SDTypeProfile<1, 1, [SDTCisVT<0, f32>, SDTCisFP<1>]>;
def SDTSPITOF :
SDTypeProfile<1, 1, [SDTCisFP<0>, SDTCisVT<1, f32>]>;
+def SDTSPFTOX :
+SDTypeProfile<1, 1, [SDTCisVT<0, f64>, SDTCisFP<1>]>;
+def SDTSPXTOF :
+SDTypeProfile<1, 1, [SDTCisFP<0>, SDTCisVT<1, f64>]>;
def SDTSPtlsadd :
SDTypeProfile<1, 3, [SDTCisInt<0>, SDTCisSameAs<0, 1>, SDTCisPtrTy<2>]>;
def SPftoi : SDNode<"SPISD::FTOI", SDTSPFTOI>;
def SPitof : SDNode<"SPISD::ITOF", SDTSPITOF>;
+def SPftox : SDNode<"SPISD::FTOX", SDTSPFTOX>;
+def SPxtof : SDNode<"SPISD::XTOF", SDTSPXTOF>;
def SPselecticc : SDNode<"SPISD::SELECT_ICC", SDTSPselectcc, [SDNPInGlue]>;
def SPselectxcc : SDNode<"SPISD::SELECT_XCC", SDTSPselectcc, [SDNPInGlue]>;
//===----------------------------------------------------------------------===//
/// F3_12 multiclass - Define a normal F3_1/F3_2 pattern in one shot.
-multiclass F3_12<string OpcStr, bits<6> Op3Val, SDNode OpNode> {
+multiclass F3_12<string OpcStr, bits<6> Op3Val, SDNode OpNode,
+ RegisterClass RC, ValueType Ty, Operand immOp> {
def rr : F3_1<2, Op3Val,
- (outs IntRegs:$dst), (ins IntRegs:$b, IntRegs:$c),
+ (outs RC:$dst), (ins RC:$b, RC:$c),
!strconcat(OpcStr, " $b, $c, $dst"),
- [(set i32:$dst, (OpNode i32:$b, i32:$c))]>;
+ [(set Ty:$dst, (OpNode Ty:$b, Ty:$c))]>;
def ri : F3_2<2, Op3Val,
- (outs IntRegs:$dst), (ins IntRegs:$b, i32imm:$c),
+ (outs RC:$dst), (ins RC:$b, immOp:$c),
!strconcat(OpcStr, " $b, $c, $dst"),
- [(set i32:$dst, (OpNode i32:$b, (i32 simm13:$c)))]>;
+ [(set Ty:$dst, (OpNode Ty:$b, (Ty simm13:$c)))]>;
}
/// F3_12np multiclass - Define a normal F3_1/F3_2 pattern in one shot, with no
// Section B.4 - Store Integer Instructions, p. 95
def STBrr : F3_1<3, 0b000101,
- (outs), (ins MEMrr:$addr, IntRegs:$src),
- "stb $src, [$addr]",
- [(truncstorei8 i32:$src, ADDRrr:$addr)]>;
+ (outs), (ins MEMrr:$addr, IntRegs:$rd),
+ "stb $rd, [$addr]",
+ [(truncstorei8 i32:$rd, ADDRrr:$addr)]>;
def STBri : F3_2<3, 0b000101,
- (outs), (ins MEMri:$addr, IntRegs:$src),
- "stb $src, [$addr]",
- [(truncstorei8 i32:$src, ADDRri:$addr)]>;
+ (outs), (ins MEMri:$addr, IntRegs:$rd),
+ "stb $rd, [$addr]",
+ [(truncstorei8 i32:$rd, ADDRri:$addr)]>;
def STHrr : F3_1<3, 0b000110,
- (outs), (ins MEMrr:$addr, IntRegs:$src),
- "sth $src, [$addr]",
- [(truncstorei16 i32:$src, ADDRrr:$addr)]>;
+ (outs), (ins MEMrr:$addr, IntRegs:$rd),
+ "sth $rd, [$addr]",
+ [(truncstorei16 i32:$rd, ADDRrr:$addr)]>;
def STHri : F3_2<3, 0b000110,
- (outs), (ins MEMri:$addr, IntRegs:$src),
- "sth $src, [$addr]",
- [(truncstorei16 i32:$src, ADDRri:$addr)]>;
+ (outs), (ins MEMri:$addr, IntRegs:$rd),
+ "sth $rd, [$addr]",
+ [(truncstorei16 i32:$rd, ADDRri:$addr)]>;
