r275645 - [CUDA][OpenMP] Create generic offload action

Richard Smith via cfe-commits cfe-commits at lists.llvm.org
Mon Jul 18 14:45:44 PDT 2016


On Fri, Jul 15, 2016 at 4:13 PM, Samuel Antao via cfe-commits <
cfe-commits at lists.llvm.org> wrote:

> Author: sfantao
> Date: Fri Jul 15 18:13:27 2016
> New Revision: 275645
>
> URL: http://llvm.org/viewvc/llvm-project?rev=275645&view=rev
> Log:
> [CUDA][OpenMP] Create generic offload action
>
> Summary:
> This patch replaces the CUDA specific action by a generic offload action.
> The offload action may have multiple dependences classier in “host” and
> “device”. The way this generic offloading action is used is very similar to
> what is done today by the CUDA implementation: it is used to set a specific
> toolchain and architecture to its dependences during the generation of jobs.
>
> This patch also proposes propagating the offloading information through
> the action graph so that that information can be easily retrieved at any
> time during the generation of commands. This allows e.g. the "clang tool”
> to evaluate whether CUDA should be supported for the device or host and
> ptas to easily retrieve the target architecture.
>
> This is an example of how the action graphs would look like (compilation
> of a single CUDA file with two GPU architectures)
> ```
> 0: input, "cudatests.cu", cuda, (host-cuda)
> 1: preprocessor, {0}, cuda-cpp-output, (host-cuda)
> 2: compiler, {1}, ir, (host-cuda)
> 3: input, "cudatests.cu", cuda, (device-cuda, sm_35)
> 4: preprocessor, {3}, cuda-cpp-output, (device-cuda, sm_35)
> 5: compiler, {4}, ir, (device-cuda, sm_35)
> 6: backend, {5}, assembler, (device-cuda, sm_35)
> 7: assembler, {6}, object, (device-cuda, sm_35)
> 8: offload, "device-cuda (nvptx64-nvidia-cuda:sm_35)" {7}, object
> 9: offload, "device-cuda (nvptx64-nvidia-cuda:sm_35)" {6}, assembler
> 10: input, "cudatests.cu", cuda, (device-cuda, sm_37)
> 11: preprocessor, {10}, cuda-cpp-output, (device-cuda, sm_37)
> 12: compiler, {11}, ir, (device-cuda, sm_37)
> 13: backend, {12}, assembler, (device-cuda, sm_37)
> 14: assembler, {13}, object, (device-cuda, sm_37)
> 15: offload, "device-cuda (nvptx64-nvidia-cuda:sm_37)" {14}, object
> 16: offload, "device-cuda (nvptx64-nvidia-cuda:sm_37)" {13}, assembler
> 17: linker, {8, 9, 15, 16}, cuda-fatbin, (device-cuda)
> 18: offload, "host-cuda (powerpc64le-unknown-linux-gnu)" {2}, "device-cuda
> (nvptx64-nvidia-cuda)" {17}, ir
> 19: backend, {18}, assembler
> 20: assembler, {19}, object
> 21: input, "cuda", object
> 22: input, "cudart", object
> 23: linker, {20, 21, 22}, image
> ```
> The changes in this patch pass the existent regression tests (keeps the
> existent functionality) and resulting binaries execute correctly in a
> Power8+K40 machine.
>
> Reviewers: echristo, hfinkel, jlebar, ABataev, tra
>
> Subscribers: guansong, andreybokhanko, tcramer, mkuron, cfe-commits,
> arpith-jacob, carlo.bertolli, caomhin
>
> Differential Revision: https://reviews.llvm.org/D18171
>
> Added:
>     cfe/trunk/test/Driver/cuda_phases.cu
> Modified:
>     cfe/trunk/include/clang/Driver/Action.h
>     cfe/trunk/include/clang/Driver/Compilation.h
>     cfe/trunk/include/clang/Driver/Driver.h
>     cfe/trunk/lib/Driver/Action.cpp
>     cfe/trunk/lib/Driver/Driver.cpp
>     cfe/trunk/lib/Driver/ToolChain.cpp
>     cfe/trunk/lib/Driver/Tools.cpp
>     cfe/trunk/lib/Driver/Tools.h
>     cfe/trunk/lib/Frontend/CreateInvocationFromCommandLine.cpp
>
> Modified: cfe/trunk/include/clang/Driver/Action.h
> URL:
> http://llvm.org/viewvc/llvm-project/cfe/trunk/include/clang/Driver/Action.h?rev=275645&r1=275644&r2=275645&view=diff
>
> ==============================================================================
> --- cfe/trunk/include/clang/Driver/Action.h (original)
> +++ cfe/trunk/include/clang/Driver/Action.h Fri Jul 15 18:13:27 2016
> @@ -13,6 +13,7 @@
>  #include "clang/Basic/Cuda.h"
>  #include "clang/Driver/Types.h"
>  #include "clang/Driver/Util.h"
> +#include "llvm/ADT/STLExtras.h"
>  #include "llvm/ADT/SmallVector.h"
>
>  namespace llvm {
> @@ -27,6 +28,8 @@ namespace opt {
>  namespace clang {
>  namespace driver {
>
> +class ToolChain;
> +
>  /// Action - Represent an abstract compilation step to perform.
>  ///
>  /// An action represents an edge in the compilation graph; typically
> @@ -50,8 +53,7 @@ public:
>    enum ActionClass {
>      InputClass = 0,
>      BindArchClass,
> -    CudaDeviceClass,
> -    CudaHostClass,
> +    OffloadClass,
>      PreprocessJobClass,
>      PrecompileJobClass,
>      AnalyzeJobClass,
> @@ -65,17 +67,13 @@ public:
>      VerifyDebugInfoJobClass,
>      VerifyPCHJobClass,
>
> -    JobClassFirst=PreprocessJobClass,
> -    JobClassLast=VerifyPCHJobClass
> +    JobClassFirst = PreprocessJobClass,
> +    JobClassLast = VerifyPCHJobClass
>    };
>
>    // The offloading kind determines if this action is binded to a
> particular
>    // programming model. Each entry reserves one bit. We also have a
> special kind
>    // to designate the host offloading tool chain.
> -  //
> -  // FIXME: This is currently used to indicate that tool chains are used
> in a
> -  // given programming, but will be used here as well once a generic
> offloading
> -  // action is implemented.
>    enum OffloadKind {
>      OFK_None = 0x00,
>      // The host offloading tool chain.
> @@ -95,6 +93,19 @@ private:
>    ActionList Inputs;
>
>  protected:
> +  ///
> +  /// Offload information.
> +  ///
> +
> +  /// The host offloading kind - a combination of kinds encoded in a mask.
> +  /// Multiple programming models may be supported simultaneously by the
> same
> +  /// host.
> +  unsigned ActiveOffloadKindMask = 0u;
> +  /// Offloading kind of the device.
> +  OffloadKind OffloadingDeviceKind = OFK_None;
> +  /// The Offloading architecture associated with this action.
> +  const char *OffloadingArch = nullptr;
> +
>    Action(ActionClass Kind, types::ID Type) : Action(Kind, ActionList(),
> Type) {}
>    Action(ActionClass Kind, Action *Input, types::ID Type)
>        : Action(Kind, ActionList({Input}), Type) {}
> @@ -124,6 +135,40 @@ public:
>    input_const_range inputs() const {
>      return input_const_range(input_begin(), input_end());
>    }
> +
> +  /// Return a string containing the offload kind of the action.
> +  std::string getOffloadingKindPrefix() const;
> +  /// Return a string that can be used as prefix in order to generate
> unique
> +  /// files for each offloading kind.
> +  std::string getOffloadingFileNamePrefix(StringRef NormalizedTriple)
> const;
> +
> +  /// Set the device offload info of this action and propagate it to its
> +  /// dependences.
> +  void propagateDeviceOffloadInfo(OffloadKind OKind, const char *OArch);
> +  /// Append the host offload info of this action and propagate it to its
> +  /// dependences.
> +  void propagateHostOffloadInfo(unsigned OKinds, const char *OArch);
> +  /// Set the offload info of this action to be the same as the provided
> action,
> +  /// and propagate it to its dependences.
> +  void propagateOffloadInfo(const Action *A);
> +
> +  unsigned getOffloadingHostActiveKinds() const {
> +    return ActiveOffloadKindMask;
> +  }
> +  OffloadKind getOffloadingDeviceKind() const { return
> OffloadingDeviceKind; }
> +  const char *getOffloadingArch() const { return OffloadingArch; }
> +
> +  /// Check if this action have any offload kinds. Note that host offload
> kinds
> +  /// are only set if the action is a dependence to a host offload action.
> +  bool isHostOffloading(OffloadKind OKind) const {
> +    return ActiveOffloadKindMask & OKind;
> +  }
> +  bool isDeviceOffloading(OffloadKind OKind) const {
> +    return OffloadingDeviceKind == OKind;
> +  }
> +  bool isOffloading(OffloadKind OKind) const {
> +    return isHostOffloading(OKind) || isDeviceOffloading(OKind);
> +  }
>  };
>
>  class InputAction : public Action {
> @@ -156,39 +201,126 @@ public:
>    }
>  };
>
> -class CudaDeviceAction : public Action {
> +/// An offload action combines host or/and device actions according to the
> +/// programming model implementation needs and propagates the offloading
> kind to
> +/// its dependences.
> +class OffloadAction final : public Action {
>    virtual void anchor();
>
> -  const CudaArch GpuArch;
> -
> -  /// True when action results are not consumed by the host action (e.g
> when
> -  /// -fsyntax-only or --cuda-device-only options are used).
> -  bool AtTopLevel;
> -
>  public:
> -  CudaDeviceAction(Action *Input, CudaArch Arch, bool AtTopLevel);
> +  /// Type used to communicate device actions. It associates bound
> architecture,
> +  /// toolchain, and offload kind to each action.
> +  class DeviceDependences final {
> +  public:
> +    typedef SmallVector<const ToolChain *, 3> ToolChainList;
> +    typedef SmallVector<const char *, 3> BoundArchList;
> +    typedef SmallVector<OffloadKind, 3> OffloadKindList;
> +
> +  private:
> +    // Lists that keep the information for each dependency. All the lists
> are
> +    // meant to be updated in sync. We are adopting separate lists
> instead of a
> +    // list of structs, because that simplifies forwarding the actions
> list to
> +    // initialize the inputs of the base Action class.
> +
> +    /// The dependence actions.
> +    ActionList DeviceActions;
> +    /// The offloading toolchains that should be used with the action.
> +    ToolChainList DeviceToolChains;
> +    /// The architectures that should be used with this action.
> +    BoundArchList DeviceBoundArchs;
> +    /// The offload kind of each dependence.
> +    OffloadKindList DeviceOffloadKinds;
> +
> +  public:
> +    /// Add a action along with the associated toolchain, bound arch, and
> +    /// offload kind.
> +    void add(Action &A, const ToolChain &TC, const char *BoundArch,
> +             OffloadKind OKind);
> +
> +    /// Get each of the individual arrays.
> +    const ActionList &getActions() const { return DeviceActions; };
> +    const ToolChainList &getToolChains() const { return DeviceToolChains;
> };
> +    const BoundArchList &getBoundArchs() const { return DeviceBoundArchs;
> };
> +    const OffloadKindList &getOffloadKinds() const {
> +      return DeviceOffloadKinds;
> +    };
> +  };
>
> -  /// Get the CUDA GPU architecture to which this Action corresponds.
> Returns
> -  /// UNKNOWN if this Action corresponds to multiple architectures.
> -  CudaArch getGpuArch() const { return GpuArch; }
> +  /// Type used to communicate host actions. It associates bound
> architecture,
> +  /// toolchain, and offload kinds to the host action.
> +  class HostDependence final {
> +    /// The dependence action.
> +    Action &HostAction;
> +    /// The offloading toolchain that should be used with the action.
> +    const ToolChain &HostToolChain;
> +    /// The architectures that should be used with this action.
