From: Yaxun Liu <Yaxun.Liu@amd.com>
Date: Fri, 20 May 2016 19:54:38 +0000 (+0000)
Subject: [OpenCL] Add to_{global|local|private} builtin functions.
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=5c2e21d12f6ff7d763c7aa057b6ed36b1081ce57;p=clang

[OpenCL] Add to_{global|local|private} builtin functions.

OpenCL builtin functions to_{global|local|private} accepts argument of pointer type to arbitrary pointee type, and return a pointer to the same pointee type in different addr space, i.e.

global gentype *to_global(gentype *p);
It is not desirable to declare it as

global void *to_global(void *);
in opencl header file since it misses diagnostics.

This patch implements these builtin functions as Clang builtin functions. In the builtin def file they are defined to have signature void*(void*). When handling call expressions, their declarations are re-written to have correct parameter type and return type corresponding to the call argument.

In codegen call to addr void *to_addr(void*) is generated with addrcasts or bitcasts to facilitate implementation in builtin library.

Differential Revision: http://reviews.llvm.org/D19932

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@270261 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/include/clang/Basic/Builtins.def b/include/clang/Basic/Builtins.def
index 53e77cf35b..532fa8f755 100644
--- a/include/clang/Basic/Builtins.def
+++ b/include/clang/Basic/Builtins.def
@@ -1305,6 +1305,11 @@ LANGBUILTIN(work_group_commit_write_pipe, "v.", "tn", OCLC_LANG)
 LANGBUILTIN(get_pipe_num_packets, "Ui.", "tn", OCLC_LANG)
 LANGBUILTIN(get_pipe_max_packets, "Ui.", "tn", OCLC_LANG)
 
+// OpenCL v2.0 s6.13.9 - Address space qualifier functions.
+LANGBUILTIN(to_global, "v*v*", "tn", OCLC_LANG)
+LANGBUILTIN(to_local, "v*v*", "tn", OCLC_LANG)
+LANGBUILTIN(to_private, "v*v*", "tn", OCLC_LANG)
+
 #undef BUILTIN
 #undef LIBBUILTIN
 #undef LANGBUILTIN
diff --git a/include/clang/Basic/DiagnosticSemaKinds.td b/include/clang/Basic/DiagnosticSemaKinds.td
index 3692166a2f..357d6f41e1 100644
--- a/include/clang/Basic/DiagnosticSemaKinds.td
+++ b/include/clang/Basic/DiagnosticSemaKinds.td
@@ -7856,6 +7856,8 @@ def err_opencl_type_can_only_be_used_as_function_parameter : Error <
 def warn_opencl_attr_deprecated_ignored : Warning <
   "%0 attribute is deprecated and ignored in OpenCL version %1">,
   InGroup<IgnoredAttributes>;
+def err_opencl_builtin_requires_version : Error<
+  "%0 requires OpenCL version %1%select{| or above}2">;
 
 // OpenCL v2.0 s6.13.6 -- Builtin Pipe Functions
 def err_opencl_builtin_pipe_first_arg : Error<
@@ -7887,6 +7889,11 @@ def err_opencl_invalid_block_declaration : Error<
 def err_opencl_extern_block_declaration : Error<
   "invalid block variable declaration - using 'extern' storage class is disallowed">;
 
+// OpenCL v2.0 s6.13.9 - Address space qualifier functions. 
+def err_opencl_builtin_to_addr_arg_num : Error<
+  "invalid number of arguments to function: %0">;
+def err_opencl_builtin_to_addr_invalid_arg : Error<
+  "invalid argument %0 to function: %1, expecting a generic pointer argument">;
 } // end of sema category
 
 let CategoryName = "OpenMP Issue" in {
diff --git a/lib/CodeGen/CGBuiltin.cpp b/lib/CodeGen/CGBuiltin.cpp
index 81ae61857a..daf89b4a74 100644
--- a/lib/CodeGen/CGBuiltin.cpp
+++ b/lib/CodeGen/CGBuiltin.cpp
@@ -2124,6 +2124,29 @@ RValue CodeGenFunction::EmitBuiltinExpr(const FunctionDecl *FD,
         Builder.CreateCall(CGM.CreateRuntimeFunction(FTy, Name), {Arg0}));
   }
 
