[llvm] b7c17ab - [MLIR][OpenMP] Add Initial Taskloop Clause Support (#174623)
via llvm-commits
llvm-commits at lists.llvm.org
Fri Jan 9 02:34:09 PST 2026
Author: Jack Styles
Date: 2026-01-09T10:34:03Z
New Revision: b7c17ab9576ccd030572872ad1c22de345b5244b
URL: https://github.com/llvm/llvm-project/commit/b7c17ab9576ccd030572872ad1c22de345b5244b
DIFF: https://github.com/llvm/llvm-project/commit/b7c17ab9576ccd030572872ad1c22de345b5244b.diff
LOG: [MLIR][OpenMP] Add Initial Taskloop Clause Support (#174623)
Following on from the work to implement MLIR -> LLVM IR Translation for
Taskloop, this adds support for the following clauses to be used
alongside taskloop:
- if
- grainsize
- num_tasks
- untied
- Nogroup
- Final
- Mergeable
- Priority
These clauses are ones which work directly through the relevant OpenMP
Runtime functions, so their information just needed collecting from the
relevant location and passing through to the appropriate runtime
function.
Remaining clauses retain their TODO message as they have not yet been
implemented.
Added:
mlir/test/Target/LLVMIR/openmp-taskloop-final.mlir
mlir/test/Target/LLVMIR/openmp-taskloop-grainsize.mlir
mlir/test/Target/LLVMIR/openmp-taskloop-if.mlir
mlir/test/Target/LLVMIR/openmp-taskloop-mergeable.mlir
mlir/test/Target/LLVMIR/openmp-taskloop-nogroup.mlir
mlir/test/Target/LLVMIR/openmp-taskloop-num_tasks.mlir
mlir/test/Target/LLVMIR/openmp-taskloop-priority.mlir
mlir/test/Target/LLVMIR/openmp-taskloop-untied.mlir
Modified:
llvm/include/llvm/Frontend/OpenMP/OMPIRBuilder.h
llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
mlir/lib/Target/LLVMIR/Dialect/OpenMP/OpenMPToLLVMIRTranslation.cpp
mlir/test/Target/LLVMIR/openmp-todo.mlir
Removed:
################################################################################
diff --git a/llvm/include/llvm/Frontend/OpenMP/OMPIRBuilder.h b/llvm/include/llvm/Frontend/OpenMP/OMPIRBuilder.h
index d720a1b457d56..15d48c84dc339 100644
--- a/llvm/include/llvm/Frontend/OpenMP/OMPIRBuilder.h
+++ b/llvm/include/llvm/Frontend/OpenMP/OMPIRBuilder.h
@@ -1466,7 +1466,22 @@ class OpenMPIRBuilder {
/// \param LBVal Lowerbound value of loop
/// \param UBVal Upperbound value of loop
/// \param StepVal Step value of loop
- /// \param Tied True if the task is tied, false if the task is untied.
+ /// \param Untied True if the task is untied, false if the task is tied.
+ /// \param IfCond i1 value. If it evaluates to `false`, an undeferred
+ /// task is generated, and the encountering thread must
+ /// suspend the current task region, for which execution
+ /// cannot be resumed until execution of the structured
+ /// block that is associated with the generated task is
+ /// completed.
+ /// \param GrainSize Value of the GrainSize/Num of Tasks if present
+ /// \param NoGroup False if NoGroup is defined, true if not
+ /// \param Sched If Grainsize is defined, Sched is 1. Num Tasks, Shed is 2.
+ /// Otherwise Sched is 0
+ /// \param Final i1 value which is `true` if the task is final, `false` if the
+ /// task is not final.
+ /// \param Mergeable If the given task is `mergeable`
+ /// \param Priority `priority-value' specifies the execution order of the
+ /// tasks that is generated by the construct
/// \param DupCB The callback to generate the duplication code. See
/// documentation for \ref TaskDupCallbackTy. This can be nullptr.
/// \param TaskContextStructPtrVal If non-null, a pointer to to be placed
@@ -1476,8 +1491,10 @@ class OpenMPIRBuilder {
const LocationDescription &Loc, InsertPointTy AllocaIP,
BodyGenCallbackTy BodyGenCB,
llvm::function_ref<llvm::Expected<llvm::CanonicalLoopInfo *>()> LoopInfo,
- Value *LBVal, Value *UBVal, Value *StepVal, bool Tied = true,
- TaskDupCallbackTy DupCB = nullptr,
+ Value *LBVal, Value *UBVal, Value *StepVal, bool Untied = false,
+ Value *IfCond = nullptr, Value *GrainSize = nullptr, bool NoGroup = false,
+ int Sched = 0, Value *Final = nullptr, bool Mergeable = false,
+ Value *Priority = nullptr, TaskDupCallbackTy DupCB = nullptr,
Value *TaskContextStructPtrVal = nullptr);
/// Generator for `#omp task`
diff --git a/llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp b/llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
index 4acb6595ecd3a..50b1bcb1bb9aa 100644
--- a/llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
+++ b/llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
@@ -2096,8 +2096,9 @@ OpenMPIRBuilder::InsertPointOrErrorTy OpenMPIRBuilder::createTaskloop(
const LocationDescription &Loc, InsertPointTy AllocaIP,
BodyGenCallbackTy BodyGenCB,
llvm::function_ref<llvm::Expected<llvm::CanonicalLoopInfo *>()> LoopInfo,
- Value *LBVal, Value *UBVal, Value *StepVal, bool Tied,
- TaskDupCallbackTy DupCB, Value *TaskContextStructPtrVal) {
+ Value *LBVal, Value *UBVal, Value *StepVal, bool Untied, Value *IfCond,
+ Value *GrainSize, bool NoGroup, int Sched, Value *Final, bool Mergeable,
+ Value *Priority, TaskDupCallbackTy DupCB, Value *TaskContextStructPtrVal) {
if (!updateToLocation(Loc))
return InsertPointTy();
@@ -2172,9 +2173,11 @@ OpenMPIRBuilder::InsertPointOrErrorTy OpenMPIRBuilder::createTaskloop(
}
Value *TaskDupFn = *TaskDupFnOrErr;
- OI.PostOutlineCB = [this, Ident, LBVal, UBVal, StepVal, Tied,
+ OI.PostOutlineCB = [this, Ident, LBVal, UBVal, StepVal, Untied,
TaskloopAllocaBB, CLI, Loc, TaskDupFn, ToBeDeleted,
- FakeLB, FakeUB, FakeStep](Function &OutlinedFn) mutable {
+ IfCond, GrainSize, NoGroup, Sched, FakeLB, FakeUB,
+ FakeStep, Final, Mergeable,
+ Priority](Function &OutlinedFn) mutable {
// Replace the Stale CI by appropriate RTL function call.
