forked from OSchip/llvm-project
9054 lines
695 KiB
C++
9054 lines
695 KiB
C++
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --function-signature --include-generated-funcs --replace-value-regex "__omp_offloading_[0-9a-z]+_[0-9a-z]+" "reduction_size[.].+[.]" "pl_cond[.].+[.|,]" --prefix-filecheck-ir-name _
|
|
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix=CHECK1
|
|
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple x86_64-apple-darwin10 -emit-pch -o %t %s
|
|
// RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-apple-darwin10 -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix=CHECK2
|
|
// RUN: %clang_cc1 -verify -fopenmp -x c++ -std=c++11 -DLAMBDA -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix=CHECK3
|
|
// RUN: %clang_cc1 -verify -fopenmp -x c++ -fblocks -DBLOCKS -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix=CHECK4
|
|
|
|
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
|
|
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple x86_64-apple-darwin10 -emit-pch -o %t %s
|
|
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple x86_64-apple-darwin10 -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
|
|
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -std=c++11 -DLAMBDA -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
|
|
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -fblocks -DBLOCKS -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
|
|
// expected-no-diagnostics
|
|
#ifndef HEADER
|
|
#define HEADER
|
|
|
|
volatile double g, g_orig;
|
|
volatile double &g1 = g_orig;
|
|
|
|
template <class T>
|
|
struct S {
|
|
T f;
|
|
S(T a) : f(a + g) {}
|
|
S() : f(g) {}
|
|
operator T() { return T(); }
|
|
S &operator&(const S &) { return *this; }
|
|
~S() {}
|
|
};
|
|
|
|
|
|
template <typename T, int length>
|
|
T tmain() {
|
|
T t;
|
|
S<T> test;
|
|
T t_var = T(), t_var1;
|
|
T vec[] = {1, 2};
|
|
S<T> s_arr[] = {1, 2};
|
|
S<T> &var = test;
|
|
S<T> var1;
|
|
S<T> arr[length];
|
|
#pragma omp parallel
|
|
#pragma omp for reduction(+:t_var) reduction(&:var) reduction(&& : var1) reduction(min: t_var1) nowait
|
|
for (int i = 0; i < 2; ++i) {
|
|
vec[i] = t_var;
|
|
s_arr[i] = var;
|
|
}
|
|
#pragma omp parallel
|
|
#pragma omp for reduction(&& : t_var)
|
|
for (int i = 0; i < 2; ++i) {
|
|
vec[i] = t_var;
|
|
s_arr[i] = var;
|
|
}
|
|
#pragma omp parallel
|
|
#pragma omp for reduction(+ : arr[1:length-2])
|
|
for (int i = 0; i < 2; ++i) {
|
|
vec[i] = t_var;
|
|
s_arr[i] = var;
|
|
}
|
|
return T();
|
|
}
|
|
|
|
extern S<float> **foo();
|
|
|
|
int main() {
|
|
#ifdef LAMBDA
|
|
[&]() {
|
|
#pragma omp parallel
|
|
#pragma omp for reduction(+:g, g1)
|
|
for (int i = 0; i < 2; ++i) {
|
|
|
|
// Reduction list for runtime.
|
|
|
|
g = 1;
|
|
g1 = 1;
|
|
|
|
[&]() {
|
|
g = 2;
|
|
g1 = 2;
|
|
}();
|
|
}
|
|
}();
|
|
return 0;
|
|
#elif defined(BLOCKS)
|
|
^{
|
|
#pragma omp parallel
|
|
#pragma omp for reduction(-:g, g1)
|
|
for (int i = 0; i < 2; ++i) {
|
|
|
|
// Reduction list for runtime.
|
|
|
|
g = 1;
|
|
g1 = 1;
|
|
|
|
^{
|
|
g = 2;
|
|
g1 = 2;
|
|
}();
|
|
}
|
|
}();
|
|
return 0;
|
|
#else
|
|
S<float> test;
|
|
float t_var = 0, t_var1;
|
|
int vec[] = {1, 2};
|
|
S<float> s_arr[] = {1, 2, 3, 4};
|
|
S<float> &var = test;
|
|
S<float> var1, arrs[10][4];
|
|
S<float> **var2 = foo();
|
|
S<float> vvar2[5];
|
|
S<float> (&var3)[4] = s_arr;
|
|
#pragma omp parallel
|
|
#pragma omp for reduction(+:t_var) reduction(&:var) reduction(&& : var1) reduction(min: t_var1)
|
|
for (int i = 0; i < 2; ++i) {
|
|
vec[i] = t_var;
|
|
s_arr[i] = var;
|
|
}
|
|
int arr[10][vec[1]];
|
|
#pragma omp parallel for reduction(+:arr[1][:vec[1]]) reduction(&:arrs[1:vec[1]][1:2])
|
|
for (int i = 0; i < 10; ++i)
|
|
++arr[1][i];
|
|
#pragma omp parallel
|
|
#pragma omp for reduction(+:arr) reduction(&:arrs)
|
|
for (int i = 0; i < 10; ++i)
|
|
++arr[1][i];
|
|
// arr is a VLA, but the array section has constant length so we can generate a constant sized array!
|
|
#pragma omp parallel
|
|
#pragma omp for reduction(+:arr[1][0:2])
|
|
for (int i = 0; i < 10; ++i)
|
|
++arr[1][i];
|
|
#pragma omp parallel
|
|
#pragma omp for reduction(& : var2[0 : 5][1 : 6])
|
|
for (int i = 0; i < 10; ++i)
|
|
;
|
|
#pragma omp parallel
|
|
#pragma omp for reduction(& : var2[1][1 : 6])
|
|
for (int i = 0; i < 10; ++i)
|
|
;
|
|
#pragma omp parallel
|
|
#pragma omp for reduction(& : var2[1 : 1][1 : 6])
|
|
for (int i = 0; i < 10; ++i)
|
|
;
|
|
#pragma omp parallel
|
|
#pragma omp for reduction(& : var2[1 : 1][1])
|
|
for (int i = 0; i < 10; ++i)
|
|
;
|
|
#pragma omp parallel
|
|
#pragma omp for reduction(& : vvar2[0 : 5])
|
|
for (int i = 0; i < 10; ++i)
|
|
;
|
|
#pragma omp parallel
|
|
#pragma omp for reduction(& : var3[1 : 2])
|
|
for (int i = 0; i < 10; ++i)
|
|
;
|
|
#pragma omp parallel
|
|
#pragma omp for reduction(& : var3[ : 2])
|
|
for (int i = 0; i < 10; ++i)
|
|
;
|
|
// TODO: The compiler should also be able to generate a constant sized array in this case!
|
|
#pragma omp parallel
|
|
#pragma omp for reduction(& : var3[2 : ])
|
|
for (int i = 0; i < 10; ++i)
|
|
;
|
|
#pragma omp parallel
|
|
#pragma omp for reduction(& : var3)
|
|
for (int i = 0; i < 10; ++i)
|
|
;
|
|
return tmain<int, 42>();
|
|
#endif
|
|
}
|
|
|
|
|
|
// Reduction list for runtime.
|
|
|
|
|
|
|
|
// For + reduction operation initial value of private variable is 0.
|
|
|
|
|
|
// For & reduction operation initial value of private variable is ones in all bits.
|
|
|
|
// For && reduction operation initial value of private variable is 1.0.
|
|
|
|
// For min reduction operation initial value of private variable is largest repesentable value.
|
|
|
|
|
|
// Skip checks for internal operations.