> +    const char *HostBoundArch = nullptr;
> +    /// The offload kind of each dependence.
> +    unsigned HostOffloadKinds = 0u;
> +
> +  public:
> +    HostDependence(Action &A, const ToolChain &TC, const char *BoundArch,
> +                   const unsigned OffloadKinds)
> +        : HostAction(A), HostToolChain(TC), HostBoundArch(BoundArch),
> +          HostOffloadKinds(OffloadKinds){};
> +    /// Constructor version that obtains the offload kinds from the device
> +    /// dependencies.
> +    HostDependence(Action &A, const ToolChain &TC, const char *BoundArch,
> +                   const DeviceDependences &DDeps);
> +    Action *getAction() const { return &HostAction; };
> +    const ToolChain *getToolChain() const { return &HostToolChain; };
> +    const char *getBoundArch() const { return HostBoundArch; };
> +    unsigned getOffloadKinds() const { return HostOffloadKinds; };
> +  };
>
> -  bool isAtTopLevel() const { return AtTopLevel; }
> +  typedef llvm::function_ref<void(Action *, const ToolChain *, const char
> *)>
> +      OffloadActionWorkTy;
>
> -  static bool classof(const Action *A) {
> -    return A->getKind() == CudaDeviceClass;
> -  }
> -};
> +private:
> +  /// The host offloading toolchain that should be used with the action.
> +  const ToolChain *HostTC = nullptr;
>
> -class CudaHostAction : public Action {
> -  virtual void anchor();
> -  ActionList DeviceActions;
> +  /// The tool chains associated with the list of actions.
> +  DeviceDependences::ToolChainList DevToolChains;
>
>  public:
> -  CudaHostAction(Action *Input, const ActionList &DeviceActions);
> -
> -  const ActionList &getDeviceActions() const { return DeviceActions; }
> +  OffloadAction(const HostDependence &HDep);
> +  OffloadAction(const DeviceDependences &DDeps, types::ID Ty);
> +  OffloadAction(const HostDependence &HDep, const DeviceDependences
> &DDeps);
> +
> +  /// Execute the work specified in \a Work on the host dependence.
> +  void doOnHostDependence(const OffloadActionWorkTy &Work) const;
> +
> +  /// Execute the work specified in \a Work on each device dependence.
> +  void doOnEachDeviceDependence(const OffloadActionWorkTy &Work) const;
> +
> +  /// Execute the work specified in \a Work on each dependence.
> +  void doOnEachDependence(const OffloadActionWorkTy &Work) const;
> +
> +  /// Execute the work specified in \a Work on each host or device
> dependence if
> +  /// \a IsHostDependenceto is true or false, respectively.
> +  void doOnEachDependence(bool IsHostDependence,
> +                          const OffloadActionWorkTy &Work) const;
> +
> +  /// Return true if the action has a host dependence.
> +  bool hasHostDependence() const;
> +
> +  /// Return the host dependence of this action. This function is only
> expected
> +  /// to be called if the host dependence exists.
> +  Action *getHostDependence() const;
> +
> +  /// Return true if the action has a single device dependence. If \a
> +  /// DoNotConsiderHostActions is set, ignore the host dependence, if
> any, while
> +  /// accounting for the number of dependences.
> +  bool hasSingleDeviceDependence(bool DoNotConsiderHostActions = false)
> const;
> +
> +  /// Return the single device dependence of this action. This function
> is only
> +  /// expected to be called if a single device dependence exists. If \a
> +  /// DoNotConsiderHostActions is set, a host dependence is allowed.
> +  Action *
> +  getSingleDeviceDependence(bool DoNotConsiderHostActions = false) const;
>
> -  static bool classof(const Action *A) { return A->getKind() ==
> CudaHostClass; }
> +  static bool classof(const Action *A) { return A->getKind() ==
> OffloadClass; }
>  };
>
>  class JobAction : public Action {
>
> Modified: cfe/trunk/include/clang/Driver/Compilation.h
> URL:
> http://llvm.org/viewvc/llvm-project/cfe/trunk/include/clang/Driver/Compilation.h?rev=275645&r1=275644&r2=275645&view=diff
>
> ==============================================================================
> --- cfe/trunk/include/clang/Driver/Compilation.h (original)
> +++ cfe/trunk/include/clang/Driver/Compilation.h Fri Jul 15 18:13:27 2016
> @@ -98,12 +98,7 @@ public:
>    const Driver &getDriver() const { return TheDriver; }
>
>    const ToolChain &getDefaultToolChain() const { return DefaultToolChain;
> }
> -  const ToolChain *getOffloadingHostToolChain() const {
> -    auto It = OrderedOffloadingToolchains.find(Action::OFK_Host);
> -    if (It != OrderedOffloadingToolchains.end())
> -      return It->second;
> -    return nullptr;
> -  }
> +
>    unsigned isOffloadingHostKind(Action::OffloadKind Kind) const {
>      return ActiveOffloadMask & Kind;
>    }
> @@ -121,8 +116,8 @@ public:
>      return OrderedOffloadingToolchains.equal_range(Kind);
>    }
>
> -  // Return an offload toolchain of the provided kind. Only one is
> expected to
> -  // exist.
> +  /// Return an offload toolchain of the provided kind. Only one is
> expected to
> +  /// exist.
>    template <Action::OffloadKind Kind>
>    const ToolChain *getSingleOffloadToolChain() const {
>      auto TCs = getOffloadToolChains<Kind>();
>
> Modified: cfe/trunk/include/clang/Driver/Driver.h
> URL:
> http://llvm.org/viewvc/llvm-project/cfe/trunk/include/clang/Driver/Driver.h?rev=275645&r1=275644&r2=275645&view=diff
>
> ==============================================================================
> --- cfe/trunk/include/clang/Driver/Driver.h (original)
> +++ cfe/trunk/include/clang/Driver/Driver.h Fri Jul 15 18:13:27 2016
> @@ -394,12 +394,13 @@ public:
>    /// BuildJobsForAction - Construct the jobs to perform for the action
> \p A and
>    /// return an InputInfo for the result of running \p A.  Will only
> construct
>    /// jobs for a given (Action, ToolChain, BoundArch) tuple once.
> -  InputInfo BuildJobsForAction(Compilation &C, const Action *A,
> -                               const ToolChain *TC, const char *BoundArch,
> -                               bool AtTopLevel, bool MultipleArchs,
> -                               const char *LinkingOutput,
> -                               std::map<std::pair<const Action *,
> std::string>,
> -                                        InputInfo> &CachedResults) const;
> +  InputInfo
> +  BuildJobsForAction(Compilation &C, const Action *A, const ToolChain *TC,
> +                     const char *BoundArch, bool AtTopLevel, bool
> MultipleArchs,
> +                     const char *LinkingOutput,
> +                     std::map<std::pair<const Action *, std::string>,
> InputInfo>
> +                         &CachedResults,
> +                     bool BuildForOffloadDevice) const;
>
>    /// Returns the default name for linked images (e.g., "a.out").
>    const char *getDefaultImageName() const;
> @@ -415,12 +416,11 @@ public:
>    /// \param BoundArch - The bound architecture.
>    /// \param AtTopLevel - Whether this is a "top-level" action.
>    /// \param MultipleArchs - Whether multiple -arch options were supplied.
> -  const char *GetNamedOutputPath(Compilation &C,
> -                                 const JobAction &JA,
> -                                 const char *BaseInput,
> -                                 const char *BoundArch,
> -                                 bool AtTopLevel,
> -                                 bool MultipleArchs) const;
> +  /// \param NormalizedTriple - The normalized triple of the relevant
> target.
> +  const char *GetNamedOutputPath(Compilation &C, const JobAction &JA,
> +                                 const char *BaseInput, const char
> *BoundArch,
> +                                 bool AtTopLevel, bool MultipleArchs,
> +                                 StringRef NormalizedTriple) const;
>
>    /// GetTemporaryPath - Return the pathname of a temporary file to use
>    /// as part of compilation; the file will have the given prefix and
> suffix.
> @@ -467,7 +467,8 @@ private:
>        const char *BoundArch, bool AtTopLevel, bool MultipleArchs,
>        const char *LinkingOutput,
>        std::map<std::pair<const Action *, std::string>, InputInfo>
> -          &CachedResults) const;
> +          &CachedResults,
> +      bool BuildForOffloadDevice) const;
>
>  public:
>    /// GetReleaseVersion - Parse (([0-9]+)(.([0-9]+)(.([0-9]+)?))?)? and
>
> Modified: cfe/trunk/lib/Driver/Action.cpp
> URL:
> http://llvm.org/viewvc/llvm-project/cfe/trunk/lib/Driver/Action.cpp?rev=275645&r1=275644&r2=275645&view=diff
>
> ==============================================================================
> --- cfe/trunk/lib/Driver/Action.cpp (original)
> +++ cfe/trunk/lib/Driver/Action.cpp Fri Jul 15 18:13:27 2016
> @@ -8,6 +8,7 @@
>
>  //===----------------------------------------------------------------------===//
>
>  #include "clang/Driver/Action.h"
> +#include "clang/Driver/ToolChain.h"
>  #include "llvm/ADT/StringSwitch.h"
>  #include "llvm/Support/ErrorHandling.h"
>  #include "llvm/Support/Regex.h"
> @@ -21,8 +22,8 @@ const char *Action::getClassName(ActionC
>    switch (AC) {
>    case InputClass: return "input";
>    case BindArchClass: return "bind-arch";
> -  case CudaDeviceClass: return "cuda-device";
> -  case CudaHostClass: return "cuda-host";
> +  case OffloadClass:
> +    return "offload";
>    case PreprocessJobClass: return "preprocessor";
>    case PrecompileJobClass: return "precompiler";
>    case AnalyzeJobClass: return "analyzer";
> @@ -40,6 +41,82 @@ const char *Action::getClassName(ActionC
>    llvm_unreachable("invalid class");
>  }
>
> +void Action::propagateDeviceOffloadInfo(OffloadKind OKind, const char
> *OArch) {
> +  // Offload action set its own kinds on their dependences.
> +  if (Kind == OffloadClass)
> +    return;
> +
> +  assert((OffloadingDeviceKind == OKind || OffloadingDeviceKind ==
> OFK_None) &&
> +         "Setting device kind to a different device??");
> +  assert(!ActiveOffloadKindMask && "Setting a device kind in a host
> action??");
> +  OffloadingDeviceKind = OKind;
> +  OffloadingArch = OArch;
> +
> +  for (auto *A : Inputs)
> +    A->propagateDeviceOffloadInfo(OffloadingDeviceKind, OArch);
> +}
> +
> +void Action::propagateHostOffloadInfo(unsigned OKinds, const char *OArch)
> {
> +  // Offload action set its own kinds on their dependences.
> +  if (Kind == OffloadClass)
> +    return;
> +
> +  assert(OffloadingDeviceKind == OFK_None &&
> +         "Setting a host kind in a device action.");
> +  ActiveOffloadKindMask |= OKinds;
> +  OffloadingArch = OArch;
> +
> +  for (auto *A : Inputs)
> +    A->propagateHostOffloadInfo(ActiveOffloadKindMask, OArch);
> +}
> +
> +void Action::propagateOffloadInfo(const Action *A) {
> +  if (unsigned HK = A->getOffloadingHostActiveKinds())
> +    propagateHostOffloadInfo(HK, A->getOffloadingArch());
> +  else
> +    propagateDeviceOffloadInfo(A->getOffloadingDeviceKind(),
> +                               A->getOffloadingArch());
> +}
> +
> +std::string Action::getOffloadingKindPrefix() const {
> +  switch (OffloadingDeviceKind) {
> +  case OFK_None:
> +    break;
> +  case OFK_Host:
> +    llvm_unreachable("Host kind is not an offloading device kind.");
> +    break;
> +  case OFK_Cuda:
> +    return "device-cuda";
> +
> +    // TODO: Add other programming models here.
