Merged main:898d52b819496ba70d0ca29cc7b60237108ae2b4 into amd-gfx:a6bdf8d91f90

Local branch amd-gfx a6bdf8d Merged main:41b55071a13374654a290c01224eb066c38dc87a into amd-gfx:20624ccc2ecf
Remote branch main 898d52b [compiler-rt][rtsan] Fix failing file permissions test by checking umask (llvm#106095)

Author: SC llvm team

clang/docs/ReleaseNotes.rst

@@ -317,6 +317,8 @@ Bug Fixes to C++ Support
 - Clang now properly handles the order of attributes in `extern` blocks. (#GH101990).
 - Fixed an assertion failure by preventing null explicit object arguments from being deduced. (#GH102025).
 - Correctly check constraints of explicit instantiations of member functions. (#GH46029)
+- When performing partial ordering of function templates, clang now checks that
+  the deduction was consistent. Fixes (#GH18291).
 - Fixed an assertion failure about a constraint of a friend function template references to a value with greater
   template depth than the friend function template. (#GH98258)
 - Clang now rebuilds the template parameters of out-of-line declarations and specializations in the context

clang/include/clang/Basic/BuiltinsNVPTX.def

@@ -844,6 +844,9 @@ BUILTIN(__nvvm_atom_xor_gen_ll, "LLiLLiD*LLi", "n")
 TARGET_BUILTIN(__nvvm_atom_cta_xor_gen_ll, "LLiLLiD*LLi", "n", SM_60)
 TARGET_BUILTIN(__nvvm_atom_sys_xor_gen_ll, "LLiLLiD*LLi", "n", SM_60)
 
+TARGET_BUILTIN(__nvvm_atom_cas_gen_us, "UsUsD*UsUs", "n", SM_70)
+TARGET_BUILTIN(__nvvm_atom_cta_cas_gen_us, "UsUsD*UsUs", "n", SM_70)
+TARGET_BUILTIN(__nvvm_atom_sys_cas_gen_us, "UsUsD*UsUs", "n", SM_70)
 BUILTIN(__nvvm_atom_cas_gen_i, "iiD*ii", "n")
 TARGET_BUILTIN(__nvvm_atom_cta_cas_gen_i, "iiD*ii", "n", SM_60)
 TARGET_BUILTIN(__nvvm_atom_sys_cas_gen_i, "iiD*ii", "n", SM_60)

clang/include/clang/Sema/Sema.h

@@ -13283,6 +13283,10 @@ class Sema final : public SemaBase {
   /// \param AllowDeducedTST Whether a DeducedTemplateSpecializationType is
   /// acceptable as the top level type of the result.
   ///
+  /// \param IsIncompleteSubstitution If provided, the pointee will be set
+  /// whenever substitution would perform a replacement with a null or
+  /// non-existent template argument.
+  ///
   /// \returns If the instantiation succeeds, the instantiated
   /// type. Otherwise, produces diagnostics and returns a NULL type.
   TypeSourceInfo *SubstType(TypeSourceInfo *T,
@@ -13292,7 +13296,8 @@ class Sema final : public SemaBase {
 
   QualType SubstType(QualType T,
                      const MultiLevelTemplateArgumentList &TemplateArgs,
-                     SourceLocation Loc, DeclarationName Entity);
+                     SourceLocation Loc, DeclarationName Entity,
+                     bool *IsIncompleteSubstitution = nullptr);
 
   TypeSourceInfo *SubstType(TypeLoc TL,
                             const MultiLevelTemplateArgumentList &TemplateArgs,

clang/lib/CodeGen/CGBuiltin.cpp

@@ -20344,6 +20344,7 @@ Value *CodeGenFunction::EmitNVPTXBuiltinExpr(unsigned BuiltinID,
   case NVPTX::BI__nvvm_atom_min_gen_ull:
     return MakeBinaryAtomicValue(*this, llvm::AtomicRMWInst::UMin, E);
 
+  case NVPTX::BI__nvvm_atom_cas_gen_us:
   case NVPTX::BI__nvvm_atom_cas_gen_i:
   case NVPTX::BI__nvvm_atom_cas_gen_l:
   case NVPTX::BI__nvvm_atom_cas_gen_ll:
@@ -20535,6 +20536,7 @@ Value *CodeGenFunction::EmitNVPTXBuiltinExpr(unsigned BuiltinID,
   case NVPTX::BI__nvvm_atom_sys_xor_gen_l:
   case NVPTX::BI__nvvm_atom_sys_xor_gen_ll:
     return MakeScopedAtomic(Intrinsic::nvvm_atomic_xor_gen_i_sys, *this, E);
+  case NVPTX::BI__nvvm_atom_cta_cas_gen_us:
   case NVPTX::BI__nvvm_atom_cta_cas_gen_i:
   case NVPTX::BI__nvvm_atom_cta_cas_gen_l:
   case NVPTX::BI__nvvm_atom_cta_cas_gen_ll: {
@@ -20546,6 +20548,7 @@ Value *CodeGenFunction::EmitNVPTXBuiltinExpr(unsigned BuiltinID,
             Intrinsic::nvvm_atomic_cas_gen_i_cta, {ElemTy, Ptr->getType()}),
         {Ptr, EmitScalarExpr(E->getArg(1)), EmitScalarExpr(E->getArg(2))});
   }
+  case NVPTX::BI__nvvm_atom_sys_cas_gen_us:
   case NVPTX::BI__nvvm_atom_sys_cas_gen_i:
   case NVPTX::BI__nvvm_atom_sys_cas_gen_l:
   case NVPTX::BI__nvvm_atom_sys_cas_gen_ll: {

clang/lib/Headers/__clang_cuda_device_functions.h

@@ -529,6 +529,20 @@ __DEVICE__ void __threadfence(void) { __nvvm_membar_gl(); }
 __DEVICE__ void __threadfence_block(void) { __nvvm_membar_cta(); };
 __DEVICE__ void __threadfence_system(void) { __nvvm_membar_sys(); };
 __DEVICE__ void __trap(void) { __asm__ __volatile__("trap;"); }
+__DEVICE__ unsigned short
+__usAtomicCAS(unsigned short *__p, unsigned short __cmp, unsigned short __v) {
+  return __nvvm_atom_cas_gen_us(__p, __cmp, __v);
+}
+__DEVICE__ unsigned short __usAtomicCAS_block(unsigned short *__p,
+                                              unsigned short __cmp,
+                                              unsigned short __v) {
+  return __nvvm_atom_cta_cas_gen_us(__p, __cmp, __v);
+}
+__DEVICE__ unsigned short __usAtomicCAS_system(unsigned short *__p,
+                                               unsigned short __cmp,
+                                               unsigned short __v) {
+  return __nvvm_atom_sys_cas_gen_us(__p, __cmp, __v);
+}
 __DEVICE__ unsigned int __uAtomicAdd(unsigned int *__p, unsigned int __v) {
   return __nvvm_atom_add_gen_i((int *)__p, __v);
 }