let PrintMethod = "printNEONModImmOperand";
let ParserMatchClass = nImmSplatI32AsmOperand;
}
+def nImmSplatNotI16AsmOperand : AsmOperandClass { let Name = "NEONi16splatNot"; }
+def nImmSplatNotI16 : Operand<i32> {
+ let ParserMatchClass = nImmSplatNotI16AsmOperand;
+}
+def nImmSplatNotI32AsmOperand : AsmOperandClass { let Name = "NEONi32splatNot"; }
+def nImmSplatNotI32 : Operand<i32> {
+ let ParserMatchClass = nImmSplatNotI32AsmOperand;
+}
def nImmVMOVI32AsmOperand : AsmOperandClass { let Name = "NEONi32vmov"; }
def nImmVMOVI32 : Operand<i32> {
let PrintMethod = "printNEONModImmOperand";
let ParserMatchClass = nImmVMOVI32AsmOperand;
}
+
+def nImmVMOVI16AsmOperandByteReplicate :
+ AsmOperandClass {
+ let Name = "NEONi16vmovByteReplicate";
+ let PredicateMethod = "isNEONi16ByteReplicate";
+ let RenderMethod = "addNEONvmovByteReplicateOperands";
+}
+def nImmVMOVI32AsmOperandByteReplicate :
+ AsmOperandClass {
+ let Name = "NEONi32vmovByteReplicate";
+ let PredicateMethod = "isNEONi32ByteReplicate";
+ let RenderMethod = "addNEONvmovByteReplicateOperands";
+}
+def nImmVMVNI16AsmOperandByteReplicate :
+ AsmOperandClass {
+ let Name = "NEONi16invByteReplicate";
+ let PredicateMethod = "isNEONi16ByteReplicate";
+ let RenderMethod = "addNEONinvByteReplicateOperands";
+}
+def nImmVMVNI32AsmOperandByteReplicate :
+ AsmOperandClass {
+ let Name = "NEONi32invByteReplicate";
+ let PredicateMethod = "isNEONi32ByteReplicate";
+ let RenderMethod = "addNEONinvByteReplicateOperands";
+}
+
+def nImmVMOVI16ByteReplicate : Operand<i32> {
+ let PrintMethod = "printNEONModImmOperand";
+ let ParserMatchClass = nImmVMOVI16AsmOperandByteReplicate;
+}
+def nImmVMOVI32ByteReplicate : Operand<i32> {
+ let PrintMethod = "printNEONModImmOperand";
+ let ParserMatchClass = nImmVMOVI32AsmOperandByteReplicate;
+}
+def nImmVMVNI16ByteReplicate : Operand<i32> {
+ let PrintMethod = "printNEONModImmOperand";
+ let ParserMatchClass = nImmVMVNI16AsmOperandByteReplicate;
+}
+def nImmVMVNI32ByteReplicate : Operand<i32> {
+ let PrintMethod = "printNEONModImmOperand";
+ let ParserMatchClass = nImmVMVNI32AsmOperandByteReplicate;
+}
+
def nImmVMOVI32NegAsmOperand : AsmOperandClass { let Name = "NEONi32vmovNeg"; }
def nImmVMOVI32Neg : Operand<i32> {
let PrintMethod = "printNEONModImmOperand";
def : Pat<(dword_alignedstore (v2f64 QPR:$value), addrmode6:$addr),
(VST1q64 addrmode6:$addr, QPR:$value)>;
def : Pat<(v2f64 (word_alignedload addrmode6:$addr)),
- (VLD1q32 addrmode6:$addr)>;
+ (VLD1q32 addrmode6:$addr)>, Requires<[IsLE]>;
def : Pat<(word_alignedstore (v2f64 QPR:$value), addrmode6:$addr),
- (VST1q32 addrmode6:$addr, QPR:$value)>;
+ (VST1q32 addrmode6:$addr, QPR:$value)>, Requires<[IsLE]>;
def : Pat<(v2f64 (hword_alignedload addrmode6:$addr)),
(VLD1q16 addrmode6:$addr)>, Requires<[IsLE]>;
def : Pat<(hword_alignedstore (v2f64 QPR:$value), addrmode6:$addr),
InstrItinClass itin, string OpcodeStr, string Dt,
ValueType ResTy, ValueType OpTy, SDPatternOperator IntOp>
: N2Vnp<0b10, op17_16, op10_8, op7, 0, (outs DPR:$Vd), (ins DPR:$Vm),
- itin, OpcodeStr, Dt, ResTy, OpTy,
+ itin, OpcodeStr, Dt,
[(set DPR:$Vd, (ResTy (IntOp (OpTy DPR:$Vm))))]>;
class N2VQIntnp<bits<2> op17_16, bits<3> op10_8, bit op7,
InstrItinClass itin, string OpcodeStr, string Dt,
ValueType ResTy, ValueType OpTy, SDPatternOperator IntOp>
: N2Vnp<0b10, op17_16, op10_8, op7, 1, (outs QPR:$Vd), (ins QPR:$Vm),
- itin, OpcodeStr, Dt, ResTy, OpTy,
+ itin, OpcodeStr, Dt,
[(set QPR:$Vd, (ResTy (IntOp (OpTy QPR:$Vm))))]>;
// Similar to NV2VQIntnp with some more encoding bits exposed (crypto).
bit op7, InstrItinClass itin, string OpcodeStr, string Dt,
ValueType ResTy, ValueType OpTy, SDPatternOperator IntOp>
: N2Vnp<op19_18, op17_16, op10_8, op7, op6, (outs QPR:$Vd), (ins QPR:$Vm),
- itin, OpcodeStr, Dt, ResTy, OpTy,
+ itin, OpcodeStr, Dt,
[(set QPR:$Vd, (ResTy (IntOp (OpTy QPR:$Vm))))]>;
// Same as N2VQIntXnp but with Vd as a src register.
