| // NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --include-generated-funcs |
| // Check that the CHECK lines are generated for clang-generated functions |
| // RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu -fopenmp %s -emit-llvm -o - | FileCheck --check-prefix=OMP %s |
| // RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu %s -emit-llvm -o - | FileCheck --check-prefix=NOOMP %s |
| |
| const int size = 1024 * 1024 * 32; |
| |
| double A[size]; |
| |
| void foo(void); |
| |
| int main() { |
| int i = 0; |
| |
| #pragma omp parallel for |
| for (i = 0; i < size; ++i) { |
| A[i] = 0.0; |
| } |
| |
| foo(); |
| |
| return 0; |
| } |
| |
| void foo(void) { |
| int i = 0; |
| |
| #pragma omp parallel for |
| for (i = 0; i < size; ++i) { |
| A[i] = 1.0; |
| } |
| } |
| // OMP-LABEL: @main( |
| // OMP-NEXT: entry: |
| // OMP-NEXT: [[RETVAL:%.*]] = alloca i32, align 4 |
| // OMP-NEXT: [[I:%.*]] = alloca i32, align 4 |
| // OMP-NEXT: store i32 0, i32* [[RETVAL]], align 4 |
| // OMP-NEXT: store i32 0, i32* [[I]], align 4 |
| // OMP-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB2:[0-9]+]], i32 0, void (i32*, i32*, ...)* bitcast (void (i32*, i32*)* @.omp_outlined. to void (i32*, i32*, ...)*)) |
| // OMP-NEXT: call void @foo() |
| // OMP-NEXT: ret i32 0 |
| // |
| // |
| // OMP-LABEL: @.omp_outlined.( |
| // OMP-NEXT: entry: |
| // OMP-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8 |
| // OMP-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8 |
| // OMP-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4 |
| // OMP-NEXT: [[TMP:%.*]] = alloca i32, align 4 |
| // OMP-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4 |
| // OMP-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4 |
| // OMP-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4 |
| // OMP-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4 |
| // OMP-NEXT: [[I:%.*]] = alloca i32, align 4 |
| // OMP-NEXT: store i32* [[DOTGLOBAL_TID_:%.*]], i32** [[DOTGLOBAL_TID__ADDR]], align 8 |
| // OMP-NEXT: store i32* [[DOTBOUND_TID_:%.*]], i32** [[DOTBOUND_TID__ADDR]], align 8 |
| // OMP-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4 |
| // OMP-NEXT: store i32 33554431, i32* [[DOTOMP_UB]], align 4 |
| // OMP-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4 |
| // OMP-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4 |
| // OMP-NEXT: [[TMP0:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8 |
| // OMP-NEXT: [[TMP1:%.*]] = load i32, i32* [[TMP0]], align 4 |
| // OMP-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 [[TMP1]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1) |
| // OMP-NEXT: [[TMP2:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4 |
| // OMP-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP2]], 33554431 |
| // OMP-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]] |
| // OMP: cond.true: |
| // OMP-NEXT: br label [[COND_END:%.*]] |
| // OMP: cond.false: |
| // OMP-NEXT: [[TMP3:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4 |
| // OMP-NEXT: br label [[COND_END]] |
| // OMP: cond.end: |
| // OMP-NEXT: [[COND:%.*]] = phi i32 [ 33554431, [[COND_TRUE]] ], [ [[TMP3]], [[COND_FALSE]] ] |
| // OMP-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4 |
| // OMP-NEXT: [[TMP4:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4 |
| // OMP-NEXT: store i32 [[TMP4]], i32* [[DOTOMP_IV]], align 4 |
| // OMP-NEXT: br label [[OMP_INNER_FOR_COND:%.*]] |
| // OMP: omp.inner.for.cond: |
| // OMP-NEXT: [[TMP5:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4 |
| // OMP-NEXT: [[TMP6:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4 |
| // OMP-NEXT: [[CMP1:%.*]] = icmp sle i32 [[TMP5]], [[TMP6]] |
| // OMP-NEXT: br i1 [[CMP1]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_END:%.*]] |
| // OMP: omp.inner.for.body: |
| // OMP-NEXT: [[TMP7:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4 |
