Skip to content

Codegen changes for strict modifier with grainsize/num_tasks of taskloop construct #117196

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 9 commits into from
Nov 28, 2024
Merged

Codegen changes for strict modifier with grainsize/num_tasks of taskloop construct #117196

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
d19f41d
Initial Codegen changes for strict modifier with grainsize/num_tasks …
Nov 21, 2024
01db551
clang-format changes
Nov 21, 2024
45fbfad
Merge branch 'main' into strict_modifier
chandraghale Nov 21, 2024
315287d
using smallvector to reduce redundant code
Nov 22, 2024
35062a0
Fix for review comment
Nov 26, 2024
b92e403
Merge branch 'main' into strict_modifier
chandraghale Nov 26, 2024
ef63bdd
Merge branch 'main' into strict_modifier
chandraghale Nov 26, 2024
cbaef60
Merge branch 'main' into strict_modifier
chandraghale Nov 26, 2024
6bc0e3f
updated with auto gen check lines
Nov 27, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
76 changes: 52 additions & 24 deletions clang/lib/CodeGen/CGOpenMPRuntime.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4666,30 +4666,58 @@ void CGOpenMPRuntime::emitTaskLoopCall(CodeGenFunction &CGF, SourceLocation Loc,
CGF.getContext().VoidPtrTy);
}
enum { NoSchedule = 0, Grainsize = 1, NumTasks = 2 };
llvm::Value *TaskArgs[] = {
UpLoc,
ThreadID,
Result.NewTask,
IfVal,
LBLVal.getPointer(CGF),
UBLVal.getPointer(CGF),
CGF.EmitLoadOfScalar(StLVal, Loc),
llvm::ConstantInt::getSigned(
CGF.IntTy, 1), // Always 1 because taskgroup emitted by the compiler
llvm::ConstantInt::getSigned(
CGF.IntTy, Data.Schedule.getPointer()
? Data.Schedule.getInt() ? NumTasks : Grainsize
: NoSchedule),
Data.Schedule.getPointer()
? CGF.Builder.CreateIntCast(Data.Schedule.getPointer(), CGF.Int64Ty,
/*isSigned=*/false)
: llvm::ConstantInt::get(CGF.Int64Ty, /*V=*/0),
Result.TaskDupFn ? CGF.Builder.CreatePointerBitCastOrAddrSpaceCast(
Result.TaskDupFn, CGF.VoidPtrTy)
: llvm::ConstantPointerNull::get(CGF.VoidPtrTy)};
CGF.EmitRuntimeCall(OMPBuilder.getOrCreateRuntimeFunction(
CGM.getModule(), OMPRTL___kmpc_taskloop),
TaskArgs);
if (Data.HasModifier) {
llvm::Value *TaskArgs[] = {
UpLoc,
ThreadID,
Result.NewTask,
IfVal,
LBLVal.getPointer(CGF),
UBLVal.getPointer(CGF),
CGF.EmitLoadOfScalar(StLVal, Loc),
llvm::ConstantInt::getSigned(
CGF.IntTy, 1), // Always 1 because taskgroup emitted by the compiler
llvm::ConstantInt::getSigned(
CGF.IntTy, Data.Schedule.getPointer()
? Data.Schedule.getInt() ? NumTasks : Grainsize
: NoSchedule),
Data.Schedule.getPointer()
? CGF.Builder.CreateIntCast(Data.Schedule.getPointer(), CGF.Int64Ty,
/*isSigned=*/false)
: llvm::ConstantInt::get(CGF.Int64Ty, /*V=*/0),
llvm::ConstantInt::get(CGF.Int32Ty, 1), // strict modifier enabled
Result.TaskDupFn ? CGF.Builder.CreatePointerBitCastOrAddrSpaceCast(
Result.TaskDupFn, CGF.VoidPtrTy)
: llvm::ConstantPointerNull::get(CGF.VoidPtrTy)};
CGF.EmitRuntimeCall(OMPBuilder.getOrCreateRuntimeFunction(
Copy link
Contributor

@shiltian shiltian Nov 25, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can you just use one EmitRuntimeCall here and check Data.HasModifier inside?

Copy link
Contributor Author

@chandraghale chandraghale Nov 26, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Fixed as suggested !!

