llvm-project/llvm/lib/Target/ARM/ARMScheduleA9.td

1738 lines
92 KiB
TableGen

//=- ARMScheduleA9.td - ARM Cortex-A9 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 ARM Cortex A9 processors.
//
//===----------------------------------------------------------------------===//
//
// Ad-hoc scheduling information derived from pretty vague "Cortex-A9 Technical
// Reference Manual".
//
// Functional units
def A9_Issue0 : FuncUnit; // Issue 0
def A9_Issue1 : FuncUnit; // Issue 1
def A9_Branch : FuncUnit; // Branch
def A9_ALU0 : FuncUnit; // ALU / MUL pipeline 0
def A9_ALU1 : FuncUnit; // ALU pipeline 1
def A9_AGU : FuncUnit; // Address generation unit for ld / st
def A9_NPipe : FuncUnit; // NEON pipeline
def A9_MUX0 : FuncUnit; // AGU + NEON/FPU multiplexer
def A9_LSUnit : FuncUnit; // L/S Unit
def A9_DRegsVFP: FuncUnit; // FP register set, VFP side
def A9_DRegsN : FuncUnit; // FP register set, NEON side
// Bypasses
def A9_LdBypass : Bypass;
def CortexA9Itineraries : ProcessorItineraries<
[A9_Issue0, A9_Issue1, A9_Branch, A9_ALU0, A9_ALU1, A9_AGU, A9_NPipe, A9_MUX0,
A9_LSUnit, A9_DRegsVFP, A9_DRegsN],
[A9_LdBypass], [
// Two fully-pipelined integer ALU pipelines
//
// Move instructions, unconditional
InstrItinData<IIC_iMOVi , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_ALU0, A9_ALU1]>], [1]>,
InstrItinData<IIC_iMOVr , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_ALU0, A9_ALU1]>], [1, 1]>,
InstrItinData<IIC_iMOVsi , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_ALU0, A9_ALU1]>], [1, 1]>,
InstrItinData<IIC_iMOVsr , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<2, [A9_ALU0, A9_ALU1]>], [2, 1, 1]>,
InstrItinData<IIC_iMOVix2 , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_ALU0, A9_ALU1]>,
InstrStage<1, [A9_ALU0, A9_ALU1]>], [2]>,
//
// MVN instructions
InstrItinData<IIC_iMVNi , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_ALU0, A9_ALU1]>],
[1]>,
InstrItinData<IIC_iMVNr , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_ALU0, A9_ALU1]>],
[1, 1], [NoBypass, A9_LdBypass]>,
InstrItinData<IIC_iMVNsi , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<2, [A9_ALU0, A9_ALU1]>],
[2, 1]>,
InstrItinData<IIC_iMVNsr , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<3, [A9_ALU0, A9_ALU1]>],
[3, 1, 1]>,
//
// No operand cycles
InstrItinData<IIC_iALUx , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_ALU0, A9_ALU1]>]>,
//
// Binary Instructions that produce a result
InstrItinData<IIC_iALUi , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_ALU0, A9_ALU1]>],
[1, 1], [NoBypass, A9_LdBypass]>,
InstrItinData<IIC_iALUr , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_ALU0, A9_ALU1]>],
[1, 1, 1], [NoBypass, A9_LdBypass, A9_LdBypass]>,
InstrItinData<IIC_iALUsi, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<2, [A9_ALU0, A9_ALU1]>],
[2, 1, 1], [NoBypass, A9_LdBypass, NoBypass]>,
InstrItinData<IIC_iALUsir,[InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<2, [A9_ALU0, A9_ALU1]>],
[2, 1, 1], [NoBypass, NoBypass, A9_LdBypass]>,
InstrItinData<IIC_iALUsr, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<3, [A9_ALU0, A9_ALU1]>],
[3, 1, 1, 1],
[NoBypass, A9_LdBypass, NoBypass, NoBypass]>,
//
// Bitwise Instructions that produce a result
InstrItinData<IIC_iBITi , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_ALU0, A9_ALU1]>], [1, 1]>,
InstrItinData<IIC_iBITr , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_ALU0, A9_ALU1]>], [1, 1, 1]>,
InstrItinData<IIC_iBITsi, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<2, [A9_ALU0, A9_ALU1]>], [2, 1, 1]>,
InstrItinData<IIC_iBITsr, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<3, [A9_ALU0, A9_ALU1]>], [3, 1, 1, 1]>,
//
// Unary Instructions that produce a result
// CLZ, RBIT, etc.
