// Load / store Instructions.
//
-let canFoldAsLoad = 1, isReMaterializable = 1, mayHaveSideEffects = 1 in {
+let canFoldAsLoad = 1, isReMaterializable = 1 in {
def VLDRD : ADI5<0b1101, 0b01, (outs DPR:$dst), (ins addrmode5:$addr),
IIC_fpLoad64, "vldr", ".64\t$dst, $addr",
- [(set DPR:$dst, (load addrmode5:$addr))]>;
+ [(set DPR:$dst, (f64 (load addrmode5:$addr)))]>;
def VLDRS : ASI5<0b1101, 0b01, (outs SPR:$dst), (ins addrmode5:$addr),
IIC_fpLoad32, "vldr", ".32\t$dst, $addr",
def VSTRD : ADI5<0b1101, 0b00, (outs), (ins DPR:$src, addrmode5:$addr),
IIC_fpStore64, "vstr", ".64\t$src, $addr",
- [(store DPR:$src, addrmode5:$addr)]>;
+ [(store (f64 DPR:$src), addrmode5:$addr)]>;
def VSTRS : ASI5<0b1101, 0b00, (outs), (ins SPR:$src, addrmode5:$addr),
IIC_fpStore32, "vstr", ".32\t$src, $addr",
// Load / store multiple Instructions.
//
-let mayLoad = 1, hasExtraDefRegAllocReq = 1 in {
-def VLDMD : AXDI5<(outs), (ins addrmode5:$addr, pred:$p, reglist:$wb,
- variable_ops), IIC_fpLoadm,
- "vldm${addr:submode}${p}\t${addr:base}, $wb",
- []> {
+let mayLoad = 1, neverHasSideEffects = 1, hasExtraDefRegAllocReq = 1 in {
+def VLDMD : AXDI4<(outs), (ins addrmode4:$addr, pred:$p, reglist:$dsts,
+ variable_ops), IndexModeNone, IIC_fpLoad_m,
+ "vldm${addr:submode}${p}\t$addr, $dsts", "", []> {
let Inst{20} = 1;
}
-def VLDMS : AXSI5<(outs), (ins addrmode5:$addr, pred:$p, reglist:$wb,
- variable_ops), IIC_fpLoadm,
- "vldm${addr:submode}${p}\t${addr:base}, $wb",
- []> {
+def VLDMS : AXSI4<(outs), (ins addrmode4:$addr, pred:$p, reglist:$dsts,
+ variable_ops), IndexModeNone, IIC_fpLoad_m,
+ "vldm${addr:submode}${p}\t$addr, $dsts", "", []> {
let Inst{20} = 1;
}
-} // mayLoad, hasExtraDefRegAllocReq
-let mayStore = 1, hasExtraSrcRegAllocReq = 1 in {
-def VSTMD : AXDI5<(outs), (ins addrmode5:$addr, pred:$p, reglist:$wb,
- variable_ops), IIC_fpStorem,
- "vstm${addr:submode}${p}\t${addr:base}, $wb",
- []> {
- let Inst{20} = 0;
+def VLDMD_UPD : AXDI4<(outs GPR:$wb), (ins addrmode4:$addr, pred:$p,
+ reglist:$dsts, variable_ops),
+ IndexModeUpd, IIC_fpLoad_mu,
+ "vldm${addr:submode}${p}\t$addr!, $dsts",
+ "$addr.addr = $wb", []> {
+ let Inst{20} = 1;
+}
+
+def VLDMS_UPD : AXSI4<(outs GPR:$wb), (ins addrmode4:$addr, pred:$p,
+ reglist:$dsts, variable_ops),
+ IndexModeUpd, IIC_fpLoad_mu,
+ "vldm${addr:submode}${p}\t$addr!, $dsts",
+ "$addr.addr = $wb", []> {
+ let Inst{20} = 1;
}
+} // mayLoad, neverHasSideEffects, hasExtraDefRegAllocReq
-def VSTMS : AXSI5<(outs), (ins addrmode5:$addr, pred:$p, reglist:$wb,
- variable_ops), IIC_fpStorem,
- "vstm${addr:submode}${p}\t${addr:base}, $wb",
- []> {
+let mayStore = 1, neverHasSideEffects = 1, hasExtraSrcRegAllocReq = 1 in {
+def VSTMD : AXDI4<(outs), (ins addrmode4:$addr, pred:$p, reglist:$srcs,
+ variable_ops), IndexModeNone, IIC_fpStore_m,
+ "vstm${addr:submode}${p}\t$addr, $srcs", "", []> {
let Inst{20} = 0;
}
-} // mayStore, hasExtraSrcRegAllocReq
-// FLDMX, FSTMX - mixing S/D registers for pre-armv6 cores
+def VSTMS : AXSI4<(outs), (ins addrmode4:$addr, pred:$p, reglist:$srcs,
+ variable_ops), IndexModeNone, IIC_fpStore_m,
+ "vstm${addr:submode}${p}\t$addr, $srcs", "", []> {
+ let Inst{20} = 0;
+}
-//===----------------------------------------------------------------------===//
-// FP Binary Operations.
