forked from OSchip/llvm-project
860 lines
44 KiB
TableGen
860 lines
44 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_Pipe0 : FuncUnit; // pipeline 0
|
|
def A9_Pipe1 : FuncUnit; // pipeline 1
|
|
def A9_LSPipe : FuncUnit; // LS pipe
|
|
def A9_NPipe : FuncUnit; // NEON ALU/MUL pipe
|
|
def A9_DRegsVFP: FuncUnit; // FP register set, VFP side
|
|
def A9_DRegsN : FuncUnit; // FP register set, NEON side
|
|
|
|
// Dual issue pipeline represented by A9_Pipe0 | A9_Pipe1
|
|
//
|
|
def CortexA9Itineraries : ProcessorItineraries<
|
|
[A9_NPipe, A9_DRegsN, A9_DRegsVFP, A9_LSPipe, A9_Pipe0, A9_Pipe1], [
|
|
// Two fully-pipelined integer ALU pipelines
|
|
// FIXME: There are no operand latencies for these instructions at all!
|
|
//
|
|
// Move instructions, unconditional
|
|
InstrItinData<IIC_iMOVi , [InstrStage<1, [A9_Pipe0, A9_Pipe1]>], [1]>,
|
|
InstrItinData<IIC_iMOVix2 , [InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
|
|
InstrStage<1, [A9_Pipe0, A9_Pipe1]>], [2]>,
|
|
InstrItinData<IIC_iMOVr , [InstrStage<1, [A9_Pipe0, A9_Pipe1]>], [1, 1]>,
|
|
InstrItinData<IIC_iMOVsi , [InstrStage<1, [A9_Pipe0, A9_Pipe1]>], [1, 1]>,
|
|
InstrItinData<IIC_iMOVsr , [InstrStage<2, [A9_Pipe0, A9_Pipe1]>], [2, 2, 1]>,
|
|
//
|
|
// No operand cycles
|
|
InstrItinData<IIC_iALUx , [InstrStage<1, [A9_Pipe0, A9_Pipe1]>]>,
|
|
//
|
|
// Binary Instructions that produce a result
|
|
InstrItinData<IIC_iALUi , [InstrStage<1, [A9_Pipe0, A9_Pipe1]>], [2, 2]>,
|
|
InstrItinData<IIC_iALUr , [InstrStage<1, [A9_Pipe0, A9_Pipe1]>], [2, 2, 2]>,
|
|
InstrItinData<IIC_iALUsi, [InstrStage<2, [A9_Pipe0, A9_Pipe1]>], [2, 2, 1]>,
|
|
InstrItinData<IIC_iALUsr,[InstrStage<3, [A9_Pipe0, A9_Pipe1]>], [2, 2, 1, 1]>,
|
|
//
|
|
// Unary Instructions that produce a result
|
|
InstrItinData<IIC_iUNAr , [InstrStage<1, [A9_Pipe0, A9_Pipe1]>], [2, 2]>,
|
|
InstrItinData<IIC_iUNAsi , [InstrStage<2, [A9_Pipe0, A9_Pipe1]>], [2, 1]>,
|
|
InstrItinData<IIC_iUNAsr , [InstrStage<3, [A9_Pipe0, A9_Pipe1]>], [2, 1, 1]>,
|
|
//
|
|
// Compare instructions
|
|
InstrItinData<IIC_iCMPi , [InstrStage<1, [A9_Pipe0, A9_Pipe1]>], [2]>,
|
|
InstrItinData<IIC_iCMPr , [InstrStage<1, [A9_Pipe0, A9_Pipe1]>], [2, 2]>,
|
|
InstrItinData<IIC_iCMPsi , [InstrStage<2, [A9_Pipe0, A9_Pipe1]>], [2, 1]>,
|
|
InstrItinData<IIC_iCMPsr , [InstrStage<3, [A9_Pipe0, A9_Pipe1]>], [2, 1, 1]>,
|
|
//
|
|
// Move instructions, conditional
