llvm-project/llvm/lib/Target/X86/X86ScheduleSLM.td

512 lines
23 KiB
TableGen
Raw Normal View History

//=- X86ScheduleSLM.td - X86 Silvermont 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 Intel Silvermont to support
// instruction scheduling and other instruction cost heuristics.
//
//===----------------------------------------------------------------------===//
def SLMModel : SchedMachineModel {
// All x86 instructions are modeled as a single micro-op, and SLM can decode 2
// instructions per cycle.
let IssueWidth = 2;
let MicroOpBufferSize = 32; // Based on the reorder buffer.
let LoadLatency = 3;
let MispredictPenalty = 10;
let PostRAScheduler = 1;
// For small loops, expand by a small factor to hide the backedge cost.
let LoopMicroOpBufferSize = 10;
// FIXME: SSE4 is unimplemented. This flag is set to allow
// the scheduler to assign a default model to unrecognized opcodes.
let CompleteModel = 0;
}
let SchedModel = SLMModel in {
// Silvermont has 5 reservation stations for micro-ops
def SLM_IEC_RSV0 : ProcResource<1>;
def SLM_IEC_RSV1 : ProcResource<1>;
def SLM_FPC_RSV0 : ProcResource<1> { let BufferSize = 1; }
def SLM_FPC_RSV1 : ProcResource<1> { let BufferSize = 1; }
def SLM_MEC_RSV : ProcResource<1>;
// Many micro-ops are capable of issuing on multiple ports.
def SLM_IEC_RSV01 : ProcResGroup<[SLM_IEC_RSV0, SLM_IEC_RSV1]>;
def SLM_FPC_RSV01 : ProcResGroup<[SLM_FPC_RSV0, SLM_FPC_RSV1]>;
def SLMDivider : ProcResource<1>;
def SLMFPMultiplier : ProcResource<1>;
def SLMFPDivider : ProcResource<1>;
// Loads are 3 cycles, so ReadAfterLd registers needn't be available until 3
// cycles after the memory operand.
def : ReadAdvance<ReadAfterLd, 3>;
def : ReadAdvance<ReadAfterVecLd, 3>;
def : ReadAdvance<ReadAfterVecXLd, 3>;
def : ReadAdvance<ReadAfterVecYLd, 3>;
[MC][X86] Correctly model additional operand latency caused by transfer delays from the integer to the floating point unit. This patch adds a new ReadAdvance definition named ReadInt2Fpu. ReadInt2Fpu allows x86 scheduling models to accurately describe delays caused by data transfers from the integer unit to the floating point unit. ReadInt2Fpu currently defaults to a delay of zero cycles (i.e. no delay) for all x86 models excluding BtVer2. That means, this patch is only a functional change for the Jaguar cpu model only. Tablegen definitions for instructions (V)PINSR* have been updated to account for the new ReadInt2Fpu. That read is mapped to the the GPR input operand. On Jaguar, int-to-fpu transfers are modeled as a +6cy delay. Before this patch, that extra delay was added to the opcode latency. In practice, the insert opcode only executes for 1cy. Most of the actual latency is actually contributed by the so-called operand-latency. According to the AMD SOG for family 16h, (V)PINSR* latency is defined by expression f+1, where f is defined as a forwarding delay from the integer unit to the fpu. When printing instruction latency from MCA (see InstructionInfoView.cpp) and LLC (only when flag -print-schedule is speified), we now need to account for any extra forwarding delays. We do this by checking if scheduling classes declare any negative ReadAdvance entries. Quoting a code comment in TargetSchedule.td: "A negative advance effectively increases latency, which may be used for cross-domain stalls". When computing the instruction latency for the purpose of our scheduling tests, we now add any extra delay to the formula. This avoids regressing existing codegen and mca schedule tests. It comes with the cost of an extra (but very simple) hook in MCSchedModel. Differential Revision: https://reviews.llvm.org/D57056 llvm-svn: 351965
2019-01-24 00:35:07 +08:00
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 SLMWriteResPair<X86FoldableSchedWrite SchedRW,
list<ProcResourceKind> ExePorts,
int Lat, list<int> Res = [1], int UOps = 1,
int LoadLat = 3> {
// 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 MEC_RSV and adds LoadLat cycles to
// the latency (default = 3).
def : WriteRes<SchedRW.Folded, !listconcat([SLM_MEC_RSV], ExePorts)> {
let Latency = !add(Lat, LoadLat);
let ResourceCycles = !listconcat([1], Res);
let NumMicroOps = UOps;
}
}
// A folded store needs a cycle on MEC_RSV for the store data, but it does not
// need an extra port cycle to recompute the address.
def : WriteRes<WriteRMW, [SLM_MEC_RSV]>;
def : WriteRes<WriteStore, [SLM_IEC_RSV01, SLM_MEC_RSV]>;
def : WriteRes<WriteStoreNT, [SLM_IEC_RSV01, SLM_MEC_RSV]>;
def : WriteRes<WriteLoad, [SLM_MEC_RSV]> { let Latency = 3; }
def : WriteRes<WriteMove, [SLM_IEC_RSV01]>;
def : WriteRes<WriteZero, []>;
// Load/store MXCSR.