-//
+def VSTMD_UPD : AXDI4<(outs GPR:$wb), (ins addrmode4:$addr, pred:$p,
+ reglist:$srcs, variable_ops),
+ IndexModeUpd, IIC_fpStore_mu,
+ "vstm${addr:submode}${p}\t$addr!, $srcs",
+ "$addr.addr = $wb", []> {
+ let Inst{20} = 0;
+}
-def VADDD : ADbI<0b11100, 0b11, 0, 0, (outs DPR:$dst), (ins DPR:$a, DPR:$b),
- IIC_fpALU64, "vadd", ".f64\t$dst, $a, $b",
- [(set DPR:$dst, (fadd DPR:$a, DPR:$b))]>;
+def VSTMS_UPD : AXSI4<(outs GPR:$wb), (ins addrmode4:$addr, pred:$p,
+ reglist:$srcs, variable_ops),
+ IndexModeUpd, IIC_fpStore_mu,
+ "vstm${addr:submode}${p}\t$addr!, $srcs",
+ "$addr.addr = $wb", []> {
+ let Inst{20} = 0;
+}
+} // mayStore, neverHasSideEffects, hasExtraSrcRegAllocReq
-def VADDS : ASbIn<0b11100, 0b11, 0, 0, (outs SPR:$dst), (ins SPR:$a, SPR:$b),
- IIC_fpALU32, "vadd", ".f32\t$dst, $a, $b",
- [(set SPR:$dst, (fadd SPR:$a, SPR:$b))]>;
+// FLDMX, FSTMX - mixing S/D registers for pre-armv6 cores
-// These are encoded as unary instructions.
-let Defs = [FPSCR] in {
-def VCMPED : ADuI<0b11101, 0b11, 0b0100, 0b11, 0, (outs), (ins DPR:$a, DPR:$b),
- IIC_fpCMP64, "vcmpe", ".f64\t$a, $b",
- [(arm_cmpfp DPR:$a, DPR:$b)]>;
-def VCMPES : ASuI<0b11101, 0b11, 0b0100, 0b11, 0, (outs), (ins SPR:$a, SPR:$b),
- IIC_fpCMP32, "vcmpe", ".f32\t$a, $b",
- [(arm_cmpfp SPR:$a, SPR:$b)]>;
+// FIXME: Can these be placed into the base class?
+class ADbI_Encode<bits<5> opcod1, bits<2> opcod2, bit op6, bit op4, dag oops,
+ dag iops, InstrItinClass itin, string opc, string asm,
+ list<dag> pattern>
+ : ADbI<opcod1, opcod2, op6, op4, oops, iops, itin, opc, asm, pattern> {
+ // Instruction operands.
+ bits<5> Dd;
+ bits<5> Dn;
+ bits<5> Dm;
+
+ // Encode instruction operands.
+ let Inst{3-0} = Dm{3-0};
+ let Inst{5} = Dm{4};
+ let Inst{19-16} = Dn{3-0};
+ let Inst{7} = Dn{4};
+ let Inst{15-12} = Dd{3-0};
+ let Inst{22} = Dd{4};
}
-def VDIVD : ADbI<0b11101, 0b00, 0, 0, (outs DPR:$dst), (ins DPR:$a, DPR:$b),
- IIC_fpDIV64, "vdiv", ".f64\t$dst, $a, $b",
- [(set DPR:$dst, (fdiv DPR:$a, DPR:$b))]>;
-
-def VDIVS : ASbI<0b11101, 0b00, 0, 0, (outs SPR:$dst), (ins SPR:$a, SPR:$b),
- IIC_fpDIV32, "vdiv", ".f32\t$dst, $a, $b",
- [(set SPR:$dst, (fdiv SPR:$a, SPR:$b))]>;
+class ASbI_Encode<bits<5> opcod1, bits<2> opcod2, bit op6, bit op4, dag oops,
+ dag iops, InstrItinClass itin, string opc, string asm,
+ list<dag> pattern>
+ : ASbI<opcod1, opcod2, op6, op4, oops, iops, itin, opc, asm, pattern> {
+ // Instruction operands.
+ bits<5> Sd;
+ bits<5> Sn;
+ bits<5> Sm;
+
+ // Encode instruction operands.
+ let Inst{3-0} = Sm{4-1};
+ let Inst{5} = Sm{0};
+ let Inst{19-16} = Sn{4-1};
+ let Inst{7} = Sn{0};
+ let Inst{15-12} = Sd{4-1};
+ let Inst{22} = Sd{0};
+}
-def VMULD : ADbI<0b11100, 0b10, 0, 0, (outs DPR:$dst), (ins DPR:$a, DPR:$b),
- IIC_fpMUL64, "vmul", ".f64\t$dst, $a, $b",
- [(set DPR:$dst, (fmul DPR:$a, DPR:$b))]>;
+class ASbIn_Encode<bits<5> opcod1, bits<2> opcod2, bit op6, bit op4, dag oops,
+ dag iops, InstrItinClass itin, string opc, string asm,
+ list<dag> pattern>
+ : ASbIn<opcod1, opcod2, op6, op4, oops, iops, itin, opc, asm, pattern> {
+ // Instruction operands.
+ bits<5> Sd;
+ bits<5> Sn;
+ bits<5> Sm;
+
+ // Encode instruction operands.
+ let Inst{3-0} = Sm{4-1};
+ let Inst{5} = Sm{0};
+ let Inst{19-16} = Sn{4-1};
+ let Inst{7} = Sn{0};
+ let Inst{15-12} = Sd{4-1};
+ let Inst{22} = Sd{0};
+}
-def VMULS : ASbIn<0b11100, 0b10, 0, 0, (outs SPR:$dst), (ins SPR:$a, SPR:$b),
- IIC_fpMUL32, "vmul", ".f32\t$dst, $a, $b",
- [(set SPR:$dst, (fmul SPR:$a, SPR:$b))]>;
-def VNMULD : ADbI<0b11100, 0b10, 1, 0, (outs DPR:$dst), (ins DPR:$a, DPR:$b),
- IIC_fpMUL64, "vnmul", ".f64\t$dst, $a, $b",
- [(set DPR:$dst, (fneg (fmul DPR:$a, DPR:$b)))]>;
+//===----------------------------------------------------------------------===//
+// FP Binary Operations.
