Skip to content

[OpenMP][offload] Fix dynamic schedule tracking #97065

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 1 commit into from
Jul 1, 2024
Merged

[OpenMP][offload] Fix dynamic schedule tracking #97065

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
14 changes: 14 additions & 0 deletions clang/lib/CodeGen/CGOpenMPRuntime.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2553,6 +2553,15 @@ void CGOpenMPRuntime::emitForDispatchInit(
Args);
}

void CGOpenMPRuntime::emitForDispatchDeinit(CodeGenFunction &CGF,
SourceLocation Loc) {
if (!CGF.HaveInsertPoint())
return;
// Call __kmpc_dispatch_deinit(ident_t *loc, kmp_int32 tid);
llvm::Value *Args[] = {emitUpdateLocation(CGF, Loc), getThreadID(CGF, Loc)};
CGF.EmitRuntimeCall(OMPBuilder.createDispatchDeinitFunction(), Args);
}

static void emitForStaticInitCall(
CodeGenFunction &CGF, llvm::Value *UpdateLocation, llvm::Value *ThreadId,
llvm::FunctionCallee ForStaticInitFunction, OpenMPSchedType Schedule,
Expand Down Expand Up @@ -11996,6 +12005,11 @@ void CGOpenMPSIMDRuntime::emitForDispatchInit(
llvm_unreachable("Not supported in SIMD-only mode");
}

void CGOpenMPSIMDRuntime::emitForDispatchDeinit(CodeGenFunction &CGF,
SourceLocation Loc) {
llvm_unreachable("Not supported in SIMD-only mode");
}

void CGOpenMPSIMDRuntime::emitForStaticInit(
CodeGenFunction &CGF, SourceLocation Loc, OpenMPDirectiveKind DKind,
const OpenMPScheduleTy &ScheduleKind, const StaticRTInput &Values) {
Expand Down
16 changes: 16 additions & 0 deletions clang/lib/CodeGen/CGOpenMPRuntime.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -946,6 +946,14 @@ class CGOpenMPRuntime {
unsigned IVSize, bool IVSigned, bool Ordered,
const DispatchRTInput &DispatchValues);

/// This is used for non static scheduled types and when the ordered
/// clause is present on the loop construct.
///
/// \param CGF Reference to current CodeGenFunction.
/// \param Loc Clang source location.
///
virtual void emitForDispatchDeinit(CodeGenFunction &CGF, SourceLocation Loc);

/// Struct with the values to be passed to the static runtime function
struct StaticRTInput {
/// Size of the iteration variable in bits.
Expand Down Expand Up @@ -1829,6 +1837,14 @@ class CGOpenMPSIMDRuntime final : public CGOpenMPRuntime {
unsigned IVSize, bool IVSigned, bool Ordered,
const DispatchRTInput &DispatchValues) override;

/// This is used for non static scheduled types and when the ordered
/// clause is present on the loop construct.
///
/// \param CGF Reference to current CodeGenFunction.
/// \param Loc Clang source location.
///
void emitForDispatchDeinit(CodeGenFunction &CGF, SourceLocation Loc) override;

/// Call the appropriate runtime routine to initialize it before start
/// of loop.
///
Expand Down
5 changes: 5 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 @@ -2985,12 +2985,14 @@ void CodeGenFunction::EmitOMPForOuterLoop(
// run-sched-var ICV. If the ICV is set to auto, the schedule is
// implementation defined
//
// __kmpc_dispatch_init();
// while(__kmpc_dispatch_next(&LB, &UB)) {
// idx = LB;
// while (idx <= UB) { BODY; ++idx;
// __kmpc_dispatch_fini_(4|8)[u](); // For ordered loops only.
// } // inner loop
// }
// __kmpc_dispatch_deinit();
//
// OpenMP [2.7.1, Loop Construct, Description, table 2-1]
// When schedule(static, chunk_size) is specified, iterations are divided into
Expand Down Expand Up @@ -3044,6 +3046,9 @@ void CodeGenFunction::EmitOMPForOuterLoop(
OuterLoopArgs.DKind = LoopArgs.DKind;
EmitOMPOuterLoop(DynamicOrOrdered, IsMonotonic, S, LoopScope, OuterLoopArgs,
emitOMPLoopBodyWithStopPoint, CodeGenOrdered);
if (DynamicOrOrdered) {
RT.emitForDispatchDeinit(*this, S.getBeginLoc());
}
}

