Add OpenCL 2.0 atomic builtin functions as Clang builtin

OpenCL 2.0 atomic builtin functions have a scope argument which is ideally
represented as synchronization scope argument in LLVM atomic instructions.

Clang supports translating Clang atomic builtin functions to LLVM atomic
instructions. However it currently does not support synchronization scope
of LLVM atomic instructions. Without this, users have to use LLVM assembly
code to implement OpenCL atomic builtin functions.

This patch adds OpenCL 2.0 atomic builtin functions as Clang builtin
functions, which supports generating LLVM atomic instructions with
synchronization scope operand.

Currently only constant memory scope argument is supported. Support of
non-constant memory scope argument will be added later.

Differential Revision: https://reviews.llvm.org/D28691

llvm-svn: 310082

1 files changed, 78 insertions, 16 deletions

diff --git a/clang/lib/Sema/SemaChecking.cpp b/clang/lib/Sema/SemaChecking.cpp
index 81dd36cf671..578dbf0aadc 100644
--- a/clang/lib/Sema/SemaChecking.cpp
+++ b/clang/lib/Sema/SemaChecking.cpp
@@ -25,6 +25,7 @@
 #include "clang/AST/StmtObjC.h"
 #include "clang/Analysis/Analyses/FormatString.h"
 #include "clang/Basic/CharInfo.h"
+#include "clang/Basic/SyncScope.h"
 #include "clang/Basic/TargetBuiltins.h"
 #include "clang/Basic/TargetInfo.h"
 #include "clang/Lex/Lexer.h" // TODO: Extract static functions to fix layering.
@@ -2787,15 +2788,18 @@ static bool isValidOrderingForOp(int64_t Ordering, AtomicExpr::AtomicOp Op) {
   auto OrderingCABI = (llvm::AtomicOrderingCABI)Ordering;
   switch (Op) {
   case AtomicExpr::AO__c11_atomic_init:
+  case AtomicExpr::AO__opencl_atomic_init:
     llvm_unreachable("There is no ordering argument for an init");
 
   case AtomicExpr::AO__c11_atomic_load:
+  case AtomicExpr::AO__opencl_atomic_load:
   case AtomicExpr::AO__atomic_load_n:
   case AtomicExpr::AO__atomic_load:
     return OrderingCABI != llvm::AtomicOrderingCABI::release &&
            OrderingCABI != llvm::AtomicOrderingCABI::acq_rel;
 
   case AtomicExpr::AO__c11_atomic_store:
+  case AtomicExpr::AO__opencl_atomic_store:
   case AtomicExpr::AO__atomic_store:
   case AtomicExpr::AO__atomic_store_n:
     return OrderingCABI != llvm::AtomicOrderingCABI::consume &&
@@ -2812,7 +2816,9 @@ ExprResult Sema::SemaAtomicOpsOverloaded(ExprResult TheCallResult,
   CallExpr *TheCall = cast<CallExpr>(TheCallResult.get());
   DeclRefExpr *DRE =cast<DeclRefExpr>(TheCall->getCallee()->IgnoreParenCasts());
 
-  // All these operations take one of the following forms:
+  // All the non-OpenCL operations take one of the following forms.
+  // The OpenCL operations take the __c11 forms with one extra argument for
+  // synchronization scope.
   enum {
     // C    __c11_atomic_init(A *, C)
     Init,
@@ -2833,6 +2839,7 @@ ExprResult Sema::SemaAtomicOpsOverloaded(ExprResult TheCallResult,
     // bool __atomic_compare_exchange(A *, C *, CP, bool, int, int)
     GNUCmpXchg
   } Form = Init;
+  const unsigned NumForm = GNUCmpXchg + 1;
   const unsigned NumArgs[] = { 2, 2, 3, 3, 3, 3, 4, 5, 6 };
   const unsigned NumVals[] = { 1, 0, 1, 1, 1, 1, 2, 2, 3 };
   // where:
@@ -2842,12 +2849,18 @@ ExprResult Sema::SemaAtomicOpsOverloaded(ExprResult TheCallResult,
   //   M is C if C is an integer, and ptrdiff_t if C is a pointer, and
   //   the int parameters are for orderings.
 
