llvm-project/llvm/lib/CodeGen/MIRPrinter.cpp

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

949 lines
33 KiB
C++
Raw Normal View History

//===- MIRPrinter.cpp - MIR serialization format printer ------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file implements the class that prints out the LLVM IR and machine
// functions using the MIR serialization format.
//
//===----------------------------------------------------------------------===//
#include "llvm/CodeGen/MIRPrinter.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/None.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/SmallBitVector.h"
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/ADT/Twine.h"
#include "llvm/CodeGen/GlobalISel/RegisterBank.h"
#include "llvm/CodeGen/MIRYamlMapping.h"
#include "llvm/CodeGen/MachineBasicBlock.h"
#include "llvm/CodeGen/MachineConstantPool.h"
#include "llvm/CodeGen/MachineFrameInfo.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineInstr.h"
#include "llvm/CodeGen/MachineJumpTableInfo.h"
#include "llvm/CodeGen/MachineMemOperand.h"
#include "llvm/CodeGen/MachineModuleSlotTracker.h"
#include "llvm/CodeGen/MachineOperand.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/PseudoSourceValue.h"
#include "llvm/CodeGen/TargetFrameLowering.h"
#include "llvm/CodeGen/TargetInstrInfo.h"
#include "llvm/CodeGen/TargetRegisterInfo.h"
#include "llvm/CodeGen/TargetSubtargetInfo.h"
#include "llvm/IR/BasicBlock.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DebugInfo.h"
#include "llvm/IR/DebugLoc.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/GlobalValue.h"
#include "llvm/IR/IRPrintingPasses.h"
#include "llvm/IR/InstrTypes.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/Intrinsics.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/ModuleSlotTracker.h"
#include "llvm/IR/Value.h"
#include "llvm/MC/LaneBitmask.h"
[x86/MIR] Implement support for pre- and post-instruction symbols, as well as MIR parsing support for `MCSymbol` `MachineOperand`s. The only real way to test pre- and post-instruction symbol support is to use them in operands, so I ended up implementing that within the patch as well. I can split out the operand support if folks really want but it doesn't really seem worth it. The functional implementation of pre- and post-instruction symbols is now *completely trivial*. Two tiny bits of code in the (misnamed) AsmPrinter. It should be completely target independent as well. We emit these exactly the same way as we emit basic block labels. Most of the code here is to give full dumping, MIR printing, and MIR parsing support so that we can write useful tests. The MIR parsing of MC symbol operands still isn't 100%, as it forces the symbols to be non-temporary and non-local symbols with names. However, those names often can encode most (if not all) of the special semantics desired, and unnamed symbols seem especially annoying to serialize and de-serialize. While this isn't perfect or full support, it seems plenty to write tests that exercise usage of these kinds of operands. The MIR support for pre-and post-instruction symbols was quite straightforward. I chose to print them out in an as-if-operand syntax similar to debug locations as this seemed the cleanest way and let me use nice introducer tokens rather than inventing more magic punctuation like we use for memoperands. However, supporting MIR-based parsing of these symbols caused me to change the design of the symbol support to allow setting arbitrary symbols. Without this, I don't see any reasonable way to test things with MIR. Differential Revision: https://reviews.llvm.org/D50833 llvm-svn: 339962
2018-08-17 07:11:05 +08:00
#include "llvm/MC/MCContext.h"
#include "llvm/MC/MCDwarf.h"
#include "llvm/MC/MCSymbol.h"
#include "llvm/Support/AtomicOrdering.h"
#include "llvm/Support/BranchProbability.h"
#include "llvm/Support/Casting.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/Format.h"
#include "llvm/Support/LowLevelTypeImpl.h"
#include "llvm/Support/YAMLTraits.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Target/TargetIntrinsicInfo.h"
#include "llvm/Target/TargetMachine.h"
#include <algorithm>
#include <cassert>
#include <cinttypes>
#include <cstdint>
#include <iterator>
#include <string>
#include <utility>
#include <vector>
using namespace llvm;
static cl::opt<bool> SimplifyMIR(
"simplify-mir", cl::Hidden,
cl::desc("Leave out unnecessary information when printing MIR"));
static cl::opt<bool> PrintLocations("mir-debug-loc", cl::Hidden, cl::init(true),
cl::desc("Print MIR debug-locations"));
namespace {
/// This structure describes how to print out stack object references.
struct FrameIndexOperand {
std::string Name;
unsigned ID;
bool IsFixed;
FrameIndexOperand(StringRef Name, unsigned ID, bool IsFixed)
: Name(Name.str()), ID(ID), IsFixed(IsFixed) {}
/// Return an ordinary stack object reference.
static FrameIndexOperand create(StringRef Name, unsigned ID) {
return FrameIndexOperand(Name, ID, /*IsFixed=*/false);
}
/// Return a fixed stack object reference.
static FrameIndexOperand createFixed(unsigned ID) {
return FrameIndexOperand("", ID, /*IsFixed=*/true);
}
};
} // end anonymous namespace
namespace llvm {
/// This class prints out the machine functions using the MIR serialization
/// format.
class MIRPrinter {
raw_ostream &OS;
DenseMap<const uint32_t *, unsigned> RegisterMaskIds;
/// Maps from stack object indices to operand indices which will be used when
/// printing frame index machine operands.
DenseMap<int, FrameIndexOperand> StackObjectOperandMapping;
public:
MIRPrinter(raw_ostream &OS) : OS(OS) {}
void print(const MachineFunction &MF);
void convert(yaml::MachineFunction &MF, const MachineRegisterInfo &RegInfo,
const TargetRegisterInfo *TRI);
void convert(ModuleSlotTracker &MST, yaml::MachineFrameInfo &YamlMFI,
const MachineFrameInfo &MFI);
void convert(yaml::MachineFunction &MF,
const MachineConstantPool &ConstantPool);
void convert(ModuleSlotTracker &MST, yaml::MachineJumpTable &YamlJTI,
const MachineJumpTableInfo &JTI);
void convertStackObjects(yaml::MachineFunction &YMF,
const MachineFunction &MF, ModuleSlotTracker &MST);
void convertCallSiteObjects(yaml::MachineFunction &YMF,
const MachineFunction &MF,
ModuleSlotTracker &MST);
void convertMachineMetadataNodes(yaml::MachineFunction &YMF,
const MachineFunction &MF,
MachineModuleSlotTracker &MST);
private:
void initRegisterMaskIds(const MachineFunction &MF);
};
/// This class prints out the machine instructions using the MIR serialization
/// format.
class MIPrinter {
raw_ostream &OS;
ModuleSlotTracker &MST;
const DenseMap<const uint32_t *, unsigned> &RegisterMaskIds;
const DenseMap<int, FrameIndexOperand> &StackObjectOperandMapping;
/// Synchronization scope names registered with LLVMContext.
SmallVector<StringRef, 8> SSNs;
bool canPredictBranchProbabilities(const MachineBasicBlock &MBB) const;
bool canPredictSuccessors(const MachineBasicBlock &MBB) const;
public:
MIPrinter(raw_ostream &OS, ModuleSlotTracker &MST,
const DenseMap<const uint32_t *, unsigned> &RegisterMaskIds,
const DenseMap<int, FrameIndexOperand> &StackObjectOperandMapping)
: OS(OS), MST(MST), RegisterMaskIds(RegisterMaskIds),
StackObjectOperandMapping(StackObjectOperandMapping) {}
MIR Serialization: Change MIR syntax - use custom syntax for MBBs. This commit modifies the way the machine basic blocks are serialized - now the machine basic blocks are serialized using a custom syntax instead of relying on YAML primitives. Instead of using YAML mappings to represent the individual machine basic blocks in a machine function's body, the new syntax uses a single YAML block scalar which contains all of the machine basic blocks and instructions for that function. This is an example of a function's body that uses the old syntax: body: - id: 0 name: entry instructions: - '%eax = MOV32r0 implicit-def %eflags' - 'RETQ %eax' ... The same body is now written like this: body: | bb.0.entry: %eax = MOV32r0 implicit-def %eflags RETQ %eax ... This syntax change is motivated by the fact that the bundled machine instructions didn't map that well to the old syntax which was using a single YAML sequence to store all of the machine instructions in a block. The bundled machine instructions internally use flags like BundledPred and BundledSucc to determine the bundles, and serializing them as MI flags using the old syntax would have had a negative impact on the readability and the ease of editing for MIR files. The new syntax allows me to serialize the bundled machine instructions using a block construct without relying on the internal flags, for example: BUNDLE implicit-def dead %itstate, implicit-def %s1 ... { t2IT 1, 24, implicit-def %itstate %s1 = VMOVS killed %s0, 1, killed %cpsr, implicit killed %itstate } This commit also converts the MIR testcases to the new syntax. I developed a script that can convert from the old syntax to the new one. I will post the script on the llvm-commits mailing list in the thread for this commit. llvm-svn: 244982
2015-08-14 07:10:16 +08:00
void print(const MachineBasicBlock &MBB);
void print(const MachineInstr &MI);
void printStackObjectReference(int FrameIndex);
void print(const MachineInstr &MI, unsigned OpIdx,
const TargetRegisterInfo *TRI, const TargetInstrInfo *TII,
bool ShouldPrintRegisterTies, LLT TypeToPrint,
bool PrintDef = true);
};
MIR Serialization: Change MIR syntax - use custom syntax for MBBs. This commit modifies the way the machine basic blocks are serialized - now the machine basic blocks are serialized using a custom syntax instead of relying on YAML primitives. Instead of using YAML mappings to represent the individual machine basic blocks in a machine function's body, the new syntax uses a single YAML block scalar which contains all of the machine basic blocks and instructions for that function. This is an example of a function's body that uses the old syntax: body: - id: 0 name: entry instructions: - '%eax = MOV32r0 implicit-def %eflags' - 'RETQ %eax' ... The same body is now written like this: body: | bb.0.entry: %eax = MOV32r0 implicit-def %eflags RETQ %eax ... This syntax change is motivated by the fact that the bundled machine instructions didn't map that well to the old syntax which was using a single YAML sequence to store all of the machine instructions in a block. The bundled machine instructions internally use flags like BundledPred and BundledSucc to determine the bundles, and serializing them as MI flags using the old syntax would have had a negative impact on the readability and the ease of editing for MIR files. The new syntax allows me to serialize the bundled machine instructions using a block construct without relying on the internal flags, for example: BUNDLE implicit-def dead %itstate, implicit-def %s1 ... { t2IT 1, 24, implicit-def %itstate %s1 = VMOVS killed %s0, 1, killed %cpsr, implicit killed %itstate } This commit also converts the MIR testcases to the new syntax. I developed a script that can convert from the old syntax to the new one. I will post the script on the llvm-commits mailing list in the thread for this commit. llvm-svn: 244982
2015-08-14 07:10:16 +08:00
} // end namespace llvm
namespace llvm {
namespace yaml {
/// This struct serializes the LLVM IR module.