InstrItinData<IIC_iUNAr , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_ALU0, A9_ALU1]>], [1, 1]>,
// BFC, BFI, UBFX, SBFX
InstrItinData<IIC_iUNAsi, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<2, [A9_ALU0, A9_ALU1]>], [2, 1]>,
//
// Zero and sign extension instructions
InstrItinData<IIC_iEXTr , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_ALU0, A9_ALU1]>], [2, 1]>,
InstrItinData<IIC_iEXTAr, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<2, [A9_ALU0, A9_ALU1]>], [3, 1, 1]>,
InstrItinData<IIC_iEXTAsr,[InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<3, [A9_ALU0, A9_ALU1]>], [3, 1, 1, 1]>,
//
// Compare instructions
InstrItinData<IIC_iCMPi , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_ALU0, A9_ALU1]>],
[1], [A9_LdBypass]>,
InstrItinData<IIC_iCMPr , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_ALU0, A9_ALU1]>],
[1, 1], [A9_LdBypass, A9_LdBypass]>,
InstrItinData<IIC_iCMPsi , [InstrStage<2, [A9_ALU0, A9_ALU1]>],
[1, 1], [A9_LdBypass, NoBypass]>,
InstrItinData<IIC_iCMPsr , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<3, [A9_ALU0, A9_ALU1]>],
[1, 1, 1], [A9_LdBypass, NoBypass, NoBypass]>,
//
// Test instructions
InstrItinData<IIC_iTSTi , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_ALU0, A9_ALU1]>], [1]>,
InstrItinData<IIC_iTSTr , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_ALU0, A9_ALU1]>], [1, 1]>,
InstrItinData<IIC_iTSTsi , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<2, [A9_ALU0, A9_ALU1]>], [1, 1]>,
InstrItinData<IIC_iTSTsr , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<3, [A9_ALU0, A9_ALU1]>], [1, 1, 1]>,
//
// Move instructions, conditional
// FIXME: Correctly model the extra input dep on the destination.
InstrItinData<IIC_iCMOVi , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_ALU0, A9_ALU1]>], [1]>,
InstrItinData<IIC_iCMOVr , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_ALU0, A9_ALU1]>], [1, 1]>,
InstrItinData<IIC_iCMOVsi , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_ALU0, A9_ALU1]>], [1, 1]>,
InstrItinData<IIC_iCMOVsr , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<2, [A9_ALU0, A9_ALU1]>], [2, 1, 1]>,
// Integer multiply pipeline
//
InstrItinData<IIC_iMUL16 , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<2, [A9_ALU0]>], [3, 1, 1]>,
InstrItinData<IIC_iMAC16 , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<2, [A9_ALU0]>],
[3, 1, 1, 1]>,
InstrItinData<IIC_iMUL32 , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<2, [A9_ALU0]>], [4, 1, 1]>,
InstrItinData<IIC_iMAC32 , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<2, [A9_ALU0]>],
[4, 1, 1, 1]>,
InstrItinData<IIC_iMUL64 , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<3, [A9_ALU0]>], [4, 5, 1, 1]>,
InstrItinData<IIC_iMAC64 , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<3, [A9_ALU0]>],
[4, 5, 1, 1]>,
// Integer load pipeline
// FIXME: The timings are some rough approximations
//
// Immediate offset
InstrItinData<IIC_iLoad_i , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_AGU], 0>,
InstrStage<1, [A9_LSUnit]>],
[3, 1], [A9_LdBypass]>,
InstrItinData<IIC_iLoad_bh_i, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<2, [A9_AGU], 0>,
InstrStage<1, [A9_LSUnit]>],
[4, 1], [A9_LdBypass]>,
// FIXME: If address is 64-bit aligned, AGU cycles is 1.
InstrItinData<IIC_iLoad_d_i , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<2, [A9_AGU], 0>,
InstrStage<1, [A9_LSUnit]>],
[3, 3, 1], [A9_LdBypass]>,
//
// Register offset
InstrItinData<IIC_iLoad_r , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_AGU], 0>,
InstrStage<1, [A9_LSUnit]>],
[3, 1, 1], [A9_LdBypass]>,
InstrItinData<IIC_iLoad_bh_r, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<2, [A9_AGU], 0>,
InstrStage<1, [A9_LSUnit]>],
[4, 1, 1], [A9_LdBypass]>,
InstrItinData<IIC_iLoad_d_r , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<2, [A9_AGU], 0>,
InstrStage<1, [A9_LSUnit]>],
[3, 3, 1, 1], [A9_LdBypass]>,
//
// Scaled register offset
InstrItinData<IIC_iLoad_si , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_AGU], 0>,
InstrStage<1, [A9_LSUnit], 0>],
[4, 1, 1], [A9_LdBypass]>,
InstrItinData<IIC_iLoad_bh_si,[InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<2, [A9_AGU], 0>,
InstrStage<1, [A9_LSUnit]>],
[5, 1, 1], [A9_LdBypass]>,
//
// Immediate offset with update
InstrItinData<IIC_iLoad_iu , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_AGU], 0>,
InstrStage<1, [A9_LSUnit]>],
[3, 2, 1], [A9_LdBypass]>,
InstrItinData<IIC_iLoad_bh_iu,[InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<2, [A9_AGU], 0>,
InstrStage<1, [A9_LSUnit]>],
[4, 3, 1], [A9_LdBypass]>,
//
// Register offset with update
InstrItinData<IIC_iLoad_ru , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_AGU], 0>,
InstrStage<1, [A9_LSUnit]>],
[3, 2, 1, 1], [A9_LdBypass]>,
InstrItinData<IIC_iLoad_bh_ru,[InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<2, [A9_AGU], 0>,
InstrStage<1, [A9_LSUnit]>],
[4, 3, 1, 1], [A9_LdBypass]>,
InstrItinData<IIC_iLoad_d_ru, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<2, [A9_AGU], 0>,
InstrStage<1, [A9_LSUnit]>],
[3, 3, 1, 1], [A9_LdBypass]>,
//
// Scaled register offset with update
InstrItinData<IIC_iLoad_siu , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_AGU], 0>,
InstrStage<1, [A9_LSUnit]>],
[4, 3, 1, 1], [A9_LdBypass]>,
InstrItinData<IIC_iLoad_bh_siu,[InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<2, [A9_AGU], 0>,
InstrStage<1, [A9_LSUnit]>],
[5, 4, 1, 1], [A9_LdBypass]>,
//
// Load multiple, def is the 5th operand.