// FIXME: These are probably wrong. They are copy pasted from WriteStore/Load.
def : WriteRes<WriteSTMXCSR, [SLM_IEC_RSV01, SLM_MEC_RSV]>;
def : WriteRes<WriteLDMXCSR, [SLM_MEC_RSV]> { let Latency = 3; }
// Treat misc copies as a move.
def : InstRW<[WriteMove], (instrs COPY)>;
defm : SLMWriteResPair<WriteALU, [SLM_IEC_RSV01], 1>;
defm : SLMWriteResPair<WriteADC, [SLM_IEC_RSV01], 1>;
defm : SLMWriteResPair<WriteIMul8, [SLM_IEC_RSV1], 3>;
defm : SLMWriteResPair<WriteIMul16, [SLM_IEC_RSV1], 3>;
defm : SLMWriteResPair<WriteIMul16Imm, [SLM_IEC_RSV1], 3>;
defm : SLMWriteResPair<WriteIMul16Reg, [SLM_IEC_RSV1], 3>;
defm : SLMWriteResPair<WriteIMul32, [SLM_IEC_RSV1], 3>;
defm : SLMWriteResPair<WriteIMul32Imm, [SLM_IEC_RSV1], 3>;
defm : SLMWriteResPair<WriteIMul32Reg, [SLM_IEC_RSV1], 3>;
defm : SLMWriteResPair<WriteIMul64, [SLM_IEC_RSV1], 3>;
defm : SLMWriteResPair<WriteIMul64Imm, [SLM_IEC_RSV1], 3>;
defm : SLMWriteResPair<WriteIMul64Reg, [SLM_IEC_RSV1], 3>;
defm : X86WriteRes<WriteBSWAP32, [SLM_IEC_RSV01], 1, [1], 1>;
defm : X86WriteRes<WriteBSWAP64, [SLM_IEC_RSV01], 1, [1], 1>;
defm : X86WriteRes<WriteCMPXCHG, [SLM_IEC_RSV01], 1, [1], 1>;
defm : X86WriteRes<WriteCMPXCHGRMW, [SLM_IEC_RSV01, SLM_MEC_RSV], 4, [1, 2], 2>;
defm : X86WriteRes<WriteXCHG, [SLM_IEC_RSV01], 1, [1], 1>;
defm : SLMWriteResPair<WriteShift, [SLM_IEC_RSV0], 1>;
defm : SLMWriteResPair<WriteShiftCL, [SLM_IEC_RSV0], 1>;
defm : SLMWriteResPair<WriteRotate, [SLM_IEC_RSV0], 1>;
defm : SLMWriteResPair<WriteRotateCL, [SLM_IEC_RSV0], 1>;
defm : X86WriteRes<WriteSHDrri, [SLM_IEC_RSV0], 1, [1], 1>;
defm : X86WriteRes<WriteSHDrrcl,[SLM_IEC_RSV0], 1, [1], 1>;
defm : X86WriteRes<WriteSHDmri, [SLM_MEC_RSV, SLM_IEC_RSV0], 4, [2, 1], 2>;
defm : X86WriteRes<WriteSHDmrcl,[SLM_MEC_RSV, SLM_IEC_RSV0], 4, [2, 1], 2>;
defm : SLMWriteResPair<WriteJump, [SLM_IEC_RSV1], 1>;
defm : SLMWriteResPair<WriteCRC32, [SLM_IEC_RSV1], 3>;
defm : SLMWriteResPair<WriteCMOV, [SLM_IEC_RSV01], 2, [2]>;
defm : SLMWriteResPair<WriteCMOV2, [SLM_IEC_RSV01], 2, [2]>;
defm : X86WriteRes<WriteFCMOV, [SLM_FPC_RSV1], 3, [1], 1>; // x87 conditional move.
def : WriteRes<WriteSETCC, [SLM_IEC_RSV01]>;
def : WriteRes<WriteSETCCStore, [SLM_IEC_RSV01, SLM_MEC_RSV]> {
// FIXME Latency and NumMicrOps?
let ResourceCycles = [2,1];
}
defm : X86WriteRes<WriteLAHFSAHF, [SLM_IEC_RSV01], 1, [1], 1>;
defm : X86WriteRes<WriteBitTest, [SLM_IEC_RSV01], 1, [1], 1>;
defm : X86WriteRes<WriteBitTestImmLd, [SLM_IEC_RSV01, SLM_MEC_RSV], 4, [1,1], 1>;
defm : X86WriteRes<WriteBitTestRegLd, [SLM_IEC_RSV01, SLM_MEC_RSV], 4, [1,1], 1>;
defm : X86WriteRes<WriteBitTestSet, [SLM_IEC_RSV01], 1, [1], 1>;
defm : X86WriteRes<WriteBitTestSetImmLd, [SLM_IEC_RSV01, SLM_MEC_RSV], 3, [1,1], 1>;
defm : X86WriteRes<WriteBitTestSetRegLd, [SLM_IEC_RSV01, SLM_MEC_RSV], 3, [1,1], 1>;
// This is for simple LEAs with one or two input operands.