template <> struct BlockScalarTraits<Module> {
static void output(const Module &Mod, void *Ctxt, raw_ostream &OS) {
Mod.print(OS, nullptr);
}
static StringRef input(StringRef Str, void *Ctxt, Module &Mod) {
llvm_unreachable("LLVM Module is supposed to be parsed separately");
return "";
}
};
} // end namespace yaml
} // end namespace llvm
static void printRegMIR(unsigned Reg, yaml::StringValue &Dest,
const TargetRegisterInfo *TRI) {
raw_string_ostream OS(Dest.Value);
OS << printReg(Reg, TRI);
}
void MIRPrinter::print(const MachineFunction &MF) {
initRegisterMaskIds(MF);
yaml::MachineFunction YamlMF;
YamlMF.Name = MF.getName();
YamlMF.Alignment = MF.getAlignment();
YamlMF.ExposesReturnsTwice = MF.exposesReturnsTwice();
YamlMF.HasWinCFI = MF.hasWinCFI();
YamlMF.Legalized = MF.getProperties().hasProperty(
MachineFunctionProperties::Property::Legalized);
YamlMF.RegBankSelected = MF.getProperties().hasProperty(
MachineFunctionProperties::Property::RegBankSelected);
YamlMF.Selected = MF.getProperties().hasProperty(
MachineFunctionProperties::Property::Selected);
YamlMF.FailedISel = MF.getProperties().hasProperty(
MachineFunctionProperties::Property::FailedISel);
convert(YamlMF, MF.getRegInfo(), MF.getSubtarget().getRegisterInfo());
MachineModuleSlotTracker MST(&MF);
MST.incorporateFunction(MF.getFunction());
convert(MST, YamlMF.FrameInfo, MF.getFrameInfo());
convertStackObjects(YamlMF, MF, MST);
convertCallSiteObjects(YamlMF, MF, MST);
for (auto &Sub : MF.DebugValueSubstitutions)
YamlMF.DebugValueSubstitutions.push_back({Sub.first.first, Sub.first.second,
Sub.second.first,
Sub.second.second});
if (const auto *ConstantPool = MF.getConstantPool())
convert(YamlMF, *ConstantPool);
if (const auto *JumpTableInfo = MF.getJumpTableInfo())
convert(MST, YamlMF.JumpTableInfo, *JumpTableInfo);
const TargetMachine &TM = MF.getTarget();
YamlMF.MachineFuncInfo =
std::unique_ptr<yaml::MachineFunctionInfo>(TM.convertFuncInfoToYAML(MF));
MIR Serialization: Change MIR syntax - use custom syntax for MBBs. This commit modifies the way the machine basic blocks are serialized - now the machine basic blocks are serialized using a custom syntax instead of relying on YAML primitives. Instead of using YAML mappings to represent the individual machine basic blocks in a machine function's body, the new syntax uses a single YAML block scalar which contains all of the machine basic blocks and instructions for that function. This is an example of a function's body that uses the old syntax: body: - id: 0 name: entry instructions: - '%eax = MOV32r0 implicit-def %eflags' - 'RETQ %eax' ... The same body is now written like this: body: | bb.0.entry: %eax = MOV32r0 implicit-def %eflags RETQ %eax ... This syntax change is motivated by the fact that the bundled machine instructions didn't map that well to the old syntax which was using a single YAML sequence to store all of the machine instructions in a block. The bundled machine instructions internally use flags like BundledPred and BundledSucc to determine the bundles, and serializing them as MI flags using the old syntax would have had a negative impact on the readability and the ease of editing for MIR files. The new syntax allows me to serialize the bundled machine instructions using a block construct without relying on the internal flags, for example: BUNDLE implicit-def dead %itstate, implicit-def %s1 ... { t2IT 1, 24, implicit-def %itstate %s1 = VMOVS killed %s0, 1, killed %cpsr, implicit killed %itstate } This commit also converts the MIR testcases to the new syntax. I developed a script that can convert from the old syntax to the new one. I will post the script on the llvm-commits mailing list in the thread for this commit. llvm-svn: 244982
2015-08-14 07:10:16 +08:00
raw_string_ostream StrOS(YamlMF.Body.Value.Value);
bool IsNewlineNeeded = false;
for (const auto &MBB : MF) {
MIR Serialization: Change MIR syntax - use custom syntax for MBBs. This commit modifies the way the machine basic blocks are serialized - now the machine basic blocks are serialized using a custom syntax instead of relying on YAML primitives. Instead of using YAML mappings to represent the individual machine basic blocks in a machine function's body, the new syntax uses a single YAML block scalar which contains all of the machine basic blocks and instructions for that function. This is an example of a function's body that uses the old syntax: body: - id: 0 name: entry instructions: - '%eax = MOV32r0 implicit-def %eflags' - 'RETQ %eax' ... The same body is now written like this: body: | bb.0.entry: %eax = MOV32r0 implicit-def %eflags RETQ %eax ... This syntax change is motivated by the fact that the bundled machine instructions didn't map that well to the old syntax which was using a single YAML sequence to store all of the machine instructions in a block. The bundled machine instructions internally use flags like BundledPred and BundledSucc to determine the bundles, and serializing them as MI flags using the old syntax would have had a negative impact on the readability and the ease of editing for MIR files. The new syntax allows me to serialize the bundled machine instructions using a block construct without relying on the internal flags, for example: BUNDLE implicit-def dead %itstate, implicit-def %s1 ... { t2IT 1, 24, implicit-def %itstate %s1 = VMOVS killed %s0, 1, killed %cpsr, implicit killed %itstate } This commit also converts the MIR testcases to the new syntax. I developed a script that can convert from the old syntax to the new one. I will post the script on the llvm-commits mailing list in the thread for this commit. llvm-svn: 244982
2015-08-14 07:10:16 +08:00
if (IsNewlineNeeded)
StrOS << "\n";
MIPrinter(StrOS, MST, RegisterMaskIds, StackObjectOperandMapping)
.print(MBB);
IsNewlineNeeded = true;
}
MIR Serialization: Change MIR syntax - use custom syntax for MBBs. This commit modifies the way the machine basic blocks are serialized - now the machine basic blocks are serialized using a custom syntax instead of relying on YAML primitives. Instead of using YAML mappings to represent the individual machine basic blocks in a machine function's body, the new syntax uses a single YAML block scalar which contains all of the machine basic blocks and instructions for that function. This is an example of a function's body that uses the old syntax: body: - id: 0 name: entry instructions: - '%eax = MOV32r0 implicit-def %eflags' - 'RETQ %eax' ... The same body is now written like this: body: | bb.0.entry: %eax = MOV32r0 implicit-def %eflags RETQ %eax ... This syntax change is motivated by the fact that the bundled machine instructions didn't map that well to the old syntax which was using a single YAML sequence to store all of the machine instructions in a block. The bundled machine instructions internally use flags like BundledPred and BundledSucc to determine the bundles, and serializing them as MI flags using the old syntax would have had a negative impact on the readability and the ease of editing for MIR files. The new syntax allows me to serialize the bundled machine instructions using a block construct without relying on the internal flags, for example: BUNDLE implicit-def dead %itstate, implicit-def %s1 ... { t2IT 1, 24, implicit-def %itstate %s1 = VMOVS killed %s0, 1, killed %cpsr, implicit killed %itstate } This commit also converts the MIR testcases to the new syntax. I developed a script that can convert from the old syntax to the new one. I will post the script on the llvm-commits mailing list in the thread for this commit. llvm-svn: 244982
2015-08-14 07:10:16 +08:00
StrOS.flush();
// Convert machine metadata collected during the print of the machine
// function.
convertMachineMetadataNodes(YamlMF, MF, MST);
yaml::Output Out(OS);
if (!SimplifyMIR)
Out.setWriteDefaultValues(true);
Out << YamlMF;
}
static void printCustomRegMask(const uint32_t *RegMask, raw_ostream &OS,
const TargetRegisterInfo *TRI) {
assert(RegMask && "Can't print an empty register mask");
OS << StringRef("CustomRegMask(");
bool IsRegInRegMaskFound = false;
for (int I = 0, E = TRI->getNumRegs(); I < E; I++) {
// Check whether the register is asserted in regmask.
