reference, declarationdefinition
definition → references, declarations, derived classes, virtual overrides
reference to multiple definitions → definitions
unreferenced
    1
    2
    3
    4
    5
    6
    7
    8
    9
   10
   11
   12
   13
   14
   15
   16
   17
   18
   19
   20
   21
   22
   23
   24
   25
   26
   27
   28
   29
   30
   31
   32
   33
   34
   35
   36
   37
   38
   39
   40
   41
   42
   43
   44
   45
   46
   47
   48
   49
   50
   51
   52
   53
   54
   55
   56
   57
   58
   59
   60
   61
   62
   63
   64
   65
   66
   67
   68
   69
   70
   71
   72
   73
   74
   75
   76
   77
   78
   79
   80
   81
   82
   83
   84
   85
   86
   87
   88
   89
   90
   91
   92
   93
   94
   95
   96
   97
   98
   99
  100
  101
  102
  103
  104
  105
  106
  107
  108
  109
  110
  111
  112
  113
  114
  115
  116
  117
  118
  119
  120
  121
  122
  123
  124
  125
  126
  127
  128
  129
  130
  131
  132
  133
  134
  135
  136
  137
  138
  139
  140
  141
  142
  143
  144
  145
  146
  147
  148
  149
  150
  151
  152
  153
  154
  155
  156
  157
  158
  159
  160
  161
  162
  163
  164
  165
  166
  167
  168
  169
  170
  171
  172
  173
  174
  175
  176
  177
  178
  179
  180
  181
  182
  183
  184
  185
  186
  187
  188
  189
  190
  191
  192
  193
  194
  195
  196
  197
  198
  199
  200
  201
  202
  203
  204
  205
  206
  207
  208
  209
  210
  211
  212
  213
  214
  215
  216
  217
  218
  219
  220
  221
  222
  223
  224
  225
  226
  227
  228
  229
  230
  231
  232
  233
  234
  235
  236
  237
  238
  239
  240
  241
  242
  243
  244
  245
  246
  247
  248
  249
  250
  251
  252
  253
  254
  255
  256
  257
  258
  259
  260
  261
  262
  263
  264
  265
  266
  267
  268
  269
  270
  271
  272
  273
  274
  275
  276
  277
  278
  279
  280
  281
//===-- SystemZTargetMachine.cpp - Define TargetMachine for SystemZ -------===//
//
// 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
//
//===----------------------------------------------------------------------===//

#include "SystemZTargetMachine.h"
#include "MCTargetDesc/SystemZMCTargetDesc.h"
#include "SystemZ.h"
#include "SystemZMachineScheduler.h"
#include "SystemZTargetTransformInfo.h"
#include "TargetInfo/SystemZTargetInfo.h"
#include "llvm/ADT/Optional.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/CodeGen/Passes.h"
#include "llvm/CodeGen/TargetLoweringObjectFileImpl.h"
#include "llvm/CodeGen/TargetPassConfig.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/Support/CodeGen.h"
#include "llvm/Support/TargetRegistry.h"
#include "llvm/Target/TargetLoweringObjectFile.h"
#include "llvm/Transforms/Scalar.h"
#include <string>

using namespace llvm;

extern "C" void LLVMInitializeSystemZTarget() {
  // Register the target.
  RegisterTargetMachine<SystemZTargetMachine> X(getTheSystemZTarget());
}

// Determine whether we use the vector ABI.
static bool UsesVectorABI(StringRef CPU, StringRef FS) {
  // We use the vector ABI whenever the vector facility is avaiable.
  // This is the case by default if CPU is z13 or later, and can be
  // overridden via "[+-]vector" feature string elements.
  bool VectorABI = true;
  if (CPU.empty() || CPU == "generic" ||
      CPU == "z10" || CPU == "z196" || CPU == "zEC12")
    VectorABI = false;

  SmallVector<StringRef, 3> Features;
  FS.split(Features, ',', -1, false /* KeepEmpty */);
  for (auto &Feature : Features) {
    if (Feature == "vector" || Feature == "+vector")
      VectorABI = true;
    if (Feature == "-vector")
      VectorABI = false;
  }

  return VectorABI;
}

static std::string computeDataLayout(const Triple &TT, StringRef CPU,
                                     StringRef FS) {
  bool VectorABI = UsesVectorABI(CPU, FS);
  std::string Ret;