def STrr : F3_1<3, 0b000100,
- (outs), (ins MEMrr:$addr, IntRegs:$src),
- "st $src, [$addr]",
- [(store i32:$src, ADDRrr:$addr)]>;
+ (outs), (ins MEMrr:$addr, IntRegs:$rd),
+ "st $rd, [$addr]",
+ [(store i32:$rd, ADDRrr:$addr)]>;
def STri : F3_2<3, 0b000100,
- (outs), (ins MEMri:$addr, IntRegs:$src),
- "st $src, [$addr]",
- [(store i32:$src, ADDRri:$addr)]>;
+ (outs), (ins MEMri:$addr, IntRegs:$rd),
+ "st $rd, [$addr]",
+ [(store i32:$rd, ADDRri:$addr)]>;
// Section B.5 - Store Floating-point Instructions, p. 97
def STFrr : F3_1<3, 0b100100,
- (outs), (ins MEMrr:$addr, FPRegs:$src),
- "st $src, [$addr]",
- [(store f32:$src, ADDRrr:$addr)]>;
+ (outs), (ins MEMrr:$addr, FPRegs:$rd),
+ "st $rd, [$addr]",
+ [(store f32:$rd, ADDRrr:$addr)]>;
def STFri : F3_2<3, 0b100100,
- (outs), (ins MEMri:$addr, FPRegs:$src),
- "st $src, [$addr]",
- [(store f32:$src, ADDRri:$addr)]>;
+ (outs), (ins MEMri:$addr, FPRegs:$rd),
+ "st $rd, [$addr]",
+ [(store f32:$rd, ADDRri:$addr)]>;
def STDFrr : F3_1<3, 0b100111,
- (outs), (ins MEMrr:$addr, DFPRegs:$src),
- "std $src, [$addr]",
- [(store f64:$src, ADDRrr:$addr)]>;
+ (outs), (ins MEMrr:$addr, DFPRegs:$rd),
+ "std $rd, [$addr]",
+ [(store f64:$rd, ADDRrr:$addr)]>;
def STDFri : F3_2<3, 0b100111,
- (outs), (ins MEMri:$addr, DFPRegs:$src),
- "std $src, [$addr]",
- [(store f64:$src, ADDRri:$addr)]>;
+ (outs), (ins MEMri:$addr, DFPRegs:$rd),
+ "std $rd, [$addr]",
+ [(store f64:$rd, ADDRri:$addr)]>;
def STQFrr : F3_1<3, 0b100110,
- (outs), (ins MEMrr:$addr, QFPRegs:$src),
- "stq $src, [$addr]",
- [(store f128:$src, ADDRrr:$addr)]>,
+ (outs), (ins MEMrr:$addr, QFPRegs:$rd),
+ "stq $rd, [$addr]",
+ [(store f128:$rd, ADDRrr:$addr)]>,
Requires<[HasV9, HasHardQuad]>;
def STQFri : F3_2<3, 0b100110,
- (outs), (ins MEMri:$addr, QFPRegs:$src),
- "stq $src, [$addr]",
- [(store f128:$src, ADDRri:$addr)]>,
+ (outs), (ins MEMri:$addr, QFPRegs:$rd),
+ "stq $rd, [$addr]",
+ [(store f128:$rd, ADDRri:$addr)]>,
Requires<[HasV9, HasHardQuad]>;
// Section B.9 - SETHI Instruction, p. 104
def SETHIi: F2_1<0b100,
- (outs IntRegs:$dst), (ins i32imm:$src),
- "sethi $src, $dst",
- [(set i32:$dst, SETHIimm:$src)]>;
+ (outs IntRegs:$rd), (ins i32imm:$imm22),
+ "sethi $imm22, $rd",
+ [(set i32:$rd, SETHIimm:$imm22)]>;
// Section B.10 - NOP Instruction, p. 105
// (It's a special case of SETHI)
def NOP : F2_1<0b100, (outs), (ins), "nop", []>;
// Section B.11 - Logical Instructions, p. 106
-defm AND : F3_12<"and", 0b000001, and>;
+defm AND : F3_12<"and", 0b000001, and, IntRegs, i32, i32imm>;
def ANDNrr : F3_1<2, 0b000101,
(outs IntRegs:$dst), (ins IntRegs:$b, IntRegs:$c),