if (RegMask[I / 32] & (1u << (I % 32))) {
if (IsRegInRegMaskFound)
OS << ',';
OS << printReg(I, TRI);
IsRegInRegMaskFound = true;
}
}
OS << ')';
}
static void printRegClassOrBank(unsigned Reg, yaml::StringValue &Dest,
const MachineRegisterInfo &RegInfo,
const TargetRegisterInfo *TRI) {
raw_string_ostream OS(Dest.Value);
[CodeGen] Use MachineOperand::print in the MIRPrinter for MO_Register. Work towards the unification of MIR and debug output by refactoring the interfaces. For MachineOperand::print, keep a simple version that can be easily called from `dump()`, and a more complex one which will be called from both the MIRPrinter and MachineInstr::print. Add extra checks inside MachineOperand for detached operands (operands with getParent() == nullptr). https://reviews.llvm.org/D40836 * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: ([^ ]+) ([^ ]+)<def> ([^ ]+)/kill: \1 def \2 \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: ([^ ]+) ([^ ]+) ([^ ]+)<def>/kill: \1 \2 def \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: def ([^ ]+) ([^ ]+) ([^ ]+)<def>/kill: def \1 \2 def \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/<def>//g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<kill>/killed \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-use,kill>/implicit killed \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<dead>/dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<def[ ]*,[ ]*dead>/dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-def[ ]*,[ ]*dead>/implicit-def dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-def>/implicit-def \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-use>/implicit \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<internal>/internal \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<undef>/undef \1/g' llvm-svn: 320022
2017-12-07 18:40:31 +08:00
OS << printRegClassOrBank(Reg, RegInfo, TRI);
}
template <typename T>
static void
printStackObjectDbgInfo(const MachineFunction::VariableDbgInfo &DebugVar,
T &Object, ModuleSlotTracker &MST) {
std::array<std::string *, 3> Outputs{{&Object.DebugVar.Value,
&Object.DebugExpr.Value,
&Object.DebugLoc.Value}};
std::array<const Metadata *, 3> Metas{{DebugVar.Var,
DebugVar.Expr,
DebugVar.Loc}};
for (unsigned i = 0; i < 3; ++i) {
raw_string_ostream StrOS(*Outputs[i]);
Metas[i]->printAsOperand(StrOS, MST);
}
}
void MIRPrinter::convert(yaml::MachineFunction &MF,
const MachineRegisterInfo &RegInfo,
const TargetRegisterInfo *TRI) {
MF.TracksRegLiveness = RegInfo.tracksLiveness();
// Print the virtual register definitions.
for (unsigned I = 0, E = RegInfo.getNumVirtRegs(); I < E; ++I) {
unsigned Reg = Register::index2VirtReg(I);
yaml::VirtualRegisterDefinition VReg;
VReg.ID = I;
if (RegInfo.getVRegName(Reg) != "")
continue;
[CodeGen] Use MachineOperand::print in the MIRPrinter for MO_Register. Work towards the unification of MIR and debug output by refactoring the interfaces. For MachineOperand::print, keep a simple version that can be easily called from `dump()`, and a more complex one which will be called from both the MIRPrinter and MachineInstr::print. Add extra checks inside MachineOperand for detached operands (operands with getParent() == nullptr). https://reviews.llvm.org/D40836 * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: ([^ ]+) ([^ ]+)<def> ([^ ]+)/kill: \1 def \2 \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: ([^ ]+) ([^ ]+) ([^ ]+)<def>/kill: \1 \2 def \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: def ([^ ]+) ([^ ]+) ([^ ]+)<def>/kill: def \1 \2 def \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/<def>//g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<kill>/killed \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-use,kill>/implicit killed \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<dead>/dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<def[ ]*,[ ]*dead>/dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-def[ ]*,[ ]*dead>/implicit-def dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-def>/implicit-def \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-use>/implicit \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<internal>/internal \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<undef>/undef \1/g' llvm-svn: 320022
2017-12-07 18:40:31 +08:00
::printRegClassOrBank(Reg, VReg.Class, RegInfo, TRI);
unsigned PreferredReg = RegInfo.getSimpleHint(Reg);
if (PreferredReg)
printRegMIR(PreferredReg, VReg.PreferredRegister, TRI);
MF.VirtualRegisters.push_back(VReg);
}
// Print the live ins.
for (std::pair<unsigned, unsigned> LI : RegInfo.liveins()) {
yaml::MachineFunctionLiveIn LiveIn;
printRegMIR(LI.first, LiveIn.Register, TRI);
if (LI.second)
printRegMIR(LI.second, LiveIn.VirtualRegister, TRI);
MF.LiveIns.push_back(LiveIn);
}
// Prints the callee saved registers.
if (RegInfo.isUpdatedCSRsInitialized()) {
const MCPhysReg *CalleeSavedRegs = RegInfo.getCalleeSavedRegs();
std::vector<yaml::FlowStringValue> CalleeSavedRegisters;
for (const MCPhysReg *I = CalleeSavedRegs; *I; ++I) {
yaml::FlowStringValue Reg;
printRegMIR(*I, Reg, TRI);
CalleeSavedRegisters.push_back(Reg);
}
MF.CalleeSavedRegisters = CalleeSavedRegisters;
}
}
void MIRPrinter::convert(ModuleSlotTracker &MST,
yaml::MachineFrameInfo &YamlMFI,
const MachineFrameInfo &MFI) {
YamlMFI.IsFrameAddressTaken = MFI.isFrameAddressTaken();
YamlMFI.IsReturnAddressTaken = MFI.isReturnAddressTaken();
YamlMFI.HasStackMap = MFI.hasStackMap();
YamlMFI.HasPatchPoint = MFI.hasPatchPoint();
YamlMFI.StackSize = MFI.getStackSize();
YamlMFI.OffsetAdjustment = MFI.getOffsetAdjustment();
YamlMFI.MaxAlignment = MFI.getMaxAlign().value();
YamlMFI.AdjustsStack = MFI.adjustsStack();
YamlMFI.HasCalls = MFI.hasCalls();
YamlMFI.MaxCallFrameSize = MFI.isMaxCallFrameSizeComputed()
? MFI.getMaxCallFrameSize() : ~0u;
YamlMFI.CVBytesOfCalleeSavedRegisters =
MFI.getCVBytesOfCalleeSavedRegisters();
YamlMFI.HasOpaqueSPAdjustment = MFI.hasOpaqueSPAdjustment();
YamlMFI.HasVAStart = MFI.hasVAStart();
YamlMFI.HasMustTailInVarArgFunc = MFI.hasMustTailInVarArgFunc();
YamlMFI.HasTailCall = MFI.hasTailCall();
YamlMFI.LocalFrameSize = MFI.getLocalFrameSize();
if (MFI.getSavePoint()) {
raw_string_ostream StrOS(YamlMFI.SavePoint.Value);
StrOS << printMBBReference(*MFI.getSavePoint());
}
if (MFI.getRestorePoint()) {
raw_string_ostream StrOS(YamlMFI.RestorePoint.Value);
StrOS << printMBBReference(*MFI.getRestorePoint());
}
}
void MIRPrinter::convertStackObjects(yaml::MachineFunction &YMF,
const MachineFunction &MF,
ModuleSlotTracker &MST) {
const MachineFrameInfo &MFI = MF.getFrameInfo();
const TargetRegisterInfo *TRI = MF.getSubtarget().getRegisterInfo();
// Process fixed stack objects.
assert(YMF.FixedStackObjects.empty());
SmallVector<int, 32> FixedStackObjectsIdx;
const int BeginIdx = MFI.getObjectIndexBegin();
if (BeginIdx < 0)
FixedStackObjectsIdx.reserve(-BeginIdx);
unsigned ID = 0;
for (int I = BeginIdx; I < 0; ++I, ++ID) {
FixedStackObjectsIdx.push_back(-1); // Fill index for possible dead.
if (MFI.isDeadObjectIndex(I))
continue;
yaml::FixedMachineStackObject YamlObject;
YamlObject.ID = ID;
YamlObject.Type = MFI.isSpillSlotObjectIndex(I)
? yaml::FixedMachineStackObject::SpillSlot
: yaml::FixedMachineStackObject::DefaultType;
YamlObject.Offset = MFI.getObjectOffset(I);
YamlObject.Size = MFI.getObjectSize(I);
YamlObject.Alignment = MFI.getObjectAlign(I);
YamlObject.StackID = (TargetStackID::Value)MFI.getStackID(I);
YamlObject.IsImmutable = MFI.isImmutableObjectIndex(I);
YamlObject.IsAliased = MFI.isAliasedObjectIndex(I);
// Save the ID' position in FixedStackObjects storage vector.