ValueType ResTy, ValueType OpTy, SDPatternOperator IntOp>
: N2Vnp<op19_18, op17_16, op10_8, op7, op6,
(outs QPR:$Vd), (ins QPR:$src, QPR:$Vm),
- itin, OpcodeStr, Dt, ResTy, OpTy,
+ itin, OpcodeStr, Dt,
[(set QPR:$Vd, (ResTy (IntOp (OpTy QPR:$src), (OpTy QPR:$Vm))))]> {
let Constraints = "$src = $Vd";
}
SDPatternOperator IntOp, bit Commutable>
: N3Vnp<op27_23, op21_20, op11_8, op6, op4,
(outs DPR:$Vd), (ins DPR:$Vn, DPR:$Vm), N3RegFrm, itin, OpcodeStr, Dt,
- ResTy, OpTy, IntOp, Commutable,
[(set DPR:$Vd, (ResTy (IntOp (OpTy DPR:$Vn), (OpTy DPR:$Vm))))]>;
class N3VDIntSL<bits<2> op21_20, bits<4> op11_8, InstrItinClass itin,
SDPatternOperator IntOp, bit Commutable>
: N3Vnp<op27_23, op21_20, op11_8, op6, op4,
(outs QPR:$Vd), (ins QPR:$Vn, QPR:$Vm), f, itin, OpcodeStr, Dt,
- ResTy, OpTy, IntOp, Commutable,
[(set QPR:$Vd, (ResTy (IntOp (OpTy QPR:$Vn), (OpTy QPR:$Vm))))]>;
// Same as N3VQIntnp but with Vd as a src register.
string Dt, ValueType ResTy, ValueType OpTy,
SDPatternOperator IntOp, bit Commutable>
: N3Vnp<op27_23, op21_20, op11_8, op6, op4,
- (outs QPR:$Vd), (ins QPR:$src, QPR:$Vn, QPR:$Vm), f, itin, OpcodeStr,
- Dt, ResTy, OpTy, IntOp, Commutable,
+ (outs QPR:$Vd), (ins QPR:$src, QPR:$Vn, QPR:$Vm),
+ f, itin, OpcodeStr, Dt,
[(set QPR:$Vd, (ResTy (IntOp (OpTy QPR:$src), (OpTy QPR:$Vn),
(OpTy QPR:$Vm))))]> {
let Constraints = "$src = $Vd";
SDPatternOperator IntOp, bit Commutable>
: N3Vnp<op27_23, op21_20, op11_8, op6, op4,
(outs QPR:$Vd), (ins DPR:$Vn, DPR:$Vm), N3RegFrm, itin, OpcodeStr, Dt,
- ResTy, OpTy, IntOp, Commutable,
[(set QPR:$Vd, (ResTy (IntOp (OpTy DPR:$Vn), (OpTy DPR:$Vm))))]>;
class N3VLIntSL<bit op24, bits<2> op21_20, bits<4> op11_8, InstrItinClass itin,
// VQDMLSL : Vector Saturating Doubling Multiply Subtract Long (Q -= D * D)
defm VQDMLSL : N3VLInt3_HS<0, 1, 0b1011, 0, IIC_VMACi16D, IIC_VMACi32D,
"vqdmlsl", "s", null_frag>;
-defm VQDMLSLsl: N3VLInt3SL_HS<0, 0b111, "vqdmlsl", "s", null_frag>;
+defm VQDMLSLsl: N3VLInt3SL_HS<0, 0b0111, "vqdmlsl", "s", null_frag>;
def : Pat<(v4i32 (int_arm_neon_vqsubs (v4i32 QPR:$src1),
(v4i32 (int_arm_neon_vqdmull (v4i16 DPR:$Vn),
[(set QPR:$Vd, (v4f32 (NEONvmovFPImm timm:$SIMM)))]>;
} // isReMaterializable
+// Add support for bytes replication feature, so it could be GAS compatible.
+// E.g. instructions below:
+// "vmov.i32 d0, 0xffffffff"
+// "vmov.i32 d0, 0xabababab"
+// "vmov.i16 d0, 0xabab"
+// are incorrect, but we could deal with such cases.
+// For last two instructions, for example, it should emit:
+// "vmov.i8 d0, 0xab"
+def : NEONInstAlias<"vmov${p}.i16 $Vd, $Vm",
+ (VMOVv8i8 DPR:$Vd, nImmVMOVI16ByteReplicate:$Vm, pred:$p)>;
+def : NEONInstAlias<"vmov${p}.i32 $Vd, $Vm",
+ (VMOVv8i8 DPR:$Vd, nImmVMOVI32ByteReplicate:$Vm, pred:$p)>;
+def : NEONInstAlias<"vmov${p}.i16 $Vd, $Vm",
+ (VMOVv16i8 QPR:$Vd, nImmVMOVI16ByteReplicate:$Vm, pred:$p)>;
+def : NEONInstAlias<"vmov${p}.i32 $Vd, $Vm",
+ (VMOVv16i8 QPR:$Vd, nImmVMOVI32ByteReplicate:$Vm, pred:$p)>;
+
+// Also add same support for VMVN instructions. So instruction:
+// "vmvn.i32 d0, 0xabababab"
+// actually means:
+// "vmov.i8 d0, 0x54"
+def : NEONInstAlias<"vmvn${p}.i16 $Vd, $Vm",
+ (VMOVv8i8 DPR:$Vd, nImmVMVNI16ByteReplicate:$Vm, pred:$p)>;
+def : NEONInstAlias<"vmvn${p}.i32 $Vd, $Vm",
+ (VMOVv8i8 DPR:$Vd, nImmVMVNI32ByteReplicate:$Vm, pred:$p)>;
+def : NEONInstAlias<"vmvn${p}.i16 $Vd, $Vm",
+ (VMOVv16i8 QPR:$Vd, nImmVMVNI16ByteReplicate:$Vm, pred:$p)>;
+def : NEONInstAlias<"vmvn${p}.i32 $Vd, $Vm",
+ (VMOVv16i8 QPR:$Vd, nImmVMVNI32ByteReplicate:$Vm, pred:$p)>;
// On some CPUs the two instructions "vmov.i32 dD, #0" and "vmov.i32 qD, #0"
