//===--- NVPTX.cpp - Implement NVPTX target feature support ---------------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file implements NVPTX TargetInfo objects.
//
//===----------------------------------------------------------------------===//

#include "NVPTX.h"
#include "Targets.h"
#include "clang/Basic/Builtins.h"
#include "clang/Basic/MacroBuilder.h"
#include "clang/Basic/TargetBuiltins.h"
#include "llvm/ADT/StringSwitch.h"

using namespace clang;
using namespace clang::targets;

const Builtin::Info NVPTXTargetInfo::BuiltinInfo[] = {
#define BUILTIN(ID, TYPE, ATTRS)                                               \
  {#ID, TYPE, ATTRS, nullptr, ALL_LANGUAGES, nullptr},
#define LIBBUILTIN(ID, TYPE, ATTRS, HEADER)                                    \
  {#ID, TYPE, ATTRS, HEADER, ALL_LANGUAGES, nullptr},
#define TARGET_BUILTIN(ID, TYPE, ATTRS, FEATURE)                               \
  {#ID, TYPE, ATTRS, nullptr, ALL_LANGUAGES, FEATURE},
#include "clang/Basic/BuiltinsNVPTX.def"
};

const char *const NVPTXTargetInfo::GCCRegNames[] = {"r0"};

NVPTXTargetInfo::NVPTXTargetInfo(const llvm::Triple &Triple,
                                 const TargetOptions &Opts,
                                 unsigned TargetPointerWidth)
    : TargetInfo(Triple) {
  assert((TargetPointerWidth == 32 || TargetPointerWidth == 64) &&
         "NVPTX only supports 32- and 64-bit modes.");

  TLSSupported = false;
  AddrSpaceMap = &NVPTXAddrSpaceMap;
  UseAddrSpaceMapMangling = true;

  // Define available target features
  // These must be defined in sorted order!
  NoAsmVariants = true;
  GPU = CudaArch::SM_20;

  if (TargetPointerWidth == 32)
    resetDataLayout("e-p:32:32-i64:64-i128:128-v16:16-v32:32-n16:32:64");
  else
    resetDataLayout("e-i64:64-i128:128-v16:16-v32:32-n16:32:64");

  // If possible, get a TargetInfo for our host triple, so we can match its
  // types.
  llvm::Triple HostTriple(Opts.HostTriple);
  if (!HostTriple.isNVPTX())
    HostTarget.reset(AllocateTarget(llvm::Triple(Opts.HostTriple), Opts));

  // If no host target, make some guesses about the data layout and return.
  if (!HostTarget) {
    LongWidth = LongAlign = TargetPointerWidth;
    PointerWidth = PointerAlign = TargetPointerWidth;
    switch (TargetPointerWidth) {
    case 32:
      SizeType = TargetInfo::UnsignedInt;
      PtrDiffType = TargetInfo::SignedInt;
      IntPtrType = TargetInfo::SignedInt;
      break;
    case 64:
      SizeType = TargetInfo::UnsignedLong;
      PtrDiffType = TargetInfo::SignedLong;
      IntPtrType = TargetInfo::SignedLong;
      break;
    default:
      llvm_unreachable("TargetPointerWidth must be 32 or 64");
    }
    return;
  }

  // Copy properties from host target.
  PointerWidth = HostTarget->getPointerWidth(/* AddrSpace = */ 0);
  PointerAlign = HostTarget->getPointerAlign(/* AddrSpace = */ 0);
  BoolWidth = HostTarget->getBoolWidth();
  BoolAlign = HostTarget->getBoolAlign();
  IntWidth = HostTarget->getIntWidth();
  IntAlign = HostTarget->getIntAlign();
  HalfWidth = HostTarget->getHalfWidth();
  HalfAlign = HostTarget->getHalfAlign();
  FloatWidth = HostTarget->getFloatWidth();
  FloatAlign = HostTarget->getFloatAlign();
  DoubleWidth = HostTarget->getDoubleWidth();
  DoubleAlign = HostTarget->getDoubleAlign();
  LongWidth = HostTarget->getLongWidth();
  LongAlign = HostTarget->getLongAlign();
  LongLongWidth = HostTarget->getLongLongWidth();
  LongLongAlign = HostTarget->getLongLongAlign();
  MinGlobalAlign = HostTarget->getMinGlobalAlign();
  NewAlign = HostTarget->getNewAlign();
  DefaultAlignForAttributeAligned =
      HostTarget->getDefaultAlignForAttributeAligned();
  SizeType = HostTarget->getSizeType();
  IntMaxType = HostTarget->getIntMaxType();
  PtrDiffType = HostTarget->getPtrDiffType(/* AddrSpace = */ 0);
  IntPtrType = HostTarget->getIntPtrType();
  WCharType = HostTarget->getWCharType();
  WIntType = HostTarget->getWIntType();
  Char16Type = HostTarget->getChar16Type();
  Char32Type = HostTarget->getChar32Type();
  Int64Type = HostTarget->getInt64Type();
  SigAtomicType = HostTarget->getSigAtomicType();
  ProcessIDType = HostTarget->getProcessIDType();

