[mips] Update the P5600 scheduler for isComplete = 1

[sdardis]

Summary

These changes update the schedule model for the P5600 and include the
rest of the MSA and MIPS32R5 instruction set.

[sdardis]

Remove repeated resource use for co-processor 0 instructions.

[sdardis]

Wrong diff uploaded.

[sdardis]

Ping.

[dsanders]

LGTM

lib/Target/Mips/Mips.td

 // Register File, Calling Conv, Instruction Descriptions
 //===----------------------------------------------------------------------===//
 
 include "MipsRegisterInfo.td"
 include "MipsSchedule.td"
 include "MipsInstrInfo.td"
 include "MipsCallingConv.td"
 
+// Avoid forward declaration issues.
+include "MipsScheduleP5600.td"
+
 def MipsInstrInfo : InstrInfo;
 
 //===----------------------------------------------------------------------===//
 // Mips Subtarget features                                                    //
 //===----------------------------------------------------------------------===//
 
 def FeatureNoABICalls  : SubtargetFeature<"noabicalls", "NoABICalls", "true",
                                 "Disable SVR4-style position-independent code">;

lib/Target/Mips/MipsSchedule.td

def MipsGenericItineraries : ProcessorItineraries<[ALU, IMULDIV], [], [
   InstrItinData<II_PREF            , [InstrStage<1,  [ALU]>]>,
   InstrItinData<II_CACHEE          , [InstrStage<1,  [ALU]>]>,
   InstrItinData<II_PREFE           , [InstrStage<1,  [ALU]>]>,
   InstrItinData<II_TLBINV          , [InstrStage<1,  [ALU]>]>,
   InstrItinData<II_TLBINVF         , [InstrStage<1,  [ALU]>]>,
   InstrItinData<II_LLE             , [InstrStage<3,  [ALU]>]>,
   InstrItinData<II_SCE             , [InstrStage<1,  [ALU]>]>
 ]>;
-
-include "MipsScheduleP5600.td"

lib/Target/Mips/MipsScheduleP5600.td

 //==- MipsScheduleP5600.td - P5600 Scheduling Definitions --*- tablegen -*-===//
 //
 //                     The LLVM Compiler Infrastructure
 //
 // This file is distributed under the University of Illinois Open Source
 // License. See LICENSE.TXT for details.
 //
 //===----------------------------------------------------------------------===//
 
 def MipsP5600Model : SchedMachineModel {
   int IssueWidth = 2; // 2x dispatched per cycle
   int MicroOpBufferSize = 48; // min(48, 48, 64)
   int LoadLatency = 4;
   int MispredictPenalty = 8; // TODO: Estimated
 
-  let CompleteModel = 0;
+  let CompleteModel = 1;
+
+  list<Predicate> UnsupportedFeatures = [HasMips32r6, HasMips64r6,
+                                         HasMips64, HasMips64r2, HasCnMips,
+                                         InMicroMips, InMips16Mode,
+                                         HasMicroMips32r6, HasMicroMips64r6,
+                                         HasDSP, HasDSPR2];
+
 }
 
 let SchedModel = MipsP5600Model in {
 
 // ALQ Pipelines
 // =============
 
 def P5600ALQ : ProcResource<1> { let BufferSize = 16; }
 def P5600IssueALU : ProcResource<1> { let Super = P5600ALQ; }
 
 // ALU Pipeline
 // ------------
 
 def P5600WriteALU : SchedWriteRes<[P5600IssueALU]>;
 
 // and, lui, nor, or, slti, sltiu, sub, subu, xor
 def : ItinRW<[P5600WriteALU],
-             [II_AND, II_LUI, II_NOR, II_OR, II_SLTI_SLTIU, II_SUBU, II_XOR]>;
+             [II_AND, II_LUI, II_NOR, II_OR, II_SLTI_SLTIU, II_SUB, II_SUBU,
+              II_XOR]>;
 