> +  }
> +
> +  if (!ActiveOffloadKindMask)
> +    return "";
> +
> +  std::string Res("host");
> +  if (ActiveOffloadKindMask & OFK_Cuda)
> +    Res += "-cuda";
> +
> +  // TODO: Add other programming models here.
> +
> +  return Res;
> +}
> +
> +std::string
> +Action::getOffloadingFileNamePrefix(StringRef NormalizedTriple) const {
> +  // A file prefix is only generated for device actions and consists of
> the
> +  // offload kind and triple.
> +  if (!OffloadingDeviceKind)
> +    return "";
> +
> +  std::string Res("-");
> +  Res += getOffloadingKindPrefix();
> +  Res += "-";
> +  Res += NormalizedTriple;
> +  return Res;
> +}
> +
>  void InputAction::anchor() {}
>
>  InputAction::InputAction(const Arg &_Input, types::ID _Type)
> @@ -51,16 +128,138 @@ void BindArchAction::anchor() {}
>  BindArchAction::BindArchAction(Action *Input, const char *_ArchName)
>      : Action(BindArchClass, Input), ArchName(_ArchName) {}
>
> -void CudaDeviceAction::anchor() {}
> +void OffloadAction::anchor() {}
> +
> +OffloadAction::OffloadAction(const HostDependence &HDep)
> +    : Action(OffloadClass, HDep.getAction()), HostTC(HDep.getToolChain())
> {
> +  OffloadingArch = HDep.getBoundArch();
> +  ActiveOffloadKindMask = HDep.getOffloadKinds();
> +  HDep.getAction()->propagateHostOffloadInfo(HDep.getOffloadKinds(),
> +                                             HDep.getBoundArch());
> +};
> +
> +OffloadAction::OffloadAction(const DeviceDependences &DDeps, types::ID Ty)
> +    : Action(OffloadClass, DDeps.getActions(), Ty),
> +      DevToolChains(DDeps.getToolChains()) {
> +  auto &OKinds = DDeps.getOffloadKinds();
> +  auto &BArchs = DDeps.getBoundArchs();
> +
> +  // If all inputs agree on the same kind, use it also for this action.
> +  if (llvm::all_of(OKinds, [&](OffloadKind K) { return K ==
> OKinds.front(); }))
> +    OffloadingDeviceKind = OKinds.front();
> +
> +  // If we have a single dependency, inherit the architecture from it.
> +  if (OKinds.size() == 1)
> +    OffloadingArch = BArchs.front();
> +
> +  // Propagate info to the dependencies.
> +  for (unsigned i = 0, e = getInputs().size(); i != e; ++i)
> +    getInputs()[i]->propagateDeviceOffloadInfo(OKinds[i], BArchs[i]);
> +}
> +
> +OffloadAction::OffloadAction(const HostDependence &HDep,
> +                             const DeviceDependences &DDeps)
> +    : Action(OffloadClass, HDep.getAction()), HostTC(HDep.getToolChain()),
> +      DevToolChains(DDeps.getToolChains()) {
> +  // We use the kinds of the host dependence for this action.
> +  OffloadingArch = HDep.getBoundArch();
> +  ActiveOffloadKindMask = HDep.getOffloadKinds();
> +  HDep.getAction()->propagateHostOffloadInfo(HDep.getOffloadKinds(),
> +                                             HDep.getBoundArch());
> +
> +  // Add device inputs and propagate info to the device actions. Do work
> only if
> +  // we have dependencies.
> +  for (unsigned i = 0, e = DDeps.getActions().size(); i != e; ++i)
> +    if (auto *A = DDeps.getActions()[i]) {
> +      getInputs().push_back(A);
> +      A->propagateDeviceOffloadInfo(DDeps.getOffloadKinds()[i],
> +                                    DDeps.getBoundArchs()[i]);
> +    }
> +}
> +
> +void OffloadAction::doOnHostDependence(const OffloadActionWorkTy &Work)
> const {
> +  if (!HostTC)
> +    return;
> +  assert(!getInputs().empty() && "No dependencies for offload action??");
> +  auto *A = getInputs().front();
> +  Work(A, HostTC, A->getOffloadingArch());
> +}
>
> -CudaDeviceAction::CudaDeviceAction(Action *Input, clang::CudaArch Arch,
> -                                   bool AtTopLevel)
> -    : Action(CudaDeviceClass, Input), GpuArch(Arch),
> AtTopLevel(AtTopLevel) {}
> +void OffloadAction::doOnEachDeviceDependence(
> +    const OffloadActionWorkTy &Work) const {
> +  auto I = getInputs().begin();
> +  auto E = getInputs().end();
> +  if (I == E)
> +    return;
> +
> +  // We expect to have the same number of input dependences and device
> tool
> +  // chains, except if we also have a host dependence. In that case we
> have one
> +  // more dependence than we have device tool chains.
> +  assert(getInputs().size() == DevToolChains.size() + (HostTC ? 1 : 0) &&
> +         "Sizes of action dependences and toolchains are not
> consistent!");
> +
> +  // Skip host action
> +  if (HostTC)
> +    ++I;
> +
> +  auto TI = DevToolChains.begin();
> +  for (; I != E; ++I, ++TI)
> +    Work(*I, *TI, (*I)->getOffloadingArch());
> +}
> +
> +void OffloadAction::doOnEachDependence(const OffloadActionWorkTy &Work)
> const {
> +  doOnHostDependence(Work);
> +  doOnEachDeviceDependence(Work);
> +}
> +
> +void OffloadAction::doOnEachDependence(bool IsHostDependence,
> +                                       const OffloadActionWorkTy &Work)
> const {
> +  if (IsHostDependence)
> +    doOnHostDependence(Work);
> +  else
> +    doOnEachDeviceDependence(Work);
> +}
>
> -void CudaHostAction::anchor() {}
> +bool OffloadAction::hasHostDependence() const { return HostTC != nullptr;
> }
>
> -CudaHostAction::CudaHostAction(Action *Input, const ActionList
> &DeviceActions)
> -    : Action(CudaHostClass, Input), DeviceActions(DeviceActions) {}
> +Action *OffloadAction::getHostDependence() const {
> +  assert(hasHostDependence() && "Host dependence does not exist!");
> +  assert(!getInputs().empty() && "No dependencies for offload action??");
> +  return HostTC ? getInputs().front() : nullptr;
> +}
> +
> +bool OffloadAction::hasSingleDeviceDependence(
> +    bool DoNotConsiderHostActions) const {
> +  if (DoNotConsiderHostActions)
> +    return getInputs().size() == (HostTC ? 2 : 1);
> +  return !HostTC && getInputs().size() == 1;
> +}
> +
> +Action *
> +OffloadAction::getSingleDeviceDependence(bool DoNotConsiderHostActions)
> const {
> +  assert(hasSingleDeviceDependence(DoNotConsiderHostActions) &&
> +         "Single device dependence does not exist!");
> +  // The previous assert ensures the number of entries in getInputs() is
> +  // consistent with what we are doing here.
> +  return HostTC ? getInputs()[1] : getInputs().front();
> +}
> +
> +void OffloadAction::DeviceDependences::add(Action &A, const ToolChain &TC,
> +                                           const char *BoundArch,
> +                                           OffloadKind OKind) {
> +  DeviceActions.push_back(&A);
> +  DeviceToolChains.push_back(&TC);
> +  DeviceBoundArchs.push_back(BoundArch);
> +  DeviceOffloadKinds.push_back(OKind);
> +}
> +
> +OffloadAction::HostDependence::HostDependence(Action &A, const ToolChain
> &TC,
> +                                              const char *BoundArch,
> +                                              const DeviceDependences
> &DDeps)
> +    : HostAction(A), HostToolChain(TC), HostBoundArch(BoundArch) {
> +  for (auto K : DDeps.getOffloadKinds())
> +    HostOffloadKinds |= K;
> +}
>
>  void JobAction::anchor() {}
>
>
> Modified: cfe/trunk/lib/Driver/Driver.cpp
> URL:
> http://llvm.org/viewvc/llvm-project/cfe/trunk/lib/Driver/Driver.cpp?rev=275645&r1=275644&r2=275645&view=diff
>
> ==============================================================================
> --- cfe/trunk/lib/Driver/Driver.cpp (original)
> +++ cfe/trunk/lib/Driver/Driver.cpp Fri Jul 15 18:13:27 2016
> @@ -435,7 +435,9 @@ void Driver::CreateOffloadingDeviceToolC
>        })) {
>      const ToolChain &TC = getToolChain(
>          C.getInputArgs(),
> -
> llvm::Triple(C.getOffloadingHostToolChain()->getTriple().isArch64Bit()
> +        llvm::Triple(C.getSingleOffloadToolChain<Action::OFK_Host>()
> +                             ->getTriple()
> +                             .isArch64Bit()
>                           ? "nvptx64-nvidia-cuda"
>                           : "nvptx-nvidia-cuda"));
>      C.addOffloadDeviceToolChain(&TC, Action::OFK_Cuda);
> @@ -1022,19 +1024,33 @@ static unsigned PrintActions1(const Comp
>    } else if (BindArchAction *BIA = dyn_cast<BindArchAction>(A)) {
>      os << '"' << BIA->getArchName() << '"' << ", {"
>         << PrintActions1(C, *BIA->input_begin(), Ids) << "}";
> -  } else if (CudaDeviceAction *CDA = dyn_cast<CudaDeviceAction>(A)) {
> -    CudaArch Arch = CDA->getGpuArch();
> -    if (Arch != CudaArch::UNKNOWN)
> -      os << "'" << CudaArchToString(Arch) << "', ";
> -    os << "{" << PrintActions1(C, *CDA->input_begin(), Ids) << "}";
> +  } else if (OffloadAction *OA = dyn_cast<OffloadAction>(A)) {
> +    bool IsFirst = true;
> +    OA->doOnEachDependence(
> +        [&](Action *A, const ToolChain *TC, const char *BoundArch) {
> +          // E.g. for two CUDA device dependences whose bound arch is
> sm_20 and
> +          // sm_35 this will generate:
> +          // "cuda-device" (nvptx64-nvidia-cuda:sm_20) {#ID},
> "cuda-device"
> +          // (nvptx64-nvidia-cuda:sm_35) {#ID}
> +          if (!IsFirst)
> +            os << ", ";
> +          os << '"';
> +          if (TC)
> +            os << A->getOffloadingKindPrefix();
> +          else
> +            os << "host";
> +          os << " (";
> +          os << TC->getTriple().normalize();
> +
> +          if (BoundArch)
> +            os << ":" << BoundArch;
> +          os << ")";
> +          os << '"';
> +          os << " {" << PrintActions1(C, A, Ids) << "}";
> +          IsFirst = false;
> +        });
>    } else {
> -    const ActionList *AL;
> -    if (CudaHostAction *CHA = dyn_cast<CudaHostAction>(A)) {
> -      os << "{" << PrintActions1(C, *CHA->input_begin(), Ids) << "}"
> -         << ", gpu binaries ";
> -      AL = &CHA->getDeviceActions();
> -    } else
> -      AL = &A->getInputs();
> +    const ActionList *AL = &A->getInputs();
>
>      if (AL->size()) {
>        const char *Prefix = "{";
> @@ -1047,10 +1063,24 @@ static unsigned PrintActions1(const Comp
>        os << "{}";
>    }
>
> +  // Append offload info for all options other than the offloading action
> +  // itself (e.g. (cuda-device, sm_20) or (cuda-host)).