|
|
|
|
// void *RedList[<n>] = {<ReductionVars>[0], ..., <ReductionVars>[<n>-1]};
|
|
|
|
|
|
// res = __kmpc_reduce(<loc>, <gtid>, <n>, sizeof(RedList), RedList, reduce_func, &<lock>);
|
|
|
|
|
|
// switch(res)
|
|
|
|
// case 1:
|
|
// t_var += t_var_reduction;
|
|
|
|
// var = var.operator &(var_reduction);
|
|
|
|
// var1 = var1.operator &&(var1_reduction);
|
|
|
|
// t_var1 = min(t_var1, t_var1_reduction);
|
|
|
|
// __kmpc_end_reduce(<loc>, <gtid>, &<lock>);
|
|
|
|
// break;
|
|
|
|
// case 2:
|
|
// t_var += t_var_reduction;
|
|
|
|
// var = var.operator &(var_reduction);
|
|
|
|
// var1 = var1.operator &&(var1_reduction);
|
|
|
|
// t_var1 = min(t_var1, t_var1_reduction);
|
|
|
|
// __kmpc_end_reduce(<loc>, <gtid>, &<lock>);
|
|
|
|
// break;
|
|
|
|
|
|
// void reduce_func(void *lhs[<n>], void *rhs[<n>]) {
|
|
// *(Type0*)lhs[0] = ReductionOperation0(*(Type0*)lhs[0], *(Type0*)rhs[0]);
|
|
// ...
|
|
// *(Type<n>-1*)lhs[<n>-1] = ReductionOperation<n>-1(*(Type<n>-1*)lhs[<n>-1],
|
|
// *(Type<n>-1*)rhs[<n>-1]);
|
|
// }
|
|
// t_var_lhs = (float*)lhs[0];
|
|
// t_var_rhs = (float*)rhs[0];
|
|
|
|
// var_lhs = (S<float>*)lhs[1];
|
|
// var_rhs = (S<float>*)rhs[1];
|
|
|
|
// var1_lhs = (S<float>*)lhs[2];
|
|
// var1_rhs = (S<float>*)rhs[2];
|
|
|
|
// t_var1_lhs = (float*)lhs[3];
|
|
// t_var1_rhs = (float*)rhs[3];
|
|
|
|
// t_var_lhs += t_var_rhs;
|
|
|
|
// var_lhs = var_lhs.operator &(var_rhs);
|
|
|
|
// var1_lhs = var1_lhs.operator &&(var1_rhs);
|
|
|
|
// t_var1_lhs = min(t_var1_lhs, t_var1_rhs);
|
|
|
|
|
|
// Reduction list for runtime.
|
|
|
|
|
|
|
|
// Check initialization of private copy.
|
|
|
|
|
|
// Check initialization of private copy.
|
|
|
|
// Skip checks for internal operations.
|
|
|
|
// void *RedList[<n>] = {<ReductionVars>[0], ..., <ReductionVars>[<n>-1]};
|
|
|
|
|
|
// res = __kmpc_reduce(<loc>, <gtid>, <n>, sizeof(RedList), RedList, reduce_func, &<lock>);
|
|
|
|
|
|
// switch(res)
|
|
|
|
// case 1:
|
|
|
|
// arr[:] += arr_reduction[:];
|
|
|
|
// arrs[:] = var.operator &(arrs_reduction[:]);
|
|
|
|
// __kmpc_end_reduce(<loc>, <gtid>, &<lock>);
|
|
|
|
// break;
|
|
|
|
// case 2:
|
|
|
|
// arr[:] += arr_reduction[:];
|
|
|
|
// arrs[:] = var.operator &(arrs_reduction[:]);
|
|
|
|
// break;
|
|
|
|
// Check destruction of private copy.
|
|
|
|
|
|
// void reduce_func(void *lhs[<n>], void *rhs[<n>]) {
|
|
// *(Type0*)lhs[0] = ReductionOperation0(*(Type0*)lhs[0], *(Type0*)rhs[0]);
|
|
// ...
|
|
// *(Type<n>-1*)lhs[<n>-1] = ReductionOperation<n>-1(*(Type<n>-1*)lhs[<n>-1],
|
|
// *(Type<n>-1*)rhs[<n>-1]);
|
|
// }
|
|
// arr_rhs = (int*)rhs[0];
|
|
// arr_lhs = (int*)lhs[0];
|
|
|
|
// arr_size = (size_t)lhs[1];
|
|
|
|
// arrs_rhs = (S<float>*)rhs[2];
|
|
// arrs_lhs = (S<float>*)lhs[2];
|
|
|
|
// arrs_size = (size_t)lhs[3];
|
|
|
|
// arr_lhs[:] += arr_rhs[:];
|
|
|
|
// arrs_lhs = arrs_lhs.operator &(arrs_rhs);
|
|
|
|
|
|
|
|
|
|
// Reduction list for runtime.
|
|
|
|
|
|
|
|
// Check initialization of private copy.
|
|
|
|
// Check initialization of private copy.
|
|
|
|
// Skip checks for internal operations.
|
|
|
|
// void *RedList[<n>] = {<ReductionVars>[0], ..., <ReductionVars>[<n>-1]};
|
|
|
|
|
|
// res = __kmpc_reduce(<loc>, <gtid>, <n>, sizeof(RedList), RedList, reduce_func, &<lock>);
|
|
|
|
|
|
// switch(res)
|
|
|
|
// case 1:
|
|
|
|
// arr[:] += arr_reduction[:];
|
|
|
|
// arrs[:] = var.operator &(arrs_reduction[:]);
|
|
|
|
// __kmpc_end_reduce(<loc>, <gtid>, &<lock>);
|
|
|
|
// break;
|
|
|
|
// case 2:
|
|
|
|
// arr[:] += arr_reduction[:];
|
|
|
|
// arrs[:] = var.operator &(arrs_reduction[:]);
|
|
|
|
// break;
|
|
|
|
// Check destruction of private copy.
|
|
|
|
|
|
// void reduce_func(void *lhs[<n>], void *rhs[<n>]) {
|
|
// *(Type0*)lhs[0] = ReductionOperation0(*(Type0*)lhs[0], *(Type0*)rhs[0]);
|
|
// ...
|
|
// *(Type<n>-1*)lhs[<n>-1] = ReductionOperation<n>-1(*(Type<n>-1*)lhs[<n>-1],
|
|
// *(Type<n>-1*)rhs[<n>-1]);
|
|
// }
|
|
// arr_rhs = (int*)rhs[0];
|
|
// arr_lhs = (int*)lhs[0];
|
|
|
|
// arr_size = (size_t)lhs[1];
|
|
|
|
// arrs_rhs = (S<float>*)rhs[2];
|
|
// arrs_lhs = (S<float>*)lhs[2];
|
|
|
|
// arr_lhs[:] += arr_rhs[:];
|
|
|
|
// arrs_lhs = arrs_lhs.operator &(arrs_rhs);
|
|
|
|
|
|
|
|
|
|
// Reduction list for runtime.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
// Reduction list for runtime.
|
|
|
|
|
|
|
|
|
|
|
|
// Reduction list for runtime.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
// Reduction list for runtime.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
// Reduction list for runtime.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
// Reduction list for runtime.
|
|
|
|
|
|
|
|
|
|
|
|
// Reduction list for runtime.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
// Reduction list for runtime.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
// Reduction list for runtime.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
// Reduction list for runtime.
|
|
|
|
|
|
|
|
|
|
|
|
// Not interested in this one:
|
|
|
|
// Reduction list for runtime.
|
|
|
|
|
|
|
|
// For + reduction operation initial value of private variable is 0.
|
|
|
|
// For & reduction operation initial value of private variable is ones in all bits.
|
|
|
|
// For && reduction operation initial value of private variable is 1.0.
|
|
|
|
// For min reduction operation initial value of private variable is largest repesentable value.
|
|
|
|
// Skip checks for internal operations.
|
|
|
|
// void *RedList[<n>] = {<ReductionVars>[0], ..., <ReductionVars>[<n>-1]};
|
|
|
|
|
|
// res = __kmpc_reduce_nowait(<loc>, <gtid>, <n>, sizeof(RedList), RedList, reduce_func, &<lock>);
|
|
|
|
|
|
// switch(res)
|
|
|
|
// case 1:
|
|
// t_var += t_var_reduction;
|
|
|
|
// var = var.operator &(var_reduction);
|
|
|
|
// var1 = var1.operator &&(var1_reduction);
|
|
|
|
// t_var1 = min(t_var1, t_var1_reduction);
|
|
|
|
// __kmpc_end_reduce_nowait(<loc>, <gtid>, &<lock>);
|
|
|
|
// break;
|
|
|
|
// case 2:
|
|
// t_var += t_var_reduction;
|
|
|
|
// var = var.operator &(var_reduction);
|
|
|
|
// var1 = var1.operator &&(var1_reduction);
|
|
|
|
// t_var1 = min(t_var1, t_var1_reduction);
|
|
|
|
// break;
|
|
|
|
// void reduce_func(void *lhs[<n>], void *rhs[<n>]) {
|
|
// *(Type0*)lhs[0] = ReductionOperation0(*(Type0*)lhs[0], *(Type0*)rhs[0]);
|
|
// ...