|
|
InstrItinData<IIC_iCMOVi , [InstrStage<1, [A9_Pipe0, A9_Pipe1]>], [2]>,
|
|
InstrItinData<IIC_iCMOVr , [InstrStage<1, [A9_Pipe0, A9_Pipe1]>], [2, 1]>,
|
|
InstrItinData<IIC_iCMOVsi , [InstrStage<1, [A9_Pipe0, A9_Pipe1]>], [2, 1]>,
|
|
InstrItinData<IIC_iCMOVsr , [InstrStage<2, [A9_Pipe0, A9_Pipe1]>], [2, 1, 1]>,
|
|
|
|
// Integer multiply pipeline
|
|
//
|
|
InstrItinData<IIC_iMUL16 , [InstrStage<1, [A9_Pipe1], 0>,
|
|
InstrStage<2, [A9_Pipe0]>], [4, 1, 1]>,
|
|
InstrItinData<IIC_iMAC16 , [InstrStage<1, [A9_Pipe1], 0>,
|
|
InstrStage<2, [A9_Pipe0]>], [4, 1, 1, 2]>,
|
|
InstrItinData<IIC_iMUL32 , [InstrStage<1, [A9_Pipe1], 0>,
|
|
InstrStage<2, [A9_Pipe0]>], [4, 1, 1]>,
|
|
InstrItinData<IIC_iMAC32 , [InstrStage<1, [A9_Pipe1], 0>,
|
|
InstrStage<2, [A9_Pipe0]>], [4, 1, 1, 2]>,
|
|
InstrItinData<IIC_iMUL64 , [InstrStage<2, [A9_Pipe1], 0>,
|
|
InstrStage<3, [A9_Pipe0]>], [4, 5, 1, 1]>,
|
|
InstrItinData<IIC_iMAC64 , [InstrStage<2, [A9_Pipe1], 0>,
|
|
InstrStage<3, [A9_Pipe0]>], [4, 5, 1, 1]>,
|
|
// Integer load pipeline
|
|
// FIXME: The timings are some rough approximations
|
|
//
|
|
// Immediate offset
|
|
InstrItinData<IIC_iLoadi , [InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_LSPipe]>], [3, 1]>,
|
|
//
|
|
// Register offset
|
|
InstrItinData<IIC_iLoadr , [InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_LSPipe]>], [3, 1, 1]>,
|
|
//
|
|
// Scaled register offset
|
|
InstrItinData<IIC_iLoadsi , [InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<2, [A9_LSPipe]>], [4, 1, 1]>,
|
|
//
|
|
// Immediate offset with update
|
|
InstrItinData<IIC_iLoadiu , [InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<2, [A9_LSPipe]>], [3, 2, 1]>,
|
|
//
|
|
// Register offset with update
|
|
InstrItinData<IIC_iLoadru , [InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<2, [A9_LSPipe]>], [3, 2, 1, 1]>,
|
|
//
|
|
// Scaled register offset with update
|
|
InstrItinData<IIC_iLoadsiu , [InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<2, [A9_LSPipe]>], [4, 3, 1, 1]>,
|
|
//
|
|
// Load multiple
|
|
InstrItinData<IIC_iLoadm , [InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_LSPipe]>]>,
|
|
|
|
//
|
|
// Load multiple plus branch
|
|
InstrItinData<IIC_iLoadmBr , [InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_LSPipe]>,
|
|
InstrStage<1, [A9_Pipe0, A9_Pipe1]>]>,
|
|
|
|
//
|
|
// iLoadi + iALUr for t2LDRpci_pic.
