llvm-project/llvm/lib/Target/X86/X86SchedBroadwell.td

1743 lines
69 KiB
TableGen

//=- X86SchedBroadwell.td - X86 Broadwell Scheduling ---------*- tablegen -*-=//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file defines the machine model for Broadwell to support instruction
// scheduling and other instruction cost heuristics.
//
//===----------------------------------------------------------------------===//
def BroadwellModel : SchedMachineModel {
// All x86 instructions are modeled as a single micro-op, and BW can decode 4
// instructions per cycle.
let IssueWidth = 4;
let MicroOpBufferSize = 192; // Based on the reorder buffer.
let LoadLatency = 5;
let MispredictPenalty = 16;
// Based on the LSD (loop-stream detector) queue size and benchmarking data.
let LoopMicroOpBufferSize = 50;
// This flag is set to allow the scheduler to assign a default model to
// unrecognized opcodes.
let CompleteModel = 0;
}
let SchedModel = BroadwellModel in {
// Broadwell can issue micro-ops to 8 different ports in one cycle.
// Ports 0, 1, 5, and 6 handle all computation.
// Port 4 gets the data half of stores. Store data can be available later than
// the store address, but since we don't model the latency of stores, we can
// ignore that.
// Ports 2 and 3 are identical. They handle loads and the address half of
// stores. Port 7 can handle address calculations.
def BWPort0 : ProcResource<1>;
def BWPort1 : ProcResource<1>;
def BWPort2 : ProcResource<1>;
def BWPort3 : ProcResource<1>;
def BWPort4 : ProcResource<1>;
def BWPort5 : ProcResource<1>;
def BWPort6 : ProcResource<1>;
def BWPort7 : ProcResource<1>;
// Many micro-ops are capable of issuing on multiple ports.
def BWPort01 : ProcResGroup<[BWPort0, BWPort1]>;
def BWPort23 : ProcResGroup<[BWPort2, BWPort3]>;
def BWPort237 : ProcResGroup<[BWPort2, BWPort3, BWPort7]>;
def BWPort04 : ProcResGroup<[BWPort0, BWPort4]>;
def BWPort05 : ProcResGroup<[BWPort0, BWPort5]>;
def BWPort06 : ProcResGroup<[BWPort0, BWPort6]>;
def BWPort15 : ProcResGroup<[BWPort1, BWPort5]>;
def BWPort16 : ProcResGroup<[BWPort1, BWPort6]>;
def BWPort56 : ProcResGroup<[BWPort5, BWPort6]>;
def BWPort015 : ProcResGroup<[BWPort0, BWPort1, BWPort5]>;
def BWPort056 : ProcResGroup<[BWPort0, BWPort5, BWPort6]>;
def BWPort0156: ProcResGroup<[BWPort0, BWPort1, BWPort5, BWPort6]>;
// 60 Entry Unified Scheduler
def BWPortAny : ProcResGroup<[BWPort0, BWPort1, BWPort2, BWPort3, BWPort4,
BWPort5, BWPort6, BWPort7]> {
let BufferSize=60;
}
// Integer division issued on port 0.
def BWDivider : ProcResource<1>;
// FP division and sqrt on port 0.
def BWFPDivider : ProcResource<1>;
// Integer loads are 5 cycles, so ReadAfterLd registers needn't be available until 5
// cycles after the memory operand.
def : ReadAdvance<ReadAfterLd, 5>;
// Vector loads are 5/5/6 cycles, so ReadAfterVec*Ld registers needn't be available
// until 5/5/6 cycles after the memory operand.
def : ReadAdvance<ReadAfterVecLd, 5>;
def : ReadAdvance<ReadAfterVecXLd, 5>;
def : ReadAdvance<ReadAfterVecYLd, 6>;
def : ReadAdvance<ReadInt2Fpu, 0>;
// Many SchedWrites are defined in pairs with and without a folded load.
// Instructions with folded loads are usually micro-fused, so they only appear
// as two micro-ops when queued in the reservation station.
// This multiclass defines the resource usage for variants with and without
// folded loads.
multiclass BWWriteResPair<X86FoldableSchedWrite SchedRW,
list<ProcResourceKind> ExePorts,
int Lat, list<int> Res = [1], int UOps = 1,
int LoadLat = 5> {
// Register variant is using a single cycle on ExePort.
def : WriteRes<SchedRW, ExePorts> {
let Latency = Lat;
let ResourceCycles = Res;
let NumMicroOps = UOps;
}
// Memory variant also uses a cycle on port 2/3 and adds LoadLat cycles to
// the latency (default = 5).
def : WriteRes<SchedRW.Folded, !listconcat([BWPort23], ExePorts)> {
let Latency = !add(Lat, LoadLat);
let ResourceCycles = !listconcat([1], Res);
let NumMicroOps = !add(UOps, 1);
}
}
// A folded store needs a cycle on port 4 for the store data, and an extra port
// 2/3/7 cycle to recompute the address.
def : WriteRes<WriteRMW, [BWPort237,BWPort4]>;
// Arithmetic.
defm : BWWriteResPair<WriteALU, [BWPort0156], 1>; // Simple integer ALU op.
defm : BWWriteResPair<WriteADC, [BWPort06], 1>; // Integer ALU + flags op.
// Integer multiplication.
defm : BWWriteResPair<WriteIMul8, [BWPort1], 3>;
defm : BWWriteResPair<WriteIMul16, [BWPort1,BWPort06,BWPort0156], 4, [1,1,2], 4>;
defm : X86WriteRes<WriteIMul16Imm, [BWPort1,BWPort0156], 4, [1,1], 2>;
defm : X86WriteRes<WriteIMul16ImmLd, [BWPort1,BWPort0156,BWPort23], 8, [1,1,1], 3>;
defm : BWWriteResPair<WriteIMul16Reg, [BWPort1], 3>;
defm : BWWriteResPair<WriteIMul32, [BWPort1,BWPort06,BWPort0156], 4, [1,1,1], 3>;
defm : BWWriteResPair<WriteIMul32Imm, [BWPort1], 3>;
defm : BWWriteResPair<WriteIMul32Reg, [BWPort1], 3>;
defm : BWWriteResPair<WriteIMul64, [BWPort1,BWPort5], 4, [1,1], 2>;
defm : BWWriteResPair<WriteIMul64Imm, [BWPort1], 3>;
defm : BWWriteResPair<WriteIMul64Reg, [BWPort1], 3>;
def : WriteRes<WriteIMulH, []> { let Latency = 3; }
// TODO: Why isn't the BWDivider used consistently?
defm : X86WriteRes<WriteDiv8, [BWPort0, BWDivider], 25, [1, 10], 1>;
defm : X86WriteRes<WriteDiv16, [BWPort0,BWPort1,BWPort5,BWPort6,BWPort01,BWPort0156], 80, [7,7,3,3,1,11], 32>;
defm : X86WriteRes<WriteDiv32, [BWPort0,BWPort1,BWPort5,BWPort6,BWPort01,BWPort0156], 80, [7,7,3,3,1,11], 32>;
defm : X86WriteRes<WriteDiv64, [BWPort0,BWPort1,BWPort5,BWPort6,BWPort01,BWPort0156], 80, [7,7,3,3,1,11], 32>;
defm : X86WriteRes<WriteDiv8Ld, [BWPort0,BWPort1,BWPort5,BWPort23,BWPort0156], 34, [2,2,2,1,1], 8>;
defm : X86WriteRes<WriteDiv16Ld, [BWPort0,BWPort1,BWPort5,BWPort23,BWPort0156], 34, [2,2,2,1,1], 8>;
defm : X86WriteRes<WriteDiv32Ld, [BWPort0,BWPort1,BWPort5,BWPort23,BWPort0156], 34, [2,2,2,1,1], 8>;
defm : X86WriteRes<WriteDiv64Ld, [BWPort0,BWPort1,BWPort5,BWPort23,BWPort0156], 34, [2,2,2,1,1], 8>;
defm : X86WriteRes<WriteIDiv8, [BWPort0, BWDivider], 25, [1,10], 1>;
defm : X86WriteRes<WriteIDiv16, [BWPort0, BWDivider], 25, [1,10], 1>;
defm : X86WriteRes<WriteIDiv32, [BWPort0, BWDivider], 25, [1,10], 1>;
defm : X86WriteRes<WriteIDiv64, [BWPort0, BWDivider], 25, [1,10], 1>;
defm : X86WriteRes<WriteIDiv8Ld, [BWPort0,BWPort1,BWPort5,BWPort23,BWPort0156], 35, [2,2,2,1,1], 8>;
defm : X86WriteRes<WriteIDiv16Ld, [BWPort0,BWPort1,BWPort5,BWPort23,BWPort0156], 35, [2,2,2,1,1], 8>;
defm : X86WriteRes<WriteIDiv32Ld, [BWPort0,BWPort1,BWPort5,BWPort23,BWPort0156], 35, [2,2,2,1,1], 8>;
defm : X86WriteRes<WriteIDiv64Ld, [BWPort0,BWPort1,BWPort5,BWPort23,BWPort0156], 35, [2,2,2,1,1], 8>;
defm : X86WriteRes<WriteCMPXCHG,[BWPort06, BWPort0156], 5, [2, 3], 5>;
defm : X86WriteRes<WriteCMPXCHGRMW,[BWPort23, BWPort06, BWPort0156, BWPort237, BWPort4], 8, [1, 2, 1, 1, 1], 6>;
defm : X86WriteRes<WriteBSWAP32, [BWPort15], 1, [1], 1>;
defm : X86WriteRes<WriteBSWAP64, [BWPort06, BWPort15], 2, [1, 1], 2>;
defm : X86WriteRes<WriteXCHG, [BWPort0156], 2, [3], 3>;
defm : BWWriteResPair<WriteCRC32, [BWPort1], 3>;
def : WriteRes<WriteLEA, [BWPort15]>; // LEA instructions can't fold loads.
defm : BWWriteResPair<WriteCMOV, [BWPort06], 1>; // Conditional move.
defm : X86WriteRes<WriteFCMOV, [BWPort1], 3, [1], 1>; // x87 conditional move.
def : WriteRes<WriteSETCC, [BWPort06]>; // Setcc.
def : WriteRes<WriteSETCCStore, [BWPort06,BWPort4,BWPort237]> {
let Latency = 2;
let NumMicroOps = 3;
}
defm : X86WriteRes<WriteLAHFSAHF, [BWPort06], 1, [1], 1>;
defm : X86WriteRes<WriteBitTest, [BWPort06], 1, [1], 1>; // Bit Test instrs
defm : X86WriteRes<WriteBitTestImmLd, [BWPort06,BWPort23], 6, [1,1], 2>;
defm : X86WriteRes<WriteBitTestRegLd, [BWPort0156,BWPort23], 6, [1,1], 2>;
defm : X86WriteRes<WriteBitTestSet, [BWPort06], 1, [1], 1>; // Bit Test + Set instrs
defm : X86WriteRes<WriteBitTestSetImmLd, [BWPort06,BWPort23], 5, [1,1], 3>;
defm : X86WriteRes<WriteBitTestSetRegLd, [BWPort0156,BWPort23], 5, [1,1], 2>;
// Bit counts.
defm : BWWriteResPair<WriteBSF, [BWPort1], 3>;
defm : BWWriteResPair<WriteBSR, [BWPort1], 3>;
defm : BWWriteResPair<WriteLZCNT, [BWPort1], 3>;
defm : BWWriteResPair<WriteTZCNT, [BWPort1], 3>;
defm : BWWriteResPair<WritePOPCNT, [BWPort1], 3>;
// Integer shifts and rotates.
defm : BWWriteResPair<WriteShift, [BWPort06], 1>;
defm : BWWriteResPair<WriteShiftCL, [BWPort06,BWPort0156], 3, [2,1], 3>;
defm : BWWriteResPair<WriteRotate, [BWPort06], 1, [1], 1>;
defm : BWWriteResPair<WriteRotateCL, [BWPort06,BWPort0156], 3, [2,1], 3>;
// SHLD/SHRD.
defm : X86WriteRes<WriteSHDrri, [BWPort1], 3, [1], 1>;
defm : X86WriteRes<WriteSHDrrcl,[BWPort1,BWPort06,BWPort0156], 6, [1, 1, 2], 4>;
defm : X86WriteRes<WriteSHDmri, [BWPort1,BWPort23,BWPort237,BWPort0156], 9, [1, 1, 1, 1], 4>;
defm : X86WriteRes<WriteSHDmrcl,[BWPort1,BWPort23,BWPort237,BWPort06,BWPort0156], 11, [1, 1, 1, 1, 2], 6>;
// BMI1 BEXTR/BLS, BMI2 BZHI
defm : BWWriteResPair<WriteBEXTR, [BWPort06,BWPort15], 2, [1,1], 2>;
defm : BWWriteResPair<WriteBLS, [BWPort15], 1>;
defm : BWWriteResPair<WriteBZHI, [BWPort15], 1>;
// Loads, stores, and moves, not folded with other operations.
defm : X86WriteRes<WriteLoad, [BWPort23], 5, [1], 1>;
defm : X86WriteRes<WriteStore, [BWPort237, BWPort4], 1, [1,1], 1>;
defm : X86WriteRes<WriteStoreNT, [BWPort237, BWPort4], 1, [1,1], 2>;
defm : X86WriteRes<WriteMove, [BWPort0156], 1, [1], 1>;
// Idioms that clear a register, like xorps %xmm0, %xmm0.