> +  std::string offload_str;
> +  llvm::raw_string_ostream offload_os(offload_str);
> +  if (!isa<OffloadAction>(A)) {
> +    auto S = A->getOffloadingKindPrefix();
> +    if (!S.empty()) {
> +      offload_os << ", (" << S;
> +      if (A->getOffloadingArch())
> +        offload_os << ", " << A->getOffloadingArch();
> +      offload_os << ")";
> +    }
> +  }
> +
>    unsigned Id = Ids.size();
>    Ids[A] = Id;
>    llvm::errs() << Id << ": " << os.str() << ", "
> -               << types::getTypeName(A->getType()) << "\n";
> +               << types::getTypeName(A->getType()) << offload_os.str() <<
> "\n";
>
>    return Id;
>  }
> @@ -1378,8 +1408,12 @@ static Action *buildCudaActions(Compilat
>        PartialCompilationArg &&
>
>  PartialCompilationArg->getOption().matches(options::OPT_cuda_device_only);
>
> -  if (CompileHostOnly)
> -    return C.MakeAction<CudaHostAction>(HostAction, ActionList());
> +  if (CompileHostOnly) {
> +    OffloadAction::HostDependence HDep(
> +        *HostAction, *C.getSingleOffloadToolChain<Action::OFK_Host>(),
> +        /*BoundArch=*/nullptr, Action::OFK_Cuda);
> +    return C.MakeAction<OffloadAction>(HDep);
> +  }
>
>    // Collect all cuda_gpu_arch parameters, removing duplicates.
>    SmallVector<CudaArch, 4> GpuArchList;
> @@ -1408,8 +1442,6 @@ static Action *buildCudaActions(Compilat
>      CudaDeviceInputs.push_back(std::make_pair(types::TY_CUDA_DEVICE,
> InputArg));
>
>    // Build actions for all device inputs.
> -  assert(C.getSingleOffloadToolChain<Action::OFK_Cuda>() &&
> -         "Missing toolchain for device-side compilation.");
>    ActionList CudaDeviceActions;
>    C.getDriver().BuildActions(C, Args, CudaDeviceInputs,
> CudaDeviceActions);
>    assert(GpuArchList.size() == CudaDeviceActions.size() &&
> @@ -1421,6 +1453,8 @@ static Action *buildCudaActions(Compilat
>          return a->getKind() != Action::AssembleJobClass;
>        });
>
> +  const ToolChain *CudaTC =
> C.getSingleOffloadToolChain<Action::OFK_Cuda>();
> +
>    // Figure out what to do with device actions -- pass them as inputs to
> the
>    // host action or run each of them independently.
>    if (PartialCompilation || CompileDeviceOnly) {
> @@ -1436,10 +1470,13 @@ static Action *buildCudaActions(Compilat
>        return nullptr;
>      }
>
> -    for (unsigned I = 0, E = GpuArchList.size(); I != E; ++I)
> -
> Actions.push_back(C.MakeAction<CudaDeviceAction>(CudaDeviceActions[I],
> -                                                       GpuArchList[I],
> -                                                       /* AtTopLevel */
> true));
> +    for (unsigned I = 0, E = GpuArchList.size(); I != E; ++I) {
> +      OffloadAction::DeviceDependences DDep;
> +      DDep.add(*CudaDeviceActions[I], *CudaTC,
> CudaArchToString(GpuArchList[I]),
> +               Action::OFK_Cuda);
> +      Actions.push_back(
> +          C.MakeAction<OffloadAction>(DDep,
> CudaDeviceActions[I]->getType()));
> +    }
>      // Kill host action in case of device-only compilation.
>      if (CompileDeviceOnly)
>        return nullptr;
> @@ -1459,19 +1496,23 @@ static Action *buildCudaActions(Compilat
>      Action* BackendAction = AssembleAction->getInputs()[0];
>      assert(BackendAction->getType() == types::TY_PP_Asm);
>
> -    for (const auto& A : {AssembleAction, BackendAction}) {
> -      DeviceActions.push_back(C.MakeAction<CudaDeviceAction>(
> -          A, GpuArchList[I], /* AtTopLevel */ false));
> +    for (auto &A : {AssembleAction, BackendAction}) {
> +      OffloadAction::DeviceDependences DDep;
> +      DDep.add(*A, *CudaTC, CudaArchToString(GpuArchList[I]),
> Action::OFK_Cuda);
> +      DeviceActions.push_back(C.MakeAction<OffloadAction>(DDep,
> A->getType()));
>      }
>    }
> -  auto FatbinAction = C.MakeAction<CudaDeviceAction>(
> -      C.MakeAction<LinkJobAction>(DeviceActions, types::TY_CUDA_FATBIN),
> -      CudaArch::UNKNOWN,
> -      /* AtTopLevel = */ false);
> +  auto FatbinAction =
> +      C.MakeAction<LinkJobAction>(DeviceActions, types::TY_CUDA_FATBIN);
> +
>    // Return a new host action that incorporates original host action and
> all
>    // device actions.
> -  return C.MakeAction<CudaHostAction>(std::move(HostAction),
> -                                      ActionList({FatbinAction}));
> +  OffloadAction::HostDependence HDep(
> +      *HostAction, *C.getSingleOffloadToolChain<Action::OFK_Host>(),
> +      /*BoundArch=*/nullptr, Action::OFK_Cuda);
> +  OffloadAction::DeviceDependences DDep;
> +  DDep.add(*FatbinAction, *CudaTC, /*BoundArch=*/nullptr,
> Action::OFK_Cuda);
> +  return C.MakeAction<OffloadAction>(HDep, DDep);
>  }
>
>  void Driver::BuildActions(Compilation &C, DerivedArgList &Args,
> @@ -1580,6 +1621,9 @@ void Driver::BuildActions(Compilation &C
>      YcArg = YuArg = nullptr;
>    }
>
> +  // Track the host offload kinds used on this compilation.
> +  unsigned CompilationActiveOffloadHostKinds = 0u;
> +
>    // Construct the actions to perform.
>    ActionList LinkerInputs;
>
> @@ -1648,6 +1692,9 @@ void Driver::BuildActions(Compilation &C
>              ? phases::Compile
>              : FinalPhase;
>
> +    // Track the host offload kinds used on this input.
> +    unsigned InputActiveOffloadHostKinds = 0u;
> +
>      // Build the pipeline for this file.
>      Action *Current = C.MakeAction<InputAction>(*InputArg, InputType);
>      for (SmallVectorImpl<phases::ID>::iterator i = PL.begin(), e =
> PL.end();
> @@ -1679,21 +1726,36 @@ void Driver::BuildActions(Compilation &C
>          Current = buildCudaActions(C, Args, InputArg, Current, Actions);
>          if (!Current)
>            break;
> +
> +        // We produced a CUDA action for this input, so the host has to
> support
> +        // CUDA.
> +        InputActiveOffloadHostKinds |= Action::OFK_Cuda;
> +        CompilationActiveOffloadHostKinds |= Action::OFK_Cuda;
>        }
>
>        if (Current->getType() == types::TY_Nothing)
>          break;
>      }
>
> -    // If we ended with something, add to the output list.
> -    if (Current)
> +    // If we ended with something, add to the output list. Also,
> propagate the
> +    // offload information to the top-level host action related with the
> current
> +    // input.
> +    if (Current) {
> +      if (InputActiveOffloadHostKinds)
> +        Current->propagateHostOffloadInfo(InputActiveOffloadHostKinds,
> +                                          /*BoundArch=*/nullptr);
>        Actions.push_back(Current);
> +    }
>    }
>
> -  // Add a link action if necessary.
> -  if (!LinkerInputs.empty())
> +  // Add a link action if necessary and propagate the offload information
> for
> +  // the current compilation.
> +  if (!LinkerInputs.empty()) {
>      Actions.push_back(
>          C.MakeAction<LinkJobAction>(LinkerInputs, types::TY_Image));
> +
> Actions.back()->propagateHostOffloadInfo(CompilationActiveOffloadHostKinds,
> +                                             /*BoundArch=*/nullptr);
> +  }
>
>    // If we are linking, claim any options which are obviously only used
> for
>    // compilation.
> @@ -1829,7 +1891,8 @@ void Driver::BuildJobs(Compilation &C) c
>                         /*BoundArch*/ nullptr,
>                         /*AtTopLevel*/ true,
>                         /*MultipleArchs*/ ArchNames.size() > 1,
> -                       /*LinkingOutput*/ LinkingOutput, CachedResults);
> +                       /*LinkingOutput*/ LinkingOutput, CachedResults,
> +                       /*BuildForOffloadDevice*/ false);
>    }
>
>    // If the user passed -Qunused-arguments or there were errors, don't
> warn
> @@ -1878,7 +1941,28 @@ void Driver::BuildJobs(Compilation &C) c
>      }
>    }
>  }
> -
> +/// Collapse an offloading action looking for a job of the given type.
> The input
> +/// action is changed to the input of the collapsed sequence. If we
> effectively
> +/// had a collapse return the corresponding offloading action, otherwise
> return
> +/// null.
> +template <typename T>
> +static OffloadAction *collapseOffloadingAction(Action *&CurAction) {
> +  if (!CurAction)
> +    return nullptr;
> +  if (auto *OA = dyn_cast<OffloadAction>(CurAction)) {
> +    if (OA->hasHostDependence())
> +      if (auto *HDep = dyn_cast<T>(OA->getHostDependence())) {
> +        CurAction = HDep;
> +        return OA;
> +      }
> +    if (OA->hasSingleDeviceDependence())
> +      if (auto *DDep = dyn_cast<T>(OA->getSingleDeviceDependence())) {
> +        CurAction = DDep;
> +        return OA;
> +      }
> +  }
> +  return nullptr;
> +}
>  // Returns a Tool for a given JobAction.  In case the action and its
>  // predecessors can be combined, updates Inputs with the inputs of the
>  // first combined action. If one of the collapsed actions is a
> @@ -1888,34 +1972,39 @@ static const Tool *selectToolForJob(Comp
>                                      bool EmbedBitcode, const ToolChain
> *TC,
>                                      const JobAction *JA,
>                                      const ActionList *&Inputs,
> -                                    const CudaHostAction *&CollapsedCHA) {
> +                                    ActionList &CollapsedOffloadAction) {
>    const Tool *ToolForJob = nullptr;
> -  CollapsedCHA = nullptr;
> +  CollapsedOffloadAction.clear();
>
>    // See if we should look for a compiler with an integrated assembler.
> We match
>    // bottom up, so what we are actually looking for is an assembler job
> with a
>    // compiler input.
>
> +  // Look through offload actions between assembler and backend actions.
> +  Action *BackendJA = (isa<AssembleJobAction>(JA) && Inputs->size() == 1)
> +                          ? *Inputs->begin()
> +                          : nullptr;
> +  auto *BackendOA = collapseOffloadingAction<BackendJobAction>(BackendJA);
> +
>    if (TC->useIntegratedAs() && !SaveTemps &&
>        !C.getArgs().hasArg(options::OPT_via_file_asm) &&
>        !C.getArgs().hasArg(options::OPT__SLASH_FA) &&
> -      !C.getArgs().hasArg(options::OPT__SLASH_Fa) &&
> -      isa<AssembleJobAction>(JA) && Inputs->size() == 1 &&
> -      isa<BackendJobAction>(*Inputs->begin())) {
> +      !C.getArgs().hasArg(options::OPT__SLASH_Fa) && BackendJA &&
> +      isa<BackendJobAction>(BackendJA)) {
>      // A BackendJob is always preceded by a CompileJob, and without
> -save-temps
>      // or -fembed-bitcode, they will always get combined together, so
> instead of
>      // checking the backend tool, check if the tool for the CompileJob
> has an
>      // integrated assembler. For -fembed-bitcode, CompileJob is still
> used to
>      // look up tools for BackendJob, but they need to match before we can
> split
>      // them.
> -    const ActionList *BackendInputs = &(*Inputs)[0]->getInputs();
> -    // Compile job may be wrapped in CudaHostAction, extract it if
> -    // that's the case and update CollapsedCHA if we combine phases.
> -    CudaHostAction *CHA =
> dyn_cast<CudaHostAction>(*BackendInputs->begin());
> -    JobAction *CompileJA = cast<CompileJobAction>(
> -        CHA ? *CHA->input_begin() : *BackendInputs->begin());
> -    assert(CompileJA && "Backend job is not preceeded by compile job.");
> -    const Tool *Compiler = TC->SelectTool(*CompileJA);
> +
> +    // Look through offload actions between backend and compile actions.
