[OpenMP] Avoid emitting maps for target link variables when unified memory is used

Summary: This patch avoids the emission of maps for target link variables when unified memory is present.

Reviewers: ABataev, caomhin

Reviewed By: ABataev

Subscribers: guansong, jdoerfert, cfe-commits

Tags: #clang

Differential Revision: https://reviews.llvm.org/D60883

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@363435 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/CGOpenMPRuntime.cpp b/lib/CodeGen/CGOpenMPRuntime.cpp
index 651cca4993cee960aed7c9b2de48cdd09c7c788c..09be478a265d03e3d9e9af7f708b962314f08630 100644 (file)
--- a/lib/CodeGen/CGOpenMPRuntime.cpp
+++ b/lib/CodeGen/CGOpenMPRuntime.cpp
@@ -8266,7 +8266,8 @@ public:
           continue;
         llvm::Optional<OMPDeclareTargetDeclAttr::MapTypeTy> Res =
             OMPDeclareTargetDeclAttr::isDeclareTargetDeclaration(VD);
-        if (!Res || *Res != OMPDeclareTargetDeclAttr::MT_Link)
+        if (CGF.CGM.getOpenMPRuntime().hasRequiresUnifiedSharedMemory() ||
+            !Res || *Res != OMPDeclareTargetDeclAttr::MT_Link)
           continue;
         StructRangeInfoTy PartialStruct;
         generateInfoForComponentList(
@@ -9251,6 +9252,10 @@ bool CGOpenMPRuntime::hasAllocateAttributeForGlobalVar(const VarDecl *VD,
   return false;
 }
 
+bool CGOpenMPRuntime::hasRequiresUnifiedSharedMemory() const {
+  return HasRequiresUnifiedSharedMemory;
+}
+
 CGOpenMPRuntime::DisableAutoDeclareTargetRAII::DisableAutoDeclareTargetRAII(
     CodeGenModule &CGM)
     : CGM(CGM) {

diff --git a/lib/CodeGen/CGOpenMPRuntime.h b/lib/CodeGen/CGOpenMPRuntime.h
index 1a26620dc70d64129da82525fa74d10269280371..5be322de23983b1201a635b05c4f4c2f4929352a 100644 (file)
--- a/lib/CodeGen/CGOpenMPRuntime.h
+++ b/lib/CodeGen/CGOpenMPRuntime.h
@@ -1623,6 +1623,9 @@ public:
   /// the predefined allocator and translates it into the corresponding address
   /// space.
   virtual bool hasAllocateAttributeForGlobalVar(const VarDecl *VD, LangAS &AS);
+
+  /// Return whether the unified_shared_memory has been specified.
+  bool hasRequiresUnifiedSharedMemory() const;
 };
 
 /// Class supports emissionof SIMD-only code.

diff --git a/lib/Sema/SemaOpenMP.cpp b/lib/Sema/SemaOpenMP.cpp
index 7e75a98070878ca90c59d82dac2bf1d928414172..a4eafb180a18563dd92087a931e1edb24dbb149b 100644 (file)
--- a/lib/Sema/SemaOpenMP.cpp
+++ b/lib/Sema/SemaOpenMP.cpp
@@ -2667,7 +2667,8 @@ public:
       llvm::Optional<OMPDeclareTargetDeclAttr::MapTypeTy> Res =
           OMPDeclareTargetDeclAttr::isDeclareTargetDeclaration(VD);
       if (VD->hasGlobalStorage() && CS && !CS->capturesVariable(VD) &&
-          (!Res || *Res != OMPDeclareTargetDeclAttr::MT_Link))
+          (Stack->hasRequiresDeclWithClause<OMPUnifiedSharedMemoryClause>() ||
+           !Res || *Res != OMPDeclareTargetDeclAttr::MT_Link))
         return;
 
       SourceLocation ELoc = E->getExprLoc();

diff --git a/test/OpenMP/nvptx_target_requires_unified_shared_memory.cpp b/test/OpenMP/nvptx_target_requires_unified_shared_memory.cpp
index 6ce2ffb45e3ccce0528cda9233984436e0d65a7c..8349649f6af2e02d38adf4092fed5365ce09a9f7 100644 (file)
--- a/test/OpenMP/nvptx_target_requires_unified_shared_memory.cpp
+++ b/test/OpenMP/nvptx_target_requires_unified_shared_memory.cpp
@@ -26,42 +26,35 @@ int bar(int n){
 // CHECK: [[VAR:@.+]] = global double 1.000000e+01
 // CHECK: [[VAR_DECL_TGT_LINK_PTR:@.+]] = global double* [[VAR]]
 
