diff options
Diffstat (limited to 'test/OpenMP/parallel_for_codegen.cpp')
| -rw-r--r-- | test/OpenMP/parallel_for_codegen.cpp | 63 |
1 files changed, 22 insertions, 41 deletions
diff --git a/test/OpenMP/parallel_for_codegen.cpp b/test/OpenMP/parallel_for_codegen.cpp index 9fda840..036fa37 100644 --- a/test/OpenMP/parallel_for_codegen.cpp +++ b/test/OpenMP/parallel_for_codegen.cpp @@ -1,7 +1,7 @@ // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple x86_64-unknown-unknown -emit-llvm %s -fexceptions -fcxx-exceptions -o - | FileCheck %s // RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -emit-pch -o %t %s // RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s -// RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -fopenmp -fexceptions -fcxx-exceptions -gline-tables-only -x c++ -emit-llvm %s -o - | FileCheck %s --check-prefix=TERM_DEBUG +// RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -fopenmp -fexceptions -fcxx-exceptions -debug-info-kind=line-tables-only -x c++ -emit-llvm %s -o - | FileCheck %s --check-prefix=TERM_DEBUG // RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -O1 -fopenmp -emit-llvm %s -o - | FileCheck %s --check-prefix=CLEANUP // REQUIRES: x86-registered-target // expected-no-diagnostics @@ -9,25 +9,19 @@ #define HEADER // CHECK-DAG: [[IDENT_T_TY:%.+]] = type { i32, i32, i32, i32, i8* } -// CHECK-DAG: [[CAP_TY:%.+]] = type { i8* } // CHECK-LABEL: with_var_schedule void with_var_schedule() { double a = 5; // CHECK: [[CHUNK_SIZE:%.+]] = fptosi double %{{.+}}to i8 // CHECK: store i8 %{{.+}}, i8* [[CHUNK:%.+]], -// CHECK: [[CHUNK_REF:%.+]] = getelementptr inbounds [[CAP_TY]], [[CAP_TY]]* [[CAP_ARG:%.+]], i{{.+}} 0, i{{.+}} 0 -// CHECK: store i8* [[CHUNK]], i8** [[CHUNK_REF]], -// CHECK: [[BITCAST:%.+]] = bitcast [[CAP_TY]]* [[CAP_ARG]] to i8* -// CHECK: call void {{.+}} @__kmpc_fork_call({{.+}}, i8* [[BITCAST]]) +// CHECK: call void {{.+}} @__kmpc_fork_call({{.+}}, i8* [[CHUNK]]) -// CHECK: [[CHUNK_REF:%.+]] = getelementptr inbounds [[CAP_TY]], [[CAP_TY]]* %{{.+}}, i{{.+}} 0, i{{.+}} 0 -// CHECK: [[CHUNK:%.+]] = load i8*, i8** [[CHUNK_REF]], +// CHECK: [[CHUNK:%.+]] = load i8*, i8** % // CHECK: [[CHUNK_VAL:%.+]] = load i8, i8* [[CHUNK]], // CHECK: [[CHUNK_SIZE:%.+]] = sext i8 [[CHUNK_VAL]] to i64 // CHECK: call void @__kmpc_for_static_init_8u([[IDENT_T_TY]]* [[DEFAULT_LOC:@[^,]+]], i32 [[GTID:%[^,]+]], i32 33, i32* [[IS_LAST:%[^,]+]], i64* [[OMP_LB:%[^,]+]], i64* [[OMP_UB:%[^,]+]], i64* [[OMP_ST:%[^,]+]], i64 1, i64 [[CHUNK_SIZE]]) // CHECK: call void @__kmpc_for_static_fini([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]]) -// CHECK: __kmpc_barrier #pragma omp parallel for schedule(static, char(a)) for (unsigned long long i = 1; i < 2; ++i) { } @@ -36,8 +30,8 @@ void with_var_schedule() { // CHECK-LABEL: define {{.*void}} @{{.*}}without_schedule_clause{{.*}}(float* {{.+}}, float* {{.+}}, float* {{.+}}, float* {{.+}}) void without_schedule_clause(float *a, float *b, float *c, float *d) { #pragma omp parallel for -// CHECK: call void ([[IDENT_T_TY]]*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call([[IDENT_T_TY]]* [[DEFAULT_LOC:[@%].