CGM.getModule(), OMPRTL___kmpc_taskloop_5),
TaskArgs);
} else {
llvm::Value *TaskArgs[] = {
UpLoc,
ThreadID,
Result.NewTask,
IfVal,
LBLVal.getPointer(CGF),
UBLVal.getPointer(CGF),
CGF.EmitLoadOfScalar(StLVal, Loc),
llvm::ConstantInt::getSigned(
CGF.IntTy, 1), // Always 1 because taskgroup emitted by the compiler
llvm::ConstantInt::getSigned(
CGF.IntTy, Data.Schedule.getPointer()
? Data.Schedule.getInt() ? NumTasks : Grainsize
: NoSchedule),
Data.Schedule.getPointer()
? CGF.Builder.CreateIntCast(Data.Schedule.getPointer(), CGF.Int64Ty,
/*isSigned=*/false)
: llvm::ConstantInt::get(CGF.Int64Ty, /*V=*/0),
Result.TaskDupFn ? CGF.Builder.CreatePointerBitCastOrAddrSpaceCast(
Result.TaskDupFn, CGF.VoidPtrTy)
: llvm::ConstantPointerNull::get(CGF.VoidPtrTy)};
CGF.EmitRuntimeCall(OMPBuilder.getOrCreateRuntimeFunction(
CGM.getModule(), OMPRTL___kmpc_taskloop),
TaskArgs);
}
}

/// Emit reduction operation for each element of array (required for
Expand Down
1 change: 1 addition & 0 deletions clang/lib/CodeGen/CGOpenMPRuntime.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,6 +122,7 @@ struct OMPTaskDataTy final {
bool IsReductionWithTaskMod = false;
bool IsWorksharingReduction = false;
bool HasNowaitClause = false;
bool HasModifier = false;
};

/// Class intended to support codegen of all kind of the reduction clauses.
Expand Down
4 changes: 4 additions & 0 deletions clang/lib/CodeGen/CGStmtOpenMP.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7831,10 +7831,14 @@ void CodeGenFunction::EmitOMPTaskLoopBasedDirective(const OMPLoopDirective &S) {
// grainsize clause
Data.Schedule.setInt(/*IntVal=*/false);
Data.Schedule.setPointer(EmitScalarExpr(Clause->getGrainsize()));
Data.HasModifier =
(Clause->getModifier() == OMPC_GRAINSIZE_strict) ? true : false;
} else if (const auto *Clause = S.getSingleClause<OMPNumTasksClause>()) {
// num_tasks clause
Data.Schedule.setInt(/*IntVal=*/true);
Data.Schedule.setPointer(EmitScalarExpr(Clause->getNumTasks()));
Data.HasModifier =
(Clause->getModifier() == OMPC_NUMTASKS_strict) ? true : false;
}

auto &&BodyGen = [CS, &S](CodeGenFunction &CGF, PrePostActionTy &) {
Expand Down
256 changes: 256 additions & 0 deletions clang/test/OpenMP/taskloop_strictmodifier_codegen.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,256 @@
// RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -fopenmp -x c++ -emit-llvm %s -o - | FileCheck %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-apple-darwin10 -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-apple-darwin10 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s

// RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -fopenmp-simd -x c++ -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple x86_64-apple-darwin10 -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple x86_64-apple-darwin10 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// SIMD-ONLY0-NOT: {{__kmpc|__tgt}}
// expected-no-diagnostics
#ifndef HEADER
#define HEADER