static void emitEmptyOrdered(CodeGenFunction &, SourceLocation Loc,
Expand Down
36 changes: 36 additions & 0 deletions clang/test/OpenMP/distribute_parallel_for_codegen.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2283,6 +2283,9 @@ int main() {
// CHECK1: omp.dispatch.inc:
// CHECK1-NEXT: br label [[OMP_DISPATCH_COND]]
// CHECK1: omp.dispatch.end:
// CHECK1-NEXT: [[TMP34:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: [[TMP35:%.*]] = load i32, ptr [[TMP34]], align 4
// CHECK1-NEXT: call void @__kmpc_dispatch_deinit(ptr @[[GLOB3]], i32 [[TMP35]])
// CHECK1-NEXT: br label [[OMP_PRECOND_END]]
// CHECK1: omp.precond.end:
// CHECK1-NEXT: ret void
Expand Down Expand Up @@ -2533,6 +2536,9 @@ int main() {
// CHECK1: omp.dispatch.inc:
// CHECK1-NEXT: br label [[OMP_DISPATCH_COND]]
// CHECK1: omp.dispatch.end:
// CHECK1-NEXT: [[TMP35:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: [[TMP36:%.*]] = load i32, ptr [[TMP35]], align 4
// CHECK1-NEXT: call void @__kmpc_dispatch_deinit(ptr @[[GLOB3]], i32 [[TMP36]])
// CHECK1-NEXT: br label [[OMP_PRECOND_END]]
// CHECK1: omp.precond.end:
// CHECK1-NEXT: ret void
Expand Down Expand Up @@ -4010,6 +4016,9 @@ int main() {
// CHECK3: omp.dispatch.inc:
// CHECK3-NEXT: br label [[OMP_DISPATCH_COND]]
// CHECK3: omp.dispatch.end:
// CHECK3-NEXT: [[TMP34:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK3-NEXT: [[TMP35:%.*]] = load i32, ptr [[TMP34]], align 4
// CHECK3-NEXT: call void @__kmpc_dispatch_deinit(ptr @[[GLOB3]], i32 [[TMP35]])
// CHECK3-NEXT: br label [[OMP_PRECOND_END]]
// CHECK3: omp.precond.end:
// CHECK3-NEXT: ret void
Expand Down Expand Up @@ -4253,6 +4262,9 @@ int main() {
// CHECK3: omp.dispatch.inc:
// CHECK3-NEXT: br label [[OMP_DISPATCH_COND]]
// CHECK3: omp.dispatch.end:
// CHECK3-NEXT: [[TMP35:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK3-NEXT: [[TMP36:%.*]] = load i32, ptr [[TMP35]], align 4
// CHECK3-NEXT: call void @__kmpc_dispatch_deinit(ptr @[[GLOB3]], i32 [[TMP36]])
// CHECK3-NEXT: br label [[OMP_PRECOND_END]]
// CHECK3: omp.precond.end:
// CHECK3-NEXT: ret void
Expand Down Expand Up @@ -6314,6 +6326,9 @@ int main() {
// CHECK9: omp.dispatch.inc:
// CHECK9-NEXT: br label [[OMP_DISPATCH_COND]]
// CHECK9: omp.dispatch.end:
// CHECK9-NEXT: [[TMP30:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK9-NEXT: [[TMP31:%.*]] = load i32, ptr [[TMP30]], align 4
// CHECK9-NEXT: call void @__kmpc_dispatch_deinit(ptr @[[GLOB3]], i32 [[TMP31]])
// CHECK9-NEXT: br label [[OMP_PRECOND_END]]
// CHECK9: omp.precond.end:
// CHECK9-NEXT: ret void
Expand Down Expand Up @@ -6554,6 +6569,9 @@ int main() {
// CHECK9: omp.dispatch.inc:
// CHECK9-NEXT: br label [[OMP_DISPATCH_COND]]
// CHECK9: omp.dispatch.end:
// CHECK9-NEXT: [[TMP31:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK9-NEXT: [[TMP32:%.*]] = load i32, ptr [[TMP31]], align 4
// CHECK9-NEXT: call void @__kmpc_dispatch_deinit(ptr @[[GLOB3]], i32 [[TMP32]])
// CHECK9-NEXT: br label [[OMP_PRECOND_END]]