// FIXME: This assumes 3 to 4 registers.
InstrItinData<IIC_iLoad_m , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<2, [A9_AGU], 1>,
InstrStage<2, [A9_LSUnit]>],
[1, 1, 1, 1, 3],
[NoBypass, NoBypass, NoBypass, NoBypass, A9_LdBypass]>,
//
// Load multiple + update, defs are the 1st and 5th operands.
InstrItinData<IIC_iLoad_mu , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<2, [A9_AGU], 1>,
InstrStage<2, [A9_LSUnit]>],
[2, 1, 1, 1, 3],
[NoBypass, NoBypass, NoBypass, NoBypass, A9_LdBypass]>,
//
// Load multiple plus branch
InstrItinData<IIC_iLoad_mBr, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_AGU], 1>,
InstrStage<2, [A9_LSUnit]>,
InstrStage<1, [A9_Branch]>],
[1, 2, 1, 1, 3],
[NoBypass, NoBypass, NoBypass, NoBypass, A9_LdBypass]>,
//
// Pop, def is the 3rd operand.
InstrItinData<IIC_iPop , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<2, [A9_AGU], 1>,
InstrStage<2, [A9_LSUnit]>],
[1, 1, 3],
[NoBypass, NoBypass, A9_LdBypass]>,
//
// Pop + branch, def is the 3rd operand.
InstrItinData<IIC_iPop_Br, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<2, [A9_AGU], 1>,
InstrStage<2, [A9_LSUnit]>,
InstrStage<1, [A9_Branch]>],
[1, 1, 3],
[NoBypass, NoBypass, A9_LdBypass]>,
//
// iLoadi + iALUr for t2LDRpci_pic.
InstrItinData<IIC_iLoadiALU, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_AGU], 0>,
InstrStage<1, [A9_LSUnit]>,
InstrStage<1, [A9_ALU0, A9_ALU1]>],
[2, 1]>,
// Integer store pipeline
///
// Immediate offset
InstrItinData<IIC_iStore_i , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_AGU], 0>,
InstrStage<1, [A9_LSUnit]>], [1, 1]>,
InstrItinData<IIC_iStore_bh_i,[InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<2, [A9_AGU], 1>,
InstrStage<1, [A9_LSUnit]>], [1, 1]>,
// FIXME: If address is 64-bit aligned, AGU cycles is 1.
InstrItinData<IIC_iStore_d_i, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<2, [A9_AGU], 1>,
InstrStage<1, [A9_LSUnit]>], [1, 1]>,
//
// Register offset
InstrItinData<IIC_iStore_r , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_AGU], 0>,
InstrStage<1, [A9_LSUnit]>], [1, 1, 1]>,
InstrItinData<IIC_iStore_bh_r,[InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<2, [A9_AGU], 1>,
InstrStage<1, [A9_LSUnit]>], [1, 1, 1]>,
InstrItinData<IIC_iStore_d_r, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<2, [A9_AGU], 1>,
InstrStage<1, [A9_LSUnit]>], [1, 1, 1]>,
//
// Scaled register offset
InstrItinData<IIC_iStore_si , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_AGU], 0>,
InstrStage<1, [A9_LSUnit]>], [1, 1, 1]>,
InstrItinData<IIC_iStore_bh_si,[InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<2, [A9_AGU], 1>,
InstrStage<1, [A9_LSUnit]>], [1, 1, 1]>,
//
// Immediate offset with update
InstrItinData<IIC_iStore_iu , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_AGU], 0>,
InstrStage<1, [A9_LSUnit]>], [2, 1, 1]>,
InstrItinData<IIC_iStore_bh_iu,[InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<2, [A9_AGU], 1>,
InstrStage<1, [A9_LSUnit]>], [3, 1, 1]>,
//
// Register offset with update
InstrItinData<IIC_iStore_ru , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_AGU], 0>,
InstrStage<1, [A9_LSUnit]>],
[2, 1, 1, 1]>,
InstrItinData<IIC_iStore_bh_ru,[InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<2, [A9_AGU], 1>,
InstrStage<1, [A9_LSUnit]>],
[3, 1, 1, 1]>,
InstrItinData<IIC_iStore_d_ru, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<2, [A9_AGU], 1>,
InstrStage<1, [A9_LSUnit]>],
[3, 1, 1, 1]>,
//
// Scaled register offset with update
InstrItinData<IIC_iStore_siu, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_AGU], 0>,
InstrStage<1, [A9_LSUnit]>],
[2, 1, 1, 1]>,
InstrItinData<IIC_iStore_bh_siu, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<2, [A9_AGU], 1>,
InstrStage<1, [A9_LSUnit]>],
[3, 1, 1, 1]>,
//
// Store multiple
InstrItinData<IIC_iStore_m , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_AGU], 0>,
InstrStage<2, [A9_LSUnit]>]>,
//
// Store multiple + update
InstrItinData<IIC_iStore_mu, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_AGU], 0>,
InstrStage<2, [A9_LSUnit]>], [2]>,
//
// Preload
InstrItinData<IIC_Preload, [InstrStage<1, [A9_Issue0, A9_Issue1]>], [1, 1]>,
// Branch
//
// no delay slots, so the latency of a branch is unimportant
InstrItinData<IIC_Br , [InstrStage<1, [A9_Issue0], 0>,
InstrStage<1, [A9_Issue1], 0>,
InstrStage<1, [A9_Branch]>]>,
// VFP and NEON shares the same register file. This means that every VFP
// instruction should wait for full completion of the consecutive NEON
// instruction and vice-versa. We model this behavior with two artificial FUs:
// DRegsVFP and DRegsVFP.