|
|
InstrItinData<IIC_iLoadiALU, [InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_LSPipe]>,
|
|
InstrStage<1, [A9_Pipe0, A9_Pipe1]>], [4, 1]>,
|
|
|
|
// Integer store pipeline
|
|
///
|
|
// Immediate offset
|
|
InstrItinData<IIC_iStorei , [InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_LSPipe]>], [3, 1]>,
|
|
//
|
|
// Register offset
|
|
InstrItinData<IIC_iStorer , [InstrStage<1, [ A9_Pipe1]>,
|
|
InstrStage<1, [A9_LSPipe]>], [3, 1, 1]>,
|
|
//
|
|
// Scaled register offset
|
|
InstrItinData<IIC_iStoresi , [InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<2, [A9_LSPipe]>], [3, 1, 1]>,
|
|
//
|
|
// Immediate offset with update
|
|
InstrItinData<IIC_iStoreiu , [InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_LSPipe]>], [2, 3, 1]>,
|
|
//
|
|
// Register offset with update
|
|
InstrItinData<IIC_iStoreru , [InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_LSPipe]>], [2, 3, 1, 1]>,
|
|
//
|
|
// Scaled register offset with update
|
|
InstrItinData<IIC_iStoresiu, [InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<2, [A9_LSPipe]>], [3, 3, 1, 1]>,
|
|
//
|
|
// Store multiple
|
|
InstrItinData<IIC_iStorem , [InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_LSPipe]>]>,
|
|
// Branch
|
|
//
|
|
// no delay slots, so the latency of a branch is unimportant
|
|
InstrItinData<IIC_Br , [InstrStage<1, [A9_Pipe0, A9_Pipe1]>]>,
|
|
|
|
// 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_DRegsVFP], 0, Required>,
|
|
InstrStage<2, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>]>,
|
|
//
|
|
// Single-precision FP Unary
|
|
InstrItinData<IIC_fpUNA32 , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
// Extra latency cycles since wbck is 2 cycles
|
|
InstrStage<3, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [1, 1]>,
|
|
//
|
|
// Double-precision FP Unary
|
|
InstrItinData<IIC_fpUNA64 , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
// Extra latency cycles since wbck is 2 cycles
|
|
InstrStage<3, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [1, 1]>,
|
|
|
|
//
|
|
// Single-precision FP Compare
|
|
InstrItinData<IIC_fpCMP32 , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
// Extra latency cycles since wbck is 4 cycles
|
|
InstrStage<5, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [1, 1]>,
|
|
//
|
|
// Double-precision FP Compare
|
|
InstrItinData<IIC_fpCMP64 , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
// Extra latency cycles since wbck is 4 cycles
|
|
InstrStage<5, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [1, 1]>,
|
|
//
|
|
// Single to Double FP Convert
|
|
InstrItinData<IIC_fpCVTSD , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
InstrStage<5, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [4, 1]>,
|
|
//
|
|
// Double to Single FP Convert
|
|
InstrItinData<IIC_fpCVTDS , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
InstrStage<5, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [4, 1]>,
|
|
|
|
//
|
|
// Single to Half FP Convert
|
|
InstrItinData<IIC_fpCVTSH , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
InstrStage<5, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [4, 1]>,
|
|
//
|
|
// Half to Single FP Convert
|
|
InstrItinData<IIC_fpCVTHS , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
InstrStage<3, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [2, 1]>,
|
|
|
|
//
|
|
// Single-Precision FP to Integer Convert
|
|
InstrItinData<IIC_fpCVTSI , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
InstrStage<5, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [4, 1]>,
|
|
//
|
|
// Double-Precision FP to Integer Convert
|
|
InstrItinData<IIC_fpCVTDI , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
InstrStage<5, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [4, 1]>,
|
|
//
|
|
// Integer to Single-Precision FP Convert
|
|
InstrItinData<IIC_fpCVTIS , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
InstrStage<5, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [4, 1]>,
|
|
//
|
|
// Integer to Double-Precision FP Convert
|
|
InstrItinData<IIC_fpCVTID , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
InstrStage<5, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [4, 1]>,
|
|
//
|
|
// Single-precision FP ALU
|
|
InstrItinData<IIC_fpALU32 , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
InstrStage<5, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [4, 1, 1]>,
|
|
//
|
|
// Double-precision FP ALU
|
|