 // AGQ Pipelines
 // =============
 
 def P5600AGQ : ProcResource<3> { let BufferSize = 16; }
 def P5600IssueAL2 : ProcResource<1> { let Super = P5600AGQ; }
 def P5600IssueCTISTD : ProcResource<1> { let Super = P5600AGQ; }
 def P5600IssueLDST : ProcResource<1> { let Super = P5600AGQ; }
 
 def P5600AL2Div : ProcResource<1>;
 // Pseudo-resource used to block CTISTD when handling multi-pipeline splits.
 def P5600CTISTD : ProcResource<1>;
 
 // CTISTD Pipeline
 // ---------------
 
 def P5600WriteJump : SchedWriteRes<[P5600IssueCTISTD, P5600CTISTD]>;
 def P5600WriteJumpAndLink : SchedWriteRes<[P5600IssueCTISTD, P5600CTISTD]> {
   let Latency = 2;
 }
 
-// b, beq, beql, bg[et]z, bl[et]z, bne, bnel, j, syscall, jal, bltzal, jalx,
+// b, beq, beql, bg[et]z, bl[et]z, bne, bnel, j, syscall, jal, bltzal,
 // jalr, jr.hb, jr
-def : ItinRW<[P5600WriteJump], [II_B, II_BCC, II_BCCZ, II_BCCZAL, II_J, II_JR]>;
-def : ItinRW<[P5600WriteJumpAndLink], [II_JAL, II_JALR]>;
+def : ItinRW<[P5600WriteJump], [II_B, II_BCC, II_BCCZ, II_BCCZAL, II_J, II_JR,
+                                II_JR_HB, II_DERET, II_ERET, II_ERETNC, 
+                                II_SYSCALL, II_BREAK, II_SDBBP, II_SSNOP,
+                                II_TEQ, II_TEQI, II_TGE, II_TGEI, II_TGEIU,
+                                II_TGEU, II_TLT, II_TLTI, II_TLTU, II_TNE,
+                                II_TNEI, II_TRAP, II_TTLTIU, II_WAIT,
+                                II_PAUSE]>;
+
+def : ItinRW<[P5600WriteJumpAndLink], [II_JAL, II_JALR, II_JALR_HB]>;
+
+def P5600COP0 : SchedWriteRes<[P5600IssueCTISTD, P5600CTISTD]>;
 
+def : ItinRW<[P5600COP0], [II_TLBINV, II_TLBINVF, II_TLBP, II_TLBR, II_TLBWI,
+                           II_TLBWR, II_MFC0, II_MTC0]>;
 // LDST Pipeline
 // -------------
 
 def P5600WriteLoad : SchedWriteRes<[P5600IssueLDST]> {
   let Latency = 4;
 }
 
 def P5600WriteLoadShifted : SchedWriteRes<[P5600IssueLDST, P5600CTISTD]> {
   let Latency = 4;
 }
 
-def P5600WritePref : SchedWriteRes<[P5600IssueLDST]>;
+def P5600WriteCache : SchedWriteRes<[P5600IssueLDST]>;
 
 def P5600WriteStore : SchedWriteRes<[P5600IssueLDST, P5600CTISTD]> {
   // FIXME: This is a bit pessimistic. P5600CTISTD is only used during cycle 2
   //        not during 0, 1, and 2.
   let ResourceCycles = [ 1, 3 ];
 }
 
 def P5600WriteGPRFromBypass : SchedWriteRes<[P5600IssueLDST]> {
   let Latency = 2;
 }
 
 def P5600WriteStoreFromOtherUnits : SchedWriteRes<[P5600IssueLDST]>;
 def P5600WriteLoadToOtherUnits : SchedWriteRes<[P5600IssueLDST]> {
   let Latency = 0;
 }
 
 // l[bhw], l[bh]u, ll
-def : ItinRW<[P5600WriteLoad], [II_LB, II_LBU, II_LH, II_LHU, II_LW, II_LWU]>;
+def : ItinRW<[P5600WriteLoad], [II_LB, II_LBE, II_LBU, II_LBUE, II_LH, II_LHE,
+                                II_LHU, II_LHUE, II_LW, II_LWE, II_LL, II_LLE,
+                                II_LWPC]>;
 
 // lw[lr]
-def : ItinRW<[P5600WriteLoadShifted], [II_LWL, II_LWR]>;
+def : ItinRW<[P5600WriteLoadShifted], [II_LWL, II_LWLE, II_LWR, II_LWRE]>;
 