> +    Action *CompileJA = *BackendJA->getInputs().begin();
> +    auto *CompileOA =
> collapseOffloadingAction<CompileJobAction>(CompileJA);
> +
> +    assert(CompileJA && isa<CompileJobAction>(CompileJA) &&
> +           "Backend job is not preceeded by compile job.");
> +    const Tool *Compiler =
> TC->SelectTool(*cast<CompileJobAction>(CompileJA));
>      if (!Compiler)
>        return nullptr;
>      // When using -fembed-bitcode, it is required to have the same tool
> (clang)
> @@ -1929,7 +2018,12 @@ static const Tool *selectToolForJob(Comp
>      if (Compiler->hasIntegratedAssembler()) {
>        Inputs = &CompileJA->getInputs();
>        ToolForJob = Compiler;
> -      CollapsedCHA = CHA;
> +      // Save the collapsed offload actions because they may still contain
> +      // device actions.
> +      if (CompileOA)
> +        CollapsedOffloadAction.push_back(CompileOA);
> +      if (BackendOA)
> +        CollapsedOffloadAction.push_back(BackendOA);
>      }
>    }
>
> @@ -1939,20 +2033,23 @@ static const Tool *selectToolForJob(Comp
>    if (isa<BackendJobAction>(JA)) {
>      // Check if the compiler supports emitting LLVM IR.
>      assert(Inputs->size() == 1);
> -    // Compile job may be wrapped in CudaHostAction, extract it if
> -    // that's the case and update CollapsedCHA if we combine phases.
> -    CudaHostAction *CHA = dyn_cast<CudaHostAction>(*Inputs->begin());
> -    JobAction *CompileJA =
> -        cast<CompileJobAction>(CHA ? *CHA->input_begin() :
> *Inputs->begin());
> -    assert(CompileJA && "Backend job is not preceeded by compile job.");
> -    const Tool *Compiler = TC->SelectTool(*CompileJA);
> +
> +    // Look through offload actions between backend and compile actions.
> +    Action *CompileJA = *JA->getInputs().begin();
> +    auto *CompileOA =
> collapseOffloadingAction<CompileJobAction>(CompileJA);
> +
> +    assert(CompileJA && isa<CompileJobAction>(CompileJA) &&
> +           "Backend job is not preceeded by compile job.");
> +    const Tool *Compiler =
> TC->SelectTool(*cast<CompileJobAction>(CompileJA));
>      if (!Compiler)
>        return nullptr;
>      if (!Compiler->canEmitIR() ||
>          (!SaveTemps && !EmbedBitcode)) {
>        Inputs = &CompileJA->getInputs();
>        ToolForJob = Compiler;
> -      CollapsedCHA = CHA;
> +
> +      if (CompileOA)
> +        CollapsedOffloadAction.push_back(CompileOA);
>      }
>    }
>
> @@ -1963,12 +2060,21 @@ static const Tool *selectToolForJob(Comp
>    // See if we should use an integrated preprocessor. We do so when we
> have
>    // exactly one input, since this is the only use case we care about
>    // (irrelevant since we don't support combine yet).
> -  if (Inputs->size() == 1 && isa<PreprocessJobAction>(*Inputs->begin()) &&
> +
> +  // Look through offload actions after preprocessing.
> +  Action *PreprocessJA = (Inputs->size() == 1) ? *Inputs->begin() :
> nullptr;
> +  auto *PreprocessOA =
> +      collapseOffloadingAction<PreprocessJobAction>(PreprocessJA);
> +
> +  if (PreprocessJA && isa<PreprocessJobAction>(PreprocessJA) &&
>        !C.getArgs().hasArg(options::OPT_no_integrated_cpp) &&
>        !C.getArgs().hasArg(options::OPT_traditional_cpp) && !SaveTemps &&
>        !C.getArgs().hasArg(options::OPT_rewrite_objc) &&
> -      ToolForJob->hasIntegratedCPP())
> -    Inputs = &(*Inputs)[0]->getInputs();
> +      ToolForJob->hasIntegratedCPP()) {
> +    Inputs = &PreprocessJA->getInputs();
> +    if (PreprocessOA)
> +      CollapsedOffloadAction.push_back(PreprocessOA);
> +  }
>
>    return ToolForJob;
>  }
> @@ -1976,8 +2082,8 @@ static const Tool *selectToolForJob(Comp
>  InputInfo Driver::BuildJobsForAction(
>      Compilation &C, const Action *A, const ToolChain *TC, const char
> *BoundArch,
>      bool AtTopLevel, bool MultipleArchs, const char *LinkingOutput,
> -    std::map<std::pair<const Action *, std::string>, InputInfo>
> &CachedResults)
> -    const {
> +    std::map<std::pair<const Action *, std::string>, InputInfo>
> &CachedResults,
> +    bool BuildForOffloadDevice) const {
>    // The bound arch is not necessarily represented in the toolchain's
> triple --
>    // for example, armv7 and armv7s both map to the same triple -- so we
> need
>    // both in our map.
> @@ -1991,9 +2097,9 @@ InputInfo Driver::BuildJobsForAction(
>    if (CachedResult != CachedResults.end()) {
>      return CachedResult->second;
>    }
> -  InputInfo Result =
> -      BuildJobsForActionNoCache(C, A, TC, BoundArch, AtTopLevel,
> MultipleArchs,
> -                                LinkingOutput, CachedResults);
> +  InputInfo Result = BuildJobsForActionNoCache(
> +      C, A, TC, BoundArch, AtTopLevel, MultipleArchs, LinkingOutput,
> +      CachedResults, BuildForOffloadDevice);
>    CachedResults[ActionTC] = Result;
>    return Result;
>  }
> @@ -2001,21 +2107,65 @@ InputInfo Driver::BuildJobsForAction(
>  InputInfo Driver::BuildJobsForActionNoCache(
>      Compilation &C, const Action *A, const ToolChain *TC, const char
> *BoundArch,
>      bool AtTopLevel, bool MultipleArchs, const char *LinkingOutput,
> -    std::map<std::pair<const Action *, std::string>, InputInfo>
> &CachedResults)
> -    const {
> +    std::map<std::pair<const Action *, std::string>, InputInfo>
> &CachedResults,
> +    bool BuildForOffloadDevice) const {
>    llvm::PrettyStackTraceString CrashInfo("Building compilation jobs");
>
> -  InputInfoList CudaDeviceInputInfos;
> -  if (const CudaHostAction *CHA = dyn_cast<CudaHostAction>(A)) {
> -    // Append outputs of device jobs to the input list.
> -    for (const Action *DA : CHA->getDeviceActions()) {
> -      CudaDeviceInputInfos.push_back(BuildJobsForAction(
> -          C, DA, TC, nullptr, AtTopLevel,
> -          /*MultipleArchs*/ false, LinkingOutput, CachedResults));
> -    }
> -    // Override current action with a real host compile action and
> continue
> -    // processing it.
> -    A = *CHA->input_begin();
> +  InputInfoList OffloadDependencesInputInfo;
> +  if (const OffloadAction *OA = dyn_cast<OffloadAction>(A)) {
> +    // The offload action is expected to be used in four different
> situations.
> +    //
> +    // a) Set a toolchain/architecture/kind for a host action:
> +    //    Host Action 1 -> OffloadAction -> Host Action 2
> +    //
> +    // b) Set a toolchain/architecture/kind for a device action;
> +    //    Device Action 1 -> OffloadAction -> Device Action 2
> +    //
> +    // c) Specify a device dependences to a host action;
> +    //    Device Action 1  _
> +    //                      \
> +    //      Host Action 1  ---> OffloadAction -> Host Action 2
> +    //
> +    // d) Specify a host dependence to a device action.
> +    //      Host Action 1  _
> +    //                      \
> +    //    Device Action 1  ---> OffloadAction -> Device Action 2
> +    //
> +    // For a) and b), we just return the job generated for the
> dependence. For
> +    // c) and d) we override the current action with the host/device
> dependence
> +    // if the current toolchain is host/device and set the offload
> dependences
> +    // info with the jobs obtained from the device/host dependence(s).
> +
> +    // If there is a single device option, just generate the job for it.
> +    if (OA->hasSingleDeviceDependence()) {
> +      InputInfo DevA;
> +      OA->doOnEachDeviceDependence([&](Action *DepA, const ToolChain
> *DepTC,
> +                                       const char *DepBoundArch) {
> +        DevA =
> +            BuildJobsForAction(C, DepA, DepTC, DepBoundArch, AtTopLevel,
> +                               /*MultipleArchs*/ !!DepBoundArch,
> LinkingOutput,
> +                               CachedResults,
> /*BuildForOffloadDevice=*/true);
> +      });
> +      return DevA;
> +    }
> +
> +    // If 'Action 2' is host, we generate jobs for the device dependences
> and
> +    // override the current action with the host dependence. Otherwise, we
> +    // generate the host dependences and override the action with the
> device
> +    // dependence. The dependences can't therefore be a top-level action.
> +    OA->doOnEachDependence(
> +        /*IsHostDependence=*/BuildForOffloadDevice,
> +        [&](Action *DepA, const ToolChain *DepTC, const char
> *DepBoundArch) {
> +          OffloadDependencesInputInfo.push_back(BuildJobsForAction(
> +              C, DepA, DepTC, DepBoundArch, /*AtTopLevel=*/false,
> +              /*MultipleArchs*/ !!DepBoundArch, LinkingOutput,
> CachedResults,
> +              /*BuildForOffloadDevice=*/DepA->getOffloadingDeviceKind() !=
> +                  Action::OFK_None));
> +        });
> +
> +    A = BuildForOffloadDevice
> +            ?
> OA->getSingleDeviceDependence(/*DoNotConsiderHostActions=*/true)
> +            : OA->getHostDependence();
>    }
>
>    if (const InputAction *IA = dyn_cast<InputAction>(A)) {
> @@ -2042,41 +2192,34 @@ InputInfo Driver::BuildJobsForActionNoCa
>        TC = &C.getDefaultToolChain();
>
>      return BuildJobsForAction(C, *BAA->input_begin(), TC, ArchName,
> AtTopLevel,
> -                              MultipleArchs, LinkingOutput,
> CachedResults);
> +                              MultipleArchs, LinkingOutput, CachedResults,
> +                              BuildForOffloadDevice);
>    }
>
> -  if (const CudaDeviceAction *CDA = dyn_cast<CudaDeviceAction>(A)) {
> -    // Initial processing of CudaDeviceAction carries host params.
> -    // Call BuildJobsForAction() again, now with correct device
> parameters.
> -    InputInfo II = BuildJobsForAction(
> -        C, *CDA->input_begin(),
> C.getSingleOffloadToolChain<Action::OFK_Cuda>(),
> -        CudaArchToString(CDA->getGpuArch()), CDA->isAtTopLevel(),
> -        /*MultipleArchs=*/true, LinkingOutput, CachedResults);
> -    // Currently II's Action is *CDA->input_begin().  Set it to CDA
> instead, so
> -    // that one can retrieve II's GPU arch.
> -    II.setAction(A);
> -    return II;
> -  }
>
>    const ActionList *Inputs = &A->getInputs();
>
>    const JobAction *JA = cast<JobAction>(A);
> -  const CudaHostAction *CollapsedCHA = nullptr;
> +  ActionList CollapsedOffloadActions;
> +
>    const Tool *T =
>        selectToolForJob(C, isSaveTempsEnabled(), embedBitcodeEnabled(),
> TC, JA,
> -                       Inputs, CollapsedCHA);
> +                       Inputs, CollapsedOffloadActions);
>    if (!T)
>      return InputInfo();
>
> -  // If we've collapsed action list that contained CudaHostAction we
> -  // need to build jobs for device-side inputs it may have held.
> -  if (CollapsedCHA) {
> -    for (const Action *DA : CollapsedCHA->getDeviceActions()) {
> -      CudaDeviceInputInfos.push_back(BuildJobsForAction(
> -          C, DA, TC, "", AtTopLevel,
> -          /*MultipleArchs*/ false, LinkingOutput, CachedResults));
> -    }
> -  }
> +  // If we've collapsed action list that contained OffloadAction we
> +  // need to build jobs for host/device-side inputs it may have held.