assert(OutlinedFn.hasOneUse() &&
"there must be a single user for the outlined function");
@@ -2202,13 +2205,29 @@ OpenMPIRBuilder::InsertPointOrErrorTy OpenMPIRBuilder::createTaskloop(
Value *ThreadID = getOrCreateThreadID(Ident);
- // Emit runtime call for @__kmpc_taskgroup
- Function *TaskgroupFn =
- getOrCreateRuntimeFunctionPtr(OMPRTL___kmpc_taskgroup);
- Builder.CreateCall(TaskgroupFn, {Ident, ThreadID});
+ if (!NoGroup) {
+ // Emit runtime call for @__kmpc_taskgroup
+ Function *TaskgroupFn =
+ getOrCreateRuntimeFunctionPtr(OMPRTL___kmpc_taskgroup);
+ Builder.CreateCall(TaskgroupFn, {Ident, ThreadID});
+ }
- // The flags are set to 1 if the task is tied, 0 otherwise.
- Value *Flags = Builder.getInt32(Tied);
+ // `flags` Argument Configuration
+ // Task is tied if (Flags & 1) == 1.
+ // Task is untied if (Flags & 1) == 0.
+ // Task is final if (Flags & 2) == 2.
+ // Task is not final if (Flags & 2) == 0.
+ // Task is mergeable if (Flags & 4) == 4.
+ // Task is not mergeable if (Flags & 4) == 0.
+ // Task is priority if (Flags & 32) == 32.
+ // Task is not priority if (Flags & 32) == 0.
+ Value *Flags = Builder.getInt32(Untied ? 0 : 1);
+ if (Final)
+ Flags = Builder.CreateOr(Builder.getInt32(2), Flags);
+ if (Mergeable)
+ Flags = Builder.CreateOr(Builder.getInt32(4), Flags);
+ if (Priority)
+ Flags = Builder.CreateOr(Builder.getInt32(32), Flags);
Value *TaskSize = Builder.getInt64(
divideCeil(M.getDataLayout().getTypeSizeInBits(Task), 8));
@@ -2251,25 +2270,34 @@ OpenMPIRBuilder::InsertPointOrErrorTy OpenMPIRBuilder::createTaskloop(
llvm::Value *Loadstep = Builder.CreateLoad(Builder.getInt64Ty(), Step);
// set up the arguments for emitting kmpc_taskloop runtime call
- // setting default values for ifval, nogroup, sched, grainsize, task_dup
- Value *IfVal = Builder.getInt32(1);
- Value *NoGroup = Builder.getInt32(1);
- Value *Sched = Builder.getInt32(0);
- Value *GrainSize = Builder.getInt64(0);
+ // setting values for ifval, nogroup, sched, grainsize, task_dup
+ Value *IfCondVal =
+ IfCond ? Builder.CreateIntCast(IfCond, Builder.getInt32Ty(), true)
+ : Builder.getInt32(1);
+ // As __kmpc_taskgroup is called manually in OMPIRBuilder, NoGroupVal should
+ // always be 1 when calling __kmpc_taskloop to ensure it is not called again
+ Value *NoGroupVal = Builder.getInt32(1);
+ Value *SchedVal = Builder.getInt32(Sched);
+ Value *GrainSizeVal =
+ GrainSize ? Builder.CreateIntCast(GrainSize, Builder.getInt64Ty(), true)
+ : Builder.getInt64(0);
Value *TaskDup = TaskDupFn;
- Value *Args[] = {Ident, ThreadID, TaskData, IfVal, Lb, Ub,
- Loadstep, NoGroup, Sched, GrainSize, TaskDup};
+ Value *Args[] = {Ident, ThreadID, TaskData, IfCondVal, Lb, Ub,
+ Loadstep, NoGroupVal, SchedVal, GrainSizeVal, TaskDup};
// taskloop runtime call
Function *TaskloopFn =
getOrCreateRuntimeFunctionPtr(OMPRTL___kmpc_taskloop);
Builder.CreateCall(TaskloopFn, Args);
- // Emit the @__kmpc_end_taskgroup runtime call to end the taskgroup
- Function *EndTaskgroupFn =
- getOrCreateRuntimeFunctionPtr(OMPRTL___kmpc_end_taskgroup);
- Builder.CreateCall(EndTaskgroupFn, {Ident, ThreadID});
+ // Emit the @__kmpc_end_taskgroup runtime call to end the taskgroup if
+ // nogroup is not defined
+ if (!NoGroup) {
+ Function *EndTaskgroupFn =
+ getOrCreateRuntimeFunctionPtr(OMPRTL___kmpc_end_taskgroup);
+ Builder.CreateCall(EndTaskgroupFn, {Ident, ThreadID});
+ }
StaleCI->eraseFromParent();
diff --git a/mlir/lib/Target/LLVMIR/Dialect/OpenMP/OpenMPToLLVMIRTranslation.cpp b/mlir/lib/Target/LLVMIR/Dialect/OpenMP/OpenMPToLLVMIRTranslation.cpp
index 3dbbdc6cd496d..3d79a83f295b4 100644
--- a/mlir/lib/Target/LLVMIR/Dialect/OpenMP/OpenMPToLLVMIRTranslation.cpp
+++ b/mlir/lib/Target/LLVMIR/Dialect/OpenMP/OpenMPToLLVMIRTranslation.cpp
@@ -353,26 +353,6 @@ static LogicalResult checkImplementationStatus(Operation &op) {
if (!op.getDependVars().empty() || op.getDependKinds())
result = todo("depend");
};
- auto checkFinal = [&todo](auto op, LogicalResult &result) {
- if (op.getFinal())
- result = todo("final");
- };
- auto checkGrainsize = [&todo](auto op, LogicalResult &result) {
- if (op.getGrainsize())
- result = todo("grainsize");
- };
- auto checkIf = [&todo](auto op, LogicalResult &result) {
- if (op.getIfExpr())
- result = todo("if");
- };
- auto checkMergeable = [&todo](auto op, LogicalResult &result) {
- if (op.getMergeable())
