[Flang] Add translation support for MutexInOutSet and InOutSet (#120715)

Implementatoin details: Both Mutexinoutset and Inoutset is recognized as flag=0x4 and 0x8 respectively, the flags is set to `kmp_depend_info` and passed as argument to `__kmpc_omp_task_with_deps` runtime call
intel · Dec 26, 2024 · cbe583b · cbe583b
1 parent 9f75b66
commit cbe583b
Show file tree

Hide file tree

Showing 8 changed files with 73 additions and 33 deletions.
diff --git a/flang/lib/Lower/OpenMP/ClauseProcessor.cpp b/flang/lib/Lower/OpenMP/ClauseProcessor.cpp
@@ -153,10 +153,13 @@ genDependKindAttr(lower::AbstractConverter &converter,
     pbKind = mlir::omp::ClauseTaskDepend::taskdependinout;
     break;
   case omp::clause::DependenceType::Mutexinoutset:
+    pbKind = mlir::omp::ClauseTaskDepend::taskdependmutexinoutset;
+    break;
   case omp::clause::DependenceType::Inoutset:
+    pbKind = mlir::omp::ClauseTaskDepend::taskdependinoutset;
+    break;
   case omp::clause::DependenceType::Depobj:
-    TODO(currentLocation,
-         "INOUTSET, MUTEXINOUTSET and DEPOBJ dependence-types");
+    TODO(currentLocation, "DEPOBJ dependence-type");
     break;
   case omp::clause::DependenceType::Sink:
   case omp::clause::DependenceType::Source:

diff --git a/flang/test/Lower/OpenMP/Todo/depend-clause-depobj.f90 b/flang/test/Lower/OpenMP/Todo/depend-clause-depobj.f90
@@ -1,7 +1,7 @@
 !RUN: %not_todo_cmd bbc -emit-hlfir -fopenmp -fopenmp-version=52 -o - %s 2>&1 | FileCheck %s
 !RUN: %not_todo_cmd %flang_fc1 -emit-hlfir -fopenmp -fopenmp-version=52 -o - %s 2>&1 | FileCheck %s
 
-!CHECK: not yet implemented: INOUTSET, MUTEXINOUTSET and DEPOBJ dependence-types
+!CHECK: not yet implemented: DEPOBJ dependence-type
 
 subroutine f00(x)
   integer :: x

diff --git a/flang/test/Lower/OpenMP/Todo/depend-clause-inoutset.f90 b/flang/test/Lower/OpenMP/Todo/depend-clause-inoutset.f90
diff --git a/flang/test/Lower/OpenMP/Todo/depend-clause-mutexinoutset.f90 b/flang/test/Lower/OpenMP/Todo/depend-clause-mutexinoutset.f90
diff --git a/flang/test/Lower/OpenMP/task.f90 b/flang/test/Lower/OpenMP/task.f90
@@ -144,6 +144,18 @@ subroutine task_depend_multi_task()
   x = x + 12
   !CHECK: omp.terminator
   !$omp end task
+  !CHECK: omp.task depend(taskdependmutexinoutset -> %{{.+}} : !fir.ref<i32>)
+  !$omp task depend(mutexinoutset : x)
+  !CHECK: arith.subi
+  x = x - 12
+  !CHECK: omp.terminator
+  !$omp end task
+    !CHECK: omp.task depend(taskdependinoutset -> %{{.+}} : !fir.ref<i32>)
+  !$omp task depend(inoutset : x)
+  !CHECK: arith.subi
+  x = x - 12
+  !CHECK: omp.terminator
+  !$omp end task
 end subroutine task_depend_multi_task
 
 !===============================================================================

diff --git a/mlir/include/mlir/Dialect/OpenMP/OpenMPEnums.td b/mlir/include/mlir/Dialect/OpenMP/OpenMPEnums.td
@@ -108,14 +108,15 @@ def ClauseRequiresAttr : OpenMP_EnumAttr<ClauseRequires, "clause_requires">;
 def ClauseTaskDependIn : I32EnumAttrCase<"taskdependin", 0>;
 def ClauseTaskDependOut : I32EnumAttrCase<"taskdependout", 1>;
 def ClauseTaskDependInOut : I32EnumAttrCase<"taskdependinout", 2>;
-
-def ClauseTaskDepend : OpenMP_I32EnumAttr<
-    "ClauseTaskDepend",
-    "depend clause in a target or task construct", [
-      ClauseTaskDependIn,
-      ClauseTaskDependOut,
-      ClauseTaskDependInOut
-    ]>;
+def ClauseTaskDependMutexInOutSet
+    : I32EnumAttrCase<"taskdependmutexinoutset", 3>;
+def ClauseTaskDependInOutSet : I32EnumAttrCase<"taskdependinoutset", 4>;
+
+def ClauseTaskDepend
+    : OpenMP_I32EnumAttr<
+          "ClauseTaskDepend", "depend clause in a target or task construct",
+          [ClauseTaskDependIn, ClauseTaskDependOut, ClauseTaskDependInOut,
+           ClauseTaskDependMutexInOutSet, ClauseTaskDependInOutSet]>;
 
 def ClauseTaskDependAttr : OpenMP_EnumAttr<ClauseTaskDepend,
                                            "clause_task_depend"> {