// CHECK-LABEL: @main
int main(int argc, char **argv) {
// CHECK: [[GTID:%.+]] = call i32 @__kmpc_global_thread_num(ptr [[DEFLOC:@.+]])
// CHECK: call ptr @__kmpc_omp_task_alloc(ptr [[DEFLOC]], i32 [[GTID]],
// CHECK: call i32 @__kmpc_omp_task(ptr [[DEFLOC]], i32 [[GTID]],
#pragma omp task
;
// CHECK: [[RES:%.+]] = call {{.*}}i32 @__kmpc_master(ptr [[DEFLOC]], i32 [[GTID]])
// CHECK-NEXT: [[IS_MASTER:%.+]] = icmp ne i32 [[RES]], 0
// CHECK-NEXT: br i1 [[IS_MASTER]], label {{%?}}[[THEN:.+]], label {{%?}}[[EXIT:.+]]
// CHECK: [[THEN]]
// CHECK: call void @__kmpc_taskgroup(ptr [[DEFLOC]], i32 [[GTID]])
// CHECK: [[TASKV:%.+]] = call ptr @__kmpc_omp_task_alloc(ptr [[DEFLOC]], i32 [[GTID]], i32 33, i64 80, i64 1, ptr [[TASK1:@.+]])
// CHECK: [[TASK_DATA:%.+]] = getelementptr inbounds nuw %{{.+}}, ptr [[TASKV]], i32 0, i32 0
// CHECK: [[DOWN:%.+]] = getelementptr inbounds nuw [[TD_TY:%.+]], ptr [[TASK_DATA]], i32 0, i32 5
// CHECK: store i64 0, ptr [[DOWN]],
// CHECK: [[UP:%.+]] = getelementptr inbounds nuw [[TD_TY]], ptr [[TASK_DATA]], i32 0, i32 6
// CHECK: store i64 9, ptr [[UP]],
// CHECK: [[ST:%.+]] = getelementptr inbounds nuw [[TD_TY]], ptr [[TASK_DATA]], i32 0, i32 7
// CHECK: store i64 1, ptr [[ST]],
// CHECK: [[ST_VAL:%.+]] = load i64, ptr [[ST]],
// CHECK: call void @__kmpc_taskloop(ptr [[DEFLOC]], i32 [[GTID]], ptr [[TASKV]], i32 1, ptr [[DOWN]], ptr [[UP]], i64 [[ST_VAL]], i32 1, i32 0, i64 0, ptr null)
// CHECK: call void @__kmpc_end_taskgroup(ptr [[DEFLOC]], i32 [[GTID]])
// CHECK-NEXT: call {{.*}}void @__kmpc_end_master(ptr [[DEFLOC]], i32 [[GTID]])
// CHECK-NEXT: br label {{%?}}[[EXIT]]
// CHECK: [[EXIT]]
#pragma omp master taskloop priority(argc)
for (int i = 0; i < 10; ++i)
;
// CHECK: [[RES:%.+]] = call {{.*}}i32 @__kmpc_master(ptr [[DEFLOC]], i32 [[GTID]])
// CHECK-NEXT: [[IS_MASTER:%.+]] = icmp ne i32 [[RES]], 0
// CHECK-NEXT: br i1 [[IS_MASTER]], label {{%?}}[[THEN:.+]], label {{%?}}[[EXIT:.+]]
// CHECK: [[THEN]]
// CHECK: [[TASKV:%.+]] = call ptr @__kmpc_omp_task_alloc(ptr [[DEFLOC]], i32 [[GTID]], i32 1, i64 80, i64 1, ptr [[TASK2:@.+]])
// CHECK: [[TASK_DATA:%.+]] = getelementptr inbounds nuw %{{.+}}, ptr [[TASKV]], i32 0, i32 0
// CHECK: [[DOWN:%.+]] = getelementptr inbounds nuw [[TD_TY:%.+]], ptr [[TASK_DATA]], i32 0, i32 5
// CHECK: store i64 0, ptr [[DOWN]],
// CHECK: [[UP:%.+]] = getelementptr inbounds nuw [[TD_TY]], ptr [[TASK_DATA]], i32 0, i32 6
// CHECK: store i64 9, ptr [[UP]],
// CHECK: [[ST:%.+]] = getelementptr inbounds nuw [[TD_TY]], ptr [[TASK_DATA]], i32 0, i32 7
// CHECK: store i64 1, ptr [[ST]],
// CHECK: [[ST_VAL:%.+]] = load i64, ptr [[ST]],
// CHECK: [[GRAINSIZE:%.+]] = zext i32 %{{.+}} to i64
// CHECK: call void @__kmpc_taskloop_5(ptr [[DEFLOC]], i32 [[GTID]], ptr [[TASKV]], i32 1, ptr [[DOWN]], ptr [[UP]], i64 [[ST_VAL]], i32 1, i32 1, i64 [[GRAINSIZE]], i32 1, ptr null)
// CHECK-NEXT: call {{.*}}void @__kmpc_end_master(ptr [[DEFLOC]], i32 [[GTID]])
// CHECK-NEXT: br label {{%?}}[[EXIT]]
// CHECK: [[EXIT]]
#pragma omp master taskloop nogroup grainsize(strict:argc)
for (int i = 0; i < 10; ++i)
;
// CHECK: [[RES:%.+]] = call {{.*}}i32 @__kmpc_master(ptr [[DEFLOC]], i32 [[GTID]])
// CHECK-NEXT: [[IS_MASTER:%.+]] = icmp ne i32 [[RES]], 0
// CHECK-NEXT: br i1 [[IS_MASTER]], label {{%?}}[[THEN:.+]], label {{%?}}[[EXIT:.+]]
// CHECK: [[THEN]]
// CHECK: call void @__kmpc_taskgroup(ptr [[DEFLOC]], i32 [[GTID]])
// CHECK: [[TASKV:%.+]] = call ptr @__kmpc_omp_task_alloc(ptr [[DEFLOC]], i32 [[GTID]], i32 1, i64 80, i64 16, ptr [[TASK3:@.+]])
// CHECK: [[TASK_DATA:%.+]] = getelementptr inbounds nuw %{{.+}}, ptr [[TASKV]], i32 0, i32 0
// CHECK: [[IF:%.+]] = icmp ne i32 %{{.+}}, 0
// CHECK: [[IF_INT:%.+]] = sext i1 [[IF]] to i32
// CHECK: [[DOWN:%.+]] = getelementptr inbounds nuw [[TD_TY:%.+]], ptr [[TASK_DATA]], i32 0, i32 5
// CHECK: store i64 0, ptr [[DOWN]],
// CHECK: [[UP:%.+]] = getelementptr inbounds nuw [[TD_TY]], ptr [[TASK_DATA]], i32 0, i32 6
// CHECK: store i64 %{{.+}}, ptr [[UP]],
// CHECK: [[ST:%.+]] = getelementptr inbounds nuw [[TD_TY]], ptr [[TASK_DATA]], i32 0, i32 7
// CHECK: store i64 1, ptr [[ST]],
// CHECK: [[ST_VAL:%.+]] = load i64, ptr [[ST]],
// CHECK: call void @__kmpc_taskloop_5(ptr [[DEFLOC]], i32 [[GTID]], ptr [[TASKV]], i32 [[IF_INT]], ptr [[DOWN]], ptr [[UP]], i64 [[ST_VAL]], i32 1, i32 2, i64 4, i32 1, ptr null)
// CHECK: call void @__kmpc_end_taskgroup(ptr [[DEFLOC]], i32 [[GTID]])
// CHECK-NEXT: call {{.*}}void @__kmpc_end_master(ptr [[DEFLOC]], i32 [[GTID]])
// CHECK-NEXT: br label {{%?}}[[EXIT]]
// CHECK: [[EXIT]]
int i;
#pragma omp master taskloop if(argc) shared(argc, argv) collapse(2) num_tasks(strict: 4)
for (i = 0; i < argc; ++i)
for (int j = argc; j < argv[argc][argc]; ++j)
;
// CHECK: [[RES:%.+]] = call {{.*}}i32 @__kmpc_master(ptr [[DEFLOC]], i32 [[GTID]])
// CHECK-NEXT: [[IS_MASTER:%.+]] = icmp ne i32 [[RES]], 0
// CHECK-NEXT: br i1 [[IS_MASTER]], label {{%?}}[[THEN:.+]], label {{%?}}[[EXIT:.+]]
// CHECK: [[THEN]]
// CHECK: call void @__kmpc_taskgroup(
// CHECK: call ptr @__kmpc_omp_task_alloc(ptr @{{.+}}, i32 %{{.+}}, i32 1, i64 80, i64 1, ptr [[TASK_CANCEL:@.+]])
// CHECK: call void @__kmpc_taskloop(
// CHECK: call void @__kmpc_end_taskgroup(
// CHECK-NEXT: call {{.*}}void @__kmpc_end_master(ptr [[DEFLOC]], i32 [[GTID]])
// CHECK-NEXT: br label {{%?}}[[EXIT]]
// CHECK: [[EXIT]]
#pragma omp master taskloop
for (int i = 0; i < 10; ++i) {
#pragma omp cancel taskgroup
#pragma omp cancellation point taskgroup
}
}