+]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %{{.+}}*)* [[OMP_PARALLEL_FUNC:@.+]] to void (i32*, i32*, ...)*), i8* %{{.+}}) -// CHECK: define internal void [[OMP_PARALLEL_FUNC]](i32* [[GTID_PARAM_ADDR:%.+]], i32* %{{.+}}, %{{.+}}* %{{.+}}) +// CHECK: call void ([[IDENT_T_TY]]*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call([[IDENT_T_TY]]* [[DEFAULT_LOC:[@%].+]], i32 4, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, float**, float**, float**, float**)* [[OMP_PARALLEL_FUNC:@.+]] to void (i32*, i32*, ...)*), +// CHECK: define internal void [[OMP_PARALLEL_FUNC]](i32* noalias [[GTID_PARAM_ADDR:%.+]], i32* noalias %{{.+}}, float** dereferenceable(8) %{{.+}}, float** dereferenceable(8) %{{.+}}, float** dereferenceable(8) %{{.+}}, float** dereferenceable(8) %{{.+}}) // CHECK: store i32* [[GTID_PARAM_ADDR]], i32** [[GTID_REF_ADDR:%.+]], // CHECK: [[GTID_REF:%.+]] = load i32*, i32** [[GTID_REF_ADDR]], // CHECK: [[GTID:%.+]] = load i32, i32* [[GTID_REF]], @@ -73,15 +67,14 @@ void without_schedule_clause(float *a, float *b, float *c, float *d) { } // CHECK: [[LOOP1_END]] // CHECK: call void @__kmpc_for_static_fini([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]]) -// CHECK: call {{.+}} @__kmpc_barrier([[IDENT_T_TY]]* [[DEFAULT_LOC_BARRIER:[@%].+]], i32 [[GTID]]) // CHECK: ret void } // CHECK-LABEL: define {{.*void}} @{{.*}}static_not_chunked{{.*}}(float* {{.+}}, float* {{.+}}, float* {{.+}}, float* {{.+}}) void static_not_chunked(float *a, float *b, float *c, float *d) { #pragma omp parallel for schedule(static) -// CHECK: call void ([[IDENT_T_TY]]*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %{{.+}}*)* [[OMP_PARALLEL_FUNC:@.+]] to void (i32*, i32*, ...)*), i8* %{{.+}}) -// CHECK: define internal void [[OMP_PARALLEL_FUNC]](i32* [[GTID_PARAM_ADDR:%.+]], i32* %{{.+}}, %{{.+}}* %{{.+}}) +// CHECK: call void ([[IDENT_T_TY]]*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call([[IDENT_T_TY]]* [[DEFAULT_LOC:[@%].+]], i32 4, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, float**, float**, float**, float**)* [[OMP_PARALLEL_FUNC:@.+]] to void (i32*, i32*, ...)*), +// CHECK: define internal void [[OMP_PARALLEL_FUNC]](i32* noalias [[GTID_PARAM_ADDR:%.+]], i32* noalias %{{.+}}, float** dereferenceable(8) %{{.+}}, float** dereferenceable(8) %{{.+}}, float** dereferenceable(8) %{{.+}}, float** dereferenceable(8) %{{.+}}) // CHECK: store i32* [[GTID_PARAM_ADDR]], i32** [[GTID_REF_ADDR:%.+]], // CHECK: [[GTID_REF:%.+]] = load i32*, i32** [[GTID_REF_ADDR]], // CHECK: [[GTID:%.+]] = load i32, i32* [[GTID_REF]], @@ -117,15 +110,14 @@ void static_not_chunked(float *a, float *b, float *c, float *d) { } // CHECK: [[LOOP1_END]] // CHECK: call void @__kmpc_for_static_fini([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]]) -// CHECK: call {{.+}} @__kmpc_barrier([[IDENT_T_TY]]* [[DEFAULT_LOC_BARRIER:[@%].+]], i32 [[GTID]]) // CHECK: ret void } // CHECK-LABEL: define {{.*void}} @{{.*}}static_chunked{{.*}}(float* {{.+}}, float* {{.+}}, float* {{.