//
// Every VFP instruction:
// - Acquires DRegsVFP resource for 1 cycle
// - Reserves DRegsN resource for the whole duration (including time to
// register file writeback!).
// Every NEON instruction does the same but with FUs swapped.
//
// Since the reserved FU cannot be acquired, this models precisely
// "cross-domain" stalls.
// VFP
// Issue through integer pipeline, and execute in NEON unit.
// FP Special Register to Integer Register File Move
InstrItinData<IIC_fpSTAT , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<2, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[1]>,
//
// Single-precision FP Unary
InstrItinData<IIC_fpUNA32 , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
// Extra latency cycles since wbck is 2 cycles
InstrStage<3, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[1, 1]>,
//
// Double-precision FP Unary
InstrItinData<IIC_fpUNA64 , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
// Extra latency cycles since wbck is 2 cycles
InstrStage<3, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[1, 1]>,
//
// Single-precision FP Compare
InstrItinData<IIC_fpCMP32 , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
// Extra latency cycles since wbck is 4 cycles
InstrStage<5, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[1, 1]>,
//
// Double-precision FP Compare
InstrItinData<IIC_fpCMP64 , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
// Extra latency cycles since wbck is 4 cycles
InstrStage<5, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[1, 1]>,
//
// Single to Double FP Convert
InstrItinData<IIC_fpCVTSD , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<5, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[4, 1]>,
//
// Double to Single FP Convert
InstrItinData<IIC_fpCVTDS , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<5, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[4, 1]>,
//
// Single to Half FP Convert
InstrItinData<IIC_fpCVTSH , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<5, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[4, 1]>,
//
// Half to Single FP Convert
InstrItinData<IIC_fpCVTHS , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<3, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[2, 1]>,
//
// Single-Precision FP to Integer Convert
InstrItinData<IIC_fpCVTSI , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<5, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[4, 1]>,
//
// Double-Precision FP to Integer Convert
InstrItinData<IIC_fpCVTDI , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<5, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[4, 1]>,
//
// Integer to Single-Precision FP Convert
InstrItinData<IIC_fpCVTIS , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<5, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[4, 1]>,
//
// Integer to Double-Precision FP Convert
InstrItinData<IIC_fpCVTID , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<5, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[4, 1]>,
//
// Single-precision FP ALU
InstrItinData<IIC_fpALU32 , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<5, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[4, 1, 1]>,
//
// Double-precision FP ALU
InstrItinData<IIC_fpALU64 , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<5, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[4, 1, 1]>,
//
// Single-precision FP Multiply
InstrItinData<IIC_fpMUL32 , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<6, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[5, 1, 1]>,
//
// Double-precision FP Multiply
InstrItinData<IIC_fpMUL64 , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<7, [A9_DRegsN], 0, Reserved>,
InstrStage<2, [A9_NPipe]>],
[6, 1, 1]>,
//
// Single-precision FP MAC
InstrItinData<IIC_fpMAC32 , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<9, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[8, 1, 1, 1]>,
//
// Double-precision FP MAC
InstrItinData<IIC_fpMAC64 , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<10, [A9_DRegsN], 0, Reserved>,
InstrStage<2, [A9_NPipe]>],
[9, 1, 1, 1]>,
//
// Single-precision FP DIV
InstrItinData<IIC_fpDIV32 , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<16, [A9_DRegsN], 0, Reserved>,
InstrStage<10, [A9_NPipe]>],
[15, 1, 1]>,
//
// Double-precision FP DIV
InstrItinData<IIC_fpDIV64 , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<26, [A9_DRegsN], 0, Reserved>,
InstrStage<20, [A9_NPipe]>],
[25, 1, 1]>,
//
// Single-precision FP SQRT
InstrItinData<IIC_fpSQRT32, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<18, [A9_DRegsN], 0, Reserved>,
InstrStage<13, [A9_NPipe]>],
[17, 1]>,
//
// Double-precision FP SQRT
InstrItinData<IIC_fpSQRT64, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<33, [A9_DRegsN], 0, Reserved>,
InstrStage<28, [A9_NPipe]>],
[32, 1]>,
//
// Integer to Single-precision Move
InstrItinData<IIC_fpMOVIS, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
// Extra 1 latency cycle since wbck is 2 cycles
InstrStage<3, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[1, 1]>,
//
// Integer to Double-precision Move
InstrItinData<IIC_fpMOVID, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
// Extra 1 latency cycle since wbck is 2 cycles
InstrStage<3, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[1, 1, 1]>,
//
// Single-precision to Integer Move
InstrItinData<IIC_fpMOVSI, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<2, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[2, 1]>,
//
// Double-precision to Integer Move
InstrItinData<IIC_fpMOVDI, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<2, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[2, 1, 1]>,
//
// Single-precision FP Load
InstrItinData<IIC_fpLoad32, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<2, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe], 0>,
InstrStage<1, [A9_LSUnit]>],
[1, 1]>,
//
// Double-precision FP Load
// FIXME: Result latency is 1 if address is 64-bit aligned.