+//
-def VNMULS : ASbI<0b11100, 0b10, 1, 0, (outs SPR:$dst), (ins SPR:$a, SPR:$b),
- IIC_fpMUL32, "vnmul", ".f32\t$dst, $a, $b",
- [(set SPR:$dst, (fneg (fmul SPR:$a, SPR:$b)))]>;
+def VADDD : ADbI_Encode<0b11100, 0b11, 0, 0,
+ (outs DPR:$Dd), (ins DPR:$Dn, DPR:$Dm),
+ IIC_fpALU64, "vadd", ".f64\t$Dd, $Dn, $Dm",
+ [(set DPR:$Dd, (fadd DPR:$Dn, (f64 DPR:$Dm)))]>;
+
+def VADDS : ASbIn_Encode<0b11100, 0b11, 0, 0,
+ (outs SPR:$Sd), (ins SPR:$Sn, SPR:$Sm),
+ IIC_fpALU32, "vadd", ".f32\t$Sd, $Sn, $Sm",
+ [(set SPR:$Sd, (fadd SPR:$Sn, SPR:$Sm))]>;
+
+def VSUBD : ADbI_Encode<0b11100, 0b11, 1, 0,
+ (outs DPR:$Dd), (ins DPR:$Dn, DPR:$Dm),
+ IIC_fpALU64, "vsub", ".f64\t$Dd, $Dn, $Dm",
+ [(set DPR:$Dd, (fsub DPR:$Dn, (f64 DPR:$Dm)))]>;
+
+def VSUBS : ASbIn_Encode<0b11100, 0b11, 1, 0,
+ (outs SPR:$Sd), (ins SPR:$Sn, SPR:$Sm),
+ IIC_fpALU32, "vsub", ".f32\t$Sd, $Sn, $Sm",
+ [(set SPR:$Sd, (fsub SPR:$Sn, SPR:$Sm))]>;
+
+def VDIVD : ADbI_Encode<0b11101, 0b00, 0, 0,
+ (outs DPR:$Dd), (ins DPR:$Dn, DPR:$Dm),
+ IIC_fpDIV64, "vdiv", ".f64\t$Dd, $Dn, $Dm",
+ [(set DPR:$Dd, (fdiv DPR:$Dn, (f64 DPR:$Dm)))]>;
+
+def VDIVS : ASbI_Encode<0b11101, 0b00, 0, 0,
+ (outs SPR:$Sd), (ins SPR:$Sn, SPR:$Sm),
+ IIC_fpDIV32, "vdiv", ".f32\t$Sd, $Sn, $Sm",
+ [(set SPR:$Sd, (fdiv SPR:$Sn, SPR:$Sm))]>;
+
+def VMULD : ADbI_Encode<0b11100, 0b10, 0, 0,
+ (outs DPR:$Dd), (ins DPR:$Dn, DPR:$Dm),
+ IIC_fpMUL64, "vmul", ".f64\t$Dd, $Dn, $Dm",
+ [(set DPR:$Dd, (fmul DPR:$Dn, (f64 DPR:$Dm)))]>;
+
+def VMULS : ASbIn_Encode<0b11100, 0b10, 0, 0,
+ (outs SPR:$Sd), (ins SPR:$Sn, SPR:$Sm),
+ IIC_fpMUL32, "vmul", ".f32\t$Sd, $Sn, $Sm",
+ [(set SPR:$Sd, (fmul SPR:$Sn, SPR:$Sm))]>;
+
+def VNMULD : ADbI_Encode<0b11100, 0b10, 1, 0,
+ (outs DPR:$Dd), (ins DPR:$Dn, DPR:$Dm),
+ IIC_fpMUL64, "vnmul", ".f64\t$Dd, $Dn, $Dm",
+ [(set DPR:$Dd, (fneg (fmul DPR:$Dn, (f64 DPR:$Dm))))]>;
+
+def VNMULS : ASbI_Encode<0b11100, 0b10, 1, 0,
+ (outs SPR:$Sd), (ins SPR:$Sn, SPR:$Sm),
+ IIC_fpMUL32, "vnmul", ".f32\t$Sd, $Sn, $Sm",
+ [(set SPR:$Sd, (fneg (fmul SPR:$Sn, SPR:$Sm)))]>;
// Match reassociated forms only if not sign dependent rounding.
-def : Pat<(fmul (fneg DPR:$a), DPR:$b),
+def : Pat<(fmul (fneg DPR:$a), (f64 DPR:$b)),
(VNMULD DPR:$a, DPR:$b)>, Requires<[NoHonorSignDependentRounding]>;
def : Pat<(fmul (fneg SPR:$a), SPR:$b),
(VNMULS SPR:$a, SPR:$b)>, Requires<[NoHonorSignDependentRounding]>;
-def VSUBD : ADbI<0b11100, 0b11, 1, 0, (outs DPR:$dst), (ins DPR:$a, DPR:$b),
- IIC_fpALU64, "vsub", ".f64\t$dst, $a, $b",
- [(set DPR:$dst, (fsub DPR:$a, DPR:$b))]>;
+// These are encoded as unary instructions.