|
|
// *(Type<n>-1*)lhs[<n>-1] = ReductionOperation<n>-1(*(Type<n>-1*)lhs[<n>-1],
|
|
// *(Type<n>-1*)rhs[<n>-1]);
|
|
// }
|
|
// t_var_lhs = (i{{[0-9]+}}*)lhs[0];
|
|
// t_var_rhs = (i{{[0-9]+}}*)rhs[0];
|
|
|
|
// var_lhs = (S<i{{[0-9]+}}>*)lhs[1];
|
|
// var_rhs = (S<i{{[0-9]+}}>*)rhs[1];
|
|
|
|
// var1_lhs = (S<i{{[0-9]+}}>*)lhs[2];
|
|
// var1_rhs = (S<i{{[0-9]+}}>*)rhs[2];
|
|
|
|
// t_var1_lhs = (i{{[0-9]+}}*)lhs[3];
|
|
// t_var1_rhs = (i{{[0-9]+}}*)rhs[3];
|
|
|
|
// t_var_lhs += t_var_rhs;
|
|
|
|
// var_lhs = var_lhs.operator &(var_rhs);
|
|
|
|
// var1_lhs = var1_lhs.operator &&(var1_rhs);
|
|
|
|
// t_var1_lhs = min(t_var1_lhs, t_var1_rhs);
|
|
|
|
|
|
|
|
// Reduction list for runtime.
|
|
|
|
|
|
|
|
|
|
#endif
|
|
// CHECK1-LABEL: define {{[^@]+}}@main
|
|
// CHECK1-SAME: () #[[ATTR0:[0-9]+]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[TEST:%.*]] = alloca [[STRUCT_S:%.*]], align 4
|
|
// CHECK1-NEXT: [[T_VAR:%.*]] = alloca float, align 4
|
|
// CHECK1-NEXT: [[T_VAR1:%.*]] = alloca float, align 4
|
|
// CHECK1-NEXT: [[VEC:%.*]] = alloca [2 x i32], align 4
|
|
// CHECK1-NEXT: [[S_ARR:%.*]] = alloca [4 x %struct.S], align 16
|
|
// CHECK1-NEXT: [[VAR:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK1-NEXT: [[VAR1:%.*]] = alloca [[STRUCT_S]], align 4
|
|
// CHECK1-NEXT: [[ARRS:%.*]] = alloca [10 x [4 x %struct.S]], align 16
|
|
// CHECK1-NEXT: [[VAR2:%.*]] = alloca %struct.S**, align 8
|
|
// CHECK1-NEXT: [[VVAR2:%.*]] = alloca [5 x %struct.S], align 16
|
|
// CHECK1-NEXT: [[VAR3:%.*]] = alloca [4 x %struct.S]*, align 8
|
|
// CHECK1-NEXT: [[OMP_OUTLINED_ARG_AGG_:%.*]] = alloca [[STRUCT_ANON:%.*]], align 8
|
|
// CHECK1-NEXT: [[SAVED_STACK:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: [[__VLA_EXPR0:%.*]] = alloca i64, align 8
|
|
// CHECK1-NEXT: [[OMP_OUTLINED_ARG_AGG_10:%.*]] = alloca [[STRUCT_ANON_0:%.*]], align 8
|
|
// CHECK1-NEXT: [[OMP_OUTLINED_ARG_AGG_11:%.*]] = alloca [[STRUCT_ANON_1:%.*]], align 8
|
|
// CHECK1-NEXT: [[OMP_OUTLINED_ARG_AGG_12:%.*]] = alloca [[STRUCT_ANON_2:%.*]], align 8
|
|
// CHECK1-NEXT: [[OMP_OUTLINED_ARG_AGG_13:%.*]] = alloca [[STRUCT_ANON_3:%.*]], align 8
|
|
// CHECK1-NEXT: [[OMP_OUTLINED_ARG_AGG_14:%.*]] = alloca [[STRUCT_ANON_4:%.*]], align 8
|
|
// CHECK1-NEXT: [[OMP_OUTLINED_ARG_AGG_15:%.*]] = alloca [[STRUCT_ANON_5:%.*]], align 8
|
|
// CHECK1-NEXT: [[OMP_OUTLINED_ARG_AGG_16:%.*]] = alloca [[STRUCT_ANON_6:%.*]], align 8
|
|
// CHECK1-NEXT: [[OMP_OUTLINED_ARG_AGG_17:%.*]] = alloca [[STRUCT_ANON_7:%.*]], align 8
|
|
// CHECK1-NEXT: [[OMP_OUTLINED_ARG_AGG_18:%.*]] = alloca [[STRUCT_ANON_8:%.*]], align 8
|
|
// CHECK1-NEXT: [[OMP_OUTLINED_ARG_AGG_19:%.*]] = alloca [[STRUCT_ANON_9:%.*]], align 8
|
|
// CHECK1-NEXT: [[OMP_OUTLINED_ARG_AGG_20:%.*]] = alloca [[STRUCT_ANON_10:%.*]], align 8
|
|
// CHECK1-NEXT: [[OMP_OUTLINED_ARG_AGG_21:%.*]] = alloca [[STRUCT_ANON_11:%.*]], align 8
|
|
// CHECK1-NEXT: store i32 0, i32* [[RETVAL]], align 4
|
|
// CHECK1-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[TEST]])
|
|
// CHECK1-NEXT: store float 0.000000e+00, float* [[T_VAR]], align 4
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = bitcast [2 x i32]* [[VEC]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP0]], i8* align 4 bitcast ([2 x i32]* @__const.main.vec to i8*), i64 8, i1 false)
|
|
// CHECK1-NEXT: [[ARRAYINIT_BEGIN:%.*]] = getelementptr inbounds [4 x %struct.S], [4 x %struct.S]* [[S_ARR]], i64 0, i64 0
|
|
// CHECK1-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYINIT_BEGIN]], float 1.000000e+00)
|
|
// CHECK1-NEXT: [[ARRAYINIT_ELEMENT:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYINIT_BEGIN]], i64 1
|
|
// CHECK1-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYINIT_ELEMENT]], float 2.000000e+00)
|
|
// CHECK1-NEXT: [[ARRAYINIT_ELEMENT1:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYINIT_ELEMENT]], i64 1
|
|
// CHECK1-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYINIT_ELEMENT1]], float 3.000000e+00)
|
|
// CHECK1-NEXT: [[ARRAYINIT_ELEMENT2:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYINIT_ELEMENT1]], i64 1
|
|
// CHECK1-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYINIT_ELEMENT2]], float 4.000000e+00)
|
|
// CHECK1-NEXT: store %struct.S* [[TEST]], %struct.S** [[VAR]], align 8
|
|
// CHECK1-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[VAR1]])
|
|
// CHECK1-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [10 x [4 x %struct.S]], [10 x [4 x %struct.S]]* [[ARRS]], i32 0, i32 0, i32 0
|
|
// CHECK1-NEXT: [[ARRAYCTOR_END:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN]], i64 40
|
|
// CHECK1-NEXT: br label [[ARRAYCTOR_LOOP:%.*]]
|
|
// CHECK1: arrayctor.loop:
|
|
// CHECK1-NEXT: [[ARRAYCTOR_CUR:%.*]] = phi %struct.S* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[ARRAYCTOR_NEXT:%.*]], [[ARRAYCTOR_LOOP]] ]
|
|
// CHECK1-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYCTOR_CUR]])
|
|
// CHECK1-NEXT: [[ARRAYCTOR_NEXT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYCTOR_CUR]], i64 1
|
|
// CHECK1-NEXT: [[ARRAYCTOR_DONE:%.*]] = icmp eq %struct.S* [[ARRAYCTOR_NEXT]], [[ARRAYCTOR_END]]
|
|
// CHECK1-NEXT: br i1 [[ARRAYCTOR_DONE]], label [[ARRAYCTOR_CONT:%.*]], label [[ARRAYCTOR_LOOP]]
|
|
// CHECK1: arrayctor.cont:
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call %struct.S** @_Z3foov()
|
|
// CHECK1-NEXT: store %struct.S** [[CALL]], %struct.S*** [[VAR2]], align 8
|
|
// CHECK1-NEXT: [[ARRAY_BEGIN3:%.*]] = getelementptr inbounds [5 x %struct.S], [5 x %struct.S]* [[VVAR2]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[ARRAYCTOR_END4:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN3]], i64 5
|
|
// CHECK1-NEXT: br label [[ARRAYCTOR_LOOP5:%.*]]
|
|
// CHECK1: arrayctor.loop5:
|
|
// CHECK1-NEXT: [[ARRAYCTOR_CUR6:%.*]] = phi %struct.S* [ [[ARRAY_BEGIN3]], [[ARRAYCTOR_CONT]] ], [ [[ARRAYCTOR_NEXT7:%.*]], [[ARRAYCTOR_LOOP5]] ]
|
|
// CHECK1-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYCTOR_CUR6]])
|
|
// CHECK1-NEXT: [[ARRAYCTOR_NEXT7]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYCTOR_CUR6]], i64 1
|
|
// CHECK1-NEXT: [[ARRAYCTOR_DONE8:%.*]] = icmp eq %struct.S* [[ARRAYCTOR_NEXT7]], [[ARRAYCTOR_END4]]
|
|
// CHECK1-NEXT: br i1 [[ARRAYCTOR_DONE8]], label [[ARRAYCTOR_CONT9:%.*]], label [[ARRAYCTOR_LOOP5]]
|
|
// CHECK1: arrayctor.cont9:
|
|
// CHECK1-NEXT: store [4 x %struct.S]* [[S_ARR]], [4 x %struct.S]** [[VAR3]], align 8
|
|
// CHECK1-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[OMP_OUTLINED_ARG_AGG_]], i32 0, i32 0
|
|