+  // OpenCL v2.0 s6.13.9 - Address space qualifier functions.
+  case Builtin::BIto_global:
+  case Builtin::BIto_local:
+  case Builtin::BIto_private: {
+    auto Arg0 = EmitScalarExpr(E->getArg(0));
+    auto NewArgT = llvm::PointerType::get(Int8Ty,
+      CGM.getContext().getTargetAddressSpace(LangAS::opencl_generic));
+    auto NewRetT = llvm::PointerType::get(Int8Ty,
+      CGM.getContext().getTargetAddressSpace(
+        E->getType()->getPointeeType().getAddressSpace()));
+    auto FTy = llvm::FunctionType::get(NewRetT, {NewArgT}, false);
+    llvm::Value *NewArg;
+    if (Arg0->getType()->getPointerAddressSpace() !=
+        NewArgT->getPointerAddressSpace())
+      NewArg = Builder.CreateAddrSpaceCast(Arg0, NewArgT);
+    else
+      NewArg = Builder.CreateBitOrPointerCast(Arg0, NewArgT);
+    auto NewCall = Builder.CreateCall(CGM.CreateRuntimeFunction(FTy,
+      E->getDirectCallee()->getName()), {NewArg});
+    return RValue::get(Builder.CreateBitOrPointerCast(NewCall,
+      ConvertType(E->getType())));
+  }
+
   case Builtin::BIprintf:
     if (getLangOpts().CUDA && getLangOpts().CUDAIsDevice)
       return EmitCUDADevicePrintfCallExpr(E, ReturnValue);
diff --git a/lib/Sema/SemaChecking.cpp b/lib/Sema/SemaChecking.cpp
index dc91b93f20..670a67de2b 100644
--- a/lib/Sema/SemaChecking.cpp
+++ b/lib/Sema/SemaChecking.cpp
@@ -455,6 +455,52 @@ static bool SemaBuiltinPipePackets(Sema &S, CallExpr *Call) {
   return false;
 }
 
+// \brief Performs semantic analysis for the to_global/local/private call.
+// \param S Reference to the semantic analyzer.
+// \param BuiltinID ID of the builtin function.
+// \param Call A pointer to the builtin call.
+// \return True if a semantic error has been found, false otherwise.
+static bool SemaOpenCLBuiltinToAddr(Sema &S, unsigned BuiltinID,
+                                    CallExpr *Call) {
+  // OpenCL v2.0 s6.13.9 - Address space qualifier functions.
+  if (S.getLangOpts().OpenCLVersion < 200) {
+    S.Diag(Call->getLocStart(), diag::err_opencl_builtin_requires_version)
+        << Call->getDirectCallee() << "2.0" << 1 << Call->getSourceRange();
+    return true;
+  }
+
+  if (Call->getNumArgs() != 1) {
+    S.Diag(Call->getLocStart(), diag::err_opencl_builtin_to_addr_arg_num)
+        << Call->getDirectCallee() << Call->getSourceRange();
+    return true;
+  }
+
+  auto RT = Call->getArg(0)->getType();
+  if (!RT->isPointerType() || RT->getPointeeType()
+      .getAddressSpace() == LangAS::opencl_constant) {
+    S.Diag(Call->getLocStart(), diag::err_opencl_builtin_to_addr_invalid_arg)
+        << Call->getArg(0) << Call->getDirectCallee() << Call->getSourceRange();
+    return true;
+  }
+
+  RT = RT->getPointeeType();
+  auto Qual = RT.getQualifiers();
+  switch (BuiltinID) {
+  case Builtin::BIto_global:
+    Qual.setAddressSpace(LangAS::opencl_global);
+    break;
+  case Builtin::BIto_local:
+    Qual.setAddressSpace(LangAS::opencl_local);
+    break;
+  default:
+    Qual.removeAddressSpace();
+  }
+  Call->setType(S.Context.getPointerType(S.Context.getQualifiedType(
+      RT.getUnqualifiedType(), Qual)));
+
+  return false;
+}
+
 ExprResult
 Sema::CheckBuiltinFunctionCall(FunctionDecl *FDecl, unsigned BuiltinID,
                                CallExpr *TheCall) {
@@ -789,6 +835,12 @@ Sema::CheckBuiltinFunctionCall(FunctionDecl *FDecl, unsigned BuiltinID,
     if (SemaBuiltinPipePackets(*this, TheCall))
       return ExprError();
     break;
+  case Builtin::BIto_global:
+  case Builtin::BIto_local:
+  case Builtin::BIto_private:
+    if (SemaOpenCLBuiltinToAddr(*this, BuiltinID, TheCall))
+      return ExprError();
+    break;
   }
 
