbering to be used for them.
bits<1> UseVSXReg = 0;
let TSFlags{6} = UseVSXReg;
// Indicate that this instruction is of type X-Form Load or Store
bits<1> XFormMemOp = 0;
let TSFlags{7} = XFormMemOp;
@ -73,7 +65,6 @@ class PPC970_Unit_VALU { bits<3> PPC970_Unit = 5; }
class PPC970_Unit_VPERM { bits<3> PPC970_Unit = 6; }
class PPC970_Unit_BRU { bits<3> PPC970_Unit = 7; }
class UseVSXReg { bits<1> UseVSXReg = 1; }
class XFormMemOp { bits<1> XFormMemOp = 1; }
// Two joined instructions; used to emit two adjacent instructions as one.

View File

@ -65,9 +65,6 @@ enum {
/// Shift count to bypass PPC970 flags
NewDef_Shift = 6,
/// The VSX instruction that uses VSX register (vs0-vs63), instead of VMX
/// register (v0-v31).
UseVSXReg = 0x1 << NewDef_Shift,
/// This instruction is an X-Form memory operation.
XFormMemOp = 0x1 << (NewDef_Shift+1)
};
@ -440,11 +437,24 @@ public:
/// operands).
static unsigned getRegNumForOperand(const MCInstrDesc &Desc, unsigned Reg,
unsigned OpNo) {
if (Desc.TSFlags & PPCII::UseVSXReg) {
if (isVRRegister(Reg))
Reg = PPC::VSX32 + (Reg - PPC::V0);
else if (isVFRegister(Reg))
Reg = PPC::VSX32 + (Reg - PPC::VF0);
int16_t regClass = Desc.OpInfo[OpNo].RegClass;
switch (regClass) {
// We store F0-F31, VF0-VF31 in MCOperand and it should be F0-F31,
// VSX32-VSX63 during encoding/disassembling
case PPC::VSSRCRegClassID:
case PPC::VSFRCRegClassID:
if (isVFRegister(Reg))
return PPC::VSX32 + (Reg - PPC::VF0);
break;
// We store VSL0-VSL31, V0-V31 in MCOperand and it should be VSL0-VSL31,
// VSX32-VSX63 during encoding/disassembling
case PPC::VSRCRegClassID:
if (isVRRegister(Reg))
return PPC::VSX32 + (Reg - PPC::V0);
break;
// Other RegClass doesn't need mapping
default:
break;
}
return Reg;
}

View File

@ -123,7 +123,6 @@ def HasOnlySwappingMemOps : Predicate<"!PPCSubTarget->hasP9Vector()">;
let Predicates = [HasVSX] in {
let AddedComplexity = 400 in { // Prefer VSX patterns over non-VSX patterns.
let UseVSXReg = 1 in {
let hasSideEffects = 0 in { // VSX instructions don't have side effects.
let Uses = [RM] in {
@ -894,11 +893,10 @@ let Uses = [RM] in {
(PPCxxsplt v4i32:$XB, imm32SExt16:$UIM))]>;
let isCodeGenOnly = 1 in
def XXSPLTWs : XX2Form_2<60, 164,
(outs vsrc:$XT), (ins vfrc:$XB, u2imm:$UIM),
(outs vsrc:$XT), (ins vsfrc:$XB, u2imm:$UIM),
"xxspltw $XT, $XB, $UIM", IIC_VecPerm, []>;
} // hasSideEffects
} // UseVSXReg = 1
// SELECT_CC_* - Used to implement the SELECT_CC DAG operation. Expanded after
// instruction selection into a branch sequence.