// CHECK1-NEXT: store float* [[T_VAR]], float** [[TMP1]], align 8
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[OMP_OUTLINED_ARG_AGG_]], i32 0, i32 1
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = load %struct.S*, %struct.S** [[VAR]], align 8
|
|
// CHECK1-NEXT: store %struct.S* [[TMP3]], %struct.S** [[TMP2]], align 8
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[OMP_OUTLINED_ARG_AGG_]], i32 0, i32 2
|
|
// CHECK1-NEXT: store %struct.S* [[VAR1]], %struct.S** [[TMP4]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[OMP_OUTLINED_ARG_AGG_]], i32 0, i32 3
|
|
// CHECK1-NEXT: store float* [[T_VAR1]], float** [[TMP5]], align 8
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[OMP_OUTLINED_ARG_AGG_]], i32 0, i32 4
|
|
// CHECK1-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[TMP6]], align 8
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[OMP_OUTLINED_ARG_AGG_]], i32 0, i32 5
|
|
// CHECK1-NEXT: store [4 x %struct.S]* [[S_ARR]], [4 x %struct.S]** [[TMP7]], align 8
|
|
// CHECK1-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3:[0-9]+]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon*)* @.omp_outlined. to void (i32*, i32*, ...)*), %struct.anon* [[OMP_OUTLINED_ARG_AGG_]])
|
|
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[VEC]], i64 0, i64 1
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = zext i32 [[TMP8]] to i64
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = call i8* @llvm.stacksave()
|
|
// CHECK1-NEXT: store i8* [[TMP10]], i8** [[SAVED_STACK]], align 8
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = mul nuw i64 10, [[TMP9]]
|
|
// CHECK1-NEXT: [[VLA:%.*]] = alloca i32, i64 [[TMP11]], align 16
|
|
// CHECK1-NEXT: store i64 [[TMP9]], i64* [[__VLA_EXPR0]], align 8
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = getelementptr inbounds [[STRUCT_ANON_0]], %struct.anon.0* [[OMP_OUTLINED_ARG_AGG_10]], i32 0, i32 0
|
|
// CHECK1-NEXT: store i64 10, i64* [[TMP12]], align 8
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = getelementptr inbounds [[STRUCT_ANON_0]], %struct.anon.0* [[OMP_OUTLINED_ARG_AGG_10]], i32 0, i32 1
|
|
// CHECK1-NEXT: store i64 [[TMP9]], i64* [[TMP13]], align 8
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = getelementptr inbounds [[STRUCT_ANON_0]], %struct.anon.0* [[OMP_OUTLINED_ARG_AGG_10]], i32 0, i32 2
|
|
// CHECK1-NEXT: store i32* [[VLA]], i32** [[TMP14]], align 8
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = getelementptr inbounds [[STRUCT_ANON_0]], %struct.anon.0* [[OMP_OUTLINED_ARG_AGG_10]], i32 0, i32 3
|
|
// CHECK1-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[TMP15]], align 8
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = getelementptr inbounds [[STRUCT_ANON_0]], %struct.anon.0* [[OMP_OUTLINED_ARG_AGG_10]], i32 0, i32 4
|
|
// CHECK1-NEXT: store [10 x [4 x %struct.S]]* [[ARRS]], [10 x [4 x %struct.S]]** [[TMP16]], align 8
|
|
// CHECK1-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.0*)* @.omp_outlined..1 to void (i32*, i32*, ...)*), %struct.anon.0* [[OMP_OUTLINED_ARG_AGG_10]])
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = getelementptr inbounds [[STRUCT_ANON_1]], %struct.anon.1* [[OMP_OUTLINED_ARG_AGG_11]], i32 0, i32 0
|
|
// CHECK1-NEXT: store i64 10, i64* [[TMP17]], align 8
|
|
// CHECK1-NEXT: [[TMP18:%.*]] = getelementptr inbounds [[STRUCT_ANON_1]], %struct.anon.1* [[OMP_OUTLINED_ARG_AGG_11]], i32 0, i32 1
|
|
// CHECK1-NEXT: store i64 [[TMP9]], i64* [[TMP18]], align 8
|
|
// CHECK1-NEXT: [[TMP19:%.*]] = getelementptr inbounds [[STRUCT_ANON_1]], %struct.anon.1* [[OMP_OUTLINED_ARG_AGG_11]], i32 0, i32 2
|
|
// CHECK1-NEXT: store i32* [[VLA]], i32** [[TMP19]], align 8
|
|
// CHECK1-NEXT: [[TMP20:%.*]] = getelementptr inbounds [[STRUCT_ANON_1]], %struct.anon.1* [[OMP_OUTLINED_ARG_AGG_11]], i32 0, i32 3
|
|
// CHECK1-NEXT: store [10 x [4 x %struct.S]]* [[ARRS]], [10 x [4 x %struct.S]]** [[TMP20]], align 8
|
|
// CHECK1-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.1*)* @.omp_outlined..3 to void (i32*, i32*, ...)*), %struct.anon.1* [[OMP_OUTLINED_ARG_AGG_11]])
|
|
// CHECK1-NEXT: [[TMP21:%.*]] = getelementptr inbounds [[STRUCT_ANON_2]], %struct.anon.2* [[OMP_OUTLINED_ARG_AGG_12]], i32 0, i32 0
|
|
// CHECK1-NEXT: store i64 10, i64* [[TMP21]], align 8
|
|
// CHECK1-NEXT: [[TMP22:%.*]] = getelementptr inbounds [[STRUCT_ANON_2]], %struct.anon.2* [[OMP_OUTLINED_ARG_AGG_12]], i32 0, i32 1
|
|
// CHECK1-NEXT: store i64 [[TMP9]], i64* [[TMP22]], align 8
|
|
// CHECK1-NEXT: [[TMP23:%.*]] = getelementptr inbounds [[STRUCT_ANON_2]], %struct.anon.2* [[OMP_OUTLINED_ARG_AGG_12]], i32 0, i32 2
|
|
// CHECK1-NEXT: store i32* [[VLA]], i32** [[TMP23]], align 8
|
|
// CHECK1-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.2*)* @.omp_outlined..5 to void (i32*, i32*, ...)*), %struct.anon.2* [[OMP_OUTLINED_ARG_AGG_12]])
|
|
// CHECK1-NEXT: [[TMP24:%.*]] = getelementptr inbounds [[STRUCT_ANON_3]], %struct.anon.3* [[OMP_OUTLINED_ARG_AGG_13]], i32 0, i32 0
|
|
// CHECK1-NEXT: store %struct.S*** [[VAR2]], %struct.S**** [[TMP24]], align 8
|
|
// CHECK1-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.3*)* @.omp_outlined..7 to void (i32*, i32*, ...)*), %struct.anon.3* [[OMP_OUTLINED_ARG_AGG_13]])
|
|
// CHECK1-NEXT: [[TMP25:%.*]] = getelementptr inbounds [[STRUCT_ANON_4]], %struct.anon.4* [[OMP_OUTLINED_ARG_AGG_14]], i32 0, i32 0
|
|
// CHECK1-NEXT: store %struct.S*** [[VAR2]], %struct.S**** [[TMP25]], align 8
|
|
// CHECK1-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.4*)* @.omp_outlined..9 to void (i32*, i32*, ...)*), %struct.anon.4* [[OMP_OUTLINED_ARG_AGG_14]])
|
|
// CHECK1-NEXT: [[TMP26:%.*]] = getelementptr inbounds [[STRUCT_ANON_5]], %struct.anon.5* [[OMP_OUTLINED_ARG_AGG_15]], i32 0, i32 0
|
|
// CHECK1-NEXT: store %struct.S*** [[VAR2]], %struct.S**** [[TMP26]], align 8
|
|
// CHECK1-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.5*)* @.omp_outlined..11 to void (i32*, i32*, ...)*), %struct.anon.5* [[OMP_OUTLINED_ARG_AGG_15]])
|
|
// CHECK1-NEXT: [[TMP27:%.*]] = getelementptr inbounds [[STRUCT_ANON_6]], %struct.anon.6* [[OMP_OUTLINED_ARG_AGG_16]], i32 0, i32 0
|
|
// CHECK1-NEXT: store %struct.S*** [[VAR2]], %struct.S**** [[TMP27]], align 8
|
|
// CHECK1-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.6*)* @.omp_outlined..13 to void (i32*, i32*, ...)*), %struct.anon.6* [[OMP_OUTLINED_ARG_AGG_16]])
|
|
// CHECK1-NEXT: [[TMP28:%.*]] = getelementptr inbounds [[STRUCT_ANON_7]], %struct.anon.7* [[OMP_OUTLINED_ARG_AGG_17]], i32 0, i32 0
|
|
