llvm-project/llvm/lib/Target/PowerPC/PPCScheduleP7.td

406 lines
22 KiB
TableGen

//===-- PPCScheduleP7.td - PPC P7 Scheduling Definitions ---*- tablegen -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file defines the itinerary class data for the POWER7 processor.
//
//===----------------------------------------------------------------------===//
// Primary reference:
// IBM POWER7 multicore server processor
// B. Sinharoy, et al.
// IBM J. Res. & Dev. (55) 3. May/June 2011.
// Scheduling for the P7 involves tracking two types of resources:
// 1. The dispatch bundle slots
// 2. The functional unit resources
// Dispatch units:
def P7_DU1 : FuncUnit;
def P7_DU2 : FuncUnit;
def P7_DU3 : FuncUnit;
def P7_DU4 : FuncUnit;
def P7_DU5 : FuncUnit;
def P7_DU6 : FuncUnit;
def P7_LS1 : FuncUnit; // Load/Store pipeline 1
def P7_LS2 : FuncUnit; // Load/Store pipeline 2
def P7_FX1 : FuncUnit; // FX pipeline 1
def P7_FX2 : FuncUnit; // FX pipeline 2
// VS pipeline 1 (vector integer ops. always here)
def P7_VS1 : FuncUnit; // VS pipeline 1
// VS pipeline 2 (128-bit stores and perms. here)
def P7_VS2 : FuncUnit; // VS pipeline 2
def P7_CRU : FuncUnit; // CR unit (CR logicals and move-from-SPRs)
def P7_BRU : FuncUnit; // BR unit
// Notes:
// Each LSU pipeline can also execute FX add and logical instructions.
// Each LSU pipeline can complete a load or store in one cycle.
//
// Each store is broken into two parts, AGEN goes to the LSU while a
// "data steering" op. goes to the FXU or VSU.
//
// FX loads have a two cycle load-to-use latency (so one "bubble" cycle).
// VSU loads have a three cycle load-to-use latency (so two "bubble" cycle).
//
// Frequent FX ops. take only one cycle and results can be used again in the
// next cycle (there is a self-bypass). Getting results from the other FX
// pipeline takes an additional cycle.
//
// The VSU XS is similar to the POWER6, but with a pipeline length of 2 cycles
// (instead of 3 cycles on the POWER6). VSU XS handles vector FX-style ops.
// Dispatch of an instruction to VS1 that uses four single prec. inputs
// (either to a float or XC op). prevents dispatch in that cycle to VS2 of any
// floating point instruction.
//
// The VSU PM is similar to the POWER6, but with a pipeline length of 3 cycles
// (instead of 4 cycles on the POWER6). vsel is handled by the PM pipeline
// (unlike on the POWER6).
//
// FMA from the VSUs can forward results in 6 cycles. VS1 XS and vector FP
// share the same write-back, and have a 5-cycle latency difference, so the
// IFU/IDU will not dispatch an XS instructon 5 cycles after a vector FP
// op. has been dispatched to VS1.
//
// Three cycles after an L1 cache hit, a dependent VSU instruction can issue.
//
// Instruction dispatch groups have (at most) four non-branch instructions, and
// two branches. Unlike on the POWER4/5, a branch does not automatically
// end the dispatch group, but a second branch must be the last in the group.
def P7Itineraries : ProcessorItineraries<
[P7_DU1, P7_DU2, P7_DU3, P7_DU4, P7_DU5, P7_DU6,
P7_LS1, P7_LS2, P7_FX1, P7_FX2, P7_VS1, P7_VS2, P7_CRU, P7_BRU], [], [
InstrItinData<IIC_IntSimple , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_FX1, P7_FX2,
P7_LS1, P7_LS2]>],
[1, 1, 1]>,
InstrItinData<IIC_IntGeneral , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[1, 1, 1]>,
InstrItinData<IIC_IntISEL, [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_FX1, P7_FX2], 0>,
InstrStage<1, [P7_BRU]>],
[1, 1, 1, 1]>,
InstrItinData<IIC_IntCompare , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[1, 1, 1]>,
// FIXME: Add record-form itinerary data.