   // Since the target specific builtins for each arch overlap, only check those
diff --git a/test/CodeGenOpenCL/to_addr_builtin.cl b/test/CodeGenOpenCL/to_addr_builtin.cl
new file mode 100644
index 0000000000..67475d565e
--- /dev/null
+++ b/test/CodeGenOpenCL/to_addr_builtin.cl
@@ -0,0 +1,89 @@
+// RUN: %clang_cc1 -triple spir-unknown-unknown -emit-llvm -O0 -cl-std=CL2.0 -o - %s | FileCheck %s
+
+// CHECK: %[[A:.*]] = type { float, float, float }
+typedef struct {
+  float x,y,z;
+} A;
+typedef private A *PA;
+typedef global A *GA;
+
+void test(void) {
+  global int *glob;
+  local int *loc;
+  private int *priv;
+  generic int *gen;
+
+  //CHECK: %[[ARG:.*]] = addrspacecast i32 addrspace(1)* %{{.*}} to i8 addrspace(4)*
+  //CHECK: %[[RET:.*]] = call i8 addrspace(1)* @to_global(i8 addrspace(4)* %[[ARG]])
+  //CHECK: %{{.*}} = bitcast i8 addrspace(1)* %[[RET]] to i32 addrspace(1)*
+  glob = to_global(glob);
+  
+  //CHECK: %[[ARG:.*]] = addrspacecast i32 addrspace(3)* %{{.*}} to i8 addrspace(4)*
+  //CHECK: %[[RET:.*]] = call i8 addrspace(1)* @to_global(i8 addrspace(4)* %[[ARG]])
+  //CHECK: %{{.*}} = bitcast i8 addrspace(1)* %[[RET]] to i32 addrspace(1)*
+  glob = to_global(loc);
+ 
+  //CHECK: %[[ARG:.*]] = addrspacecast i32* %{{.*}} to i8 addrspace(4)*
+  //CHECK: %[[RET:.*]] = call i8 addrspace(1)* @to_global(i8 addrspace(4)* %[[ARG]])
+  //CHECK: %{{.*}} = bitcast i8 addrspace(1)* %[[RET]] to i32 addrspace(1)*
+  glob = to_global(priv);
+ 
+  //CHECK: %[[ARG:.*]] = bitcast i32 addrspace(4)* %{{.*}} to i8 addrspace(4)*
+  //CHECK: %[[RET:.*]] = call i8 addrspace(1)* @to_global(i8 addrspace(4)* %[[ARG]])
+  //CHECK: %{{.*}} = bitcast i8 addrspace(1)* %[[RET]] to i32 addrspace(1)*
+  glob = to_global(gen);
+  
+  //CHECK: %[[ARG:.*]] = addrspacecast i32 addrspace(1)* %{{.*}} to i8 addrspace(4)*
+  //CHECK: %[[RET:.*]] = call i8 addrspace(3)* @to_local(i8 addrspace(4)* %[[ARG]])
+  //CHECK: %{{.*}} = bitcast i8 addrspace(3)* %[[RET]] to i32 addrspace(3)*
+  loc = to_local(glob);
+
+  //CHECK: %[[ARG:.*]] = addrspacecast i32 addrspace(3)* %{{.*}} to i8 addrspace(4)*
+  //CHECK: %[[RET:.*]] = call i8 addrspace(3)* @to_local(i8 addrspace(4)* %[[ARG]])
+  //CHECK: %{{.*}} = bitcast i8 addrspace(3)* %[[RET]] to i32 addrspace(3)*
+  loc = to_local(loc);
+
+  //CHECK: %[[ARG:.*]] = addrspacecast i32* %{{.*}} to i8 addrspace(4)*
+  //CHECK: %[[RET:.*]] = call i8 addrspace(3)* @to_local(i8 addrspace(4)* %[[ARG]])
+  //CHECK: %{{.*}} = bitcast i8 addrspace(3)* %[[RET]] to i32 addrspace(3)*
+  loc = to_local(priv);
+
+  //CHECK: %[[ARG:.*]] = bitcast i32 addrspace(4)* %{{.*}} to i8 addrspace(4)*
+  //CHECK: %[[RET:.*]] = call i8 addrspace(3)* @to_local(i8 addrspace(4)* %[[ARG]])
+  //CHECK: %{{.*}} = bitcast i8 addrspace(3)* %[[RET]] to i32 addrspace(3)*
+  loc = to_local(gen);
+
+  //CHECK: %[[ARG:.*]] = addrspacecast i32 addrspace(1)* %{{.*}} to i8 addrspace(4)*
+  //CHECK: %[[RET:.*]] = call i8* @to_private(i8 addrspace(4)* %[[ARG]])
+  //CHECK: %{{.*}} = bitcast i8* %[[RET]] to i32*
+  priv = to_private(glob);
+
+  //CHECK: %[[ARG:.*]] = addrspacecast i32 addrspace(3)* %{{.*}} to i8 addrspace(4)*
+  //CHECK: %[[RET:.*]] = call i8* @to_private(i8 addrspace(4)* %[[ARG]])