> +  for (const auto *OA : CollapsedOffloadActions)
> +    cast<OffloadAction>(OA)->doOnEachDependence(
> +        /*IsHostDependence=*/BuildForOffloadDevice,
> +        [&](Action *DepA, const ToolChain *DepTC, const char
> *DepBoundArch) {
> +          OffloadDependencesInputInfo.push_back(BuildJobsForAction(
> +              C, DepA, DepTC, DepBoundArch, AtTopLevel,
> +              /*MultipleArchs=*/!!DepBoundArch, LinkingOutput,
> CachedResults,
> +              /*BuildForOffloadDevice=*/DepA->getOffloadingDeviceKind() !=
> +                  Action::OFK_None));
> +        });
>
>    // Only use pipes when there is exactly one input.
>    InputInfoList InputInfos;
> @@ -2086,9 +2229,9 @@ InputInfo Driver::BuildJobsForActionNoCa
>      // FIXME: Clean this up.
>      bool SubJobAtTopLevel =
>          AtTopLevel && (isa<DsymutilJobAction>(A) ||
> isa<VerifyJobAction>(A));
> -    InputInfos.push_back(BuildJobsForAction(C, Input, TC, BoundArch,
> -                                            SubJobAtTopLevel,
> MultipleArchs,
> -                                            LinkingOutput,
> CachedResults));
> +    InputInfos.push_back(BuildJobsForAction(
> +        C, Input, TC, BoundArch, SubJobAtTopLevel, MultipleArchs,
> LinkingOutput,
> +        CachedResults, BuildForOffloadDevice));
>    }
>
>    // Always use the first input as the base input.
> @@ -2099,9 +2242,10 @@ InputInfo Driver::BuildJobsForActionNoCa
>    if (JA->getType() == types::TY_dSYM)
>      BaseInput = InputInfos[0].getFilename();
>
> -  // Append outputs of cuda device jobs to the input list
> -  if (CudaDeviceInputInfos.size())
> -    InputInfos.append(CudaDeviceInputInfos.begin(),
> CudaDeviceInputInfos.end());
> +  // Append outputs of offload device jobs to the input list
> +  if (!OffloadDependencesInputInfo.empty())
> +    InputInfos.append(OffloadDependencesInputInfo.begin(),
> +                      OffloadDependencesInputInfo.end());
>
>    // Determine the place to write output to, if any.
>    InputInfo Result;
> @@ -2109,7 +2253,8 @@ InputInfo Driver::BuildJobsForActionNoCa
>      Result = InputInfo(A, BaseInput);
>    else
>      Result = InputInfo(A, GetNamedOutputPath(C, *JA, BaseInput, BoundArch,
> -                                             AtTopLevel, MultipleArchs),
> +                                             AtTopLevel, MultipleArchs,
> +                                             TC->getTriple().normalize()),
>                         BaseInput);
>
>    if (CCCPrintBindings && !CCGenDiagnostics) {
> @@ -2169,7 +2314,8 @@ static const char *MakeCLOutputFilename(
>  const char *Driver::GetNamedOutputPath(Compilation &C, const JobAction
> &JA,
>                                         const char *BaseInput,
>                                         const char *BoundArch, bool
> AtTopLevel,
> -                                       bool MultipleArchs) const {
> +                                       bool MultipleArchs,
> +                                       StringRef NormalizedTriple) const {
>    llvm::PrettyStackTraceString CrashInfo("Computing output path");
>    // Output to a user requested destination?
>    if (AtTopLevel && !isa<DsymutilJobAction>(JA) &&
> !isa<VerifyJobAction>(JA)) {
> @@ -2255,6 +2401,7 @@ const char *Driver::GetNamedOutputPath(C
>            MakeCLOutputFilename(C.getArgs(), "", BaseName,
> types::TY_Image);
>      } else if (MultipleArchs && BoundArch) {
>        SmallString<128> Output(getDefaultImageName());
> +      Output += JA.getOffloadingFileNamePrefix(NormalizedTriple);
>        Output += "-";
>        Output.append(BoundArch);
>        NamedOutput = C.getArgs().MakeArgString(Output.c_str());
> @@ -2271,6 +2418,7 @@ const char *Driver::GetNamedOutputPath(C
>      if (!types::appendSuffixForType(JA.getType()))
>        End = BaseName.rfind('.');
>      SmallString<128> Suffixed(BaseName.substr(0, End));
> +    Suffixed += JA.getOffloadingFileNamePrefix(NormalizedTriple);
>      if (MultipleArchs && BoundArch) {
>        Suffixed += "-";
>        Suffixed.append(BoundArch);
>
> Modified: cfe/trunk/lib/Driver/ToolChain.cpp
> URL:
> http://llvm.org/viewvc/llvm-project/cfe/trunk/lib/Driver/ToolChain.cpp?rev=275645&r1=275644&r2=275645&view=diff
>
> ==============================================================================
> --- cfe/trunk/lib/Driver/ToolChain.cpp (original)
> +++ cfe/trunk/lib/Driver/ToolChain.cpp Fri Jul 15 18:13:27 2016
> @@ -248,8 +248,7 @@ Tool *ToolChain::getTool(Action::ActionC
>
>    case Action::InputClass:
>    case Action::BindArchClass:
> -  case Action::CudaDeviceClass:
> -  case Action::CudaHostClass:
> +  case Action::OffloadClass:
>    case Action::LipoJobClass:
>    case Action::DsymutilJobClass:
>    case Action::VerifyDebugInfoJobClass:
>
> Modified: cfe/trunk/lib/Driver/Tools.cpp
> URL:
> http://llvm.org/viewvc/llvm-project/cfe/trunk/lib/Driver/Tools.cpp?rev=275645&r1=275644&r2=275645&view=diff
>
> ==============================================================================
> --- cfe/trunk/lib/Driver/Tools.cpp (original)
> +++ cfe/trunk/lib/Driver/Tools.cpp Fri Jul 15 18:13:27 2016
> @@ -296,12 +296,45 @@ static bool forwardToGCC(const Option &O
>           !O.hasFlag(options::DriverOption) &&
> !O.hasFlag(options::LinkerInput);
>  }
>
> +/// Add the C++ include args of other offloading toolchains. If this is a
> host
> +/// job, the device toolchains are added. If this is a device job, the
> host
> +/// toolchains will be added.
> +static void addExtraOffloadCXXStdlibIncludeArgs(Compilation &C,
> +                                                const JobAction &JA,
> +                                                const ArgList &Args,
> +                                                ArgStringList &CmdArgs) {
> +
> +  if (JA.isHostOffloading(Action::OFK_Cuda))
> +    C.getSingleOffloadToolChain<Action::OFK_Cuda>()
> +        ->AddClangCXXStdlibIncludeArgs(Args, CmdArgs);
> +  else if (JA.isDeviceOffloading(Action::OFK_Cuda))
> +    C.getSingleOffloadToolChain<Action::OFK_Host>()
> +        ->AddClangCXXStdlibIncludeArgs(Args, CmdArgs);
> +
> +  // TODO: Add support for other programming models here.
> +}
> +
> +/// Add the include args that are specific of each offloading programming
> model.
> +static void addExtraOffloadSpecificIncludeArgs(Compilation &C,
> +                                               const JobAction &JA,
> +                                               const ArgList &Args,
> +                                               ArgStringList &CmdArgs) {
> +
> +  if (JA.isHostOffloading(Action::OFK_Cuda))
> +    C.getSingleOffloadToolChain<Action::OFK_Host>()->AddCudaIncludeArgs(
> +        Args, CmdArgs);
> +  else if (JA.isDeviceOffloading(Action::OFK_Cuda))
> +    C.getSingleOffloadToolChain<Action::OFK_Cuda>()->AddCudaIncludeArgs(
> +        Args, CmdArgs);
> +
> +  // TODO: Add support for other programming models here.
> +}
> +
>  void Clang::AddPreprocessingOptions(Compilation &C, const JobAction &JA,
>                                      const Driver &D, const ArgList &Args,
>                                      ArgStringList &CmdArgs,
>                                      const InputInfo &Output,
> -                                    const InputInfoList &Inputs,
> -                                    const ToolChain *AuxToolChain) const {
> +                                    const InputInfoList &Inputs) const {
>    Arg *A;
>    const bool IsIAMCU = getToolChain().getTriple().isOSIAMCU();
>
> @@ -566,31 +599,27 @@ void Clang::AddPreprocessingOptions(Comp
>    // OBJCPLUS_INCLUDE_PATH - system includes enabled when compiling
> ObjC++.
>    addDirectoryList(Args, CmdArgs, "-objcxx-isystem",
> "OBJCPLUS_INCLUDE_PATH");
>
> -  // Optional AuxToolChain indicates that we need to include headers
> -  // for more than one target. If that's the case, add include paths
> -  // from AuxToolChain right after include paths of the same kind for
> -  // the current target.
> +  // While adding the include arguments, we also attempt to retrieve the
> +  // arguments of related offloading toolchains or arguments that are
> specific
> +  // of an offloading programming model.
>
>    // Add C++ include arguments, if needed.
>    if (types::isCXX(Inputs[0].getType())) {
>      getToolChain().AddClangCXXStdlibIncludeArgs(Args, CmdArgs);
> -    if (AuxToolChain)
> -      AuxToolChain->AddClangCXXStdlibIncludeArgs(Args, CmdArgs);
> +    addExtraOffloadCXXStdlibIncludeArgs(C, JA, Args, CmdArgs);
>    }
>
>    // Add system include arguments for all targets but IAMCU.
>    if (!IsIAMCU) {
>      getToolChain().AddClangSystemIncludeArgs(Args, CmdArgs);
> -    if (AuxToolChain)
> -      AuxToolChain->AddClangCXXStdlibIncludeArgs(Args, CmdArgs);
> +    addExtraOffloadCXXStdlibIncludeArgs(C, JA, Args, CmdArgs);
>

This doesn't make much sense to me: we already added the C++ stdlib
includes a few lines above for C++ compiles. Should this be adding the
(non-C++) system include args instead?


>    } else {
>      // For IAMCU add special include arguments.
>      getToolChain().AddIAMCUIncludeArgs(Args, CmdArgs);
>    }
>
> -  // Add CUDA include arguments, if needed.
> -  if (types::isCuda(Inputs[0].getType()))
> -    getToolChain().AddCudaIncludeArgs(Args, CmdArgs);
> +  // Add offload include arguments, if needed.
> +  addExtraOffloadSpecificIncludeArgs(C, JA, Args, CmdArgs);
>  }
>
>  // FIXME: Move to target hook.
> @@ -3799,7 +3828,7 @@ void Clang::ConstructJob(Compilation &C,
>    // CUDA compilation may have multiple inputs (source file + results of
>    // device-side compilations). All other jobs are expected to have
> exactly one
>    // input.
> -  bool IsCuda = types::isCuda(Input.getType());
> +  bool IsCuda = JA.isOffloading(Action::OFK_Cuda);
>    assert((IsCuda || Inputs.size() == 1) && "Unable to handle multiple
> inputs.");
>
>    // C++ is not supported for IAMCU.
> @@ -3815,21 +3844,21 @@ void Clang::ConstructJob(Compilation &C,
>    CmdArgs.push_back("-triple");
>    CmdArgs.push_back(Args.MakeArgString(TripleStr));
>
> -  const ToolChain *AuxToolChain = nullptr;
>    if (IsCuda) {
> -    // FIXME: We need a (better) way to pass information about
> -    // particular compilation pass we're constructing here. For now we
> -    // can check which toolchain we're using and pick the other one to
> -    // extract the triple.
> -    if (&getToolChain() ==
> C.getSingleOffloadToolChain<Action::OFK_Cuda>())
> -      AuxToolChain = C.getOffloadingHostToolChain();
> -    else if (&getToolChain() == C.getOffloadingHostToolChain())
> -      AuxToolChain = C.getSingleOffloadToolChain<Action::OFK_Cuda>();
> -    else
> -      llvm_unreachable("Can't figure out CUDA compilation mode.");
> -    assert(AuxToolChain != nullptr && "No aux toolchain.");
> +    // We have to pass the triple of the host if compiling for a CUDA
> device and
> +    // vice-versa.
