forked from OSchip/llvm-project
1145 lines
53 KiB
TableGen
1145 lines
53 KiB
TableGen
//=- ARMScheduleSwift.td - Swift 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 Swift processor..
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// ===---------------------------------------------------------------------===//
|
|
// This section contains legacy support for itineraries. This is
|
|
// required until SD and PostRA schedulers are replaced by MachineScheduler.
|
|
|
|
def SW_DIS0 : FuncUnit;
|
|
def SW_DIS1 : FuncUnit;
|
|
def SW_DIS2 : FuncUnit;
|
|
|
|
def SW_ALU0 : FuncUnit;
|
|
def SW_ALU1 : FuncUnit;
|
|
def SW_LS : FuncUnit;
|
|
def SW_IDIV : FuncUnit;
|
|
def SW_FDIV : FuncUnit;
|
|
|
|
// FIXME: Need bypasses.
|
|
// FIXME: Model the multiple stages of IIC_iMOVix2, IIC_iMOVix2addpc, and
|
|
// IIC_iMOVix2ld better.
|
|
// FIXME: Model the special immediate shifts that are not microcoded.
|
|
// FIXME: Do we need to model the fact that uses of r15 in a micro-op force it
|
|
// to issue on pipe 1?
|
|
// FIXME: Model the pipelined behavior of CMP / TST instructions.
|
|
// FIXME: Better model the microcode stages of multiply instructions, especially
|
|
// conditional variants.
|
|
// FIXME: Add preload instruction when it is documented.
|
|
// FIXME: Model non-pipelined nature of FP div / sqrt unit.
|
|
|
|
def SwiftItineraries : ProcessorItineraries<
|
|
[SW_DIS0, SW_DIS1, SW_DIS2, SW_ALU0, SW_ALU1, SW_LS, SW_IDIV, SW_FDIV], [], [
|
|
//
|
|
// Move instructions, unconditional
|
|
InstrItinData<IIC_iMOVi , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[1]>,
|
|
InstrItinData<IIC_iMOVr , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[1]>,
|
|
InstrItinData<IIC_iMOVsi , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[1]>,
|
|
InstrItinData<IIC_iMOVsr , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[1]>,
|
|
InstrItinData<IIC_iMOVix2 , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[2]>,
|
|
InstrItinData<IIC_iMOVix2addpc,[InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[3]>,
|
|
InstrItinData<IIC_iMOVix2ld,[InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[5]>,
|
|
//
|
|
// MVN instructions
|
|
InstrItinData<IIC_iMVNi , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[1]>,
|
|
InstrItinData<IIC_iMVNr , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[1]>,
|
|
InstrItinData<IIC_iMVNsi , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[1]>,
|
|
InstrItinData<IIC_iMVNsr , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[1]>,
|
|
//
|
|
// No operand cycles
|
|
InstrItinData<IIC_iALUx , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>]>,
|
|
//
|
|
// Binary Instructions that produce a result
|
|
InstrItinData<IIC_iALUi , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[1, 1]>,
|
|
InstrItinData<IIC_iALUr , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[1, 1, 1]>,
|
|
InstrItinData<IIC_iALUsi, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[2, 1, 1]>,
|
|
InstrItinData<IIC_iALUsir,[InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[2, 1, 1]>,
|
|
InstrItinData<IIC_iALUsr, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[2, 1, 1, 1]>,
|
|
//
|
|
// Bitwise Instructions that produce a result
|
|
InstrItinData<IIC_iBITi , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[1, 1]>,
|
|
InstrItinData<IIC_iBITr , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[1, 1, 1]>,
|
|
InstrItinData<IIC_iBITsi, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[2, 1, 1]>,
|
|
InstrItinData<IIC_iBITsr, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[2, 1, 1, 1]>,
|
|
//
|
|
// Unary Instructions that produce a result
|
|
|
|
// CLZ, RBIT, etc.
