maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/clang/test/OpenMP/irbuilder_for_unsigned.c

156 lines
9.6 KiB
C
Raw Blame History

// 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
//
Reference in New Issue View Git Blame Copy Permalink