+let Defs = [FPSCR] in {
+def VCMPED : ADuI<0b11101, 0b11, 0b0100, 0b11, 0, (outs),(ins DPR:$Dd, DPR:$Dm),
+ IIC_fpCMP64, "vcmpe", ".f64\t$Dd, $Dm",
+ [(arm_cmpfp DPR:$Dd, (f64 DPR:$Dm))]> {
+ // Instruction operands.
+ bits<5> Dd;
+ bits<5> Dm;
+
+ // Encode instruction operands.
+ let Inst{3-0} = Dm{3-0};
+ let Inst{5} = Dm{4};
+ let Inst{15-12} = Dd{3-0};
+ let Inst{22} = Dd{4};
+}
+
+def VCMPES : ASuI<0b11101, 0b11, 0b0100, 0b11, 0, (outs),(ins SPR:$Sd, SPR:$Sm),
+ IIC_fpCMP32, "vcmpe", ".f32\t$Sd, $Sm",
+ [(arm_cmpfp SPR:$Sd, SPR:$Sm)]> {
+ // Instruction operands.
+ bits<5> Sd;
+ bits<5> Sm;
+
+ // Encode instruction operands.
+ let Inst{3-0} = Sm{4-1};
+ let Inst{5} = Sm{0};
+ let Inst{15-12} = Sd{4-1};
+ let Inst{22} = Sd{0};
+}
-def VSUBS : ASbIn<0b11100, 0b11, 1, 0, (outs SPR:$dst), (ins SPR:$a, SPR:$b),
- IIC_fpALU32, "vsub", ".f32\t$dst, $a, $b",
- [(set SPR:$dst, (fsub SPR:$a, SPR:$b))]>;
+def VCMPD : ADuI<0b11101, 0b11, 0b0100, 0b01, 0, (outs), (ins DPR:$a, DPR:$b),
+ IIC_fpCMP64, "vcmp", ".f64\t$a, $b",
+ [/* For disassembly only; pattern left blank */]>;
+
+def VCMPS : ASuI<0b11101, 0b11, 0b0100, 0b01, 0, (outs), (ins SPR:$a, SPR:$b),
+ IIC_fpCMP32, "vcmp", ".f32\t$a, $b",
+ [/* For disassembly only; pattern left blank */]>;
+}
//===----------------------------------------------------------------------===//
// FP Unary Operations.
def VABSD : ADuI<0b11101, 0b11, 0b0000, 0b11, 0, (outs DPR:$dst), (ins DPR:$a),
IIC_fpUNA64, "vabs", ".f64\t$dst, $a",
- [(set DPR:$dst, (fabs DPR:$a))]>;
+ [(set DPR:$dst, (fabs (f64 DPR:$a)))]>;
def VABSS : ASuIn<0b11101, 0b11, 0b0000, 0b11, 0,(outs SPR:$dst), (ins SPR:$a),
IIC_fpUNA32, "vabs", ".f32\t$dst, $a",
let Defs = [FPSCR] in {
def VCMPEZD : ADuI<0b11101, 0b11, 0b0101, 0b11, 0, (outs), (ins DPR:$a),
IIC_fpCMP64, "vcmpe", ".f64\t$a, #0",
- [(arm_cmpfp0 DPR:$a)]>;
+ [(arm_cmpfp0 (f64 DPR:$a))]>;
+
+def VCMPZD : ADuI<0b11101, 0b11, 0b0101, 0b01, 0, (outs), (ins DPR:$a),
+ IIC_fpCMP64, "vcmp", ".f64\t$a, #0",
+ [/* For disassembly only; pattern left blank */]>;
def VCMPEZS : ASuI<0b11101, 0b11, 0b0101, 0b11, 0, (outs), (ins SPR:$a),
IIC_fpCMP32, "vcmpe", ".f32\t$a, #0",
[(arm_cmpfp0 SPR:$a)]>;
+
+def VCMPZS : ASuI<0b11101, 0b11, 0b0101, 0b01, 0, (outs), (ins SPR:$a),
+ IIC_fpCMP32, "vcmp", ".f32\t$a, #0",
+ [/* For disassembly only; pattern left blank */]>;
}
def VCVTDS : ASuI<0b11101, 0b11, 0b0111, 0b11, 0, (outs DPR:$dst), (ins SPR:$a),
let Inst{4} = 0;
}
+// Between half-precision and single-precision. For disassembly only.