// CHECK1-NEXT: store [5 x %struct.S]* [[VVAR2]], [5 x %struct.S]** [[TMP28]], align 8
|
|
// CHECK1-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.7*)* @.omp_outlined..15 to void (i32*, i32*, ...)*), %struct.anon.7* [[OMP_OUTLINED_ARG_AGG_17]])
|
|
// CHECK1-NEXT: [[TMP29:%.*]] = getelementptr inbounds [[STRUCT_ANON_8]], %struct.anon.8* [[OMP_OUTLINED_ARG_AGG_18]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP30:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[VAR3]], align 8
|
|
// CHECK1-NEXT: store [4 x %struct.S]* [[TMP30]], [4 x %struct.S]** [[TMP29]], align 8
|
|
// CHECK1-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.8*)* @.omp_outlined..17 to void (i32*, i32*, ...)*), %struct.anon.8* [[OMP_OUTLINED_ARG_AGG_18]])
|
|
// CHECK1-NEXT: [[TMP31:%.*]] = getelementptr inbounds [[STRUCT_ANON_9]], %struct.anon.9* [[OMP_OUTLINED_ARG_AGG_19]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP32:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[VAR3]], align 8
|
|
// CHECK1-NEXT: store [4 x %struct.S]* [[TMP32]], [4 x %struct.S]** [[TMP31]], align 8
|
|
// CHECK1-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.9*)* @.omp_outlined..19 to void (i32*, i32*, ...)*), %struct.anon.9* [[OMP_OUTLINED_ARG_AGG_19]])
|
|
// CHECK1-NEXT: [[TMP33:%.*]] = getelementptr inbounds [[STRUCT_ANON_10]], %struct.anon.10* [[OMP_OUTLINED_ARG_AGG_20]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP34:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[VAR3]], align 8
|
|
// CHECK1-NEXT: store [4 x %struct.S]* [[TMP34]], [4 x %struct.S]** [[TMP33]], align 8
|
|
// CHECK1-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.10*)* @.omp_outlined..21 to void (i32*, i32*, ...)*), %struct.anon.10* [[OMP_OUTLINED_ARG_AGG_20]])
|
|
// CHECK1-NEXT: [[TMP35:%.*]] = getelementptr inbounds [[STRUCT_ANON_11]], %struct.anon.11* [[OMP_OUTLINED_ARG_AGG_21]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP36:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[VAR3]], align 8
|
|
// CHECK1-NEXT: store [4 x %struct.S]* [[TMP36]], [4 x %struct.S]** [[TMP35]], align 8
|
|
// CHECK1-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.11*)* @.omp_outlined..23 to void (i32*, i32*, ...)*), %struct.anon.11* [[OMP_OUTLINED_ARG_AGG_21]])
|
|
// CHECK1-NEXT: [[CALL22:%.*]] = call i32 @_Z5tmainIiLi42EET_v()
|
|
// CHECK1-NEXT: store i32 [[CALL22]], i32* [[RETVAL]], align 4
|
|
// CHECK1-NEXT: [[TMP37:%.*]] = load i8*, i8** [[SAVED_STACK]], align 8
|
|
// CHECK1-NEXT: call void @llvm.stackrestore(i8* [[TMP37]])
|
|
// CHECK1-NEXT: [[ARRAY_BEGIN23:%.*]] = getelementptr inbounds [5 x %struct.S], [5 x %struct.S]* [[VVAR2]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP38:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN23]], i64 5
|
|
// CHECK1-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
|
|
// CHECK1: arraydestroy.body:
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP38]], [[ARRAYCTOR_CONT9]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
|
|
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5:[0-9]+]]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN23]]
|
|
// CHECK1-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE24:%.*]], label [[ARRAYDESTROY_BODY]]
|
|
// CHECK1: arraydestroy.done24:
|
|
// CHECK1-NEXT: [[ARRAY_BEGIN25:%.*]] = getelementptr inbounds [10 x [4 x %struct.S]], [10 x [4 x %struct.S]]* [[ARRS]], i32 0, i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP39:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN25]], i64 40
|
|
// CHECK1-NEXT: br label [[ARRAYDESTROY_BODY26:%.*]]
|
|
// CHECK1: arraydestroy.body26:
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENTPAST27:%.*]] = phi %struct.S* [ [[TMP39]], [[ARRAYDESTROY_DONE24]] ], [ [[ARRAYDESTROY_ELEMENT28:%.*]], [[ARRAYDESTROY_BODY26]] ]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENT28]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST27]], i64 -1
|
|
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT28]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_DONE29:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT28]], [[ARRAY_BEGIN25]]
|
|
// CHECK1-NEXT: br i1 [[ARRAYDESTROY_DONE29]], label [[ARRAYDESTROY_DONE30:%.*]], label [[ARRAYDESTROY_BODY26]]
|
|
// CHECK1: arraydestroy.done30:
|
|
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[VAR1]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: [[ARRAY_BEGIN31:%.*]] = getelementptr inbounds [4 x %struct.S], [4 x %struct.S]* [[S_ARR]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP40:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN31]], i64 4
|
|
// CHECK1-NEXT: br label [[ARRAYDESTROY_BODY32:%.*]]
|
|
// CHECK1: arraydestroy.body32:
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENTPAST33:%.*]] = phi %struct.S* [ [[TMP40]], [[ARRAYDESTROY_DONE30]] ], [ [[ARRAYDESTROY_ELEMENT34:%.*]], [[ARRAYDESTROY_BODY32]] ]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENT34]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST33]], i64 -1
|
|
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT34]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_DONE35:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT34]], [[ARRAY_BEGIN31]]
|
|
// CHECK1-NEXT: br i1 [[ARRAYDESTROY_DONE35]], label [[ARRAYDESTROY_DONE36:%.*]], label [[ARRAYDESTROY_BODY32]]
|
|
// CHECK1: arraydestroy.done36:
|
|
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[TEST]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: [[TMP41:%.*]] = load i32, i32* [[RETVAL]], align 4
|
|
// CHECK1-NEXT: ret i32 [[TMP41]]
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfEC1Ev
|
|
// CHECK1-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1:[0-9]+]] align 2 {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK1-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: call void @_ZN1SIfEC2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]])
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfEC1Ef
|
|
// CHECK1-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], float [[A:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK1-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
|
|
// CHECK1-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: store float [[A]], float* [[A_ADDR]], align 4
|
|
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load float, float* [[A_ADDR]], align 4
|
|
// CHECK1-NEXT: call void @_ZN1SIfEC2Ef(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]], float [[TMP0]])
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined.