+}}, float* {{.+}}) void static_chunked(float *a, float *b, float *c, float *d) { #pragma omp parallel for schedule(static, 5) -// CHECK: call void ([[IDENT_T_TY]]*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %{{.+}}*)* [[OMP_PARALLEL_FUNC:@.+]] to void (i32*, i32*, ...)*), i8* %{{.+}}) -// CHECK: define internal void [[OMP_PARALLEL_FUNC]](i32* [[GTID_PARAM_ADDR:%.+]], i32* %{{.+}}, %{{.+}}* %{{.+}}) +// CHECK: call void ([[IDENT_T_TY]]*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call([[IDENT_T_TY]]* [[DEFAULT_LOC:[@%].+]], i32 4, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, float**, float**, float**, float**)* [[OMP_PARALLEL_FUNC:@.+]] to void (i32*, i32*, ...)*), +// CHECK: define internal void [[OMP_PARALLEL_FUNC]](i32* noalias [[GTID_PARAM_ADDR:%.+]], i32* noalias %{{.+}}, float** dereferenceable(8) %{{.+}}, float** dereferenceable(8) %{{.+}}, float** dereferenceable(8) %{{.+}}, float** dereferenceable(8) %{{.+}}) // CHECK: store i32* [[GTID_PARAM_ADDR]], i32** [[GTID_REF_ADDR:%.+]], // CHECK: [[GTID_REF:%.+]] = load i32*, i32** [[GTID_REF_ADDR]], // CHECK: [[GTID:%.+]] = load i32, i32* [[GTID_REF]], @@ -180,15 +172,14 @@ void static_chunked(float *a, float *b, float *c, float *d) { // CHECK: [[O_LOOP1_END]] // CHECK: call void @__kmpc_for_static_fini([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]]) -// CHECK: call {{.+}} @__kmpc_barrier([[IDENT_T_TY]]* [[DEFAULT_LOC_BARRIER:[@%].+]], i32 [[GTID]]) // CHECK: ret void } // CHECK-LABEL: define {{.*void}} @{{.*}}dynamic1{{.*}}(float* {{.+}}, float* {{.+}}, float* {{.+}}, float* {{.+}}) void dynamic1(float *a, float *b, float *c, float *d) { #pragma omp parallel for schedule(dynamic) -// CHECK: call void ([[IDENT_T_TY]]*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %{{.+}}*)* [[OMP_PARALLEL_FUNC:@.+]] to void (i32*, i32*, ...)*), i8* %{{.+}}) -// CHECK: define internal void [[OMP_PARALLEL_FUNC]](i32* [[GTID_PARAM_ADDR:%.+]], i32* %{{.+}}, %{{.+}}* %{{.+}}) +// CHECK: call void ([[IDENT_T_TY]]*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call([[IDENT_T_TY]]* [[DEFAULT_LOC:[@%].+]], i32 4, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, float**, float**, float**, float**)* [[OMP_PARALLEL_FUNC:@.+]] to void (i32*, i32*, ...)*), +// CHECK: define internal void [[OMP_PARALLEL_FUNC]](i32* noalias [[GTID_PARAM_ADDR:%.+]], i32* noalias %{{.+}}, float** dereferenceable(8) %{{.+}}, float** dereferenceable(8) %{{.+}}, float** dereferenceable(8) %{{.+}}, float** dereferenceable(8) %{{.+}}) // CHECK: store i32* [[GTID_PARAM_ADDR]], i32** [[GTID_REF_ADDR:%.+]], // CHECK: [[GTID_REF:%.+]] = load i32*, i32** [[GTID_REF_ADDR]], // CHECK: [[GTID:%.+]] = load i32, i32* [[GTID_REF]], @@ -225,15 +216,14 @@ void dynamic1(float *a, float *b, float *c, float *d) { } // CHECK: [[LOOP1_END]] // CHECK: [[O_LOOP1_END]] -// CHECK: call {{.+}} @__kmpc_barrier([[IDENT_T_TY]]* [[DEFAULT_LOC_BARRIER:[@%].+]], i32 [[GTID]]) // CHECK: ret void } // CHECK-LABEL: define {{.*void}} @{{.*}}guided7{{.*}}(float* {{.+}}, float* {{.+}}, float* {{.+}}, float* {{.