+
+def VCVTBSH: ASuI<0b11101, 0b11, 0b0010, 0b01, 0, (outs SPR:$dst), (ins SPR:$a),
+ /* FIXME */ IIC_fpCVTSH, "vcvtb", ".f32.f16\t$dst, $a",
+ [/* For disassembly only; pattern left blank */]>;
+
+def : ARMPat<(f32_to_f16 SPR:$a),
+ (i32 (COPY_TO_REGCLASS (VCVTBSH SPR:$a), GPR))>;
+
+def VCVTBHS: ASuI<0b11101, 0b11, 0b0011, 0b01, 0, (outs SPR:$dst), (ins SPR:$a),
+ /* FIXME */ IIC_fpCVTHS, "vcvtb", ".f16.f32\t$dst, $a",
+ [/* For disassembly only; pattern left blank */]>;
+
+def : ARMPat<(f16_to_f32 GPR:$a),
+ (VCVTBHS (COPY_TO_REGCLASS GPR:$a, SPR))>;
+
+def VCVTTSH: ASuI<0b11101, 0b11, 0b0010, 0b11, 0, (outs SPR:$dst), (ins SPR:$a),
+ /* FIXME */ IIC_fpCVTSH, "vcvtt", ".f32.f16\t$dst, $a",
+ [/* For disassembly only; pattern left blank */]>;
+
+def VCVTTHS: ASuI<0b11101, 0b11, 0b0011, 0b11, 0, (outs SPR:$dst), (ins SPR:$a),
+ /* FIXME */ IIC_fpCVTHS, "vcvtt", ".f16.f32\t$dst, $a",
+ [/* For disassembly only; pattern left blank */]>;
+
let neverHasSideEffects = 1 in {
def VMOVD: ADuI<0b11101, 0b11, 0b0000, 0b01, 0, (outs DPR:$dst), (ins DPR:$a),
IIC_fpUNA64, "vmov", ".f64\t$dst, $a", []>;
def VNEGD : ADuI<0b11101, 0b11, 0b0001, 0b01, 0, (outs DPR:$dst), (ins DPR:$a),
IIC_fpUNA64, "vneg", ".f64\t$dst, $a",
- [(set DPR:$dst, (fneg DPR:$a))]>;
+ [(set DPR:$dst, (fneg (f64 DPR:$a)))]>;
def VNEGS : ASuIn<0b11101, 0b11, 0b0001, 0b01, 0,(outs SPR:$dst), (ins SPR:$a),
IIC_fpUNA32, "vneg", ".f32\t$dst, $a",
def VSQRTD : ADuI<0b11101, 0b11, 0b0001, 0b11, 0, (outs DPR:$dst), (ins DPR:$a),
IIC_fpSQRT64, "vsqrt", ".f64\t$dst, $a",
- [(set DPR:$dst, (fsqrt DPR:$a))]>;
+ [(set DPR:$dst, (fsqrt (f64 DPR:$a)))]>;
def VSQRTS : ASuI<0b11101, 0b11, 0b0001, 0b11, 0, (outs SPR:$dst), (ins SPR:$a),
IIC_fpSQRT32, "vsqrt", ".f32\t$dst, $a",
//
def VMOVRS : AVConv2I<0b11100001, 0b1010, (outs GPR:$dst), (ins SPR:$src),
- IIC_VMOVSI, "vmov", "\t$dst, $src",
+ IIC_fpMOVSI, "vmov", "\t$dst, $src",
[(set GPR:$dst, (bitconvert SPR:$src))]>;
def VMOVSR : AVConv4I<0b11100000, 0b1010, (outs SPR:$dst), (ins GPR:$src),
- IIC_VMOVIS, "vmov", "\t$dst, $src",
+ IIC_fpMOVIS, "vmov", "\t$dst, $src",
[(set SPR:$dst, (bitconvert GPR:$src))]>;
+let neverHasSideEffects = 1 in {
def VMOVRRD : AVConv3I<0b11000101, 0b1011,
(outs GPR:$wb, GPR:$dst2), (ins DPR:$src),
- IIC_VMOVDI, "vmov", "\t$wb, $dst2, $src",
+ IIC_fpMOVDI, "vmov", "\t$wb, $dst2, $src",
[/* FIXME: Can't write pattern for multiple result instr*/]> {
let Inst{7-6} = 0b00;
}
def VMOVRRS : AVConv3I<0b11000101, 0b1010,
(outs GPR:$wb, GPR:$dst2), (ins SPR:$src1, SPR:$src2),
- IIC_VMOVDI, "vmov", "\t$wb, $dst2, $src1, $src2",
+ IIC_fpMOVDI, "vmov", "\t$wb, $dst2, $src1, $src2",
[/* For disassembly only; pattern left blank */]> {
let Inst{7-6} = 0b00;
}
+} // neverHasSideEffects
// FMDHR: GPR -> SPR
// FMDLR: GPR -> SPR
def VMOVDRR : AVConv5I<0b11000100, 0b1011,
(outs DPR:$dst), (ins GPR:$src1, GPR:$src2),
- IIC_VMOVID, "vmov", "\t$dst, $src1, $src2",
+ IIC_fpMOVID, "vmov", "\t$dst, $src1, $src2",
[(set DPR:$dst, (arm_fmdrr GPR:$src1, GPR:$src2))]> {
let Inst{7-6} = 0b00;
}
+let neverHasSideEffects = 1 in
def VMOVSRR : AVConv5I<0b11000100, 0b1010,
(outs SPR:$dst1, SPR:$dst2), (ins GPR:$src1, GPR:$src2),
- IIC_VMOVID, "vmov", "\t$dst1, $dst2, $src1, $src2",
+ IIC_fpMOVID, "vmov", "\t$dst1, $dst2, $src1, $src2",
[/* For disassembly only; pattern left blank */]> {
let Inst{7-6} = 0b00;
}
// FMSRR: GPR -> SPR
-// FMXR: GPR -> VFP Sstem reg
+// FMXR: GPR -> VFP system reg
// Int to FP:
def VSITOD : AVConv1I<0b11101, 0b11, 0b1000, 0b1011,
(outs DPR:$dst), (ins SPR:$a),
IIC_fpCVTID, "vcvt", ".f64.s32\t$dst, $a",
- [(set DPR:$dst, (arm_sitof SPR:$a))]> {
+ [(set DPR:$dst, (f64 (arm_sitof SPR:$a)))]> {
let Inst{7} = 1; // s32
}
def VUITOD : AVConv1I<0b11101, 0b11, 0b1000, 0b1011,
(outs DPR:$dst), (ins SPR:$a),
IIC_fpCVTID, "vcvt", ".f64.u32\t$dst, $a",
- [(set DPR:$dst, (arm_uitof SPR:$a))]> {
+ [(set DPR:$dst, (f64 (arm_uitof SPR:$a)))]> {
let Inst{7} = 0; // u32
}
def VTOSIZD : AVConv1I<0b11101, 0b11, 0b1101, 0b1011,
(outs SPR:$dst), (ins DPR:$a),
IIC_fpCVTDI, "vcvt", ".s32.f64\t$dst, $a",
- [(set SPR:$dst, (arm_ftosi DPR:$a))]> {
+ [(set SPR:$dst, (arm_ftosi (f64 DPR:$a)))]> {
let Inst{7} = 1; // Z bit
}
def VTOUIZD : AVConv1I<0b11101, 0b11, 0b1100, 0b1011,
(outs SPR:$dst), (ins DPR:$a),
IIC_fpCVTDI, "vcvt", ".u32.f64\t$dst, $a",
- [(set SPR:$dst, (arm_ftoui DPR:$a))]> {
+ [(set SPR:$dst, (arm_ftoui (f64 DPR:$a)))]> {
let Inst{7} = 1; // Z bit
}
let Inst{7} = 1; // Z bit
}
+// And the Z bit '0' variants, i.e. use the rounding mode specified by FPSCR.
