forked from OSchip/llvm-project
101 lines
4.1 KiB
Plaintext
101 lines
4.1 KiB
Plaintext
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
|
|
// 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);
|
|
|
|
// 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
|
|
//
|
|
// 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
|
|
//
|
|
int main(void) {
|
|
int i = 0;
|
|
|
|
#pragma omp parallel for
|
|
for (i = 0; i < size; ++i) {
|
|
A[i] = 0.0;
|
|
}
|
|
|
|
foo();
|
|
|
|
return 0;
|
|
}
|
|
|
|
// 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
|
|
//
|
|
// 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
|
|
//
|
|
void foo(void) {
|
|
int i = 0;
|
|
|
|
#pragma omp parallel for
|
|
for (i = 0; i < size; ++i) {
|
|
A[i] = 1.0;
|
|
}
|
|
}
|