InstrItinData<IIC_fpLoad64, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<2, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe], 0>,
InstrStage<1, [A9_LSUnit]>],
[2, 1]>,
//
// FP Load Multiple
InstrItinData<IIC_fpLoad_m, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<2, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe], 0>,
InstrStage<1, [A9_LSUnit]>], [1, 1, 1, 1]>,
//
// FP Load Multiple + update
InstrItinData<IIC_fpLoad_mu,[InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<2, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe], 0>,
InstrStage<1, [A9_LSUnit]>], [2, 1, 1, 1]>,
//
// Single-precision FP Store
InstrItinData<IIC_fpStore32,[InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<2, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe], 0>,
InstrStage<1, [A9_LSUnit]>],
[1, 1]>,
//
// Double-precision FP Store
InstrItinData<IIC_fpStore64,[InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<2, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe], 0>,
InstrStage<1, [A9_LSUnit]>],
[1, 1]>,
//
// FP Store Multiple
InstrItinData<IIC_fpStore_m,[InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<2, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe], 0>,
InstrStage<1, [A9_LSUnit]>], [1, 1, 1, 1]>,
//
// FP Store Multiple + update
InstrItinData<IIC_fpStore_mu,[InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<2, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_NPipe], 0>,
InstrStage<1, [A9_LSUnit]>], [2, 1, 1, 1]>,
// NEON
// VLD1
// FIXME: Conservatively assume insufficent alignment.
InstrItinData<IIC_VLD1, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe], 0>,
InstrStage<2, [A9_LSUnit]>],
[2, 1]>,
// VLD1x2
InstrItinData<IIC_VLD1x2, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe], 0>,
InstrStage<2, [A9_LSUnit]>],
[2, 2, 1]>,
// VLD1x3
InstrItinData<IIC_VLD1x3, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe], 0>,
InstrStage<3, [A9_LSUnit]>],
[2, 2, 3, 1]>,
// VLD1x4
InstrItinData<IIC_VLD1x4, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe], 0>,
InstrStage<3, [A9_LSUnit]>],
[2, 2, 3, 3, 1]>,
// VLD1u
InstrItinData<IIC_VLD1u, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe], 0>,
InstrStage<2, [A9_LSUnit]>],
[2, 2, 1]>,
// VLD1x2u
InstrItinData<IIC_VLD1x2u, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe], 0>,
InstrStage<2, [A9_LSUnit]>],
[2, 2, 2, 1]>,
// VLD1x3u
InstrItinData<IIC_VLD1x3u, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe], 0>,
InstrStage<3, [A9_LSUnit]>],
[2, 2, 3, 2, 1]>,
// VLD1x4u
InstrItinData<IIC_VLD1x4u, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe], 0>,
InstrStage<3, [A9_LSUnit]>],
[2, 2, 3, 3, 2, 1]>,
//
// VLD1ln
InstrItinData<IIC_VLD1ln, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe], 1>,
InstrStage<3, [A9_LSUnit]>],
[4, 1, 1, 1]>,
//
// VLD1lnu
InstrItinData<IIC_VLD1lnu, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe], 1>,
InstrStage<3, [A9_LSUnit]>],
[4, 2, 1, 1, 1, 1]>,
//
// VLD2
InstrItinData<IIC_VLD2, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe], 0>,
InstrStage<2, [A9_LSUnit]>],
[3, 3, 1]>,
//
// VLD2x2
InstrItinData<IIC_VLD2x2, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe], 0>,
InstrStage<3, [A9_LSUnit]>],
[3, 4, 3, 4, 1]>,
//
// VLD2ln
InstrItinData<IIC_VLD2ln, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe], 0>,
InstrStage<3, [A9_LSUnit]>],
[4, 4, 1, 1, 1, 1]>,
//
// VLD2u
InstrItinData<IIC_VLD2u, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe], 0>,
InstrStage<2, [A9_LSUnit]>],
[3, 3, 2, 1, 1, 1]>,
//
// VLD2x2u
InstrItinData<IIC_VLD2x2u, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe], 0>,
InstrStage<3, [A9_LSUnit]>],
[3, 4, 3, 4, 2, 1]>,
//
// VLD2lnu
InstrItinData<IIC_VLD2lnu, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe], 0>,
InstrStage<3, [A9_LSUnit]>],
[4, 4, 2, 1, 1, 1, 1, 1]>,
//
// VLD3
InstrItinData<IIC_VLD3, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<10,[A9_DRegsVFP], 0, Reserved>,
InstrStage<4, [A9_NPipe], 0>,
InstrStage<4, [A9_LSUnit]>],
[4, 4, 5, 1]>,
//
// VLD3ln
InstrItinData<IIC_VLD3ln, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<11,[A9_DRegsVFP], 0, Reserved>,
InstrStage<5, [A9_NPipe], 0>,
InstrStage<5, [A9_LSUnit]>],
[5, 5, 6, 1, 1, 1, 1, 2]>,
//
// VLD3u
InstrItinData<IIC_VLD3u, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<10,[A9_DRegsVFP], 0, Reserved>,
InstrStage<4, [A9_NPipe], 0>,
InstrStage<4, [A9_LSUnit]>],
[4, 4, 5, 2, 1]>,
//
// VLD3lnu
InstrItinData<IIC_VLD3lnu, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<11,[A9_DRegsVFP], 0, Reserved>,
InstrStage<5, [A9_NPipe], 0>,
InstrStage<5, [A9_LSUnit]>],
[5, 5, 6, 2, 1, 1, 1, 1, 1, 2]>,
//
// VLD4
InstrItinData<IIC_VLD4, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<10,[A9_DRegsVFP], 0, Reserved>,