// The complex ones can only execute on port 1, and they require two cycles on
// the port to read all inputs. We don't model that.
def : WriteRes<WriteLEA, [SLM_IEC_RSV1]>;
// Bit counts.
defm : SLMWriteResPair<WriteBSF, [SLM_IEC_RSV01], 10, [20], 10>;
defm : SLMWriteResPair<WriteBSR, [SLM_IEC_RSV01], 10, [20], 10>;
defm : SLMWriteResPair<WriteLZCNT, [SLM_IEC_RSV0], 3>;
defm : SLMWriteResPair<WriteTZCNT, [SLM_IEC_RSV0], 3>;
defm : SLMWriteResPair<WritePOPCNT, [SLM_IEC_RSV0], 3>;
// BMI1 BEXTR/BLS, BMI2 BZHI
defm : X86WriteResPairUnsupported<WriteBEXTR>;
defm : X86WriteResPairUnsupported<WriteBLS>;
defm : X86WriteResPairUnsupported<WriteBZHI>;
defm : SLMWriteResPair<WriteDiv8, [SLM_IEC_RSV01, SLMDivider], 25, [1,25], 1, 4>;
defm : SLMWriteResPair<WriteDiv16, [SLM_IEC_RSV01, SLMDivider], 25, [1,25], 1, 4>;
defm : SLMWriteResPair<WriteDiv32, [SLM_IEC_RSV01, SLMDivider], 25, [1,25], 1, 4>;
defm : SLMWriteResPair<WriteDiv64, [SLM_IEC_RSV01, SLMDivider], 25, [1,25], 1, 4>;
defm : SLMWriteResPair<WriteIDiv8, [SLM_IEC_RSV01, SLMDivider], 25, [1,25], 1, 4>;
defm : SLMWriteResPair<WriteIDiv16, [SLM_IEC_RSV01, SLMDivider], 25, [1,25], 1, 4>;
defm : SLMWriteResPair<WriteIDiv32, [SLM_IEC_RSV01, SLMDivider], 25, [1,25], 1, 4>;
defm : SLMWriteResPair<WriteIDiv64, [SLM_IEC_RSV01, SLMDivider], 25, [1,25], 1, 4>;
// Scalar and vector floating point.
defm : X86WriteRes<WriteFLD0, [SLM_FPC_RSV01], 1, [1], 1>;
defm : X86WriteRes<WriteFLD1, [SLM_FPC_RSV01], 1, [1], 1>;
defm : X86WriteRes<WriteFLDC, [SLM_FPC_RSV01], 1, [2], 2>;
def : WriteRes<WriteFLoad, [SLM_MEC_RSV]> { let Latency = 3; }
def : WriteRes<WriteFLoadX, [SLM_MEC_RSV]> { let Latency = 3; }
def : WriteRes<WriteFLoadY, [SLM_MEC_RSV]> { let Latency = 3; }
def : WriteRes<WriteFMaskedLoad, [SLM_MEC_RSV]> { let Latency = 3; }
def : WriteRes<WriteFMaskedLoadY, [SLM_MEC_RSV]> { let Latency = 3; }
def : WriteRes<WriteFStore, [SLM_MEC_RSV]>;
def : WriteRes<WriteFStoreX, [SLM_MEC_RSV]>;
def : WriteRes<WriteFStoreY, [SLM_MEC_RSV]>;
def : WriteRes<WriteFStoreNT, [SLM_MEC_RSV]>;
def : WriteRes<WriteFStoreNTX, [SLM_MEC_RSV]>;
def : WriteRes<WriteFStoreNTY, [SLM_MEC_RSV]>;
def : WriteRes<WriteFMaskedStore, [SLM_MEC_RSV]>;
def : WriteRes<WriteFMaskedStoreY, [SLM_MEC_RSV]>;
def : WriteRes<WriteFMove, [SLM_FPC_RSV01]>;
def : WriteRes<WriteFMoveX, [SLM_FPC_RSV01]>;
def : WriteRes<WriteFMoveY, [SLM_FPC_RSV01]>;
defm : X86WriteRes<WriteEMMS, [SLM_FPC_RSV01], 10, [10], 9>;
defm : SLMWriteResPair<WriteFAdd, [SLM_FPC_RSV1], 3>;
defm : SLMWriteResPair<WriteFAddX, [SLM_FPC_RSV1], 3>;
defm : SLMWriteResPair<WriteFAddY, [SLM_FPC_RSV1], 3>;
defm : X86WriteResPairUnsupported<WriteFAddZ>;
defm : SLMWriteResPair<WriteFAdd64, [SLM_FPC_RSV1], 3>;