|
|
InstrItinData<IIC_iUNAr , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[1, 1]>,
|
|
|
|
// BFC, BFI, UBFX, SBFX
|
|
InstrItinData<IIC_iUNAsi, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[2, 1]>,
|
|
|
|
//
|
|
// Zero and sign extension instructions
|
|
InstrItinData<IIC_iEXTr , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[1, 1]>,
|
|
InstrItinData<IIC_iEXTAr, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[1, 1, 1]>,
|
|
InstrItinData<IIC_iEXTAsr,[InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[1, 1, 1, 1]>,
|
|
//
|
|
// Compare instructions
|
|
InstrItinData<IIC_iCMPi , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[1]>,
|
|
InstrItinData<IIC_iCMPr , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[1, 1]>,
|
|
InstrItinData<IIC_iCMPsi , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<2, [SW_ALU0, SW_ALU1]>],
|
|
[1, 1]>,
|
|
InstrItinData<IIC_iCMPsr , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<2, [SW_ALU0, SW_ALU1]>],
|
|
[1, 1, 1]>,
|
|
//
|
|
// Test instructions
|
|
InstrItinData<IIC_iTSTi , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[1]>,
|
|
InstrItinData<IIC_iTSTr , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[1, 1]>,
|
|
InstrItinData<IIC_iTSTsi , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<2, [SW_ALU0, SW_ALU1]>],
|
|
[1, 1]>,
|
|
InstrItinData<IIC_iTSTsr , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<2, [SW_ALU0, SW_ALU1]>],
|
|
[1, 1, 1]>,
|
|
//
|
|
// Move instructions, conditional
|
|
// FIXME: Correctly model the extra input dep on the destination.
|
|
InstrItinData<IIC_iCMOVi , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[1]>,
|
|
InstrItinData<IIC_iCMOVr , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[1, 1]>,
|
|
InstrItinData<IIC_iCMOVsi , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[1, 1]>,
|
|
InstrItinData<IIC_iCMOVsr , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[2, 1, 1]>,
|
|
InstrItinData<IIC_iCMOVix2, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[2]>,
|
|
|
|
// Integer multiply pipeline
|
|
//
|
|
InstrItinData<IIC_iMUL16 , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[3, 1, 1]>,
|
|
InstrItinData<IIC_iMAC16 , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[3, 1, 1, 1]>,
|
|
InstrItinData<IIC_iMUL32 , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[4, 1, 1]>,
|
|
InstrItinData<IIC_iMAC32 , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[4, 1, 1, 1]>,
|
|
InstrItinData<IIC_iMUL64 , [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0], 1>,
|
|
InstrStage<1, [SW_ALU0], 3>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[5, 5, 1, 1]>,
|
|
InstrItinData<IIC_iMAC64 , [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0], 1>,
|
|
InstrStage<1, [SW_ALU0], 1>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 3>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[5, 6, 1, 1]>,
|
|
//
|
|
// Integer divide
|
|
InstrItinData<IIC_iDIV , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0], 0>,
|
|
InstrStage<14, [SW_IDIV]>],
|
|
[14, 1, 1]>,
|
|
|
|
// Integer load pipeline
|
|
// FIXME: The timings are some rough approximations
|
|
//
|
|
// Immediate offset
|
|
InstrItinData<IIC_iLoad_i , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[3, 1]>,
|
|
InstrItinData<IIC_iLoad_bh_i, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[3, 1]>,
|
|
InstrItinData<IIC_iLoad_d_i , [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_LS], 1>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[3, 4, 1]>,
|
|
//
|
|
// Register offset
|
|
InstrItinData<IIC_iLoad_r , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[3, 1, 1]>,
|
|
InstrItinData<IIC_iLoad_bh_r, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[3, 1, 1]>,
|
|
InstrItinData<IIC_iLoad_d_r , [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_DIS2], 0>,
|
|
InstrStage<1, [SW_LS], 1>,
|
|
InstrStage<1, [SW_LS], 3>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[3, 4, 1, 1]>,
|
|
//
|
|
// Scaled register offset
|
|
InstrItinData<IIC_iLoad_si , [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 2>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[5, 1, 1]>,
|
|
InstrItinData<IIC_iLoad_bh_si,[InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 2>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[5, 1, 1]>,
|
|
//
|
|
// Immediate offset with update
|
|
InstrItinData<IIC_iLoad_iu , [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 1>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[3, 1, 1]>,
|
|
InstrItinData<IIC_iLoad_bh_iu,[InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 1>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[3, 1, 1]>,
|
|
//
|
|
// Register offset with update
|
|
InstrItinData<IIC_iLoad_ru , [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_ALU0], 1>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[3, 1, 1, 1]>,
|
|
InstrItinData<IIC_iLoad_bh_ru,[InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_ALU0], 1>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[3, 1, 1, 1]>,
|
|
InstrItinData<IIC_iLoad_d_ru, [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 0>,
|
|
InstrStage<1, [SW_LS], 3>,
|
|
InstrStage<1, [SW_LS], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[3, 4, 1, 1]>,
|
|
//
|
|
// Scaled register offset with update
|
|
InstrItinData<IIC_iLoad_siu , [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 2>,
|
|
InstrStage<1, [SW_LS], 3>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[5, 3, 1, 1]>,
|
|
InstrItinData<IIC_iLoad_bh_siu,[InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 2>,
|
|
InstrStage<1, [SW_LS], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[5, 3, 1, 1]>,
|
|
//
|
|
// Load multiple, def is the 5th operand.