InstrItinData<IIC_fpALU64 , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
InstrStage<5, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [4, 1, 1]>,
|
|
//
|
|
// Single-precision FP Multiply
|
|
InstrItinData<IIC_fpMUL32 , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
InstrStage<6, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [5, 1, 1]>,
|
|
//
|
|
// Double-precision FP Multiply
|
|
InstrItinData<IIC_fpMUL64 , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
InstrStage<7, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<2, [A9_NPipe]>], [6, 1, 1]>,
|
|
//
|
|
// Single-precision FP MAC
|
|
InstrItinData<IIC_fpMAC32 , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
InstrStage<9, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [8, 0, 1, 1]>,
|
|
//
|
|
// Double-precision FP MAC
|
|
InstrItinData<IIC_fpMAC64 , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
InstrStage<10, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<2, [A9_NPipe]>], [9, 0, 1, 1]>,
|
|
//
|
|
// Single-precision FP DIV
|
|
InstrItinData<IIC_fpDIV32 , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
InstrStage<16, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<10, [A9_NPipe]>], [15, 1, 1]>,
|
|
//
|
|
// Double-precision FP DIV
|
|
InstrItinData<IIC_fpDIV64 , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
InstrStage<26, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<20, [A9_NPipe]>], [25, 1, 1]>,
|
|
//
|
|
// Single-precision FP SQRT
|
|
InstrItinData<IIC_fpSQRT32, [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
InstrStage<18, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<13, [A9_NPipe]>], [17, 1]>,
|
|
//
|
|
// Double-precision FP SQRT
|
|
InstrItinData<IIC_fpSQRT64, [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
InstrStage<33, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<28, [A9_NPipe]>], [32, 1]>,
|
|
|
|
//
|
|
// Integer to Single-precision Move
|
|
InstrItinData<IIC_fpMOVIS, [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
// Extra 1 latency cycle since wbck is 2 cycles
|
|
InstrStage<3, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [1, 1]>,
|
|
//
|
|
// Integer to Double-precision Move
|
|
InstrItinData<IIC_fpMOVID, [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
// Extra 1 latency cycle since wbck is 2 cycles
|
|
InstrStage<3, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [1, 1, 1]>,
|
|
//
|
|
// Single-precision to Integer Move
|
|
InstrItinData<IIC_fpMOVSI, [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
InstrStage<2, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [1, 1]>,
|
|
//
|
|
// Double-precision to Integer Move
|
|
InstrItinData<IIC_fpMOVDI, [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
InstrStage<2, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [1, 1, 1]>,
|
|
//
|
|
// Single-precision FP Load
|
|
InstrItinData<IIC_fpLoad32, [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
InstrStage<2, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1], 0>,
|
|
InstrStage<1, [A9_LSPipe]>,
|
|
InstrStage<1, [A9_NPipe]>]>,
|
|
//
|
|
// Double-precision FP Load
|
|
InstrItinData<IIC_fpLoad64, [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
InstrStage<2, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1], 0>,
|
|
InstrStage<1, [A9_LSPipe]>,
|
|
InstrStage<1, [A9_NPipe]>]>,
|
|
//
|
|
// FP Load Multiple
|
|
InstrItinData<IIC_fpLoadm, [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
InstrStage<2, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1], 0>,
|
|
InstrStage<1, [A9_LSPipe]>,
|
|
InstrStage<1, [A9_NPipe]>]>,
|
|
//
|
|
// Single-precision FP Store
|
|
InstrItinData<IIC_fpStore32,[InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
InstrStage<2, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1], 0>,
|
|
InstrStage<1, [A9_LSPipe]>,
|
|
InstrStage<1, [A9_NPipe]>]>,
|
|
//
|
|
// Double-precision FP Store
|
|
InstrItinData<IIC_fpStore64,[InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
InstrStage<2, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1], 0>,
|
|
InstrStage<1, [A9_LSPipe]>,
|
|
InstrStage<1, [A9_NPipe]>]>,
|
|
//
|
|
// FP Store Multiple
|
|
InstrItinData<IIC_fpStorem, [InstrStage<1, [A9_DRegsVFP], 0, Required>,
|
|
InstrStage<2, [A9_DRegsN], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1], 0>,
|
|
InstrStage<1, [A9_LSPipe]>,
|
|
InstrStage<1, [A9_NPipe]>]>,
|
|
// NEON
|
|
// Issue through integer pipeline, and execute in NEON unit.