- result = todo("mergeable");
- };
- auto checkNogroup = [&todo](auto op, LogicalResult &result) {
- if (op.getNogroup())
- result = todo("nogroup");
- };
auto checkHint = [](auto op, LogicalResult &) {
if (op.getHint())
op.emitWarning("hint clause discarded");
@@ -386,10 +366,6 @@ static LogicalResult checkImplementationStatus(Operation &op) {
if (op.getNowait())
result = todo("nowait");
};
- auto checkNumTasks = [&todo](auto op, LogicalResult &result) {
- if (op.getNumTasks())
- result = todo("num_tasks");
- };
auto checkOrder = [&todo](auto op, LogicalResult &result) {
if (op.getOrder() || op.getOrderMod())
result = todo("order");
@@ -398,10 +374,6 @@ static LogicalResult checkImplementationStatus(Operation &op) {
if (op.getParLevelSimd())
result = todo("parallelization-level");
};
- auto checkPriority = [&todo](auto op, LogicalResult &result) {
- if (op.getPriority())
- result = todo("priority");
- };
auto checkPrivate = [&todo](auto op, LogicalResult &result) {
if (!op.getPrivateVars().empty() || op.getPrivateSyms())
result = todo("privatization");
@@ -420,10 +392,6 @@ static LogicalResult checkImplementationStatus(Operation &op) {
op.getTaskReductionSyms())
result = todo("task_reduction");
};
- auto checkUntied = [&todo](auto op, LogicalResult &result) {
- if (op.getUntied())
- result = todo("untied");
- };
LogicalResult result = success();
llvm::TypeSwitch<Operation &>(op)
@@ -467,16 +435,8 @@ static LogicalResult checkImplementationStatus(Operation &op) {
})
.Case([&](omp::TaskloopOp op) {
checkAllocate(op, result);
- checkFinal(op, result);
- checkGrainsize(op, result);
- checkIf(op, result);
checkInReduction(op, result);
- checkMergeable(op, result);
- checkNogroup(op, result);
- checkNumTasks(op, result);
checkReduction(op, result);
- checkUntied(op, result);
- checkPriority(op, result);
})
.Case([&](omp::WsloopOp op) {
checkAllocate(op, result);
@@ -2854,6 +2814,21 @@ convertOmpTaskloopOp(Operation &opInst, llvm::IRBuilderBase &builder,
return loopInfo;
};
+ llvm::Value *ifCond = nullptr;
+ llvm::Value *grainsize = nullptr;
+ int sched = 0; // default
+ mlir::Value grainsizeVal = taskloopOp.getGrainsize();
+ mlir::Value numTasksVal = taskloopOp.getNumTasks();
+ if (Value ifVar = taskloopOp.getIfExpr())
+ ifCond = moduleTranslation.lookupValue(ifVar);
+ if (grainsizeVal) {
+ grainsize = moduleTranslation.lookupValue(grainsizeVal);
+ sched = 1; // grainsize
+ } else if (numTasksVal) {
+ grainsize = moduleTranslation.lookupValue(numTasksVal);
+ sched = 2; // num_tasks
+ }
+
llvm::OpenMPIRBuilder::TaskDupCallbackTy taskDupOrNull = nullptr;
if (!taskStructMgr.getLLVMPrivateVarGEPs().empty())
taskDupOrNull = taskDupCB;
@@ -2865,7 +2840,11 @@ convertOmpTaskloopOp(Operation &opInst, llvm::IRBuilderBase &builder,
moduleTranslation.lookupValue(loopOp.getLoopLowerBounds()[0]),
moduleTranslation.lookupValue(loopOp.getLoopUpperBounds()[0]),
moduleTranslation.lookupValue(loopOp.getLoopSteps()[0]),
- /*Tied=*/true, taskDupOrNull, taskStructMgr.getStructPtr());
+ taskloopOp.getUntied(), ifCond, grainsize, taskloopOp.getNogroup(),
+ sched, moduleTranslation.lookupValue(taskloopOp.getFinal()),
+ taskloopOp.getMergeable(),
+ moduleTranslation.lookupValue(taskloopOp.getPriority()),
+ taskDupOrNull, taskStructMgr.getStructPtr());
if (failed(handleError(afterIP, opInst)))
return failure();
diff --git a/mlir/test/Target/LLVMIR/openmp-taskloop-final.mlir b/mlir/test/Target/LLVMIR/openmp-taskloop-final.mlir
new file mode 100644
index 0000000000000..7034192612ba4
--- /dev/null
+++ b/mlir/test/Target/LLVMIR/openmp-taskloop-final.mlir
@@ -0,0 +1,39 @@
+// RUN: mlir-translate -mlir-to-llvmir %s | FileCheck %s
+
+omp.private {type = private} @_QFtestEi_private_i32 : i32
+
+omp.private {type = firstprivate} @_QFtestEa_firstprivate_i32 : i32 copy {
+^bb0(%arg0: !llvm.ptr, %arg1: !llvm.ptr):
+ %0 = llvm.load %arg0 : !llvm.ptr -> i32
+ llvm.store %0, %arg1 : i32, !llvm.ptr
+ omp.yield(%arg1 : !llvm.ptr)
+}
+
+
+llvm.func @_QPtest() {
+ %0 = llvm.mlir.constant(1 : i64) : i64
+ %1 = llvm.alloca %0 x i32 {bindc_name = "i"} : (i64) -> !llvm.ptr
+ %3 = llvm.alloca %0 x i32 {bindc_name = "a"} : (i64) -> !llvm.ptr
+ %6 = llvm.mlir.constant(20 : i32) : i32
+ llvm.store %6, %3 : i32, !llvm.ptr
+ %7 = llvm.mlir.constant(1 : i32) : i32
+ %8 = llvm.mlir.constant(5 : i32) : i32