@ -1247,7 +1245,7 @@ def HasDirectMove : Predicate<"PPCSubTarget->hasDirectMove()">;
def NoP9Vector : Predicate<"!PPCSubTarget->hasP9Vector()">;
let Predicates = [HasP8Vector] in {
let AddedComplexity = 400 in { // Prefer VSX patterns over non-VSX patterns.
let isCommutable = 1, UseVSXReg = 1 in {
let isCommutable = 1 in {
def XXLEQV : XX3Form<60, 186,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xxleqv $XT, $XA, $XB", IIC_VecGeneral,
@ -1257,12 +1255,11 @@ let AddedComplexity = 400 in { // Prefer VSX patterns over non-VSX patterns.
"xxlnand $XT, $XA, $XB", IIC_VecGeneral,
[(set v4i32:$XT, (vnot_ppc (and v4i32:$XA,
v4i32:$XB)))]>;
} // isCommutable, UseVSXReg
} // isCommutable
def : Pat<(int_ppc_vsx_xxleqv v4i32:$A, v4i32:$B),
(XXLEQV $A, $B)>;
let UseVSXReg = 1 in {
def XXLORC : XX3Form<60, 170,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xxlorc $XT, $XA, $XB", IIC_VecGeneral,
@ -1311,7 +1308,6 @@ let AddedComplexity = 400 in { // Prefer VSX patterns over non-VSX patterns.
"#STIWX",
[(PPCstfiwx f64:$XT, xoaddr:$dst)]>;
} // mayStore
} // UseVSXReg = 1
def : Pat<(f64 (extloadf32 xoaddr:$src)),
(COPY_TO_REGCLASS (XFLOADf32 xoaddr:$src), VSFRC)>;
@ -1341,7 +1337,6 @@ let AddedComplexity = 400 in { // Prefer VSX patterns over non-VSX patterns.
def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETNE)),
(SELECT_VSSRC (CRXOR $lhs, $rhs), $tval, $fval)>;
let UseVSXReg = 1 in {
// VSX Elementary Scalar FP arithmetic (SP)
let isCommutable = 1 in {
def XSADDSP : XX3Form<60, 0,
@ -1469,7 +1464,6 @@ let AddedComplexity = 400 in { // Prefer VSX patterns over non-VSX patterns.
"xscvdpspn $XT, $XB", IIC_VecFP, []>;
def XSCVSPDPN : XX2Form<60, 331, (outs vssrc:$XT), (ins vsrc:$XB),
"xscvspdpn $XT, $XB", IIC_VecFP, []>;
} // UseVSXReg = 1
let Predicates = [IsLittleEndian] in {
def : Pat<DWToSPExtractConv.El0SS1,
@ -1516,7 +1510,7 @@ let AddedComplexity = 400 in { // Prefer VSX patterns over non-VSX patterns.
} // AddedComplexity = 400
} // HasP8Vector
let UseVSXReg = 1, AddedComplexity = 400 in {
let AddedComplexity = 400 in {
let Predicates = [HasDirectMove] in {
// VSX direct move instructions
def MFVSRD : XX1_RS6_RD5_XO<31, 51, (outs g8rc:$rA), (ins vsfrc:$XT),
@ -1524,7 +1518,7 @@ let Predicates = [HasDirectMove] in {
[(set i64:$rA, (PPCmfvsr f64:$XT))]>,
Requires<[In64BitMode]>;
let isCodeGenOnly = 1 in
def MFVRD : XX1_RS6_RD5_XO<31, 51, (outs g8rc:$rA), (ins vrrc:$XT),
def MFVRD : XX1_RS6_RD5_XO<31, 51, (outs g8rc:$rA), (ins vsrc:$XT),
"mfvsrd $rA, $XT", IIC_VecGeneral,
[]>,
Requires<[In64BitMode]>;
@ -1556,7 +1550,7 @@ let Predicates = [IsISA3_0, HasDirectMove] in {
[]>, Requires<[In64BitMode]>;
} // IsISA3_0, HasDirectMove
} // UseVSXReg = 1
} // AddedComplexity = 400
// We want to parse this from asm, but we don't want to emit this as it would
// be emitted with a VSX reg. So leave Emit = 0 here.