FixedStackObjectsIdx[ID] = YMF.FixedStackObjects.size();
YMF.FixedStackObjects.push_back(YamlObject);
StackObjectOperandMapping.insert(
std::make_pair(I, FrameIndexOperand::createFixed(ID)));
}
// Process ordinary stack objects.
assert(YMF.StackObjects.empty());
SmallVector<unsigned, 32> StackObjectsIdx;
const int EndIdx = MFI.getObjectIndexEnd();
if (EndIdx > 0)
StackObjectsIdx.reserve(EndIdx);
ID = 0;
for (int I = 0; I < EndIdx; ++I, ++ID) {
StackObjectsIdx.push_back(-1); // Fill index for possible dead.
if (MFI.isDeadObjectIndex(I))
continue;
yaml::MachineStackObject YamlObject;
YamlObject.ID = ID;
if (const auto *Alloca = MFI.getObjectAllocation(I))
YamlObject.Name.Value = std::string(
Alloca->hasName() ? Alloca->getName() : "");
YamlObject.Type = MFI.isSpillSlotObjectIndex(I)
? yaml::MachineStackObject::SpillSlot
: MFI.isVariableSizedObjectIndex(I)
? yaml::MachineStackObject::VariableSized
: yaml::MachineStackObject::DefaultType;
YamlObject.Offset = MFI.getObjectOffset(I);
YamlObject.Size = MFI.getObjectSize(I);
YamlObject.Alignment = MFI.getObjectAlign(I);
YamlObject.StackID = (TargetStackID::Value)MFI.getStackID(I);
// Save the ID' position in StackObjects storage vector.
StackObjectsIdx[ID] = YMF.StackObjects.size();
YMF.StackObjects.push_back(YamlObject);
StackObjectOperandMapping.insert(std::make_pair(
I, FrameIndexOperand::create(YamlObject.Name.Value, ID)));
}
for (const auto &CSInfo : MFI.getCalleeSavedInfo()) {
const int FrameIdx = CSInfo.getFrameIdx();
if (!CSInfo.isSpilledToReg() && MFI.isDeadObjectIndex(FrameIdx))
continue;
yaml::StringValue Reg;
printRegMIR(CSInfo.getReg(), Reg, TRI);
if (!CSInfo.isSpilledToReg()) {
assert(FrameIdx >= MFI.getObjectIndexBegin() &&
FrameIdx < MFI.getObjectIndexEnd() &&
"Invalid stack object index");
if (FrameIdx < 0) { // Negative index means fixed objects.
auto &Object =
YMF.FixedStackObjects
[FixedStackObjectsIdx[FrameIdx + MFI.getNumFixedObjects()]];
Object.CalleeSavedRegister = Reg;
Object.CalleeSavedRestored = CSInfo.isRestored();
} else {
auto &Object = YMF.StackObjects[StackObjectsIdx[FrameIdx]];
Object.CalleeSavedRegister = Reg;
Object.CalleeSavedRestored = CSInfo.isRestored();
}
}
}
for (unsigned I = 0, E = MFI.getLocalFrameObjectCount(); I < E; ++I) {
auto LocalObject = MFI.getLocalFrameObjectMap(I);
assert(LocalObject.first >= 0 && "Expected a locally mapped stack object");
YMF.StackObjects[StackObjectsIdx[LocalObject.first]].LocalOffset =
LocalObject.second;
}
// Print the stack object references in the frame information class after
// converting the stack objects.
if (MFI.hasStackProtectorIndex()) {
raw_string_ostream StrOS(YMF.FrameInfo.StackProtector.Value);
MIPrinter(StrOS, MST, RegisterMaskIds, StackObjectOperandMapping)
.printStackObjectReference(MFI.getStackProtectorIndex());
}
// Print the debug variable information.
for (const MachineFunction::VariableDbgInfo &DebugVar :
MF.getVariableDbgInfo()) {
assert(DebugVar.Slot >= MFI.getObjectIndexBegin() &&
DebugVar.Slot < MFI.getObjectIndexEnd() &&
"Invalid stack object index");
if (DebugVar.Slot < 0) { // Negative index means fixed objects.
auto &Object =
YMF.FixedStackObjects[FixedStackObjectsIdx[DebugVar.Slot +
MFI.getNumFixedObjects()]];
printStackObjectDbgInfo(DebugVar, Object, MST);
} else {
auto &Object = YMF.StackObjects[StackObjectsIdx[DebugVar.Slot]];
printStackObjectDbgInfo(DebugVar, Object, MST);
}
}
}
void MIRPrinter::convertCallSiteObjects(yaml::MachineFunction &YMF,
const MachineFunction &MF,
ModuleSlotTracker &MST) {
const auto *TRI = MF.getSubtarget().getRegisterInfo();
for (auto CSInfo : MF.getCallSitesInfo()) {
yaml::CallSiteInfo YmlCS;
yaml::CallSiteInfo::MachineInstrLoc CallLocation;
// Prepare instruction position.
MachineBasicBlock::const_instr_iterator CallI = CSInfo.first->getIterator();
CallLocation.BlockNum = CallI->getParent()->getNumber();
// Get call instruction offset from the beginning of block.
CallLocation.Offset =
std::distance(CallI->getParent()->instr_begin(), CallI);
YmlCS.CallLocation = CallLocation;
// Construct call arguments and theirs forwarding register info.
for (auto ArgReg : CSInfo.second) {
yaml::CallSiteInfo::ArgRegPair YmlArgReg;
YmlArgReg.ArgNo = ArgReg.ArgNo;
printRegMIR(ArgReg.Reg, YmlArgReg.Reg, TRI);
YmlCS.ArgForwardingRegs.emplace_back(YmlArgReg);
}
YMF.CallSitesInfo.push_back(YmlCS);
}
// Sort call info by position of call instructions.
llvm::sort(YMF.CallSitesInfo.begin(), YMF.CallSitesInfo.end(),
[](yaml::CallSiteInfo A, yaml::CallSiteInfo B) {
if (A.CallLocation.BlockNum == B.CallLocation.BlockNum)
return A.CallLocation.Offset < B.CallLocation.Offset;
return A.CallLocation.BlockNum < B.CallLocation.BlockNum;
});
}
void MIRPrinter::convertMachineMetadataNodes(yaml::MachineFunction &YMF,
const MachineFunction &MF,
MachineModuleSlotTracker &MST) {
MachineModuleSlotTracker::MachineMDNodeListType MDList;
MST.collectMachineMDNodes(MDList);
for (auto &MD : MDList) {
std::string NS;
raw_string_ostream StrOS(NS);
MD.second->print(StrOS, MST, MF.getFunction().getParent());
YMF.MachineMetadataNodes.push_back(StrOS.str());
}
}
void MIRPrinter::convert(yaml::MachineFunction &MF,
const MachineConstantPool &ConstantPool) {
unsigned ID = 0;
for (const MachineConstantPoolEntry &Constant : ConstantPool.getConstants()) {
std::string Str;
raw_string_ostream StrOS(Str);
if (Constant.isMachineConstantPoolEntry()) {
Constant.Val.MachineCPVal->print(StrOS);
} else {
Constant.Val.ConstVal->printAsOperand(StrOS);
}
yaml::MachineConstantPoolValue YamlConstant;
YamlConstant.ID = ID++;
YamlConstant.Value = StrOS.str();
YamlConstant.Alignment = Constant.getAlign();
YamlConstant.IsTargetSpecific = Constant.isMachineConstantPoolEntry();
MF.Constants.push_back(YamlConstant);
}
}
void MIRPrinter::convert(ModuleSlotTracker &MST,
yaml::MachineJumpTable &YamlJTI,
const MachineJumpTableInfo &JTI) {
YamlJTI.Kind = JTI.getEntryKind();
unsigned ID = 0;
for (const auto &Table : JTI.getJumpTables()) {
std::string Str;
yaml::MachineJumpTable::Entry Entry;
Entry.ID = ID++;
for (const auto *MBB : Table.MBBs) {
raw_string_ostream StrOS(Str);
StrOS << printMBBReference(*MBB);
Entry.Blocks.push_back(StrOS.str());
Str.clear();
}
YamlJTI.Entries.push_back(Entry);
}
}
MIR Serialization: Change MIR syntax - use custom syntax for MBBs. This commit modifies the way the machine basic blocks are serialized - now the machine basic blocks are serialized using a custom syntax instead of relying on YAML primitives. Instead of using YAML mappings to represent the individual machine basic blocks in a machine function's body, the new syntax uses a single YAML block scalar which contains all of the machine basic blocks and instructions for that function. This is an example of a function's body that uses the old syntax: body: - id: 0 name: entry instructions: - '%eax = MOV32r0 implicit-def %eflags' - 'RETQ %eax' ... The same body is now written like this: body: | bb.0.entry: %eax = MOV32r0 implicit-def %eflags RETQ %eax ... This syntax change is motivated by the fact that the bundled machine instructions didn't map that well to the old syntax which was using a single YAML sequence to store all of the machine instructions in a block. The bundled machine instructions internally use flags like BundledPred and BundledSucc to determine the bundles, and serializing them as MI flags using the old syntax would have had a negative impact on the readability and the ease of editing for MIR files. The new syntax allows me to serialize the bundled machine instructions using a block construct without relying on the internal flags, for example: BUNDLE implicit-def dead %itstate, implicit-def %s1 ... { t2IT 1, 24, implicit-def %itstate %s1 = VMOVS killed %s0, 1, killed %cpsr, implicit killed %itstate } This commit also converts the MIR testcases to the new syntax. I developed a script that can convert from the old syntax to the new one. I will post the script on the llvm-commits mailing list in the thread for this commit. llvm-svn: 244982
2015-08-14 07:10:16 +08:00
void MIRPrinter::initRegisterMaskIds(const MachineFunction &MF) {
const auto *TRI = MF.getSubtarget().getRegisterInfo();
unsigned I = 0;
for (const uint32_t *Mask : TRI->getRegMasks())
RegisterMaskIds.insert(std::make_pair(Mask, I++));
}
void llvm::guessSuccessors(const MachineBasicBlock &MBB,
SmallVectorImpl<MachineBasicBlock*> &Result,
bool &IsFallthrough) {
SmallPtrSet<MachineBasicBlock*,8> Seen;
for (const MachineInstr &MI : MBB) {
if (MI.isPHI())
continue;
for (const MachineOperand &MO : MI.operands()) {
if (!MO.isMBB())
continue;
MachineBasicBlock *Succ = MO.getMBB();
auto RP = Seen.insert(Succ);
if (RP.second)
Result.push_back(Succ);
}
}
MachineBasicBlock::const_iterator I = MBB.getLastNonDebugInstr();
IsFallthrough = I == MBB.end() || !I->isBarrier();
}
bool
MIPrinter::canPredictBranchProbabilities(const MachineBasicBlock &MBB) const {
if (MBB.succ_size() <= 1)
return true;
if (!MBB.hasSuccessorProbabilities())
return true;
SmallVector<BranchProbability,8> Normalized(MBB.Probs.begin(),
MBB.Probs.end());
BranchProbability::normalizeProbabilities(Normalized.begin(),
Normalized.end());
SmallVector<BranchProbability,8> Equal(Normalized.size());