// require zero cycles to execute so they should be used wherever possible for
[(set DPR:$V, (insertelt (v2i32 DPR:$src1),
GPR:$R, imm:$lane))]> {
let Inst{21} = lane{0};
+ // This instruction is equivalent as
+ // $V = INSERT_SUBREG $src1, $R, translateImmToSubIdx($imm)
+ let isInsertSubreg = 1;
}
}
def : Pat<(vector_insert (v16i8 QPR:$src1), GPR:$src2, imm:$lane),
//===----------------------------------------------------------------------===//
// bit_convert
-def : Pat<(v1i64 (bitconvert (v2i32 DPR:$src))), (v1i64 DPR:$src)>;
-def : Pat<(v1i64 (bitconvert (v4i16 DPR:$src))), (v1i64 DPR:$src)>;
-def : Pat<(v1i64 (bitconvert (v8i8 DPR:$src))), (v1i64 DPR:$src)>;
+let Predicates = [IsLE] in {
+ def : Pat<(v1i64 (bitconvert (v2i32 DPR:$src))), (v1i64 DPR:$src)>;
+ def : Pat<(v1i64 (bitconvert (v4i16 DPR:$src))), (v1i64 DPR:$src)>;
+ def : Pat<(v1i64 (bitconvert (v8i8 DPR:$src))), (v1i64 DPR:$src)>;
+}
def : Pat<(v1i64 (bitconvert (f64 DPR:$src))), (v1i64 DPR:$src)>;
-def : Pat<(v1i64 (bitconvert (v2f32 DPR:$src))), (v1i64 DPR:$src)>;
-def : Pat<(v2i32 (bitconvert (v1i64 DPR:$src))), (v2i32 DPR:$src)>;
-def : Pat<(v2i32 (bitconvert (v4i16 DPR:$src))), (v2i32 DPR:$src)>;
-def : Pat<(v2i32 (bitconvert (v8i8 DPR:$src))), (v2i32 DPR:$src)>;
-def : Pat<(v2i32 (bitconvert (f64 DPR:$src))), (v2i32 DPR:$src)>;
+let Predicates = [IsLE] in {
+ def : Pat<(v1i64 (bitconvert (v2f32 DPR:$src))), (v1i64 DPR:$src)>;
+ def : Pat<(v2i32 (bitconvert (v1i64 DPR:$src))), (v2i32 DPR:$src)>;
+ def : Pat<(v2i32 (bitconvert (v4i16 DPR:$src))), (v2i32 DPR:$src)>;
+ def : Pat<(v2i32 (bitconvert (v8i8 DPR:$src))), (v2i32 DPR:$src)>;
+ def : Pat<(v2i32 (bitconvert (f64 DPR:$src))), (v2i32 DPR:$src)>;
+}
def : Pat<(v2i32 (bitconvert (v2f32 DPR:$src))), (v2i32 DPR:$src)>;
-def : Pat<(v4i16 (bitconvert (v1i64 DPR:$src))), (v4i16 DPR:$src)>;
-def : Pat<(v4i16 (bitconvert (v2i32 DPR:$src))), (v4i16 DPR:$src)>;
-def : Pat<(v4i16 (bitconvert (v8i8 DPR:$src))), (v4i16 DPR:$src)>;
-def : Pat<(v4i16 (bitconvert (f64 DPR:$src))), (v4i16 DPR:$src)>;
-def : Pat<(v4i16 (bitconvert (v2f32 DPR:$src))), (v4i16 DPR:$src)>;
-def : Pat<(v8i8 (bitconvert (v1i64 DPR:$src))), (v8i8 DPR:$src)>;
-def : Pat<(v8i8 (bitconvert (v2i32 DPR:$src))), (v8i8 DPR:$src)>;
-def : Pat<(v8i8 (bitconvert (v4i16 DPR:$src))), (v8i8 DPR:$src)>;
-def : Pat<(v8i8 (bitconvert (f64 DPR:$src))), (v8i8 DPR:$src)>;
-def : Pat<(v8i8 (bitconvert (v2f32 DPR:$src))), (v8i8 DPR:$src)>;
+let Predicates = [IsLE] in {
+ def : Pat<(v4i16 (bitconvert (v1i64 DPR:$src))), (v4i16 DPR:$src)>;
+ def : Pat<(v4i16 (bitconvert (v2i32 DPR:$src))), (v4i16 DPR:$src)>;
+ def : Pat<(v4i16 (bitconvert (v8i8 DPR:$src))), (v4i16 DPR:$src)>;
+ def : Pat<(v4i16 (bitconvert (f64 DPR:$src))), (v4i16 DPR:$src)>;
+ def : Pat<(v4i16 (bitconvert (v2f32 DPR:$src))), (v4i16 DPR:$src)>;
+ def : Pat<(v8i8 (bitconvert (v1i64 DPR:$src))), (v8i8 DPR:$src)>;
+ def : Pat<(v8i8 (bitconvert (v2i32 DPR:$src))), (v8i8 DPR:$src)>;
+ def : Pat<(v8i8 (bitconvert (v4i16 DPR:$src))), (v8i8 DPR:$src)>;
+ def : Pat<(v8i8 (bitconvert (f64 DPR:$src))), (v8i8 DPR:$src)>;
+ def : Pat<(v8i8 (bitconvert (v2f32 DPR:$src))), (v8i8 DPR:$src)>;
+}
def : Pat<(f64 (bitconvert (v1i64 DPR:$src))), (f64 DPR:$src)>;
-def : Pat<(f64 (bitconvert (v2i32 DPR:$src))), (f64 DPR:$src)>;
-def : Pat<(f64 (bitconvert (v4i16 DPR:$src))), (f64 DPR:$src)>;
-def : Pat<(f64 (bitconvert (v8i8 DPR:$src))), (f64 DPR:$src)>;
-def : Pat<(f64 (bitconvert (v2f32 DPR:$src))), (f64 DPR:$src)>;
-def : Pat<(v2f32 (bitconvert (f64 DPR:$src))), (v2f32 DPR:$src)>;