  // Big endian.
  Ret += "E";

  // Data mangling.
  Ret += DataLayout::getManglingComponent(TT);

  // Make sure that global data has at least 16 bits of alignment by
  // default, so that we can refer to it using LARL.  We don't have any
  // special requirements for stack variables though.
  Ret += "-i1:8:16-i8:8:16";

  // 64-bit integers are naturally aligned.
  Ret += "-i64:64";

  // 128-bit floats are aligned only to 64 bits.
  Ret += "-f128:64";

  // When using the vector ABI, 128-bit vectors are also aligned to 64 bits.
  if (VectorABI)
    Ret += "-v128:64";

  // We prefer 16 bits of aligned for all globals; see above.
  Ret += "-a:8:16";

  // Integer registers are 32 or 64 bits.
  Ret += "-n32:64";

  return Ret;
}

static Reloc::Model getEffectiveRelocModel(Optional<Reloc::Model> RM) {
  // Static code is suitable for use in a dynamic executable; there is no
  // separate DynamicNoPIC model.
  if (!RM.hasValue() || *RM == Reloc::DynamicNoPIC)
    return Reloc::Static;
  return *RM;
}

// For SystemZ we define the models as follows:
//
// Small:  BRASL can call any function and will use a stub if necessary.
//         Locally-binding symbols will always be in range of LARL.
//
// Medium: BRASL can call any function and will use a stub if necessary.
//         GOT slots and locally-defined text will always be in range
//         of LARL, but other symbols might not be.
//
// Large:  Equivalent to Medium for now.
//
// Kernel: Equivalent to Medium for now.
//
// This means that any PIC module smaller than 4GB meets the
// requirements of Small, so Small seems like the best default there.
//
// All symbols bind locally in a non-PIC module, so the choice is less
// obvious.  There are two cases:
//
// - When creating an executable, PLTs and copy relocations allow
//   us to treat external symbols as part of the executable.
//   Any executable smaller than 4GB meets the requirements of Small,
//   so that seems like the best default.
//
// - When creating JIT code, stubs will be in range of BRASL if the
//   image is less than 4GB in size.  GOT entries will likewise be
//   in range of LARL.  However, the JIT environment has no equivalent
//   of copy relocs, so locally-binding data symbols might not be in
//   the range of LARL.  We need the Medium model in that case.
static CodeModel::Model
getEffectiveSystemZCodeModel(Optional<CodeModel::Model> CM, Reloc::Model RM,
                             bool JIT) {
  if (CM) {
    if (*CM == CodeModel::Tiny)
      report_fatal_error("Target does not support the tiny CodeModel", false);
    if (*CM == CodeModel::Kernel)
      report_fatal_error("Target does not support the kernel CodeModel", false);
    return *CM;
  }
  if (JIT)
    return RM == Reloc::PIC_ ? CodeModel::Small : CodeModel::Medium;
  return CodeModel::Small;
}

SystemZTargetMachine::SystemZTargetMachine(const Target &T, const Triple &TT,
                                           StringRef CPU, StringRef FS,
                                           const TargetOptions &Options,
                                           Optional<Reloc::Model> RM,
                                           Optional<CodeModel::Model> CM,
                                           CodeGenOpt::Level OL, bool JIT)
    : LLVMTargetMachine(
          T, computeDataLayout(TT, CPU, FS), TT, CPU, FS, Options,
          getEffectiveRelocModel(RM),
          getEffectiveSystemZCodeModel(CM, getEffectiveRelocModel(RM), JIT),
          OL),
      TLOF(std::make_unique<TargetLoweringObjectFileELF>()),
      Subtarget(TT, CPU, FS, *this) {
  initAsmInfo();
}

SystemZTargetMachine::~SystemZTargetMachine() = default;

namespace {

/// SystemZ Code Generator Pass Configuration Options.
class SystemZPassConfig : public TargetPassConfig {
public:
  SystemZPassConfig(SystemZTargetMachine &TM, PassManagerBase &PM)
    : TargetPassConfig(TM, PM) {}