InstrStage<4, [A9_NPipe], 0>,
InstrStage<4, [A9_LSUnit]>],
[4, 4, 5, 5, 1]>,
//
// VLD4ln
InstrItinData<IIC_VLD4ln, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<11,[A9_DRegsVFP], 0, Reserved>,
InstrStage<5, [A9_NPipe], 0>,
InstrStage<5, [A9_LSUnit]>],
[5, 5, 6, 6, 1, 1, 1, 1, 2, 2]>,
//
// VLD4u
InstrItinData<IIC_VLD4u, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<10,[A9_DRegsVFP], 0, Reserved>,
InstrStage<4, [A9_NPipe], 0>,
InstrStage<4, [A9_LSUnit]>],
[4, 4, 5, 5, 2, 1]>,
//
// VLD4lnu
InstrItinData<IIC_VLD4lnu, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<11,[A9_DRegsVFP], 0, Reserved>,
InstrStage<5, [A9_NPipe], 0>,
InstrStage<5, [A9_LSUnit]>],
[5, 5, 6, 6, 2, 1, 1, 1, 1, 1, 2, 2]>,
//
// VST1
InstrItinData<IIC_VST1, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe], 0>,
InstrStage<2, [A9_LSUnit]>],
[1, 1, 1]>,
//
// VST1x2
InstrItinData<IIC_VST1x2, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe], 0>,
InstrStage<2, [A9_LSUnit]>],
[1, 1, 1, 1]>,
//
// VST1x3
InstrItinData<IIC_VST1x3, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe], 0>,
InstrStage<3, [A9_LSUnit]>],
[1, 1, 1, 1, 2]>,
//
// VST1x4
InstrItinData<IIC_VST1x4, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe], 0>,
InstrStage<3, [A9_LSUnit]>],
[1, 1, 1, 1, 2, 2]>,
//
// VST1u
InstrItinData<IIC_VST1u, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe], 0>,
InstrStage<2, [A9_LSUnit]>],
[2, 1, 1, 1, 1]>,
//
// VST1x2u
InstrItinData<IIC_VST1x2u, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe], 0>,
InstrStage<2, [A9_LSUnit]>],
[2, 1, 1, 1, 1, 1]>,
//
// VST1x3u
InstrItinData<IIC_VST1x3u, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe], 0>,
InstrStage<3, [A9_LSUnit]>],
[2, 1, 1, 1, 1, 1, 2]>,
//
// VST1x4u
InstrItinData<IIC_VST1x4u, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe], 0>,
InstrStage<3, [A9_LSUnit]>],
[2, 1, 1, 1, 1, 1, 2, 2]>,
//
// VST1ln
InstrItinData<IIC_VST1ln, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe], 1>,
InstrStage<2, [A9_LSUnit]>],
[1, 1, 1]>,
//
// VST1lnu
InstrItinData<IIC_VST1lnu, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe], 1>,
InstrStage<3, [A9_LSUnit]>],
[2, 1, 1, 1, 1]>,
//
// VST2
InstrItinData<IIC_VST2, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe], 0>,
InstrStage<2, [A9_LSUnit]>],
[1, 1, 1, 1]>,
//
// VST2x2
InstrItinData<IIC_VST2x2, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe], 0>,
InstrStage<3, [A9_LSUnit]>],
[1, 1, 1, 1, 2, 2]>,
//
// VST2u
InstrItinData<IIC_VST2u, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe], 0>,
InstrStage<2, [A9_LSUnit]>],
[2, 1, 1, 1, 1, 1]>,
//
// VST2x2u
InstrItinData<IIC_VST2x2u, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe], 0>,
InstrStage<3, [A9_LSUnit]>],
[2, 1, 1, 1, 1, 1, 2, 2]>,
//
// VST2ln
InstrItinData<IIC_VST2ln, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe], 0>,
InstrStage<2, [A9_LSUnit]>],
[1, 1, 1, 1]>,
//
// VST2lnu
InstrItinData<IIC_VST2lnu, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe], 0>,
InstrStage<3, [A9_LSUnit]>],
[2, 1, 1, 1, 1, 1]>,
//
// VST3
InstrItinData<IIC_VST3, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe], 0>,
InstrStage<3, [A9_LSUnit]>],
[1, 1, 1, 1, 2]>,
//
// VST3u
InstrItinData<IIC_VST3u, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe], 0>,
InstrStage<3, [A9_LSUnit]>],
[2, 1, 1, 1, 1, 1, 2]>,
//
// VST3ln
InstrItinData<IIC_VST3ln, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe], 0>,
InstrStage<3, [A9_LSUnit]>],
[1, 1, 1, 1, 2]>,
//
// VST3lnu
InstrItinData<IIC_VST3lnu, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe], 0>,
InstrStage<3, [A9_LSUnit]>],
[2, 1, 1, 1, 1, 1, 2]>,
//
// VST4
InstrItinData<IIC_VST4, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe], 0>,
InstrStage<3, [A9_LSUnit]>],
[1, 1, 1, 1, 2, 2]>,
//
// VST4u
InstrItinData<IIC_VST4u, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe], 0>,
InstrStage<3, [A9_LSUnit]>],
[2, 1, 1, 1, 1, 1, 2, 2]>,
//
// VST4ln
InstrItinData<IIC_VST4ln, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe], 0>,
InstrStage<3, [A9_LSUnit]>],
[1, 1, 1, 1, 2, 2]>,
//
// VST4lnu
InstrItinData<IIC_VST4lnu, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe], 0>,
InstrStage<3, [A9_LSUnit]>],
[2, 1, 1, 1, 1, 1, 2, 2]>,
//
// Double-register Integer Unary
InstrItinData<IIC_VUNAiD, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[4, 2]>,
//
// Quad-register Integer Unary
InstrItinData<IIC_VUNAiQ, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[4, 2]>,
//
// Double-register Integer Q-Unary
InstrItinData<IIC_VQUNAiD, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[4, 1]>,
//
// Quad-register Integer CountQ-Unary
InstrItinData<IIC_VQUNAiQ, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[4, 1]>,
//