-def : Pat<(v2f32 (bitconvert (v1i64 DPR:$src))), (v2f32 DPR:$src)>;
+let Predicates = [IsLE] in {
+ def : Pat<(f64 (bitconvert (v2i32 DPR:$src))), (f64 DPR:$src)>;
+ def : Pat<(f64 (bitconvert (v4i16 DPR:$src))), (f64 DPR:$src)>;
+ def : Pat<(f64 (bitconvert (v8i8 DPR:$src))), (f64 DPR:$src)>;
+ def : Pat<(f64 (bitconvert (v2f32 DPR:$src))), (f64 DPR:$src)>;
+ def : Pat<(v2f32 (bitconvert (f64 DPR:$src))), (v2f32 DPR:$src)>;
+ def : Pat<(v2f32 (bitconvert (v1i64 DPR:$src))), (v2f32 DPR:$src)>;
+}
def : Pat<(v2f32 (bitconvert (v2i32 DPR:$src))), (v2f32 DPR:$src)>;
-def : Pat<(v2f32 (bitconvert (v4i16 DPR:$src))), (v2f32 DPR:$src)>;
-def : Pat<(v2f32 (bitconvert (v8i8 DPR:$src))), (v2f32 DPR:$src)>;
+let Predicates = [IsLE] in {
+ def : Pat<(v2f32 (bitconvert (v4i16 DPR:$src))), (v2f32 DPR:$src)>;
+ def : Pat<(v2f32 (bitconvert (v8i8 DPR:$src))), (v2f32 DPR:$src)>;
+}
-def : Pat<(v2i64 (bitconvert (v4i32 QPR:$src))), (v2i64 QPR:$src)>;
-def : Pat<(v2i64 (bitconvert (v8i16 QPR:$src))), (v2i64 QPR:$src)>;
-def : Pat<(v2i64 (bitconvert (v16i8 QPR:$src))), (v2i64 QPR:$src)>;
+let Predicates = [IsLE] in {
+ def : Pat<(v2i64 (bitconvert (v4i32 QPR:$src))), (v2i64 QPR:$src)>;
+ def : Pat<(v2i64 (bitconvert (v8i16 QPR:$src))), (v2i64 QPR:$src)>;
+ def : Pat<(v2i64 (bitconvert (v16i8 QPR:$src))), (v2i64 QPR:$src)>;
+}
def : Pat<(v2i64 (bitconvert (v2f64 QPR:$src))), (v2i64 QPR:$src)>;
-def : Pat<(v2i64 (bitconvert (v4f32 QPR:$src))), (v2i64 QPR:$src)>;
-def : Pat<(v4i32 (bitconvert (v2i64 QPR:$src))), (v4i32 QPR:$src)>;
-def : Pat<(v4i32 (bitconvert (v8i16 QPR:$src))), (v4i32 QPR:$src)>;
-def : Pat<(v4i32 (bitconvert (v16i8 QPR:$src))), (v4i32 QPR:$src)>;
-def : Pat<(v4i32 (bitconvert (v2f64 QPR:$src))), (v4i32 QPR:$src)>;
+let Predicates = [IsLE] in {
+ def : Pat<(v2i64 (bitconvert (v4f32 QPR:$src))), (v2i64 QPR:$src)>;
+ def : Pat<(v4i32 (bitconvert (v2i64 QPR:$src))), (v4i32 QPR:$src)>;
+ def : Pat<(v4i32 (bitconvert (v8i16 QPR:$src))), (v4i32 QPR:$src)>;
+ def : Pat<(v4i32 (bitconvert (v16i8 QPR:$src))), (v4i32 QPR:$src)>;
+ def : Pat<(v4i32 (bitconvert (v2f64 QPR:$src))), (v4i32 QPR:$src)>;
+}
def : Pat<(v4i32 (bitconvert (v4f32 QPR:$src))), (v4i32 QPR:$src)>;
-def : Pat<(v8i16 (bitconvert (v2i64 QPR:$src))), (v8i16 QPR:$src)>;
-def : Pat<(v8i16 (bitconvert (v4i32 QPR:$src))), (v8i16 QPR:$src)>;
-def : Pat<(v8i16 (bitconvert (v16i8 QPR:$src))), (v8i16 QPR:$src)>;
-def : Pat<(v8i16 (bitconvert (v2f64 QPR:$src))), (v8i16 QPR:$src)>;
-def : Pat<(v8i16 (bitconvert (v4f32 QPR:$src))), (v8i16 QPR:$src)>;
-def : Pat<(v16i8 (bitconvert (v2i64 QPR:$src))), (v16i8 QPR:$src)>;
-def : Pat<(v16i8 (bitconvert (v4i32 QPR:$src))), (v16i8 QPR:$src)>;
-def : Pat<(v16i8 (bitconvert (v8i16 QPR:$src))), (v16i8 QPR:$src)>;
-def : Pat<(v16i8 (bitconvert (v2f64 QPR:$src))), (v16i8 QPR:$src)>;
-def : Pat<(v16i8 (bitconvert (v4f32 QPR:$src))), (v16i8 QPR:$src)>;
-def : Pat<(v4f32 (bitconvert (v2i64 QPR:$src))), (v4f32 QPR:$src)>;
+let Predicates = [IsLE] in {
+ def : Pat<(v8i16 (bitconvert (v2i64 QPR:$src))), (v8i16 QPR:$src)>;
+ def : Pat<(v8i16 (bitconvert (v4i32 QPR:$src))), (v8i16 QPR:$src)>;
+ def : Pat<(v8i16 (bitconvert (v16i8 QPR:$src))), (v8i16 QPR:$src)>;
+ def : Pat<(v8i16 (bitconvert (v2f64 QPR:$src))), (v8i16 QPR:$src)>;
+ def : Pat<(v8i16 (bitconvert (v4f32 QPR:$src))), (v8i16 QPR:$src)>;
+ def : Pat<(v16i8 (bitconvert (v2i64 QPR:$src))), (v16i8 QPR:$src)>;
+ def : Pat<(v16i8 (bitconvert (v4i32 QPR:$src))), (v16i8 QPR:$src)>;
+ def : Pat<(v16i8 (bitconvert (v8i16 QPR:$src))), (v16i8 QPR:$src)>;
+ def : Pat<(v16i8 (bitconvert (v2f64 QPR:$src))), (v16i8 QPR:$src)>;