-// CHECK: [[OFFLOAD_SIZES:@.+]] = private unnamed_addr constant [3 x i64] [i64 4, i64 8, i64 8]
-// CHECK: [[OFFLOAD_MAPTYPES:@.+]] = private unnamed_addr constant [3 x i64] [i64 800, i64 800, i64 531]
+// CHECK: [[OFFLOAD_SIZES:@.+]] = private unnamed_addr constant [2 x i64] [i64 4, i64 8]
+// CHECK: [[OFFLOAD_MAPTYPES:@.+]] = private unnamed_addr constant [2 x i64] [i64 800, i64 800]
 
 // CHECK: [[N_CASTED:%.+]] = alloca i64
 // CHECK: [[SUM_CASTED:%.+]] = alloca i64
 
-// CHECK: [[OFFLOAD_BASEPTRS:%.+]] = alloca [3 x i8*]
-// CHECK: [[OFFLOAD_PTRS:%.+]] = alloca [3 x i8*]
+// CHECK: [[OFFLOAD_BASEPTRS:%.+]] = alloca [2 x i8*]
+// CHECK: [[OFFLOAD_PTRS:%.+]] = alloca [2 x i8*]
 
 // CHECK: [[LOAD1:%.+]] = load i64, i64* [[N_CASTED]]
 // CHECK: [[LOAD2:%.+]] = load i64, i64* [[SUM_CASTED]]
 
-// CHECK: [[BPTR1:%.+]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[OFFLOAD_BASEPTRS]], i32 0, i32 0
+// CHECK: [[BPTR1:%.+]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[OFFLOAD_BASEPTRS]], i32 0, i32 0
 // CHECK: [[BCAST1:%.+]] = bitcast i8** [[BPTR1]] to i64*
 // CHECK: store i64 [[LOAD1]], i64* [[BCAST1]]
-// CHECK: [[BPTR2:%.+]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[OFFLOAD_PTRS]], i32 0, i32 0
+// CHECK: [[BPTR2:%.+]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[OFFLOAD_PTRS]], i32 0, i32 0
 // CHECK: [[BCAST2:%.+]] = bitcast i8** [[BPTR2]] to i64*
 // CHECK: store i64 [[LOAD1]], i64* [[BCAST2]]
 
-// CHECK: [[BPTR3:%.+]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[OFFLOAD_BASEPTRS]], i32 0, i32 1
+// CHECK: [[BPTR3:%.+]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[OFFLOAD_BASEPTRS]], i32 0, i32 1
 // CHECK: [[BCAST3:%.+]] = bitcast i8** [[BPTR3]] to i64*
 // CHECK: store i64 [[LOAD2]], i64* [[BCAST3]]
-// CHECK: [[BPTR4:%.+]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[OFFLOAD_PTRS]], i32 0, i32 1
+// CHECK: [[BPTR4:%.+]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[OFFLOAD_PTRS]], i32 0, i32 1
 // CHECK: [[BCAST4:%.+]] = bitcast i8** [[BPTR4]] to i64*
 // CHECK: store i64 [[LOAD2]], i64* [[BCAST4]]
 
-// CHECK: [[BPTR5:%.+]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[OFFLOAD_BASEPTRS]], i32 0, i32 2
-// CHECK: [[BCAST5:%.+]] = bitcast i8** [[BPTR5]] to double***
-// CHECK: store double** [[VAR_DECL_TGT_LINK_PTR]], double*** [[BCAST5]]
-// CHECK: [[BPTR6:%.+]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[OFFLOAD_PTRS]], i32 0, i32 2
-// CHECK: [[BCAST6:%.+]] = bitcast i8** [[BPTR6]] to double**
-// CHECK: store double* [[VAR]], double** [[BCAST6]]
+// CHECK: [[BPTR7:%.+]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[OFFLOAD_BASEPTRS]], i32 0, i32 0
+// CHECK: [[BPTR8:%.+]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[OFFLOAD_PTRS]], i32 0, i32 0
 
-// CHECK: [[BPTR7:%.+]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[OFFLOAD_BASEPTRS]], i32 0, i32 0
-// CHECK: [[BPTR8:%.+]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[OFFLOAD_PTRS]], i32 0, i32 0
-
-// CHECK: call i32 @__tgt_target(i64 -1, i8* @{{.*}}.region_id, i32 3, i8** [[BPTR7]], i8** [[BPTR8]], i64* getelementptr inbounds ([3 x i64], [3 x i64]* [[OFFLOAD_SIZES]], i32 0, i32 0), i64* getelementptr inbounds ([3 x i64], [3 x i64]* [[OFFLOAD_MAPTYPES]], i32 0, i32 0))
+// CHECK: call i32 @__tgt_target(i64 -1, i8* @{{.*}}.region_id, i32 2, i8** [[BPTR7]], i8** [[BPTR8]], i64* getelementptr inbounds ([2 x i64], [2 x i64]* [[OFFLOAD_SIZES]], i32 0, i32 0), i64* getelementptr inbounds ([2 x i64], [2 x i64]* [[OFFLOAD_MAPTYPES]], i32 0, i32 0))
 
 #endif