defm : SLMWriteResPair<WriteFAdd64X, [SLM_FPC_RSV1], 3>;
defm : SLMWriteResPair<WriteFAdd64Y, [SLM_FPC_RSV1], 3>;
defm : X86WriteResPairUnsupported<WriteFAdd64Z>;
defm : SLMWriteResPair<WriteFCmp, [SLM_FPC_RSV1], 3>;
defm : SLMWriteResPair<WriteFCmpX, [SLM_FPC_RSV1], 3>;
defm : SLMWriteResPair<WriteFCmpY, [SLM_FPC_RSV1], 3>;
defm : X86WriteResPairUnsupported<WriteFCmpZ>;
defm : SLMWriteResPair<WriteFCmp64, [SLM_FPC_RSV1], 3>;
defm : SLMWriteResPair<WriteFCmp64X, [SLM_FPC_RSV1], 3>;
defm : SLMWriteResPair<WriteFCmp64Y, [SLM_FPC_RSV1], 3>;
defm : X86WriteResPairUnsupported<WriteFCmp64Z>;
defm : SLMWriteResPair<WriteFCom, [SLM_FPC_RSV1], 3>;
defm : SLMWriteResPair<WriteFMul, [SLM_FPC_RSV0, SLMFPMultiplier], 5, [1,2]>;
defm : SLMWriteResPair<WriteFMulX, [SLM_FPC_RSV0, SLMFPMultiplier], 5, [1,2]>;
defm : SLMWriteResPair<WriteFMulY, [SLM_FPC_RSV0, SLMFPMultiplier], 5, [1,2]>;
defm : X86WriteResPairUnsupported<WriteFMulZ>;
defm : SLMWriteResPair<WriteFMul64, [SLM_FPC_RSV0, SLMFPMultiplier], 5, [1,2]>;
defm : SLMWriteResPair<WriteFMul64X, [SLM_FPC_RSV0, SLMFPMultiplier], 5, [1,2]>;
defm : SLMWriteResPair<WriteFMul64Y, [SLM_FPC_RSV0, SLMFPMultiplier], 5, [1,2]>;
defm : X86WriteResPairUnsupported<WriteFMul64Z>;
defm : SLMWriteResPair<WriteFDiv, [SLM_FPC_RSV0, SLMFPDivider], 19, [1,17]>;
defm : SLMWriteResPair<WriteFDivX, [SLM_FPC_RSV0, SLMFPDivider], 39, [1,39]>;
defm : SLMWriteResPair<WriteFDivY, [SLM_FPC_RSV0, SLMFPDivider], 39, [1,39]>;
defm : X86WriteResPairUnsupported<WriteFDivZ>;
defm : SLMWriteResPair<WriteFDiv64, [SLM_FPC_RSV0, SLMFPDivider], 34, [1,32]>;
defm : SLMWriteResPair<WriteFDiv64X, [SLM_FPC_RSV0, SLMFPDivider], 69, [1,69]>;
defm : SLMWriteResPair<WriteFDiv64Y, [SLM_FPC_RSV0, SLMFPDivider], 69, [1,69]>;
defm : X86WriteResPairUnsupported<WriteFDiv64Z>;
defm : SLMWriteResPair<WriteFRcp, [SLM_FPC_RSV0], 5>;
defm : SLMWriteResPair<WriteFRcpX, [SLM_FPC_RSV0], 5>;
defm : SLMWriteResPair<WriteFRcpY, [SLM_FPC_RSV0], 5>;
defm : X86WriteResPairUnsupported<WriteFRcpZ>;
defm : SLMWriteResPair<WriteFRsqrt, [SLM_FPC_RSV0], 5>;
defm : SLMWriteResPair<WriteFRsqrtX, [SLM_FPC_RSV0], 5>;
defm : SLMWriteResPair<WriteFRsqrtY, [SLM_FPC_RSV0], 5>;
defm : X86WriteResPairUnsupported<WriteFRsqrtZ>;
defm : SLMWriteResPair<WriteFSqrt, [SLM_FPC_RSV0,SLMFPDivider], 20, [1,20], 1, 3>;
defm : SLMWriteResPair<WriteFSqrtX, [SLM_FPC_RSV0,SLMFPDivider], 41, [1,40], 1, 3>;
defm : SLMWriteResPair<WriteFSqrtY, [SLM_FPC_RSV0,SLMFPDivider], 41, [1,40], 1, 3>;
defm : X86WriteResPairUnsupported<WriteFSqrtZ>;
defm : SLMWriteResPair<WriteFSqrt64, [SLM_FPC_RSV0,SLMFPDivider], 35, [1,35], 1, 3>;
defm : SLMWriteResPair<WriteFSqrt64X, [SLM_FPC_RSV0,SLMFPDivider], 71, [1,70], 1, 3>;
defm : SLMWriteResPair<WriteFSqrt64Y, [SLM_FPC_RSV0,SLMFPDivider], 71, [1,70], 1, 3>;