BranchProbability::normalizeProbabilities(Equal.begin(), Equal.end());
return std::equal(Normalized.begin(), Normalized.end(), Equal.begin());
}
bool MIPrinter::canPredictSuccessors(const MachineBasicBlock &MBB) const {
SmallVector<MachineBasicBlock*,8> GuessedSuccs;
bool GuessedFallthrough;
guessSuccessors(MBB, GuessedSuccs, GuessedFallthrough);
if (GuessedFallthrough) {
const MachineFunction &MF = *MBB.getParent();
MachineFunction::const_iterator NextI = std::next(MBB.getIterator());
if (NextI != MF.end()) {
MachineBasicBlock *Next = const_cast<MachineBasicBlock*>(&*NextI);
if (!is_contained(GuessedSuccs, Next))
GuessedSuccs.push_back(Next);
}
}
if (GuessedSuccs.size() != MBB.succ_size())
return false;
return std::equal(MBB.succ_begin(), MBB.succ_end(), GuessedSuccs.begin());
}
MIR Serialization: Change MIR syntax - use custom syntax for MBBs. This commit modifies the way the machine basic blocks are serialized - now the machine basic blocks are serialized using a custom syntax instead of relying on YAML primitives. Instead of using YAML mappings to represent the individual machine basic blocks in a machine function's body, the new syntax uses a single YAML block scalar which contains all of the machine basic blocks and instructions for that function. This is an example of a function's body that uses the old syntax: body: - id: 0 name: entry instructions: - '%eax = MOV32r0 implicit-def %eflags' - 'RETQ %eax' ... The same body is now written like this: body: | bb.0.entry: %eax = MOV32r0 implicit-def %eflags RETQ %eax ... This syntax change is motivated by the fact that the bundled machine instructions didn't map that well to the old syntax which was using a single YAML sequence to store all of the machine instructions in a block. The bundled machine instructions internally use flags like BundledPred and BundledSucc to determine the bundles, and serializing them as MI flags using the old syntax would have had a negative impact on the readability and the ease of editing for MIR files. The new syntax allows me to serialize the bundled machine instructions using a block construct without relying on the internal flags, for example: BUNDLE implicit-def dead %itstate, implicit-def %s1 ... { t2IT 1, 24, implicit-def %itstate %s1 = VMOVS killed %s0, 1, killed %cpsr, implicit killed %itstate } This commit also converts the MIR testcases to the new syntax. I developed a script that can convert from the old syntax to the new one. I will post the script on the llvm-commits mailing list in the thread for this commit. llvm-svn: 244982
2015-08-14 07:10:16 +08:00
void MIPrinter::print(const MachineBasicBlock &MBB) {
assert(MBB.getNumber() >= 0 && "Invalid MBB number");
MBB.printName(OS,
MachineBasicBlock::PrintNameIr |
MachineBasicBlock::PrintNameAttributes,
&MST);
MIR Serialization: Change MIR syntax - use custom syntax for MBBs. This commit modifies the way the machine basic blocks are serialized - now the machine basic blocks are serialized using a custom syntax instead of relying on YAML primitives. Instead of using YAML mappings to represent the individual machine basic blocks in a machine function's body, the new syntax uses a single YAML block scalar which contains all of the machine basic blocks and instructions for that function. This is an example of a function's body that uses the old syntax: body: - id: 0 name: entry instructions: - '%eax = MOV32r0 implicit-def %eflags' - 'RETQ %eax' ... The same body is now written like this: body: | bb.0.entry: %eax = MOV32r0 implicit-def %eflags RETQ %eax ... This syntax change is motivated by the fact that the bundled machine instructions didn't map that well to the old syntax which was using a single YAML sequence to store all of the machine instructions in a block. The bundled machine instructions internally use flags like BundledPred and BundledSucc to determine the bundles, and serializing them as MI flags using the old syntax would have had a negative impact on the readability and the ease of editing for MIR files. The new syntax allows me to serialize the bundled machine instructions using a block construct without relying on the internal flags, for example: BUNDLE implicit-def dead %itstate, implicit-def %s1 ... { t2IT 1, 24, implicit-def %itstate %s1 = VMOVS killed %s0, 1, killed %cpsr, implicit killed %itstate } This commit also converts the MIR testcases to the new syntax. I developed a script that can convert from the old syntax to the new one. I will post the script on the llvm-commits mailing list in the thread for this commit. llvm-svn: 244982
2015-08-14 07:10:16 +08:00
OS << ":\n";
bool HasLineAttributes = false;
// Print the successors
bool canPredictProbs = canPredictBranchProbabilities(MBB);
// Even if the list of successors is empty, if we cannot guess it,
// we need to print it to tell the parser that the list is empty.
// This is needed, because MI model unreachable as empty blocks
// with an empty successor list. If the parser would see that
// without the successor list, it would guess the code would
// fallthrough.
if ((!MBB.succ_empty() && !SimplifyMIR) || !canPredictProbs ||
!canPredictSuccessors(MBB)) {
MIR Serialization: Change MIR syntax - use custom syntax for MBBs. This commit modifies the way the machine basic blocks are serialized - now the machine basic blocks are serialized using a custom syntax instead of relying on YAML primitives. Instead of using YAML mappings to represent the individual machine basic blocks in a machine function's body, the new syntax uses a single YAML block scalar which contains all of the machine basic blocks and instructions for that function. This is an example of a function's body that uses the old syntax: body: - id: 0 name: entry instructions: - '%eax = MOV32r0 implicit-def %eflags' - 'RETQ %eax' ... The same body is now written like this: body: | bb.0.entry: %eax = MOV32r0 implicit-def %eflags RETQ %eax ... This syntax change is motivated by the fact that the bundled machine instructions didn't map that well to the old syntax which was using a single YAML sequence to store all of the machine instructions in a block. The bundled machine instructions internally use flags like BundledPred and BundledSucc to determine the bundles, and serializing them as MI flags using the old syntax would have had a negative impact on the readability and the ease of editing for MIR files. The new syntax allows me to serialize the bundled machine instructions using a block construct without relying on the internal flags, for example: BUNDLE implicit-def dead %itstate, implicit-def %s1 ... { t2IT 1, 24, implicit-def %itstate %s1 = VMOVS killed %s0, 1, killed %cpsr, implicit killed %itstate } This commit also converts the MIR testcases to the new syntax. I developed a script that can convert from the old syntax to the new one. I will post the script on the llvm-commits mailing list in the thread for this commit. llvm-svn: 244982
2015-08-14 07:10:16 +08:00
OS.indent(2) << "successors: ";
for (auto I = MBB.succ_begin(), E = MBB.succ_end(); I != E; ++I) {
if (I != MBB.succ_begin())
OS << ", ";
OS << printMBBReference(**I);
if (!SimplifyMIR || !canPredictProbs)
OS << '('
<< format("0x%08" PRIx32, MBB.getSuccProbability(I).getNumerator())
<< ')';
MIR Serialization: Change MIR syntax - use custom syntax for MBBs. This commit modifies the way the machine basic blocks are serialized - now the machine basic blocks are serialized using a custom syntax instead of relying on YAML primitives. Instead of using YAML mappings to represent the individual machine basic blocks in a machine function's body, the new syntax uses a single YAML block scalar which contains all of the machine basic blocks and instructions for that function. This is an example of a function's body that uses the old syntax: body: - id: 0 name: entry instructions: - '%eax = MOV32r0 implicit-def %eflags' - 'RETQ %eax' ... The same body is now written like this: body: | bb.0.entry: %eax = MOV32r0 implicit-def %eflags RETQ %eax ... This syntax change is motivated by the fact that the bundled machine instructions didn't map that well to the old syntax which was using a single YAML sequence to store all of the machine instructions in a block. The bundled machine instructions internally use flags like BundledPred and BundledSucc to determine the bundles, and serializing them as MI flags using the old syntax would have had a negative impact on the readability and the ease of editing for MIR files. The new syntax allows me to serialize the bundled machine instructions using a block construct without relying on the internal flags, for example: BUNDLE implicit-def dead %itstate, implicit-def %s1 ... { t2IT 1, 24, implicit-def %itstate %s1 = VMOVS killed %s0, 1, killed %cpsr, implicit killed %itstate } This commit also converts the MIR testcases to the new syntax. I developed a script that can convert from the old syntax to the new one. I will post the script on the llvm-commits mailing list in the thread for this commit. llvm-svn: 244982
2015-08-14 07:10:16 +08:00
}
OS << "\n";
HasLineAttributes = true;
}
// Print the live in registers.