diff --git a/mlir/lib/Target/LLVMIR/Dialect/OpenMP/OpenMPToLLVMIRTranslation.cpp b/mlir/lib/Target/LLVMIR/Dialect/OpenMP/OpenMPToLLVMIRTranslation.cpp
@@ -1701,6 +1701,12 @@ buildDependData(std::optional<ArrayAttr> dependKinds, OperandRange dependVars,
     case mlir::omp::ClauseTaskDepend::taskdependinout:
       type = llvm::omp::RTLDependenceKindTy::DepInOut;
       break;
+    case mlir::omp::ClauseTaskDepend::taskdependmutexinoutset:
+      type = llvm::omp::RTLDependenceKindTy::DepMutexInOutSet;
+      break;
+    case mlir::omp::ClauseTaskDepend::taskdependinoutset:
+      type = llvm::omp::RTLDependenceKindTy::DepInOutSet;
+      break;
     };
     llvm::Value *depVal = moduleTranslation.lookupValue(std::get<0>(dep));
     llvm::OpenMPIRBuilder::DependData dd(type, depVal->getType(), depVal);

diff --git a/mlir/test/Target/LLVMIR/openmp-llvm.mlir b/mlir/test/Target/LLVMIR/openmp-llvm.mlir
@@ -2590,6 +2590,34 @@ llvm.func @omp_task_attrs() -> () attributes {
 // CHECK:  store i64 8, ptr %[[dep_arr_addr_0_size]], align 4
 // CHECK:  %[[dep_arr_addr_0_kind:.+]] = getelementptr inbounds nuw %struct.kmp_dep_info, ptr %[[dep_arr_addr_0]], i32 0, i32 2
 // CHECK: store i8 1, ptr %[[dep_arr_addr_0_kind]], align 1
+// -----
+// dependence_type: Out
+// CHECK:  %[[DEP_ARR_ADDR1:.+]] = alloca [1 x %struct.kmp_dep_info], align 8
+// CHECK:  %[[DEP_ARR_ADDR_1:.+]] = getelementptr inbounds [1 x %struct.kmp_dep_info], ptr %[[DEP_ARR_ADDR1]], i64 0, i64 0
+//         [...]
+// CHECK:  %[[DEP_TYPE_1:.+]] = getelementptr inbounds nuw %struct.kmp_dep_info, ptr %[[DEP_ARR_ADDR_1]], i32 0, i32 2
+// CHECK:  store i8 3, ptr %[[DEP_TYPE_1]], align 1
+// -----
+// dependence_type: Inout
+// CHECK:  %[[DEP_ARR_ADDR2:.+]] = alloca [1 x %struct.kmp_dep_info], align 8
+// CHECK:  %[[DEP_ARR_ADDR_2:.+]] = getelementptr inbounds [1 x %struct.kmp_dep_info], ptr %[[DEP_ARR_ADDR2]], i64 0, i64 0
+//         [...]
+// CHECK:  %[[DEP_TYPE_2:.+]] = getelementptr inbounds nuw %struct.kmp_dep_info, ptr %[[DEP_ARR_ADDR_2]], i32 0, i32 2
+// CHECK:  store i8 3, ptr %[[DEP_TYPE_2]], align 1
+// -----
+// dependence_type: Mutexinoutset
+// CHECK:  %[[DEP_ARR_ADDR3:.+]] = alloca [1 x %struct.kmp_dep_info], align 8
+// CHECK:  %[[DEP_ARR_ADDR_3:.+]] = getelementptr inbounds [1 x %struct.kmp_dep_info], ptr %[[DEP_ARR_ADDR3]], i64 0, i64 0
+//         [...]
+// CHECK:  %[[DEP_TYPE_3:.+]] = getelementptr inbounds nuw %struct.kmp_dep_info, ptr %[[DEP_ARR_ADDR_3]], i32 0, i32 2
+// CHECK:  store i8 4, ptr %[[DEP_TYPE_3]], align 1
+// -----
+// dependence_type: Inoutset
+// CHECK:  %[[DEP_ARR_ADDR4:.+]] = alloca [1 x %struct.kmp_dep_info], align 8
+// CHECK:  %[[DEP_ARR_ADDR_4:.+]] = getelementptr inbounds [1 x %struct.kmp_dep_info], ptr %[[DEP_ARR_ADDR4]], i64 0, i64 0
+//         [...]
+// CHECK:  %[[DEP_TYPE_4:.+]] = getelementptr inbounds nuw %struct.kmp_dep_info, ptr %[[DEP_ARR_ADDR_4]], i32 0, i32 2
+// CHECK:  store i8 8, ptr %[[DEP_TYPE_4]], align 1
 llvm.func @omp_task_with_deps(%zaddr: !llvm.ptr) {
   // CHECK: %[[omp_global_thread_num:.+]] = call i32 @__kmpc_global_thread_num({{.+}})
   // CHECK: %[[task_data:.+]] = call ptr @__kmpc_omp_task_alloc
@@ -2604,6 +2632,18 @@ llvm.func @omp_task_with_deps(%zaddr: !llvm.ptr) {
     llvm.store %double, %valaddr : i32, !llvm.ptr
     omp.terminator
   }
+  omp.task depend(taskdependout -> %zaddr : !llvm.ptr) {
+    omp.terminator
+  }
+  omp.task depend(taskdependinout -> %zaddr : !llvm.ptr) {
+    omp.terminator
+  }
+  omp.task depend(taskdependmutexinoutset -> %zaddr : !llvm.ptr) {
+    omp.terminator
+  }
+  omp.task depend(taskdependinoutset -> %zaddr : !llvm.ptr) {
+    omp.terminator
+  }
   llvm.return
 }