|
|
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon* noalias [[__CONTEXT:%.*]]) #[[ATTR4:[0-9]+]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon*, align 8
|
|
// CHECK1-NEXT: [[TMP:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK1-NEXT: [[_TMP1:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK1-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[_TMP2:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[T_VAR:%.*]] = alloca float, align 4
|
|
// CHECK1-NEXT: [[VAR:%.*]] = alloca [[STRUCT_S:%.*]], align 4
|
|
// CHECK1-NEXT: [[_TMP3:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK1-NEXT: [[VAR1:%.*]] = alloca [[STRUCT_S]], align 4
|
|
// CHECK1-NEXT: [[T_VAR1:%.*]] = alloca float, align 4
|
|
// CHECK1-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [4 x i8*], align 8
|
|
// CHECK1-NEXT: [[REF_TMP:%.*]] = alloca [[STRUCT_S]], align 4
|
|
// CHECK1-NEXT: [[ATOMIC_TEMP:%.*]] = alloca float, align 4
|
|
// CHECK1-NEXT: [[_TMP18:%.*]] = alloca float, align 4
|
|
// CHECK1-NEXT: [[REF_TMP21:%.*]] = alloca [[STRUCT_S]], align 4
|
|
// CHECK1-NEXT: [[ATOMIC_TEMP31:%.*]] = alloca float, align 4
|
|
// CHECK1-NEXT: [[_TMP32:%.*]] = alloca float, align 4
|
|
// CHECK1-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store %struct.anon* [[__CONTEXT]], %struct.anon** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load %struct.anon*, %struct.anon** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON:%.*]], %struct.anon* [[TMP0]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load float*, float** [[TMP1]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[TMP0]], i32 0, i32 1
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load %struct.S*, %struct.S** [[TMP3]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[TMP0]], i32 0, i32 2
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = load %struct.S*, %struct.S** [[TMP5]], align 8
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[TMP0]], i32 0, i32 3
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = load float*, float** [[TMP7]], align 8
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[TMP0]], i32 0, i32 4
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = load [2 x i32]*, [2 x i32]** [[TMP9]], align 8
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[TMP0]], i32 0, i32 5
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[TMP11]], align 8
|
|
// CHECK1-NEXT: store %struct.S* [[TMP4]], %struct.S** [[TMP]], align 8
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = load %struct.S*, %struct.S** [[TMP]], align 8
|
|
// CHECK1-NEXT: store %struct.S* [[TMP13]], %struct.S** [[_TMP1]], align 8
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK1-NEXT: store float 0.000000e+00, float* [[T_VAR]], align 4
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = load %struct.S*, %struct.S** [[_TMP1]], align 8
|
|
// CHECK1-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[VAR]])
|
|
// CHECK1-NEXT: store %struct.S* [[VAR]], %struct.S** [[_TMP3]], align 8
|
|
// CHECK1-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[VAR1]])
|
|
// CHECK1-NEXT: store float 0x47EFFFFFE0000000, float* [[T_VAR1]], align 4
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = load i32, i32* [[TMP15]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 [[TMP16]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP17]], 1
|
|
// CHECK1-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK1: cond.true:
|
|
// CHECK1-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK1: cond.false:
|
|
// CHECK1-NEXT: [[TMP18:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END]]
|
|
// CHECK1: cond.end:
|
|
// CHECK1-NEXT: [[COND:%.*]] = phi i32 [ 1, [[COND_TRUE]] ], [ [[TMP18]], [[COND_FALSE]] ]
|
|
// CHECK1-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[TMP19:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 [[TMP19]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK1: omp.inner.for.cond:
|
|
// CHECK1-NEXT: [[TMP20:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[TMP21:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP4:%.*]] = icmp sle i32 [[TMP20]], [[TMP21]]
|
|
// CHECK1-NEXT: br i1 [[CMP4]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK1: omp.inner.for.cond.cleanup:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK1: omp.inner.for.body:
|
|
// CHECK1-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP22]], 1
|
|
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK1-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK1-NEXT: [[TMP23:%.*]] = load float, float* [[T_VAR]], align 4
|
|
// CHECK1-NEXT: [[CONV:%.*]] = fptosi float [[TMP23]] to i32
|
|
// CHECK1-NEXT: [[TMP24:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK1-NEXT: [[IDXPROM:%.*]] = sext i32 [[TMP24]] to i64
|
|
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[TMP10]], i64 0, i64 [[IDXPROM]]
|
|
// CHECK1-NEXT: store i32 [[CONV]], i32* [[ARRAYIDX]], align 4
|
|
// CHECK1-NEXT: [[TMP25:%.*]] = load %struct.S*, %struct.S** [[_TMP3]], align 8
|
|
// CHECK1-NEXT: [[TMP26:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK1-NEXT: [[IDXPROM5:%.*]] = sext i32 [[TMP26]] to i64
|
|
// CHECK1-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds [4 x %struct.S], [4 x %struct.S]* [[TMP12]], i64 0, i64 [[IDXPROM5]]
|
|
// CHECK1-NEXT: [[TMP27:%.*]] = bitcast %struct.S* [[ARRAYIDX6]] to i8*
|
|
// CHECK1-NEXT: [[TMP28:%.*]] = bitcast %struct.S* [[TMP25]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP27]], i8* align 4 [[TMP28]], i64 4, i1 false)
|
|
// CHECK1-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK1: omp.body.continue:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK1: omp.inner.for.inc:
|
|
// CHECK1-NEXT: [[TMP29:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[ADD7:%.*]] = add nsw i32 [[TMP29]], 1
|
|
// CHECK1-NEXT: store i32 [[ADD7]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK1: omp.inner.for.end:
|
|
// CHECK1-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK1: omp.loop.exit:
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP16]])
|
|
// CHECK1-NEXT: [[TMP30:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP31:%.*]] = bitcast float* [[T_VAR]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP31]], i8** [[TMP30]], align 8
|
|
// CHECK1-NEXT: [[TMP32:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 1
|
|
// CHECK1-NEXT: [[TMP33:%.*]] = bitcast %struct.S* [[VAR]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP33]], i8** [[TMP32]], align 8
|
|
// CHECK1-NEXT: [[TMP34:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 2
|
|
// CHECK1-NEXT: [[TMP35:%.*]] = bitcast %struct.S* [[VAR1]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP35]], i8** [[TMP34]], align 8
|
|