+ %9 = llvm.mlir.constant(1 : i32) : i32
+ %true = llvm.mlir.constant(true) : i1
+ omp.taskloop final(%true) private(@_QFtestEa_firstprivate_i32 %3 -> %arg0, @_QFtestEi_private_i32 %1 -> %arg1 : !llvm.ptr, !llvm.ptr) {
+ omp.loop_nest (%arg2) : i32 = (%7) to (%8) inclusive step (%9) {
+ llvm.store %arg2, %arg1 : i32, !llvm.ptr
+ %10 = llvm.load %arg0 : !llvm.ptr -> i32
+ %11 = llvm.mlir.constant(1 : i32) : i32
+ %12 = llvm.add %10, %11 : i32
+ llvm.store %12, %arg0 : i32, !llvm.ptr
+ omp.yield
+ }
+ }
+ llvm.return
+}
+
+// CHECK: %[[omp_global_thread_num:.*]] = call i32 @__kmpc_global_thread_num(ptr @1)
+// CHECK: %[[VAL:.*]] = call ptr @__kmpc_omp_task_alloc(ptr @1, i32 %[[omp_global_thread_num]], i32 3, i64 40, i64 32, ptr @_QPtest..omp_par)
+
+// -----
diff --git a/mlir/test/Target/LLVMIR/openmp-taskloop-grainsize.mlir b/mlir/test/Target/LLVMIR/openmp-taskloop-grainsize.mlir
new file mode 100644
index 0000000000000..7b7451331ce30
--- /dev/null
+++ b/mlir/test/Target/LLVMIR/openmp-taskloop-grainsize.mlir
@@ -0,0 +1,46 @@
+// RUN: mlir-translate -mlir-to-llvmir %s | FileCheck %s
+
+omp.private {type = private} @_QFtestEi_private_i32 : i32
+
+omp.private {type = firstprivate} @_QFtestEa_firstprivate_i32 : i32 copy {
+^bb0(%arg0: !llvm.ptr, %arg1: !llvm.ptr):
+ %0 = llvm.load %arg0 : !llvm.ptr -> i32
+ llvm.store %0, %arg1 : i32, !llvm.ptr
+ omp.yield(%arg1 : !llvm.ptr)
+}
+
+
+llvm.func @_QPtest() {
+ %0 = llvm.mlir.constant(1 : i64) : i64
+ %1 = llvm.alloca %0 x i32 {bindc_name = "i"} : (i64) -> !llvm.ptr
+ %3 = llvm.alloca %0 x i32 {bindc_name = "a"} : (i64) -> !llvm.ptr
+ %6 = llvm.mlir.constant(20 : i32) : i32
+ llvm.store %6, %3 : i32, !llvm.ptr
+ %7 = llvm.mlir.constant(1 : i32) : i32
+ %8 = llvm.mlir.constant(5 : i32) : i32
+ %9 = llvm.mlir.constant(1 : i32) : i32
+ %c2_i32 = llvm.mlir.constant(2 : i32) : i32
+ omp.taskloop grainsize(%c2_i32: i32) private(@_QFtestEa_firstprivate_i32 %3 -> %arg0, @_QFtestEi_private_i32 %1 -> %arg1 : !llvm.ptr, !llvm.ptr) {
+ omp.loop_nest (%arg2) : i32 = (%7) to (%8) inclusive step (%9) {
+ llvm.store %arg2, %arg1 : i32, !llvm.ptr
+ %10 = llvm.load %arg0 : !llvm.ptr -> i32
+ %11 = llvm.mlir.constant(1 : i32) : i32
+ %12 = llvm.add %10, %11 : i32
+ llvm.store %12, %arg0 : i32, !llvm.ptr
+ omp.yield
+ }
+ }
+ llvm.return
+}
+
+// CHECK: %[[structArg:.*]] = alloca { i64, i64, i64, ptr }, align 8
+// CHECK: %[[omp_global_thread_num:.*]] = call i32 @__kmpc_global_thread_num(ptr @1)
+// CHECK: %[[VAL_1:.*]] = call ptr @__kmpc_omp_task_alloc(ptr @1, i32 %[[omp_global_thread_num]], i32 1, i64 40, i64 32, ptr @_QPtest..omp_par)
+// CHECK: %[[VAL_2:.*]] = load ptr, ptr %[[VAL_1]], align 8
+// CHECK: call void @llvm.memcpy.p0.p0.i64(ptr align 1 %[[VAL_2]], ptr align 1 %[[structArg]], i64 32, i1 false)
+// CHECK: %[[VAL_3:.*]] = getelementptr { i64, i64, i64, ptr }, ptr %[[VAL_2]], i32 0, i32 0
+// CHECK: %[[VAL_4:.*]] = getelementptr { i64, i64, i64, ptr }, ptr %[[VAL_2]], i32 0, i32 1
+// CHECK: %[[VAL_5:.*]] = getelementptr { i64, i64, i64, ptr }, ptr %[[VAL_2]], i32 0, i32 2
+// CHECK: %[[VAL_6:.*]] = load i64, ptr %[[VAL_5]], align 4
+// CHECK: call void @__kmpc_taskloop(ptr @1, i32 %omp_global_thread_num, ptr %5, i32 1, ptr %[[VAL_3]], ptr %[[VAL_4]], i64 %[[VAL_6]], i32 1, i32 1, i64 2, ptr @omp_taskloop_dup)
+
diff --git a/mlir/test/Target/LLVMIR/openmp-taskloop-if.mlir b/mlir/test/Target/LLVMIR/openmp-taskloop-if.mlir
new file mode 100644
index 0000000000000..f47b588e60a7d
--- /dev/null
+++ b/mlir/test/Target/LLVMIR/openmp-taskloop-if.mlir
@@ -0,0 +1,49 @@
+// RUN: mlir-translate -mlir-to-llvmir %s | FileCheck %s
+
+omp.private {type = private} @_QFtestEi_private_i32 : i32
+
+omp.private {type = firstprivate} @_QFtestEa_firstprivate_i32 : i32 copy {
+^bb0(%arg0: !llvm.ptr, %arg1: !llvm.ptr):
+ %0 = llvm.load %arg0 : !llvm.ptr -> i32
+ llvm.store %0, %arg1 : i32, !llvm.ptr
+ omp.yield(%arg1 : !llvm.ptr)
+}
+
+
+llvm.func @_QPtest() {
+ %0 = llvm.mlir.constant(1 : i64) : i64
+ %1 = llvm.alloca %0 x i32 {bindc_name = "i"} : (i64) -> !llvm.ptr
+ %3 = llvm.alloca %0 x i32 {bindc_name = "a"} : (i64) -> !llvm.ptr
+ %6 = llvm.mlir.constant(20 : i32) : i32
+ llvm.store %6, %3 : i32, !llvm.ptr
+ %7 = llvm.mlir.constant(1 : i32) : i32
+ %8 = llvm.mlir.constant(5 : i32) : i32
+ %9 = llvm.mlir.constant(1 : i32) : i32
+ %a_val = llvm.load %3 : !llvm.ptr -> i32