+  static_assert(sizeof(NumArgs)/sizeof(NumArgs[0]) == NumForm
+      && sizeof(NumVals)/sizeof(NumVals[0]) == NumForm,
+      "need to update code for modified forms");
   static_assert(AtomicExpr::AO__c11_atomic_init == 0 &&
                     AtomicExpr::AO__c11_atomic_fetch_xor + 1 ==
                         AtomicExpr::AO__atomic_load,
                 "need to update code for modified C11 atomics");
-  bool IsC11 = Op >= AtomicExpr::AO__c11_atomic_init &&
-               Op <= AtomicExpr::AO__c11_atomic_fetch_xor;
+  bool IsOpenCL = Op >= AtomicExpr::AO__opencl_atomic_init &&
+                  Op <= AtomicExpr::AO__opencl_atomic_fetch_max;
+  bool IsC11 = (Op >= AtomicExpr::AO__c11_atomic_init &&
+               Op <= AtomicExpr::AO__c11_atomic_fetch_xor) ||
+               IsOpenCL;
   bool IsN = Op == AtomicExpr::AO__atomic_load_n ||
              Op == AtomicExpr::AO__atomic_store_n ||
              Op == AtomicExpr::AO__atomic_exchange_n ||
@@ -2856,10 +2869,12 @@ ExprResult Sema::SemaAtomicOpsOverloaded(ExprResult TheCallResult,
 
   switch (Op) {
   case AtomicExpr::AO__c11_atomic_init:
+  case AtomicExpr::AO__opencl_atomic_init:
     Form = Init;
     break;
 
   case AtomicExpr::AO__c11_atomic_load:
+  case AtomicExpr::AO__opencl_atomic_load:
   case AtomicExpr::AO__atomic_load_n:
     Form = Load;
     break;
@@ -2869,6 +2884,7 @@ ExprResult Sema::SemaAtomicOpsOverloaded(ExprResult TheCallResult,
     break;
 
   case AtomicExpr::AO__c11_atomic_store:
+  case AtomicExpr::AO__opencl_atomic_store:
   case AtomicExpr::AO__atomic_store:
   case AtomicExpr::AO__atomic_store_n:
     Form = Copy;
@@ -2876,6 +2892,10 @@ ExprResult Sema::SemaAtomicOpsOverloaded(ExprResult TheCallResult,
 
   case AtomicExpr::AO__c11_atomic_fetch_add:
   case AtomicExpr::AO__c11_atomic_fetch_sub:
+  case AtomicExpr::AO__opencl_atomic_fetch_add:
+  case AtomicExpr::AO__opencl_atomic_fetch_sub:
+  case AtomicExpr::AO__opencl_atomic_fetch_min:
+  case AtomicExpr::AO__opencl_atomic_fetch_max:
   case AtomicExpr::AO__atomic_fetch_add:
   case AtomicExpr::AO__atomic_fetch_sub:
   case AtomicExpr::AO__atomic_add_fetch:
@@ -2885,6 +2905,9 @@ ExprResult Sema::SemaAtomicOpsOverloaded(ExprResult TheCallResult,
   case AtomicExpr::AO__c11_atomic_fetch_and:
   case AtomicExpr::AO__c11_atomic_fetch_or:
   case AtomicExpr::AO__c11_atomic_fetch_xor:
+  case AtomicExpr::AO__opencl_atomic_fetch_and:
+  case AtomicExpr::AO__opencl_atomic_fetch_or:
+  case AtomicExpr::AO__opencl_atomic_fetch_xor:
   case AtomicExpr::AO__atomic_fetch_and:
   case AtomicExpr::AO__atomic_fetch_or:
   case AtomicExpr::AO__atomic_fetch_xor:
@@ -2897,6 +2920,7 @@ ExprResult Sema::SemaAtomicOpsOverloaded(ExprResult TheCallResult,
     break;
 
   case AtomicExpr::AO__c11_atomic_exchange:
+  case AtomicExpr::AO__opencl_atomic_exchange:
   case AtomicExpr::AO__atomic_exchange_n:
     Form = Xchg;
     break;
@@ -2907,6 +2931,8 @@ ExprResult Sema::SemaAtomicOpsOverloaded(ExprResult TheCallResult,
 
   case AtomicExpr::AO__c11_atomic_compare_exchange_strong:
   case AtomicExpr::AO__c11_atomic_compare_exchange_weak:
+  case AtomicExpr::AO__opencl_atomic_compare_exchange_strong:
+  case AtomicExpr::AO__opencl_atomic_compare_exchange_weak:
     Form = C11CmpXchg;
     break;
 