// These can often bypass execution ports completely.
def : WriteRes<WriteZero, []>;
// Treat misc copies as a move.
def : InstRW<[WriteMove], (instrs COPY)>;
// Branches don't produce values, so they have no latency, but they still
// consume resources. Indirect branches can fold loads.
defm : BWWriteResPair<WriteJump, [BWPort06], 1>;
// Floating point. This covers both scalar and vector operations.
defm : X86WriteRes<WriteFLD0, [BWPort01], 1, [1], 1>;
defm : X86WriteRes<WriteFLD1, [BWPort01], 1, [2], 2>;
defm : X86WriteRes<WriteFLDC, [BWPort01], 1, [2], 2>;
defm : X86WriteRes<WriteFLoad, [BWPort23], 5, [1], 1>;
defm : X86WriteRes<WriteFLoadX, [BWPort23], 5, [1], 1>;
defm : X86WriteRes<WriteFLoadY, [BWPort23], 6, [1], 1>;
defm : X86WriteRes<WriteFMaskedLoad, [BWPort23,BWPort5], 7, [1,2], 3>;
defm : X86WriteRes<WriteFMaskedLoadY, [BWPort23,BWPort5], 8, [1,2], 3>;
defm : X86WriteRes<WriteFStore, [BWPort237,BWPort4], 1, [1,1], 2>;
defm : X86WriteRes<WriteFStoreX, [BWPort237,BWPort4], 1, [1,1], 2>;
defm : X86WriteRes<WriteFStoreY, [BWPort237,BWPort4], 1, [1,1], 2>;
defm : X86WriteRes<WriteFStoreNT, [BWPort237,BWPort4], 1, [1,1], 2>;
defm : X86WriteRes<WriteFStoreNTX, [BWPort237,BWPort4], 1, [1,1], 2>;
defm : X86WriteRes<WriteFStoreNTY, [BWPort237,BWPort4], 1, [1,1], 2>;
defm : X86WriteRes<WriteFMaskedStore32, [BWPort0,BWPort4,BWPort237,BWPort15], 5, [1,1,1,1], 4>;
defm : X86WriteRes<WriteFMaskedStore32Y, [BWPort0,BWPort4,BWPort237,BWPort15], 5, [1,1,1,1], 4>;
defm : X86WriteRes<WriteFMaskedStore64, [BWPort0,BWPort4,BWPort237,BWPort15], 5, [1,1,1,1], 4>;
defm : X86WriteRes<WriteFMaskedStore64Y, [BWPort0,BWPort4,BWPort237,BWPort15], 5, [1,1,1,1], 4>;
defm : X86WriteRes<WriteFMove, [BWPort5], 1, [1], 1>;
defm : X86WriteRes<WriteFMoveX, [BWPort5], 1, [1], 1>;
defm : X86WriteRes<WriteFMoveY, [BWPort5], 1, [1], 1>;
defm : BWWriteResPair<WriteFAdd, [BWPort1], 3, [1], 1, 5>; // Floating point add/sub.
defm : BWWriteResPair<WriteFAddX, [BWPort1], 3, [1], 1, 5>; // Floating point add/sub (XMM).
defm : BWWriteResPair<WriteFAddY, [BWPort1], 3, [1], 1, 6>; // Floating point add/sub (YMM/ZMM).
defm : X86WriteResPairUnsupported<WriteFAddZ>;
defm : BWWriteResPair<WriteFAdd64, [BWPort1], 3, [1], 1, 5>; // Floating point double add/sub.
defm : BWWriteResPair<WriteFAdd64X, [BWPort1], 3, [1], 1, 5>; // Floating point double add/sub (XMM).
defm : BWWriteResPair<WriteFAdd64Y, [BWPort1], 3, [1], 1, 6>; // Floating point double add/sub (YMM/ZMM).
defm : X86WriteResPairUnsupported<WriteFAdd64Z>;
defm : BWWriteResPair<WriteFCmp, [BWPort1], 3, [1], 1, 5>; // Floating point compare.
defm : BWWriteResPair<WriteFCmpX, [BWPort1], 3, [1], 1, 5>; // Floating point compare (XMM).
defm : BWWriteResPair<WriteFCmpY, [BWPort1], 3, [1], 1, 6>; // Floating point compare (YMM/ZMM).
defm : X86WriteResPairUnsupported<WriteFCmpZ>;
defm : BWWriteResPair<WriteFCmp64, [BWPort1], 3, [1], 1, 5>; // Floating point double compare.
defm : BWWriteResPair<WriteFCmp64X, [BWPort1], 3, [1], 1, 5>; // Floating point double compare (XMM).
defm : BWWriteResPair<WriteFCmp64Y, [BWPort1], 3, [1], 1, 6>; // Floating point double compare (YMM/ZMM).
defm : X86WriteResPairUnsupported<WriteFCmp64Z>;
defm : BWWriteResPair<WriteFCom, [BWPort1], 3>; // Floating point compare to flags.
defm : BWWriteResPair<WriteFMul, [BWPort01], 3, [1], 1, 5>; // Floating point multiplication.
defm : BWWriteResPair<WriteFMulX, [BWPort01], 3, [1], 1, 5>; // Floating point multiplication (XMM).
defm : BWWriteResPair<WriteFMulY, [BWPort01], 3, [1], 1, 6>; // Floating point multiplication (YMM/ZMM).
defm : X86WriteResPairUnsupported<WriteFMulZ>;
defm : BWWriteResPair<WriteFMul64, [BWPort01], 3, [1], 1, 5>; // Floating point double multiplication.
defm : BWWriteResPair<WriteFMul64X, [BWPort01], 3, [1], 1, 5>; // Floating point double multiplication (XMM).
defm : BWWriteResPair<WriteFMul64Y, [BWPort01], 3, [1], 1, 6>; // Floating point double multiplication (YMM/ZMM).
defm : X86WriteResPairUnsupported<WriteFMul64Z>;
//defm : BWWriteResPair<WriteFDiv, [BWPort0,BWFPDivider], 11, [1,3], 1, 5>; // Floating point division.
defm : BWWriteResPair<WriteFDivX, [BWPort0,BWFPDivider], 11, [1,5], 1, 5>; // Floating point division (XMM).
defm : BWWriteResPair<WriteFDivY, [BWPort0,BWPort015,BWFPDivider], 17, [2,1,10], 3, 6>; // Floating point division (YMM).
defm : X86WriteResPairUnsupported<WriteFDivZ>;
//defm : BWWriteResPair<WriteFDiv64, [BWPort0,BWFPDivider], 14, [1,8], 1, 5>; // Floating point division.
defm : BWWriteResPair<WriteFDiv64X, [BWPort0,BWFPDivider], 14, [1,8], 1, 5>; // Floating point division (XMM).
defm : BWWriteResPair<WriteFDiv64Y, [BWPort0,BWPort015,BWFPDivider], 23, [2,1,16], 3, 6>; // Floating point division (YMM).
defm : X86WriteResPairUnsupported<WriteFDiv64Z>;
defm : X86WriteRes<WriteFSqrt, [BWPort0,BWFPDivider], 11, [1,4], 1>; // Floating point square root.
defm : X86WriteRes<WriteFSqrtLd, [BWPort0,BWPort23,BWFPDivider], 16, [1,1,7], 2>;
defm : BWWriteResPair<WriteFSqrtX, [BWPort0,BWFPDivider], 11, [1,7], 1, 5>; // Floating point square root (XMM).
defm : BWWriteResPair<WriteFSqrtY, [BWPort0,BWPort015,BWFPDivider], 21, [2,1,14], 3, 6>; // Floating point square root (YMM).
defm : X86WriteResPairUnsupported<WriteFSqrtZ>;
defm : X86WriteRes<WriteFSqrt64, [BWPort0,BWFPDivider], 16, [1,8], 1>; // Floating point double square root.
defm : X86WriteRes<WriteFSqrt64Ld, [BWPort0,BWPort23,BWFPDivider], 21, [1,1,14], 2>;
defm : BWWriteResPair<WriteFSqrt64X, [BWPort0,BWFPDivider], 16, [1,14],1, 5>; // Floating point double square root (XMM).
defm : BWWriteResPair<WriteFSqrt64Y, [BWPort0,BWPort015,BWFPDivider], 29, [2,1,28], 3, 6>; // Floating point double square root (YMM).
defm : X86WriteResPairUnsupported<WriteFSqrt64Z>;
defm : BWWriteResPair<WriteFSqrt80, [BWPort0,BWFPDivider], 23, [1,9]>; // Floating point long double square root.
defm : BWWriteResPair<WriteFRcp, [BWPort0], 5, [1], 1, 5>; // Floating point reciprocal estimate.
defm : BWWriteResPair<WriteFRcpX, [BWPort0], 5, [1], 1, 5>; // Floating point reciprocal estimate (XMM).
defm : BWWriteResPair<WriteFRcpY, [BWPort0,BWPort015], 11, [2,1], 3, 6>; // Floating point reciprocal estimate (YMM/ZMM).
defm : X86WriteResPairUnsupported<WriteFRcpZ>;
defm : BWWriteResPair<WriteFRsqrt, [BWPort0], 5, [1], 1, 5>; // Floating point reciprocal square root estimate.
defm : BWWriteResPair<WriteFRsqrtX,[BWPort0], 5, [1], 1, 5>; // Floating point reciprocal square root estimate (XMM).
defm : BWWriteResPair<WriteFRsqrtY,[BWPort0,BWPort015], 11, [2,1], 3, 6>; // Floating point reciprocal square root estimate (YMM/ZMM).
defm : X86WriteResPairUnsupported<WriteFRsqrtZ>;
defm : BWWriteResPair<WriteFMA, [BWPort01], 5, [1], 1, 5>; // Fused Multiply Add.
defm : BWWriteResPair<WriteFMAX, [BWPort01], 5, [1], 1, 5>; // Fused Multiply Add (XMM).
defm : BWWriteResPair<WriteFMAY, [BWPort01], 5, [1], 1, 6>; // Fused Multiply Add (YMM/ZMM).