|
|
// FIXME: Neon pipeline and LdSt unit are multiplexed.
|
|
// Add some syntactic sugar to model this!
|
|
// VLD1
|
|
// FIXME: We don't model this instruction properly
|
|
InstrItinData<IIC_VLD1, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1], 0>,
|
|
InstrStage<1, [A9_LSPipe]>,
|
|
InstrStage<1, [A9_NPipe]>]>,
|
|
//
|
|
// VLD2
|
|
// FIXME: We don't model this instruction properly
|
|
InstrItinData<IIC_VLD2, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1], 0>,
|
|
InstrStage<1, [A9_LSPipe]>,
|
|
InstrStage<1, [A9_NPipe]>], [2, 2, 1]>,
|
|
//
|
|
// VLD3
|
|
// FIXME: We don't model this instruction properly
|
|
InstrItinData<IIC_VLD3, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1], 0>,
|
|
InstrStage<1, [A9_LSPipe]>,
|
|
InstrStage<1, [A9_NPipe]>], [2, 2, 2, 1]>,
|
|
//
|
|
// VLD4
|
|
// FIXME: We don't model this instruction properly
|
|
InstrItinData<IIC_VLD4, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1], 0>,
|
|
InstrStage<1, [A9_LSPipe]>,
|
|
InstrStage<1, [A9_NPipe]>], [2, 2, 2, 2, 1]>,
|
|
//
|
|
// VST
|
|
// FIXME: We don't model this instruction properly
|
|
InstrItinData<IIC_VST, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1], 0>,
|
|
InstrStage<1, [A9_LSPipe]>,
|
|
InstrStage<1, [A9_NPipe]>]>,
|
|
//
|
|
// Double-register Integer Unary
|
|
InstrItinData<IIC_VUNAiD, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [4, 2]>,
|
|
//
|
|
// Quad-register Integer Unary
|
|
InstrItinData<IIC_VUNAiQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [4, 2]>,
|
|
//
|
|
// Double-register Integer Q-Unary
|
|
InstrItinData<IIC_VQUNAiD, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [4, 1]>,
|
|
//
|
|
// Quad-register Integer CountQ-Unary
|
|
InstrItinData<IIC_VQUNAiQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [4, 1]>,
|
|
//
|
|
// Double-register Integer Binary
|
|
InstrItinData<IIC_VBINiD, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [3, 2, 2]>,
|
|
//
|
|
// Quad-register Integer Binary
|
|
InstrItinData<IIC_VBINiQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [3, 2, 2]>,
|
|
//
|
|
// Double-register Integer Subtract
|
|
InstrItinData<IIC_VSUBiD, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [3, 2, 1]>,
|
|
//
|
|
// Quad-register Integer Subtract
|
|
InstrItinData<IIC_VSUBiQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [3, 2, 1]>,
|
|
//
|
|
// Double-register Integer Shift
|
|
InstrItinData<IIC_VSHLiD, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [3, 1, 1]>,
|
|
//
|
|
// Quad-register Integer Shift
|
|
InstrItinData<IIC_VSHLiQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [3, 1, 1]>,
|
|
//
|
|
// Double-register Integer Shift (4 cycle)
|
|
InstrItinData<IIC_VSHLi4D, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [4, 1, 1]>,
|
|
//
|
|
// Quad-register Integer Shift (4 cycle)
|
|
InstrItinData<IIC_VSHLi4Q, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [4, 1, 1]>,
|
|
//
|
|
// Double-register Integer Binary (4 cycle)
|
|
InstrItinData<IIC_VBINi4D, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [4, 2, 2]>,
|
|
//
|
|
// Quad-register Integer Binary (4 cycle)
|
|
InstrItinData<IIC_VBINi4Q, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [4, 2, 2]>,
|
|
//
|
|
// Double-register Integer Subtract (4 cycle)
|
|
InstrItinData<IIC_VSUBiD, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [4, 2, 1]>,
|
|
//
|
|
// Quad-register Integer Subtract (4 cycle)
|
|
InstrItinData<IIC_VSUBiQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [4, 2, 1]>,
|
|
|
|
//
|
|
// Double-register Integer Count
|
|
InstrItinData<IIC_VCNTiD, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
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_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 7 cycles
|
|
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<2, [A9_NPipe]>], [4, 2, 2]>,
|
|
//
|
|
// Double-register Absolute Difference and Accumulate
|
|
InstrItinData<IIC_VABAD, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [6, 3, 2, 1]>,
|
|
//
|
|
// Quad-register Absolute Difference and Accumulate
|
|
InstrItinData<IIC_VABAQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<2, [A9_NPipe]>], [6, 3, 2, 1]>,
|
|
//
|