|
|
// FIXME: This assumes 3 to 4 registers.
|
|
InstrItinData<IIC_iLoad_m , [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 1>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[1, 1, 1, 1, 3], [], -1>, // dynamic uops
|
|
|
|
//
|
|
// Load multiple + update, defs are the 1st and 5th operands.
|
|
InstrItinData<IIC_iLoad_mu , [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 0>,
|
|
InstrStage<1, [SW_LS], 3>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[2, 1, 1, 1, 3], [], -1>, // dynamic uops
|
|
//
|
|
// Load multiple plus branch
|
|
InstrItinData<IIC_iLoad_mBr, [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 1>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[1, 1, 1, 1, 3], [], -1>, // dynamic uops
|
|
//
|
|
// Pop, def is the 3rd operand.
|
|
InstrItinData<IIC_iPop , [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 1>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[1, 1, 3], [], -1>, // dynamic uops
|
|
//
|
|
// Pop + branch, def is the 3rd operand.
|
|
InstrItinData<IIC_iPop_Br, [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 1>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[1, 1, 3], [], -1>, // dynamic uops
|
|
|
|
//
|
|
// iLoadi + iALUr for t2LDRpci_pic.
|
|
InstrItinData<IIC_iLoadiALU, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_LS], 3>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[4, 1]>,
|
|
|
|
// Integer store pipeline
|
|
///
|
|
// Immediate offset
|
|
InstrItinData<IIC_iStore_i , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[1, 1]>,
|
|
InstrItinData<IIC_iStore_bh_i,[InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[1, 1]>,
|
|
InstrItinData<IIC_iStore_d_i, [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_DIS2], 0>,
|
|
InstrStage<1, [SW_LS], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 1>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[1, 1]>,
|
|
//
|
|
// Register offset
|
|
InstrItinData<IIC_iStore_r , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[1, 1, 1]>,
|
|
InstrItinData<IIC_iStore_bh_r,[InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[1, 1, 1]>,
|
|
InstrItinData<IIC_iStore_d_r, [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_DIS2], 0>,
|
|
InstrStage<1, [SW_LS], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 1>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[1, 1, 1]>,
|
|
//
|
|
// Scaled register offset
|
|
InstrItinData<IIC_iStore_si , [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 2>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[1, 1, 1]>,
|
|
InstrItinData<IIC_iStore_bh_si,[InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 2>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[1, 1, 1]>,
|
|
//
|
|
// Immediate offset with update
|
|
InstrItinData<IIC_iStore_iu , [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 1>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[1, 1, 1]>,
|
|
InstrItinData<IIC_iStore_bh_iu,[InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 1>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[1, 1, 1]>,
|
|
//
|
|
// Register offset with update
|
|
InstrItinData<IIC_iStore_ru , [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 1>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[1, 1, 1, 1]>,
|
|
InstrItinData<IIC_iStore_bh_ru,[InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 1>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[1, 1, 1, 1]>,
|
|
InstrItinData<IIC_iStore_d_ru, [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 1>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[1, 1, 1, 1]>,
|
|
//
|
|
// Scaled register offset with update
|
|
InstrItinData<IIC_iStore_siu, [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 2>,
|
|
InstrStage<1, [SW_LS], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 1>],
|
|
[3, 1, 1, 1]>,
|
|
InstrItinData<IIC_iStore_bh_siu, [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 2>,
|
|
InstrStage<1, [SW_LS], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 1>],
|
|
[3, 1, 1, 1]>,
|
|
//
|
|
// Store multiple
|
|
InstrItinData<IIC_iStore_m , [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 1>,
|
|
InstrStage<1, [SW_LS], 1>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 1>,
|
|
InstrStage<1, [SW_LS], 1>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 1>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[], [], -1>, // dynamic uops
|
|
//
|
|
// Store multiple + update
|
|
InstrItinData<IIC_iStore_mu, [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 1>,
|
|
InstrStage<1, [SW_LS], 1>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 1>,
|
|
InstrStage<1, [SW_LS], 1>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1], 1>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[2], [], -1>, // dynamic uops
|
|
|
|
//
|
|
// Preload
|
|
InstrItinData<IIC_Preload, [InstrStage<1, [SW_DIS0], 0>], [1, 1]>,
|
|
|
|
// Branch
|
|
//
|
|
// no delay slots, so the latency of a branch is unimportant
|
|
InstrItinData<IIC_Br , [InstrStage<1, [SW_DIS0], 0>]>,
|
|
|
|
// FP Special Register to Integer Register File Move
|
|
InstrItinData<IIC_fpSTAT , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[1]>,
|
|
//
|
|
// Single-precision FP Unary
|
|
//
|
|
// Most floating-point moves get issued on ALU0.