// CHECK: define internal noundef i32 [[TASK1]](
// CHECK: [[DOWN:%.+]] = getelementptr inbounds nuw [[TD_TY:%.+]], ptr %{{.+}}, i32 0, i32 5
// CHECK: [[DOWN_VAL:%.+]] = load i64, ptr [[DOWN]],
// CHECK: [[UP:%.+]] = getelementptr inbounds nuw [[TD_TY]], ptr %{{.+}}, i32 0, i32 6
// CHECK: [[UP_VAL:%.+]] = load i64, ptr [[UP]],
// CHECK: [[ST:%.+]] = getelementptr inbounds nuw [[TD_TY]], ptr %{{.+}}, i32 0, i32 7
// CHECK: [[ST_VAL:%.+]] = load i64, ptr [[ST]],
// CHECK: [[LITER:%.+]] = getelementptr inbounds nuw [[TD_TY]], ptr %{{.+}}, i32 0, i32 8
// CHECK: [[LITER_VAL:%.+]] = load i32, ptr [[LITER]],
// CHECK: store i64 [[DOWN_VAL]], ptr [[LB:%[^,]+]],
// CHECK: store i64 [[UP_VAL]], ptr [[UB:%[^,]+]],
// CHECK: store i64 [[ST_VAL]], ptr [[ST:%[^,]+]],
// CHECK: store i32 [[LITER_VAL]], ptr [[LITER:%[^,]+]],
// CHECK: [[LB_VAL:%.+]] = load i64, ptr [[LB]],
// CHECK: [[LB_I32:%.+]] = trunc i64 [[LB_VAL]] to i32
// CHECK: store i32 [[LB_I32]], ptr [[CNT:%.+]],
// CHECK: br label
// CHECK: [[VAL:%.+]] = load i32, ptr [[CNT]],
// CHECK: [[VAL_I64:%.+]] = sext i32 [[VAL]] to i64
// CHECK: [[UB_VAL:%.+]] = load i64, ptr [[UB]],
// CHECK: [[CMP:%.+]] = icmp ule i64 [[VAL_I64]], [[UB_VAL]]
// CHECK: br i1 [[CMP]], label %{{.+}}, label %{{.+}}
// CHECK: load i32, ptr %
// CHECK: store i32 %
// CHECK: load i32, ptr %
// CHECK: add nsw i32 %{{.+}}, 1
// CHECK: store i32 %{{.+}}, ptr %
// CHECK: br label %
// CHECK: ret i32 0