|
// Double-register Integer Pair Add Long
|
|
InstrItinData<IIC_VPALiD, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [6, 3, 1]>,
|
|
//
|
|
// Quad-register Integer Pair Add Long
|
|
InstrItinData<IIC_VPALiQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<2, [A9_NPipe]>], [6, 3, 1]>,
|
|
|
|
//
|
|
// Double-register Integer Multiply (.8, .16)
|
|
InstrItinData<IIC_VMULi16D, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [6, 2, 2]>,
|
|
//
|
|
// Quad-register Integer Multiply (.8, .16)
|
|
InstrItinData<IIC_VMULi16Q, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 7 cycles
|
|
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<2, [A9_NPipe]>], [7, 2, 2]>,
|
|
|
|
//
|
|
// Double-register Integer Multiply (.32)
|
|
InstrItinData<IIC_VMULi32D, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 7 cycles
|
|
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<2, [A9_NPipe]>], [7, 2, 1]>,
|
|
//
|
|
// Quad-register Integer Multiply (.32)
|
|
InstrItinData<IIC_VMULi32Q, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 9 cycles
|
|
InstrStage<10, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<4, [A9_NPipe]>], [9, 2, 1]>,
|
|
//
|
|
// Double-register Integer Multiply-Accumulate (.8, .16)
|
|
InstrItinData<IIC_VMACi16D, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [6, 3, 2, 2]>,
|
|
//
|
|
// Double-register Integer Multiply-Accumulate (.32)
|
|
InstrItinData<IIC_VMACi32D, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 7 cycles
|
|
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<2, [A9_NPipe]>], [7, 3, 2, 1]>,
|
|
//
|
|
// Quad-register Integer Multiply-Accumulate (.8, .16)
|
|
InstrItinData<IIC_VMACi16Q, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 7 cycles
|
|
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<2, [A9_NPipe]>], [7, 3, 2, 2]>,
|
|
//
|
|
// Quad-register Integer Multiply-Accumulate (.32)
|
|
InstrItinData<IIC_VMACi32Q, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 9 cycles
|
|
InstrStage<10, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<4, [A9_NPipe]>], [9, 3, 2, 1]>,
|
|
//
|
|
// Move Immediate
|
|
InstrItinData<IIC_VMOVImm, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [3]>,
|
|
//
|
|
// Double-register Permute Move
|
|
InstrItinData<IIC_VMOVD, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// FIXME: all latencies are arbitrary, no information is available
|
|
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_LSPipe]>], [2, 1]>,
|
|
//
|
|
// Quad-register Permute Move
|
|
// Result written in N2, but that is relative to the last cycle of multicycle,
|
|
// so we use 3 for those cases
|
|
InstrItinData<IIC_VMOVQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// FIXME: all latencies are arbitrary, no information is available
|
|
InstrStage<4, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<2, [A9_NPipe]>], [3, 1]>,
|
|
//
|
|
// Integer to Single-precision Move
|
|
InstrItinData<IIC_VMOVIS , [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// FIXME: all latencies are arbitrary, no information is available
|
|
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [2, 1]>,
|
|
//
|
|
// Integer to Double-precision Move
|
|
InstrItinData<IIC_VMOVID , [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// FIXME: all latencies are arbitrary, no information is available
|
|
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [2, 1, 1]>,
|
|
//
|
|
// Single-precision to Integer Move
|
|
InstrItinData<IIC_VMOVSI , [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// FIXME: all latencies are arbitrary, no information is available
|
|
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [2, 1]>,
|
|
//
|
|
// Double-precision to Integer Move
|
|
InstrItinData<IIC_VMOVDI , [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// FIXME: all latencies are arbitrary, no information is available
|
|
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [2, 2, 1]>,
|
|
//
|
|
// Integer to Lane Move
|
|
InstrItinData<IIC_VMOVISL , [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// FIXME: all latencies are arbitrary, no information is available
|
|
InstrStage<4, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<2, [A9_NPipe]>], [3, 1, 1]>,