+ def : Pat<(v16i8 (bitconvert (v4f32 QPR:$src))), (v16i8 QPR:$src)>;
+ def : Pat<(v4f32 (bitconvert (v2i64 QPR:$src))), (v4f32 QPR:$src)>;
+}
def : Pat<(v4f32 (bitconvert (v4i32 QPR:$src))), (v4f32 QPR:$src)>;
-def : Pat<(v4f32 (bitconvert (v8i16 QPR:$src))), (v4f32 QPR:$src)>;
-def : Pat<(v4f32 (bitconvert (v16i8 QPR:$src))), (v4f32 QPR:$src)>;
-def : Pat<(v4f32 (bitconvert (v2f64 QPR:$src))), (v4f32 QPR:$src)>;
+let Predicates = [IsLE] in {
+ def : Pat<(v4f32 (bitconvert (v8i16 QPR:$src))), (v4f32 QPR:$src)>;
+ def : Pat<(v4f32 (bitconvert (v16i8 QPR:$src))), (v4f32 QPR:$src)>;
+ def : Pat<(v4f32 (bitconvert (v2f64 QPR:$src))), (v4f32 QPR:$src)>;
+}
def : Pat<(v2f64 (bitconvert (v2i64 QPR:$src))), (v2f64 QPR:$src)>;
-def : Pat<(v2f64 (bitconvert (v4i32 QPR:$src))), (v2f64 QPR:$src)>;
-def : Pat<(v2f64 (bitconvert (v8i16 QPR:$src))), (v2f64 QPR:$src)>;
-def : Pat<(v2f64 (bitconvert (v16i8 QPR:$src))), (v2f64 QPR:$src)>;
-def : Pat<(v2f64 (bitconvert (v4f32 QPR:$src))), (v2f64 QPR:$src)>;
+let Predicates = [IsLE] in {
+ def : Pat<(v2f64 (bitconvert (v4i32 QPR:$src))), (v2f64 QPR:$src)>;
+ def : Pat<(v2f64 (bitconvert (v8i16 QPR:$src))), (v2f64 QPR:$src)>;
+ def : Pat<(v2f64 (bitconvert (v16i8 QPR:$src))), (v2f64 QPR:$src)>;
+ def : Pat<(v2f64 (bitconvert (v4f32 QPR:$src))), (v2f64 QPR:$src)>;
+}
+
+let Predicates = [IsBE] in {
+ // 64 bit conversions
+ def : Pat<(v1i64 (bitconvert (v2i32 DPR:$src))), (VREV64d32 DPR:$src)>;
+ def : Pat<(v1i64 (bitconvert (v4i16 DPR:$src))), (VREV64d16 DPR:$src)>;
+ def : Pat<(v1i64 (bitconvert (v8i8 DPR:$src))), (VREV64d8 DPR:$src)>;
+ def : Pat<(v1i64 (bitconvert (v2f32 DPR:$src))), (VREV64d32 DPR:$src)>;
+ def : Pat<(v2i32 (bitconvert (v1i64 DPR:$src))), (VREV64d32 DPR:$src)>;
+ def : Pat<(v2i32 (bitconvert (v4i16 DPR:$src))), (VREV32d16 DPR:$src)>;
+ def : Pat<(v2i32 (bitconvert (v8i8 DPR:$src))), (VREV32d8 DPR:$src)>;
+ def : Pat<(v2i32 (bitconvert (f64 DPR:$src))), (VREV64d32 DPR:$src)>;
+ def : Pat<(v4i16 (bitconvert (v1i64 DPR:$src))), (VREV64d16 DPR:$src)>;
+ def : Pat<(v4i16 (bitconvert (v2i32 DPR:$src))), (VREV32d16 DPR:$src)>;
+ def : Pat<(v4i16 (bitconvert (v8i8 DPR:$src))), (VREV16d8 DPR:$src)>;
+ def : Pat<(v4i16 (bitconvert (f64 DPR:$src))), (VREV64d16 DPR:$src)>;
+ def : Pat<(v4i16 (bitconvert (v2f32 DPR:$src))), (VREV32d16 DPR:$src)>;
+ def : Pat<(v8i8 (bitconvert (v1i64 DPR:$src))), (VREV64d8 DPR:$src)>;
+ def : Pat<(v8i8 (bitconvert (v2i32 DPR:$src))), (VREV32d8 DPR:$src)>;
+ def : Pat<(v8i8 (bitconvert (v4i16 DPR:$src))), (VREV16d8 DPR:$src)>;
+ def : Pat<(v8i8 (bitconvert (f64 DPR:$src))), (VREV64d8 DPR:$src)>;
+ def : Pat<(v8i8 (bitconvert (v2f32 DPR:$src))), (VREV32d8 DPR:$src)>;
+ def : Pat<(f64 (bitconvert (v2i32 DPR:$src))), (VREV64d32 DPR:$src)>;
+ def : Pat<(f64 (bitconvert (v4i16 DPR:$src))), (VREV64d16 DPR:$src)>;
+ def : Pat<(f64 (bitconvert (v8i8 DPR:$src))), (VREV64d8 DPR:$src)>;
+ def : Pat<(f64 (bitconvert (v2f32 DPR:$src))), (VREV64d32 DPR:$src)>;
+ def : Pat<(v2f32 (bitconvert (f64 DPR:$src))), (VREV64d32 DPR:$src)>;
+ def : Pat<(v2f32 (bitconvert (v1i64 DPR:$src))), (VREV64d32 DPR:$src)>;
+ def : Pat<(v2f32 (bitconvert (v4i16 DPR:$src))), (VREV32d16 DPR:$src)>;
+ def : Pat<(v2f32 (bitconvert (v8i8 DPR:$src))), (VREV32d8 DPR:$src)>;
+
+ // 128 bit conversions
+ def : Pat<(v2i64 (bitconvert (v4i32 QPR:$src))), (VREV64q32 QPR:$src)>;
+ def : Pat<(v2i64 (bitconvert (v8i16 QPR:$src))), (VREV64q16 QPR:$src)>;
+ def : Pat<(v2i64 (bitconvert (v16i8 QPR:$src))), (VREV64q8 QPR:$src)>;
+ def : Pat<(v2i64 (bitconvert (v4f32 QPR:$src))), (VREV64q32 QPR:$src)>;