+// For disassembly only.
+let Uses = [FPSCR] in {
+def VTOSIRD : AVConv1I<0b11101, 0b11, 0b1101, 0b1011,
+ (outs SPR:$dst), (ins DPR:$a),
+ IIC_fpCVTDI, "vcvtr", ".s32.f64\t$dst, $a",
+ [(set SPR:$dst, (int_arm_vcvtr (f64 DPR:$a)))]> {
+ let Inst{7} = 0; // Z bit
+}
+
+def VTOSIRS : AVConv1In<0b11101, 0b11, 0b1101, 0b1010,
+ (outs SPR:$dst), (ins SPR:$a),
+ IIC_fpCVTSI, "vcvtr", ".s32.f32\t$dst, $a",
+ [(set SPR:$dst, (int_arm_vcvtr SPR:$a))]> {
+ let Inst{7} = 0; // Z bit
+}
+
+def VTOUIRD : AVConv1I<0b11101, 0b11, 0b1100, 0b1011,
+ (outs SPR:$dst), (ins DPR:$a),
+ IIC_fpCVTDI, "vcvtr", ".u32.f64\t$dst, $a",
+ [(set SPR:$dst, (int_arm_vcvtru (f64 DPR:$a)))]> {
+ let Inst{7} = 0; // Z bit
+}
+
+def VTOUIRS : AVConv1In<0b11101, 0b11, 0b1100, 0b1010,
+ (outs SPR:$dst), (ins SPR:$a),
+ IIC_fpCVTSI, "vcvtr", ".u32.f32\t$dst, $a",
+ [(set SPR:$dst, (int_arm_vcvtru SPR:$a))]> {
+ let Inst{7} = 0; // Z bit
+}
+}
+
+// Convert between floating-point and fixed-point
+// Data type for fixed-point naming convention:
+// S16 (U=0, sx=0) -> SH
+// U16 (U=1, sx=0) -> UH
+// S32 (U=0, sx=1) -> SL
+// U32 (U=1, sx=1) -> UL
+
+let Constraints = "$a = $dst" in {
+
+// FP to Fixed-Point:
+
+let isCodeGenOnly = 1 in {
+def VTOSHS : AVConv1XI<0b11101, 0b11, 0b1110, 0b1010, 0,
+ (outs SPR:$dst), (ins SPR:$a, i32imm:$fbits),
+ IIC_fpCVTSI, "vcvt", ".s16.f32\t$dst, $a, $fbits",
+ [/* For disassembly only; pattern left blank */]>;
+
+def VTOUHS : AVConv1XI<0b11101, 0b11, 0b1111, 0b1010, 0,
+ (outs SPR:$dst), (ins SPR:$a, i32imm:$fbits),
+ IIC_fpCVTSI, "vcvt", ".u16.f32\t$dst, $a, $fbits",
+ [/* For disassembly only; pattern left blank */]>;
+
+def VTOSLS : AVConv1XI<0b11101, 0b11, 0b1110, 0b1010, 1,
+ (outs SPR:$dst), (ins SPR:$a, i32imm:$fbits),
+ IIC_fpCVTSI, "vcvt", ".s32.f32\t$dst, $a, $fbits",
+ [/* For disassembly only; pattern left blank */]>;
+
+def VTOULS : AVConv1XI<0b11101, 0b11, 0b1111, 0b1010, 1,
+ (outs SPR:$dst), (ins SPR:$a, i32imm:$fbits),
+ IIC_fpCVTSI, "vcvt", ".u32.f32\t$dst, $a, $fbits",
+ [/* For disassembly only; pattern left blank */]>;
+
+def VTOSHD : AVConv1XI<0b11101, 0b11, 0b1110, 0b1011, 0,
+ (outs DPR:$dst), (ins DPR:$a, i32imm:$fbits),
+ IIC_fpCVTDI, "vcvt", ".s16.f64\t$dst, $a, $fbits",
+ [/* For disassembly only; pattern left blank */]>;
+
+def VTOUHD : AVConv1XI<0b11101, 0b11, 0b1111, 0b1011, 0,
+ (outs DPR:$dst), (ins DPR:$a, i32imm:$fbits),
+ IIC_fpCVTDI, "vcvt", ".u16.f64\t$dst, $a, $fbits",