> +    StringRef NormalizedTriple;
> +    if (JA.isDeviceOffloading(Action::OFK_Cuda))
> +      NormalizedTriple = C.getSingleOffloadToolChain<Action::OFK_Host>()
> +                             ->getTriple()
> +                             .normalize();
> +    else
> +      NormalizedTriple = C.getSingleOffloadToolChain<Action::OFK_Cuda>()
> +                             ->getTriple()
> +                             .normalize();
> +
>      CmdArgs.push_back("-aux-triple");
> -
> CmdArgs.push_back(Args.MakeArgString(AuxToolChain->getTriple().str()));
> +    CmdArgs.push_back(Args.MakeArgString(NormalizedTriple));
>    }
>
>    if (Triple.isOSWindows() && (Triple.getArch() == llvm::Triple::arm ||
> @@ -4718,8 +4747,7 @@ void Clang::ConstructJob(Compilation &C,
>    //
>    // FIXME: Support -fpreprocessed
>    if (types::getPreprocessedType(InputType) != types::TY_INVALID)
> -    AddPreprocessingOptions(C, JA, D, Args, CmdArgs, Output, Inputs,
> -                            AuxToolChain);
> +    AddPreprocessingOptions(C, JA, D, Args, CmdArgs, Output, Inputs);
>
>    // Don't warn about "clang -c -DPIC -fPIC test.i" because libtool.m4
> assumes
>    // that "The compiler can only warn and ignore the option if not
> recognized".
> @@ -11193,15 +11221,14 @@ void NVPTX::Assembler::ConstructJob(Comp
>        static_cast<const toolchains::CudaToolChain &>(getToolChain());
>    assert(TC.getTriple().isNVPTX() && "Wrong platform");
>
> -  std::vector<std::string> gpu_archs =
> -      Args.getAllArgValues(options::OPT_march_EQ);
> -  assert(gpu_archs.size() == 1 && "Exactly one GPU Arch required for
> ptxas.");
> -  const std::string& gpu_arch = gpu_archs[0];
> +  // Obtain architecture from the action.
> +  CudaArch gpu_arch = StringToCudaArch(JA.getOffloadingArch());
> +  assert(gpu_arch != CudaArch::UNKNOWN &&
> +         "Device action expected to have an architecture.");
>
>    // Check that our installation's ptxas supports gpu_arch.
>    if (!Args.hasArg(options::OPT_no_cuda_version_check)) {
> -    TC.cudaInstallation().CheckCudaVersionSupportsArch(
> -        StringToCudaArch(gpu_arch));
> +    TC.cudaInstallation().CheckCudaVersionSupportsArch(gpu_arch);
>    }
>
>    ArgStringList CmdArgs;
> @@ -11245,7 +11272,7 @@ void NVPTX::Assembler::ConstructJob(Comp
>    }
>
>    CmdArgs.push_back("--gpu-name");
> -  CmdArgs.push_back(Args.MakeArgString(gpu_arch));
> +  CmdArgs.push_back(Args.MakeArgString(CudaArchToString(gpu_arch)));
>    CmdArgs.push_back("--output-file");
>    CmdArgs.push_back(Args.MakeArgString(Output.getFilename()));
>    for (const auto& II : Inputs)
> @@ -11277,13 +11304,20 @@ void NVPTX::Linker::ConstructJob(Compila
>    CmdArgs.push_back(Args.MakeArgString(Output.getFilename()));
>
>    for (const auto& II : Inputs) {
> -    auto* A = cast<const CudaDeviceAction>(II.getAction());
> +    auto *A = II.getAction();
> +    assert(A->getInputs().size() == 1 &&
> +           "Device offload action is expected to have a single input");
> +    const char *gpu_arch_str = A->getOffloadingArch();
> +    assert(gpu_arch_str &&
> +           "Device action expected to have associated a GPU
> architecture!");
> +    CudaArch gpu_arch = StringToCudaArch(gpu_arch_str);
> +
>      // We need to pass an Arch of the form "sm_XX" for cubin files and
>      // "compute_XX" for ptx.
>      const char *Arch =
>          (II.getType() == types::TY_PP_Asm)
> -            ?
> CudaVirtualArchToString(VirtualArchForCudaArch(A->getGpuArch()))
> -            : CudaArchToString(A->getGpuArch());
> +            ? CudaVirtualArchToString(VirtualArchForCudaArch(gpu_arch))
> +            : gpu_arch_str;
>      CmdArgs.push_back(Args.MakeArgString(llvm::Twine("--image=profile=") +
>                                           Arch + ",file=" +
> II.getFilename()));
>    }
>
> Modified: cfe/trunk/lib/Driver/Tools.h
> URL:
> http://llvm.org/viewvc/llvm-project/cfe/trunk/lib/Driver/Tools.h?rev=275645&r1=275644&r2=275645&view=diff
>
> ==============================================================================
> --- cfe/trunk/lib/Driver/Tools.h (original)
> +++ cfe/trunk/lib/Driver/Tools.h Fri Jul 15 18:13:27 2016
> @@ -57,8 +57,7 @@ private:
>                                 const Driver &D, const llvm::opt::ArgList
> &Args,
>                                 llvm::opt::ArgStringList &CmdArgs,
>                                 const InputInfo &Output,
> -                               const InputInfoList &Inputs,
> -                               const ToolChain *AuxToolChain) const;
> +                               const InputInfoList &Inputs) const;
>
>    void AddAArch64TargetArgs(const llvm::opt::ArgList &Args,
>                              llvm::opt::ArgStringList &CmdArgs) const;
>
> Modified: cfe/trunk/lib/Frontend/CreateInvocationFromCommandLine.cpp
> URL:
> http://llvm.org/viewvc/llvm-project/cfe/trunk/lib/Frontend/CreateInvocationFromCommandLine.cpp?rev=275645&r1=275644&r2=275645&view=diff
>
> ==============================================================================
> --- cfe/trunk/lib/Frontend/CreateInvocationFromCommandLine.cpp (original)
> +++ cfe/trunk/lib/Frontend/CreateInvocationFromCommandLine.cpp Fri Jul 15
> 18:13:27 2016
> @@ -60,25 +60,25 @@ clang::createInvocationFromCommandLine(A
>    }
>
>    // We expect to get back exactly one command job, if we didn't something
> -  // failed. CUDA compilation is an exception as it creates multiple
> jobs. If
> -  // that's the case, we proceed with the first job. If caller needs
> particular
> -  // CUDA job, it should be controlled via --cuda-{host|device}-only
> option
> -  // passed to the driver.
> +  // failed. Offload compilation is an exception as it creates multiple
> jobs. If
> +  // that's the case, we proceed with the first job. If caller needs a
> +  // particular job, it should be controlled via options (e.g.
> +  // --cuda-{host|device}-only for CUDA) passed to the driver.
>    const driver::JobList &Jobs = C->getJobs();
> -  bool CudaCompilation = false;
> +  bool OffloadCompilation = false;
>    if (Jobs.size() > 1) {
>      for (auto &A : C->getActions()){
>        // On MacOSX real actions may end up being wrapped in BindArchAction
>        if (isa<driver::BindArchAction>(A))
>          A = *A->input_begin();
> -      if (isa<driver::CudaDeviceAction>(A)) {
> -        CudaCompilation = true;
> +      if (isa<driver::OffloadAction>(A)) {
> +        OffloadCompilation = true;
>          break;
>        }
>      }
>    }
>    if (Jobs.size() == 0 || !isa<driver::Command>(*Jobs.begin()) ||
> -      (Jobs.size() > 1 && !CudaCompilation)) {
> +      (Jobs.size() > 1 && !OffloadCompilation)) {
>      SmallString<256> Msg;
>      llvm::raw_svector_ostream OS(Msg);
>      Jobs.Print(OS, "; ", true);
>
> Added: cfe/trunk/test/Driver/cuda_phases.cu
> URL:
> http://llvm.org/viewvc/llvm-project/cfe/trunk/test/Driver/cuda_phases.cu?rev=275645&view=auto
>
> ==============================================================================
> --- cfe/trunk/test/Driver/cuda_phases.cu (added)
> +++ cfe/trunk/test/Driver/cuda_phases.cu Fri Jul 15 18:13:27 2016
> @@ -0,0 +1,206 @@
> +// Tests the phases generated for a CUDA offloading target for different
> +// combinations of:
> +// - Number of gpu architectures;
> +// - Host/device-only compilation;
> +// - User-requested final phase - binary or assembly.
> +
> +// REQUIRES: clang-driver
> +// REQUIRES: powerpc-registered-target
> +// REQUIRES: nvptx-registered-target
> +
> +//
> +// Test single gpu architecture with complete compilation.
> +//
> +// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-phases
> --cuda-gpu-arch=sm_30 %s 2>&1 \
> +// RUN: | FileCheck -check-prefix=BIN %s
> +// BIN: 0: input, "{{.*}}cuda_phases.cu", cuda, (host-cuda)
> +// BIN: 1: preprocessor, {0}, cuda-cpp-output, (host-cuda)
> +// BIN: 2: compiler, {1}, ir, (host-cuda)
> +// BIN: 3: input, "{{.*}}cuda_phases.cu", cuda, (device-cuda, sm_30)
> +// BIN: 4: preprocessor, {3}, cuda-cpp-output, (device-cuda, sm_30)
> +// BIN: 5: compiler, {4}, ir, (device-cuda, sm_30)
> +// BIN: 6: backend, {5}, assembler, (device-cuda, sm_30)
> +// BIN: 7: assembler, {6}, object, (device-cuda, sm_30)
> +// BIN: 8: offload, "device-cuda (nvptx64-nvidia-cuda:sm_30)" {7}, object
> +// BIN: 9: offload, "device-cuda (nvptx64-nvidia-cuda:sm_30)" {6},
> assembler
> +// BIN: 10: linker, {8, 9}, cuda-fatbin, (device-cuda)
> +// BIN: 11: offload, "host-cuda (powerpc64le-ibm-linux-gnu)" {2},
> "device-cuda (nvptx64-nvidia-cuda)" {10}, ir
> +// BIN: 12: backend, {11}, assembler, (host-cuda)
> +// BIN: 13: assembler, {12}, object, (host-cuda)
> +// BIN: 14: linker, {13}, image, (host-cuda)
> +
> +//
> +// Test single gpu architecture up to the assemble phase.
> +//
> +// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-phases
> --cuda-gpu-arch=sm_30 %s -S 2>&1 \
> +// RUN: | FileCheck -check-prefix=ASM %s
> +// ASM: 0: input, "{{.*}}cuda_phases.cu", cuda, (device-cuda, sm_30)
> +// ASM: 1: preprocessor, {0}, cuda-cpp-output, (device-cuda, sm_30)
> +// ASM: 2: compiler, {1}, ir, (device-cuda, sm_30)
> +// ASM: 3: backend, {2}, assembler, (device-cuda, sm_30)
> +// ASM: 4: offload, "device-cuda (nvptx64-nvidia-cuda:sm_30)" {3},
> assembler
> +// ASM: 5: input, "{{.*}}cuda_phases.cu", cuda, (host-cuda)
> +// ASM: 6: preprocessor, {5}, cuda-cpp-output, (host-cuda)
> +// ASM: 7: compiler, {6}, ir, (host-cuda)
> +// ASM: 8: backend, {7}, assembler, (host-cuda)
> +
> +//
> +// Test two gpu architectures with complete compilation.