+}}) void guided7(float *a, float *b, float *c, float *d) { #pragma omp parallel for schedule(guided, 7) -// CHECK: call void ([[IDENT_T_TY]]*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %{{.+}}*)* [[OMP_PARALLEL_FUNC:@.+]] to void (i32*, i32*, ...)*), i8* %{{.+}}) -// CHECK: define internal void [[OMP_PARALLEL_FUNC]](i32* [[GTID_PARAM_ADDR:%.+]], i32* %{{.+}}, %{{.+}}* %{{.+}}) +// CHECK: call void ([[IDENT_T_TY]]*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call([[IDENT_T_TY]]* [[DEFAULT_LOC:[@%].+]], i32 4, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, float**, float**, float**, float**)* [[OMP_PARALLEL_FUNC:@.+]] to void (i32*, i32*, ...)*), +// CHECK: define internal void [[OMP_PARALLEL_FUNC]](i32* noalias [[GTID_PARAM_ADDR:%.+]], i32* noalias %{{.+}}, float** dereferenceable(8) %{{.+}}, float** dereferenceable(8) %{{.+}}, float** dereferenceable(8) %{{.+}}, float** dereferenceable(8) %{{.+}}) // CHECK: store i32* [[GTID_PARAM_ADDR]], i32** [[GTID_REF_ADDR:%.+]], // CHECK: [[GTID_REF:%.+]] = load i32*, i32** [[GTID_REF_ADDR]], // CHECK: [[GTID:%.+]] = load i32, i32* [[GTID_REF]], @@ -270,7 +260,6 @@ void guided7(float *a, float *b, float *c, float *d) { } // CHECK: [[LOOP1_END]] // CHECK: [[O_LOOP1_END]] -// CHECK: call {{.+}} @__kmpc_barrier([[IDENT_T_TY]]* [[DEFAULT_LOC_BARRIER:[@%].+]], i32 [[GTID]]) // CHECK: ret void } @@ -279,8 +268,8 @@ void test_auto(float *a, float *b, float *c, float *d) { unsigned int x = 0; unsigned int y = 0; #pragma omp parallel for schedule(auto) collapse(2) -// CHECK: call void ([[IDENT_T_TY]]*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %{{.+}}*)* [[OMP_PARALLEL_FUNC:@.+]] to void (i32*, i32*, ...)*), i8* %{{.+}}) -// CHECK: define internal void [[OMP_PARALLEL_FUNC]](i32* [[GTID_PARAM_ADDR:%.+]], i32* %{{.+}}, %{{.+}}* %{{.+}}) +// CHECK: call void ([[IDENT_T_TY]]*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call([[IDENT_T_TY]]* [[DEFAULT_LOC:[@%].+]], i32 6, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i32*, i32*, float**, float**, float**, float**)* [[OMP_PARALLEL_FUNC:@.+]] to void (i32*, i32*, ...)*), +// CHECK: define internal void [[OMP_PARALLEL_FUNC]](i32* noalias [[GTID_PARAM_ADDR:%.+]], i32* noalias %{{.+}}, i32* dereferenceable(4) %{{.+}}, i32* dereferenceable(4) %{{.+}}, float** dereferenceable(8) %{{.+}}, float** dereferenceable(8) %{{.+}}, float** dereferenceable(8) %{{.+}}, float** dereferenceable(8) %{{.+}}) // CHECK: store i32* [[GTID_PARAM_ADDR]], i32** [[GTID_REF_ADDR:%.+]], // CHECK: [[GTID_REF:%.+]] = load i32*, i32** [[GTID_REF_ADDR]], // CHECK: [[GTID:%.+]] = load i32, i32* [[GTID_REF]], @@ -320,9 +309,6 @@ void test_auto(float *a, float *b, float *c, float *d) { } // CHECK: [[LOOP1_END]] // CHECK: [[O_LOOP1_END]] -// CHECK: [[GTID_REF:%.+]] = load i32*, i32** [[GTID_REF_ADDR]], -// CHECK: [[GTID:%.+]] = load i32, i32* [[GTID_REF]], -// CHECK: call {{.+}} @__kmpc_barrier([[IDENT_T_TY]]* [[DEFAULT_LOC_BARRIER:[@%].