 // s[bhw], sw[lr]
-def : ItinRW<[P5600WriteStore], [II_SB, II_SH, II_SW, II_SWL, II_SWR]>;
-
-// pref
-// (this instruction does not exist in the backend yet)
-def : ItinRW<[P5600WritePref], []>;
-
-// sc
-// (this instruction does not exist in the backend yet)
-def : ItinRW<[P5600WriteStore], []>;
+def : ItinRW<[P5600WriteStore], [II_SB, II_SBE, II_SH, II_SHE, II_SW, II_SWE,
+                                 II_SWL, II_SWLE, II_SWR, II_SWRE, II_SC,
+                                 II_SCE]>;
+
+// pref, cache, sync, synci
+def : ItinRW<[P5600WriteCache], [II_PREF, II_PREFE, II_CACHE, II_CACHEE,
+                                 II_SYNC, II_SYNCI]>;
 
 // LDST is also used in moves from general purpose registers to floating point
 // and MSA.
 def P5600WriteMoveGPRToOtherUnits : SchedWriteRes<[P5600IssueLDST]> {
   let Latency = 0;
 }
 
 // AL2 Pipeline
def P5600WriteAL2DivU : SchedWriteRes<[P5600IssueAL2, P5600AL2Div]> {
   let ResourceCycles = [1, 34];
 }
 def P5600WriteAL2Mul : SchedWriteRes<[P5600IssueAL2]> { let Latency = 3; }
 def P5600WriteAL2Mult: SchedWriteRes<[P5600IssueAL2]> { let Latency = 5; }
 def P5600WriteAL2MAdd: SchedWriteRes<[P5600IssueAL2, P5600CTISTD]> {
   let Latency = 5;
 }
 
-// clo, clz, di, mfhi, mflo
-def : ItinRW<[P5600WriteAL2], [II_CLO, II_CLZ, II_MFHI_MFLO]>;
+// clo, clz, di, ei, mfhi, mflo
+def : ItinRW<[P5600WriteAL2], [II_CLO, II_CLZ, II_DI, II_EI, II_MFHI_MFLO]>;
 
 // ehb, rdhwr, rdpgpr, wrpgpr, wsbh
-def : ItinRW<[P5600WriteAL2ShadowMov], [II_RDHWR]>;
+def : ItinRW<[P5600WriteAL2ShadowMov], [II_EHB, II_RDHWR, II_WSBH]>;
 
 // mov[nz]
 def : ItinRW<[P5600WriteAL2CondMov], [II_MOVN, II_MOVZ]>;
 
 // divu?
 def : ItinRW<[P5600WriteAL2Div], [II_DIV]>;
 def : ItinRW<[P5600WriteAL2DivU], [II_DIVU]>;
 
 // mul
 def : ItinRW<[P5600WriteAL2Mul], [II_MUL]>;
 // multu?, multu?
 def : ItinRW<[P5600WriteAL2Mult], [II_MULT, II_MULTU]>;
 // maddu?, msubu?, mthi, mtlo
 def : ItinRW<[P5600WriteAL2MAdd],
              [II_MADD, II_MADDU, II_MSUB, II_MSUBU, II_MTHI_MTLO]>;
 
 // ext, ins
-def : ItinRW<[P5600WriteAL2BitExt],
-             [II_EXT, II_INS]>;
+def : ItinRW<[P5600WriteAL2BitExt], [II_EXT, II_INS]>;
 
 // Either ALU or AL2 Pipelines
 // ---------------------------
 //
 // Some instructions can choose between ALU and AL2, but once dispatched to
 // ALQ or AGQ respectively they are committed to that path.
 // The decision is based on the outcome of the most recent selection when the
 // choice was last available. For now, we assume ALU is always chosen.
 
 def P5600WriteEitherALU : SchedWriteVariant<
   // FIXME: Implement selection predicate
   [SchedVar<SchedPredicate<[{1}]>, [P5600WriteALU]>,
    SchedVar<SchedPredicate<[{0}]>, [P5600WriteAL2]>
   ]>;
 