+ [/* For disassembly only; pattern left blank */]>;
+
+def VTOSLD : AVConv1XI<0b11101, 0b11, 0b1110, 0b1011, 1,
+ (outs DPR:$dst), (ins DPR:$a, i32imm:$fbits),
+ IIC_fpCVTDI, "vcvt", ".s32.f64\t$dst, $a, $fbits",
+ [/* For disassembly only; pattern left blank */]>;
+
+def VTOULD : AVConv1XI<0b11101, 0b11, 0b1111, 0b1011, 1,
+ (outs DPR:$dst), (ins DPR:$a, i32imm:$fbits),
+ IIC_fpCVTDI, "vcvt", ".u32.f64\t$dst, $a, $fbits",
+ [/* For disassembly only; pattern left blank */]>;
+}
+
+// Fixed-Point to FP:
+
+let isCodeGenOnly = 1 in {
+def VSHTOS : AVConv1XI<0b11101, 0b11, 0b1010, 0b1010, 0,
+ (outs SPR:$dst), (ins SPR:$a, i32imm:$fbits),
+ IIC_fpCVTIS, "vcvt", ".f32.s16\t$dst, $a, $fbits",
+ [/* For disassembly only; pattern left blank */]>;
+
+def VUHTOS : AVConv1XI<0b11101, 0b11, 0b1011, 0b1010, 0,
+ (outs SPR:$dst), (ins SPR:$a, i32imm:$fbits),
+ IIC_fpCVTIS, "vcvt", ".f32.u16\t$dst, $a, $fbits",
+ [/* For disassembly only; pattern left blank */]>;
+
+def VSLTOS : AVConv1XI<0b11101, 0b11, 0b1010, 0b1010, 1,
+ (outs SPR:$dst), (ins SPR:$a, i32imm:$fbits),
+ IIC_fpCVTIS, "vcvt", ".f32.s32\t$dst, $a, $fbits",
+ [/* For disassembly only; pattern left blank */]>;
+
+def VULTOS : AVConv1XI<0b11101, 0b11, 0b1011, 0b1010, 1,
+ (outs SPR:$dst), (ins SPR:$a, i32imm:$fbits),
+ IIC_fpCVTIS, "vcvt", ".f32.u32\t$dst, $a, $fbits",
+ [/* For disassembly only; pattern left blank */]>;
+
+def VSHTOD : AVConv1XI<0b11101, 0b11, 0b1010, 0b1011, 0,
+ (outs DPR:$dst), (ins DPR:$a, i32imm:$fbits),
+ IIC_fpCVTID, "vcvt", ".f64.s16\t$dst, $a, $fbits",
+ [/* For disassembly only; pattern left blank */]>;
+
+def VUHTOD : AVConv1XI<0b11101, 0b11, 0b1011, 0b1011, 0,
+ (outs DPR:$dst), (ins DPR:$a, i32imm:$fbits),
+ IIC_fpCVTID, "vcvt", ".f64.u16\t$dst, $a, $fbits",
+ [/* For disassembly only; pattern left blank */]>;
+
+def VSLTOD : AVConv1XI<0b11101, 0b11, 0b1010, 0b1011, 1,
+ (outs DPR:$dst), (ins DPR:$a, i32imm:$fbits),
+ IIC_fpCVTID, "vcvt", ".f64.s32\t$dst, $a, $fbits",
+ [/* For disassembly only; pattern left blank */]>;
+
+def VULTOD : AVConv1XI<0b11101, 0b11, 0b1011, 0b1011, 1,
+ (outs DPR:$dst), (ins DPR:$a, i32imm:$fbits),
+ IIC_fpCVTID, "vcvt", ".f64.u32\t$dst, $a, $fbits",
+ [/* For disassembly only; pattern left blank */]>;
+}
+
+} // End of 'let Constraints = "$src = $dst" in'
+
//===----------------------------------------------------------------------===//
// FP FMA Operations.