defm : X86WriteResPairUnsupported<WriteFSqrt64Z>;
defm : SLMWriteResPair<WriteFSqrt80, [SLM_FPC_RSV0,SLMFPDivider], 40, [1,40]>;
defm : SLMWriteResPair<WriteDPPD, [SLM_FPC_RSV1], 3>;
defm : SLMWriteResPair<WriteDPPS, [SLM_FPC_RSV1], 3>;
defm : SLMWriteResPair<WriteDPPSY, [SLM_FPC_RSV1], 3>;
defm : X86WriteResPairUnsupported<WriteDPPSZ>;
defm : SLMWriteResPair<WriteFSign, [SLM_FPC_RSV01], 1>;
defm : SLMWriteResPair<WriteFRnd, [SLM_FPC_RSV1], 3>;
defm : SLMWriteResPair<WriteFRndY, [SLM_FPC_RSV1], 3>;
defm : X86WriteResPairUnsupported<WriteFRndZ>;
defm : SLMWriteResPair<WriteFLogic, [SLM_FPC_RSV01], 1>;
defm : SLMWriteResPair<WriteFLogicY, [SLM_FPC_RSV01], 1>;
defm : X86WriteResPairUnsupported<WriteFLogicZ>;
defm : SLMWriteResPair<WriteFTest, [SLM_FPC_RSV01], 1>;
defm : SLMWriteResPair<WriteFTestY, [SLM_FPC_RSV01], 1>;
defm : X86WriteResPairUnsupported<WriteFTestZ>;
defm : SLMWriteResPair<WriteFShuffle, [SLM_FPC_RSV0], 1>;
defm : SLMWriteResPair<WriteFShuffleY, [SLM_FPC_RSV0], 1>;
defm : X86WriteResPairUnsupported<WriteFShuffleZ>;
defm : SLMWriteResPair<WriteFVarShuffle, [SLM_FPC_RSV0], 1>;
defm : SLMWriteResPair<WriteFVarShuffleY,[SLM_FPC_RSV0], 1>;
defm : X86WriteResPairUnsupported<WriteFVarShuffleZ>;
defm : SLMWriteResPair<WriteFBlend, [SLM_FPC_RSV0], 1>;
// Conversion between integer and float.
defm : SLMWriteResPair<WriteCvtSS2I, [SLM_FPC_RSV01], 4>;
defm : SLMWriteResPair<WriteCvtPS2I, [SLM_FPC_RSV01], 4>;
defm : SLMWriteResPair<WriteCvtPS2IY, [SLM_FPC_RSV01], 4>;
defm : X86WriteResPairUnsupported<WriteCvtPS2IZ>;
defm : SLMWriteResPair<WriteCvtSD2I, [SLM_FPC_RSV01], 4>;
defm : SLMWriteResPair<WriteCvtPD2I, [SLM_FPC_RSV01], 4>;
defm : SLMWriteResPair<WriteCvtPD2IY, [SLM_FPC_RSV01], 4>;
defm : X86WriteResPairUnsupported<WriteCvtPD2IZ>;
defm : SLMWriteResPair<WriteCvtI2SS, [SLM_FPC_RSV01], 4>;
defm : SLMWriteResPair<WriteCvtI2PS, [SLM_FPC_RSV01], 4>;
defm : SLMWriteResPair<WriteCvtI2PSY, [SLM_FPC_RSV01], 4>;
defm : X86WriteResPairUnsupported<WriteCvtI2PSZ>;
defm : SLMWriteResPair<WriteCvtI2SD, [SLM_FPC_RSV01], 4>;
defm : SLMWriteResPair<WriteCvtI2PD, [SLM_FPC_RSV01], 4>;
defm : SLMWriteResPair<WriteCvtI2PDY, [SLM_FPC_RSV01], 4>;
defm : X86WriteResPairUnsupported<WriteCvtI2PDZ>;
defm : SLMWriteResPair<WriteCvtSS2SD, [SLM_FPC_RSV01], 4>;
defm : SLMWriteResPair<WriteCvtPS2PD, [SLM_FPC_RSV01], 4>;
defm : SLMWriteResPair<WriteCvtPS2PDY, [SLM_FPC_RSV01], 4>;
defm : X86WriteResPairUnsupported<WriteCvtPS2PDZ>;
defm : SLMWriteResPair<WriteCvtSD2SS, [SLM_FPC_RSV01], 4>;
defm : SLMWriteResPair<WriteCvtPD2PS, [SLM_FPC_RSV01], 4>;
defm : SLMWriteResPair<WriteCvtPD2PSY, [SLM_FPC_RSV01], 4>;
defm : X86WriteResPairUnsupported<WriteCvtPD2PSZ>;
// Vector integer operations.