 // add, addi, addiu, addu, andi, ori, rotr, se[bh], sllv?, sr[al]v?, slt, sltu,
 // xori
 def : ItinRW<[P5600WriteEitherALU],
-             [II_ADDI, II_ADDIU, II_ANDI, II_ORI, II_ROTR, II_SEB, II_SEH,
+             [II_ADD, II_ADDI, II_ADDIU, II_ANDI, II_ORI, II_ROTR, II_SEB, II_SEH,
               II_SLT_SLTU, II_SLL, II_SRA, II_SRL, II_XORI, II_ADDU, II_SLLV,
-              II_SRAV, II_SRLV]>;
+              II_SRAV, II_SRLV, II_LSA]>;
+def : InstRW<[], (instrs COPY)>;
 
 // FPU Pipelines
 // =============
 
 def P5600FPQ : ProcResource<3> { let BufferSize = 16; }
 def P5600IssueFPUS : ProcResource<1> { let Super = P5600FPQ; }
 def P5600IssueFPUL : ProcResource<1> { let Super = P5600FPQ; }
 def P5600IssueFPULoad : ProcResource<1> { let Super = P5600FPQ; }
 
 def P5600FPUDivSqrt : ProcResource<2>;
 
 def P5600WriteFPUS : SchedWriteRes<[P5600IssueFPUS]>;
 def P5600WriteFPUL : SchedWriteRes<[P5600IssueFPUL]> { let Latency = 4; }
 def P5600WriteFPUL_MADDSUB : SchedWriteRes<[P5600IssueFPUL]> { let Latency = 6; }
+def P5600WriteFPUDivI : SchedWriteRes<[P5600IssueFPUL, P5600FPUDivSqrt]> {
+  // Best/Common/Worst case = 7 / 23 / 27
+  let Latency = 23; // Using common case
+  let ResourceCycles = [ 1, 23 ];
+}
 def P5600WriteFPUDivS : SchedWriteRes<[P5600IssueFPUL, P5600FPUDivSqrt]> {
   // Best/Common/Worst case = 7 / 23 / 27
   let Latency = 23; // Using common case
   let ResourceCycles = [ 1, 23 ];
 }
 def P5600WriteFPUDivD : SchedWriteRes<[P5600IssueFPUL, P5600FPUDivSqrt]> {
   // Best/Common/Worst case = 7 / 31 / 35
   let Latency = 31; // Using common case

 def P5600WriteFPUSqrtD : SchedWriteRes<[P5600IssueFPUL, P5600FPUDivSqrt]> {
   // Best/Common/Worst case = 7 / 35 / 39
   let Latency = 35; // Using common case
   let ResourceCycles = [ 1, 35 ];
 }
 def P5600WriteMSAShortLogic : SchedWriteRes<[P5600IssueFPUS]>;
 def P5600WriteMSAShortInt : SchedWriteRes<[P5600IssueFPUS]> { let Latency = 2; }
 def P5600WriteMoveOtherUnitsToFPU : SchedWriteRes<[P5600IssueFPUS]>;
+def P5600WriteMSAOther3 : SchedWriteRes<[P5600IssueFPUS]> { let Latency = 3; }
+def P5600WriteMSALongInt : SchedWriteRes<[P5600IssueFPUS]> { let Latency = 5; }
+
+// vshf.[bhwd], binsl.[bhwd], binsr.[bhwd], insert.[bhwd], sld?.[bhwd],
+// bset.[bhwd], bclr.[bhwd], bneg.[bhwd], bsel_v, bseli_b
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^VSHF_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^(BINSL|BINSLI)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^(BINSR|BINSRI)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^INSERT_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^(SLD|SLDI)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^(BSET|BSETI)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^(BCLR|BCLRI)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^(BNEG|BNEGI)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^(BSEL_V|BSELI_B)$")>;
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^BMN*Z.*$")>;
+
+// pcnt.[bhwd], sat_s.[bhwd], sat_u.bhwd]
+def : InstRW<[P5600WriteMSAOther3], (instregex "^PCNT_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAOther3], (instregex "^SAT_(S|U)_[BHWD]$")>;
+
+// bnz.[bhwdv], cfcmsa, ctcmsa
+def : InstRW<[P5600WriteMSAShortLogic], (instregex "^(BNZ|BZ)_[BHWDV]$")>;
+def : InstRW<[P5600WriteMSAShortLogic], (instregex "^C(F|T)CMSA$")>;
 