// CHECK: define internal noundef i32 [[TASK2]](
// CHECK: [[DOWN:%.+]] = getelementptr inbounds nuw [[TD_TY:%.+]], ptr %{{.+}}, i32 0, i32 5
// CHECK: [[DOWN_VAL:%.+]] = load i64, ptr [[DOWN]],
// CHECK: [[UP:%.+]] = getelementptr inbounds nuw [[TD_TY]], ptr %{{.+}}, i32 0, i32 6
// CHECK: [[UP_VAL:%.+]] = load i64, ptr [[UP]],
// CHECK: [[ST:%.+]] = getelementptr inbounds nuw [[TD_TY]], ptr %{{.+}}, i32 0, i32 7
// CHECK: [[ST_VAL:%.+]] = load i64, ptr [[ST]],
// CHECK: [[LITER:%.+]] = getelementptr inbounds nuw [[TD_TY]], ptr %{{.+}}, i32 0, i32 8
// CHECK: [[LITER_VAL:%.+]] = load i32, ptr [[LITER]],
// CHECK: store i64 [[DOWN_VAL]], ptr [[LB:%[^,]+]],
// CHECK: store i64 [[UP_VAL]], ptr [[UB:%[^,]+]],
// CHECK: store i64 [[ST_VAL]], ptr [[ST:%[^,]+]],
// CHECK: store i32 [[LITER_VAL]], ptr [[LITER:%[^,]+]],
// CHECK: [[LB_VAL:%.+]] = load i64, ptr [[LB]],
// CHECK: [[LB_I32:%.+]] = trunc i64 [[LB_VAL]] to i32
// CHECK: store i32 [[LB_I32]], ptr [[CNT:%.+]],
// CHECK: br label
// CHECK: [[VAL:%.+]] = load i32, ptr [[CNT]],
// CHECK: [[VAL_I64:%.+]] = sext i32 [[VAL]] to i64
// CHECK: [[UB_VAL:%.+]] = load i64, ptr [[UB]],
// CHECK: [[CMP:%.+]] = icmp ule i64 [[VAL_I64]], [[UB_VAL]]
// CHECK: br i1 [[CMP]], label %{{.+}}, label %{{.+}}
// CHECK: load i32, ptr %
// CHECK: store i32 %
// CHECK: load i32, ptr %
// CHECK: add nsw i32 %{{.+}}, 1
// CHECK: store i32 %{{.+}}, ptr %
// CHECK: br label %
// CHECK: ret i32 0