InstrItinData<IIC_IntDivW , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_DU2], 0>,
InstrStage<36, [P7_FX1, P7_FX2]>],
[36, 1, 1]>,
InstrItinData<IIC_IntDivD , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_DU2], 0>,
InstrStage<68, [P7_FX1, P7_FX2]>],
[68, 1, 1]>,
InstrItinData<IIC_IntMulHW , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[4, 1, 1]>,
InstrItinData<IIC_IntMulHWU , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[4, 1, 1]>,
InstrItinData<IIC_IntMulHD , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[4, 1, 1]>,
InstrItinData<IIC_IntMulLI , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[4, 1, 1]>,
InstrItinData<IIC_IntRotate , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[1, 1, 1]>,
InstrItinData<IIC_IntRotateD , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[1, 1, 1]>,
InstrItinData<IIC_IntRotateDI , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[1, 1, 1]>,
InstrItinData<IIC_IntShift , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[1, 1, 1]>,
InstrItinData<IIC_IntTrapW , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[1, 1]>,
InstrItinData<IIC_IntTrapD , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[1, 1]>,
InstrItinData<IIC_BrB , [InstrStage<1, [P7_DU5, P7_DU6], 0>,
InstrStage<1, [P7_BRU]>],
[3, 1, 1]>,
InstrItinData<IIC_BrCR , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_CRU]>],
[3, 1, 1]>,
InstrItinData<IIC_BrMCR , [InstrStage<1, [P7_DU5, P7_DU6], 0>,
InstrStage<1, [P7_BRU]>],
[3, 1, 1]>,
InstrItinData<IIC_BrMCRX , [InstrStage<1, [P7_DU5, P7_DU6], 0>,
InstrStage<1, [P7_BRU]>],
[3, 1, 1]>,
InstrItinData<IIC_LdStLoad , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_LS1, P7_LS2]>],
[2, 1, 1]>,
InstrItinData<IIC_LdStLoadUpd , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_DU2], 0>,
InstrStage<1, [P7_LS1, P7_LS2], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[2, 2, 1, 1]>,
InstrItinData<IIC_LdStLoadUpdX, [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_DU2], 0>,
InstrStage<1, [P7_DU3], 0>,
InstrStage<1, [P7_DU4], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>,
InstrStage<1, [P7_LS1, P7_LS2], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[3, 3, 1, 1]>,
InstrItinData<IIC_LdStLD , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_LS1, P7_LS2]>],
[2, 1, 1]>,
InstrItinData<IIC_LdStLDU , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_DU2], 0>,
InstrStage<1, [P7_LS1, P7_LS2], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[2, 2, 1, 1]>,
InstrItinData<IIC_LdStLDUX , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_DU2], 0>,
InstrStage<1, [P7_DU3], 0>,
InstrStage<1, [P7_DU4], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>,
InstrStage<1, [P7_LS1, P7_LS2], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[3, 3, 1, 1]>,
InstrItinData<IIC_LdStLFD , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_LS1, P7_LS2]>],
[3, 1, 1]>,
InstrItinData<IIC_LdStLVecX , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_LS1, P7_LS2]>],
[3, 1, 1]>,
InstrItinData<IIC_LdStLFDU , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_DU2], 0>,
InstrStage<1, [P7_LS1, P7_LS2], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[3, 3, 1, 1]>,
InstrItinData<IIC_LdStLFDUX , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_DU2], 0>,
InstrStage<1, [P7_LS1, P7_LS2], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[3, 3, 1, 1]>,
InstrItinData<IIC_LdStLHA , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_DU2], 0>,
InstrStage<1, [P7_LS1, P7_LS2]>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[3, 1, 1]>,
InstrItinData<IIC_LdStLHAU , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_DU2], 0>,
InstrStage<1, [P7_LS1, P7_LS2], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[4, 4, 1, 1]>,
InstrItinData<IIC_LdStLHAUX , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_DU2], 0>,
InstrStage<1, [P7_DU3], 0>,
InstrStage<1, [P7_DU4], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>,
InstrStage<1, [P7_LS1, P7_LS2], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[4, 4, 1, 1]>,
InstrItinData<IIC_LdStLWA , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_DU2], 0>,
InstrStage<1, [P7_LS1, P7_LS2]>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[3, 1, 1]>,
InstrItinData<IIC_LdStLWARX, [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_DU2], 0>,
InstrStage<1, [P7_DU3], 0>,
InstrStage<1, [P7_DU4], 0>,
InstrStage<1, [P7_LS1, P7_LS2]>],
[3, 1, 1]>,
InstrItinData<IIC_LdStLDARX, [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_DU2], 0>,
InstrStage<1, [P7_DU3], 0>,
InstrStage<1, [P7_DU4], 0>,
InstrStage<1, [P7_LS1, P7_LS2]>],
[3, 1, 1]>,
InstrItinData<IIC_LdStLMW , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_LS1, P7_LS2]>],
[2, 1, 1]>,