defm : X86WriteResPairUnsupported<WriteFMAZ>;
defm : BWWriteResPair<WriteDPPD, [BWPort0,BWPort1,BWPort5], 9, [1,1,1], 3, 5>; // Floating point double dot product.
defm : BWWriteResPair<WriteDPPS, [BWPort0,BWPort1,BWPort5], 14, [2,1,1], 4, 5>; // Floating point single dot product.
defm : BWWriteResPair<WriteDPPSY, [BWPort0,BWPort1,BWPort5], 14, [2,1,1], 4, 6>; // Floating point single dot product (YMM).
defm : X86WriteResPairUnsupported<WriteDPPSZ>;
defm : BWWriteResPair<WriteFSign, [BWPort5], 1>; // Floating point fabs/fchs.
defm : X86WriteRes<WriteFRnd, [BWPort23], 6, [1], 1>; // Floating point rounding.
defm : X86WriteRes<WriteFRndY, [BWPort23], 6, [1], 1>; // Floating point rounding (YMM/ZMM).
defm : X86WriteResPairUnsupported<WriteFRndZ>;
defm : X86WriteRes<WriteFRndLd, [BWPort1,BWPort23], 11, [2,1], 3>;
defm : X86WriteRes<WriteFRndYLd, [BWPort1,BWPort23], 12, [2,1], 3>;
defm : BWWriteResPair<WriteFLogic, [BWPort5], 1, [1], 1, 5>; // Floating point and/or/xor logicals.
defm : BWWriteResPair<WriteFLogicY, [BWPort5], 1, [1], 1, 6>; // Floating point and/or/xor logicals (YMM/ZMM).
defm : X86WriteResPairUnsupported<WriteFLogicZ>;
defm : BWWriteResPair<WriteFTest, [BWPort0], 1, [1], 1, 5>; // Floating point TEST instructions.
defm : BWWriteResPair<WriteFTestY, [BWPort0], 1, [1], 1, 6>; // Floating point TEST instructions (YMM/ZMM).
defm : X86WriteResPairUnsupported<WriteFTestZ>;
defm : BWWriteResPair<WriteFShuffle, [BWPort5], 1, [1], 1, 5>; // Floating point vector shuffles.
defm : BWWriteResPair<WriteFShuffleY, [BWPort5], 1, [1], 1, 6>; // Floating point vector shuffles (YMM/ZMM).
defm : X86WriteResPairUnsupported<WriteFShuffleZ>;
defm : BWWriteResPair<WriteFVarShuffle, [BWPort5], 1, [1], 1, 5>; // Floating point vector variable shuffles.
defm : BWWriteResPair<WriteFVarShuffleY, [BWPort5], 1, [1], 1, 6>; // Floating point vector variable shuffles.
defm : X86WriteResPairUnsupported<WriteFVarShuffleZ>;
defm : BWWriteResPair<WriteFBlend, [BWPort015], 1, [1], 1, 5>; // Floating point vector blends.
defm : BWWriteResPair<WriteFBlendY, [BWPort015], 1, [1], 1, 6>; // Floating point vector blends.
defm : X86WriteResPairUnsupported<WriteFBlendZ>;
defm : BWWriteResPair<WriteFVarBlend, [BWPort5], 2, [2], 2, 5>; // Fp vector variable blends.
defm : BWWriteResPair<WriteFVarBlendY, [BWPort5], 2, [2], 2, 6>; // Fp vector variable blends.
defm : X86WriteResPairUnsupported<WriteFVarBlendZ>;
// FMA Scheduling helper class.
// class FMASC { X86FoldableSchedWrite Sched = WriteFAdd; }
// Vector integer operations.
defm : X86WriteRes<WriteVecLoad, [BWPort23], 5, [1], 1>;
defm : X86WriteRes<WriteVecLoadX, [BWPort23], 5, [1], 1>;
defm : X86WriteRes<WriteVecLoadY, [BWPort23], 6, [1], 1>;
defm : X86WriteRes<WriteVecLoadNT, [BWPort23], 5, [1], 1>;
defm : X86WriteRes<WriteVecLoadNTY, [BWPort23], 6, [1], 1>;
defm : X86WriteRes<WriteVecMaskedLoad, [BWPort23,BWPort5], 7, [1,2], 3>;
defm : X86WriteRes<WriteVecMaskedLoadY, [BWPort23,BWPort5], 8, [1,2], 3>;
defm : X86WriteRes<WriteVecStore, [BWPort237,BWPort4], 1, [1,1], 2>;
defm : X86WriteRes<WriteVecStoreX, [BWPort237,BWPort4], 1, [1,1], 2>;
defm : X86WriteRes<WriteVecStoreY, [BWPort237,BWPort4], 1, [1,1], 2>;
defm : X86WriteRes<WriteVecStoreNT, [BWPort237,BWPort4], 1, [1,1], 2>;
defm : X86WriteRes<WriteVecStoreNTY, [BWPort237,BWPort4], 1, [1,1], 2>;
defm : X86WriteRes<WriteVecMaskedStore, [BWPort0,BWPort4,BWPort237,BWPort15], 5, [1,1,1,1], 4>;
defm : X86WriteRes<WriteVecMaskedStoreY, [BWPort0,BWPort4,BWPort237,BWPort15], 5, [1,1,1,1], 4>;
defm : X86WriteRes<WriteVecMove, [BWPort015], 1, [1], 1>;
defm : X86WriteRes<WriteVecMoveX, [BWPort015], 1, [1], 1>;
defm : X86WriteRes<WriteVecMoveY, [BWPort015], 1, [1], 1>;
defm : X86WriteRes<WriteVecMoveToGpr, [BWPort0], 1, [1], 1>;
defm : X86WriteRes<WriteVecMoveFromGpr, [BWPort5], 1, [1], 1>;
defm : X86WriteRes<WriteEMMS, [BWPort01,BWPort15,BWPort015,BWPort0156], 31, [8,1,21,1], 31>;
defm : BWWriteResPair<WriteVecALU, [BWPort15], 1, [1], 1, 5>; // Vector integer ALU op, no logicals.
defm : BWWriteResPair<WriteVecALUX, [BWPort15], 1, [1], 1, 5>; // Vector integer ALU op, no logicals.
defm : BWWriteResPair<WriteVecALUY, [BWPort15], 1, [1], 1, 6>; // Vector integer ALU op, no logicals (YMM/ZMM).
defm : X86WriteResPairUnsupported<WriteVecALUZ>;
defm : BWWriteResPair<WriteVecLogic, [BWPort015], 1, [1], 1, 5>; // Vector integer and/or/xor.
defm : BWWriteResPair<WriteVecLogicX,[BWPort015], 1, [1], 1, 5>; // Vector integer and/or/xor.
defm : BWWriteResPair<WriteVecLogicY,[BWPort015], 1, [1], 1, 6>; // Vector integer and/or/xor (YMM/ZMM).
defm : X86WriteResPairUnsupported<WriteVecLogicZ>;
defm : BWWriteResPair<WriteVecTest, [BWPort0,BWPort5], 2, [1,1], 2, 5>; // Vector integer TEST instructions.
defm : BWWriteResPair<WriteVecTestY, [BWPort0,BWPort5], 4, [1,1], 2, 6>; // Vector integer TEST instructions (YMM/ZMM).
defm : X86WriteResPairUnsupported<WriteVecTestZ>;
defm : BWWriteResPair<WriteVecIMul, [BWPort0], 5, [1], 1, 5>; // Vector integer multiply.
defm : BWWriteResPair<WriteVecIMulX, [BWPort0], 5, [1], 1, 5>; // Vector integer multiply.
defm : BWWriteResPair<WriteVecIMulY, [BWPort0], 5, [1], 1, 6>; // Vector integer multiply.
defm : X86WriteResPairUnsupported<WriteVecIMulZ>;
defm : BWWriteResPair<WritePMULLD, [BWPort0], 10, [2], 2, 5>; // Vector PMULLD.
defm : BWWriteResPair<WritePMULLDY, [BWPort0], 10, [2], 2, 6>; // Vector PMULLD (YMM/ZMM).
defm : X86WriteResPairUnsupported<WritePMULLDZ>;
defm : BWWriteResPair<WriteShuffle, [BWPort5], 1, [1], 1, 5>; // Vector shuffles.
defm : BWWriteResPair<WriteShuffleX, [BWPort5], 1, [1], 1, 5>; // Vector shuffles.
defm : BWWriteResPair<WriteShuffleY, [BWPort5], 1, [1], 1, 6>; // Vector shuffles (YMM/ZMM).
defm : X86WriteResPairUnsupported<WriteShuffleZ>;
defm : BWWriteResPair<WriteVarShuffle, [BWPort5], 1, [1], 1, 5>; // Vector variable shuffles.
defm : BWWriteResPair<WriteVarShuffleX,[BWPort5], 1, [1], 1, 5>; // Vector variable shuffles.
defm : BWWriteResPair<WriteVarShuffleY,[BWPort5], 1, [1], 1, 6>; // Vector variable shuffles (YMM/ZMM).
defm : X86WriteResPairUnsupported<WriteVarShuffleZ>;
defm : BWWriteResPair<WriteBlend, [BWPort5], 1, [1], 1, 5>; // Vector blends.
defm : BWWriteResPair<WriteBlendY, [BWPort5], 1, [1], 1, 6>; // Vector blends (YMM/ZMM).
defm : X86WriteResPairUnsupported<WriteBlendZ>;
defm : BWWriteResPair<WriteVarBlend, [BWPort5], 2, [2], 2, 5>; // Vector variable blends.
defm : BWWriteResPair<WriteVarBlendY, [BWPort5], 2, [2], 2, 6>; // Vector variable blends (YMM/ZMM).
defm : X86WriteResPairUnsupported<WriteVarBlendZ>;
defm : BWWriteResPair<WriteMPSAD, [BWPort0, BWPort5], 7, [1, 2], 3, 5>; // Vector MPSAD.
defm : BWWriteResPair<WriteMPSADY, [BWPort0, BWPort5], 7, [1, 2], 3, 6>; // Vector MPSAD.
defm : X86WriteResPairUnsupported<WriteMPSADZ>;
defm : BWWriteResPair<WritePSADBW, [BWPort0], 5, [1], 1, 5>; // Vector PSADBW.
defm : BWWriteResPair<WritePSADBWX, [BWPort0], 5, [1], 1, 5>; // Vector PSADBW.
defm : BWWriteResPair<WritePSADBWY, [BWPort0], 5, [1], 1, 6>; // Vector PSADBW (YMM/ZMM).
defm : X86WriteResPairUnsupported<WritePSADBWZ>;
defm : BWWriteResPair<WritePHMINPOS, [BWPort0], 5>; // Vector PHMINPOS.