// CHECK1-NEXT: [[TMP36:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 3
|
|
// CHECK1-NEXT: [[TMP37:%.*]] = bitcast float* [[T_VAR1]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP37]], i8** [[TMP36]], align 8
|
|
// CHECK1-NEXT: [[TMP38:%.*]] = bitcast [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK1-NEXT: [[TMP39:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2:[0-9]+]], i32 [[TMP16]], i32 4, i64 32, i8* [[TMP38]], void (i8*, i8*)* @.omp.reduction.reduction_func, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: switch i32 [[TMP39]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK1-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK1-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK1-NEXT: ]
|
|
// CHECK1: .omp.reduction.case1:
|
|
// CHECK1-NEXT: [[TMP40:%.*]] = load float, float* [[TMP2]], align 4
|
|
// CHECK1-NEXT: [[TMP41:%.*]] = load float, float* [[T_VAR]], align 4
|
|
// CHECK1-NEXT: [[ADD8:%.*]] = fadd float [[TMP40]], [[TMP41]]
|
|
// CHECK1-NEXT: store float [[ADD8]], float* [[TMP2]], align 4
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[TMP14]], %struct.S* nonnull align 4 dereferenceable(4) [[VAR]])
|
|
// CHECK1-NEXT: [[TMP42:%.*]] = bitcast %struct.S* [[TMP14]] to i8*
|
|
// CHECK1-NEXT: [[TMP43:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP42]], i8* align 4 [[TMP43]], i64 4, i1 false)
|
|
// CHECK1-NEXT: [[CALL9:%.*]] = call float @_ZN1SIfEcvfEv(%struct.S* nonnull align 4 dereferenceable(4) [[TMP6]])
|
|
// CHECK1-NEXT: [[TOBOOL:%.*]] = fcmp une float [[CALL9]], 0.000000e+00
|
|
// CHECK1-NEXT: br i1 [[TOBOOL]], label [[LAND_RHS:%.*]], label [[LAND_END:%.*]]
|
|
// CHECK1: land.rhs:
|
|
// CHECK1-NEXT: [[CALL10:%.*]] = call float @_ZN1SIfEcvfEv(%struct.S* nonnull align 4 dereferenceable(4) [[VAR1]])
|
|
// CHECK1-NEXT: [[TOBOOL11:%.*]] = fcmp une float [[CALL10]], 0.000000e+00
|
|
// CHECK1-NEXT: br label [[LAND_END]]
|
|
// CHECK1: land.end:
|
|
// CHECK1-NEXT: [[TMP44:%.*]] = phi i1 [ false, [[DOTOMP_REDUCTION_CASE1]] ], [ [[TOBOOL11]], [[LAND_RHS]] ]
|
|
// CHECK1-NEXT: [[CONV12:%.*]] = uitofp i1 [[TMP44]] to float
|
|
// CHECK1-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) [[REF_TMP]], float [[CONV12]])
|
|
// CHECK1-NEXT: [[TMP45:%.*]] = bitcast %struct.S* [[TMP6]] to i8*
|
|
// CHECK1-NEXT: [[TMP46:%.*]] = bitcast %struct.S* [[REF_TMP]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP45]], i8* align 4 [[TMP46]], i64 4, i1 false)
|
|
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[REF_TMP]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: [[TMP47:%.*]] = load float, float* [[TMP8]], align 4
|
|
// CHECK1-NEXT: [[TMP48:%.*]] = load float, float* [[T_VAR1]], align 4
|
|
// CHECK1-NEXT: [[CMP13:%.*]] = fcmp olt float [[TMP47]], [[TMP48]]
|
|
// CHECK1-NEXT: br i1 [[CMP13]], label [[COND_TRUE14:%.*]], label [[COND_FALSE15:%.*]]
|
|
// CHECK1: cond.true14:
|
|
// CHECK1-NEXT: [[TMP49:%.*]] = load float, float* [[TMP8]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END16:%.*]]
|
|
// CHECK1: cond.false15:
|
|
// CHECK1-NEXT: [[TMP50:%.*]] = load float, float* [[T_VAR1]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END16]]
|
|
// CHECK1: cond.end16:
|
|
// CHECK1-NEXT: [[COND17:%.*]] = phi float [ [[TMP49]], [[COND_TRUE14]] ], [ [[TMP50]], [[COND_FALSE15]] ]
|
|
// CHECK1-NEXT: store float [[COND17]], float* [[TMP8]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP16]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.case2:
|
|
// CHECK1-NEXT: [[TMP51:%.*]] = load float, float* [[T_VAR]], align 4
|
|
// CHECK1-NEXT: [[TMP52:%.*]] = bitcast float* [[TMP2]] to i32*
|
|
// CHECK1-NEXT: [[ATOMIC_LOAD:%.*]] = load atomic i32, i32* [[TMP52]] monotonic, align 4
|
|
// CHECK1-NEXT: br label [[ATOMIC_CONT:%.*]]
|
|
// CHECK1: atomic_cont:
|
|
// CHECK1-NEXT: [[TMP53:%.*]] = phi i32 [ [[ATOMIC_LOAD]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[TMP61:%.*]], [[ATOMIC_CONT]] ]
|
|
// CHECK1-NEXT: [[TMP54:%.*]] = bitcast float* [[ATOMIC_TEMP]] to i32*
|
|
// CHECK1-NEXT: [[TMP55:%.*]] = bitcast i32 [[TMP53]] to float
|
|
// CHECK1-NEXT: store float [[TMP55]], float* [[_TMP18]], align 4
|
|
// CHECK1-NEXT: [[TMP56:%.*]] = load float, float* [[_TMP18]], align 4
|
|
// CHECK1-NEXT: [[TMP57:%.*]] = load float, float* [[T_VAR]], align 4
|
|
// CHECK1-NEXT: [[ADD19:%.*]] = fadd float [[TMP56]], [[TMP57]]
|
|
// CHECK1-NEXT: store float [[ADD19]], float* [[ATOMIC_TEMP]], align 4
|
|
// CHECK1-NEXT: [[TMP58:%.*]] = load i32, i32* [[TMP54]], align 4
|
|
// CHECK1-NEXT: [[TMP59:%.*]] = bitcast float* [[TMP2]] to i32*
|
|
// CHECK1-NEXT: [[TMP60:%.*]] = cmpxchg i32* [[TMP59]], i32 [[TMP53]], i32 [[TMP58]] monotonic monotonic, align 4
|
|
// CHECK1-NEXT: [[TMP61]] = extractvalue { i32, i1 } [[TMP60]], 0
|
|
// CHECK1-NEXT: [[TMP62:%.*]] = extractvalue { i32, i1 } [[TMP60]], 1
|
|
// CHECK1-NEXT: br i1 [[TMP62]], label [[ATOMIC_EXIT:%.*]], label [[ATOMIC_CONT]]
|
|
// CHECK1: atomic_exit:
|
|
// CHECK1-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP16]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[CALL20:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[TMP14]], %struct.S* nonnull align 4 dereferenceable(4) [[VAR]])
|
|
// CHECK1-NEXT: [[TMP63:%.*]] = bitcast %struct.S* [[TMP14]] to i8*
|
|
// CHECK1-NEXT: [[TMP64:%.*]] = bitcast %struct.S* [[CALL20]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP63]], i8* align 4 [[TMP64]], i64 4, i1 false)
|
|
// CHECK1-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP16]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP16]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[CALL22:%.*]] = call float @_ZN1SIfEcvfEv(%struct.S* nonnull align 4 dereferenceable(4) [[TMP6]])
|
|
// CHECK1-NEXT: [[TOBOOL23:%.*]] = fcmp une float [[CALL22]], 0.000000e+00
|
|
// CHECK1-NEXT: br i1 [[TOBOOL23]], label [[LAND_RHS24:%.*]], label [[LAND_END27:%.*]]
|
|
// CHECK1: land.rhs24:
|
|
// CHECK1-NEXT: [[CALL25:%.*]] = call float @_ZN1SIfEcvfEv(%struct.S* nonnull align 4 dereferenceable(4) [[VAR1]])
|
|
// CHECK1-NEXT: [[TOBOOL26:%.*]] = fcmp une float [[CALL25]], 0.000000e+00
|
|
// CHECK1-NEXT: br label [[LAND_END27]]
|
|
// CHECK1: land.end27:
|
|
// CHECK1-NEXT: [[TMP65:%.*]] = phi i1 [ false, [[ATOMIC_EXIT]] ], [ [[TOBOOL26]], [[LAND_RHS24]] ]
|
|
// CHECK1-NEXT: [[CONV28:%.*]] = uitofp i1 [[TMP65]] to float
|
|
// CHECK1-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) [[REF_TMP21]], float [[CONV28]])
|
|
// CHECK1-NEXT: [[TMP66:%.*]] = bitcast %struct.S* [[TMP6]] to i8*
|
|
// CHECK1-NEXT: [[TMP67:%.*]] = bitcast %struct.S* [[REF_TMP21]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP66]], i8* align 4 [[TMP67]], i64 4, i1 false)
|
|