+ def : Pat<(v4i32 (bitconvert (v2i64 QPR:$src))), (VREV64q32 QPR:$src)>;
+ def : Pat<(v4i32 (bitconvert (v8i16 QPR:$src))), (VREV32q16 QPR:$src)>;
+ def : Pat<(v4i32 (bitconvert (v16i8 QPR:$src))), (VREV32q8 QPR:$src)>;
+ def : Pat<(v4i32 (bitconvert (v2f64 QPR:$src))), (VREV64q32 QPR:$src)>;
+ def : Pat<(v8i16 (bitconvert (v2i64 QPR:$src))), (VREV64q16 QPR:$src)>;
+ def : Pat<(v8i16 (bitconvert (v4i32 QPR:$src))), (VREV32q16 QPR:$src)>;
+ def : Pat<(v8i16 (bitconvert (v16i8 QPR:$src))), (VREV16q8 QPR:$src)>;
+ def : Pat<(v8i16 (bitconvert (v2f64 QPR:$src))), (VREV64q16 QPR:$src)>;
+ def : Pat<(v8i16 (bitconvert (v4f32 QPR:$src))), (VREV32q16 QPR:$src)>;
+ def : Pat<(v16i8 (bitconvert (v2i64 QPR:$src))), (VREV64q8 QPR:$src)>;
+ def : Pat<(v16i8 (bitconvert (v4i32 QPR:$src))), (VREV32q8 QPR:$src)>;
+ def : Pat<(v16i8 (bitconvert (v8i16 QPR:$src))), (VREV16q8 QPR:$src)>;
+ def : Pat<(v16i8 (bitconvert (v2f64 QPR:$src))), (VREV64q8 QPR:$src)>;
+ def : Pat<(v16i8 (bitconvert (v4f32 QPR:$src))), (VREV32q8 QPR:$src)>;
+ def : Pat<(v4f32 (bitconvert (v2i64 QPR:$src))), (VREV64q32 QPR:$src)>;
+ def : Pat<(v4f32 (bitconvert (v8i16 QPR:$src))), (VREV32q16 QPR:$src)>;
+ def : Pat<(v4f32 (bitconvert (v16i8 QPR:$src))), (VREV32q8 QPR:$src)>;
+ def : Pat<(v4f32 (bitconvert (v2f64 QPR:$src))), (VREV64q32 QPR:$src)>;
+ def : Pat<(v2f64 (bitconvert (v4i32 QPR:$src))), (VREV64q32 QPR:$src)>;
+ def : Pat<(v2f64 (bitconvert (v8i16 QPR:$src))), (VREV64q16 QPR:$src)>;
+ def : Pat<(v2f64 (bitconvert (v16i8 QPR:$src))), (VREV64q8 QPR:$src)>;
+ def : Pat<(v2f64 (bitconvert (v4f32 QPR:$src))), (VREV64q32 QPR:$src)>;
+}
// Fold extracting an element out of a v2i32 into a vfp register.
def : Pat<(f32 (bitconvert (i32 (extractelt (v2i32 DPR:$src), imm:$lane)))),
dsub_0)>;
}
+// The following class definition is basically a copy of the
+// Lengthen_HalfSingle definition above, however with an additional parameter
+// "RevLanes" to select the correct VREV32dXX instruction. This is to convert
+// data loaded by VLD1LN into proper vector format in big endian mode.
+multiclass Lengthen_HalfSingle_Big_Endian<string DestLanes, string DestTy, string SrcTy,
+ string InsnLanes, string InsnTy, string RevLanes> {
+ def _Any : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
+ (!cast<PatFrag>("extloadv" # SrcTy) addrmode6oneL32:$addr)),
+ (EXTRACT_SUBREG (!cast<Instruction>("VMOVLuv" # InsnLanes # InsnTy)
+ (!cast<Instruction>("VREV32d" # RevLanes)
+ (VLD1LNd32 addrmode6oneL32:$addr, (f64 (IMPLICIT_DEF)), (i32 0)))),
+ dsub_0)>;
+ def _Z : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
+ (!cast<PatFrag>("zextloadv" # SrcTy) addrmode6oneL32:$addr)),
+ (EXTRACT_SUBREG (!cast<Instruction>("VMOVLuv" # InsnLanes # InsnTy)
+ (!cast<Instruction>("VREV32d" # RevLanes)
+ (VLD1LNd32 addrmode6oneL32:$addr, (f64 (IMPLICIT_DEF)), (i32 0)))),
+ dsub_0)>;
+ def _S : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
+ (!cast<PatFrag>("sextloadv" # SrcTy) addrmode6oneL32:$addr)),
+ (EXTRACT_SUBREG (!cast<Instruction>("VMOVLsv" # InsnLanes # InsnTy)
+ (!cast<Instruction>("VREV32d" # RevLanes)
+ (VLD1LNd32 addrmode6oneL32:$addr, (f64 (IMPLICIT_DEF)), (i32 0)))),
+ dsub_0)>;
+}
+
// extload, zextload and sextload for a lengthening load followed by another
// lengthening load, to quadruple the initial length.
//
dsub_0))>;
}
+// The following class definition is basically a copy of the
+// Lengthen_Double definition above, however with an additional parameter
+// "RevLanes" to select the correct VREV32dXX instruction. This is to convert
+// data loaded by VLD1LN into proper vector format in big endian mode.
