| // NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --function-signature --include-generated-funcs |
| // RUN: %clang_cc1 -fopenmp-enable-irbuilder -verify -fopenmp -fopenmp-version=45 -x c++ -triple x86_64-unknown-unknown -emit-llvm %s -o - | FileCheck %s |
| // expected-no-diagnostics |
| |
| #ifndef HEADER |
| #define HEADER |
| |
| extern "C" void workshareloop_unsigned(float *a, float *b, float *c, float *d) { |
| #pragma omp for |
| for (unsigned i = 33; i < 32000000; i += 7) { |
| a[i] = b[i] * c[i] * d[i]; |
| } |
| } |
| |
| #endif // HEADER |
| // CHECK-LABEL: define {{[^@]+}}@workshareloop_unsigned |
| // CHECK-SAME: (float* [[A:%.*]], float* [[B:%.*]], float* [[C:%.*]], float* [[D:%.*]]) #[[ATTR0:[0-9]+]] { |
| // CHECK-NEXT: entry: |
| // CHECK-NEXT: [[A_ADDR:%.*]] = alloca float*, align 8 |
| // CHECK-NEXT: [[B_ADDR:%.*]] = alloca float*, align 8 |
| // CHECK-NEXT: [[C_ADDR:%.*]] = alloca float*, align 8 |
| // CHECK-NEXT: [[D_ADDR:%.*]] = alloca float*, align 8 |
| // CHECK-NEXT: [[I:%.*]] = alloca i32, align 4 |
| // CHECK-NEXT: [[AGG_CAPTURED:%.*]] = alloca [[STRUCT_ANON:%.*]], align 8 |
| // CHECK-NEXT: [[AGG_CAPTURED1:%.*]] = alloca [[STRUCT_ANON_0:%.*]], align 4 |
| // CHECK-NEXT: [[DOTCOUNT_ADDR:%.*]] = alloca i32, align 4 |
| // CHECK-NEXT: [[P_LASTITER:%.*]] = alloca i32, align 4 |
| // CHECK-NEXT: [[P_LOWERBOUND:%.*]] = alloca i32, align 4 |
| // CHECK-NEXT: [[P_UPPERBOUND:%.*]] = alloca i32, align 4 |
| // CHECK-NEXT: [[P_STRIDE:%.*]] = alloca i32, align 4 |
| // CHECK-NEXT: store float* [[A]], float** [[A_ADDR]], align 8 |
| // CHECK-NEXT: store float* [[B]], float** [[B_ADDR]], align 8 |
| // CHECK-NEXT: store float* [[C]], float** [[C_ADDR]], align 8 |
| // CHECK-NEXT: store float* [[D]], float** [[D_ADDR]], align 8 |
| // CHECK-NEXT: store i32 33, i32* [[I]], align 4 |
| // CHECK-NEXT: [[TMP0:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[AGG_CAPTURED]], i32 0, i32 0 |
| // CHECK-NEXT: store i32* [[I]], i32** [[TMP0]], align 8 |
| // CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_0]], %struct.anon.0* [[AGG_CAPTURED1]], i32 0, i32 0 |
| // CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[I]], align 4 |
| // CHECK-NEXT: store i32 [[TMP2]], i32* [[TMP1]], align 4 |
| // CHECK-NEXT: call void @__captured_stmt(i32* [[DOTCOUNT_ADDR]], %struct.anon* [[AGG_CAPTURED]]) |
| // CHECK-NEXT: [[DOTCOUNT:%.*]] = load i32, i32* [[DOTCOUNT_ADDR]], align 4 |
| // CHECK-NEXT: br label [[OMP_LOOP_PREHEADER:%.*]] |
| // CHECK: omp_loop.preheader: |
| // CHECK-NEXT: store i32 0, i32* [[P_LOWERBOUND]], align 4 |
| // CHECK-NEXT: [[TMP3:%.*]] = sub i32 [[DOTCOUNT]], 1 |
| // CHECK-NEXT: store i32 [[TMP3]], i32* [[P_UPPERBOUND]], align 4 |
| // CHECK-NEXT: store i32 1, i32* [[P_STRIDE]], align 4 |
| // CHECK-NEXT: [[OMP_GLOBAL_THREAD_NUM:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1:[0-9]+]]) |
| // CHECK-NEXT: call void @__kmpc_for_static_init_4u(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM]], i32 34, i32* [[P_LASTITER]], i32* [[P_LOWERBOUND]], i32* [[P_UPPERBOUND]], i32* [[P_STRIDE]], i32 1, i32 1) |
| // CHECK-NEXT: [[TMP4:%.*]] = load i32, i32* [[P_LOWERBOUND]], align 4 |
| // CHECK-NEXT: [[TMP5:%.*]] = load i32, i32* [[P_UPPERBOUND]], align 4 |
| // CHECK-NEXT: [[TMP6:%.*]] = sub i32 [[TMP5]], [[TMP4]] |
