[SYCL] Implement OpenCL kernel function generation

All SYCL memory objects shared between host and device (buffers/images, these
objects map to OpenCL buffers and images) must be accessed through special
accessor classes. The "device" side implementation of these classes contain
pointers to the device memory. As there is no way in OpenCL to pass
structures with pointers inside as kernel arguments, all memory objects
shared between host and device must be passed to the kernel as raw
pointers. SYCL also has a special mechanism for passing kernel arguments
from host to the device. In OpenCL kernel arguments are set by calling
`clSetKernelArg` function for each kernel argument, meanwhile in SYCL all the
kernel arguments are fields of "SYCL kernel function" which can be defined
as a lambda function or a named function object and passed as an argument
to SYCL function for invoking kernels (such as `parallel_for` or `single_task`).

To facilitate the mapping of SYCL kernel data members to OpenCL kernel
arguments and overcome OpenCL limitations we added the generation of an
OpenCL kernel function inside the compiler. An OpenCL kernel function
contains the body of the SYCL kernel function, receives OpenCL-like
parameters and additionally does some manipulation to initialize SYCL
kernel data members with these parameters. In some pseudo code the OpenCL
kernel function can look like this:

```
// SYCL kernel is defined in SYCL headers:
template <typename KernelName, typename KernelType/*, ...*/>
__attribute__((sycl_kernel)) void sycl_kernel_function(KernelType KernelFuncObj) {
  // ...
  KernelFuncObj();
}

// Generated OpenCL kernel function
__kernel KernelName(global int* a) {
  KernelType KernelFuncObj; // Actually kernel function object declaration
  // doesn't have a name in AST.
  // Let the kernel function object have one captured field - accessor A.
  // We need to init it with global pointer from arguments:
  KernelFuncObj.A.__init(a);
  // Body of the SYCL kernel from SYCL headers:
  {
    KernelFuncObj();
  }
}
```
OpenCL kernel function is generated by the compiler inside the Sema
using AST nodes.

clang/include/clang/Sema/Sema.h

@@ -11632,6 +11632,19 @@ class Sema final {
     ConstructorDestructor,
     BuiltinFunction
   };
+
+private:
+  /// Contains generated OpenCL kernel functions for SYCL.
+  SmallVector<Decl *, 4> SYCLKernels;
+
+public:
+  void addSYCLKernel(Decl *D) { SYCLKernels.push_back(D); }
+  /// Access to SYCL kernels.
+  SmallVectorImpl<Decl *> &getSYCLKernels() { return SYCLKernels; }
+
+  /// Constructs an OpenCL kernel using the KernelCaller function and adds it to
+  /// the SYCL device code.
+  void constructOpenCLKernel(FunctionDecl *KernelCallerFunc, MangleContext &MC);
 };
 
 /// RAII object that enters a new expression evaluation context.

clang/lib/AST/ASTContext.cpp

@@ -10023,6 +10023,10 @@ bool ASTContext::DeclMustBeEmitted(const Decl *D) {
   if (D->hasAttr<AliasAttr>() || D->hasAttr<UsedAttr>())
     return true;
 
+  // If SYCL, only kernels are required.
+  if (LangOpts.SYCLIsDevice && !(D->hasAttr<OpenCLKernelAttr>()))
+    return false;
+
   if (const auto *FD = dyn_cast<FunctionDecl>(D)) {
     // Forward declarations aren't required.
     if (!FD->doesThisDeclarationHaveABody())

clang/lib/CodeGen/CodeGenModule.cpp

@@ -2474,6 +2474,12 @@ void CodeGenModule::EmitGlobal(GlobalDecl GD) {
     }
   }
 
+  if (LangOpts.SYCLIsDevice && Global->hasAttr<OpenCLKernelAttr>() &&
+      MustBeEmitted(Global)) {
+    addDeferredDeclToEmit(GD);
+    return;
+  }
+
   // Ignore declarations, they will be emitted on their first use.
   if (const auto *FD = dyn_cast<FunctionDecl>(Global)) {
     // Forward declarations are emitted lazily on first use.

clang/lib/Parse/ParseAST.cpp

@@ -168,6 +168,10 @@ void clang::ParseAST(Sema &S, bool PrintStats, bool SkipFunctionBodies) {
   for (Decl *D : S.WeakTopLevelDecls())
     Consumer->HandleTopLevelDecl(DeclGroupRef(D));
 
+  if (S.getLangOpts().SYCLIsDevice)
+    for (Decl *D : S.getSYCLKernels())
+      Consumer->HandleTopLevelDecl(DeclGroupRef(D));
+
   Consumer->HandleTranslationUnit(S.getASTContext());
 
   // Finalize the template instantiation observer chain.

clang/lib/Sema/CMakeLists.txt

@@ -57,6 +57,7 @@ add_clang_library(clangSema
   SemaStmt.cpp
   SemaStmtAsm.cpp
   SemaStmtAttr.cpp
+  SemaSYCL.cpp
   SemaTemplate.cpp
   SemaTemplateDeduction.cpp
   SemaTemplateInstantiate.cpp