|
|
|
|
//
|
|
// Double-register FP Unary
|
|
InstrItinData<IIC_VUNAD, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
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_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 7 cycles
|
|
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
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_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 7 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [5, 2, 2]>,
|
|
//
|
|
// 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_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 8 cycles
|
|
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<2, [A9_NPipe]>], [6, 2, 2]>,
|
|
//
|
|
// Double-register FP Multiple-Accumulate
|
|
InstrItinData<IIC_VMACD, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 7 cycles
|
|
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
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_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 9 cycles
|
|
InstrStage<10, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<4, [A9_NPipe]>], [8, 4, 2, 1]>,
|
|
//
|
|
// Double-register Reciprical Step
|
|
InstrItinData<IIC_VRECSD, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 7 cycles
|
|
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<2, [A9_NPipe]>], [6, 2, 2]>,
|
|
//
|
|
// Quad-register Reciprical Step
|
|
InstrItinData<IIC_VRECSQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 9 cycles
|
|
InstrStage<10, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<4, [A9_NPipe]>], [8, 2, 2]>,
|
|
//
|
|
// Double-register Permute
|
|
InstrItinData<IIC_VPERMD, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 6 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
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_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 7 cycles
|
|
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
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_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 8 cycles
|
|
InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<3, [A9_LSPipe]>], [4, 4, 1, 1]>,
|
|
|
|
//
|
|
// Double-register VEXT
|
|
InstrItinData<IIC_VEXTD, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 7 cycles
|
|
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<1, [A9_NPipe]>], [2, 1, 1]>,
|
|
//
|
|
// Quad-register VEXT
|
|
InstrItinData<IIC_VEXTQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 9 cycles
|
|
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<2, [A9_NPipe]>], [3, 1, 1]>,
|
|
//
|
|
// VTB
|
|
InstrItinData<IIC_VTB1, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 7 cycles
|
|
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<2, [A9_NPipe]>], [3, 2, 1]>,
|
|
InstrItinData<IIC_VTB2, [InstrStage<2, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 7 cycles
|
|
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<2, [A9_NPipe]>], [3, 2, 2, 1]>,
|
|
InstrItinData<IIC_VTB3, [InstrStage<2, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 8 cycles
|
|
InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<3, [A9_NPipe]>], [4, 2, 2, 3, 1]>,
|
|
InstrItinData<IIC_VTB4, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 8 cycles
|
|
InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<3, [A9_NPipe]>], [4, 2, 2, 3, 3, 1]>,
|
|
//
|
|
// VTBX
|
|
InstrItinData<IIC_VTBX1, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 7 cycles
|
|
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<2, [A9_NPipe]>], [3, 1, 2, 1]>,
|
|
InstrItinData<IIC_VTBX2, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 7 cycles
|
|
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<2, [A9_NPipe]>], [3, 1, 2, 2, 1]>,
|
|
InstrItinData<IIC_VTBX3, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 8 cycles
|
|
InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<3, [A9_NPipe]>], [4, 1, 2, 2, 3, 1]>,
|
|
InstrItinData<IIC_VTBX4, [InstrStage<1, [A9_DRegsN], 0, Required>,
|
|
// Extra latency cycles since wbck is 8 cycles
|
|
InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
|
|
InstrStage<1, [A9_Pipe1]>,
|
|
InstrStage<2, [A9_NPipe]>], [4, 1, 2, 2, 3, 3, 1]>
|
|
]>;
|