+  //CHECK: %{{.*}} = bitcast i8* %[[RET]] to i32*
+  priv = to_private(loc);
+
+  //CHECK: %[[ARG:.*]] = addrspacecast i32* %{{.*}} to i8 addrspace(4)*
+  //CHECK: %[[RET:.*]] = call i8* @to_private(i8 addrspace(4)* %[[ARG]])
+  //CHECK: %{{.*}} = bitcast i8* %[[RET]] to i32*
+  priv = to_private(priv);
+
+  //CHECK: %[[ARG:.*]] = bitcast i32 addrspace(4)* %{{.*}} to i8 addrspace(4)*
+  //CHECK: %[[RET:.*]] = call i8* @to_private(i8 addrspace(4)* %[[ARG]])
+  //CHECK: %{{.*}} = bitcast i8* %[[RET]] to i32*
+  priv = to_private(gen);
+
+  //CHECK: %[[ARG:.*]] = addrspacecast %[[A]]* %{{.*}} to i8 addrspace(4)*
+  //CHECK: %[[RET:.*]] = call i8 addrspace(1)* @to_global(i8 addrspace(4)* %[[ARG]])
+  //CHECK: %{{.*}} = bitcast i8 addrspace(1)* %[[RET]] to %[[A]] addrspace(1)*
+  PA pA;
+  GA gA = to_global(pA);
+
+  //CHECK-NOT: addrspacecast
+  //CHECK-NOT: bitcast
+  //CHECK: call i8 addrspace(1)* @to_global(i8 addrspace(4)* %{{.*}})
+  //CHECK-NOT: addrspacecast
+  //CHECK-NOT: bitcast
+  generic void *gen_v;
+  global void *glob_v = to_global(gen_v);
+}
diff --git a/test/SemaOpenCL/to_addr_builtin.cl b/test/SemaOpenCL/to_addr_builtin.cl
new file mode 100644
index 0000000000..5fefaa5adc
--- /dev/null
+++ b/test/SemaOpenCL/to_addr_builtin.cl
@@ -0,0 +1,54 @@
+// RUN: %clang_cc1 -verify -fsyntax-only %s
+// RUN: %clang_cc1 -verify -fsyntax-only -cl-std=CL2.0 %s
+
+void test(void) {
+  global int *glob;
+  local int *loc;
+  constant int *con;
+  typedef constant int const_int_ty;
+  const_int_ty *con_typedef;
+
+  glob = to_global(glob, loc);
+#if __OPENCL_C_VERSION__ < CL_VERSION_2_0
+  // expected-error@-2{{'to_global' requires OpenCL version 2.0 or above}}
+#else
+  // expected-error@-4{{invalid number of arguments to function: 'to_global'}}
+#endif
+
+  int x;
+  glob = to_global(x);
+#if __OPENCL_C_VERSION__ < CL_VERSION_2_0
+  // expected-error@-2{{'to_global' requires OpenCL version 2.0 or above}}
+#else
+  // expected-error@-4{{invalid argument x to function: 'to_global', expecting a generic pointer argument}}
+#endif
+
+  glob = to_global(con);
+#if __OPENCL_C_VERSION__ < CL_VERSION_2_0
+  // expected-error@-2{{'to_global' requires OpenCL version 2.0 or above}}
+#else
+  // expected-error@-4{{invalid argument con to function: 'to_global', expecting a generic pointer argument}}
+#endif
+
+  glob = to_global(con_typedef);
+#if __OPENCL_C_VERSION__ < CL_VERSION_2_0
+  // expected-error@-2{{'to_global' requires OpenCL version 2.0 or above}}
+#else
+  // expected-error@-4{{invalid argument con_typedef to function: 'to_global', expecting a generic pointer argument}}
+#endif
+
+  loc = to_global(glob);
+#if __OPENCL_C_VERSION__ < CL_VERSION_2_0
+  // expected-error@-2{{'to_global' requires OpenCL version 2.0 or above}}
+#else
+  // expected-error@-4{{assigning '__global int *' to '__local int *' changes address space of pointer}}
+#endif
+
+  global char *glob_c = to_global(loc);
+#if __OPENCL_C_VERSION__ < CL_VERSION_2_0
+  // expected-error@-2{{'to_global' requires OpenCL version 2.0 or above}}
+#else
+  // expected-warning@-4{{incompatible pointer types initializing '__global char *' with an expression of type '__global int *'}}
+#endif
+
+}