+ %c20 = llvm.mlir.constant(20 : i32) : i32
+ %cmp = llvm.icmp "slt" %a_val, %c20 : i32
+ omp.taskloop if(%cmp) private(@_QFtestEa_firstprivate_i32 %3 -> %arg0, @_QFtestEi_private_i32 %1 -> %arg1 : !llvm.ptr, !llvm.ptr) {
+ omp.loop_nest (%arg2) : i32 = (%7) to (%8) inclusive step (%9) {
+ llvm.store %arg2, %arg1 : i32, !llvm.ptr
+ %10 = llvm.load %arg0 : !llvm.ptr -> i32
+ %11 = llvm.mlir.constant(1 : i32) : i32
+ %12 = llvm.add %10, %11 : i32
+ llvm.store %12, %arg0 : i32, !llvm.ptr
+ omp.yield
+ }
+ }
+ llvm.return
+}
+
+// CHECK: define void @_QPtest() {
+// CHECK: %[[structArg:.*]] = alloca { i64, i64, i64, ptr }, align 8
+// CHECK: %[[omp_global_thread_num:.*]] = call i32 @__kmpc_global_thread_num(ptr @1)
+// CHECK: %[[VAL_1:.*]] = call ptr @__kmpc_omp_task_alloc(ptr @1, i32 %[[omp_global_thread_num]], i32 1, i64 40, i64 32, ptr @_QPtest..omp_par)
+// CHECK: %[[VAL_2:.*]] = load ptr, ptr %[[VAL_1]], align 8
+// CHECK: call void @llvm.memcpy.p0.p0.i64(ptr align 1 %[[VAL_2]], ptr align 1 %[[structArg]], i64 32, i1 false)
+// CHECK: %[[VAL_3:.*]] = getelementptr { i64, i64, i64, ptr }, ptr %[[VAL_2]], i32 0, i32 0
+// CHECK: %[[VAL_4:.*]] = getelementptr { i64, i64, i64, ptr }, ptr %[[VAL_2]], i32 0, i32 1
+// CHECK: %[[VAL_5:.*]] = getelementptr { i64, i64, i64, ptr }, ptr %[[VAL_2]], i32 0, i32 2
+// CHECK: %[[VAL_6:.*]] = load i64, ptr %[[VAL_5]], align 4
+// CHECK: %[[IF_VAL:.*]] = sext i1 %4 to i32
+// CHECK: call void @__kmpc_taskloop(ptr @1, i32 %[[omp_global_thread_num]], ptr %[[VAL_1]], i32 %[[IF_VAL]], ptr %[[VAL_3]], ptr %[[VAL_4]], i64 %[[VAL_6]], i32 1, i32 0, i64 0, ptr @omp_taskloop_dup)
diff --git a/mlir/test/Target/LLVMIR/openmp-taskloop-mergeable.mlir b/mlir/test/Target/LLVMIR/openmp-taskloop-mergeable.mlir
new file mode 100644
index 0000000000000..ba46fc9794e74
--- /dev/null
+++ b/mlir/test/Target/LLVMIR/openmp-taskloop-mergeable.mlir
@@ -0,0 +1,36 @@
+// RUN: mlir-translate -mlir-to-llvmir %s | FileCheck %s
+
+omp.private {type = private} @_QFtestEi_private_i32 : i32
+
+omp.private {type = firstprivate} @_QFtestEa_firstprivate_i32 : i32 copy {
+^bb0(%arg0: !llvm.ptr, %arg1: !llvm.ptr):
+ %0 = llvm.load %arg0 : !llvm.ptr -> i32
+ llvm.store %0, %arg1 : i32, !llvm.ptr
+ omp.yield(%arg1 : !llvm.ptr)
+}
+
+
+llvm.func @_QPtest() {
+ %0 = llvm.mlir.constant(1 : i64) : i64
+ %1 = llvm.alloca %0 x i32 {bindc_name = "i"} : (i64) -> !llvm.ptr
+ %3 = llvm.alloca %0 x i32 {bindc_name = "a"} : (i64) -> !llvm.ptr
+ %6 = llvm.mlir.constant(20 : i32) : i32
+ llvm.store %6, %3 : i32, !llvm.ptr
+ %7 = llvm.mlir.constant(1 : i32) : i32
+ %8 = llvm.mlir.constant(5 : i32) : i32
+ %9 = llvm.mlir.constant(1 : i32) : i32
+ omp.taskloop mergeable private(@_QFtestEa_firstprivate_i32 %3 -> %arg0, @_QFtestEi_private_i32 %1 -> %arg1 : !llvm.ptr, !llvm.ptr) {
+ omp.loop_nest (%arg2) : i32 = (%7) to (%8) inclusive step (%9) {
+ llvm.store %arg2, %arg1 : i32, !llvm.ptr
+ %10 = llvm.load %arg0 : !llvm.ptr -> i32
+ %11 = llvm.mlir.constant(1 : i32) : i32
+ %12 = llvm.add %10, %11 : i32
+ llvm.store %12, %arg0 : i32, !llvm.ptr
+ omp.yield
+ }
+ }
+ llvm.return
+}
+
+// CHECK: %[[omp_global_thread_num:.*]] = call i32 @__kmpc_global_thread_num(ptr @1)
+// CHECK: %[[VAL:.*]] = call ptr @__kmpc_omp_task_alloc(ptr @1, i32 %[[omp_global_thread_num]], i32 5, i64 40, i64 32, ptr @_QPtest..omp_par)
diff --git a/mlir/test/Target/LLVMIR/openmp-taskloop-nogroup.mlir b/mlir/test/Target/LLVMIR/openmp-taskloop-nogroup.mlir
new file mode 100644
index 0000000000000..b15b5721a67f8
--- /dev/null
+++ b/mlir/test/Target/LLVMIR/openmp-taskloop-nogroup.mlir
@@ -0,0 +1,46 @@
+// RUN: mlir-translate -mlir-to-llvmir %s | FileCheck %s
+
+omp.private {type = private} @_QFtestEi_private_i32 : i32
+
+omp.private {type = firstprivate} @_QFtestEa_firstprivate_i32 : i32 copy {
+^bb0(%arg0: !llvm.ptr, %arg1: !llvm.ptr):
+ %0 = llvm.load %arg0 : !llvm.ptr -> i32
+ llvm.store %0, %arg1 : i32, !llvm.ptr
+ omp.yield(%arg1 : !llvm.ptr)
+}
+
+
+llvm.func @_QPtest() {
+ %0 = llvm.mlir.constant(1 : i64) : i64
+ %1 = llvm.alloca %0 x i32 {bindc_name = "i"} : (i64) -> !llvm.ptr
+ %3 = llvm.alloca %0 x i32 {bindc_name = "a"} : (i64) -> !llvm.ptr
+ %6 = llvm.mlir.constant(20 : i32) : i32
+ llvm.store %6, %3 : i32, !llvm.ptr
+ %7 = llvm.mlir.constant(1 : i32) : i32
+ %8 = llvm.mlir.constant(5 : i32) : i32