  SystemZTargetMachine &getSystemZTargetMachine() const {
    return getTM<SystemZTargetMachine>();
  }

  ScheduleDAGInstrs *
  createPostMachineScheduler(MachineSchedContext *C) const override {
    return new ScheduleDAGMI(C,
                             std::make_unique<SystemZPostRASchedStrategy>(C),
                             /*RemoveKillFlags=*/true);
  }

  void addIRPasses() override;
  bool addInstSelector() override;
  bool addILPOpts() override;
  void addPostRewrite() override;
  void addPostRegAlloc() override;
  void addPreSched2() override;
  void addPreEmitPass() override;
};

} // end anonymous namespace

void SystemZPassConfig::addIRPasses() {
  if (getOptLevel() != CodeGenOpt::None) {
    addPass(createSystemZTDCPass());
    addPass(createLoopDataPrefetchPass());
  }

  TargetPassConfig::addIRPasses();
}

bool SystemZPassConfig::addInstSelector() {
  addPass(createSystemZISelDag(getSystemZTargetMachine(), getOptLevel()));

 if (getOptLevel() != CodeGenOpt::None)
    addPass(createSystemZLDCleanupPass(getSystemZTargetMachine()));

  return false;
}

bool SystemZPassConfig::addILPOpts() {
  addPass(&EarlyIfConverterID);
  return true;
}

void SystemZPassConfig::addPostRewrite() {
  addPass(createSystemZPostRewritePass(getSystemZTargetMachine()));
}

void SystemZPassConfig::addPostRegAlloc() {
  // PostRewrite needs to be run at -O0 also (in which case addPostRewrite()
  // is not called).
  if (getOptLevel() == CodeGenOpt::None)
    addPass(createSystemZPostRewritePass(getSystemZTargetMachine()));
}

void SystemZPassConfig::addPreSched2() {
  if (getOptLevel() != CodeGenOpt::None)
    addPass(&IfConverterID);
}

void SystemZPassConfig::addPreEmitPass() {
  // Do instruction shortening before compare elimination because some
  // vector instructions will be shortened into opcodes that compare
  // elimination recognizes.
  if (getOptLevel() != CodeGenOpt::None)
    addPass(createSystemZShortenInstPass(getSystemZTargetMachine()), false);

  // We eliminate comparisons here rather than earlier because some
  // transformations can change the set of available CC values and we
  // generally want those transformations to have priority.  This is
  // especially true in the commonest case where the result of the comparison
  // is used by a single in-range branch instruction, since we will then
  // be able to fuse the compare and the branch instead.
  //
  // For example, two-address NILF can sometimes be converted into
  // three-address RISBLG.  NILF produces a CC value that indicates whether
  // the low word is zero, but RISBLG does not modify CC at all.  On the
  // other hand, 64-bit ANDs like NILL can sometimes be converted to RISBG.
  // The CC value produced by NILL isn't useful for our purposes, but the
  // value produced by RISBG can be used for any comparison with zero
  // (not just equality).  So there are some transformations that lose
  // CC values (while still being worthwhile) and others that happen to make
  // the CC result more useful than it was originally.
  //
  // Another reason is that we only want to use BRANCH ON COUNT in cases
  // where we know that the count register is not going to be spilled.
  //
  // Doing it so late makes it more likely that a register will be reused
  // between the comparison and the branch, but it isn't clear whether
  // preventing that would be a win or not.
  if (getOptLevel() != CodeGenOpt::None)
    addPass(createSystemZElimComparePass(getSystemZTargetMachine()), false);
  addPass(createSystemZLongBranchPass(getSystemZTargetMachine()));

  // Do final scheduling after all other optimizations, to get an
  // optimal input for the decoder (branch relaxation must happen
  // after block placement).
  if (getOptLevel() != CodeGenOpt::None)
    addPass(&PostMachineSchedulerID);
}

TargetPassConfig *SystemZTargetMachine::createPassConfig(PassManagerBase &PM) {
  return new SystemZPassConfig(*this, PM);
}

TargetTransformInfo
SystemZTargetMachine::getTargetTransformInfo(const Function &F) {
  return TargetTransformInfo(SystemZTTIImpl(this, F));
}