const MachineRegisterInfo &MRI = MBB.getParent()->getRegInfo();
if (MRI.tracksLiveness() && !MBB.livein_empty()) {
const TargetRegisterInfo &TRI = *MRI.getTargetRegisterInfo();
MIR Serialization: Change MIR syntax - use custom syntax for MBBs. This commit modifies the way the machine basic blocks are serialized - now the machine basic blocks are serialized using a custom syntax instead of relying on YAML primitives. Instead of using YAML mappings to represent the individual machine basic blocks in a machine function's body, the new syntax uses a single YAML block scalar which contains all of the machine basic blocks and instructions for that function. This is an example of a function's body that uses the old syntax: body: - id: 0 name: entry instructions: - '%eax = MOV32r0 implicit-def %eflags' - 'RETQ %eax' ... The same body is now written like this: body: | bb.0.entry: %eax = MOV32r0 implicit-def %eflags RETQ %eax ... This syntax change is motivated by the fact that the bundled machine instructions didn't map that well to the old syntax which was using a single YAML sequence to store all of the machine instructions in a block. The bundled machine instructions internally use flags like BundledPred and BundledSucc to determine the bundles, and serializing them as MI flags using the old syntax would have had a negative impact on the readability and the ease of editing for MIR files. The new syntax allows me to serialize the bundled machine instructions using a block construct without relying on the internal flags, for example: BUNDLE implicit-def dead %itstate, implicit-def %s1 ... { t2IT 1, 24, implicit-def %itstate %s1 = VMOVS killed %s0, 1, killed %cpsr, implicit killed %itstate } This commit also converts the MIR testcases to the new syntax. I developed a script that can convert from the old syntax to the new one. I will post the script on the llvm-commits mailing list in the thread for this commit. llvm-svn: 244982
2015-08-14 07:10:16 +08:00
OS.indent(2) << "liveins: ";
bool First = true;
for (const auto &LI : MBB.liveins()) {
if (!First)
MIR Serialization: Change MIR syntax - use custom syntax for MBBs. This commit modifies the way the machine basic blocks are serialized - now the machine basic blocks are serialized using a custom syntax instead of relying on YAML primitives. Instead of using YAML mappings to represent the individual machine basic blocks in a machine function's body, the new syntax uses a single YAML block scalar which contains all of the machine basic blocks and instructions for that function. This is an example of a function's body that uses the old syntax: body: - id: 0 name: entry instructions: - '%eax = MOV32r0 implicit-def %eflags' - 'RETQ %eax' ... The same body is now written like this: body: | bb.0.entry: %eax = MOV32r0 implicit-def %eflags RETQ %eax ... This syntax change is motivated by the fact that the bundled machine instructions didn't map that well to the old syntax which was using a single YAML sequence to store all of the machine instructions in a block. The bundled machine instructions internally use flags like BundledPred and BundledSucc to determine the bundles, and serializing them as MI flags using the old syntax would have had a negative impact on the readability and the ease of editing for MIR files. The new syntax allows me to serialize the bundled machine instructions using a block construct without relying on the internal flags, for example: BUNDLE implicit-def dead %itstate, implicit-def %s1 ... { t2IT 1, 24, implicit-def %itstate %s1 = VMOVS killed %s0, 1, killed %cpsr, implicit killed %itstate } This commit also converts the MIR testcases to the new syntax. I developed a script that can convert from the old syntax to the new one. I will post the script on the llvm-commits mailing list in the thread for this commit. llvm-svn: 244982
2015-08-14 07:10:16 +08:00
OS << ", ";
First = false;
OS << printReg(LI.PhysReg, &TRI);
if (!LI.LaneMask.all())
OS << ":0x" << PrintLaneMask(LI.LaneMask);
MIR Serialization: Change MIR syntax - use custom syntax for MBBs. This commit modifies the way the machine basic blocks are serialized - now the machine basic blocks are serialized using a custom syntax instead of relying on YAML primitives. Instead of using YAML mappings to represent the individual machine basic blocks in a machine function's body, the new syntax uses a single YAML block scalar which contains all of the machine basic blocks and instructions for that function. This is an example of a function's body that uses the old syntax: body: - id: 0 name: entry instructions: - '%eax = MOV32r0 implicit-def %eflags' - 'RETQ %eax' ... The same body is now written like this: body: | bb.0.entry: %eax = MOV32r0 implicit-def %eflags RETQ %eax ... This syntax change is motivated by the fact that the bundled machine instructions didn't map that well to the old syntax which was using a single YAML sequence to store all of the machine instructions in a block. The bundled machine instructions internally use flags like BundledPred and BundledSucc to determine the bundles, and serializing them as MI flags using the old syntax would have had a negative impact on the readability and the ease of editing for MIR files. The new syntax allows me to serialize the bundled machine instructions using a block construct without relying on the internal flags, for example: BUNDLE implicit-def dead %itstate, implicit-def %s1 ... { t2IT 1, 24, implicit-def %itstate %s1 = VMOVS killed %s0, 1, killed %cpsr, implicit killed %itstate } This commit also converts the MIR testcases to the new syntax. I developed a script that can convert from the old syntax to the new one. I will post the script on the llvm-commits mailing list in the thread for this commit. llvm-svn: 244982
2015-08-14 07:10:16 +08:00
}
OS << "\n";
HasLineAttributes = true;
}
MIR Serialization: Change MIR syntax - use custom syntax for MBBs. This commit modifies the way the machine basic blocks are serialized - now the machine basic blocks are serialized using a custom syntax instead of relying on YAML primitives. Instead of using YAML mappings to represent the individual machine basic blocks in a machine function's body, the new syntax uses a single YAML block scalar which contains all of the machine basic blocks and instructions for that function. This is an example of a function's body that uses the old syntax: body: - id: 0 name: entry instructions: - '%eax = MOV32r0 implicit-def %eflags' - 'RETQ %eax' ... The same body is now written like this: body: | bb.0.entry: %eax = MOV32r0 implicit-def %eflags RETQ %eax ... This syntax change is motivated by the fact that the bundled machine instructions didn't map that well to the old syntax which was using a single YAML sequence to store all of the machine instructions in a block. The bundled machine instructions internally use flags like BundledPred and BundledSucc to determine the bundles, and serializing them as MI flags using the old syntax would have had a negative impact on the readability and the ease of editing for MIR files. The new syntax allows me to serialize the bundled machine instructions using a block construct without relying on the internal flags, for example: BUNDLE implicit-def dead %itstate, implicit-def %s1 ... { t2IT 1, 24, implicit-def %itstate %s1 = VMOVS killed %s0, 1, killed %cpsr, implicit killed %itstate } This commit also converts the MIR testcases to the new syntax. I developed a script that can convert from the old syntax to the new one. I will post the script on the llvm-commits mailing list in the thread for this commit. llvm-svn: 244982
2015-08-14 07:10:16 +08:00
if (HasLineAttributes)
OS << "\n";
bool IsInBundle = false;
for (auto I = MBB.instr_begin(), E = MBB.instr_end(); I != E; ++I) {
const MachineInstr &MI = *I;
if (IsInBundle && !MI.isInsideBundle()) {
OS.indent(2) << "}\n";
IsInBundle = false;
}
OS.indent(IsInBundle ? 4 : 2);
MIR Serialization: Change MIR syntax - use custom syntax for MBBs. This commit modifies the way the machine basic blocks are serialized - now the machine basic blocks are serialized using a custom syntax instead of relying on YAML primitives. Instead of using YAML mappings to represent the individual machine basic blocks in a machine function's body, the new syntax uses a single YAML block scalar which contains all of the machine basic blocks and instructions for that function. This is an example of a function's body that uses the old syntax: body: - id: 0 name: entry instructions: - '%eax = MOV32r0 implicit-def %eflags' - 'RETQ %eax' ... The same body is now written like this: body: | bb.0.entry: %eax = MOV32r0 implicit-def %eflags RETQ %eax ... This syntax change is motivated by the fact that the bundled machine instructions didn't map that well to the old syntax which was using a single YAML sequence to store all of the machine instructions in a block. The bundled machine instructions internally use flags like BundledPred and BundledSucc to determine the bundles, and serializing them as MI flags using the old syntax would have had a negative impact on the readability and the ease of editing for MIR files. The new syntax allows me to serialize the bundled machine instructions using a block construct without relying on the internal flags, for example: BUNDLE implicit-def dead %itstate, implicit-def %s1 ... { t2IT 1, 24, implicit-def %itstate %s1 = VMOVS killed %s0, 1, killed %cpsr, implicit killed %itstate } This commit also converts the MIR testcases to the new syntax. I developed a script that can convert from the old syntax to the new one. I will post the script on the llvm-commits mailing list in the thread for this commit. llvm-svn: 244982
2015-08-14 07:10:16 +08:00
print(MI);
if (!IsInBundle && MI.getFlag(MachineInstr::BundledSucc)) {
OS << " {";
IsInBundle = true;
}