// CHECK: define internal noundef i32 [[TASK3]](
// CHECK: [[DOWN:%.+]] = getelementptr inbounds nuw [[TD_TY:%.+]], ptr %{{.+}}, i32 0, i32 5
// CHECK: [[DOWN_VAL:%.+]] = load i64, ptr [[DOWN]],
// CHECK: [[UP:%.+]] = getelementptr inbounds nuw [[TD_TY]], ptr %{{.+}}, i32 0, i32 6
// CHECK: [[UP_VAL:%.+]] = load i64, ptr [[UP]],
// CHECK: [[ST:%.+]] = getelementptr inbounds nuw [[TD_TY]], ptr %{{.+}}, i32 0, i32 7
// CHECK: [[ST_VAL:%.+]] = load i64, ptr [[ST]],
// CHECK: [[LITER:%.+]] = getelementptr inbounds nuw [[TD_TY]], ptr %{{.+}}, i32 0, i32 8
// CHECK: [[LITER_VAL:%.+]] = load i32, ptr [[LITER]],
// CHECK: store i64 [[DOWN_VAL]], ptr [[LB:%[^,]+]],
// CHECK: store i64 [[UP_VAL]], ptr [[UB:%[^,]+]],
// CHECK: store i64 [[ST_VAL]], ptr [[ST:%[^,]+]],
// CHECK: store i32 [[LITER_VAL]], ptr [[LITER:%[^,]+]],
// CHECK: [[LB_VAL:%.+]] = load i64, ptr [[LB]],
// CHECK: store i64 [[LB_VAL]], ptr [[CNT:%.+]],
// CHECK: br label
// CHECK: ret i32 0

// CHECK: define internal noundef i32 [[TASK_CANCEL]](
// CHECK: [[RES:%.+]] = call i32 @__kmpc_cancel(ptr @{{.+}}, i32 %{{.+}}, i32 4)
// CHECK: [[IS_CANCEL:%.+]] = icmp ne i32 [[RES]], 0
// CHECK: br i1 [[IS_CANCEL]], label %[[EXIT:.+]], label %[[CONTINUE:[^,]+]]
// CHECK: [[EXIT]]:
// CHECK: store i32 1, ptr [[CLEANUP_SLOT:%.+]],
// CHECK: br label %[[DONE:[^,]+]]
// CHECK: [[CONTINUE]]:
// CHECK: [[RES:%.+]] = call i32 @__kmpc_cancellationpoint(ptr @{{.+}}, i32 %{{.+}}, i32 4)
// CHECK: [[IS_CANCEL:%.+]] = icmp ne i32 [[RES]], 0
// CHECK: br i1 [[IS_CANCEL]], label %[[EXIT2:.+]], label %[[CONTINUE2:[^,]+]]
// CHECK: [[EXIT2]]:
// CHECK: store i32 1, ptr [[CLEANUP_SLOT]],
// CHECK: br label %[[DONE]]
// CHECK: store i32 0, ptr [[CLEANUP_SLOT]],
// CHECK: br label %[[DONE]]
// CHECK: [[DONE]]:
// CHECK: ret i32 0

// CHECK-LABEL: @_ZN1SC2Ei
struct S {
int a;
S(int c) {
// CHECK: [[GTID:%.+]] = call i32 @__kmpc_global_thread_num(ptr [[DEFLOC:@.+]])
// CHECK: [[TASKV:%.+]] = call ptr @__kmpc_omp_task_alloc(ptr [[DEFLOC]], i32 [[GTID]], i32 1, i64 80, i64 16, ptr [[TASK4:@.+]])
// CHECK: [[TASK_DATA:%.+]] = getelementptr inbounds nuw %{{.+}}, ptr [[TASKV]], i32 0, i32 0
// CHECK: [[DOWN:%.+]] = getelementptr inbounds nuw [[TD_TY:%.+]], ptr [[TASK_DATA]], i32 0, i32 5
// CHECK: store i64 0, ptr [[DOWN]],
// CHECK: [[UP:%.+]] = getelementptr inbounds nuw [[TD_TY]], ptr [[TASK_DATA]], i32 0, i32 6
// CHECK: store i64 %{{.+}}, ptr [[UP]],
// CHECK: [[ST:%.+]] = getelementptr inbounds nuw [[TD_TY]], ptr [[TASK_DATA]], i32 0, i32 7
// CHECK: store i64 1, ptr [[ST]],
// CHECK: [[ST_VAL:%.+]] = load i64, ptr [[ST]],
// CHECK: [[NUM_TASKS:%.+]] = zext i32 %{{.+}} to i64
// CHECK: call void @__kmpc_taskloop_5(ptr [[DEFLOC]], i32 [[GTID]], ptr [[TASKV]], i32 1, ptr [[DOWN]], ptr [[UP]], i64 [[ST_VAL]], i32 1, i32 2, i64 [[NUM_TASKS]], i32 1, ptr null)
#pragma omp master taskloop shared(c) num_tasks(strict:a)
for (a = 0; a < c; ++a)
;
}
} s(1);