@ -2414,7 +2408,6 @@ let AddedComplexity = 400, Predicates = [HasP9Vector] in {
list<dag> pattern>
: X_VT5_XO5_VB5_VSFR<opcode, xo2, xo, opc, pattern>, isDOT;
let UseVSXReg = 1 in {
// [PO T XO B XO BX /]
class XX2_RT5_XO5_XB6<bits<6> opcode, bits<5> xo2, bits<9> xo, string opc,
list<dag> pattern>
@ -2433,7 +2426,6 @@ let AddedComplexity = 400, Predicates = [HasP9Vector] in {
InstrItinClass itin, list<dag> pattern>
: XX3Form<opcode, xo, (outs xty:$XT), (ins aty:$XA, bty:$XB),
!strconcat(opc, " $XT, $XA, $XB"), itin, pattern>;
} // UseVSXReg = 1
// [PO VRT VRA VRB XO /]
class X_VT5_VA5_VB5<bits<6> opcode, bits<10> xo, string opc,
@ -2571,8 +2563,7 @@ let AddedComplexity = 400, Predicates = [HasP9Vector] in {
// DP/QP Compare Exponents
def XSCMPEXPDP : XX3Form_1<60, 59,
(outs crrc:$crD), (ins vsfrc:$XA, vsfrc:$XB),
"xscmpexpdp $crD, $XA, $XB", IIC_FPCompare, []>,
UseVSXReg;
"xscmpexpdp $crD, $XA, $XB", IIC_FPCompare, []>;
def XSCMPEXPQP : X_BF3_VA5_VB5<63, 164, "xscmpexpqp", []>;
// DP Compare ==, >=, >, !=
@ -2630,7 +2621,6 @@ let AddedComplexity = 400, Predicates = [HasP9Vector] in {
def : Pat<(f128 (uint_to_fp (i32 (load xoaddr:$src)))),
(f128 (XSCVUDQP (LIWZX xoaddr:$src)))>;
let UseVSXReg = 1 in {
//===--------------------------------------------------------------------===//
// Round to Floating-Point Integer Instructions
@ -2647,8 +2637,6 @@ let AddedComplexity = 400, Predicates = [HasP9Vector] in {
[(set v4f32:$XT,
(int_ppc_vsx_xvcvsphp v4f32:$XB))]>;
} // UseVSXReg = 1
// Pattern for matching Vector HP -> Vector SP intrinsic. Defined as a
// separate pattern so that it can convert the input register class from
// VRRC(v8i16) to VSRC.
@ -2690,7 +2678,7 @@ let AddedComplexity = 400, Predicates = [HasP9Vector] in {
// Insert Exponent DP/QP
// XT NOTE: XT.dword[1] = 0xUUUU_UUUU_UUUU_UUUU
def XSIEXPDP : XX1Form <60, 918, (outs vsrc:$XT), (ins g8rc:$rA, g8rc:$rB),
"xsiexpdp $XT, $rA, $rB", IIC_VecFP, []>, UseVSXReg;
"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),
@ -2711,7 +2699,6 @@ let AddedComplexity = 400, Predicates = [HasP9Vector] in {
(v2i64 (XSXEXPQP $vA)), sub_64)))>;
// Vector Insert Word
let UseVSXReg = 1 in {
// XB NOTE: Only XB.dword[1] is used, but we use vsrc on XB.