MIR Serialization: Change MIR syntax - use custom syntax for MBBs. This commit modifies the way the machine basic blocks are serialized - now the machine basic blocks are serialized using a custom syntax instead of relying on YAML primitives. Instead of using YAML mappings to represent the individual machine basic blocks in a machine function's body, the new syntax uses a single YAML block scalar which contains all of the machine basic blocks and instructions for that function. This is an example of a function's body that uses the old syntax: body: - id: 0 name: entry instructions: - '%eax = MOV32r0 implicit-def %eflags' - 'RETQ %eax' ... The same body is now written like this: body: | bb.0.entry: %eax = MOV32r0 implicit-def %eflags RETQ %eax ... This syntax change is motivated by the fact that the bundled machine instructions didn't map that well to the old syntax which was using a single YAML sequence to store all of the machine instructions in a block. The bundled machine instructions internally use flags like BundledPred and BundledSucc to determine the bundles, and serializing them as MI flags using the old syntax would have had a negative impact on the readability and the ease of editing for MIR files. The new syntax allows me to serialize the bundled machine instructions using a block construct without relying on the internal flags, for example: BUNDLE implicit-def dead %itstate, implicit-def %s1 ... { t2IT 1, 24, implicit-def %itstate %s1 = VMOVS killed %s0, 1, killed %cpsr, implicit killed %itstate } This commit also converts the MIR testcases to the new syntax. I developed a script that can convert from the old syntax to the new one. I will post the script on the llvm-commits mailing list in the thread for this commit. llvm-svn: 244982
2015-08-14 07:10:16 +08:00
OS << "\n";
}
if (IsInBundle)
OS.indent(2) << "}\n";
}
void MIPrinter::print(const MachineInstr &MI) {
const auto *MF = MI.getMF();
const auto &MRI = MF->getRegInfo();
const auto &SubTarget = MF->getSubtarget();
const auto *TRI = SubTarget.getRegisterInfo();
assert(TRI && "Expected target register info");
const auto *TII = SubTarget.getInstrInfo();
assert(TII && "Expected target instruction info");
if (MI.isCFIInstruction())
assert(MI.getNumOperands() == 1 && "Expected 1 operand in CFI instruction");
SmallBitVector PrintedTypes(8);
[CodeGen] Use MachineOperand::print in the MIRPrinter for MO_Register. Work towards the unification of MIR and debug output by refactoring the interfaces. For MachineOperand::print, keep a simple version that can be easily called from `dump()`, and a more complex one which will be called from both the MIRPrinter and MachineInstr::print. Add extra checks inside MachineOperand for detached operands (operands with getParent() == nullptr). https://reviews.llvm.org/D40836 * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: ([^ ]+) ([^ ]+)<def> ([^ ]+)/kill: \1 def \2 \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: ([^ ]+) ([^ ]+) ([^ ]+)<def>/kill: \1 \2 def \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: def ([^ ]+) ([^ ]+) ([^ ]+)<def>/kill: def \1 \2 def \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/<def>//g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<kill>/killed \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-use,kill>/implicit killed \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<dead>/dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<def[ ]*,[ ]*dead>/dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-def[ ]*,[ ]*dead>/implicit-def dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-def>/implicit-def \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-use>/implicit \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<internal>/internal \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<undef>/undef \1/g' llvm-svn: 320022
2017-12-07 18:40:31 +08:00
bool ShouldPrintRegisterTies = MI.hasComplexRegisterTies();
unsigned I = 0, E = MI.getNumOperands();
for (; I < E && MI.getOperand(I).isReg() && MI.getOperand(I).isDef() &&
!MI.getOperand(I).isImplicit();
++I) {
if (I)
OS << ", ";
print(MI, I, TRI, TII, ShouldPrintRegisterTies,
[CodeGen] Use MachineOperand::print in the MIRPrinter for MO_Register. Work towards the unification of MIR and debug output by refactoring the interfaces. For MachineOperand::print, keep a simple version that can be easily called from `dump()`, and a more complex one which will be called from both the MIRPrinter and MachineInstr::print. Add extra checks inside MachineOperand for detached operands (operands with getParent() == nullptr). https://reviews.llvm.org/D40836 * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: ([^ ]+) ([^ ]+)<def> ([^ ]+)/kill: \1 def \2 \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: ([^ ]+) ([^ ]+) ([^ ]+)<def>/kill: \1 \2 def \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: def ([^ ]+) ([^ ]+) ([^ ]+)<def>/kill: def \1 \2 def \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/<def>//g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<kill>/killed \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-use,kill>/implicit killed \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<dead>/dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<def[ ]*,[ ]*dead>/dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-def[ ]*,[ ]*dead>/implicit-def dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-def>/implicit-def \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-use>/implicit \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<internal>/internal \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<undef>/undef \1/g' llvm-svn: 320022
2017-12-07 18:40:31 +08:00
MI.getTypeToPrint(I, PrintedTypes, MRI),
/*PrintDef=*/false);
}
if (I)
OS << " = ";
if (MI.getFlag(MachineInstr::FrameSetup))
OS << "frame-setup ";
if (MI.getFlag(MachineInstr::FrameDestroy))
OS << "frame-destroy ";
if (MI.getFlag(MachineInstr::FmNoNans))
OS << "nnan ";
if (MI.getFlag(MachineInstr::FmNoInfs))
OS << "ninf ";
if (MI.getFlag(MachineInstr::FmNsz))
OS << "nsz ";
if (MI.getFlag(MachineInstr::FmArcp))
OS << "arcp ";
if (MI.getFlag(MachineInstr::FmContract))
OS << "contract ";
if (MI.getFlag(MachineInstr::FmAfn))
OS << "afn ";
if (MI.getFlag(MachineInstr::FmReassoc))
OS << "reassoc ";
if (MI.getFlag(MachineInstr::NoUWrap))
OS << "nuw ";
if (MI.getFlag(MachineInstr::NoSWrap))
OS << "nsw ";
if (MI.getFlag(MachineInstr::IsExact))
OS << "exact ";
if (MI.getFlag(MachineInstr::NoFPExcept))
OS << "nofpexcept ";
if (MI.getFlag(MachineInstr::NoMerge))
OS << "nomerge ";
OS << TII->getName(MI.getOpcode());
if (I < E)
OS << ' ';
bool NeedComma = false;
for (; I < E; ++I) {
if (NeedComma)
OS << ", ";
print(MI, I, TRI, TII, ShouldPrintRegisterTies,
[CodeGen] Use MachineOperand::print in the MIRPrinter for MO_Register. Work towards the unification of MIR and debug output by refactoring the interfaces. For MachineOperand::print, keep a simple version that can be easily called from `dump()`, and a more complex one which will be called from both the MIRPrinter and MachineInstr::print. Add extra checks inside MachineOperand for detached operands (operands with getParent() == nullptr). https://reviews.llvm.org/D40836 * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: ([^ ]+) ([^ ]+)<def> ([^ ]+)/kill: \1 def \2 \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: ([^ ]+) ([^ ]+) ([^ ]+)<def>/kill: \1 \2 def \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: def ([^ ]+) ([^ ]+) ([^ ]+)<def>/kill: def \1 \2 def \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/<def>//g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<kill>/killed \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-use,kill>/implicit killed \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<dead>/dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<def[ ]*,[ ]*dead>/dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-def[ ]*,[ ]*dead>/implicit-def dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-def>/implicit-def \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-use>/implicit \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<internal>/internal \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<undef>/undef \1/g' llvm-svn: 320022
2017-12-07 18:40:31 +08:00
MI.getTypeToPrint(I, PrintedTypes, MRI));
NeedComma = true;
}
[x86/MIR] Implement support for pre- and post-instruction symbols, as well as MIR parsing support for `MCSymbol` `MachineOperand`s. The only real way to test pre- and post-instruction symbol support is to use them in operands, so I ended up implementing that within the patch as well. I can split out the operand support if folks really want but it doesn't really seem worth it. The functional implementation of pre- and post-instruction symbols is now *completely trivial*. Two tiny bits of code in the (misnamed) AsmPrinter. It should be completely target independent as well. We emit these exactly the same way as we emit basic block labels. Most of the code here is to give full dumping, MIR printing, and MIR parsing support so that we can write useful tests. The MIR parsing of MC symbol operands still isn't 100%, as it forces the symbols to be non-temporary and non-local symbols with names. However, those names often can encode most (if not all) of the special semantics desired, and unnamed symbols seem especially annoying to serialize and de-serialize. While this isn't perfect or full support, it seems plenty to write tests that exercise usage of these kinds of operands. The MIR support for pre-and post-instruction symbols was quite straightforward. I chose to print them out in an as-if-operand syntax similar to debug locations as this seemed the cleanest way and let me use nice introducer tokens rather than inventing more magic punctuation like we use for memoperands. However, supporting MIR-based parsing of these symbols caused me to change the design of the symbol support to allow setting arbitrary symbols. Without this, I don't see any reasonable way to test things with MIR. Differential Revision: https://reviews.llvm.org/D50833 llvm-svn: 339962
2018-08-17 07:11:05 +08:00
// Print any optional symbols attached to this instruction as-if they were
// operands.