| // CHECK-NEXT: [[TMP7:%.*]] = add i32 [[TMP6]], 1 |
| // CHECK-NEXT: br label [[OMP_LOOP_HEADER:%.*]] |
| // CHECK: omp_loop.header: |
| // CHECK-NEXT: [[OMP_LOOP_IV:%.*]] = phi i32 [ 0, [[OMP_LOOP_PREHEADER]] ], [ [[OMP_LOOP_NEXT:%.*]], [[OMP_LOOP_INC:%.*]] ] |
| // CHECK-NEXT: br label [[OMP_LOOP_COND:%.*]] |
| // CHECK: omp_loop.cond: |
| // CHECK-NEXT: [[OMP_LOOP_CMP:%.*]] = icmp ult i32 [[OMP_LOOP_IV]], [[TMP7]] |
| // CHECK-NEXT: br i1 [[OMP_LOOP_CMP]], label [[OMP_LOOP_BODY:%.*]], label [[OMP_LOOP_EXIT:%.*]] |
| // CHECK: omp_loop.body: |
| // CHECK-NEXT: [[TMP8:%.*]] = add i32 [[OMP_LOOP_IV]], [[TMP4]] |
| // CHECK-NEXT: call void @__captured_stmt.1(i32* [[I]], i32 [[TMP8]], %struct.anon.0* [[AGG_CAPTURED1]]) |
| // CHECK-NEXT: [[TMP9:%.*]] = load float*, float** [[B_ADDR]], align 8 |
| // CHECK-NEXT: [[TMP10:%.*]] = load i32, i32* [[I]], align 4 |
| // CHECK-NEXT: [[IDXPROM:%.*]] = zext i32 [[TMP10]] to i64 |
| // CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds float, float* [[TMP9]], i64 [[IDXPROM]] |
| // CHECK-NEXT: [[TMP11:%.*]] = load float, float* [[ARRAYIDX]], align 4 |
| // CHECK-NEXT: [[TMP12:%.*]] = load float*, float** [[C_ADDR]], align 8 |
| // CHECK-NEXT: [[TMP13:%.*]] = load i32, i32* [[I]], align 4 |
| // CHECK-NEXT: [[IDXPROM2:%.*]] = zext i32 [[TMP13]] to i64 |
| // CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds float, float* [[TMP12]], i64 [[IDXPROM2]] |
| // CHECK-NEXT: [[TMP14:%.*]] = load float, float* [[ARRAYIDX3]], align 4 |
| // CHECK-NEXT: [[MUL:%.*]] = fmul float [[TMP11]], [[TMP14]] |
| // CHECK-NEXT: [[TMP15:%.*]] = load float*, float** [[D_ADDR]], align 8 |
| // CHECK-NEXT: [[TMP16:%.*]] = load i32, i32* [[I]], align 4 |
| // CHECK-NEXT: [[IDXPROM4:%.*]] = zext i32 [[TMP16]] to i64 |
| // CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds float, float* [[TMP15]], i64 [[IDXPROM4]] |
| // CHECK-NEXT: [[TMP17:%.*]] = load float, float* [[ARRAYIDX5]], align 4 |
| // CHECK-NEXT: [[MUL6:%.*]] = fmul float [[MUL]], [[TMP17]] |
| // CHECK-NEXT: [[TMP18:%.*]] = load float*, float** [[A_ADDR]], align 8 |
| // CHECK-NEXT: [[TMP19:%.*]] = load i32, i32* [[I]], align 4 |
| // CHECK-NEXT: [[IDXPROM7:%.*]] = zext i32 [[TMP19]] to i64 |
| // CHECK-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds float, float* [[TMP18]], i64 [[IDXPROM7]] |
| // CHECK-NEXT: store float [[MUL6]], float* [[ARRAYIDX8]], align 4 |
| // CHECK-NEXT: br label [[OMP_LOOP_INC]] |
| // CHECK: omp_loop.inc: |
| // CHECK-NEXT: [[OMP_LOOP_NEXT]] = add nuw i32 [[OMP_LOOP_IV]], 1 |
| // CHECK-NEXT: br label [[OMP_LOOP_HEADER]] |
| // CHECK: omp_loop.exit: |
| // CHECK-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM]]) |
| // CHECK-NEXT: [[OMP_GLOBAL_THREAD_NUM9:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1]]) |
| // CHECK-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB2:[0-9]+]], i32 [[OMP_GLOBAL_THREAD_NUM9]]) |
| // CHECK-NEXT: br label [[OMP_LOOP_AFTER:%.*]] |
| // CHECK: omp_loop.after: |
| // CHECK-NEXT: ret void |
| // |
| // |
| // CHECK-LABEL: define {{[^@]+}}@__captured_stmt |
| // CHECK-SAME: (i32* nonnull align 4 dereferenceable(4) [[DISTANCE:%.*]], %struct.anon* noalias [[__CONTEXT:%.*]]) #[[ATTR1:[0-9]+]] { |
| // CHECK-NEXT: entry: |
| // CHECK-NEXT: [[DISTANCE_ADDR:%.*]] = alloca i32*, align 8 |