(outs IntRegs:$dst), (ins IntRegs:$b, i32imm:$c),
"andn $b, $c, $dst", []>;
-defm OR : F3_12<"or", 0b000010, or>;
+defm OR : F3_12<"or", 0b000010, or, IntRegs, i32, i32imm>;
def ORNrr : F3_1<2, 0b000110,
(outs IntRegs:$dst), (ins IntRegs:$b, IntRegs:$c),
def ORNri : F3_2<2, 0b000110,
(outs IntRegs:$dst), (ins IntRegs:$b, i32imm:$c),
"orn $b, $c, $dst", []>;
-defm XOR : F3_12<"xor", 0b000011, xor>;
+defm XOR : F3_12<"xor", 0b000011, xor, IntRegs, i32, i32imm>;
def XNORrr : F3_1<2, 0b000111,
(outs IntRegs:$dst), (ins IntRegs:$b, IntRegs:$c),
"xnor $b, $c, $dst", []>;
// Section B.12 - Shift Instructions, p. 107
-defm SLL : F3_12<"sll", 0b100101, shl>;
-defm SRL : F3_12<"srl", 0b100110, srl>;
-defm SRA : F3_12<"sra", 0b100111, sra>;
+defm SLL : F3_12<"sll", 0b100101, shl, IntRegs, i32, i32imm>;
+defm SRL : F3_12<"srl", 0b100110, srl, IntRegs, i32, i32imm>;
+defm SRA : F3_12<"sra", 0b100111, sra, IntRegs, i32, i32imm>;
// Section B.13 - Add Instructions, p. 108
-defm ADD : F3_12<"add", 0b000000, add>;
+defm ADD : F3_12<"add", 0b000000, add, IntRegs, i32, i32imm>;
// "LEA" forms of add (patterns to make tblgen happy)
-def LEA_ADDri : F3_2<2, 0b000000,
- (outs IntRegs:$dst), (ins MEMri:$addr),
- "add ${addr:arith}, $dst",
- [(set iPTR:$dst, ADDRri:$addr)]>;
+let Predicates = [Is32Bit] in
+ def LEA_ADDri : F3_2<2, 0b000000,
+ (outs IntRegs:$dst), (ins MEMri:$addr),
+ "add ${addr:arith}, $dst",
+ [(set iPTR:$dst, ADDRri:$addr)]>;
let Defs = [ICC] in
- defm ADDCC : F3_12<"addcc", 0b010000, addc>;
+ defm ADDCC : F3_12<"addcc", 0b010000, addc, IntRegs, i32, i32imm>;
-let Uses = [ICC] in
- defm ADDX : F3_12<"addx", 0b001000, adde>;
+let Uses = [ICC], Defs = [ICC] in
+ defm ADDE : F3_12<"addxcc", 0b011000, adde, IntRegs, i32, i32imm>;
// Section B.15 - Subtract Instructions, p. 110
-defm SUB : F3_12 <"sub" , 0b000100, sub>;
-let Uses = [ICC] in
- defm SUBX : F3_12 <"subx" , 0b001100, sube>;
+defm SUB : F3_12 <"sub" , 0b000100, sub, IntRegs, i32, i32imm>;
+let Uses = [ICC], Defs = [ICC] in
+ defm SUBE : F3_12 <"subxcc" , 0b011100, sube, IntRegs, i32, i32imm>;
let Defs = [ICC] in
- defm SUBCC : F3_12 <"subcc", 0b010100, subc>;
+ defm SUBCC : F3_12 <"subcc", 0b010100, subc, IntRegs, i32, i32imm>;
let Defs = [ICC], rd = 0 in {
def CMPrr : F3_1<2, 0b010100,
// Section B.18 - Multiply Instructions, p. 113
let Defs = [Y] in {
defm UMUL : F3_12np<"umul", 0b001010>;
- defm SMUL : F3_12 <"smul", 0b001011, mul>;
+ defm SMUL : F3_12 <"smul", 0b001011, mul, IntRegs, i32, i32imm>;
}
// Section B.19 - Divide Instructions, p. 115
// Floating-point Compare Instructions, p. 148
// Note: the 2nd template arg is different for these guys.