InstrItinData<IIC_LdStStore , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_LS1, P7_LS2], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[1, 1, 1]>,
InstrItinData<IIC_LdStSTD , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_LS1, P7_LS2], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[1, 1, 1]>,
InstrItinData<IIC_LdStSTDU , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_DU2], 0>,
InstrStage<1, [P7_LS1, P7_LS2], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[2, 1, 1, 1]>,
InstrItinData<IIC_LdStSTDUX , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_DU2], 0>,
InstrStage<1, [P7_DU3], 0>,
InstrStage<1, [P7_DU4], 0>,
InstrStage<1, [P7_LS1, P7_LS2], 0>,
InstrStage<1, [P7_FX1, P7_FX2]>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[2, 1, 1, 1]>,
InstrItinData<IIC_LdStSTFD , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_LS1, P7_LS2], 0>,
InstrStage<1, [P7_VS1, P7_VS2]>],
[1, 1, 1]>,
InstrItinData<IIC_LdStSTFDU , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_DU2], 0>,
InstrStage<1, [P7_LS1, P7_LS2], 0>,
InstrStage<1, [P7_FX1, P7_FX2], 0>,
InstrStage<1, [P7_VS1, P7_VS2]>],
[2, 1, 1, 1]>,
InstrItinData<IIC_LdStSTVEBX , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_LS1, P7_LS2], 0>,
InstrStage<1, [P7_VS2]>],
[1, 1, 1]>,
InstrItinData<IIC_LdStSTDCX , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_DU2], 0>,
InstrStage<1, [P7_DU3], 0>,
InstrStage<1, [P7_DU4], 0>,
InstrStage<1, [P7_LS1, P7_LS2]>],
[1, 1, 1]>,
InstrItinData<IIC_LdStSTWCX , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_DU2], 0>,
InstrStage<1, [P7_DU3], 0>,
InstrStage<1, [P7_DU4], 0>,
InstrStage<1, [P7_LS1, P7_LS2]>],
[1, 1, 1]>,
InstrItinData<IIC_BrMCRX , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_DU2], 0>,
InstrStage<1, [P7_DU3], 0>,
InstrStage<1, [P7_DU4], 0>,
InstrStage<1, [P7_CRU]>,
InstrStage<1, [P7_FX1, P7_FX2]>],
[3, 1]>, // mtcr
InstrItinData<IIC_SprMFCR , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_CRU]>],
[6, 1]>,
InstrItinData<IIC_SprMFCRF , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_CRU]>],
[3, 1]>,
InstrItinData<IIC_SprMTSPR , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_FX1]>],
[4, 1]>, // mtctr
InstrItinData<IIC_FPGeneral , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_VS1, P7_VS2]>],
[5, 1, 1]>,
InstrItinData<IIC_FPAddSub , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_VS1, P7_VS2]>],
[5, 1, 1]>,
InstrItinData<IIC_FPCompare , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_VS1, P7_VS2]>],
[8, 1, 1]>,
InstrItinData<IIC_FPDivD , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_VS1, P7_VS2]>],
[33, 1, 1]>,
InstrItinData<IIC_FPDivS , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_VS1, P7_VS2]>],
[27, 1, 1]>,
InstrItinData<IIC_FPSqrtD , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_VS1, P7_VS2]>],
[44, 1, 1]>,
InstrItinData<IIC_FPSqrtS , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_VS1, P7_VS2]>],
[32, 1, 1]>,
InstrItinData<IIC_FPFused , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_VS1, P7_VS2]>],
[5, 1, 1, 1]>,
InstrItinData<IIC_FPRes , [InstrStage<1, [P7_DU1, P7_DU2,
P7_DU3, P7_DU4], 0>,
InstrStage<1, [P7_VS1, P7_VS2]>],
[5, 1, 1]>,
InstrItinData<IIC_VecGeneral , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_VS1]>],
[2, 1, 1]>,
InstrItinData<IIC_VecVSL , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_VS1]>],
[2, 1, 1]>,
InstrItinData<IIC_VecVSR , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_VS1]>],
[2, 1, 1]>,
InstrItinData<IIC_VecFP , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_VS1, P7_VS2]>],
[6, 1, 1]>,
InstrItinData<IIC_VecFPCompare, [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_VS1, P7_VS2]>],
[6, 1, 1]>,
InstrItinData<IIC_VecFPRound , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_VS1, P7_VS2]>],
[6, 1, 1]>,
InstrItinData<IIC_VecComplex , [InstrStage<1, [P7_DU1], 0>,
InstrStage<1, [P7_VS1]>],
[7, 1, 1]>,
InstrItinData<IIC_VecPerm , [InstrStage<1, [P7_DU1, P7_DU2], 0>,
InstrStage<1, [P7_VS2]>],
[3, 1, 1]>
]>;
// ===---------------------------------------------------------------------===//
// P7 machine model for scheduling and other instruction cost heuristics.
def P7Model : SchedMachineModel {
let IssueWidth = 6; // 4 (non-branch) instructions are dispatched per cycle.
// Note that the dispatch bundle size is 6 (including
// branches), but the total internal issue bandwidth per
// cycle (from all queues) is 8.
let LoadLatency = 3; // Optimistic load latency assuming bypass.
// This is overriden by OperandCycles if the
// Itineraries are queried instead.
let MispredictPenalty = 16;
// Try to make sure we have at least 10 dispatch groups in a loop.
let LoopMicroOpBufferSize = 40;
let CompleteModel = 0;
let Itineraries = P7Itineraries;
}