// CHECK: define internal noundef i32 [[TASK4]](
// CHECK: [[DOWN:%.+]] = getelementptr inbounds nuw [[TD_TY:%.+]], ptr %{{.+}}, i32 0, i32 5
// CHECK: [[DOWN_VAL:%.+]] = load i64, ptr [[DOWN]],
// CHECK: [[UP:%.+]] = getelementptr inbounds nuw [[TD_TY]], ptr %{{.+}}, i32 0, i32 6
// CHECK: [[UP_VAL:%.+]] = load i64, ptr [[UP]],
// CHECK: [[ST:%.+]] = getelementptr inbounds nuw [[TD_TY]], ptr %{{.+}}, i32 0, i32 7
// CHECK: [[ST_VAL:%.+]] = load i64, ptr [[ST]],
// CHECK: [[LITER:%.+]] = getelementptr inbounds nuw [[TD_TY]], ptr %{{.+}}, i32 0, i32 8
// CHECK: [[LITER_VAL:%.+]] = load i32, ptr [[LITER]],
// CHECK: store i64 [[DOWN_VAL]], ptr [[LB:%[^,]+]],
// CHECK: store i64 [[UP_VAL]], ptr [[UB:%[^,]+]],
// CHECK: store i64 [[ST_VAL]], ptr [[ST:%[^,]+]],
// CHECK: store i32 [[LITER_VAL]], ptr [[LITER:%[^,]+]],
// CHECK: [[LB_VAL:%.+]] = load i64, ptr [[LB]],
// CHECK: [[LB_I32:%.+]] = trunc i64 [[LB_VAL]] to i32
// CHECK: store i32 [[LB_I32]], ptr [[CNT:%.+]],
// CHECK: br label
// CHECK: [[VAL:%.+]] = load i32, ptr [[CNT]],
// CHECK: [[VAL_I64:%.+]] = sext i32 [[VAL]] to i64
// CHECK: [[UB_VAL:%.+]] = load i64, ptr [[UB]],
// CHECK: [[CMP:%.+]] = icmp ule i64 [[VAL_I64]], [[UB_VAL]]
// CHECK: br i1 [[CMP]], label %{{.+}}, label %{{.+}}
// CHECK: load i32, ptr %
// CHECK: store i32 %
// CHECK: load i32, ptr %
// CHECK: add nsw i32 %{{.+}}, 1
// CHECK: store i32 %{{.+}}, ptr %
// CHECK: br label %
// CHECK: ret i32 0

#endif
3 changes: 3 additions & 0 deletions llvm/include/llvm/Frontend/OpenMP/OMPKinds.def
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -365,6 +365,9 @@ __OMP_RTL(__kmpc_omp_task_with_deps, false, Int32, IdentPtr, Int32,
__OMP_RTL(__kmpc_taskloop, false, Void, IdentPtr, /* Int */ Int32, VoidPtr,
/* Int */ Int32, Int64Ptr, Int64Ptr, Int64, /* Int */ Int32,
/* Int */ Int32, Int64, VoidPtr)
__OMP_RTL(__kmpc_taskloop_5, false, Void, IdentPtr, /* Int */ Int32, VoidPtr,
/* Int */ Int32, Int64Ptr, Int64Ptr, Int64, /* Int */ Int32,
/* Int */ Int32, Int64, Int32, VoidPtr)
__OMP_RTL(__kmpc_omp_target_task_alloc, false, /* kmp_task_t */ VoidPtr,
IdentPtr, Int32, Int32, SizeTy, SizeTy, TaskRoutineEntryPtr, Int64)
__OMP_RTL(__kmpc_taskred_modifier_init, false, /* kmp_taskgroup */ VoidPtr,
Expand Down
Loading