  UseBitFieldTypeAlignment = HostTarget->useBitFieldTypeAlignment();
  UseZeroLengthBitfieldAlignment = HostTarget->useZeroLengthBitfieldAlignment();
  UseExplicitBitFieldAlignment = HostTarget->useExplicitBitFieldAlignment();
  ZeroLengthBitfieldBoundary = HostTarget->getZeroLengthBitfieldBoundary();

  // This is a bit of a lie, but it controls __GCC_ATOMIC_XXX_LOCK_FREE, and
  // we need those macros to be identical on host and device, because (among
  // other things) they affect which standard library classes are defined, and
  // we need all classes to be defined on both the host and device.
  MaxAtomicInlineWidth = HostTarget->getMaxAtomicInlineWidth();

  // Properties intentionally not copied from host:
  // - LargeArrayMinWidth, LargeArrayAlign: Not visible across the
  //   host/device boundary.
  // - SuitableAlign: Not visible across the host/device boundary, and may
  //   correctly be different on host/device, e.g. if host has wider vector
  //   types than device.
  // - LongDoubleWidth, LongDoubleAlign: nvptx's long double type is the same
  //   as its double type, but that's not necessarily true on the host.
  //   TODO: nvcc emits a warning when using long double on device; we should
  //   do the same.
}

ArrayRef<const char *> NVPTXTargetInfo::getGCCRegNames() const {
  return llvm::makeArrayRef(GCCRegNames);
}

bool NVPTXTargetInfo::hasFeature(StringRef Feature) const {
  return llvm::StringSwitch<bool>(Feature)
      .Cases("ptx", "nvptx", true)
      .Case("satom", GPU >= CudaArch::SM_60) // Atomics w/ scope.
      .Default(false);
}

void NVPTXTargetInfo::getTargetDefines(const LangOptions &Opts,
                                       MacroBuilder &Builder) const {
  Builder.defineMacro("__PTX__");
  Builder.defineMacro("__NVPTX__");
  if (Opts.CUDAIsDevice) {
    // Set __CUDA_ARCH__ for the GPU specified.
    std::string CUDAArchCode = [this] {
      switch (GPU) {
      case CudaArch::UNKNOWN:
        assert(false && "No GPU arch when compiling CUDA device code.");
        return "";
      case CudaArch::SM_20:
        return "200";
      case CudaArch::SM_21:
        return "210";
      case CudaArch::SM_30:
        return "300";
      case CudaArch::SM_32:
        return "320";
      case CudaArch::SM_35:
        return "350";
      case CudaArch::SM_37:
        return "370";
      case CudaArch::SM_50:
        return "500";
      case CudaArch::SM_52:
        return "520";
      case CudaArch::SM_53:
        return "530";
      case CudaArch::SM_60:
        return "600";
      case CudaArch::SM_61:
        return "610";
      case CudaArch::SM_62:
        return "620";
      case CudaArch::SM_70:
        return "700";
      }
      llvm_unreachable("unhandled CudaArch");
    }();
    Builder.defineMacro("__CUDA_ARCH__", CUDAArchCode);
  }
}

ArrayRef<Builtin::Info> NVPTXTargetInfo::getTargetBuiltins() const {
  return llvm::makeArrayRef(BuiltinInfo, clang::NVPTX::LastTSBuiltin -
                                             Builtin::FirstTSBuiltin);
}