|
|
InstrItinData<IIC_fpUNA32 , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[2, 1]>,
|
|
//
|
|
// Double-precision FP Unary
|
|
InstrItinData<IIC_fpUNA64 , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[2, 1]>,
|
|
|
|
//
|
|
// Single-precision FP Compare
|
|
InstrItinData<IIC_fpCMP32 , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[1, 1]>,
|
|
//
|
|
// Double-precision FP Compare
|
|
InstrItinData<IIC_fpCMP64 , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[1, 1]>,
|
|
//
|
|
// Single to Double FP Convert
|
|
InstrItinData<IIC_fpCVTSD , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[4, 1]>,
|
|
//
|
|
// Double to Single FP Convert
|
|
InstrItinData<IIC_fpCVTDS , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[4, 1]>,
|
|
|
|
//
|
|
// Single to Half FP Convert
|
|
InstrItinData<IIC_fpCVTSH , [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_ALU1], 4>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[6, 1]>,
|
|
//
|
|
// Half to Single FP Convert
|
|
InstrItinData<IIC_fpCVTHS , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[4, 1]>,
|
|
|
|
//
|
|
// Single-Precision FP to Integer Convert
|
|
InstrItinData<IIC_fpCVTSI , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[4, 1]>,
|
|
//
|
|
// Double-Precision FP to Integer Convert
|
|
InstrItinData<IIC_fpCVTDI , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[4, 1]>,
|
|
//
|
|
// Integer to Single-Precision FP Convert
|
|
InstrItinData<IIC_fpCVTIS , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[4, 1]>,
|
|
//
|
|
// Integer to Double-Precision FP Convert
|
|
InstrItinData<IIC_fpCVTID , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[4, 1]>,
|
|
//
|
|
// Single-precision FP ALU
|
|
InstrItinData<IIC_fpALU32 , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[2, 1, 1]>,
|
|
//
|
|
// Double-precision FP ALU
|
|
InstrItinData<IIC_fpALU64 , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[2, 1, 1]>,
|
|
//
|
|
// Single-precision FP Multiply
|
|
InstrItinData<IIC_fpMUL32 , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[4, 1, 1]>,
|
|
//
|
|
// Double-precision FP Multiply
|
|
InstrItinData<IIC_fpMUL64 , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[6, 1, 1]>,
|
|
//
|
|
// Single-precision FP MAC
|
|
InstrItinData<IIC_fpMAC32 , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[8, 1, 1]>,
|
|
//
|
|
// Double-precision FP MAC
|
|
InstrItinData<IIC_fpMAC64 , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[12, 1, 1]>,
|
|
//
|
|
// Single-precision Fused FP MAC
|
|
InstrItinData<IIC_fpFMAC32, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[8, 1, 1]>,
|
|
//
|
|
// Double-precision Fused FP MAC
|
|
InstrItinData<IIC_fpFMAC64, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[12, 1, 1]>,
|
|
//
|
|
// Single-precision FP DIV
|
|
InstrItinData<IIC_fpDIV32 , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1], 0>,
|
|
InstrStage<15, [SW_FDIV]>],
|
|
[17, 1, 1]>,
|
|
//
|
|
// Double-precision FP DIV
|
|
InstrItinData<IIC_fpDIV64 , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1], 0>,
|
|
InstrStage<30, [SW_FDIV]>],
|
|
[32, 1, 1]>,
|
|
//
|
|
// Single-precision FP SQRT
|
|
InstrItinData<IIC_fpSQRT32, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1], 0>,
|
|
InstrStage<15, [SW_FDIV]>],
|
|
[17, 1]>,
|
|
//
|
|
// Double-precision FP SQRT
|
|
InstrItinData<IIC_fpSQRT64, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1], 0>,
|
|
InstrStage<30, [SW_FDIV]>],
|
|
[32, 1, 1]>,
|
|
|
|
//
|
|
// Integer to Single-precision Move
|
|
InstrItinData<IIC_fpMOVIS, [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_LS], 4>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[6, 1]>,
|
|
//
|
|
// Integer to Double-precision Move
|
|
InstrItinData<IIC_fpMOVID, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[4, 1]>,
|
|
//
|
|
// Single-precision to Integer Move
|
|
InstrItinData<IIC_fpMOVSI, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[3, 1]>,
|
|
//
|
|
// Double-precision to Integer Move
|
|
InstrItinData<IIC_fpMOVDI, [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_LS], 3>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[3, 4, 1]>,
|
|
//
|
|
// Single-precision FP Load
|
|
InstrItinData<IIC_fpLoad32, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[4, 1]>,
|
|
//
|
|
// Double-precision FP Load
|
|
InstrItinData<IIC_fpLoad64, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[4, 1]>,
|
|
//
|
|
// FP Load Multiple
|
|
// FIXME: Assumes a single Q register.