// CHECK9: omp.precond.end:
// CHECK9-NEXT: ret void
Expand Down Expand Up @@ -8627,6 +8645,9 @@ int main() {
// CHECK9: omp.dispatch.inc:
// CHECK9-NEXT: br label [[OMP_DISPATCH_COND]]
// CHECK9: omp.dispatch.end:
// CHECK9-NEXT: [[TMP30:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK9-NEXT: [[TMP31:%.*]] = load i32, ptr [[TMP30]], align 4
// CHECK9-NEXT: call void @__kmpc_dispatch_deinit(ptr @[[GLOB3]], i32 [[TMP31]])
// CHECK9-NEXT: br label [[OMP_PRECOND_END]]
// CHECK9: omp.precond.end:
// CHECK9-NEXT: ret void
Expand Down Expand Up @@ -8867,6 +8888,9 @@ int main() {
// CHECK9: omp.dispatch.inc:
// CHECK9-NEXT: br label [[OMP_DISPATCH_COND]]
// CHECK9: omp.dispatch.end:
// CHECK9-NEXT: [[TMP31:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK9-NEXT: [[TMP32:%.*]] = load i32, ptr [[TMP31]], align 4
// CHECK9-NEXT: call void @__kmpc_dispatch_deinit(ptr @[[GLOB3]], i32 [[TMP32]])
// CHECK9-NEXT: br label [[OMP_PRECOND_END]]
// CHECK9: omp.precond.end:
// CHECK9-NEXT: ret void
Expand Down Expand Up @@ -10884,6 +10908,9 @@ int main() {
// CHECK11: omp.dispatch.inc:
// CHECK11-NEXT: br label [[OMP_DISPATCH_COND]]
// CHECK11: omp.dispatch.end:
// CHECK11-NEXT: [[TMP30:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK11-NEXT: [[TMP31:%.*]] = load i32, ptr [[TMP30]], align 4
// CHECK11-NEXT: call void @__kmpc_dispatch_deinit(ptr @[[GLOB3]], i32 [[TMP31]])
// CHECK11-NEXT: br label [[OMP_PRECOND_END]]
// CHECK11: omp.precond.end:
// CHECK11-NEXT: ret void
Expand Down Expand Up @@ -11117,6 +11144,9 @@ int main() {
// CHECK11: omp.dispatch.inc:
// CHECK11-NEXT: br label [[OMP_DISPATCH_COND]]
// CHECK11: omp.dispatch.end:
// CHECK11-NEXT: [[TMP31:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK11-NEXT: [[TMP32:%.*]] = load i32, ptr [[TMP31]], align 4
// CHECK11-NEXT: call void @__kmpc_dispatch_deinit(ptr @[[GLOB3]], i32 [[TMP32]])
// CHECK11-NEXT: br label [[OMP_PRECOND_END]]
// CHECK11: omp.precond.end:
// CHECK11-NEXT: ret void
Expand Down Expand Up @@ -13146,6 +13176,9 @@ int main() {
// CHECK11: omp.dispatch.inc:
// CHECK11-NEXT: br label [[OMP_DISPATCH_COND]]
// CHECK11: omp.dispatch.end:
// CHECK11-NEXT: [[TMP30:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK11-NEXT: [[TMP31:%.*]] = load i32, ptr [[TMP30]], align 4
// CHECK11-NEXT: call void @__kmpc_dispatch_deinit(ptr @[[GLOB3]], i32 [[TMP31]])
// CHECK11-NEXT: br label [[OMP_PRECOND_END]]
// CHECK11: omp.precond.end:
// CHECK11-NEXT: ret void
Expand Down Expand Up @@ -13379,6 +13412,9 @@ int main() {
// CHECK11: omp.dispatch.inc:
// CHECK11-NEXT: br label [[OMP_DISPATCH_COND]]
// CHECK11: omp.dispatch.end:
// CHECK11-NEXT: [[TMP31:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK11-NEXT: [[TMP32:%.*]] = load i32, ptr [[TMP31]], align 4
// CHECK11-NEXT: call void @__kmpc_dispatch_deinit(ptr @[[GLOB3]], i32 [[TMP32]])
// CHECK11-NEXT: br label [[OMP_PRECOND_END]]
// CHECK11: omp.precond.end:
// CHECK11-NEXT: ret void
Expand Down
Loading
Loading