@@ -2916,16 +2942,19 @@ ExprResult Sema::SemaAtomicOpsOverloaded(ExprResult TheCallResult,
     break;
   }
 
+  unsigned AdjustedNumArgs = NumArgs[Form];
+  if (IsOpenCL && Op != AtomicExpr::AO__opencl_atomic_init)
+    ++AdjustedNumArgs;
   // Check we have the right number of arguments.
-  if (TheCall->getNumArgs() < NumArgs[Form]) {
+  if (TheCall->getNumArgs() < AdjustedNumArgs) {
     Diag(TheCall->getLocEnd(), diag::err_typecheck_call_too_few_args)
-      << 0 << NumArgs[Form] << TheCall->getNumArgs()
+      << 0 << AdjustedNumArgs << TheCall->getNumArgs()
       << TheCall->getCallee()->getSourceRange();
     return ExprError();
-  } else if (TheCall->getNumArgs() > NumArgs[Form]) {
-    Diag(TheCall->getArg(NumArgs[Form])->getLocStart(),
+  } else if (TheCall->getNumArgs() > AdjustedNumArgs) {
+    Diag(TheCall->getArg(AdjustedNumArgs)->getLocStart(),
          diag::err_typecheck_call_too_many_args)
-      << 0 << NumArgs[Form] << TheCall->getNumArgs()
+      << 0 << AdjustedNumArgs << TheCall->getNumArgs()
       << TheCall->getCallee()->getSourceRange();
     return ExprError();
   }
@@ -2953,9 +2982,11 @@ ExprResult Sema::SemaAtomicOpsOverloaded(ExprResult TheCallResult,
         << Ptr->getType() << Ptr->getSourceRange();
       return ExprError();
     }
-    if (AtomTy.isConstQualified()) {
+    if (AtomTy.isConstQualified() ||
+        AtomTy.getAddressSpace() == LangAS::opencl_constant) {
       Diag(DRE->getLocStart(), diag::err_atomic_op_needs_non_const_atomic)
-        << Ptr->getType() << Ptr->getSourceRange();
+          << (AtomTy.isConstQualified() ? 0 : 1) << Ptr->getType()
+          << Ptr->getSourceRange();
       return ExprError();
     }
     ValType = AtomTy->getAs<AtomicType>()->getValueType();
@@ -3024,7 +3055,8 @@ ExprResult Sema::SemaAtomicOpsOverloaded(ExprResult TheCallResult,
   ValType.removeLocalVolatile();
   ValType.removeLocalConst();
   QualType ResultType = ValType;
-  if (Form == Copy || Form == LoadCopy || Form == GNUXchg || Form == Init)
+  if (Form == Copy || Form == LoadCopy || Form == GNUXchg ||
+      Form == Init)
     ResultType = Context.VoidTy;
   else if (Form == C11CmpXchg || Form == GNUCmpXchg)
     ResultType = Context.BoolTy;
@@ -3038,7 +3070,7 @@ ExprResult Sema::SemaAtomicOpsOverloaded(ExprResult TheCallResult,
   // The first argument --- the pointer --- has a fixed type; we
   // deduce the types of the rest of the arguments accordingly.  Walk
   // the remaining arguments, converting them to the deduced value type.
-  for (unsigned i = 1; i != NumArgs[Form]; ++i) {
+  for (unsigned i = 1; i != TheCall->getNumArgs(); ++i) {
     QualType Ty;
     if (i < NumVals[Form] + 1) {
       switch (i) {
@@ -3080,7 +3112,7 @@ ExprResult Sema::SemaAtomicOpsOverloaded(ExprResult TheCallResult,
         break;
       }
     } else {
-      // The order(s) are always converted to int.
+      // The order(s) and scope are always converted to int.
       Ty = Context.IntTy;
     }
 