+ %9 = llvm.mlir.constant(1 : i32) : i32
+ omp.taskloop nogroup private(@_QFtestEa_firstprivate_i32 %3 -> %arg0, @_QFtestEi_private_i32 %1 -> %arg1 : !llvm.ptr, !llvm.ptr) {
+ omp.loop_nest (%arg2) : i32 = (%7) to (%8) inclusive step (%9) {
+ llvm.store %arg2, %arg1 : i32, !llvm.ptr
+ %10 = llvm.load %arg0 : !llvm.ptr -> i32
+ %11 = llvm.mlir.constant(1 : i32) : i32
+ %12 = llvm.add %10, %11 : i32
+ llvm.store %12, %arg0 : i32, !llvm.ptr
+ omp.yield
+ }
+ }
+ llvm.return
+}
+
+// CHECK: %[[structArg:.*]] = alloca { i64, i64, i64, ptr }, align 8
+// CHECK: %[[omp_global_thread_num:.*]] = call i32 @__kmpc_global_thread_num(ptr @1)
+// CHECK-NOT: call void @__kmpc_taskgroup(ptr @1, i32 %[[omp_global_thread_num]])
+// CHECK: %[[VAL_1:.*]] = call ptr @__kmpc_omp_task_alloc(ptr @1, i32 %[[omp_global_thread_num]], i32 1, i64 40, i64 32, ptr @_QPtest..omp_par)
+// CHECK: %[[VAL_2:.*]] = load ptr, ptr %[[VAL_1]], align 8
+// CHECK: call void @llvm.memcpy.p0.p0.i64(ptr align 1 %[[VAL_2]], ptr align 1 %[[structArg]], i64 32, i1 false)
+// CHECK: %[[VAL_3:.*]] = getelementptr { i64, i64, i64, ptr }, ptr %[[VAL_2]], i32 0, i32 0
+// CHECK: %[[VAL_4:.*]] = getelementptr { i64, i64, i64, ptr }, ptr %[[VAL_2]], i32 0, i32 1
+// CHECK: %[[VAL_5:.*]] = getelementptr { i64, i64, i64, ptr }, ptr %[[VAL_2]], i32 0, i32 2
+// CHECK: %[[VAL_6:.*]] = load i64, ptr %[[VAL_5]], align 4
+// CHECK: call void @__kmpc_taskloop(ptr @1, i32 %omp_global_thread_num, ptr %[[VAL_1]], i32 1, ptr %[[VAL_3]], ptr %[[VAL_4]], i64 %[[VAL_6]], i32 1, i32 0, i64 0, ptr @omp_taskloop_dup)
+// CHECK-NOT: call void @__kmpc_end_taskgroup(ptr @1, i32 %omp_global_thread_num)
diff --git a/mlir/test/Target/LLVMIR/openmp-taskloop-num_tasks.mlir b/mlir/test/Target/LLVMIR/openmp-taskloop-num_tasks.mlir
new file mode 100644
index 0000000000000..d4481d1199a75
--- /dev/null
+++ b/mlir/test/Target/LLVMIR/openmp-taskloop-num_tasks.mlir
@@ -0,0 +1,45 @@
+// RUN: mlir-translate -mlir-to-llvmir %s | FileCheck %s
+
+omp.private {type = private} @_QFtestEi_private_i32 : i32
+
+omp.private {type = firstprivate} @_QFtestEa_firstprivate_i32 : i32 copy {
+^bb0(%arg0: !llvm.ptr, %arg1: !llvm.ptr):
+ %0 = llvm.load %arg0 : !llvm.ptr -> i32
+ llvm.store %0, %arg1 : i32, !llvm.ptr
+ omp.yield(%arg1 : !llvm.ptr)
+}
+
+
+llvm.func @_QPtest() {
+ %0 = llvm.mlir.constant(1 : i64) : i64
+ %1 = llvm.alloca %0 x i32 {bindc_name = "i"} : (i64) -> !llvm.ptr
+ %3 = llvm.alloca %0 x i32 {bindc_name = "a"} : (i64) -> !llvm.ptr
+ %6 = llvm.mlir.constant(20 : i32) : i32
+ llvm.store %6, %3 : i32, !llvm.ptr
+ %7 = llvm.mlir.constant(1 : i32) : i32
+ %8 = llvm.mlir.constant(5 : i32) : i32
+ %9 = llvm.mlir.constant(1 : i32) : i32
+ %c2_i32 = llvm.mlir.constant(2: i32) : i32
+ omp.taskloop num_tasks(%c2_i32 : i32) private(@_QFtestEa_firstprivate_i32 %3 -> %arg0, @_QFtestEi_private_i32 %1 -> %arg1 : !llvm.ptr, !llvm.ptr) {
+ omp.loop_nest (%arg2) : i32 = (%7) to (%8) inclusive step (%9) {
+ llvm.store %arg2, %arg1 : i32, !llvm.ptr
+ %10 = llvm.load %arg0 : !llvm.ptr -> i32
+ %11 = llvm.mlir.constant(1 : i32) : i32
+ %12 = llvm.add %10, %11 : i32
+ llvm.store %12, %arg0 : i32, !llvm.ptr
+ omp.yield
+ }
+ }
+ llvm.return
+}
+
+// CHECK: %[[structArg:.*]] = alloca { i64, i64, i64, ptr }, align 8
+// CHECK: %[[omp_global_thread_num:.*]] = call i32 @__kmpc_global_thread_num(ptr @1)
+// CHECK: %[[VAL_1:.*]] = call ptr @__kmpc_omp_task_alloc(ptr @1, i32 %[[omp_global_thread_num]], i32 1, i64 40, i64 32, ptr @_QPtest..omp_par)
+// CHECK: %[[VAL_2:.*]] = load ptr, ptr %[[VAL_1]], align 8
+// CHECK: call void @llvm.memcpy.p0.p0.i64(ptr align 1 %[[VAL_2]], ptr align 1 %[[structArg]], i64 32, i1 false)
+// CHECK: %[[VAL_3:.*]] = getelementptr { i64, i64, i64, ptr }, ptr %[[VAL_2]], i32 0, i32 0
+// CHECK: %[[VAL_4:.*]] = getelementptr { i64, i64, i64, ptr }, ptr %[[VAL_2]], i32 0, i32 1
+// CHECK: %[[VAL_5:.*]] = getelementptr { i64, i64, i64, ptr }, ptr %[[VAL_2]], i32 0, i32 2
+// CHECK: %[[VAL_6:.*]] = load i64, ptr %[[VAL_5]], align 4
+// CHECK: call void @__kmpc_taskloop(ptr @1, i32 %omp_global_thread_num, ptr %[[VAL_1]], i32 1, ptr %[[VAL_3]], ptr %[[VAL_4]], i64 %[[VAL_6]], i32 1, i32 2, i64 2, ptr @omp_taskloop_dup)
diff --git a/mlir/test/Target/LLVMIR/openmp-taskloop-priority.mlir b/mlir/test/Target/LLVMIR/openmp-taskloop-priority.mlir
new file mode 100644