> +//
> +// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-phases
> --cuda-gpu-arch=sm_30 --cuda-gpu-arch=sm_35 %s 2>&1 \
> +// RUN: | FileCheck -check-prefix=BIN2 %s
> +// BIN2: 0: input, "{{.*}}cuda_phases.cu", cuda, (host-cuda)
> +// BIN2: 1: preprocessor, {0}, cuda-cpp-output, (host-cuda)
> +// BIN2: 2: compiler, {1}, ir, (host-cuda)
> +// BIN2: 3: input, "{{.*}}cuda_phases.cu", cuda, (device-cuda, sm_30)
> +// BIN2: 4: preprocessor, {3}, cuda-cpp-output, (device-cuda, sm_30)
> +// BIN2: 5: compiler, {4}, ir, (device-cuda, sm_30)
> +// BIN2: 6: backend, {5}, assembler, (device-cuda, sm_30)
> +// BIN2: 7: assembler, {6}, object, (device-cuda, sm_30)
> +// BIN2: 8: offload, "device-cuda (nvptx64-nvidia-cuda:sm_30)" {7}, object
> +// BIN2: 9: offload, "device-cuda (nvptx64-nvidia-cuda:sm_30)" {6},
> assembler
> +// BIN2: 10: input, "{{.*}}cuda_phases.cu", cuda, (device-cuda, sm_35)
> +// BIN2: 11: preprocessor, {10}, cuda-cpp-output, (device-cuda, sm_35)
> +// BIN2: 12: compiler, {11}, ir, (device-cuda, sm_35)
> +// BIN2: 13: backend, {12}, assembler, (device-cuda, sm_35)
> +// BIN2: 14: assembler, {13}, object, (device-cuda, sm_35)
> +// BIN2: 15: offload, "device-cuda (nvptx64-nvidia-cuda:sm_35)" {14},
> object
> +// BIN2: 16: offload, "device-cuda (nvptx64-nvidia-cuda:sm_35)" {13},
> assembler
> +// BIN2: 17: linker, {8, 9, 15, 16}, cuda-fatbin, (device-cuda)
> +// BIN2: 18: offload, "host-cuda (powerpc64le-ibm-linux-gnu)" {2},
> "device-cuda (nvptx64-nvidia-cuda)" {17}, ir
> +// BIN2: 19: backend, {18}, assembler, (host-cuda)
> +// BIN2: 20: assembler, {19}, object, (host-cuda)
> +// BIN2: 21: linker, {20}, image, (host-cuda)
> +
> +//
> +// Test two gpu architecturess up to the assemble phase.
> +//
> +// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-phases
> --cuda-gpu-arch=sm_30 --cuda-gpu-arch=sm_35 %s -S 2>&1 \
> +// RUN: | FileCheck -check-prefix=ASM2 %s
> +// ASM2: 0: input, "{{.*}}cuda_phases.cu", cuda, (device-cuda, sm_30)
> +// ASM2: 1: preprocessor, {0}, cuda-cpp-output, (device-cuda, sm_30)
> +// ASM2: 2: compiler, {1}, ir, (device-cuda, sm_30)
> +// ASM2: 3: backend, {2}, assembler, (device-cuda, sm_30)
> +// ASM2: 4: offload, "device-cuda (nvptx64-nvidia-cuda:sm_30)" {3},
> assembler
> +// ASM2: 5: input, "{{.*}}cuda_phases.cu", cuda, (device-cuda, sm_35)
> +// ASM2: 6: preprocessor, {5}, cuda-cpp-output, (device-cuda, sm_35)
> +// ASM2: 7: compiler, {6}, ir, (device-cuda, sm_35)
> +// ASM2: 8: backend, {7}, assembler, (device-cuda, sm_35)
> +// ASM2: 9: offload, "device-cuda (nvptx64-nvidia-cuda:sm_35)" {8},
> assembler
> +// ASM2: 10: input, "{{.*}}cuda_phases.cu", cuda, (host-cuda)
> +// ASM2: 11: preprocessor, {10}, cuda-cpp-output, (host-cuda)
> +// ASM2: 12: compiler, {11}, ir, (host-cuda)
> +// ASM2: 13: backend, {12}, assembler, (host-cuda)
> +
> +//
> +// Test single gpu architecture with complete compilation in host-only
> +// compilation mode.
> +//
> +// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-phases
> --cuda-gpu-arch=sm_30 %s --cuda-host-only 2>&1 \
> +// RUN: | FileCheck -check-prefix=HBIN %s
> +// HBIN: 0: input, "{{.*}}cuda_phases.cu", cuda, (host-cuda)
> +// HBIN: 1: preprocessor, {0}, cuda-cpp-output, (host-cuda)
> +// HBIN: 2: compiler, {1}, ir, (host-cuda)
> +// HBIN: 3: offload, "host-cuda (powerpc64le-ibm-linux-gnu)" {2}, ir
> +// HBIN: 4: backend, {3}, assembler, (host-cuda)
> +// HBIN: 5: assembler, {4}, object, (host-cuda)
> +// HBIN: 6: linker, {5}, image, (host-cuda)
> +
> +//
> +// Test single gpu architecture up to the assemble phase in host-only
> +// compilation mode.
> +//
> +// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-phases
> --cuda-gpu-arch=sm_30 %s --cuda-host-only -S 2>&1 \
> +// RUN: | FileCheck -check-prefix=HASM %s
> +// HASM: 0: input, "{{.*}}cuda_phases.cu", cuda, (host-cuda)
> +// HASM: 1: preprocessor, {0}, cuda-cpp-output, (host-cuda)
> +// HASM: 2: compiler, {1}, ir, (host-cuda)
> +// HASM: 3: offload, "host-cuda (powerpc64le-ibm-linux-gnu)" {2}, ir
> +// HASM: 4: backend, {3}, assembler, (host-cuda)
> +
> +//
> +// Test two gpu architectures with complete compilation in host-only
> +// compilation mode.
> +//
> +// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-phases
> --cuda-gpu-arch=sm_30 --cuda-gpu-arch=sm_35 %s --cuda-host-only 2>&1 \
> +// RUN: | FileCheck -check-prefix=HBIN2 %s
> +// HBIN2: 0: input, "{{.*}}cuda_phases.cu", cuda, (host-cuda)
> +// HBIN2: 1: preprocessor, {0}, cuda-cpp-output, (host-cuda)
> +// HBIN2: 2: compiler, {1}, ir, (host-cuda)
> +// HBIN2: 3: offload, "host-cuda (powerpc64le-ibm-linux-gnu)" {2}, ir
> +// HBIN2: 4: backend, {3}, assembler, (host-cuda)
> +// HBIN2: 5: assembler, {4}, object, (host-cuda)
> +// HBIN2: 6: linker, {5}, image, (host-cuda)
> +
> +//
> +// Test two gpu architectures up to the assemble phase in host-only
> +// compilation mode.
> +//
> +// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-phases
> --cuda-gpu-arch=sm_30 --cuda-gpu-arch=sm_35 %s --cuda-host-only -S 2>&1 \
> +// RUN: | FileCheck -check-prefix=HASM2 %s
> +// HASM2: 0: input, "{{.*}}cuda_phases.cu", cuda, (host-cuda)
> +// HASM2: 1: preprocessor, {0}, cuda-cpp-output, (host-cuda)
> +// HASM2: 2: compiler, {1}, ir, (host-cuda)
> +// HASM2: 3: offload, "host-cuda (powerpc64le-ibm-linux-gnu)" {2}, ir
> +// HASM2: 4: backend, {3}, assembler, (host-cuda)
> +
> +//
> +// Test single gpu architecture with complete compilation in device-only
> +// compilation mode.
> +//
> +// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-phases
> --cuda-gpu-arch=sm_30 %s --cuda-device-only 2>&1 \
> +// RUN: | FileCheck -check-prefix=DBIN %s
> +// DBIN: 0: input, "{{.*}}cuda_phases.cu", cuda, (device-cuda, sm_30)
> +// DBIN: 1: preprocessor, {0}, cuda-cpp-output, (device-cuda, sm_30)
> +// DBIN: 2: compiler, {1}, ir, (device-cuda, sm_30)
> +// DBIN: 3: backend, {2}, assembler, (device-cuda, sm_30)
> +// DBIN: 4: assembler, {3}, object, (device-cuda, sm_30)
> +// DBIN: 5: offload, "device-cuda (nvptx64-nvidia-cuda:sm_30)" {4}, object
> +
> +//
> +// Test single gpu architecture up to the assemble phase in device-only
> +// compilation mode.
> +//
> +// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-phases
> --cuda-gpu-arch=sm_30 %s --cuda-device-only -S 2>&1 \
> +// RUN: | FileCheck -check-prefix=DASM %s
> +// DASM: 0: input, "{{.*}}cuda_phases.cu", cuda, (device-cuda, sm_30)
> +// DASM: 1: preprocessor, {0}, cuda-cpp-output, (device-cuda, sm_30)
> +// DASM: 2: compiler, {1}, ir, (device-cuda, sm_30)
> +// DASM: 3: backend, {2}, assembler, (device-cuda, sm_30)
> +// DASM: 4: offload, "device-cuda (nvptx64-nvidia-cuda:sm_30)" {3},
> assembler
> +
> +//
> +// Test two gpu architectures with complete compilation in device-only
> +// compilation mode.
> +//
> +// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-phases
> --cuda-gpu-arch=sm_30 --cuda-gpu-arch=sm_35 %s --cuda-device-only 2>&1 \
> +// RUN: | FileCheck -check-prefix=DBIN2 %s
> +// DBIN2: 0: input, "{{.*}}cuda_phases.cu", cuda, (device-cuda, sm_30)
> +// DBIN2: 1: preprocessor, {0}, cuda-cpp-output, (device-cuda, sm_30)
> +// DBIN2: 2: compiler, {1}, ir, (device-cuda, sm_30)
> +// DBIN2: 3: backend, {2}, assembler, (device-cuda, sm_30)
> +// DBIN2: 4: assembler, {3}, object, (device-cuda, sm_30)
> +// DBIN2: 5: offload, "device-cuda (nvptx64-nvidia-cuda:sm_30)" {4},
> object
> +// DBIN2: 6: input, "{{.*}}cuda_phases.cu", cuda, (device-cuda, sm_35)
> +// DBIN2: 7: preprocessor, {6}, cuda-cpp-output, (device-cuda, sm_35)
> +// DBIN2: 8: compiler, {7}, ir, (device-cuda, sm_35)
> +// DBIN2: 9: backend, {8}, assembler, (device-cuda, sm_35)
> +// DBIN2: 10: assembler, {9}, object, (device-cuda, sm_35)
> +// DBIN2: 11: offload, "device-cuda (nvptx64-nvidia-cuda:sm_35)" {10},
> object
> +
> +//
> +// Test two gpu architectures up to the assemble phase in device-only
> +// compilation mode.
> +//
> +// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-phases
> --cuda-gpu-arch=sm_30 --cuda-gpu-arch=sm_35 %s --cuda-device-only -S 2>&1 \
> +// RUN: | FileCheck -check-prefix=DASM2 %s
> +// DASM2: 0: input, "{{.*}}cuda_phases.cu", cuda, (device-cuda, sm_30)
> +// DASM2: 1: preprocessor, {0}, cuda-cpp-output, (device-cuda, sm_30)
> +// DASM2: 2: compiler, {1}, ir, (device-cuda, sm_30)
> +// DASM2: 3: backend, {2}, assembler, (device-cuda, sm_30)
> +// DASM2: 4: offload, "device-cuda (nvptx64-nvidia-cuda:sm_30)" {3},
> assembler
> +// DASM2: 5: input, "{{.*}}cuda_phases.cu", cuda, (device-cuda, sm_35)
> +// DASM2: 6: preprocessor, {5}, cuda-cpp-output, (device-cuda, sm_35)
> +// DASM2: 7: compiler, {6}, ir, (device-cuda, sm_35)
> +// DASM2: 8: backend, {7}, assembler, (device-cuda, sm_35)
> +// DASM2: 9: offload, "device-cuda (nvptx64-nvidia-cuda:sm_35)" {8},
> assembler
>
>
> _______________________________________________
> cfe-commits mailing list
> cfe-commits at lists.llvm.org
> http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20160718/750093e9/attachment-0001.html>


More information about the cfe-commits mailing list