@@ -3093,6 +3125,27 @@ ExprResult Sema::SemaAtomicOpsOverloaded(ExprResult TheCallResult,
     TheCall->setArg(i, Arg.get());
   }
 
+  Expr *Scope;
+  if (Form != Init) {
+    if (IsOpenCL) {
+      Scope = TheCall->getArg(TheCall->getNumArgs() - 1);
+      llvm::APSInt Result(32);
+      if (!Scope->isIntegerConstantExpr(Result, Context))
+        Diag(Scope->getLocStart(),
+             diag::err_atomic_op_has_non_constant_synch_scope)
+            << Scope->getSourceRange();
+      else if (!isValidSyncScopeValue(Result.getZExtValue()))
+        Diag(Scope->getLocStart(), diag::err_atomic_op_has_invalid_synch_scope)
+            << Scope->getSourceRange();
+    } else {
+      Scope = IntegerLiteral::Create(
+          Context,
+          llvm::APInt(Context.getTypeSize(Context.IntTy),
+                      static_cast<unsigned>(SyncScope::OpenCLAllSVMDevices)),
+          Context.IntTy, SourceLocation());
+    }
+  }
+
   // Permute the arguments into a 'consistent' order.
   SmallVector<Expr*, 5> SubExprs;
   SubExprs.push_back(Ptr);
@@ -3103,28 +3156,33 @@ ExprResult Sema::SemaAtomicOpsOverloaded(ExprResult TheCallResult,
     break;
   case Load:
     SubExprs.push_back(TheCall->getArg(1)); // Order
+    SubExprs.push_back(Scope);              // Scope
     break;
   case LoadCopy:
   case Copy:
   case Arithmetic:
   case Xchg:
     SubExprs.push_back(TheCall->getArg(2)); // Order
+    SubExprs.push_back(Scope);              // Scope
     SubExprs.push_back(TheCall->getArg(1)); // Val1
     break;
   case GNUXchg:
     // Note, AtomicExpr::getVal2() has a special case for this atomic.
     SubExprs.push_back(TheCall->getArg(3)); // Order
+    SubExprs.push_back(Scope);              // Scope
     SubExprs.push_back(TheCall->getArg(1)); // Val1
     SubExprs.push_back(TheCall->getArg(2)); // Val2
     break;
   case C11CmpXchg:
     SubExprs.push_back(TheCall->getArg(3)); // Order
+    SubExprs.push_back(Scope);              // Scope
     SubExprs.push_back(TheCall->getArg(1)); // Val1
     SubExprs.push_back(TheCall->getArg(4)); // OrderFail
     SubExprs.push_back(TheCall->getArg(2)); // Val2
     break;
   case GNUCmpXchg:
     SubExprs.push_back(TheCall->getArg(4)); // Order
+    SubExprs.push_back(Scope);              // Scope
     SubExprs.push_back(TheCall->getArg(1)); // Val1
     SubExprs.push_back(TheCall->getArg(5)); // OrderFail
     SubExprs.push_back(TheCall->getArg(2)); // Val2
@@ -3146,10 +3204,14 @@ ExprResult Sema::SemaAtomicOpsOverloaded(ExprResult TheCallResult,
                                             TheCall->getRParenLoc());
   
   if ((Op == AtomicExpr::AO__c11_atomic_load ||
-       (Op == AtomicExpr::AO__c11_atomic_store)) &&
+       Op == AtomicExpr::AO__c11_atomic_store ||
+       Op == AtomicExpr::AO__opencl_atomic_load ||
+       Op == AtomicExpr::AO__opencl_atomic_store ) &&
       Context.AtomicUsesUnsupportedLibcall(AE))
-    Diag(AE->getLocStart(), diag::err_atomic_load_store_uses_lib) <<
-    ((Op == AtomicExpr::AO__c11_atomic_load) ? 0 : 1);
+    Diag(AE->getLocStart(), diag::err_atomic_load_store_uses_lib)
+        << ((Op == AtomicExpr::AO__c11_atomic_load ||
+            Op == AtomicExpr::AO__opencl_atomic_load)
+                ? 0 : 1);
 
   return AE;
 }