forked from OSchip/llvm-project
406 lines
22 KiB
TableGen
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;
|
|
}
|
|
|