// Double-register Integer Binary
InstrItinData<IIC_VBINiD, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[3, 2, 2]>,
//
// Quad-register Integer Binary
InstrItinData<IIC_VBINiQ, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[3, 2, 2]>,
//
// Double-register Integer Subtract
InstrItinData<IIC_VSUBiD, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[3, 2, 1]>,
//
// Quad-register Integer Subtract
InstrItinData<IIC_VSUBiQ, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[3, 2, 1]>,
//
// Double-register Integer Shift
InstrItinData<IIC_VSHLiD, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[3, 1, 1]>,
//
// Quad-register Integer Shift
InstrItinData<IIC_VSHLiQ, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[3, 1, 1]>,
//
// Double-register Integer Shift (4 cycle)
InstrItinData<IIC_VSHLi4D, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[4, 1, 1]>,
//
// Quad-register Integer Shift (4 cycle)
InstrItinData<IIC_VSHLi4Q, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[4, 1, 1]>,
//
// Double-register Integer Binary (4 cycle)
InstrItinData<IIC_VBINi4D, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[4, 2, 2]>,
//
// Quad-register Integer Binary (4 cycle)
InstrItinData<IIC_VBINi4Q, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[4, 2, 2]>,
//
// Double-register Integer Subtract (4 cycle)
InstrItinData<IIC_VSUBi4D, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[4, 2, 1]>,
//
// Quad-register Integer Subtract (4 cycle)
InstrItinData<IIC_VSUBi4Q, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[4, 2, 1]>,
//
// Double-register Integer Count
InstrItinData<IIC_VCNTiD, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[3, 2, 2]>,
//
// Quad-register Integer Count
// Result written in N3, but that is relative to the last cycle of multicycle,
// so we use 4 for those cases
InstrItinData<IIC_VCNTiQ, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe]>],
[4, 2, 2]>,
//
// Double-register Absolute Difference and Accumulate
InstrItinData<IIC_VABAD, [InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<1, [A9_NPipe]>],
[6, 3, 2, 1]>,
//
// Quad-register Absolute Difference and Accumulate
InstrItinData<IIC_VABAQ, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe]>],
[6, 3, 2, 1]>,
//
// Double-register Integer Pair Add Long
InstrItinData<IIC_VPALiD, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[6, 3, 1]>,
//
// Quad-register Integer Pair Add Long
InstrItinData<IIC_VPALiQ, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe]>],
[6, 3, 1]>,
//
// Double-register Integer Multiply (.8, .16)
InstrItinData<IIC_VMULi16D, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[6, 2, 2]>,
//
// Quad-register Integer Multiply (.8, .16)
InstrItinData<IIC_VMULi16Q, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe]>],
[7, 2, 2]>,
//
// Double-register Integer Multiply (.32)
InstrItinData<IIC_VMULi32D, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe]>],
[7, 2, 1]>,
//
// Quad-register Integer Multiply (.32)
InstrItinData<IIC_VMULi32Q, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 9 cycles
InstrStage<10, [A9_DRegsVFP], 0, Reserved>,
InstrStage<4, [A9_NPipe]>],
[9, 2, 1]>,
//
// Double-register Integer Multiply-Accumulate (.8, .16)
InstrItinData<IIC_VMACi16D, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[6, 3, 2, 2]>,
//
// Double-register Integer Multiply-Accumulate (.32)
InstrItinData<IIC_VMACi32D, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe]>],
[7, 3, 2, 1]>,
//
// Quad-register Integer Multiply-Accumulate (.8, .16)
InstrItinData<IIC_VMACi16Q, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe]>],
[7, 3, 2, 2]>,
//
// Quad-register Integer Multiply-Accumulate (.32)
InstrItinData<IIC_VMACi32Q, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 9 cycles
InstrStage<10, [A9_DRegsVFP], 0, Reserved>,
InstrStage<4, [A9_NPipe]>],
[9, 3, 2, 1]>,
//
// Move
InstrItinData<IIC_VMOV, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<1, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[1,1]>,
//
// Move Immediate
InstrItinData<IIC_VMOVImm, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[3]>,
//
// Double-register Permute Move
InstrItinData<IIC_VMOVD, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[2, 1]>,
//
// Quad-register Permute Move
InstrItinData<IIC_VMOVQ, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[2, 1]>,
//
// Integer to Single-precision Move
InstrItinData<IIC_VMOVIS , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[1, 1]>,
//
// Integer to Double-precision Move
InstrItinData<IIC_VMOVID , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[1, 1, 1]>,
//
// Single-precision to Integer Move
InstrItinData<IIC_VMOVSI , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[2, 1]>,
//
// Double-precision to Integer Move