// Vector integer shifts.
defm : BWWriteResPair<WriteVecShift, [BWPort0], 1, [1], 1, 5>;
defm : BWWriteResPair<WriteVecShiftX, [BWPort0,BWPort5], 2, [1,1], 2, 5>;
defm : X86WriteRes<WriteVecShiftY, [BWPort0,BWPort5], 4, [1,1], 2>;
defm : X86WriteRes<WriteVecShiftYLd, [BWPort0,BWPort23], 7, [1,1], 2>;
defm : X86WriteResPairUnsupported<WriteVecShiftZ>;
defm : BWWriteResPair<WriteVecShiftImm, [BWPort0], 1, [1], 1, 5>;
defm : BWWriteResPair<WriteVecShiftImmX, [BWPort0], 1, [1], 1, 5>; // Vector integer immediate shifts (XMM).
defm : BWWriteResPair<WriteVecShiftImmY, [BWPort0], 1, [1], 1, 6>; // Vector integer immediate shifts (YMM/ZMM).
defm : X86WriteResPairUnsupported<WriteVecShiftImmZ>;
defm : BWWriteResPair<WriteVarVecShift, [BWPort0, BWPort5], 3, [2,1], 3, 5>; // Variable vector shifts.
defm : BWWriteResPair<WriteVarVecShiftY, [BWPort0, BWPort5], 3, [2,1], 3, 6>; // Variable vector shifts (YMM/ZMM).
defm : X86WriteResPairUnsupported<WriteVarVecShiftZ>;
// Vector insert/extract operations.
def : WriteRes<WriteVecInsert, [BWPort5]> {
let Latency = 2;
let NumMicroOps = 2;
let ResourceCycles = [2];
}
def : WriteRes<WriteVecInsertLd, [BWPort5,BWPort23]> {
let Latency = 6;
let NumMicroOps = 2;
}
def : WriteRes<WriteVecExtract, [BWPort0,BWPort5]> {
let Latency = 2;
let NumMicroOps = 2;
}
def : WriteRes<WriteVecExtractSt, [BWPort4,BWPort5,BWPort237]> {
let Latency = 2;
let NumMicroOps = 3;
}
// Conversion between integer and float.
defm : BWWriteResPair<WriteCvtSS2I, [BWPort1], 3>;
defm : BWWriteResPair<WriteCvtPS2I, [BWPort1], 3>;
defm : BWWriteResPair<WriteCvtPS2IY, [BWPort1], 3>;
defm : X86WriteResPairUnsupported<WriteCvtPS2IZ>;
defm : BWWriteResPair<WriteCvtSD2I, [BWPort1], 3>;
defm : BWWriteResPair<WriteCvtPD2I, [BWPort1], 3>;
defm : BWWriteResPair<WriteCvtPD2IY, [BWPort1], 3>;
defm : X86WriteResPairUnsupported<WriteCvtPD2IZ>;
defm : BWWriteResPair<WriteCvtI2SS, [BWPort1], 4>;
defm : BWWriteResPair<WriteCvtI2PS, [BWPort1], 4>;
defm : BWWriteResPair<WriteCvtI2PSY, [BWPort1], 4>;
defm : X86WriteResPairUnsupported<WriteCvtI2PSZ>;
defm : BWWriteResPair<WriteCvtI2SD, [BWPort1], 4>;
defm : BWWriteResPair<WriteCvtI2PD, [BWPort1], 4>;
defm : BWWriteResPair<WriteCvtI2PDY, [BWPort1], 4>;
defm : X86WriteResPairUnsupported<WriteCvtI2PDZ>;
defm : BWWriteResPair<WriteCvtSS2SD, [BWPort1], 3>;
defm : BWWriteResPair<WriteCvtPS2PD, [BWPort1], 3>;
defm : BWWriteResPair<WriteCvtPS2PDY, [BWPort1], 3>;
defm : X86WriteResPairUnsupported<WriteCvtPS2PDZ>;
defm : BWWriteResPair<WriteCvtSD2SS, [BWPort1], 3>;
defm : BWWriteResPair<WriteCvtPD2PS, [BWPort1], 3>;
defm : BWWriteResPair<WriteCvtPD2PSY, [BWPort1], 3>;
defm : X86WriteResPairUnsupported<WriteCvtPD2PSZ>;
defm : X86WriteRes<WriteCvtPH2PS, [BWPort0,BWPort5], 2, [1,1], 2>;
defm : X86WriteRes<WriteCvtPH2PSY, [BWPort0,BWPort5], 2, [1,1], 2>;
defm : X86WriteResUnsupported<WriteCvtPH2PSZ>;
defm : X86WriteRes<WriteCvtPH2PSLd, [BWPort0,BWPort23], 6, [1,1], 2>;
defm : X86WriteRes<WriteCvtPH2PSYLd, [BWPort0,BWPort23], 6, [1,1], 2>;
defm : X86WriteResUnsupported<WriteCvtPH2PSZLd>;
defm : X86WriteRes<WriteCvtPS2PH, [BWPort1,BWPort5], 4, [1,1], 2>;
defm : X86WriteRes<WriteCvtPS2PHY, [BWPort1,BWPort5], 6, [1,1], 2>;
defm : X86WriteResUnsupported<WriteCvtPS2PHZ>;
defm : X86WriteRes<WriteCvtPS2PHSt, [BWPort1,BWPort4,BWPort237], 5, [1,1,1], 3>;
defm : X86WriteRes<WriteCvtPS2PHYSt, [BWPort1,BWPort4,BWPort237], 7, [1,1,1], 3>;
defm : X86WriteResUnsupported<WriteCvtPS2PHZSt>;
// Strings instructions.
// Packed Compare Implicit Length Strings, Return Mask
def : WriteRes<WritePCmpIStrM, [BWPort0]> {
let Latency = 11;
let NumMicroOps = 3;
let ResourceCycles = [3];
}
def : WriteRes<WritePCmpIStrMLd, [BWPort0, BWPort23]> {
let Latency = 16;
let NumMicroOps = 4;
let ResourceCycles = [3,1];
}
// Packed Compare Explicit Length Strings, Return Mask
def : WriteRes<WritePCmpEStrM, [BWPort0, BWPort5, BWPort015, BWPort0156]> {
let Latency = 19;
let NumMicroOps = 9;
let ResourceCycles = [4,3,1,1];
}
def : WriteRes<WritePCmpEStrMLd, [BWPort0, BWPort5, BWPort23, BWPort015, BWPort0156]> {
let Latency = 24;
let NumMicroOps = 10;
let ResourceCycles = [4,3,1,1,1];
}
// Packed Compare Implicit Length Strings, Return Index
def : WriteRes<WritePCmpIStrI, [BWPort0]> {
let Latency = 11;
let NumMicroOps = 3;
let ResourceCycles = [3];
}
def : WriteRes<WritePCmpIStrILd, [BWPort0, BWPort23]> {
let Latency = 16;
let NumMicroOps = 4;
let ResourceCycles = [3,1];
}
// Packed Compare Explicit Length Strings, Return Index
def : WriteRes<WritePCmpEStrI, [BWPort0, BWPort5, BWPort0156]> {
let Latency = 18;
let NumMicroOps = 8;
let ResourceCycles = [4,3,1];
}
def : WriteRes<WritePCmpEStrILd, [BWPort0, BWPort5, BWPort23, BWPort0156]> {
let Latency = 23;
let NumMicroOps = 9;
let ResourceCycles = [4,3,1,1];
}
// MOVMSK Instructions.
def : WriteRes<WriteFMOVMSK, [BWPort0]> { let Latency = 3; }
def : WriteRes<WriteVecMOVMSK, [BWPort0]> { let Latency = 3; }
def : WriteRes<WriteVecMOVMSKY, [BWPort0]> { let Latency = 3; }
def : WriteRes<WriteMMXMOVMSK, [BWPort0]> { let Latency = 1; }
// AES instructions.
def : WriteRes<WriteAESDecEnc, [BWPort5]> { // Decryption, encryption.
let Latency = 7;
let NumMicroOps = 1;
let ResourceCycles = [1];
}
def : WriteRes<WriteAESDecEncLd, [BWPort5, BWPort23]> {
let Latency = 12;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def : WriteRes<WriteAESIMC, [BWPort5]> { // InvMixColumn.
let Latency = 14;
let NumMicroOps = 2;
let ResourceCycles = [2];
}
def : WriteRes<WriteAESIMCLd, [BWPort5, BWPort23]> {
let Latency = 19;
let NumMicroOps = 3;
let ResourceCycles = [2,1];
}
def : WriteRes<WriteAESKeyGen, [BWPort0, BWPort5, BWPort015]> { // Key Generation.
let Latency = 29;
let NumMicroOps = 11;
let ResourceCycles = [2,7,2];
}
def : WriteRes<WriteAESKeyGenLd, [BWPort0, BWPort5, BWPort23, BWPort015]> {
let Latency = 33;
let NumMicroOps = 11;
let ResourceCycles = [2,7,1,1];
}
// Carry-less multiplication instructions.
defm : BWWriteResPair<WriteCLMul, [BWPort0], 5>;
// Catch-all for expensive system instructions.
def : WriteRes<WriteSystem, [BWPort0156]> { let Latency = 100; } // def WriteSystem : SchedWrite;
// AVX2.
defm : BWWriteResPair<WriteFShuffle256, [BWPort5], 3, [1], 1, 6>; // Fp 256-bit width vector shuffles.
defm : BWWriteResPair<WriteFVarShuffle256, [BWPort5], 3, [1], 1, 6>; // Fp 256-bit width vector variable shuffles.
defm : BWWriteResPair<WriteShuffle256, [BWPort5], 3, [1], 1, 6>; // 256-bit width vector shuffles.
defm : BWWriteResPair<WriteVarShuffle256, [BWPort5], 3, [1], 1, 6>; // 256-bit width vector variable shuffles.
// Old microcoded instructions that nobody use.
def : WriteRes<WriteMicrocoded, [BWPort0156]> { let Latency = 100; } // def WriteMicrocoded : SchedWrite;
// Fence instructions.
def : WriteRes<WriteFence, [BWPort23, BWPort4]>;
// Load/store MXCSR.
def : WriteRes<WriteLDMXCSR, [BWPort0,BWPort23,BWPort0156]> { let Latency = 7; let NumMicroOps = 3; let ResourceCycles = [1,1,1]; }
def : WriteRes<WriteSTMXCSR, [BWPort4,BWPort5,BWPort237]> { let Latency = 2; let NumMicroOps = 3; let ResourceCycles = [1,1,1]; }
// Nop, not very useful expect it provides a model for nops!
def : WriteRes<WriteNop, []>;
////////////////////////////////////////////////////////////////////////////////
// Horizontal add/sub instructions.
////////////////////////////////////////////////////////////////////////////////
defm : BWWriteResPair<WriteFHAdd, [BWPort1,BWPort5], 5, [1,2], 3, 5>;
defm : BWWriteResPair<WriteFHAddY, [BWPort1,BWPort5], 5, [1,2], 3, 6>;
defm : BWWriteResPair<WritePHAdd, [BWPort5,BWPort15], 3, [2,1], 3, 5>;
defm : BWWriteResPair<WritePHAddX, [BWPort5,BWPort15], 3, [2,1], 3, 5>;
defm : BWWriteResPair<WritePHAddY, [BWPort5,BWPort15], 3, [2,1], 3, 6>;
// Remaining instrs.