 // FPUS is also used in moves from floating point and MSA registers to general
 // purpose registers.
 def P5600WriteMoveFPUSToOtherUnits : SchedWriteRes<[P5600IssueFPUS]> {
   let Latency = 0;
 }
 
 // FPUL is also used in moves from floating point and MSA registers to general
 // purpose registers.
 def P5600WriteMoveFPULToOtherUnits : SchedWriteRes<[P5600IssueFPUL]>;
 
 // Short Pipe
 // ----------
 //
 // abs.[ds], abs.ps, bc1[tf]l?, mov[tf].[ds], mov[tf], mov.[ds], [cm][ft]c1,
 // m[ft]hc1, neg.[ds], neg.ps, nor.v, nori.b, or.v, ori.b, xor.v, xori.b,
 // sdxc1, sdc1, st.[bhwd], swc1, swxc1
 def : ItinRW<[P5600WriteFPUS], [II_ABS, II_MOVF_D, II_MOVF_S, II_MOVT_D,
                                 II_MOVT_S, II_MOV_D, II_MOV_S, II_NEG]>;
 
 // adds_a.[bhwd], adds_[asu].[bhwd], addvi?.[bhwd], asub_[us].[bhwd],
-// aver?_[us].[bhwd]
+// aver?_[us].[bhwd], shf.[bhw], fill[bhwd], splat?.[bhwd]
 def : InstRW<[P5600WriteMSAShortInt], (instregex "^ADD_A_[BHWD]$")>;
 def : InstRW<[P5600WriteMSAShortInt], (instregex "^ADDS_[ASU]_[BHWD]$")>;
 // TODO: ADDVI_[BHW] might be 1 cycle latency rather than 2. Need to confirm it.
 def : InstRW<[P5600WriteMSAShortInt], (instregex "^ADDVI?_[BHWD]$")>;
 def : InstRW<[P5600WriteMSAShortInt], (instregex "^ASUB_[US].[BHWD]$")>;
 def : InstRW<[P5600WriteMSAShortInt], (instregex "^AVER?_[US].[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^SHF_[BHW]$")>;
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^FILL_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^(SPLAT|SPLATI)_[BHWD]$")>;
 
 // and.v, andi.b, move.v, ldi.[bhwd]
 def : InstRW<[P5600WriteMSAShortLogic], (instregex "^MOVE_V$")>;
 def : InstRW<[P5600WriteMSAShortLogic], (instregex "^LDI_[BHWD]$")>;
 def : InstRW<[P5600WriteMSAShortLogic], (instregex "^(AND|OR|[XN]OR)_V$")>;
 def : InstRW<[P5600WriteMSAShortLogic], (instregex "^(AND|OR|[XN]OR)I_B$")>;
 