+multiclass Lengthen_Double_Big_Endian<string DestLanes, string DestTy, string SrcTy,
+ string Insn1Lanes, string Insn1Ty, string Insn2Lanes,
+ string Insn2Ty, string RevLanes> {
+ def _Any : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
+ (!cast<PatFrag>("extloadv" # SrcTy) addrmode6oneL32:$addr)),
+ (!cast<Instruction>("VMOVLuv" # Insn2Lanes # Insn2Ty)
+ (EXTRACT_SUBREG (!cast<Instruction>("VMOVLuv" # Insn1Lanes # Insn1Ty)
+ (!cast<Instruction>("VREV32d" # RevLanes)
+ (VLD1LNd32 addrmode6oneL32:$addr, (f64 (IMPLICIT_DEF)), (i32 0)))),
+ dsub_0))>;
+ def _Z : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
+ (!cast<PatFrag>("zextloadv" # SrcTy) addrmode6oneL32:$addr)),
+ (!cast<Instruction>("VMOVLuv" # Insn2Lanes # Insn2Ty)
+ (EXTRACT_SUBREG (!cast<Instruction>("VMOVLuv" # Insn1Lanes # Insn1Ty)
+ (!cast<Instruction>("VREV32d" # RevLanes)
+ (VLD1LNd32 addrmode6oneL32:$addr, (f64 (IMPLICIT_DEF)), (i32 0)))),
+ dsub_0))>;
+ def _S : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
+ (!cast<PatFrag>("sextloadv" # SrcTy) addrmode6oneL32:$addr)),
+ (!cast<Instruction>("VMOVLsv" # Insn2Lanes # Insn2Ty)
+ (EXTRACT_SUBREG (!cast<Instruction>("VMOVLsv" # Insn1Lanes # Insn1Ty)
+ (!cast<Instruction>("VREV32d" # RevLanes)
+ (VLD1LNd32 addrmode6oneL32:$addr, (f64 (IMPLICIT_DEF)), (i32 0)))),
+ dsub_0))>;
+}
+
// extload, zextload and sextload for a lengthening load followed by another
// lengthening load, to quadruple the initial length, but which ends up only
// requiring half the available lanes (a 64-bit outcome instead of a 128-bit).
dsub_0)>;
}
+// The following class definition is basically a copy of the
+// Lengthen_HalfDouble definition above, however with an additional VREV16d8
+// instruction to convert data loaded by VLD1LN into proper vector format
+// in big endian mode.
+multiclass Lengthen_HalfDouble_Big_Endian<string DestLanes, string DestTy, string SrcTy,
+ string Insn1Lanes, string Insn1Ty, string Insn2Lanes,
+ string Insn2Ty> {
+ def _Any : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
+ (!cast<PatFrag>("extloadv" # SrcTy) addrmode6:$addr)),
+ (EXTRACT_SUBREG (!cast<Instruction>("VMOVLuv" # Insn2Lanes # Insn2Ty)
+ (EXTRACT_SUBREG (!cast<Instruction>("VMOVLuv" # Insn1Lanes # Insn1Ty)
+ (!cast<Instruction>("VREV16d8")
+ (VLD1LNd16 addrmode6:$addr, (f64 (IMPLICIT_DEF)), (i32 0)))),
+ dsub_0)),
+ dsub_0)>;
+ def _Z : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
+ (!cast<PatFrag>("zextloadv" # SrcTy) addrmode6:$addr)),
+ (EXTRACT_SUBREG (!cast<Instruction>("VMOVLuv" # Insn2Lanes # Insn2Ty)
+ (EXTRACT_SUBREG (!cast<Instruction>("VMOVLuv" # Insn1Lanes # Insn1Ty)
+ (!cast<Instruction>("VREV16d8")
+ (VLD1LNd16 addrmode6:$addr, (f64 (IMPLICIT_DEF)), (i32 0)))),
+ dsub_0)),
+ dsub_0)>;
+ def _S : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
+ (!cast<PatFrag>("sextloadv" # SrcTy) addrmode6:$addr)),
+ (EXTRACT_SUBREG (!cast<Instruction>("VMOVLsv" # Insn2Lanes # Insn2Ty)
+ (EXTRACT_SUBREG (!cast<Instruction>("VMOVLsv" # Insn1Lanes # Insn1Ty)
+ (!cast<Instruction>("VREV16d8")
+ (VLD1LNd16 addrmode6:$addr, (f64 (IMPLICIT_DEF)), (i32 0)))),
+ dsub_0)),
+ dsub_0)>;
+}
+
defm : Lengthen_Single<"8", "i16", "8">; // v8i8 -> v8i16
defm : Lengthen_Single<"4", "i32", "16">; // v4i16 -> v4i32
defm : Lengthen_Single<"2", "i64", "32">; // v2i32 -> v2i64
-defm : Lengthen_HalfSingle<"4", "i16", "i8", "8", "i16">; // v4i8 -> v4i16
-defm : Lengthen_HalfSingle<"2", "i32", "i16", "4", "i32">; // v2i16 -> v2i32
+let Predicates = [IsLE] in {
+ defm : Lengthen_HalfSingle<"4", "i16", "i8", "8", "i16">; // v4i8 -> v4i16
+ defm : Lengthen_HalfSingle<"2", "i32", "i16", "4", "i32">; // v2i16 -> v2i32
+
+ // Double lengthening - v4i8 -> v4i16 -> v4i32
+ defm : Lengthen_Double<"4", "i32", "i8", "8", "i16", "4", "i32">;
+ // v2i8 -> v2i16 -> v2i32
+ defm : Lengthen_HalfDouble<"2", "i32", "i8", "8", "i16", "4", "i32">;
+ // v2i16 -> v2i32 -> v2i64
+ defm : Lengthen_Double<"2", "i64", "i16", "4", "i32", "2", "i64">;
+}
+
+let Predicates = [IsBE] in {