def : WriteRes<WriteVecLoad, [SLM_MEC_RSV]> { let Latency = 3; }
def : WriteRes<WriteVecLoadX, [SLM_MEC_RSV]> { let Latency = 3; }
def : WriteRes<WriteVecLoadY, [SLM_MEC_RSV]> { let Latency = 3; }
def : WriteRes<WriteVecLoadNT, [SLM_MEC_RSV]> { let Latency = 3; }
def : WriteRes<WriteVecLoadNTY, [SLM_MEC_RSV]> { let Latency = 3; }
def : WriteRes<WriteVecMaskedLoad, [SLM_MEC_RSV]> { let Latency = 3; }
def : WriteRes<WriteVecMaskedLoadY, [SLM_MEC_RSV]> { let Latency = 3; }
def : WriteRes<WriteVecStore, [SLM_MEC_RSV]>;
def : WriteRes<WriteVecStoreX, [SLM_MEC_RSV]>;
def : WriteRes<WriteVecStoreY, [SLM_MEC_RSV]>;
def : WriteRes<WriteVecStoreNT, [SLM_MEC_RSV]>;
def : WriteRes<WriteVecStoreNTY, [SLM_MEC_RSV]>;
def : WriteRes<WriteVecMaskedStore, [SLM_MEC_RSV]>;
def : WriteRes<WriteVecMaskedStoreY, [SLM_MEC_RSV]>;
def : WriteRes<WriteVecMove, [SLM_FPC_RSV01]>;
def : WriteRes<WriteVecMoveX, [SLM_FPC_RSV01]>;
def : WriteRes<WriteVecMoveY, [SLM_FPC_RSV01]>;
def : WriteRes<WriteVecMoveToGpr, [SLM_IEC_RSV01]>;
def : WriteRes<WriteVecMoveFromGpr, [SLM_IEC_RSV01]>;
defm : SLMWriteResPair<WriteVecShift, [SLM_FPC_RSV0], 1>;
defm : SLMWriteResPair<WriteVecShiftX, [SLM_FPC_RSV0], 1>;
defm : SLMWriteResPair<WriteVecShiftY, [SLM_FPC_RSV0], 1>;
defm : X86WriteResPairUnsupported<WriteVecShiftZ>;
defm : SLMWriteResPair<WriteVecShiftImm, [SLM_FPC_RSV0], 1>;
defm : SLMWriteResPair<WriteVecShiftImmX,[SLM_FPC_RSV0], 1>;
defm : SLMWriteResPair<WriteVecShiftImmY,[SLM_FPC_RSV0], 1>;
defm : X86WriteResPairUnsupported<WriteVecShiftImmZ>;
defm : SLMWriteResPair<WriteVecLogic, [SLM_FPC_RSV01], 1>;
defm : SLMWriteResPair<WriteVecLogicX,[SLM_FPC_RSV01], 1>;
defm : SLMWriteResPair<WriteVecLogicY,[SLM_FPC_RSV01], 1>;
defm : X86WriteResPairUnsupported<WriteVecLogicZ>;
defm : SLMWriteResPair<WriteVecTest, [SLM_FPC_RSV01], 1>;
defm : SLMWriteResPair<WriteVecTestY, [SLM_FPC_RSV01], 1>;
defm : X86WriteResPairUnsupported<WriteVecTestZ>;
defm : SLMWriteResPair<WriteVecALU, [SLM_FPC_RSV01], 1>;
defm : SLMWriteResPair<WriteVecALUX, [SLM_FPC_RSV01], 1>;
defm : SLMWriteResPair<WriteVecALUY, [SLM_FPC_RSV01], 1>;
defm : X86WriteResPairUnsupported<WriteVecALUZ>;
defm : SLMWriteResPair<WriteVecIMul, [SLM_FPC_RSV0], 4>;
defm : SLMWriteResPair<WriteVecIMulX, [SLM_FPC_RSV0], 4>;
defm : SLMWriteResPair<WriteVecIMulY, [SLM_FPC_RSV0], 4>;
defm : X86WriteResPairUnsupported<WriteVecIMulZ>;
// FIXME: The below is closer to correct, but caused some perf regressions.