| // OMP-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP7]], 1 |
| // OMP-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]] |
| // OMP-NEXT: store i32 [[ADD]], i32* [[I]], align 4 |
| // OMP-NEXT: [[TMP8:%.*]] = load i32, i32* [[I]], align 4 |
| // OMP-NEXT: [[IDXPROM:%.*]] = sext i32 [[TMP8]] to i64 |
| // OMP-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [33554432 x double], [33554432 x double]* @A, i64 0, i64 [[IDXPROM]] |
| // OMP-NEXT: store double 0.000000e+00, double* [[ARRAYIDX]], align 8 |
| // OMP-NEXT: br label [[OMP_BODY_CONTINUE:%.*]] |
| // OMP: omp.body.continue: |
| // OMP-NEXT: br label [[OMP_INNER_FOR_INC:%.*]] |
| // OMP: omp.inner.for.inc: |
| // OMP-NEXT: [[TMP9:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4 |
| // OMP-NEXT: [[ADD2:%.*]] = add nsw i32 [[TMP9]], 1 |
| // OMP-NEXT: store i32 [[ADD2]], i32* [[DOTOMP_IV]], align 4 |
| // OMP-NEXT: br label [[OMP_INNER_FOR_COND]] |
| // OMP: omp.inner.for.end: |
| // OMP-NEXT: br label [[OMP_LOOP_EXIT:%.*]] |
| // OMP: omp.loop.exit: |
| // OMP-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP1]]) |
| // OMP-NEXT: ret void |
| // |
| // |
| // OMP-LABEL: @foo( |
| // OMP-NEXT: entry: |
| // OMP-NEXT: [[I:%.*]] = alloca i32, align 4 |
| // OMP-NEXT: store i32 0, i32* [[I]], align 4 |
| // OMP-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB2]], i32 0, void (i32*, i32*, ...)* bitcast (void (i32*, i32*)* @.omp_outlined..1 to void (i32*, i32*, ...)*)) |
| // OMP-NEXT: ret void |
| // |
| // |
| // OMP-LABEL: @.omp_outlined..1( |
| // OMP-NEXT: entry: |
| // OMP-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8 |
| // OMP-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8 |
| // OMP-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4 |
| // OMP-NEXT: [[TMP:%.*]] = alloca i32, align 4 |
| // OMP-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4 |
| // OMP-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4 |
| // OMP-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4 |
| // OMP-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4 |
| // OMP-NEXT: [[I:%.*]] = alloca i32, align 4 |
| // OMP-NEXT: store i32* [[DOTGLOBAL_TID_:%.*]], i32** [[DOTGLOBAL_TID__ADDR]], align 8 |
| // OMP-NEXT: store i32* [[DOTBOUND_TID_:%.*]], i32** [[DOTBOUND_TID__ADDR]], align 8 |
| // OMP-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4 |
| // OMP-NEXT: store i32 33554431, i32* [[DOTOMP_UB]], align 4 |
| // OMP-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4 |
| // OMP-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4 |
| // OMP-NEXT: [[TMP0:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8 |
| // OMP-NEXT: [[TMP1:%.*]] = load i32, i32* [[TMP0]], align 4 |
| // OMP-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP1]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1) |
| // OMP-NEXT: [[TMP2:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4 |
| // OMP-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP2]], 33554431 |
| // OMP-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]] |
| // OMP: cond.true: |
| // OMP-NEXT: br label [[COND_END:%.*]] |
| // OMP: cond.false: |
| // OMP-NEXT: [[TMP3:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4 |
| // OMP-NEXT: br label [[COND_END]] |
| // OMP: cond.end: |
| // OMP-NEXT: [[COND:%.*]] = phi i32 [ 33554431, [[COND_TRUE]] ], [ [[TMP3]], [[COND_FALSE]] ] |
| // OMP-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4 |
| // OMP-NEXT: [[TMP4:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4 |
| // OMP-NEXT: store i32 [[TMP4]], i32* [[DOTOMP_IV]], align 4 |
| // OMP-NEXT: br label [[OMP_INNER_FOR_COND:%.*]] |
| // OMP: omp.inner.for.cond: |
| // OMP-NEXT: [[TMP5:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4 |
| // OMP-NEXT: [[TMP6:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4 |
| // OMP-NEXT: [[CMP1:%.*]] = icmp sle i32 [[TMP5]], [[TMP6]] |