if (MCSymbol *PreInstrSymbol = MI.getPreInstrSymbol()) {
if (NeedComma)
OS << ',';
OS << " pre-instr-symbol ";
MachineOperand::printSymbol(OS, *PreInstrSymbol);
NeedComma = true;
}
if (MCSymbol *PostInstrSymbol = MI.getPostInstrSymbol()) {
if (NeedComma)
OS << ',';
OS << " post-instr-symbol ";
MachineOperand::printSymbol(OS, *PostInstrSymbol);
NeedComma = true;
}
if (MDNode *HeapAllocMarker = MI.getHeapAllocMarker()) {
if (NeedComma)
OS << ',';
OS << " heap-alloc-marker ";
HeapAllocMarker->printAsOperand(OS, MST);
NeedComma = true;
}
[x86/MIR] Implement support for pre- and post-instruction symbols, as well as MIR parsing support for `MCSymbol` `MachineOperand`s. The only real way to test pre- and post-instruction symbol support is to use them in operands, so I ended up implementing that within the patch as well. I can split out the operand support if folks really want but it doesn't really seem worth it. The functional implementation of pre- and post-instruction symbols is now *completely trivial*. Two tiny bits of code in the (misnamed) AsmPrinter. It should be completely target independent as well. We emit these exactly the same way as we emit basic block labels. Most of the code here is to give full dumping, MIR printing, and MIR parsing support so that we can write useful tests. The MIR parsing of MC symbol operands still isn't 100%, as it forces the symbols to be non-temporary and non-local symbols with names. However, those names often can encode most (if not all) of the special semantics desired, and unnamed symbols seem especially annoying to serialize and de-serialize. While this isn't perfect or full support, it seems plenty to write tests that exercise usage of these kinds of operands. The MIR support for pre-and post-instruction symbols was quite straightforward. I chose to print them out in an as-if-operand syntax similar to debug locations as this seemed the cleanest way and let me use nice introducer tokens rather than inventing more magic punctuation like we use for memoperands. However, supporting MIR-based parsing of these symbols caused me to change the design of the symbol support to allow setting arbitrary symbols. Without this, I don't see any reasonable way to test things with MIR. Differential Revision: https://reviews.llvm.org/D50833 llvm-svn: 339962
2018-08-17 07:11:05 +08:00
if (auto Num = MI.peekDebugInstrNum()) {
if (NeedComma)
OS << ',';
OS << " debug-instr-number " << Num;
NeedComma = true;
}
if (PrintLocations) {
if (const DebugLoc &DL = MI.getDebugLoc()) {
if (NeedComma)
OS << ',';
OS << " debug-location ";
DL->printAsOperand(OS, MST);
}
}
if (!MI.memoperands_empty()) {
OS << " :: ";
const LLVMContext &Context = MF->getFunction().getContext();
const MachineFrameInfo &MFI = MF->getFrameInfo();
bool NeedComma = false;
for (const auto *Op : MI.memoperands()) {
if (NeedComma)
OS << ", ";
Op->print(OS, MST, SSNs, Context, &MFI, TII);
NeedComma = true;
}
}
}
void MIPrinter::printStackObjectReference(int FrameIndex) {
auto ObjectInfo = StackObjectOperandMapping.find(FrameIndex);
assert(ObjectInfo != StackObjectOperandMapping.end() &&
"Invalid frame index");
const FrameIndexOperand &Operand = ObjectInfo->second;
MachineOperand::printStackObjectReference(OS, Operand.ID, Operand.IsFixed,
Operand.Name);
}
static std::string formatOperandComment(std::string Comment) {
if (Comment.empty())
return Comment;
return std::string(" /* " + Comment + " */");
}
void MIPrinter::print(const MachineInstr &MI, unsigned OpIdx,
const TargetRegisterInfo *TRI,
const TargetInstrInfo *TII,
bool ShouldPrintRegisterTies, LLT TypeToPrint,
[CodeGen] Use MachineOperand::print in the MIRPrinter for MO_Register. Work towards the unification of MIR and debug output by refactoring the interfaces. For MachineOperand::print, keep a simple version that can be easily called from `dump()`, and a more complex one which will be called from both the MIRPrinter and MachineInstr::print. Add extra checks inside MachineOperand for detached operands (operands with getParent() == nullptr). https://reviews.llvm.org/D40836 * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: ([^ ]+) ([^ ]+)<def> ([^ ]+)/kill: \1 def \2 \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: ([^ ]+) ([^ ]+) ([^ ]+)<def>/kill: \1 \2 def \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: def ([^ ]+) ([^ ]+) ([^ ]+)<def>/kill: def \1 \2 def \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/<def>//g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<kill>/killed \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-use,kill>/implicit killed \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<dead>/dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<def[ ]*,[ ]*dead>/dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-def[ ]*,[ ]*dead>/implicit-def dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-def>/implicit-def \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-use>/implicit \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<internal>/internal \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<undef>/undef \1/g' llvm-svn: 320022
2017-12-07 18:40:31 +08:00
bool PrintDef) {
const MachineOperand &Op = MI.getOperand(OpIdx);
std::string MOComment = TII->createMIROperandComment(MI, Op, OpIdx, TRI);
switch (Op.getType()) {
case MachineOperand::MO_Immediate:
if (MI.isOperandSubregIdx(OpIdx)) {
MachineOperand::printTargetFlags(OS, Op);
MachineOperand::printSubRegIdx(OS, Op.getImm(), TRI);
break;
}
LLVM_FALLTHROUGH;
case MachineOperand::MO_Register:
case MachineOperand::MO_CImmediate:
case MachineOperand::MO_FPImmediate:
case MachineOperand::MO_MachineBasicBlock:
case MachineOperand::MO_ConstantPoolIndex:
case MachineOperand::MO_TargetIndex:
case MachineOperand::MO_JumpTableIndex:
case MachineOperand::MO_ExternalSymbol:
case MachineOperand::MO_GlobalAddress:
case MachineOperand::MO_RegisterLiveOut:
case MachineOperand::MO_Metadata:
case MachineOperand::MO_MCSymbol:
case MachineOperand::MO_CFIIndex:
case MachineOperand::MO_IntrinsicID:
case MachineOperand::MO_Predicate:
case MachineOperand::MO_BlockAddress:
case MachineOperand::MO_ShuffleMask: {
[CodeGen] Use MachineOperand::print in the MIRPrinter for MO_Register. Work towards the unification of MIR and debug output by refactoring the interfaces. For MachineOperand::print, keep a simple version that can be easily called from `dump()`, and a more complex one which will be called from both the MIRPrinter and MachineInstr::print. Add extra checks inside MachineOperand for detached operands (operands with getParent() == nullptr). https://reviews.llvm.org/D40836 * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: ([^ ]+) ([^ ]+)<def> ([^ ]+)/kill: \1 def \2 \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: ([^ ]+) ([^ ]+) ([^ ]+)<def>/kill: \1 \2 def \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: def ([^ ]+) ([^ ]+) ([^ ]+)<def>/kill: def \1 \2 def \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/<def>//g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<kill>/killed \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-use,kill>/implicit killed \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<dead>/dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<def[ ]*,[ ]*dead>/dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-def[ ]*,[ ]*dead>/implicit-def dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-def>/implicit-def \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-use>/implicit \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<internal>/internal \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<undef>/undef \1/g' llvm-svn: 320022
2017-12-07 18:40:31 +08:00
unsigned TiedOperandIdx = 0;
if (ShouldPrintRegisterTies && Op.isReg() && Op.isTied() && !Op.isDef())
[CodeGen] Use MachineOperand::print in the MIRPrinter for MO_Register. Work towards the unification of MIR and debug output by refactoring the interfaces. For MachineOperand::print, keep a simple version that can be easily called from `dump()`, and a more complex one which will be called from both the MIRPrinter and MachineInstr::print. Add extra checks inside MachineOperand for detached operands (operands with getParent() == nullptr). https://reviews.llvm.org/D40836 * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: ([^ ]+) ([^ ]+)<def> ([^ ]+)/kill: \1 def \2 \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: ([^ ]+) ([^ ]+) ([^ ]+)<def>/kill: \1 \2 def \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: def ([^ ]+) ([^ ]+) ([^ ]+)<def>/kill: def \1 \2 def \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/<def>//g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<kill>/killed \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-use,kill>/implicit killed \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<dead>/dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<def[ ]*,[ ]*dead>/dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-def[ ]*,[ ]*dead>/implicit-def dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-def>/implicit-def \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-use>/implicit \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<internal>/internal \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<undef>/undef \1/g' llvm-svn: 320022
2017-12-07 18:40:31 +08:00
TiedOperandIdx = Op.getParent()->findTiedOperandIdx(OpIdx);
const TargetIntrinsicInfo *TII = MI.getMF()->getTarget().getIntrinsicInfo();
Op.print(OS, MST, TypeToPrint, OpIdx, PrintDef, /*IsStandalone=*/false,
ShouldPrintRegisterTies, TiedOperandIdx, TRI, TII);
OS << formatOperandComment(MOComment);
break;
}
case MachineOperand::MO_FrameIndex:
printStackObjectReference(Op.getIndex());
break;
case MachineOperand::MO_RegisterMask: {
auto RegMaskInfo = RegisterMaskIds.find(Op.getRegMask());
if (RegMaskInfo != RegisterMaskIds.end())
OS << StringRef(TRI->getRegMaskNames()[RegMaskInfo->second]).lower();
else
printCustomRegMask(Op.getRegMask(), OS, TRI);
break;
}
}
}
void MIRFormatter::printIRValue(raw_ostream &OS, const Value &V,
ModuleSlotTracker &MST) {
if (isa<GlobalValue>(V)) {
V.printAsOperand(OS, /*PrintType=*/false, MST);
return;
}
if (isa<Constant>(V)) {
// Machine memory operands can load/store to/from constant value pointers.
OS << '`';
V.printAsOperand(OS, /*PrintType=*/true, MST);
OS << '`';
return;
}
OS << "%ir.";
if (V.hasName()) {
printLLVMNameWithoutPrefix(OS, V.getName());
return;
}
int Slot = MST.getCurrentFunction() ? MST.getLocalSlot(&V) : -1;
MachineOperand::printIRSlotNumber(OS, Slot);
}
void llvm::printMIR(raw_ostream &OS, const Module &M) {
yaml::Output Out(OS);
Out << const_cast<Module &>(M);
}
void llvm::printMIR(raw_ostream &OS, const MachineFunction &MF) {
MIRPrinter Printer(OS);
Printer.print(MF);
}