// Note 2: the result of a FCMP is not available until the 2nd cycle
-// after the instr is retired, but there is no interlock. This behavior
-// is modelled with a forced noop after the instruction.
+// after the instr is retired, but there is no interlock in Sparc V8.
+// This behavior is modeled with a forced noop after the instruction in
+// DelaySlotFiller.
+
let Defs = [FCC] in {
def FCMPS : F3_3c<2, 0b110101, 0b001010001,
(outs), (ins FPRegs:$src1, FPRegs:$src2),
- "fcmps $src1, $src2\n\tnop",
+ "fcmps $src1, $src2",
[(SPcmpfcc f32:$src1, f32:$src2)]>;
def FCMPD : F3_3c<2, 0b110101, 0b001010010,
(outs), (ins DFPRegs:$src1, DFPRegs:$src2),
- "fcmpd $src1, $src2\n\tnop",
+ "fcmpd $src1, $src2",
[(SPcmpfcc f64:$src1, f64:$src2)]>;
def FCMPQ : F3_3c<2, 0b110101, 0b001010011,
(outs), (ins QFPRegs:$src1, QFPRegs:$src2),
- "fcmpq $src1, $src2\n\tnop",
+ "fcmpq $src1, $src2",
[(SPcmpfcc f128:$src1, f128:$src2)]>,
Requires<[HasHardQuad]>;
}
[(set i32:$dst,
(tlsld ADDRrr:$addr, tglobaltlsaddr:$sym))]>;
-let Uses = [O6], isCall = 1 in
+let Uses = [O6], isCall = 1, hasDelaySlot = 1 in
def TLS_CALL : InstSP<(outs),
(ins calltarget:$disp, TLSSym:$sym, variable_ops),
- "call $disp, $sym\n\tnop",
+ "call $disp, $sym",
[(tlscall texternalsym:$disp, tglobaltlsaddr:$sym)]> {
bits<30> disp;
let op = 1;
}
// POPCrr - This does a ctpop of a 64-bit register. As such, we have to clear
-// the top 32-bits before using it. To do this clearing, we use a SLLri X,0.
+// the top 32-bits before using it. To do this clearing, we use a SRLri X,0.
let rs1 = 0 in
def POPCrr : F3_1<2, 0b101110,
(outs IntRegs:$dst), (ins IntRegs:$src),
"popc $src, $dst", []>, Requires<[HasV9]>;
def : Pat<(ctpop i32:$src),
- (POPCrr (SLLri $src, 0))>;
+ (POPCrr (SRLri $src, 0))>;
//===----------------------------------------------------------------------===//
// Non-Instruction Patterns
// Global addresses, constant pool entries
+let Predicates = [Is32Bit] in {
+
def : Pat<(SPhi tglobaladdr:$in), (SETHIi tglobaladdr:$in)>;
def : Pat<(SPlo tglobaladdr:$in), (ORri (i32 G0), tglobaladdr:$in)>;
def : Pat<(SPhi tconstpool:$in), (SETHIi tconstpool:$in)>;
def : Pat<(add iPTR:$r, (SPlo tconstpool:$in)), (ADDri $r, tconstpool:$in)>;
def : Pat<(add iPTR:$r, (SPlo tblockaddress:$in)),
(ADDri $r, tblockaddress:$in)>;
+}
// Calls:
def : Pat<(call tglobaladdr:$dst),
projects / oota-llvm.git / blobdiff