def XXINSERTW :
XX2_RD6_UIM5_RS6<60, 181, (outs vsrc:$XT),
@ -2725,7 +2712,6 @@ let AddedComplexity = 400, Predicates = [HasP9Vector] in {
def XXEXTRACTUW : XX2_RD6_UIM5_RS6<60, 165,
(outs vsfrc:$XT), (ins vsrc:$XB, u4imm:$UIMM),
"xxextractuw $XT, $XB, $UIMM", IIC_VecFP, []>;
} // UseVSXReg = 1
// Vector Insert Exponent DP/SP
def XVIEXPDP : XX3_XT5_XA5_XB5<60, 248, "xviexpdp", vsrc, vsrc, vsrc,
@ -2758,20 +2744,17 @@ let AddedComplexity = 400, Predicates = [HasP9Vector] in {
//===--------------------------------------------------------------------===//
// Test Data Class SP/DP/QP
let UseVSXReg = 1 in {
def XSTSTDCSP : XX2_BF3_DCMX7_RS6<60, 298,
(outs crrc:$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, $DCMX", IIC_VecFP, []>;
} // UseVSXReg = 1
def XSTSTDCQP : X_BF3_DCMX7_RS5 <63, 708,
(outs crrc:$BF), (ins u7imm:$DCMX, vrrc:$vB),
"xststdcqp $BF, $vB, $DCMX", IIC_VecFP, []>;
// Vector Test Data Class SP/DP
let UseVSXReg = 1 in {
def XVTSTDCSP : XX2_RD6_DCMX7_RS6<60, 13, 5,
(outs vsrc:$XT), (ins u7imm:$DCMX, vsrc:$XB),
"xvtstdcsp $XT, $XB, $DCMX", IIC_VecFP,
@ -2782,7 +2765,6 @@ let AddedComplexity = 400, Predicates = [HasP9Vector] in {
"xvtstdcdp $XT, $XB, $DCMX", IIC_VecFP,
[(set v2i64: $XT,
(int_ppc_vsx_xvtstdcdp v2f64:$XB, imm:$DCMX))]>;
} // UseVSXReg = 1
//===--------------------------------------------------------------------===//
@ -2823,7 +2805,7 @@ let AddedComplexity = 400, Predicates = [HasP9Vector] in {
// Vector Splat Immediate Byte
def XXSPLTIB : X_RD6_IMM8<60, 360, (outs vsrc:$XT), (ins u8imm:$IMM8),
"xxspltib $XT, $IMM8", IIC_VecPerm, []>, UseVSXReg;
"xxspltib $XT, $IMM8", IIC_VecPerm, []>;
//===--------------------------------------------------------------------===//
// Vector/Scalar Load/Store Instructions
@ -2833,7 +2815,7 @@ let AddedComplexity = 400, Predicates = [HasP9Vector] in {
let mayLoad = 1, mayStore = 0 in {
// Load Vector
def LXV : DQ_RD6_RS5_DQ12<61, 1, (outs vsrc:$XT), (ins memrix16:$src),
"lxv $XT, $src", IIC_LdStLFD, []>, UseVSXReg;
"lxv $XT, $src", IIC_LdStLFD, []>;
// Load DWord
def LXSD : DSForm_1<57, 2, (outs vfrc:$vD), (ins memrix:$src),
"lxsd $vD, $src", IIC_LdStLFD, []>;
@ -2846,7 +2828,7 @@ let AddedComplexity = 400, Predicates = [HasP9Vector] in {
class X_XT6_RA5_RB5<bits<6> opcode, bits<10> xo, string opc,
RegisterOperand vtype, list<dag> pattern>
: XX1Form_memOp<opcode, xo, (outs vtype:$XT), (ins memrr:$src),
!strconcat(opc, " $XT, $src"), IIC_LdStLFD, pattern>, UseVSXReg;
!strconcat(opc, " $XT, $src"), IIC_LdStLFD, pattern>;
// Load as Integer Byte/Halfword & Zero Indexed
def LXSIBZX : X_XT6_RA5_RB5<31, 781, "lxsibzx", vsfrc,
@ -2864,12 +2846,10 @@ let AddedComplexity = 400, Predicates = [HasP9Vector] in {
// Load Vector (Left-justified) with Length
def LXVL : XX1Form_memOp<31, 269, (outs vsrc:$XT), (ins memr:$src, g8rc:$rB),
"lxvl $XT, $src, $rB", IIC_LdStLoad,
[(set v4i32:$XT, (int_ppc_vsx_lxvl addr:$src, i64:$rB))]>,
UseVSXReg;
[(set v4i32:$XT, (int_ppc_vsx_lxvl addr:$src, i64:$rB))]>;
def LXVLL : XX1Form_memOp<31,301, (outs vsrc:$XT), (ins memr:$src, g8rc:$rB),
"lxvll $XT, $src, $rB", IIC_LdStLoad,
[(set v4i32:$XT, (int_ppc_vsx_lxvll addr:$src, i64:$rB))]>,
UseVSXReg;
[(set v4i32:$XT, (int_ppc_vsx_lxvll addr:$src, i64:$rB))]>;
// Load Vector Word & Splat Indexed
def LXVWSX : X_XT6_RA5_RB5<31, 364, "lxvwsx" , vsrc, []>;
@ -2880,7 +2860,7 @@ let AddedComplexity = 400, Predicates = [HasP9Vector] in {
let mayStore = 1, mayLoad = 0 in {
// Store Vector
def STXV : DQ_RD6_RS5_DQ12<61, 5, (outs), (ins vsrc:$XT, memrix16:$dst),
"stxv $XT, $dst", IIC_LdStSTFD, []>, UseVSXReg;
"stxv $XT, $dst", IIC_LdStSTFD, []>;
// Store DWord
def STXSD : DSForm_1<61, 2, (outs), (ins vfrc:$vS, memrix:$dst),
"stxsd $vS, $dst", IIC_LdStSTFD, []>;
@ -2892,7 +2872,7 @@ let AddedComplexity = 400, Predicates = [HasP9Vector] in {
class X_XS6_RA5_RB5<bits<6> opcode, bits<10> xo, string opc,
RegisterOperand vtype, list<dag> pattern>