|
|
InstrItinData<IIC_fpLoad_m, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[1, 1, 1, 4], [], -1>, // dynamic uops
|
|
//
|
|
// FP Load Multiple + update
|
|
// FIXME: Assumes a single Q register.
|
|
InstrItinData<IIC_fpLoad_mu,[InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_LS], 4>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[2, 1, 1, 1, 4], [], -1>, // dynamic uops
|
|
//
|
|
// Single-precision FP Store
|
|
InstrItinData<IIC_fpStore32,[InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[1, 1]>,
|
|
//
|
|
// Double-precision FP Store
|
|
InstrItinData<IIC_fpStore64,[InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[1, 1]>,
|
|
//
|
|
// FP Store Multiple
|
|
// FIXME: Assumes a single Q register.
|
|
InstrItinData<IIC_fpStore_m,[InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[1, 1, 1], [], -1>, // dynamic uops
|
|
//
|
|
// FP Store Multiple + update
|
|
// FIXME: Assumes a single Q register.
|
|
InstrItinData<IIC_fpStore_mu,[InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_LS], 4>,
|
|
InstrStage<1, [SW_ALU0, SW_ALU1]>],
|
|
[2, 1, 1, 1], [], -1>, // dynamic uops
|
|
// NEON
|
|
//
|
|
// Double-register Integer Unary
|
|
InstrItinData<IIC_VUNAiD, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[4, 1]>,
|
|
//
|
|
// Quad-register Integer Unary
|
|
InstrItinData<IIC_VUNAiQ, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[4, 1]>,
|
|
//
|
|
// Double-register Integer Q-Unary
|
|
InstrItinData<IIC_VQUNAiD, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[4, 1]>,
|
|
//
|
|
// Quad-register Integer CountQ-Unary
|
|
InstrItinData<IIC_VQUNAiQ, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[4, 1]>,
|
|
//
|
|
// Double-register Integer Binary
|
|
InstrItinData<IIC_VBINiD, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[2, 1, 1]>,
|
|
//
|
|
// Quad-register Integer Binary
|
|
InstrItinData<IIC_VBINiQ, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[2, 1, 1]>,
|
|
//
|
|
// Double-register Integer Subtract
|
|
InstrItinData<IIC_VSUBiD, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[2, 1, 1]>,
|
|
//
|
|
// Quad-register Integer Subtract
|
|
InstrItinData<IIC_VSUBiQ, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[2, 1, 1]>,
|
|
//
|
|
// Double-register Integer Shift
|
|
InstrItinData<IIC_VSHLiD, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[2, 1, 1]>,
|
|
//
|
|
// Quad-register Integer Shift
|
|
InstrItinData<IIC_VSHLiQ, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[2, 1, 1]>,
|
|
//
|
|
// Double-register Integer Shift (4 cycle)
|
|
InstrItinData<IIC_VSHLi4D, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[4, 1, 1]>,
|
|
//
|
|
// Quad-register Integer Shift (4 cycle)
|
|
InstrItinData<IIC_VSHLi4Q, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[4, 1, 1]>,
|
|
//
|
|
// Double-register Integer Binary (4 cycle)
|
|
InstrItinData<IIC_VBINi4D, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[4, 1, 1]>,
|
|
//
|
|
// Quad-register Integer Binary (4 cycle)
|
|
InstrItinData<IIC_VBINi4Q, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[4, 1, 1]>,
|
|
//
|
|
// Double-register Integer Subtract (4 cycle)
|
|
InstrItinData<IIC_VSUBi4D, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[4, 1, 1]>,
|
|
//
|
|
// Quad-register Integer Subtract (4 cycle)
|
|
InstrItinData<IIC_VSUBi4Q, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[4, 1, 1]>,
|
|
|
|
//
|
|
// Double-register Integer Count
|
|
InstrItinData<IIC_VCNTiD, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[2, 1, 1]>,
|
|
//
|
|
// Quad-register Integer Count
|
|
InstrItinData<IIC_VCNTiQ, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[2, 1, 1]>,
|
|
//
|
|
// Double-register Absolute Difference and Accumulate
|
|
InstrItinData<IIC_VABAD, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[4, 1, 1, 1]>,
|
|
//
|
|