+// vshf.[bhwd], binsl.[bhwd], binsr.[bhwd], insert.[bhwd], sld?.[bhwd],
+// bset.[bhwd], bclr.[bhwd], bneg.[bhwd], bsel_v, bseli_b
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^VSHF_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^(BINSL|BINSLI)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^(BINSR|BINSRI)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^INSERT_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^(SLD|SLDI)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^(BSET|BSETI)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^(BCLR|BCLRI)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^(BNEG|BNEGI)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^(BSEL_V|BSELI_B)$")>;
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^BMN*Z.*$")>;
+
+// pcnt.[bhwd], sat_s.[bhwd], sat_u.bhwd]
+def : InstRW<[P5600WriteMSAOther3], (instregex "^PCNT_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAOther3], (instregex "^SAT_(S|U)_[BHWD]$")>;
+
+// fexp2_w, fexp2_d
+def : InstRW<[P5600WriteFPUS], (instregex "^FEXP2_(W|D)$")>;
+
+// compare, converts, round to int, floating point truncate.
+def : InstRW<[P5600WriteFPUS], (instregex "^(CLT|CLTI)_(S|U)_[BHWD]$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^(CLE|CLEI)_(S|U)_[BHWD]$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^(CEQ|CEQI)_[BHWD]$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^CMP_UN_(S|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^CMP_UEQ_(S|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^CMP_EQ_(S|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^CMP_LT_(S|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^CMP_ULT_(S|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^CMP_LE_(S|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^CMP_ULE_(S|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FS(AF|EQ|LT|LE|NE|OR)_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FSUEQ_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FSULE_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FSULT_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FSUNE_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FSUN_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FCAF_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FCEQ_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FCLE_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FCLT_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FCNE_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FCOR_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FCUEQ_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FCULE_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FCULT_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FCUNE_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FCUN_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FABS_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FFINT_(U|S)_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FFQL_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FFQR_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FTINT_(U|S)_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FRINT_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FTQ_(H|W)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FTRUNC_(U|S)_(W|D)$")>;
+
+// fexdo.[hw], fexupl.[wd], fexupr.[wd]
+def : InstRW<[P5600WriteFPUS], (instregex "^FEXDO_(H|W)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FEXUPL_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FEXUPR_(W|D)$")>;
+
+// fclass.[wd], fmax.[wd], fmax_a.[wd], fmin.[wd], fmin_a.[wd], flog2.[wd]
+def : InstRW<[P5600WriteFPUS], (instregex "^FCLASS_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FMAX_A_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FMAX_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FMIN_A_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FMIN_(W|D)$")>;
+def : InstRW<[P5600WriteFPUS], (instregex "^FLOG2_(W|D)$")>;
+
+// interleave right/left, interleave even/odd, insert
+def : InstRW<[P5600WriteMSAShortLogic], (instregex "^(ILVR|ILVL)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortLogic], (instregex "^(ILVEV|ILVOD)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortLogic], (instregex "^INSVE_[BHWD]$")>;
+
+// subs_?.[bhwd], subsus_?.[bhwd], subsuu_?.[bhwd], subvi.[bhwd], subv.[bhwd],
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^SUBS_(S|U)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^SUBSUS_(S|U)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^SUBSUU_(S|U)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^SUBVI_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortInt], (instregex "^SUBV_[BHWD]$")>;
+
+// mod_[su].[bhwd], div_[su].[bhwd]
+def : InstRW<[P5600WriteFPUDivI], (instregex "^MOD_(S|U)_[BHWD]$")>;
+def : InstRW<[P5600WriteFPUDivI], (instregex "^DIV_(S|U)_[BHWD]$")>;
+
+// hadd_[su].[bhwd], hsub_[su].[bhwd], max_[sua].[bhwd], min_[sua].[bhwd],
+// maxi_[su].[bhwd], mini_[su].[bhwd], sra?.[bhwd], srar?.[bhwd], srlr.[bhwd],
+// sll?.[bhwd], pckev.[bhwd], pckod.[bhwd], nloc.[bhwd], nlzc.[bhwd],
+// insve.[bhwd]
+def : InstRW<[P5600WriteMSAShortLogic], (instregex "^HADD_(S|U)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortLogic], (instregex "^HSUB_(S|U)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortLogic], (instregex "^(MAX|MIN)_S_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortLogic], (instregex "^(MAX|MIN)_U_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortLogic], (instregex "^(MAX|MIN)_A_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortLogic], (instregex "^(MAXI|MINI)_(S|U)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortLogic], (instregex "^(SRA|SRAI)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortLogic], (instregex "^(SRL|SRLI)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortLogic], (instregex "^(SRAR|SRARI)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortLogic], (instregex "^(SRLR|SRLRI)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortLogic], (instregex "^(SLL|SLLI)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortLogic], (instregex "^(PCKEV|PCKOD)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortLogic], (instregex "^(NLOC|NLZC)_[BHWD]$")>;
+def : InstRW<[P5600WriteMSAShortLogic], (instregex "^INSVE_[BHWD]$")>;
+
 // Long Pipe
 // ----------
 //
 // add.[ds], add.ps, cvt.d.[sw], cvt.s.[dw], cvt.w.[sd], cvt.[sw].ps,
 // cvt.ps.[sw], c.<cc>.[ds], c.<cc>.ps, mul.[ds], mul.ps, sub.[ds], sub.ps,
 // trunc.w.[ds], trunc.w.ps
 def : ItinRW<[P5600WriteFPUL],
              [II_ADD_D, II_ADD_S, II_CVT, II_C_CC_D, II_C_CC_S, II_MUL_D,
               II_MUL_S, II_SUB_D, II_SUB_S, II_TRUNC]>;
 