: XX1Form_memOp<opcode, xo, (outs), (ins vtype:$XT, memrr:$dst),
!strconcat(opc, " $XT, $dst"), IIC_LdStSTFD, pattern>, UseVSXReg;
!strconcat(opc, " $XT, $dst"), IIC_LdStSTFD, pattern>;
// Store as Integer Byte/Halfword Indexed
def STXSIBX : X_XS6_RA5_RB5<31, 909, "stxsibx" , vsfrc,
@ -2900,8 +2880,8 @@ let AddedComplexity = 400, Predicates = [HasP9Vector] in {
def STXSIHX : X_XS6_RA5_RB5<31, 941, "stxsihx" , vsfrc,
[(PPCstxsix f64:$XT, xoaddr:$dst, 2)]>;
let isCodeGenOnly = 1 in {
def STXSIBXv : X_XS6_RA5_RB5<31, 909, "stxsibx" , vrrc, []>;
def STXSIHXv : X_XS6_RA5_RB5<31, 941, "stxsihx" , vrrc, []>;
def STXSIBXv : X_XS6_RA5_RB5<31, 909, "stxsibx" , vsrc, []>;
def STXSIHXv : X_XS6_RA5_RB5<31, 941, "stxsihx" , vsrc, []>;
}
// Store Vector Halfword*8/Byte*16 Indexed
@ -2917,14 +2897,12 @@ let AddedComplexity = 400, Predicates = [HasP9Vector] in {
(ins vsrc:$XT, memr:$dst, g8rc:$rB),
"stxvl $XT, $dst, $rB", IIC_LdStLoad,
[(int_ppc_vsx_stxvl v4i32:$XT, addr:$dst,
i64:$rB)]>,
UseVSXReg;
i64:$rB)]>;
def STXVLL : XX1Form_memOp<31, 429, (outs),
(ins vsrc:$XT, memr:$dst, g8rc:$rB),
"stxvll $XT, $dst, $rB", IIC_LdStLoad,
[(int_ppc_vsx_stxvll v4i32:$XT, addr:$dst,
i64:$rB)]>,
UseVSXReg;
i64:$rB)]>;
} // mayStore
let Predicates = [IsLittleEndian] in {
@ -3158,109 +3136,109 @@ let AddedComplexity = 400, Predicates = [HasP9Vector] in {
let Predicates = [IsBigEndian, HasP9Vector] in {
// Scalar stores of i8
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 0)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 9)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 9)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 1)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 10)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 10)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 2)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 11)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 11)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 3)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 12)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 12)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 4)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 13)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 13)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 5)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 14)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 14)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 6)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 15)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 15)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 7)), xoaddr:$dst),
(STXSIBXv $S, xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS $S, VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 8)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 1)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 1)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 9)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 2)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 2)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 10)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 3)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 3)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 11)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 4)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 4)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 12)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 5)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 5)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 13)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 6)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 6)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 14)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 7)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 7)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 15)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 8)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 8)), VSRC), xoaddr:$dst)>;