+ defm : Lengthen_HalfSingle_Big_Endian<"4", "i16", "i8", "8", "i16", "8">; // v4i8 -> v4i16
+ defm : Lengthen_HalfSingle_Big_Endian<"2", "i32", "i16", "4", "i32", "16">; // v2i16 -> v2i32
-// Double lengthening - v4i8 -> v4i16 -> v4i32
-defm : Lengthen_Double<"4", "i32", "i8", "8", "i16", "4", "i32">;
-// v2i8 -> v2i16 -> v2i32
-defm : Lengthen_HalfDouble<"2", "i32", "i8", "8", "i16", "4", "i32">;
-// v2i16 -> v2i32 -> v2i64
-defm : Lengthen_Double<"2", "i64", "i16", "4", "i32", "2", "i64">;
+ // Double lengthening - v4i8 -> v4i16 -> v4i32
+ defm : Lengthen_Double_Big_Endian<"4", "i32", "i8", "8", "i16", "4", "i32", "8">;
+ // v2i8 -> v2i16 -> v2i32
+ defm : Lengthen_HalfDouble_Big_Endian<"2", "i32", "i8", "8", "i16", "4", "i32">;
+ // v2i16 -> v2i32 -> v2i64
+ defm : Lengthen_Double_Big_Endian<"2", "i64", "i16", "4", "i32", "2", "i64", "16">;
+}
// Triple lengthening - v2i8 -> v2i16 -> v2i32 -> v2i64
-def : Pat<(v2i64 (extloadvi8 addrmode6:$addr)),
- (VMOVLuv2i64 (EXTRACT_SUBREG (VMOVLuv4i32 (EXTRACT_SUBREG (VMOVLuv8i16
- (VLD1LNd16 addrmode6:$addr,
- (f64 (IMPLICIT_DEF)), (i32 0))), dsub_0)), dsub_0))>;
-def : Pat<(v2i64 (zextloadvi8 addrmode6:$addr)),
- (VMOVLuv2i64 (EXTRACT_SUBREG (VMOVLuv4i32 (EXTRACT_SUBREG (VMOVLuv8i16
- (VLD1LNd16 addrmode6:$addr,
- (f64 (IMPLICIT_DEF)), (i32 0))), dsub_0)), dsub_0))>;
-def : Pat<(v2i64 (sextloadvi8 addrmode6:$addr)),
- (VMOVLsv2i64 (EXTRACT_SUBREG (VMOVLsv4i32 (EXTRACT_SUBREG (VMOVLsv8i16
- (VLD1LNd16 addrmode6:$addr,
- (f64 (IMPLICIT_DEF)), (i32 0))), dsub_0)), dsub_0))>;
+let Predicates = [IsLE] in {
+ def : Pat<(v2i64 (extloadvi8 addrmode6:$addr)),
+ (VMOVLuv2i64 (EXTRACT_SUBREG (VMOVLuv4i32 (EXTRACT_SUBREG (VMOVLuv8i16
+ (VLD1LNd16 addrmode6:$addr,
+ (f64 (IMPLICIT_DEF)), (i32 0))), dsub_0)), dsub_0))>;
+ def : Pat<(v2i64 (zextloadvi8 addrmode6:$addr)),
+ (VMOVLuv2i64 (EXTRACT_SUBREG (VMOVLuv4i32 (EXTRACT_SUBREG (VMOVLuv8i16
+ (VLD1LNd16 addrmode6:$addr,
+ (f64 (IMPLICIT_DEF)), (i32 0))), dsub_0)), dsub_0))>;
+ def : Pat<(v2i64 (sextloadvi8 addrmode6:$addr)),
+ (VMOVLsv2i64 (EXTRACT_SUBREG (VMOVLsv4i32 (EXTRACT_SUBREG (VMOVLsv8i16
+ (VLD1LNd16 addrmode6:$addr,
+ (f64 (IMPLICIT_DEF)), (i32 0))), dsub_0)), dsub_0))>;
+}
+// The following patterns are basically a copy of the patterns above,
+// however with an additional VREV16d instruction to convert data
+// loaded by VLD1LN into proper vector format in big endian mode.
+let Predicates = [IsBE] in {
+ def : Pat<(v2i64 (extloadvi8 addrmode6:$addr)),
+ (VMOVLuv2i64 (EXTRACT_SUBREG (VMOVLuv4i32 (EXTRACT_SUBREG (VMOVLuv8i16
+ (!cast<Instruction>("VREV16d8")
+ (VLD1LNd16 addrmode6:$addr,
+ (f64 (IMPLICIT_DEF)), (i32 0)))), dsub_0)), dsub_0))>;
+ def : Pat<(v2i64 (zextloadvi8 addrmode6:$addr)),
+ (VMOVLuv2i64 (EXTRACT_SUBREG (VMOVLuv4i32 (EXTRACT_SUBREG (VMOVLuv8i16
+ (!cast<Instruction>("VREV16d8")
+ (VLD1LNd16 addrmode6:$addr,
+ (f64 (IMPLICIT_DEF)), (i32 0)))), dsub_0)), dsub_0))>;
+ def : Pat<(v2i64 (sextloadvi8 addrmode6:$addr)),
+ (VMOVLsv2i64 (EXTRACT_SUBREG (VMOVLsv4i32 (EXTRACT_SUBREG (VMOVLsv8i16
+ (!cast<Instruction>("VREV16d8")
+ (VLD1LNd16 addrmode6:$addr,
+ (f64 (IMPLICIT_DEF)), (i32 0)))), dsub_0)), dsub_0))>;
+}
//===----------------------------------------------------------------------===//
// Assembler aliases
(VORRd DPR:$Vdn, DPR:$Vdn, DPR:$Vm, pred:$p)>;
defm : NEONDTAnyInstAlias<"vorr${p}", "$Vdn, $Vm",
(VORRq QPR:$Vdn, QPR:$Vdn, QPR:$Vm, pred:$p)>;
+// ... immediates
+def : NEONInstAlias<"vand${p}.i16 $Vd, $imm",
+ (VBICiv4i16 DPR:$Vd, nImmSplatNotI16:$imm, pred:$p)>;
+def : NEONInstAlias<"vand${p}.i32 $Vd, $imm",
+ (VBICiv2i32 DPR:$Vd, nImmSplatNotI32:$imm, pred:$p)>;
+def : NEONInstAlias<"vand${p}.i16 $Vd, $imm",
+ (VBICiv8i16 QPR:$Vd, nImmSplatNotI16:$imm, pred:$p)>;
+def : NEONInstAlias<"vand${p}.i32 $Vd, $imm",
+ (VBICiv4i32 QPR:$Vd, nImmSplatNotI32:$imm, pred:$p)>;
+
// VLD1 single-lane pseudo-instructions. These need special handling for
// the lane index that an InstAlias can't handle, so we use these instead.
projects / oota-llvm.git / blobdiff