 // div.[ds], div.ps
 def : ItinRW<[P5600WriteFPUDivS], [II_DIV_S]>;
 def : ItinRW<[P5600WriteFPUDivD], [II_DIV_D]>;
 
 // sqrt.[ds], sqrt.ps
 def : ItinRW<[P5600WriteFPUSqrtS], [II_SQRT_S]>;
 def : ItinRW<[P5600WriteFPUSqrtD], [II_SQRT_D]>;
 
+// frcp.[wd], frsqrt.[wd]
+def : InstRW<[P5600WriteFPURsqrtD], (instregex "^FRCP_(W|D)$")>;
+def : InstRW<[P5600WriteFPURsqrtD], (instregex "^FRSQRT_(W|D)$")>;
+
+// fmadd.[wd], fmsubb.[wd], fdiv.[wd], fsqrt.[wd], fmul.[wd], fadd.[wd],
+// fsub.[wd]
+def : InstRW<[P5600WriteFPUL_MADDSUB], (instregex "^FMADD_(W|D)$")>;
+def : InstRW<[P5600WriteFPUL_MADDSUB], (instregex "^FMSUB_(W|D)$")>;
+def : InstRW<[P5600WriteFPUDivS], (instregex "^FDIV_W$")>;
+def : InstRW<[P5600WriteFPUDivD], (instregex "^FDIV_D$")>;
+def : InstRW<[P5600WriteFPUSqrtS], (instregex "^FSQRT_W$")>;
+def : InstRW<[P5600WriteFPUSqrtD], (instregex "^FSQRT_D$")>;
+def : InstRW<[P5600WriteFPUL], (instregex "^FMUL_(W|D)$")>;
+def : InstRW<[P5600WriteFPUL], (instregex "^FADD_(W|D)$")>;
+def : InstRW<[P5600WriteFPUL], (instregex "^FSUB_(W|D)$")>;
+
+// dpadd_?.[bhwd], dpsub_?.[bhwd], dotp_?.[bhwd], msubv.[bhwd], maddv.[bhwd]
+// mulv.[bhwd].
+def : InstRW<[P5600WriteMSALongInt], (instregex "^DPADD_(S|U)_[HWD]$")>;
+def : InstRW<[P5600WriteMSALongInt], (instregex "^DPSUB_(S|U)_[HWD]$")>;
+def : InstRW<[P5600WriteMSALongInt], (instregex "^DOTP_(S|U)_[HWD]$")>;
+def : InstRW<[P5600WriteMSALongInt], (instregex "^MSUBV_[BHWD]$")>;
+def : InstRW<[P5600WriteMSALongInt], (instregex "^MADDV_[BHWD]$")>;
+def : InstRW<[P5600WriteMSALongInt], (instregex "^MULV_[BHWD]$")>;
+
+def : InstRW<[P5600WriteMSALongInt], (instregex "^MADDR_Q_[HW]$")>;
+def : InstRW<[P5600WriteMSALongInt], (instregex "^MADD_Q_[HW]$")>;
+def : InstRW<[P5600WriteMSALongInt], (instregex "^MSUBR_Q_[HW]$")>;
+def : InstRW<[P5600WriteMSALongInt], (instregex "^MSUB_Q_[HW]$")>;
+def : InstRW<[P5600WriteMSALongInt], (instregex "^MULR_Q_[HW]$")>;
+def : InstRW<[P5600WriteMSALongInt], (instregex "^MUL_Q_[HW]$")>;
+
 // madd.[ds], msub.[ds], nmadd.[ds], nmsub.[ds],
 // Operand 0 is read on cycle 5. All other operands are read on operand 0.
 def : ItinRW<[SchedReadAdvance<5>, P5600WriteFPUL_MADDSUB],
              [II_MADD_D, II_MADD_S, II_MSUB_D, II_MSUB_S, II_NMADD_D,
               II_NMADD_S, II_NMSUB_D, II_NMSUB_S]>;
 
 // madd.ps, msub.ps, nmadd.ps, nmsub.ps
 // Operand 0 and 1 are read on cycle 5. All others are read on operand 0.