// Scalar stores of i16
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 0)), xoaddr:$dst),
(STXSIHXv (v16i8 (VSLDOI $S, $S, 10)), xoaddr:$dst)>;
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 10)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 1)), xoaddr:$dst),
(STXSIHXv (v16i8 (VSLDOI $S, $S, 12)), xoaddr:$dst)>;
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 12)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 2)), xoaddr:$dst),
(STXSIHXv (v16i8 (VSLDOI $S, $S, 14)), xoaddr:$dst)>;
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 14)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 3)), xoaddr:$dst),
(STXSIHXv $S, xoaddr:$dst)>;
(STXSIHXv (COPY_TO_REGCLASS $S, VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 4)), xoaddr:$dst),
(STXSIHXv (v16i8 (VSLDOI $S, $S, 2)), xoaddr:$dst)>;
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 2)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 5)), xoaddr:$dst),
(STXSIHXv (v16i8 (VSLDOI $S, $S, 4)), xoaddr:$dst)>;
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 4)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 6)), xoaddr:$dst),
(STXSIHXv (v16i8 (VSLDOI $S, $S, 6)), xoaddr:$dst)>;
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 6)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 7)), xoaddr:$dst),
(STXSIHXv (v16i8 (VSLDOI $S, $S, 8)), xoaddr:$dst)>;
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 8)), VSRC), xoaddr:$dst)>;
} // IsBigEndian, HasP9Vector
let Predicates = [IsLittleEndian, HasP9Vector] in {
// Scalar stores of i8
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 0)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 8)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 8)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 1)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 7)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 7)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 2)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 6)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 6)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 3)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 5)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 5)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 4)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 4)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 4)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 5)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 3)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 3)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 6)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 2)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 2)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 7)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 1)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 1)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 8)), xoaddr:$dst),
(STXSIBXv $S, xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS $S, VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 9)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 15)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 15)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 10)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 14)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 14)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 11)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 13)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 13)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 12)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 12)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 12)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 13)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 11)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 11)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 14)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 10)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 10)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 15)), xoaddr:$dst),
