intel/llvm
1
0
Fork 0
mirror of https://github.com/intel/llvm.git synced 2026-02-03 19:18:13 +08:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
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

llvm-svn: 363435
This commit is contained in:
Gheorghe-Teodor Bercea
2019-06-14 17:58:26 +00:00
parent f79d3bc724
commit 5254f0a9ab
4 changed files with 22 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
clang/lib/CodeGen/CGOpenMPRuntime.cpp
View File

@@ -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) {

3
clang/lib/CodeGen/CGOpenMPRuntime.h
View File

@@ -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.

3
clang/lib/Sema/SemaOpenMP.cpp
View File

@@ -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();

29
clang/test/OpenMP/nvptx_target_requires_unified_shared_memory.cpp
View File

@@ -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