def BWWriteResGroup1 : SchedWriteRes<[BWPort0]> {
let Latency = 1;
let NumMicroOps = 1;
let ResourceCycles = [1];
}
def: InstRW<[BWWriteResGroup1], (instregex "VPSLLVQ(Y?)rr",
"VPSRLVQ(Y?)rr")>;
def BWWriteResGroup2 : SchedWriteRes<[BWPort1]> {
let Latency = 1;
let NumMicroOps = 1;
let ResourceCycles = [1];
}
def: InstRW<[BWWriteResGroup2], (instregex "COM(P?)_FST0r",
"UCOM_F(P?)r")>;
def BWWriteResGroup3 : SchedWriteRes<[BWPort5]> {
let Latency = 1;
let NumMicroOps = 1;
let ResourceCycles = [1];
}
def: InstRW<[BWWriteResGroup3], (instrs MMX_MOVQ2DQrr)>;
def BWWriteResGroup4 : SchedWriteRes<[BWPort6]> {
let Latency = 1;
let NumMicroOps = 1;
let ResourceCycles = [1];
}
def: InstRW<[BWWriteResGroup4], (instregex "JMP(16|32|64)r")>;
def BWWriteResGroup5 : SchedWriteRes<[BWPort01]> {
let Latency = 1;
let NumMicroOps = 1;
let ResourceCycles = [1];
}
def: InstRW<[BWWriteResGroup5], (instrs FINCSTP, FNOP)>;
def BWWriteResGroup6 : SchedWriteRes<[BWPort06]> {
let Latency = 1;
let NumMicroOps = 1;
let ResourceCycles = [1];
}
def: InstRW<[BWWriteResGroup6], (instrs CDQ, CQO)>;
def BWWriteResGroup7 : SchedWriteRes<[BWPort15]> {
let Latency = 1;
let NumMicroOps = 1;
let ResourceCycles = [1];
}
def: InstRW<[BWWriteResGroup7], (instregex "ANDN(32|64)rr")>;
def BWWriteResGroup8 : SchedWriteRes<[BWPort015]> {
let Latency = 1;
let NumMicroOps = 1;
let ResourceCycles = [1];
}
def: InstRW<[BWWriteResGroup8], (instregex "VPBLENDD(Y?)rri")>;
def BWWriteResGroup9 : SchedWriteRes<[BWPort0156]> {
let Latency = 1;
let NumMicroOps = 1;
let ResourceCycles = [1];
}
def: InstRW<[BWWriteResGroup9], (instrs SGDT64m,
SIDT64m,
SMSW16m,
STRm,
SYSCALL)>;
def BWWriteResGroup10 : SchedWriteRes<[BWPort4,BWPort237]> {
let Latency = 1;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup10], (instrs FBSTPm)>;
def: InstRW<[BWWriteResGroup10], (instregex "ST_FP(32|64|80)m")>;
def BWWriteResGroup12 : SchedWriteRes<[BWPort01]> {
let Latency = 2;
let NumMicroOps = 2;
let ResourceCycles = [2];
}
def: InstRW<[BWWriteResGroup12], (instrs FDECSTP)>;
def BWWriteResGroup14 : SchedWriteRes<[BWPort0156]> {
let Latency = 2;
let NumMicroOps = 2;
let ResourceCycles = [2];
}
def: InstRW<[BWWriteResGroup14], (instrs LFENCE,
MFENCE,
WAIT,
XGETBV)>;
def BWWriteResGroup15 : SchedWriteRes<[BWPort0,BWPort5]> {
let Latency = 2;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup15], (instregex "(V?)CVTPS2PDrr",
"(V?)CVTSS2SDrr")>;
def BWWriteResGroup16 : SchedWriteRes<[BWPort6,BWPort0156]> {
let Latency = 2;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup16], (instregex "CLFLUSH")>;
def BWWriteResGroup17 : SchedWriteRes<[BWPort01,BWPort015]> {
let Latency = 2;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup17], (instrs MMX_MOVDQ2Qrr)>;
def BWWriteResGroup18 : SchedWriteRes<[BWPort237,BWPort0156]> {
let Latency = 2;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup18], (instrs SFENCE)>;
def BWWriteResGroup20 : SchedWriteRes<[BWPort06,BWPort0156]> {
let Latency = 2;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup20], (instrs CWD,
JCXZ, JECXZ, JRCXZ,
ADC8i8, SBB8i8,
ADC16i16, SBB16i16,
ADC32i32, SBB32i32,
ADC64i32, SBB64i32)>;
def BWWriteResGroup22 : SchedWriteRes<[BWPort4,BWPort6,BWPort237]> {
let Latency = 2;
let NumMicroOps = 3;
let ResourceCycles = [1,1,1];
}
def: InstRW<[BWWriteResGroup22], (instrs FNSTCW16m)>;
def BWWriteResGroup24 : SchedWriteRes<[BWPort4,BWPort237,BWPort15]> {
let Latency = 2;
let NumMicroOps = 3;
let ResourceCycles = [1,1,1];
}
def: InstRW<[BWWriteResGroup24], (instregex "MOVBE(16|32|64)mr")>;
def BWWriteResGroup25 : SchedWriteRes<[BWPort4,BWPort237,BWPort0156]> {
let Latency = 2;
let NumMicroOps = 3;
let ResourceCycles = [1,1,1];
}
def: InstRW<[BWWriteResGroup25], (instrs PUSH16r, PUSH32r, PUSH64r, PUSH64i8,
STOSB, STOSL, STOSQ, STOSW)>;
def: InstRW<[BWWriteResGroup25], (instregex "PUSH(16|32|64)rmr")>;
def BWWriteResGroup27 : SchedWriteRes<[BWPort1]> {
let Latency = 3;
let NumMicroOps = 1;
let ResourceCycles = [1];
}
def: InstRW<[BWWriteResGroup27], (instrs MMX_CVTPI2PSirr)>;
def: InstRW<[BWWriteResGroup27], (instregex "P(DEP|EXT)(32|64)rr",
"(V?)CVTDQ2PS(Y?)rr")>;
def BWWriteResGroup28 : SchedWriteRes<[BWPort5]> {
let Latency = 3;
let NumMicroOps = 1;
let ResourceCycles = [1];
}
def: InstRW<[BWWriteResGroup28], (instrs VPBROADCASTBrr,
VPBROADCASTWrr)>;
def BWWriteResGroup33 : SchedWriteRes<[BWPort5,BWPort0156]> {
let Latency = 3;
let NumMicroOps = 3;
let ResourceCycles = [2,1];
}
def: InstRW<[BWWriteResGroup33], (instrs MMX_PACKSSDWirr,
MMX_PACKSSWBirr,
MMX_PACKUSWBirr)>;
def BWWriteResGroup34 : SchedWriteRes<[BWPort6,BWPort0156]> {
let Latency = 3;
let NumMicroOps = 3;
let ResourceCycles = [1,2];
}
def: InstRW<[BWWriteResGroup34], (instregex "CLD")>;
def BWWriteResGroup35 : SchedWriteRes<[BWPort06,BWPort0156]> {
let Latency = 3;
let NumMicroOps = 3;
let ResourceCycles = [1,2];
}
def: InstRW<[BWWriteResGroup35], (instregex "RCL(8|16|32|64)r(1|i)",
"RCR(8|16|32|64)r(1|i)")>;
def BWWriteResGroup37 : SchedWriteRes<[BWPort4,BWPort6,BWPort237,BWPort0156]> {
let Latency = 3;
let NumMicroOps = 4;
let ResourceCycles = [1,1,1,1];
}
def: InstRW<[BWWriteResGroup37], (instregex "CALL(16|32|64)r")>;
def BWWriteResGroup38 : SchedWriteRes<[BWPort4,BWPort237,BWPort06,BWPort0156]> {
let Latency = 3;
let NumMicroOps = 4;
let ResourceCycles = [1,1,1,1];
}
def: InstRW<[BWWriteResGroup38], (instrs CALL64pcrel32)>;
def BWWriteResGroup39 : SchedWriteRes<[BWPort0,BWPort1]> {
let Latency = 4;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup39], (instregex "(V?)CVT(T?)SD2SI64rr",
"(V?)CVT(T?)SD2SIrr",
"(V?)CVT(T?)SS2SI64rr",
"(V?)CVT(T?)SS2SIrr")>;
def BWWriteResGroup40 : SchedWriteRes<[BWPort0,BWPort5]> {
let Latency = 4;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup40], (instrs VCVTPS2PDYrr)>;
def BWWriteResGroup41 : SchedWriteRes<[BWPort0,BWPort0156]> {
let Latency = 4;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup41], (instrs FNSTSW16r)>;
def BWWriteResGroup42 : SchedWriteRes<[BWPort1,BWPort5]> {
let Latency = 4;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup42], (instrs MMX_CVTPI2PDirr)>;
def: InstRW<[BWWriteResGroup42], (instregex "MMX_CVT(T?)PD2PIirr",
"MMX_CVT(T?)PS2PIirr",
"(V?)CVTDQ2PDrr",
"(V?)CVTPD2PSrr",
"(V?)CVTSD2SSrr",
"(V?)CVTSI642SDrr",
"(V?)CVTSI2SDrr",
"(V?)CVTSI2SSrr",
"(V?)CVT(T?)PD2DQrr")>;
def BWWriteResGroup43 : SchedWriteRes<[BWPort0,BWPort4,BWPort237]> {
let Latency = 4;
let NumMicroOps = 3;
let ResourceCycles = [1,1,1];
}
def: InstRW<[BWWriteResGroup43], (instrs FNSTSWm)>;
def BWWriteResGroup44 : SchedWriteRes<[BWPort1,BWPort4,BWPort237]> {
let Latency = 4;
let NumMicroOps = 3;
let ResourceCycles = [1,1,1];
}
def: InstRW<[BWWriteResGroup44], (instregex "IST(T?)_FP(16|32|64)m",
"IST_F(16|32)m")>;
def BWWriteResGroup45 : SchedWriteRes<[BWPort0156]> {
let Latency = 4;
let NumMicroOps = 4;
let ResourceCycles = [4];
}
def: InstRW<[BWWriteResGroup45], (instrs FNCLEX)>;
def BWWriteResGroup46 : SchedWriteRes<[]> {
let Latency = 0;
let NumMicroOps = 4;
let ResourceCycles = [];
}
def: InstRW<[BWWriteResGroup46], (instrs VZEROUPPER)>;
def BWWriteResGroup47 : SchedWriteRes<[BWPort0]> {
let Latency = 5;
let NumMicroOps = 1;
let ResourceCycles = [1];
}
def: InstRW<[BWWriteResGroup47], (instregex "MUL_(FPrST0|FST0r|FrST0)")>;
def BWWriteResGroup49 : SchedWriteRes<[BWPort23]> {
let Latency = 5;
let NumMicroOps = 1;
let ResourceCycles = [1];
}
def: InstRW<[BWWriteResGroup49], (instregex "MOVSX(16|32|64)rm(8|16|32)",
"MOVZX(16|32|64)rm(8|16)")>;
def: InstRW<[BWWriteResGroup49], (instrs VBROADCASTSSrm,
VMOVDDUPrm, MOVDDUPrm,
VMOVSHDUPrm, MOVSHDUPrm,
VMOVSLDUPrm, MOVSLDUPrm,
VPBROADCASTDrm,
VPBROADCASTQrm)>;
def BWWriteResGroup50 : SchedWriteRes<[BWPort1,BWPort5]> {
let Latency = 5;
let NumMicroOps = 3;
let ResourceCycles = [1,2];
}
def: InstRW<[BWWriteResGroup50], (instregex "(V?)CVTSI642SSrr")>;
def BWWriteResGroup51 : SchedWriteRes<[BWPort1,BWPort6,BWPort06]> {
let Latency = 5;
let NumMicroOps = 3;
let ResourceCycles = [1,1,1];
}