(STXSIBXv (v16i8 (VSLDOI $S, $S, 9)), xoaddr:$dst)>;
(STXSIBXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 9)), VSRC), xoaddr:$dst)>;
// Scalar stores of i16
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 0)), xoaddr:$dst),
(STXSIHXv (v16i8 (VSLDOI $S, $S, 8)), xoaddr:$dst)>;
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 8)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 1)), xoaddr:$dst),
(STXSIHXv (v16i8 (VSLDOI $S, $S, 6)), xoaddr:$dst)>;
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 6)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 2)), xoaddr:$dst),
(STXSIHXv (v16i8 (VSLDOI $S, $S, 4)), xoaddr:$dst)>;
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 4)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 3)), xoaddr:$dst),
(STXSIHXv (v16i8 (VSLDOI $S, $S, 2)), xoaddr:$dst)>;
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 2)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 4)), xoaddr:$dst),
(STXSIHXv $S, xoaddr:$dst)>;
(STXSIHXv (COPY_TO_REGCLASS $S, VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 5)), xoaddr:$dst),
(STXSIHXv (v16i8 (VSLDOI $S, $S, 14)), xoaddr:$dst)>;
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 14)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 6)), xoaddr:$dst),
(STXSIHXv (v16i8 (VSLDOI $S, $S, 12)), xoaddr:$dst)>;
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 12)), VSRC), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 7)), xoaddr:$dst),
(STXSIHXv (v16i8 (VSLDOI $S, $S, 10)), xoaddr:$dst)>;
(STXSIHXv (COPY_TO_REGCLASS (v16i8 (VSLDOI $S, $S, 10)), VSRC), xoaddr:$dst)>;
} // IsLittleEndian, HasP9Vector

View File

@ -41,11 +41,11 @@ entry:
%splat.splat = shufflevector <4 x i32> %splat.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
ret <4 x i32> %splat.splat
; CHECK-LABEL: vecuiuc
; CHECK: lxsibzx 34, 0, 3
; CHECK-NEXT: xxspltw 34, 34, 1
; CHECK: lxsibzx 0, 0, 3
; CHECK-NEXT: xxspltw 34, 0, 1
; CHECK-BE-LABEL: vecuiuc
; CHECK-BE: lxsibzx 34, 0, 3
; CHECK-BE-NEXT: xxspltw 34, 34, 1
; CHECK-BE: lxsibzx 0, 0, 3
; CHECK-BE-NEXT: xxspltw 34, 0, 1
}
; Function Attrs: norecurse nounwind readonly
@ -104,11 +104,11 @@ entry:
%splat.splat = shufflevector <4 x i32> %splat.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
ret <4 x i32> %splat.splat
; CHECK-LABEL: vecsiuc
; CHECK: lxsibzx 34, 0, 3
; CHECK-NEXT: xxspltw 34, 34, 1
; CHECK: lxsibzx 0, 0, 3
; CHECK-NEXT: xxspltw 34, 0, 1
; CHECK-BE-LABEL: vecsiuc
; CHECK-BE: lxsibzx 34, 0, 3
; CHECK-BE-NEXT: xxspltw 34, 34, 1
; CHECK-BE: lxsibzx 0, 0, 3
; CHECK-BE-NEXT: xxspltw 34, 0, 1
}
; Function Attrs: norecurse nounwind readonly
@ -350,11 +350,11 @@ entry:
%splat.splat = shufflevector <4 x i32> %splat.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
ret <4 x i32> %splat.splat
; CHECK-LABEL: vecuius
; CHECK: lxsihzx 34, 0, 3
; CHECK-NEXT: xxspltw 34, 34, 1
; CHECK: lxsihzx 0, 0, 3
; CHECK-NEXT: xxspltw 34, 0, 1
; CHECK-BE-LABEL: vecuius
; CHECK-BE: lxsihzx 34, 0, 3
; CHECK-BE-NEXT: xxspltw 34, 34, 1
; CHECK-BE: lxsihzx 0, 0, 3
; CHECK-BE-NEXT: xxspltw 34, 0, 1
}
; Function Attrs: norecurse nounwind readonly
@ -414,11 +414,11 @@ entry:
%splat.splat = shufflevector <4 x i32> %splat.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
ret <4 x i32> %splat.splat
; CHECK-LABEL: vecsius
; CHECK: lxsihzx 34, 0, 3
; CHECK-NEXT: xxspltw 34, 34, 1
; CHECK: lxsihzx 0, 0, 3
; CHECK-NEXT: xxspltw 34, 0, 1
; CHECK-BE-LABEL: vecsius
; CHECK-BE: lxsihzx 34, 0, 3
; CHECK-BE-NEXT: xxspltw 34, 34, 1
; CHECK-BE: lxsihzx 0, 0, 3
; CHECK-BE-NEXT: xxspltw 34, 0, 1
}
; Function Attrs: norecurse nounwind readonly