| // CHECK-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon*, align 8 |
| // CHECK-NEXT: [[DOTSTART:%.*]] = alloca i32, align 4 |
| // CHECK-NEXT: [[DOTSTOP:%.*]] = alloca i32, align 4 |
| // CHECK-NEXT: [[DOTSTEP:%.*]] = alloca i32, align 4 |
| // CHECK-NEXT: store i32* [[DISTANCE]], i32** [[DISTANCE_ADDR]], align 8 |
| // CHECK-NEXT: store %struct.anon* [[__CONTEXT]], %struct.anon** [[__CONTEXT_ADDR]], align 8 |
| // CHECK-NEXT: [[TMP0:%.*]] = load %struct.anon*, %struct.anon** [[__CONTEXT_ADDR]], align 8 |
| // CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON:%.*]], %struct.anon* [[TMP0]], i32 0, i32 0 |
| // CHECK-NEXT: [[TMP2:%.*]] = load i32*, i32** [[TMP1]], align 8 |
| // CHECK-NEXT: [[TMP3:%.*]] = load i32, i32* [[TMP2]], align 4 |
| // CHECK-NEXT: store i32 [[TMP3]], i32* [[DOTSTART]], align 4 |
| // CHECK-NEXT: store i32 32000000, i32* [[DOTSTOP]], align 4 |
| // CHECK-NEXT: store i32 7, i32* [[DOTSTEP]], align 4 |
| // CHECK-NEXT: [[TMP4:%.*]] = load i32, i32* [[DOTSTART]], align 4 |
| // CHECK-NEXT: [[TMP5:%.*]] = load i32, i32* [[DOTSTOP]], align 4 |
| // CHECK-NEXT: [[CMP:%.*]] = icmp ult i32 [[TMP4]], [[TMP5]] |
| // CHECK-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]] |
| // CHECK: cond.true: |
| // CHECK-NEXT: [[TMP6:%.*]] = load i32, i32* [[DOTSTOP]], align 4 |
| // CHECK-NEXT: [[TMP7:%.*]] = load i32, i32* [[DOTSTART]], align 4 |
| // CHECK-NEXT: [[SUB:%.*]] = sub i32 [[TMP6]], [[TMP7]] |
| // CHECK-NEXT: [[TMP8:%.*]] = load i32, i32* [[DOTSTEP]], align 4 |
| // CHECK-NEXT: [[DIV:%.*]] = udiv i32 [[SUB]], [[TMP8]] |
| // CHECK-NEXT: br label [[COND_END:%.*]] |
| // CHECK: cond.false: |
| // CHECK-NEXT: br label [[COND_END]] |
| // CHECK: cond.end: |
| // CHECK-NEXT: [[COND:%.*]] = phi i32 [ [[DIV]], [[COND_TRUE]] ], [ 0, [[COND_FALSE]] ] |
| // CHECK-NEXT: [[TMP9:%.*]] = load i32*, i32** [[DISTANCE_ADDR]], align 8 |
| // CHECK-NEXT: store i32 [[COND]], i32* [[TMP9]], align 4 |
| // CHECK-NEXT: ret void |
| // |
| // |
| // CHECK-LABEL: define {{[^@]+}}@__captured_stmt.1 |
| // CHECK-SAME: (i32* nonnull align 4 dereferenceable(4) [[LOOPVAR:%.*]], i32 [[LOGICAL:%.*]], %struct.anon.0* noalias [[__CONTEXT:%.*]]) #[[ATTR1]] { |
| // CHECK-NEXT: entry: |
| // CHECK-NEXT: [[LOOPVAR_ADDR:%.*]] = alloca i32*, align 8 |
| // CHECK-NEXT: [[LOGICAL_ADDR:%.*]] = alloca i32, align 4 |
| // CHECK-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.0*, align 8 |
| // CHECK-NEXT: store i32* [[LOOPVAR]], i32** [[LOOPVAR_ADDR]], align 8 |
| // CHECK-NEXT: store i32 [[LOGICAL]], i32* [[LOGICAL_ADDR]], align 4 |
| // CHECK-NEXT: store %struct.anon.0* [[__CONTEXT]], %struct.anon.0** [[__CONTEXT_ADDR]], align 8 |
| // CHECK-NEXT: [[TMP0:%.*]] = load %struct.anon.0*, %struct.anon.0** [[__CONTEXT_ADDR]], align 8 |
| // CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_0:%.*]], %struct.anon.0* [[TMP0]], i32 0, i32 0 |
| // CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[TMP1]], align 4 |
| // CHECK-NEXT: [[TMP3:%.*]] = load i32, i32* [[LOGICAL_ADDR]], align 4 |
| // CHECK-NEXT: [[MUL:%.*]] = mul i32 7, [[TMP3]] |
| // CHECK-NEXT: [[ADD:%.*]] = add i32 [[TMP2]], [[MUL]] |
| // CHECK-NEXT: [[TMP4:%.*]] = load i32*, i32** [[LOOPVAR_ADDR]], align 8 |
| // CHECK-NEXT: store i32 [[ADD]], i32* [[TMP4]], align 4 |
| // CHECK-NEXT: ret void |
| // |