// Quad-register Absolute Difference and Accumulate
|
|
InstrItinData<IIC_VABAQ, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[4, 1, 1, 1]>,
|
|
//
|
|
// Double-register Integer Pair Add Long
|
|
InstrItinData<IIC_VPALiD, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[4, 1, 1]>,
|
|
//
|
|
// Quad-register Integer Pair Add Long
|
|
InstrItinData<IIC_VPALiQ, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[4, 1, 1]>,
|
|
|
|
//
|
|
// Double-register Integer Multiply (.8, .16)
|
|
InstrItinData<IIC_VMULi16D, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[4, 1, 1]>,
|
|
//
|
|
// Quad-register Integer Multiply (.8, .16)
|
|
InstrItinData<IIC_VMULi16Q, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[4, 1, 1]>,
|
|
|
|
//
|
|
// Double-register Integer Multiply (.32)
|
|
InstrItinData<IIC_VMULi32D, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[4, 1, 1]>,
|
|
//
|
|
// Quad-register Integer Multiply (.32)
|
|
InstrItinData<IIC_VMULi32Q, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[4, 1, 1]>,
|
|
//
|
|
// Double-register Integer Multiply-Accumulate (.8, .16)
|
|
InstrItinData<IIC_VMACi16D, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[4, 1, 1, 1]>,
|
|
//
|
|
// Double-register Integer Multiply-Accumulate (.32)
|
|
InstrItinData<IIC_VMACi32D, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[4, 1, 1, 1]>,
|
|
//
|
|
// Quad-register Integer Multiply-Accumulate (.8, .16)
|
|
InstrItinData<IIC_VMACi16Q, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[4, 1, 1, 1]>,
|
|
//
|
|
// Quad-register Integer Multiply-Accumulate (.32)
|
|
InstrItinData<IIC_VMACi32Q, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[4, 1, 1, 1]>,
|
|
|
|
//
|
|
// Move
|
|
InstrItinData<IIC_VMOV, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[2, 1]>,
|
|
//
|
|
// Move Immediate
|
|
InstrItinData<IIC_VMOVImm, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[2]>,
|
|
//
|
|
// Double-register Permute Move
|
|
InstrItinData<IIC_VMOVD, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[2, 1]>,
|
|
//
|
|
// Quad-register Permute Move
|
|
InstrItinData<IIC_VMOVQ, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[2, 1]>,
|
|
//
|
|
// Integer to Single-precision Move
|
|
InstrItinData<IIC_VMOVIS , [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_LS], 4>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[6, 1]>,
|
|
//
|
|
// Integer to Double-precision Move
|
|
InstrItinData<IIC_VMOVID , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[4, 1, 1]>,
|
|
//
|
|
// Single-precision to Integer Move
|
|
InstrItinData<IIC_VMOVSI , [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[3, 1]>,
|
|
//
|
|
// Double-precision to Integer Move
|
|
InstrItinData<IIC_VMOVDI , [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_LS], 3>,
|
|
InstrStage<1, [SW_LS]>],
|
|
[3, 4, 1]>,
|
|
//
|
|
// Integer to Lane Move
|
|
// FIXME: I think this is correct, but it is not clear from the tuning guide.
|
|
InstrItinData<IIC_VMOVISL , [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_LS], 4>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[6, 1]>,
|
|
|
|
//
|
|
// Vector narrow move
|
|
InstrItinData<IIC_VMOVN, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[2, 1]>,
|
|
//
|
|
// Double-register FP Unary
|
|
// FIXME: VRECPE / VRSQRTE has a longer latency than VABS, which is used here,
|
|
// and they issue on a different pipeline.
|
|
InstrItinData<IIC_VUNAD, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[2, 1]>,
|
|
//
|
|
// Quad-register FP Unary
|
|
// FIXME: VRECPE / VRSQRTE has a longer latency than VABS, which is used here,
|
|
// and they issue on a different pipeline.
|
|
InstrItinData<IIC_VUNAQ, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[2, 1]>,
|
|
//
|
|
// Double-register FP Binary
|
|
// FIXME: We're using this itin for many instructions.