//defm : SLMWriteResPair<WritePMULLD, [SLM_FPC_RSV0], 11, [11], 7>;
defm : SLMWriteResPair<WritePMULLD, [SLM_FPC_RSV0], 4>;
defm : SLMWriteResPair<WritePMULLDY, [SLM_FPC_RSV0], 4>;
defm : X86WriteResPairUnsupported<WritePMULLDZ>;
defm : SLMWriteResPair<WriteShuffle, [SLM_FPC_RSV0], 1>;
defm : SLMWriteResPair<WriteShuffleY, [SLM_FPC_RSV0], 1>;
defm : X86WriteResPairUnsupported<WriteShuffleZ>;
defm : SLMWriteResPair<WriteShuffleX, [SLM_FPC_RSV0], 1>;
defm : SLMWriteResPair<WriteVarShuffle, [SLM_FPC_RSV0], 1>;
defm : SLMWriteResPair<WriteVarShuffleX, [SLM_FPC_RSV0], 1>;
defm : SLMWriteResPair<WriteVarShuffleY, [SLM_FPC_RSV0], 1>;
defm : X86WriteResPairUnsupported<WriteVarShuffleZ>;
defm : SLMWriteResPair<WriteBlend, [SLM_FPC_RSV0], 1>;
defm : SLMWriteResPair<WriteBlendY, [SLM_FPC_RSV0], 1>;
defm : X86WriteResPairUnsupported<WriteBlendZ>;
defm : SLMWriteResPair<WriteMPSAD, [SLM_FPC_RSV0], 7>;
defm : SLMWriteResPair<WriteMPSADY, [SLM_FPC_RSV0], 7>;
defm : X86WriteResPairUnsupported<WriteMPSADZ>;
defm : SLMWriteResPair<WritePSADBW, [SLM_FPC_RSV0], 4>;
defm : SLMWriteResPair<WritePSADBWX, [SLM_FPC_RSV0], 4>;
defm : SLMWriteResPair<WritePSADBWY, [SLM_FPC_RSV0], 4>;
defm : X86WriteResPairUnsupported<WritePSADBWZ>;
defm : SLMWriteResPair<WritePHMINPOS, [SLM_FPC_RSV0], 4>;
// Vector insert/extract operations.
defm : SLMWriteResPair<WriteVecInsert, [SLM_FPC_RSV0], 1>;
def : WriteRes<WriteVecExtract, [SLM_FPC_RSV0]>;
def : WriteRes<WriteVecExtractSt, [SLM_FPC_RSV0, SLM_MEC_RSV]> {
let Latency = 4;
let NumMicroOps = 2;
let ResourceCycles = [1, 2];
}
////////////////////////////////////////////////////////////////////////////////
// Horizontal add/sub instructions.
////////////////////////////////////////////////////////////////////////////////
defm : SLMWriteResPair<WriteFHAdd, [SLM_FPC_RSV01], 3, [2]>;
defm : SLMWriteResPair<WriteFHAddY, [SLM_FPC_RSV01], 3, [2]>;
defm : X86WriteResPairUnsupported<WriteFHAddZ>;
defm : SLMWriteResPair<WritePHAdd, [SLM_FPC_RSV01], 1>;
defm : SLMWriteResPair<WritePHAddX, [SLM_FPC_RSV01], 1>;
defm : SLMWriteResPair<WritePHAddY, [SLM_FPC_RSV01], 1>;
defm : X86WriteResPairUnsupported<WritePHAddZ>;
// String instructions.
// Packed Compare Implicit Length Strings, Return Mask
def : WriteRes<WritePCmpIStrM, [SLM_FPC_RSV0]> {
let Latency = 13;
let ResourceCycles = [13];
}
def : WriteRes<WritePCmpIStrMLd, [SLM_FPC_RSV0, SLM_MEC_RSV]> {
let Latency = 13;
let ResourceCycles = [13, 1];
}
// Packed Compare Explicit Length Strings, Return Mask
def : WriteRes<WritePCmpEStrM, [SLM_FPC_RSV0]> {
let Latency = 17;
let ResourceCycles = [17];
}
def : WriteRes<WritePCmpEStrMLd, [SLM_FPC_RSV0, SLM_MEC_RSV]> {
let Latency = 17;
let ResourceCycles = [17, 1];
}
// Packed Compare Implicit Length Strings, Return Index
def : WriteRes<WritePCmpIStrI, [SLM_FPC_RSV0]> {
let Latency = 17;
let ResourceCycles = [17];
}
def : WriteRes<WritePCmpIStrILd, [SLM_FPC_RSV0, SLM_MEC_RSV]> {
let Latency = 17;
let ResourceCycles = [17, 1];
}
// Packed Compare Explicit Length Strings, Return Index
def : WriteRes<WritePCmpEStrI, [SLM_FPC_RSV0]> {
let Latency = 21;
let ResourceCycles = [21];
}
def : WriteRes<WritePCmpEStrILd, [SLM_FPC_RSV0, SLM_MEC_RSV]> {
let Latency = 21;
let ResourceCycles = [21, 1];
}
// MOVMSK Instructions.