def: InstRW<[BWWriteResGroup51], (instregex "STR(16|32|64)r")>;
def BWWriteResGroup54 : SchedWriteRes<[BWPort6,BWPort0156]> {
let Latency = 5;
let NumMicroOps = 5;
let ResourceCycles = [1,4];
}
def: InstRW<[BWWriteResGroup54], (instrs PAUSE)>;
def BWWriteResGroup55 : SchedWriteRes<[BWPort06,BWPort0156]> {
let Latency = 5;
let NumMicroOps = 5;
let ResourceCycles = [1,4];
}
def: InstRW<[BWWriteResGroup55], (instrs XSETBV)>;
def BWWriteResGroup57 : SchedWriteRes<[BWPort4,BWPort237,BWPort0156]> {
let Latency = 5;
let NumMicroOps = 6;
let ResourceCycles = [1,1,4];
}
def: InstRW<[BWWriteResGroup57], (instregex "PUSHF(16|64)")>;
def BWWriteResGroup58 : SchedWriteRes<[BWPort23]> {
let Latency = 6;
let NumMicroOps = 1;
let ResourceCycles = [1];
}
def: InstRW<[BWWriteResGroup58], (instregex "LD_F(32|64|80)m")>;
def: InstRW<[BWWriteResGroup58], (instrs VBROADCASTF128,
VBROADCASTI128,
VBROADCASTSDYrm,
VBROADCASTSSYrm,
VMOVDDUPYrm,
VMOVSHDUPYrm,
VMOVSLDUPYrm,
VPBROADCASTDYrm,
VPBROADCASTQYrm)>;
def BWWriteResGroup59 : SchedWriteRes<[BWPort0,BWPort23]> {
let Latency = 6;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup59], (instrs CVTPS2PDrm, VCVTPS2PDrm,
CVTSS2SDrm, VCVTSS2SDrm,
CVTSS2SDrm_Int, VCVTSS2SDrm_Int,
VPSLLVQrm,
VPSRLVQrm)>;
def BWWriteResGroup60 : SchedWriteRes<[BWPort1,BWPort5]> {
let Latency = 6;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup60], (instrs VCVTDQ2PDYrr,
VCVTPD2PSYrr,
VCVTPD2DQYrr,
VCVTTPD2DQYrr)>;
def BWWriteResGroup62 : SchedWriteRes<[BWPort6,BWPort23]> {
let Latency = 6;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup62], (instrs FARJMP64)>;
def: InstRW<[BWWriteResGroup62], (instregex "JMP(16|32|64)m")>;
def BWWriteResGroup64 : SchedWriteRes<[BWPort23,BWPort15]> {
let Latency = 6;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup64], (instregex "ANDN(32|64)rm",
"MOVBE(16|32|64)rm")>;
def BWWriteResGroup65 : SchedWriteRes<[BWPort23,BWPort015]> {
let Latency = 6;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup65], (instrs VINSERTF128rm,
VINSERTI128rm,
VPBLENDDrmi)>;
def BWWriteResGroup66 : SchedWriteRes<[BWPort23,BWPort0156]> {
let Latency = 6;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup66], (instrs POP16r, POP32r, POP64r)>;
def: InstRW<[BWWriteResGroup66], (instregex "POP(16|32|64)rmr")>;
def BWWriteResGroup68 : SchedWriteRes<[BWPort1,BWPort6,BWPort06,BWPort0156]> {
let Latency = 6;
let NumMicroOps = 4;
let ResourceCycles = [1,1,1,1];
}
def: InstRW<[BWWriteResGroup68], (instregex "SLDT(16|32|64)r")>;
def BWWriteResGroup69 : SchedWriteRes<[BWPort4,BWPort23,BWPort237,BWPort06]> {
let Latency = 6;
let NumMicroOps = 4;
let ResourceCycles = [1,1,1,1];
}
def: InstRW<[BWWriteResGroup69], (instregex "SAR(8|16|32|64)m(1|i)",
"SHL(8|16|32|64)m(1|i)",
"SHR(8|16|32|64)m(1|i)")>;
def BWWriteResGroup70 : SchedWriteRes<[BWPort4,BWPort23,BWPort237,BWPort0156]> {
let Latency = 6;
let NumMicroOps = 4;
let ResourceCycles = [1,1,1,1];
}
def: InstRW<[BWWriteResGroup70], (instregex "POP(16|32|64)rmm",
"PUSH(16|32|64)rmm")>;
def BWWriteResGroup71 : SchedWriteRes<[BWPort6,BWPort0156]> {
let Latency = 6;
let NumMicroOps = 6;
let ResourceCycles = [1,5];
}
def: InstRW<[BWWriteResGroup71], (instrs STD)>;
def BWWriteResGroup73 : SchedWriteRes<[BWPort0,BWPort23]> {
let Latency = 7;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup73], (instrs VPSLLVQYrm,
VPSRLVQYrm)>;
def BWWriteResGroup74 : SchedWriteRes<[BWPort1,BWPort23]> {
let Latency = 7;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup74], (instregex "FCOM(P?)(32|64)m")>;
def BWWriteResGroup77 : SchedWriteRes<[BWPort23,BWPort015]> {
let Latency = 7;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup77], (instrs VPBLENDDYrmi)>;
def BWWriteResGroup79 : SchedWriteRes<[BWPort5,BWPort23]> {
let Latency = 7;
let NumMicroOps = 3;
let ResourceCycles = [2,1];
}
def: InstRW<[BWWriteResGroup79], (instrs MMX_PACKSSDWirm,
MMX_PACKSSWBirm,
MMX_PACKUSWBirm)>;
def BWWriteResGroup80 : SchedWriteRes<[BWPort23,BWPort0156]> {
let Latency = 7;
let NumMicroOps = 3;
let ResourceCycles = [1,2];
}
def: InstRW<[BWWriteResGroup80], (instrs LEAVE, LEAVE64,
SCASB, SCASL, SCASQ, SCASW)>;
def BWWriteResGroup82 : SchedWriteRes<[BWPort0,BWPort01,BWPort23]> {
let Latency = 7;
let NumMicroOps = 3;
let ResourceCycles = [1,1,1];
}
def: InstRW<[BWWriteResGroup82], (instrs FLDCW16m)>;
def BWWriteResGroup84 : SchedWriteRes<[BWPort6,BWPort23,BWPort0156]> {
let Latency = 7;
let NumMicroOps = 3;
let ResourceCycles = [1,1,1];
}
def: InstRW<[BWWriteResGroup84], (instrs LRETQ, RETQ)>;
def BWWriteResGroup87 : SchedWriteRes<[BWPort4,BWPort23,BWPort237,BWPort06]> {
let Latency = 7;
let NumMicroOps = 5;
let ResourceCycles = [1,1,1,2];
}
def: InstRW<[BWWriteResGroup87], (instregex "ROL(8|16|32|64)m(1|i)",
"ROR(8|16|32|64)m(1|i)")>;
def BWWriteResGroup87_1 : SchedWriteRes<[BWPort06]> {
let Latency = 2;
let NumMicroOps = 2;
let ResourceCycles = [2];
}
def: InstRW<[BWWriteResGroup87_1], (instrs ROL8r1, ROL16r1, ROL32r1, ROL64r1,
ROR8r1, ROR16r1, ROR32r1, ROR64r1)>;
def BWWriteResGroup88 : SchedWriteRes<[BWPort4,BWPort23,BWPort237,BWPort0156]> {
let Latency = 7;
let NumMicroOps = 5;
let ResourceCycles = [1,1,1,2];
}
def: InstRW<[BWWriteResGroup88], (instregex "XADD(8|16|32|64)rm")>;
def BWWriteResGroup89 : SchedWriteRes<[BWPort4,BWPort6,BWPort23,BWPort237,BWPort0156]> {
let Latency = 7;
let NumMicroOps = 5;
let ResourceCycles = [1,1,1,1,1];
}
def: InstRW<[BWWriteResGroup89], (instregex "CALL(16|32|64)m")>;
def: InstRW<[BWWriteResGroup89], (instrs FARCALL64)>;
def BWWriteResGroup90 : SchedWriteRes<[BWPort6,BWPort06,BWPort15,BWPort0156]> {
let Latency = 7;
let NumMicroOps = 7;
let ResourceCycles = [2,2,1,2];
}
def: InstRW<[BWWriteResGroup90], (instrs LOOP)>;
def BWWriteResGroup91 : SchedWriteRes<[BWPort1,BWPort23]> {
let Latency = 8;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup91], (instrs MMX_CVTPI2PSirm,
CVTDQ2PSrm,
VCVTDQ2PSrm)>;
def: InstRW<[BWWriteResGroup91], (instregex "P(DEP|EXT)(32|64)rm")>;
def BWWriteResGroup92 : SchedWriteRes<[BWPort5,BWPort23]> {
let Latency = 8;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup92], (instrs VPMOVSXBDYrm,
VPMOVSXBQYrm,
VPMOVSXBWYrm,
VPMOVSXDQYrm,
VPMOVSXWDYrm,
VPMOVSXWQYrm,
VPMOVZXWDYrm)>;
def BWWriteResGroup97 : SchedWriteRes<[BWPort23,BWPort237,BWPort06,BWPort0156]> {
let Latency = 8;
let NumMicroOps = 5;
let ResourceCycles = [1,1,1,2];
}
def: InstRW<[BWWriteResGroup97], (instregex "RCL(8|16|32|64)m(1|i)",
"RCR(8|16|32|64)m(1|i)")>;
def BWWriteResGroup99 : SchedWriteRes<[BWPort4,BWPort23,BWPort237,BWPort0156]> {
let Latency = 8;
let NumMicroOps = 6;
let ResourceCycles = [1,1,1,3];
}
def: InstRW<[BWWriteResGroup99], (instregex "XCHG(8|16|32|64)rm")>;
def BWWriteResGroup100 : SchedWriteRes<[BWPort4,BWPort23,BWPort237,BWPort06,BWPort0156]> {
let Latency = 8;
let NumMicroOps = 6;
let ResourceCycles = [1,1,1,2,1];
}
def : SchedAlias<WriteADCRMW, BWWriteResGroup100>;
def: InstRW<[BWWriteResGroup100], (instregex "ROL(8|16|32|64)mCL",
"ROR(8|16|32|64)mCL",
"SAR(8|16|32|64)mCL",
"SHL(8|16|32|64)mCL",
"SHR(8|16|32|64)mCL")>;
def BWWriteResGroup101 : SchedWriteRes<[BWPort1,BWPort23]> {
let Latency = 9;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup101], (instregex "(ADD|SUB|SUBR)_F(32|64)m",
"ILD_F(16|32|64)m")>;
def: InstRW<[BWWriteResGroup101], (instrs VCVTPS2DQYrm,
VCVTTPS2DQYrm)>;
def BWWriteResGroup105 : SchedWriteRes<[BWPort0,BWPort1,BWPort23]> {
let Latency = 9;
let NumMicroOps = 3;
let ResourceCycles = [1,1,1];
}
def: InstRW<[BWWriteResGroup105], (instregex "(V?)CVTSS2SI(64)?rm",
"(V?)CVT(T?)SD2SI64rm",
"(V?)CVT(T?)SD2SIrm",
"VCVTTSS2SI64rm",
"(V?)CVTTSS2SIrm")>;
def BWWriteResGroup106 : SchedWriteRes<[BWPort0,BWPort5,BWPort23]> {
let Latency = 9;
let NumMicroOps = 3;
let ResourceCycles = [1,1,1];
}
def: InstRW<[BWWriteResGroup106], (instrs VCVTPS2PDYrm)>;
def BWWriteResGroup107 : SchedWriteRes<[BWPort1,BWPort5,BWPort23]> {
let Latency = 9;
let NumMicroOps = 3;
let ResourceCycles = [1,1,1];
}
def: InstRW<[BWWriteResGroup107], (instrs CVTPD2PSrm,