|
|
InstrItinData<IIC_VBIND, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[4, 1, 1]>,
|
|
|
|
//
|
|
// VPADD, etc.
|
|
InstrItinData<IIC_VPBIND, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[4, 1, 1]>,
|
|
//
|
|
// Double-register FP VMUL
|
|
InstrItinData<IIC_VFMULD, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[4, 1, 1]>,
|
|
//
|
|
// Quad-register FP Binary
|
|
InstrItinData<IIC_VBINQ, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU0]>],
|
|
[4, 1, 1]>,
|
|
//
|
|
// Quad-register FP VMUL
|
|
InstrItinData<IIC_VFMULQ, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[4, 1, 1]>,
|
|
//
|
|
// Double-register FP Multiple-Accumulate
|
|
InstrItinData<IIC_VMACD, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[8, 1, 1]>,
|
|
//
|
|
// Quad-register FP Multiple-Accumulate
|
|
InstrItinData<IIC_VMACQ, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[8, 1, 1]>,
|
|
//
|
|
// Double-register Fused FP Multiple-Accumulate
|
|
InstrItinData<IIC_VFMACD, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[8, 1, 1]>,
|
|
//
|
|
// Quad-register FusedF P Multiple-Accumulate
|
|
InstrItinData<IIC_VFMACQ, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[8, 1, 1]>,
|
|
//
|
|
// Double-register Reciprical Step
|
|
InstrItinData<IIC_VRECSD, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[8, 1, 1]>,
|
|
//
|
|
// Quad-register Reciprical Step
|
|
InstrItinData<IIC_VRECSQ, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[8, 1, 1]>,
|
|
//
|
|
// Double-register Permute
|
|
// FIXME: The latencies are unclear from the documentation.
|
|
InstrItinData<IIC_VPERMD, [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1], 2>,
|
|
InstrStage<1, [SW_ALU1], 2>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[3, 4, 3, 4]>,
|
|
//
|
|
// Quad-register Permute
|
|
// FIXME: The latencies are unclear from the documentation.
|
|
InstrItinData<IIC_VPERMQ, [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1], 2>,
|
|
InstrStage<1, [SW_ALU1], 2>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[3, 4, 3, 4]>,
|
|
//
|
|
// Quad-register Permute (3 cycle issue on A9)
|
|
InstrItinData<IIC_VPERMQ3, [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1], 2>,
|
|
InstrStage<1, [SW_ALU1], 2>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[3, 4, 3, 4]>,
|
|
|
|
//
|
|
// Double-register VEXT
|
|
InstrItinData<IIC_VEXTD, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[2, 1, 1]>,
|
|
//
|
|
// Quad-register VEXT
|
|
InstrItinData<IIC_VEXTQ, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[2, 1, 1]>,
|
|
//
|
|
// VTB
|
|
InstrItinData<IIC_VTB1, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[2, 1, 1]>,
|
|
InstrItinData<IIC_VTB2, [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_ALU1], 2>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[4, 1, 3, 3]>,
|
|
InstrItinData<IIC_VTB3, [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1], 2>,
|
|
InstrStage<1, [SW_ALU1], 2>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[6, 1, 3, 5, 5]>,
|
|
InstrItinData<IIC_VTB4, [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1], 2>,
|
|
InstrStage<1, [SW_ALU1], 2>,
|
|
InstrStage<1, [SW_ALU1], 2>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[8, 1, 3, 5, 7, 7]>,
|
|
//
|
|
// VTBX
|
|
InstrItinData<IIC_VTBX1, [InstrStage<1, [SW_DIS0, SW_DIS1, SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[2, 1, 1]>,
|
|
InstrItinData<IIC_VTBX2, [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_ALU1], 2>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[4, 1, 3, 3]>,
|
|
InstrItinData<IIC_VTBX3, [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1], 2>,
|
|
InstrStage<1, [SW_ALU1], 2>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[6, 1, 3, 5, 5]>,
|
|
InstrItinData<IIC_VTBX4, [InstrStage<1, [SW_DIS0], 0>,
|
|
InstrStage<1, [SW_DIS1], 0>,
|
|
InstrStage<1, [SW_DIS2], 0>,
|
|
InstrStage<1, [SW_ALU1], 2>,
|
|
InstrStage<1, [SW_ALU1], 2>,
|
|
InstrStage<1, [SW_ALU1], 2>,
|
|
InstrStage<1, [SW_ALU1]>],
|
|
[8, 1, 3, 5, 7, 7]>
|
|
]>;
|
|
|
|
// ===---------------------------------------------------------------------===//
|
|
// This following definitions describe the simple machine model which
|
|
// will replace itineraries.