InstrItinData<IIC_VMOVDI , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[2, 2, 1]>,
//
// Integer to Lane Move
InstrItinData<IIC_VMOVISL , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
InstrStage<4, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe]>],
[3, 1, 1]>,
//
// Vector narrow move
InstrItinData<IIC_VMOVN, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[3, 1]>,
//
// Double-register FP Unary
InstrItinData<IIC_VUNAD, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[5, 2]>,
//
// Quad-register FP Unary
// Result written in N5, but that is relative to the last cycle of multicycle,
// so we use 6 for those cases
InstrItinData<IIC_VUNAQ, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe]>],
[6, 2]>,
//
// Double-register FP Binary
// FIXME: We're using this itin for many instructions and [2, 2] here is too
// optimistic.
InstrItinData<IIC_VBIND, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[5, 2, 2]>,
//
// VPADD, etc.
InstrItinData<IIC_VPBIND, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[5, 1, 1]>,
//
// Double-register FP VMUL
InstrItinData<IIC_VFMULD, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[5, 2, 1]>,
//
// Quad-register FP Binary
// Result written in N5, but that is relative to the last cycle of multicycle,
// so we use 6 for those cases
// FIXME: We're using this itin for many instructions and [2, 2] here is too
// optimistic.
InstrItinData<IIC_VBINQ, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe]>],
[6, 2, 2]>,
//
// Quad-register FP VMUL
InstrItinData<IIC_VFMULQ, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[6, 2, 1]>,
//
// Double-register FP Multiple-Accumulate
InstrItinData<IIC_VMACD, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe]>],
[6, 3, 2, 1]>,
//
// Quad-register FP Multiple-Accumulate
// Result written in N9, but that is relative to the last cycle of multicycle,
// so we use 10 for those cases
InstrItinData<IIC_VMACQ, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 9 cycles
InstrStage<10, [A9_DRegsVFP], 0, Reserved>,
InstrStage<4, [A9_NPipe]>],
[8, 4, 2, 1]>,
//
// Double-register Reciprical Step
InstrItinData<IIC_VRECSD, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 10 cycles
InstrStage<11, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[9, 2, 2]>,
//
// Quad-register Reciprical Step
InstrItinData<IIC_VRECSQ, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 11 cycles
InstrStage<12, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe]>],
[10, 2, 2]>,
//
// Double-register Permute
InstrItinData<IIC_VPERMD, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[2, 2, 1, 1]>,
//
// Quad-register Permute
// Result written in N2, but that is relative to the last cycle of multicycle,
// so we use 3 for those cases
InstrItinData<IIC_VPERMQ, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe]>],
[3, 3, 1, 1]>,
//
// Quad-register Permute (3 cycle issue)
// Result written in N2, but that is relative to the last cycle of multicycle,
// so we use 4 for those cases
InstrItinData<IIC_VPERMQ3, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 8 cycles
InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe]>],
[4, 4, 1, 1]>,
//
// Double-register VEXT
InstrItinData<IIC_VEXTD, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_NPipe]>],
[2, 1, 1]>,
//
// Quad-register VEXT
InstrItinData<IIC_VEXTQ, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe]>],
[3, 1, 2]>,
//
// VTB
InstrItinData<IIC_VTB1, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe]>],
[3, 2, 1]>,
InstrItinData<IIC_VTB2, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<2, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe]>],
[3, 2, 2, 1]>,
InstrItinData<IIC_VTB3, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<2, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 8 cycles
InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe]>],
[4, 2, 2, 3, 1]>,
InstrItinData<IIC_VTB4, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 8 cycles
InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe]>],
[4, 2, 2, 3, 3, 1]>,
//
// VTBX
InstrItinData<IIC_VTBX1, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe]>],
[3, 1, 2, 1]>,
InstrItinData<IIC_VTBX2, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe]>],
[3, 1, 2, 2, 1]>,
InstrItinData<IIC_VTBX3, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 8 cycles
InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
InstrStage<3, [A9_NPipe]>],
[4, 1, 2, 2, 3, 1]>,
InstrItinData<IIC_VTBX4, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
InstrStage<1, [A9_MUX0], 0>,
InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 8 cycles
InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
InstrStage<2, [A9_NPipe]>],
[4, 1, 2, 2, 3, 3, 1]>
]>;