//
-def VMLAD : ADbI<0b11100, 0b00, 0, 0,
+def VMLAD : ADbI_vmlX<0b11100, 0b00, 0, 0,
(outs DPR:$dst), (ins DPR:$dstin, DPR:$a, DPR:$b),
IIC_fpMAC64, "vmla", ".f64\t$dst, $a, $b",
- [(set DPR:$dst, (fadd (fmul DPR:$a, DPR:$b), DPR:$dstin))]>,
+ [(set DPR:$dst, (fadd (fmul DPR:$a, DPR:$b),
+ (f64 DPR:$dstin)))]>,
RegConstraint<"$dstin = $dst">;
def VMLAS : ASbIn<0b11100, 0b00, 0, 0,
[(set SPR:$dst, (fadd (fmul SPR:$a, SPR:$b), SPR:$dstin))]>,
RegConstraint<"$dstin = $dst">;
-def VNMLSD : ADbI<0b11100, 0b01, 0, 0,
+def VNMLSD : ADbI_vmlX<0b11100, 0b01, 0, 0,
(outs DPR:$dst), (ins DPR:$dstin, DPR:$a, DPR:$b),
IIC_fpMAC64, "vnmls", ".f64\t$dst, $a, $b",
- [(set DPR:$dst, (fsub (fmul DPR:$a, DPR:$b), DPR:$dstin))]>,
+ [(set DPR:$dst, (fsub (fmul DPR:$a, DPR:$b),
+ (f64 DPR:$dstin)))]>,
RegConstraint<"$dstin = $dst">;
def VNMLSS : ASbI<0b11100, 0b01, 0, 0,
[(set SPR:$dst, (fsub (fmul SPR:$a, SPR:$b), SPR:$dstin))]>,
RegConstraint<"$dstin = $dst">;
-def VMLSD : ADbI<0b11100, 0b00, 1, 0,
+def VMLSD : ADbI_vmlX<0b11100, 0b00, 1, 0,
(outs DPR:$dst), (ins DPR:$dstin, DPR:$a, DPR:$b),
IIC_fpMAC64, "vmls", ".f64\t$dst, $a, $b",
- [(set DPR:$dst, (fadd (fneg (fmul DPR:$a, DPR:$b)), DPR:$dstin))]>,
+ [(set DPR:$dst, (fadd (fneg (fmul DPR:$a, DPR:$b)),
+ (f64 DPR:$dstin)))]>,
RegConstraint<"$dstin = $dst">;
def VMLSS : ASbIn<0b11100, 0b00, 1, 0,
[(set SPR:$dst, (fadd (fneg (fmul SPR:$a, SPR:$b)), SPR:$dstin))]>,
RegConstraint<"$dstin = $dst">;
-def : Pat<(fsub DPR:$dstin, (fmul DPR:$a, DPR:$b)),
+def : Pat<(fsub DPR:$dstin, (fmul DPR:$a, (f64 DPR:$b))),
(VMLSD DPR:$dstin, DPR:$a, DPR:$b)>, Requires<[DontUseNEONForFP]>;
def : Pat<(fsub SPR:$dstin, (fmul SPR:$a, SPR:$b)),
(VMLSS SPR:$dstin, SPR:$a, SPR:$b)>, Requires<[DontUseNEONForFP]>;
-def VNMLAD : ADbI<0b11100, 0b01, 1, 0,
+def VNMLAD : ADbI_vmlX<0b11100, 0b01, 1, 0,
(outs DPR:$dst), (ins DPR:$dstin, DPR:$a, DPR:$b),
IIC_fpMAC64, "vnmla", ".f64\t$dst, $a, $b",
- [(set DPR:$dst, (fsub (fneg (fmul DPR:$a, DPR:$b)), DPR:$dstin))]>,
+ [(set DPR:$dst, (fsub (fneg (fmul DPR:$a, DPR:$b)),
+ (f64 DPR:$dstin)))]>,
RegConstraint<"$dstin = $dst">;
def VNMLAS : ASbI<0b11100, 0b01, 1, 0,
// FP Conditional moves.
//
+let neverHasSideEffects = 1 in {
def VMOVDcc : ADuI<0b11101, 0b11, 0b0000, 0b01, 0,
(outs DPR:$dst), (ins DPR:$false, DPR:$true),
IIC_fpUNA64, "vmov", ".f64\t$dst, $true",
IIC_fpUNA32, "vneg", ".f32\t$dst, $true",
[/*(set SPR:$dst, (ARMcneg SPR:$false, SPR:$true, imm:$cc))*/]>,
RegConstraint<"$false = $dst">;
-
+} // neverHasSideEffects
//===----------------------------------------------------------------------===//
// Misc.
let Inst{4} = 1;
}
+// FPSCR <-> GPR (for disassembly only)
+let hasSideEffects = 1, Uses = [FPSCR] in
+def VMRS : VFPAI<(outs GPR:$dst), (ins), VFPMiscFrm, IIC_fpSTAT,
+ "vmrs", "\t$dst, fpscr",
+ [(set GPR:$dst, (int_arm_get_fpscr))]> {
+ let Inst{27-20} = 0b11101111;
+ let Inst{19-16} = 0b0001;
+ let Inst{11-8} = 0b1010;
+ let Inst{7} = 0;
+ let Inst{4} = 1;
+}
+
+let Defs = [FPSCR] in
+def VMSR : VFPAI<(outs), (ins GPR:$src), VFPMiscFrm, IIC_fpSTAT,
+ "vmsr", "\tfpscr, $src",
+ [(int_arm_set_fpscr GPR:$src)]> {
+ let Inst{27-20} = 0b11101110;
+ let Inst{19-16} = 0b0001;
+ let Inst{11-8} = 0b1010;
+ let Inst{7} = 0;
+ let Inst{4} = 1;
+}
// Materialize FP immediates. VFP3 only.
let isReMaterializable = 1 in {
def FCONSTD : VFPAI<(outs DPR:$dst), (ins vfp_f64imm:$imm),
- VFPMiscFrm, IIC_VMOVImm,
+ VFPMiscFrm, IIC_fpUNA64,
"vmov", ".f64\t$dst, $imm",
[(set DPR:$dst, vfp_f64imm:$imm)]>, Requires<[HasVFP3]> {
let Inst{27-23} = 0b11101;
}
def FCONSTS : VFPAI<(outs SPR:$dst), (ins vfp_f32imm:$imm),
- VFPMiscFrm, IIC_VMOVImm,
+ VFPMiscFrm, IIC_fpUNA32,
"vmov", ".f32\t$dst, $imm",
[(set SPR:$dst, vfp_f32imm:$imm)]>, Requires<[HasVFP3]> {
let Inst{27-23} = 0b11101;