CVTPD2DQrm,
CVTTPD2DQrm,
MMX_CVTPI2PDirm)>;
def: InstRW<[BWWriteResGroup107], (instregex "MMX_CVT(T?)PD2PIirm",
"(V?)CVTDQ2PDrm",
"(V?)CVTSD2SSrm")>;
def BWWriteResGroup108 : SchedWriteRes<[BWPort5,BWPort23,BWPort015]> {
let Latency = 9;
let NumMicroOps = 3;
let ResourceCycles = [1,1,1];
}
def: InstRW<[BWWriteResGroup108], (instregex "VPBROADCASTB(Y?)rm",
"VPBROADCASTW(Y?)rm")>;
def BWWriteResGroup112 : SchedWriteRes<[BWPort23,BWPort06,BWPort0156]> {
let Latency = 9;
let NumMicroOps = 5;
let ResourceCycles = [1,1,3];
}
def: InstRW<[BWWriteResGroup112], (instrs RDRAND16r, RDRAND32r, RDRAND64r)>;
def BWWriteResGroup113 : SchedWriteRes<[BWPort1,BWPort6,BWPort23,BWPort0156]> {
let Latency = 9;
let NumMicroOps = 5;
let ResourceCycles = [1,2,1,1];
}
def: InstRW<[BWWriteResGroup113], (instregex "LAR(16|32|64)rm",
"LSL(16|32|64)rm")>;
def BWWriteResGroup115 : SchedWriteRes<[BWPort0,BWPort23]> {
let Latency = 10;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup115], (instregex "(V?)PCMPGTQrm")>;
def BWWriteResGroup117 : SchedWriteRes<[BWPort1,BWPort23]> {
let Latency = 10;
let NumMicroOps = 3;
let ResourceCycles = [2,1];
}
def: InstRW<[BWWriteResGroup117], (instregex "FICOM(P?)(16|32)m")>;
def BWWriteResGroup120 : SchedWriteRes<[BWPort0,BWPort1,BWPort5,BWPort23]> {
let Latency = 10;
let NumMicroOps = 4;
let ResourceCycles = [1,1,1,1];
}
def: InstRW<[BWWriteResGroup120], (instregex "CVTTSS2SI64rm")>;
def BWWriteResGroup122_1 : SchedWriteRes<[BWPort0,BWFPDivider]> {
let Latency = 11;
let NumMicroOps = 1;
let ResourceCycles = [1,3]; // Really 2.5 cycle throughput
}
def : SchedAlias<WriteFDiv, BWWriteResGroup122_1>; // TODO - convert to ZnWriteResFpuPair
def BWWriteResGroup123 : SchedWriteRes<[BWPort0,BWPort23]> {
let Latency = 11;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup123], (instregex "MUL_F(32|64)m")>;
def: InstRW<[BWWriteResGroup123], (instrs VPCMPGTQYrm)>;
def BWWriteResGroup128 : SchedWriteRes<[BWPort1,BWPort5,BWPort23]> {
let Latency = 11;
let NumMicroOps = 3;
let ResourceCycles = [1,1,1];
}
def: InstRW<[BWWriteResGroup128], (instrs VCVTDQ2PDYrm)>;
def BWWriteResGroup131 : SchedWriteRes<[BWPort1,BWPort06,BWPort0156]> {
let Latency = 11;
let NumMicroOps = 7;
let ResourceCycles = [2,2,3];
}
def: InstRW<[BWWriteResGroup131], (instregex "RCL(16|32|64)rCL",
"RCR(16|32|64)rCL")>;
def BWWriteResGroup132 : SchedWriteRes<[BWPort1,BWPort06,BWPort15,BWPort0156]> {
let Latency = 11;
let NumMicroOps = 9;
let ResourceCycles = [1,4,1,3];
}
def: InstRW<[BWWriteResGroup132], (instrs RCL8rCL)>;
def BWWriteResGroup133 : SchedWriteRes<[BWPort06,BWPort0156]> {
let Latency = 11;
let NumMicroOps = 11;
let ResourceCycles = [2,9];
}
def: InstRW<[BWWriteResGroup133], (instrs LOOPE)>;
def: InstRW<[BWWriteResGroup133], (instrs LOOPNE)>;
def BWWriteResGroup135 : SchedWriteRes<[BWPort1,BWPort23]> {
let Latency = 12;
let NumMicroOps = 3;
let ResourceCycles = [2,1];
}
def: InstRW<[BWWriteResGroup135], (instregex "(ADD|SUB|SUBR)_FI(16|32)m")>;
def BWWriteResGroup139_1 : SchedWriteRes<[BWPort0,BWFPDivider]> {
let Latency = 14;
let NumMicroOps = 1;
let ResourceCycles = [1,4];
}
def : SchedAlias<WriteFDiv64, BWWriteResGroup139_1>; // TODO - convert to ZnWriteResFpuPair
def BWWriteResGroup141 : SchedWriteRes<[BWPort0,BWPort1,BWPort23]> {
let Latency = 14;
let NumMicroOps = 3;
let ResourceCycles = [1,1,1];
}
def: InstRW<[BWWriteResGroup141], (instregex "MUL_FI(16|32)m")>;
def BWWriteResGroup144 : SchedWriteRes<[BWPort1,BWPort6,BWPort23,BWPort0156]> {
let Latency = 14;
let NumMicroOps = 8;
let ResourceCycles = [2,2,1,3];
}
def: InstRW<[BWWriteResGroup144], (instregex "LAR(16|32|64)rr")>;
def BWWriteResGroup145 : SchedWriteRes<[BWPort1,BWPort06,BWPort15,BWPort0156]> {
let Latency = 14;
let NumMicroOps = 10;
let ResourceCycles = [2,3,1,4];
}
def: InstRW<[BWWriteResGroup145], (instrs RCR8rCL)>;
def BWWriteResGroup146 : SchedWriteRes<[BWPort0,BWPort1,BWPort6,BWPort0156]> {
let Latency = 14;
let NumMicroOps = 12;
let ResourceCycles = [2,1,4,5];
}
def: InstRW<[BWWriteResGroup146], (instrs XCH_F)>;
def BWWriteResGroup147 : SchedWriteRes<[BWPort0]> {
let Latency = 15;
let NumMicroOps = 1;
let ResourceCycles = [1];
}
def: InstRW<[BWWriteResGroup147], (instregex "DIVR_(FPrST0|FST0r|FrST0)")>;
def BWWriteResGroup149 : SchedWriteRes<[BWPort1,BWPort23,BWPort237,BWPort06,BWPort15,BWPort0156]> {
let Latency = 15;
let NumMicroOps = 10;
let ResourceCycles = [1,1,1,4,1,2];
}
def: InstRW<[BWWriteResGroup149], (instregex "RCL(8|16|32|64)mCL")>;
def BWWriteResGroup150 : SchedWriteRes<[BWPort0,BWPort23,BWFPDivider]> {
let Latency = 16;
let NumMicroOps = 2;
let ResourceCycles = [1,1,5];
}
def : SchedAlias<WriteFDivLd, BWWriteResGroup150>; // TODO - convert to ZnWriteResFpuPair
def BWWriteResGroup153 : SchedWriteRes<[BWPort4,BWPort23,BWPort237,BWPort06,BWPort15,BWPort0156]> {
let Latency = 16;
let NumMicroOps = 14;
let ResourceCycles = [1,1,1,4,2,5];
}
def: InstRW<[BWWriteResGroup153], (instrs CMPXCHG8B)>;
def BWWriteResGroup154 : SchedWriteRes<[BWPort5,BWPort6]> {
let Latency = 8;
let NumMicroOps = 20;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup154], (instrs VZEROALL)>;
def BWWriteResGroup159 : SchedWriteRes<[BWPort5,BWPort6,BWPort06,BWPort0156]> {
let Latency = 18;
let NumMicroOps = 8;
let ResourceCycles = [1,1,1,5];
}
def: InstRW<[BWWriteResGroup159], (instrs CPUID)>;
def: InstRW<[BWWriteResGroup159], (instrs RDTSC)>;
def BWWriteResGroup160 : SchedWriteRes<[BWPort1,BWPort23,BWPort237,BWPort06,BWPort15,BWPort0156]> {
let Latency = 18;
let NumMicroOps = 11;
let ResourceCycles = [2,1,1,3,1,3];
}
def: InstRW<[BWWriteResGroup160], (instregex "RCR(8|16|32|64)mCL")>;
def BWWriteResGroup161 : SchedWriteRes<[BWPort0,BWPort23,BWFPDivider]> {
let Latency = 19;
let NumMicroOps = 2;
let ResourceCycles = [1,1,8];
}
def : SchedAlias<WriteFDiv64Ld, BWWriteResGroup161>; // TODO - convert to ZnWriteResFpuPair
def BWWriteResGroup165 : SchedWriteRes<[BWPort0]> {
let Latency = 20;
let NumMicroOps = 1;
let ResourceCycles = [1];
}
def: InstRW<[BWWriteResGroup165], (instregex "DIV_(FPrST0|FST0r|FrST0)")>;
def BWWriteResGroup167 : SchedWriteRes<[BWPort4,BWPort5,BWPort6,BWPort23,BWPort237,BWPort06,BWPort0156]> {
let Latency = 20;
let NumMicroOps = 8;
let ResourceCycles = [1,1,1,1,1,1,2];
}
def: InstRW<[BWWriteResGroup167], (instrs INSB, INSL, INSW)>;
def BWWriteResGroup169 : SchedWriteRes<[BWPort0,BWPort23]> {
let Latency = 21;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup169], (instregex "DIV_F(32|64)m")>;
def BWWriteResGroup171 : SchedWriteRes<[BWPort0,BWPort4,BWPort5,BWPort23,BWPort237,BWPort06,BWPort0156]> {
let Latency = 21;
let NumMicroOps = 19;
let ResourceCycles = [2,1,4,1,1,4,6];
}
def: InstRW<[BWWriteResGroup171], (instrs CMPXCHG16B)>;
def BWWriteResGroup172 : SchedWriteRes<[BWPort6,BWPort23,BWPort0156]> {
let Latency = 22;
let NumMicroOps = 18;
let ResourceCycles = [1,1,16];
}
def: InstRW<[BWWriteResGroup172], (instrs POPF64)>;
def BWWriteResGroup176 : SchedWriteRes<[BWPort6,BWPort23,BWPort0156]> {
let Latency = 23;
let NumMicroOps = 19;
let ResourceCycles = [3,1,15];
}
def: InstRW<[BWWriteResGroup176], (instregex "XRSTOR(64)?")>;
def BWWriteResGroup177 : SchedWriteRes<[BWPort0,BWPort1,BWPort23]> {
let Latency = 24;
let NumMicroOps = 3;
let ResourceCycles = [1,1,1];
}
def: InstRW<[BWWriteResGroup177], (instregex "DIV_FI(16|32)m")>;
def BWWriteResGroup180 : SchedWriteRes<[BWPort0,BWPort23]> {
let Latency = 26;
let NumMicroOps = 2;
let ResourceCycles = [1,1];
}
def: InstRW<[BWWriteResGroup180], (instregex "DIVR_F(32|64)m")>;
def BWWriteResGroup182 : SchedWriteRes<[BWPort0,BWPort1,BWPort23]> {
let Latency = 29;
let NumMicroOps = 3;
let ResourceCycles = [1,1,1];
}
def: InstRW<[BWWriteResGroup182], (instregex "DIVR_FI(16|32)m")>;
def BWWriteResGroup183_1 : SchedWriteRes<[BWPort4, BWPort5, BWPort23, BWPort0156]> {
let Latency = 22;
let NumMicroOps = 7;
let ResourceCycles = [1,3,2,1];
}
def: InstRW<[BWWriteResGroup183_1], (instrs VGATHERQPDrm)>;