index 0000000000000..15618c9c9317a
--- /dev/null
+++ b/mlir/test/Target/LLVMIR/openmp-taskloop-priority.mlir
@@ -0,0 +1,37 @@
+// RUN: mlir-translate -mlir-to-llvmir %s | FileCheck %s
+
+omp.private {type = private} @_QFtestEi_private_i32 : i32
+
+omp.private {type = firstprivate} @_QFtestEa_firstprivate_i32 : i32 copy {
+^bb0(%arg0: !llvm.ptr, %arg1: !llvm.ptr):
+ %0 = llvm.load %arg0 : !llvm.ptr -> i32
+ llvm.store %0, %arg1 : i32, !llvm.ptr
+ omp.yield(%arg1 : !llvm.ptr)
+}
+
+
+llvm.func @_QPtest() {
+ %0 = llvm.mlir.constant(1 : i64) : i64
+ %1 = llvm.alloca %0 x i32 {bindc_name = "i"} : (i64) -> !llvm.ptr
+ %3 = llvm.alloca %0 x i32 {bindc_name = "a"} : (i64) -> !llvm.ptr
+ %6 = llvm.mlir.constant(20 : i32) : i32
+ llvm.store %6, %3 : i32, !llvm.ptr
+ %7 = llvm.mlir.constant(1 : i32) : i32
+ %8 = llvm.mlir.constant(5 : i32) : i32
+ %9 = llvm.mlir.constant(1 : i32) : i32
+ %c1_i32 = llvm.mlir.constant(1 : i32) : i32
+ omp.taskloop priority(%c1_i32 : i32) private(@_QFtestEa_firstprivate_i32 %3 -> %arg0, @_QFtestEi_private_i32 %1 -> %arg1 : !llvm.ptr, !llvm.ptr) {
+ omp.loop_nest (%arg2) : i32 = (%7) to (%8) inclusive step (%9) {
+ llvm.store %arg2, %arg1 : i32, !llvm.ptr
+ %10 = llvm.load %arg0 : !llvm.ptr -> i32
+ %11 = llvm.mlir.constant(1 : i32) : i32
+ %12 = llvm.add %10, %11 : i32
+ llvm.store %12, %arg0 : i32, !llvm.ptr
+ omp.yield
+ }
+ }
+ llvm.return
+}
+
+// CHECK: %[[omp_global_thread_num:.*]] = call i32 @__kmpc_global_thread_num(ptr @1)
+// CHECK: %[[VAL_5:.*]] = call ptr @__kmpc_omp_task_alloc(ptr @1, i32 %[[omp_global_thread_num]], i32 33, i64 40, i64 32, ptr @_QPtest..omp_par)
diff --git a/mlir/test/Target/LLVMIR/openmp-taskloop-untied.mlir b/mlir/test/Target/LLVMIR/openmp-taskloop-untied.mlir
new file mode 100644
index 0000000000000..c9c06bdf5cd43
--- /dev/null
+++ b/mlir/test/Target/LLVMIR/openmp-taskloop-untied.mlir
@@ -0,0 +1,63 @@
+// RUN: mlir-translate -mlir-to-llvmir %s | FileCheck %s
+
+omp.private {type = private} @_QFtestEi_private_i32 : i32
+
+omp.private {type = firstprivate} @_QFtestEa_firstprivate_i32 : i32 copy {
+^bb0(%arg0: !llvm.ptr, %arg1: !llvm.ptr):
+ %0 = llvm.load %arg0 : !llvm.ptr -> i32
+ llvm.store %0, %arg1 : i32, !llvm.ptr
+ omp.yield(%arg1 : !llvm.ptr)
+}
+
+
+llvm.func @_QPtest() {
+ %0 = llvm.mlir.constant(1 : i64) : i64
+ %1 = llvm.alloca %0 x i32 {bindc_name = "i"} : (i64) -> !llvm.ptr
+ %3 = llvm.alloca %0 x i32 {bindc_name = "a"} : (i64) -> !llvm.ptr
+ %6 = llvm.mlir.constant(20 : i32) : i32
+ llvm.store %6, %3 : i32, !llvm.ptr
+ %7 = llvm.mlir.constant(1 : i32) : i32
+ %8 = llvm.mlir.constant(5 : i32) : i32
+ %9 = llvm.mlir.constant(1 : i32) : i32
+ omp.taskloop untied private(@_QFtestEa_firstprivate_i32 %3 -> %arg0, @_QFtestEi_private_i32 %1 -> %arg1 : !llvm.ptr, !llvm.ptr) {
+ omp.loop_nest (%arg2) : i32 = (%7) to (%8) inclusive step (%9) {
+ llvm.store %arg2, %arg1 : i32, !llvm.ptr
+ %10 = llvm.load %arg0 : !llvm.ptr -> i32
+ %11 = llvm.mlir.constant(1 : i32) : i32
+ %12 = llvm.add %10, %11 : i32
+ llvm.store %12, %arg0 : i32, !llvm.ptr
+ omp.yield
+ }
+ }
+ llvm.return
+}
+
+// CHECK: %[[omp_global_thread_num:.*]] = call i32 @__kmpc_global_thread_num(ptr @1)
+// CHECK: %[[VAL:.*]] = call ptr @__kmpc_omp_task_alloc(ptr @1, i32 %[[omp_global_thread_num]], i32 0, i64 40, i64 32, ptr @_QPtest..omp_par)
+
+// -----
+
+llvm.func @_QPtest_tied() {
+ %0 = llvm.mlir.constant(1 : i64) : i64
+ %1 = llvm.alloca %0 x i32 {bindc_name = "i"} : (i64) -> !llvm.ptr
+ %3 = llvm.alloca %0 x i32 {bindc_name = "a"} : (i64) -> !llvm.ptr
+ %6 = llvm.mlir.constant(20 : i32) : i32
+ llvm.store %6, %3 : i32, !llvm.ptr
+ %7 = llvm.mlir.constant(1 : i32) : i32
+ %8 = llvm.mlir.constant(5 : i32) : i32
+ %9 = llvm.mlir.constant(1 : i32) : i32
+ omp.taskloop private(@_QFtestEa_firstprivate_i32 %3 -> %arg0, @_QFtestEi_private_i32 %1 -> %arg1 : !llvm.ptr, !llvm.ptr) {
+ omp.loop_nest (%arg2) : i32 = (%7) to (%8) inclusive step (%9) {
+ llvm.store %arg2, %arg1 : i32, !llvm.ptr
+ %10 = llvm.load %arg0 : !llvm.ptr -> i32
+ %11 = llvm.mlir.constant(1 : i32) : i32
+ %12 = llvm.add %10, %11 : i32
+ llvm.store %12, %arg0 : i32, !llvm.ptr
+ omp.yield
+ }
+ }
+ llvm.return
+}
+
+// CHECK: %[[omp_global_thread_num:.*]] = call i32 @__kmpc_global_thread_num(ptr @1)
+// CHECK: %[[VAL:.*]] = call ptr @__kmpc_omp_task_alloc(ptr @1, i32 %[[omp_global_thread_num]], i32 1, i64 40, i64 32, ptr @_QPtest_tied..omp_par)