|
|
|
|
// Swift machine model for scheduling and other instruction cost heuristics.
|
|
def SwiftModel : SchedMachineModel {
|
|
let IssueWidth = 3; // 3 micro-ops are dispatched per cycle.
|
|
let MinLatency = 0; // Data dependencies are allowed within dispatch groups.
|
|
let LoadLatency = 3;
|
|
let MispredictPenalty = 14; // A branch direction mispredict.
|
|
|
|
let Itineraries = SwiftItineraries;
|
|
}
|
|
|
|
// Swift predicates.
|
|
def IsFastImmShiftSwiftPred : SchedPredicate<[{TII->isSwiftFastImmShift(MI)}]>;
|
|
|
|
// Swift resource mapping.
|
|
let SchedModel = SwiftModel in {
|
|
// Processor resources.
|
|
def SwiftUnitP01 : ProcResource<2>; // ALU unit.
|
|
def SwiftUnitP0 : ProcResource<1> { let Super = SwiftUnitP01; } // Mul unit.
|
|
def SwiftUnitP1 : ProcResource<1> { let Super = SwiftUnitP01; } // Br unit.
|
|
def SwiftUnitP2 : ProcResource<1>; // LS unit.
|
|
def SwiftUnitDiv : ProcResource<1>;
|
|
|
|
// Generic resource requirements.
|
|
def SwiftWriteP01TwoCycle : SchedWriteRes<[SwiftUnitP01]> { let Latency = 2; }
|
|
def SwiftWriteP01ThreeCycleTwoUops :
|
|
SchedWriteRes<[SwiftUnitP01, SwiftUnitP01]> {
|
|
let Latency = 3;
|
|
let NumMicroOps = 2;
|
|
}
|
|
def SwiftWriteP0ThreeCycleThreeUops : SchedWriteRes<[SwiftUnitP0]> {
|
|
let Latency = 3;
|
|
let NumMicroOps = 3;
|
|
let ResourceCycles = [3];
|
|
}
|
|
|
|
// 4.2.4 Arithmetic and Logical.
|
|
// ALU operation register shifted by immediate variant.
|
|
def SwiftWriteALUsi : SchedWriteVariant<[
|
|
// lsl #2, lsl #1, or lsr #1.
|
|
SchedVar<IsFastImmShiftSwiftPred, [SwiftWriteP01TwoCycle]>,
|
|
SchedVar<NoSchedPred, [WriteALU]>
|
|
]>;
|
|
def SwiftWriteALUsr : SchedWriteVariant<[
|
|
SchedVar<IsPredicatedPred, [SwiftWriteP01ThreeCycleTwoUops]>,
|
|
SchedVar<NoSchedPred, [SwiftWriteP01TwoCycle]>
|
|
]>;
|
|
def SwiftWriteALUSsr : SchedWriteVariant<[
|
|
SchedVar<IsPredicatedPred, [SwiftWriteP0ThreeCycleThreeUops]>,
|
|
SchedVar<NoSchedPred, [SwiftWriteP01TwoCycle]>
|
|
]>;
|
|
def SwiftReadAdvanceALUsr : SchedReadVariant<[
|
|
SchedVar<IsPredicatedPred, [SchedReadAdvance<2>]>,
|
|
SchedVar<NoSchedPred, [NoReadAdvance]>
|
|
]>;
|
|
// ADC,ADD,NEG,RSB,RSC,SBC,SUB,ADR
|
|
// AND,BIC,EOR,ORN,ORR
|
|
// CLZ,RBIT,REV,REV16,REVSH,PKH
|
|
def : WriteRes<WriteALU, [SwiftUnitP01]>;
|
|
def : SchedAlias<WriteALUsi, SwiftWriteALUsi>;
|
|
def : SchedAlias<WriteALUsr, SwiftWriteALUsr>;
|
|
def : SchedAlias<WriteALUSsr, SwiftWriteALUSsr>;
|
|
def : ReadAdvance<ReadALU, 0>;
|
|
def : SchedAlias<ReadALUsr, SwiftReadAdvanceALUsr>;
|
|
|
|
// 4.2.5 Integer comparison
|
|
def : WriteRes<WriteCMP, [SwiftUnitP01]>;
|
|
def : WriteRes<WriteCMPsi, [SwiftUnitP01]>;
|
|
def : WriteRes<WriteCMPsr, [SwiftUnitP01]>;
|
|
}
|