def BWWriteResGroup183_2 : SchedWriteRes<[BWPort4, BWPort5, BWPort23, BWPort0156]> {
let Latency = 23;
let NumMicroOps = 9;
let ResourceCycles = [1,3,4,1];
}
def: InstRW<[BWWriteResGroup183_2], (instrs VGATHERQPDYrm)>;
def BWWriteResGroup183_3 : SchedWriteRes<[BWPort4, BWPort5, BWPort23, BWPort0156]> {
let Latency = 24;
let NumMicroOps = 9;
let ResourceCycles = [1,5,2,1];
}
def: InstRW<[BWWriteResGroup183_3], (instrs VGATHERQPSYrm)>;
def BWWriteResGroup183_4 : SchedWriteRes<[BWPort4, BWPort5, BWPort23, BWPort0156]> {
let Latency = 25;
let NumMicroOps = 7;
let ResourceCycles = [1,3,2,1];
}
def: InstRW<[BWWriteResGroup183_4], (instrs VGATHERDPDrm,
VGATHERDPSrm)>;
def BWWriteResGroup183_5 : SchedWriteRes<[BWPort4, BWPort5, BWPort23, BWPort0156]> {
let Latency = 26;
let NumMicroOps = 9;
let ResourceCycles = [1,5,2,1];
}
def: InstRW<[BWWriteResGroup183_5], (instrs VGATHERDPDYrm)>;
def BWWriteResGroup183_6 : SchedWriteRes<[BWPort4, BWPort5, BWPort23, BWPort0156]> {
let Latency = 26;
let NumMicroOps = 14;
let ResourceCycles = [1,4,8,1];
}
def: InstRW<[BWWriteResGroup183_6], (instrs VGATHERDPSYrm)>;
def BWWriteResGroup183_7 : SchedWriteRes<[BWPort4, BWPort5, BWPort23, BWPort0156]> {
let Latency = 27;
let NumMicroOps = 9;
let ResourceCycles = [1,5,2,1];
}
def: InstRW<[BWWriteResGroup183_7], (instrs VGATHERQPSrm)>;
def BWWriteResGroup185 : SchedWriteRes<[BWPort4,BWPort6,BWPort23,BWPort237,BWPort0156]> {
let Latency = 29;
let NumMicroOps = 27;
let ResourceCycles = [1,5,1,1,19];
}
def: InstRW<[BWWriteResGroup185], (instrs XSAVE64)>;
def BWWriteResGroup186 : SchedWriteRes<[BWPort4,BWPort6,BWPort23,BWPort237,BWPort0156]> {
let Latency = 30;
let NumMicroOps = 28;
let ResourceCycles = [1,6,1,1,19];
}
def: InstRW<[BWWriteResGroup186], (instrs XSAVE)>;
def: InstRW<[BWWriteResGroup186], (instregex "XSAVEC", "XSAVES", "XSAVEOPT")>;
def BWWriteResGroup191 : SchedWriteRes<[BWPort5,BWPort6,BWPort23,BWPort06,BWPort0156]> {
let Latency = 34;
let NumMicroOps = 23;
let ResourceCycles = [1,5,3,4,10];
}
def: InstRW<[BWWriteResGroup191], (instregex "IN(8|16|32)ri",
"IN(8|16|32)rr")>;
def BWWriteResGroup194 : SchedWriteRes<[BWPort5,BWPort6,BWPort23,BWPort237,BWPort06,BWPort0156]> {
let Latency = 35;
let NumMicroOps = 23;
let ResourceCycles = [1,5,2,1,4,10];
}
def: InstRW<[BWWriteResGroup194], (instregex "OUT(8|16|32)ir",
"OUT(8|16|32)rr")>;
def BWWriteResGroup196 : SchedWriteRes<[BWPort5,BWPort0156]> {
let Latency = 42;
let NumMicroOps = 22;
let ResourceCycles = [2,20];
}
def: InstRW<[BWWriteResGroup196], (instrs RDTSCP)>;
def BWWriteResGroup197 : SchedWriteRes<[BWPort0,BWPort01,BWPort23,BWPort05,BWPort06,BWPort015,BWPort0156]> {
let Latency = 60;
let NumMicroOps = 64;
let ResourceCycles = [2,2,8,1,10,2,39];
}
def: InstRW<[BWWriteResGroup197], (instrs FLDENVm)>;
def BWWriteResGroup198 : SchedWriteRes<[BWPort0,BWPort6,BWPort23,BWPort05,BWPort06,BWPort15,BWPort0156]> {
let Latency = 63;
let NumMicroOps = 88;
let ResourceCycles = [4,4,31,1,2,1,45];
}
def: InstRW<[BWWriteResGroup198], (instrs FXRSTOR64)>;
def BWWriteResGroup199 : SchedWriteRes<[BWPort0,BWPort6,BWPort23,BWPort05,BWPort06,BWPort15,BWPort0156]> {
let Latency = 63;
let NumMicroOps = 90;
let ResourceCycles = [4,2,33,1,2,1,47];
}
def: InstRW<[BWWriteResGroup199], (instrs FXRSTOR)>;
def BWWriteResGroup200 : SchedWriteRes<[BWPort5,BWPort01,BWPort0156]> {
let Latency = 75;
let NumMicroOps = 15;
let ResourceCycles = [6,3,6];
}
def: InstRW<[BWWriteResGroup200], (instrs FNINIT)>;
def BWWriteResGroup202 : SchedWriteRes<[BWPort0,BWPort1,BWPort4,BWPort5,BWPort6,BWPort237,BWPort06,BWPort0156]> {
let Latency = 115;
let NumMicroOps = 100;
let ResourceCycles = [9,9,11,8,1,11,21,30];
}
def: InstRW<[BWWriteResGroup202], (instrs FSTENVm)>;
def: InstRW<[WriteZero], (instrs CLC)>;
// Intruction variants handled by the renamer. These might not need execution
// ports in certain conditions.
// See Agner's Fog "The microarchitecture of Intel, AMD and VIA CPUs",
// section "Haswell and Broadwell Pipeline" > "Register allocation and
// renaming".
// These can be investigated with llvm-exegesis, e.g.
// echo 'pxor %mm0, %mm0' | /tmp/llvm-exegesis -mode=uops -snippets-file=-
// echo 'vxorpd %xmm0, %xmm0, %xmm1' | /tmp/llvm-exegesis -mode=uops -snippets-file=-
def BWWriteZeroLatency : SchedWriteRes<[]> {
let Latency = 0;
}
def BWWriteZeroIdiom : SchedWriteVariant<[
SchedVar<MCSchedPredicate<ZeroIdiomPredicate>, [BWWriteZeroLatency]>,
SchedVar<NoSchedPred, [WriteALU]>
]>;
def : InstRW<[BWWriteZeroIdiom], (instrs SUB32rr, SUB64rr,
XOR32rr, XOR64rr)>;
def BWWriteFZeroIdiom : SchedWriteVariant<[
SchedVar<MCSchedPredicate<ZeroIdiomPredicate>, [BWWriteZeroLatency]>,
SchedVar<NoSchedPred, [WriteFLogic]>
]>;
def : InstRW<[BWWriteFZeroIdiom], (instrs XORPSrr, VXORPSrr, XORPDrr,
VXORPDrr)>;
def BWWriteFZeroIdiomY : SchedWriteVariant<[
SchedVar<MCSchedPredicate<ZeroIdiomPredicate>, [BWWriteZeroLatency]>,
SchedVar<NoSchedPred, [WriteFLogicY]>
]>;
def : InstRW<[BWWriteFZeroIdiomY], (instrs VXORPSYrr, VXORPDYrr)>;
def BWWriteVZeroIdiomLogicX : SchedWriteVariant<[
SchedVar<MCSchedPredicate<ZeroIdiomPredicate>, [BWWriteZeroLatency]>,
SchedVar<NoSchedPred, [WriteVecLogicX]>
]>;
def : InstRW<[BWWriteVZeroIdiomLogicX], (instrs PXORrr, VPXORrr)>;
def BWWriteVZeroIdiomLogicY : SchedWriteVariant<[
SchedVar<MCSchedPredicate<ZeroIdiomPredicate>, [BWWriteZeroLatency]>,
SchedVar<NoSchedPred, [WriteVecLogicY]>
]>;
def : InstRW<[BWWriteVZeroIdiomLogicY], (instrs VPXORYrr)>;
def BWWriteVZeroIdiomALUX : SchedWriteVariant<[
SchedVar<MCSchedPredicate<ZeroIdiomPredicate>, [BWWriteZeroLatency]>,
SchedVar<NoSchedPred, [WriteVecALUX]>
]>;
def : InstRW<[BWWriteVZeroIdiomALUX], (instrs PSUBBrr, VPSUBBrr,
PSUBDrr, VPSUBDrr,
PSUBQrr, VPSUBQrr,
PSUBWrr, VPSUBWrr,
PCMPGTBrr, VPCMPGTBrr,
PCMPGTDrr, VPCMPGTDrr,
PCMPGTWrr, VPCMPGTWrr)>;
def BWWriteVZeroIdiomALUY : SchedWriteVariant<[
SchedVar<MCSchedPredicate<ZeroIdiomPredicate>, [BWWriteZeroLatency]>,
SchedVar<NoSchedPred, [WriteVecALUY]>
]>;
def : InstRW<[BWWriteVZeroIdiomALUY], (instrs VPSUBBYrr,
VPSUBDYrr,
VPSUBQYrr,
VPSUBWYrr,
VPCMPGTBYrr,
VPCMPGTDYrr,
VPCMPGTWYrr)>;
def BWWritePCMPGTQ : SchedWriteRes<[BWPort0]> {
let Latency = 5;
let NumMicroOps = 1;
let ResourceCycles = [1];
}
def BWWriteVZeroIdiomPCMPGTQ : SchedWriteVariant<[
SchedVar<MCSchedPredicate<ZeroIdiomPredicate>, [BWWriteZeroLatency]>,
SchedVar<NoSchedPred, [BWWritePCMPGTQ]>
]>;
def : InstRW<[BWWriteVZeroIdiomPCMPGTQ], (instrs PCMPGTQrr, VPCMPGTQrr,
VPCMPGTQYrr)>;
// CMOVs that use both Z and C flag require an extra uop.
def BWWriteCMOVA_CMOVBErr : SchedWriteRes<[BWPort06,BWPort0156]> {
let Latency = 2;
let ResourceCycles = [1,1];
let NumMicroOps = 2;
}
def BWWriteCMOVA_CMOVBErm : SchedWriteRes<[BWPort23,BWPort06,BWPort0156]> {
let Latency = 7;
let ResourceCycles = [1,1,1];
let NumMicroOps = 3;
}
def BWCMOVA_CMOVBErr : SchedWriteVariant<[
SchedVar<MCSchedPredicate<IsCMOVArr_Or_CMOVBErr>, [BWWriteCMOVA_CMOVBErr]>,
SchedVar<NoSchedPred, [WriteCMOV]>
]>;
def BWCMOVA_CMOVBErm : SchedWriteVariant<[
SchedVar<MCSchedPredicate<IsCMOVArm_Or_CMOVBErm>, [BWWriteCMOVA_CMOVBErm]>,
SchedVar<NoSchedPred, [WriteCMOV.Folded]>
]>;
def : InstRW<[BWCMOVA_CMOVBErr], (instrs CMOV16rr, CMOV32rr, CMOV64rr)>;
def : InstRW<[BWCMOVA_CMOVBErm], (instrs CMOV16rm, CMOV32rm, CMOV64rm)>;
// SETCCs that use both Z and C flag require an extra uop.
def BWWriteSETA_SETBEr : SchedWriteRes<[BWPort06,BWPort0156]> {
let Latency = 2;
let ResourceCycles = [1,1];
let NumMicroOps = 2;
}
def BWWriteSETA_SETBEm : SchedWriteRes<[BWPort4,BWPort237,BWPort06,BWPort0156]> {
let Latency = 3;
let ResourceCycles = [1,1,1,1];
let NumMicroOps = 4;
}
def BWSETA_SETBErr : SchedWriteVariant<[
SchedVar<MCSchedPredicate<IsSETAr_Or_SETBEr>, [BWWriteSETA_SETBEr]>,
SchedVar<NoSchedPred, [WriteSETCC]>
]>;
def BWSETA_SETBErm : SchedWriteVariant<[
SchedVar<MCSchedPredicate<IsSETAm_Or_SETBEm>, [BWWriteSETA_SETBEm]>,
SchedVar<NoSchedPred, [WriteSETCCStore]>
]>;
def : InstRW<[BWSETA_SETBErr], (instrs SETCCr)>;
def : InstRW<[BWSETA_SETBErm], (instrs SETCCm)>;
} // SchedModel