+]], i32 [[GTID]]) // CHECK: ret void } @@ -330,8 +316,8 @@ void test_auto(float *a, float *b, float *c, float *d) { void runtime(float *a, float *b, float *c, float *d) { int x = 0; #pragma omp parallel for collapse(2) schedule(runtime) -// CHECK: call void ([[IDENT_T_TY]]*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %{{.+}}*)* [[OMP_PARALLEL_FUNC:@.+]] to void (i32*, i32*, ...)*), i8* %{{.+}}) -// CHECK: define internal void [[OMP_PARALLEL_FUNC]](i32* [[GTID_PARAM_ADDR:%.+]], i32* %{{.+}}, %{{.+}}* %{{.+}}) +// CHECK: call void ([[IDENT_T_TY]]*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call([[IDENT_T_TY]]* [[DEFAULT_LOC:[@%].+]], i32 5, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i32*, float**, float**, float**, float**)* [[OMP_PARALLEL_FUNC:@.+]] to void (i32*, i32*, ...)*), +// CHECK: define internal void [[OMP_PARALLEL_FUNC]](i32* noalias [[GTID_PARAM_ADDR:%.+]], i32* noalias %{{.+}}, i32* dereferenceable(4) %{{.+}}, float** dereferenceable(8) %{{.+}}, float** dereferenceable(8) %{{.+}}, float** dereferenceable(8) %{{.+}}, float** dereferenceable(8) %{{.+}}) // CHECK: store i32* [[GTID_PARAM_ADDR]], i32** [[GTID_REF_ADDR:%.+]], // CHECK: [[GTID_REF:%.+]] = load i32*, i32** [[GTID_REF_ADDR]], // CHECK: [[GTID:%.+]] = load i32, i32* [[GTID_REF]], @@ -367,9 +353,6 @@ void runtime(float *a, float *b, float *c, float *d) { } // CHECK: [[LOOP1_END]] // CHECK: [[O_LOOP1_END]] -// CHECK: [[GTID_REF:%.+]] = load i32*, i32** [[GTID_REF_ADDR]], -// CHECK: [[GTID:%.+]] = load i32, i32* [[GTID_REF]], -// CHECK: call {{.+}} @__kmpc_barrier([[IDENT_T_TY]]* [[DEFAULT_LOC_BARRIER:[@%].+]], i32 [[GTID]]) // CHECK: ret void } @@ -378,29 +361,27 @@ int foo() {return 0;}; // TERM_DEBUG-LABEL: parallel_for // CLEANUP: parallel_for -void parallel_for(float *a) { -#pragma omp parallel for schedule(static, 5) +void parallel_for(float *a, int n) { + float arr[n]; +#pragma omp parallel for schedule(static, 5) private(arr) // TERM_DEBUG-NOT: __kmpc_global_thread_num // TERM_DEBUG: call void @__kmpc_for_static_init_4u({{.+}}), !dbg [[DBG_LOC_START:![0-9]+]] // TERM_DEBUG: invoke i32 {{.*}}foo{{.*}}() // TERM_DEBUG: unwind label %[[TERM_LPAD:.+]], // TERM_DEBUG-NOT: __kmpc_global_thread_num // TERM_DEBUG: call void @__kmpc_for_static_fini({{.+}}), !dbg [[DBG_LOC_END:![0-9]+]] - // TERM_DEBUG: call {{.+}} @__kmpc_barrier({{.+}}), !dbg [[DBG_LOC_CANCEL:![0-9]+]] // TERM_DEBUG: [[TERM_LPAD]] // TERM_DEBUG: call void @__clang_call_terminate // TERM_DEBUG: unreachable // CLEANUP-NOT: __kmpc_global_thread_num // CLEANUP: call void @__kmpc_for_static_init_4u({{.+}}) // CLEANUP: call void @__kmpc_for_static_fini({{.+}}) - // CLEANUP: call {{.+}} @__kmpc_barrier({{.+}}) for (unsigned i = 131071; i <= 2147483647; i += 127) - a[i] += foo(); + a[i] += foo() + arr[i]; } // Check source line corresponds to "#pragma omp parallel for schedule(static, 5)" above: // TERM_DEBUG-DAG: [[DBG_LOC_START]] = !DILocation(line: [[@LINE-4]], -// TERM_DEBUG-DAG: [[DBG_LOC_END]] = !DILocation(line: [[@LINE-20]], -// TERM_DEBUG-DAG: [[DBG_LOC_CANCEL]] = !DILocation(line: [[@LINE-21]], +// TERM_DEBUG-DAG: [[DBG_LOC_END]] = !DILocation(line: [[@LINE-18]], #endif // HEADER |