diff --git a/mlir/test/Target/LLVMIR/openmp-todo.mlir b/mlir/test/Target/LLVMIR/openmp-todo.mlir
index cb15ad0b199a1..9ad22a2a5e80b 100644
--- a/mlir/test/Target/LLVMIR/openmp-todo.mlir
+++ b/mlir/test/Target/LLVMIR/openmp-todo.mlir
@@ -345,45 +345,6 @@ llvm.func @taskloop_collapse(%lb : i32, %ub : i32, %step : i32, %lb1 : i32, %ub1
llvm.return
}
-// -----
-
-llvm.func @taskloop_final(%lb : i32, %ub : i32, %step : i32, %true : i1) {
- // expected-error at below {{not yet implemented: Unhandled clause final in omp.taskloop operation}}
- // expected-error at below {{LLVM Translation failed for operation: omp.taskloop}}
- omp.taskloop final(%true) {
- omp.loop_nest (%iv) : i32 = (%lb) to (%ub) step (%step) {
- omp.yield
- }
- }
- llvm.return
-}
-
-// -----
-
-llvm.func @taskloop_grainsize(%lb : i32, %ub : i32, %step : i32, %grainsize : i32) {
- // expected-error at below {{not yet implemented: Unhandled clause grainsize in omp.taskloop operation}}
- // expected-error at below {{LLVM Translation failed for operation: omp.taskloop}}
- omp.taskloop grainsize(%grainsize: i32) {
- omp.loop_nest (%iv) : i32 = (%lb) to (%ub) step (%step) {
- omp.yield
- }
- }
- llvm.return
-}
-
-// -----
-
-llvm.func @taskloop_if(%lb : i32, %ub : i32, %step : i32, %true : i1) {
- // expected-error at below {{not yet implemented: Unhandled clause if in omp.taskloop operation}}
- // expected-error at below {{LLVM Translation failed for operation: omp.taskloop}}
- omp.taskloop if(%true) {
- omp.loop_nest (%iv) : i32 = (%lb) to (%ub) step (%step) {
- omp.yield
- }
- }
- llvm.return
-}
-
// -----
omp.declare_reduction @add_reduction_i32 : i32 init {
^bb0(%arg0: i32):
@@ -406,58 +367,6 @@ llvm.func @taskloop_inreduction(%lb : i32, %ub : i32, %step : i32, %x : !llvm.pt
llvm.return
}
-// -----
-
-llvm.func @taskloop_mergeable(%lb : i32, %ub : i32, %step : i32) {
- // expected-error at below {{not yet implemented: Unhandled clause mergeable in omp.taskloop operation}}
- // expected-error at below {{LLVM Translation failed for operation: omp.taskloop}}
- omp.taskloop mergeable {
- omp.loop_nest (%iv) : i32 = (%lb) to (%ub) step (%step) {
- omp.yield
- }
- }
- llvm.return
-}
-
-// -----
-
-llvm.func @taskloop_nogroup(%lb : i32, %ub : i32, %step : i32) {
- // expected-error at below {{not yet implemented: Unhandled clause nogroup in omp.taskloop operation}}
- // expected-error at below {{LLVM Translation failed for operation: omp.taskloop}}
- omp.taskloop nogroup {
- omp.loop_nest (%iv) : i32 = (%lb) to (%ub) step (%step) {
- omp.yield
- }
- }
- llvm.return
-}
-
-// -----
-
-llvm.func @taskloop_num_tasks(%lb : i32, %ub : i32, %step : i32, %numtasks : i32) {
- // expected-error at below {{not yet implemented: Unhandled clause num_tasks in omp.taskloop operation}}
- // expected-error at below {{LLVM Translation failed for operation: omp.taskloop}}
- omp.taskloop num_tasks(%numtasks: i32) {
- omp.loop_nest (%iv) : i32 = (%lb) to (%ub) step (%step) {
- omp.yield
- }
- }
- llvm.return
-}
-
-// -----
-
-llvm.func @taskloop_priority(%lb : i32, %ub : i32, %step : i32, %priority : i32) {
- // expected-error at below {{not yet implemented: Unhandled clause priority in omp.taskloop operation}}
- // expected-error at below {{LLVM Translation failed for operation: omp.taskloop}}
- omp.taskloop priority(%priority: i32) {
- omp.loop_nest (%iv) : i32 = (%lb) to (%ub) step (%step) {
- omp.yield
- }
- }
- llvm.return
-}
-
// -----
omp.declare_reduction @add_reduction_i32 : i32 init {
^bb0(%arg0: i32):
@@ -482,19 +391,6 @@ llvm.func @taskloop_reduction(%lb : i32, %ub : i32, %step : i32, %x : !llvm.ptr)
// -----
-llvm.func @taskloop_untied(%lb : i32, %ub : i32, %step : i32) {
- // expected-error at below {{not yet implemented: Unhandled clause untied in omp.taskloop operation}}
- // expected-error at below {{LLVM Translation failed for operation: omp.taskloop}}
- omp.taskloop untied {
- omp.loop_nest (%iv) : i32 = (%lb) to (%ub) step (%step) {
- omp.yield
- }
- }
- llvm.return
-}
-
-// -----
-
llvm.func @taskwait_depend(%x: !llvm.ptr) {
// expected-error at below {{not yet implemented: Unhandled clause depend in omp.taskwait operation}}
// expected-error at below {{LLVM Translation failed for operation: omp.taskwait}}
More information about the llvm-commits
mailing list