 //        current aggregates the resources and ignores the exact cycle they are
 //        used.
 def P5600WriteLoadFPU : WriteSequence<[P5600WriteLoadToOtherUnits,
                                        P5600WriteLoadOtherUnitsToFPU]>;
 
 // ctc1, mtc1, mthc1
 def : ItinRW<[P5600WriteMoveGPRToFPU], [II_CTC1, II_MTC1, II_MTHC1]>;
 
+// copy.[su]_[bhwd]
+def : InstRW<[P5600WriteMoveFPUToGPR], (instregex "^COPY_U_[BHW]$")>;
+def : InstRW<[P5600WriteMoveFPUToGPR], (instregex "^COPY_S_[BHWD]$")>;
+
 // bc1[ft], cfc1, mfc1, mfhc1, movf, movt
 def : ItinRW<[P5600WriteMoveFPUToGPR],
-             [II_BC1F, II_BC1T, II_CFC1, II_MFC1, II_MFHC1, II_MOVF, II_MOVT]>;
+             [II_BC1F, II_BC1FL, II_BC1T, II_BC1TL, II_CFC1, II_MFC1, II_MFHC1, II_MOVF, II_MOVT]>;
 
 // swc1, swxc1, st.[bhwd]
-def : ItinRW<[P5600WriteStoreFPUS], [II_SWC1, II_SWXC1]>;
+def : ItinRW<[P5600WriteStoreFPUS], [II_SDC1, II_SDXC1, II_SUXC1, II_SWC1,
+                                     II_SWXC1]>;
 def : InstRW<[P5600WriteStoreFPUS], (instregex "^ST_[BHWD]$")>;
 
 // movn.[ds], movz.[ds]
 def : ItinRW<[P5600WriteStoreFPUL], [II_MOVN_D, II_MOVN_S, II_MOVZ_D, II_MOVZ_S]>;
 
 // l[dw]x?c1, ld.[bhwd]
-def : ItinRW<[P5600WriteLoadFPU], [II_LDC1, II_LDXC1, II_LWC1, II_LWXC1]>;
+def : ItinRW<[P5600WriteLoadFPU], [II_LDC1, II_LDXC1, II_LWC1, II_LWXC1, II_LUXC1]>;
 def : InstRW<[P5600WriteLoadFPU], (instregex "LD_[BHWD]")>;
 
 // Unsupported Instructions
 // ========================
 //
 // The following instruction classes are never valid on P5600.
 //   II_DADDIU, II_DADDU, II_DMFC1, II_DMTC1, II_DMULT, II_DMULTU, II_DROTR,
 //   II_DROTR32, II_DROTRV, II_DDIV, II_DSLL, II_DSLL32, II_DSLLV, II_DSRA,
 //   II_DSRA32, II_DSRAV, II_DSRL, II_DSRL32, II_DSRLV, II_DSUBU, II_DDIVU,
-//   II_JALRC, II_LD, II_LD[LR], II_LUXC1, II_RESTORE, II_SAVE, II_SD, II_SDC1,
-//   II_SDL, II_SDR, II_SDXC1
+//   II_JALRC, II_LD, II_LD[LR], II_RESTORE, II_SAVE, II_SD, II_SDC1, II_SD[LR]
 //
 // The following instructions are never valid on P5600.
-//   addq.ph, rdhwr, repl.ph, repl.qb, subq.ph, subu_s.qb
+//   addq.ph, repl.ph, repl.qb, subq.ph, subu_s.qb
 //
 // Guesswork
 // =========
 //
 // This section is largely temporary guesswork.
 
 // ceil.[lw].[ds], floor.[lw].[ds]
 // Reason behind guess: trunc.[lw].ds and the various cvt's are in FPUL
 def : ItinRW<[P5600WriteFPUL], [II_CEIL, II_FLOOR, II_ROUND]>;
 
 // rotrv
 // Reason behind guess: rotr is in the same category and the two register forms
 //                      generally follow the immediate forms in this category
 def : ItinRW<[P5600WriteEitherALU], [II_ROTRV]>;
 }