| // OMP-NEXT: br i1 [[CMP1]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_END:%.*]] |
| // OMP: omp.inner.for.body: |
| // OMP-NEXT: [[TMP7:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4 |
| // OMP-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP7]], 1 |
| // OMP-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]] |
| // OMP-NEXT: store i32 [[ADD]], i32* [[I]], align 4 |
| // OMP-NEXT: [[TMP8:%.*]] = load i32, i32* [[I]], align 4 |
| // OMP-NEXT: [[IDXPROM:%.*]] = sext i32 [[TMP8]] to i64 |
| // OMP-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [33554432 x double], [33554432 x double]* @A, i64 0, i64 [[IDXPROM]] |
| // OMP-NEXT: store double 1.000000e+00, double* [[ARRAYIDX]], align 8 |
| // OMP-NEXT: br label [[OMP_BODY_CONTINUE:%.*]] |
| // OMP: omp.body.continue: |
| // OMP-NEXT: br label [[OMP_INNER_FOR_INC:%.*]] |
| // OMP: omp.inner.for.inc: |
| // OMP-NEXT: [[TMP9:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4 |
| // OMP-NEXT: [[ADD2:%.*]] = add nsw i32 [[TMP9]], 1 |
| // OMP-NEXT: store i32 [[ADD2]], i32* [[DOTOMP_IV]], align 4 |
| // OMP-NEXT: br label [[OMP_INNER_FOR_COND]] |
| // OMP: omp.inner.for.end: |
| // OMP-NEXT: br label [[OMP_LOOP_EXIT:%.*]] |
| // OMP: omp.loop.exit: |
| // OMP-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP1]]) |
| // OMP-NEXT: ret void |
| // |
| // |
| // NOOMP-LABEL: @main( |
| // NOOMP-NEXT: entry: |
| // NOOMP-NEXT: [[RETVAL:%.*]] = alloca i32, align 4 |
| // NOOMP-NEXT: [[I:%.*]] = alloca i32, align 4 |
| // NOOMP-NEXT: store i32 0, i32* [[RETVAL]], align 4 |
| // NOOMP-NEXT: store i32 0, i32* [[I]], align 4 |
| // NOOMP-NEXT: store i32 0, i32* [[I]], align 4 |
| // NOOMP-NEXT: br label [[FOR_COND:%.*]] |
| // NOOMP: for.cond: |
| // NOOMP-NEXT: [[TMP0:%.*]] = load i32, i32* [[I]], align 4 |
| // NOOMP-NEXT: [[CMP:%.*]] = icmp slt i32 [[TMP0]], 33554432 |
| // NOOMP-NEXT: br i1 [[CMP]], label [[FOR_BODY:%.*]], label [[FOR_END:%.*]] |
| // NOOMP: for.body: |
| // NOOMP-NEXT: [[TMP1:%.*]] = load i32, i32* [[I]], align 4 |
| // NOOMP-NEXT: [[IDXPROM:%.*]] = sext i32 [[TMP1]] to i64 |
| // NOOMP-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [33554432 x double], [33554432 x double]* @A, i64 0, i64 [[IDXPROM]] |
| // NOOMP-NEXT: store double 0.000000e+00, double* [[ARRAYIDX]], align 8 |
| // NOOMP-NEXT: br label [[FOR_INC:%.*]] |
| // NOOMP: for.inc: |
| // NOOMP-NEXT: [[TMP2:%.*]] = load i32, i32* [[I]], align 4 |
| // NOOMP-NEXT: [[INC:%.*]] = add nsw i32 [[TMP2]], 1 |
| // NOOMP-NEXT: store i32 [[INC]], i32* [[I]], align 4 |
| // NOOMP-NEXT: br label [[FOR_COND]], !llvm.loop [[LOOP2:![0-9]+]] |
| // NOOMP: for.end: |
| // NOOMP-NEXT: call void @foo() |
| // NOOMP-NEXT: ret i32 0 |
| // |
| // |
| // NOOMP-LABEL: @foo( |
| // NOOMP-NEXT: entry: |
| // NOOMP-NEXT: [[I:%.*]] = alloca i32, align 4 |
| // NOOMP-NEXT: store i32 0, i32* [[I]], align 4 |
| // NOOMP-NEXT: store i32 0, i32* [[I]], align 4 |
| // NOOMP-NEXT: br label [[FOR_COND:%.*]] |
| // NOOMP: for.cond: |
| // NOOMP-NEXT: [[TMP0:%.*]] = load i32, i32* [[I]], align 4 |
| // NOOMP-NEXT: [[CMP:%.*]] = icmp slt i32 [[TMP0]], 33554432 |
| // NOOMP-NEXT: br i1 [[CMP]], label [[FOR_BODY:%.*]], label [[FOR_END:%.*]] |
| // NOOMP: for.body: |
| // NOOMP-NEXT: [[TMP1:%.*]] = load i32, i32* [[I]], align 4 |
| // NOOMP-NEXT: [[IDXPROM:%.*]] = sext i32 [[TMP1]] to i64 |
| // NOOMP-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [33554432 x double], [33554432 x double]* @A, i64 0, i64 [[IDXPROM]] |
| // NOOMP-NEXT: store double 1.000000e+00, double* [[ARRAYIDX]], align 8 |
| // NOOMP-NEXT: br label [[FOR_INC:%.*]] |
| // NOOMP: for.inc: |
| // NOOMP-NEXT: [[TMP2:%.*]] = load i32, i32* [[I]], align 4 |
| // NOOMP-NEXT: [[INC:%.*]] = add nsw i32 [[TMP2]], 1 |
| // NOOMP-NEXT: store i32 [[INC]], i32* [[I]], align 4 |
| // NOOMP-NEXT: br label [[FOR_COND]], !llvm.loop [[LOOP4:![0-9]+]] |
| // NOOMP: for.end: |
| // NOOMP-NEXT: ret void |
| // |