def : WriteRes<WriteFMOVMSK, [SLM_FPC_RSV1]> { let Latency = 4; }
def : WriteRes<WriteVecMOVMSK, [SLM_FPC_RSV1]> { let Latency = 4; }
def : WriteRes<WriteVecMOVMSKY, [SLM_FPC_RSV1]> { let Latency = 4; }
def : WriteRes<WriteMMXMOVMSK, [SLM_FPC_RSV1]> { let Latency = 4; }
// AES Instructions.
def : WriteRes<WriteAESDecEnc, [SLM_FPC_RSV0]> {
let Latency = 8;
let ResourceCycles = [5];
}
def : WriteRes<WriteAESDecEncLd, [SLM_FPC_RSV0, SLM_MEC_RSV]> {
let Latency = 8;
let ResourceCycles = [5, 1];
}
def : WriteRes<WriteAESIMC, [SLM_FPC_RSV0]> {
let Latency = 8;
let ResourceCycles = [5];
}
def : WriteRes<WriteAESIMCLd, [SLM_FPC_RSV0, SLM_MEC_RSV]> {
let Latency = 8;
let ResourceCycles = [5, 1];
}
def : WriteRes<WriteAESKeyGen, [SLM_FPC_RSV0]> {
let Latency = 8;
let ResourceCycles = [5];
}
def : WriteRes<WriteAESKeyGenLd, [SLM_FPC_RSV0, SLM_MEC_RSV]> {
let Latency = 8;
let ResourceCycles = [5, 1];
}
// Carry-less multiplication instructions.
def : WriteRes<WriteCLMul, [SLM_FPC_RSV0]> {
let Latency = 10;
let ResourceCycles = [10];
}
def : WriteRes<WriteCLMulLd, [SLM_FPC_RSV0, SLM_MEC_RSV]> {
let Latency = 10;
let ResourceCycles = [10, 1];
}
def : WriteRes<WriteSystem, [SLM_FPC_RSV0]> { let Latency = 100; }
def : WriteRes<WriteMicrocoded, [SLM_FPC_RSV0]> { let Latency = 100; }
def : WriteRes<WriteFence, [SLM_MEC_RSV]>;
def : WriteRes<WriteNop, []>;
// AVX/FMA is not supported on that architecture, but we should define the basic
// scheduling resources anyway.
def : WriteRes<WriteIMulH, [SLM_FPC_RSV0]>;
defm : X86WriteResPairUnsupported<WriteFBlendY>;
defm : X86WriteResPairUnsupported<WriteFBlendZ>;
defm : SLMWriteResPair<WriteVarBlend, [SLM_FPC_RSV0], 1>;
defm : X86WriteResPairUnsupported<WriteVarBlendY>;
defm : X86WriteResPairUnsupported<WriteVarBlendZ>;
defm : SLMWriteResPair<WriteFVarBlend, [SLM_FPC_RSV0], 1>;
defm : X86WriteResPairUnsupported<WriteFVarBlendY>;
defm : X86WriteResPairUnsupported<WriteFVarBlendZ>;
defm : X86WriteResPairUnsupported<WriteFShuffle256>;
defm : X86WriteResPairUnsupported<WriteFVarShuffle256>;
defm : X86WriteResPairUnsupported<WriteShuffle256>;
defm : X86WriteResPairUnsupported<WriteVarShuffle256>;
defm : SLMWriteResPair<WriteVarVecShift, [SLM_FPC_RSV0], 1>;
defm : X86WriteResPairUnsupported<WriteVarVecShiftY>;
defm : X86WriteResPairUnsupported<WriteVarVecShiftZ>;
defm : X86WriteResPairUnsupported<WriteFMA>;
defm : X86WriteResPairUnsupported<WriteFMAX>;
defm : X86WriteResPairUnsupported<WriteFMAY>;
defm : X86WriteResPairUnsupported<WriteFMAZ>;
defm : X86WriteResPairUnsupported<WriteCvtPH2PS>;
defm : X86WriteResPairUnsupported<WriteCvtPH2PSY>;
defm : X86WriteResPairUnsupported<WriteCvtPH2PSZ>;
defm : X86WriteResUnsupported<WriteCvtPS2PH>;
defm : X86WriteResUnsupported<WriteCvtPS2PHY>;
defm : X86WriteResUnsupported<WriteCvtPS2PHZ>;
defm : X86WriteResUnsupported<WriteCvtPS2PHSt>;
defm : X86WriteResUnsupported<WriteCvtPS2PHYSt>;
defm : X86WriteResUnsupported<WriteCvtPS2PHZSt>;
} // SchedModel