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[REF_TMP21]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP16]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[TMP68:%.*]] = load float, float* [[T_VAR1]], align 4
|
|
// CHECK1-NEXT: [[TMP69:%.*]] = bitcast float* [[TMP8]] to i32*
|
|
// CHECK1-NEXT: [[ATOMIC_LOAD29:%.*]] = load atomic i32, i32* [[TMP69]] monotonic, align 4
|
|
// CHECK1-NEXT: br label [[ATOMIC_CONT30:%.*]]
|
|
// CHECK1: atomic_cont30:
|
|
// CHECK1-NEXT: [[TMP70:%.*]] = phi i32 [ [[ATOMIC_LOAD29]], [[LAND_END27]] ], [ [[TMP80:%.*]], [[COND_END36:%.*]] ]
|
|
// CHECK1-NEXT: [[TMP71:%.*]] = bitcast float* [[ATOMIC_TEMP31]] to i32*
|
|
// CHECK1-NEXT: [[TMP72:%.*]] = bitcast i32 [[TMP70]] to float
|
|
// CHECK1-NEXT: store float [[TMP72]], float* [[_TMP32]], align 4
|
|
// CHECK1-NEXT: [[TMP73:%.*]] = load float, float* [[_TMP32]], align 4
|
|
// CHECK1-NEXT: [[TMP74:%.*]] = load float, float* [[T_VAR1]], align 4
|
|
// CHECK1-NEXT: [[CMP33:%.*]] = fcmp olt float [[TMP73]], [[TMP74]]
|
|
// CHECK1-NEXT: br i1 [[CMP33]], label [[COND_TRUE34:%.*]], label [[COND_FALSE35:%.*]]
|
|
// CHECK1: cond.true34:
|
|
// CHECK1-NEXT: [[TMP75:%.*]] = load float, float* [[_TMP32]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END36]]
|
|
// CHECK1: cond.false35:
|
|
// CHECK1-NEXT: [[TMP76:%.*]] = load float, float* [[T_VAR1]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END36]]
|
|
// CHECK1: cond.end36:
|
|
// CHECK1-NEXT: [[COND37:%.*]] = phi float [ [[TMP75]], [[COND_TRUE34]] ], [ [[TMP76]], [[COND_FALSE35]] ]
|
|
// CHECK1-NEXT: store float [[COND37]], float* [[ATOMIC_TEMP31]], align 4
|
|
// CHECK1-NEXT: [[TMP77:%.*]] = load i32, i32* [[TMP71]], align 4
|
|
// CHECK1-NEXT: [[TMP78:%.*]] = bitcast float* [[TMP8]] to i32*
|
|
// CHECK1-NEXT: [[TMP79:%.*]] = cmpxchg i32* [[TMP78]], i32 [[TMP70]], i32 [[TMP77]] monotonic monotonic, align 4
|
|
// CHECK1-NEXT: [[TMP80]] = extractvalue { i32, i1 } [[TMP79]], 0
|
|
// CHECK1-NEXT: [[TMP81:%.*]] = extractvalue { i32, i1 } [[TMP79]], 1
|
|
// CHECK1-NEXT: br i1 [[TMP81]], label [[ATOMIC_EXIT38:%.*]], label [[ATOMIC_CONT30]]
|
|
// CHECK1: atomic_exit38:
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP16]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.default:
|
|
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[VAR1]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[VAR]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4:[0-9]+]], i32 [[TMP16]])
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func
|
|
// CHECK1-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6:[0-9]+]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: [[REF_TMP:%.*]] = alloca [[STRUCT_S:%.*]], align 4
|
|
// CHECK1-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [4 x i8*]*
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [4 x i8*]*
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to float*
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to float*
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 1
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = load i8*, i8** [[TMP12]], align 8
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = bitcast i8* [[TMP13]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 1
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = load i8*, i8** [[TMP15]], align 8
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = bitcast i8* [[TMP16]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP18:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 2
|
|
// CHECK1-NEXT: [[TMP19:%.*]] = load i8*, i8** [[TMP18]], align 8
|
|
// CHECK1-NEXT: [[TMP20:%.*]] = bitcast i8* [[TMP19]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP21:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 2
|
|
// CHECK1-NEXT: [[TMP22:%.*]] = load i8*, i8** [[TMP21]], align 8
|
|
// CHECK1-NEXT: [[TMP23:%.*]] = bitcast i8* [[TMP22]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP24:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 3
|
|
// CHECK1-NEXT: [[TMP25:%.*]] = load i8*, i8** [[TMP24]], align 8
|
|
// CHECK1-NEXT: [[TMP26:%.*]] = bitcast i8* [[TMP25]] to float*
|
|
// CHECK1-NEXT: [[TMP27:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 3
|
|
// CHECK1-NEXT: [[TMP28:%.*]] = load i8*, i8** [[TMP27]], align 8
|
|
// CHECK1-NEXT: [[TMP29:%.*]] = bitcast i8* [[TMP28]] to float*
|
|
// CHECK1-NEXT: [[TMP30:%.*]] = load float, float* [[TMP11]], align 4
|
|
// CHECK1-NEXT: [[TMP31:%.*]] = load float, float* [[TMP8]], align 4
|
|
// CHECK1-NEXT: [[ADD:%.*]] = fadd float [[TMP30]], [[TMP31]]
|
|
// CHECK1-NEXT: store float [[ADD]], float* [[TMP11]], align 4
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[TMP17]], %struct.S* nonnull align 4 dereferenceable(4) [[TMP14]])
|
|
// CHECK1-NEXT: [[TMP32:%.*]] = bitcast %struct.S* [[TMP17]] to i8*
|
|
// CHECK1-NEXT: [[TMP33:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP32]], i8* align 4 [[TMP33]], i64 4, i1 false)
|
|
// CHECK1-NEXT: [[CALL2:%.*]] = call float @_ZN1SIfEcvfEv(%struct.S* nonnull align 4 dereferenceable(4) [[TMP23]])
|
|
// CHECK1-NEXT: [[TOBOOL:%.*]] = fcmp une float [[CALL2]], 0.000000e+00
|
|
// CHECK1-NEXT: br i1 [[TOBOOL]], label [[LAND_RHS:%.*]], label [[LAND_END:%.*]]
|
|
// CHECK1: land.rhs:
|
|
// CHECK1-NEXT: [[CALL3:%.*]] = call float @_ZN1SIfEcvfEv(%struct.S* nonnull align 4 dereferenceable(4) [[TMP20]])
|
|
// CHECK1-NEXT: [[TOBOOL4:%.*]] = fcmp une float [[CALL3]], 0.000000e+00
|
|
// CHECK1-NEXT: br label [[LAND_END]]
|
|
// CHECK1: land.end:
|
|
// CHECK1-NEXT: [[TMP34:%.*]] = phi i1 [ false, [[ENTRY:%.*]] ], [ [[TOBOOL4]], [[LAND_RHS]] ]
|
|
// CHECK1-NEXT: [[CONV:%.*]] = uitofp i1 [[TMP34]] to float
|
|
// CHECK1-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) [[REF_TMP]], float [[CONV]])
|
|
// CHECK1-NEXT: [[TMP35:%.*]] = bitcast %struct.S* [[TMP23]] to i8*
|
|
// CHECK1-NEXT: [[TMP36:%.*]] = bitcast %struct.S* [[REF_TMP]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP35]], i8* align 4 [[TMP36]], i64 4, i1 false)
|
|
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[REF_TMP]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: [[TMP37:%.*]] = load float, float* [[TMP29]], align 4
|
|
// CHECK1-NEXT: [[TMP38:%.*]] = load float, float* [[TMP26]], align 4
|
|
// CHECK1-NEXT: [[CMP:%.*]] = fcmp olt float [[TMP37]], [[TMP38]]
|
|
// CHECK1-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK1: cond.true:
|
|
// CHECK1-NEXT: [[TMP39:%.*]] = load float, float* [[TMP29]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK1: cond.false:
|
|
// CHECK1-NEXT: [[TMP40:%.*]] = load float, float* [[TMP26]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END]]
|
|
// CHECK1: cond.end:
|
|
// CHECK1-NEXT: [[COND:%.*]] = phi float [ [[TMP39]], [[COND_TRUE]] ], [ [[TMP40]], [[COND_FALSE]] ]
|
|
// CHECK1-NEXT: store float [[COND]], float* [[TMP29]], align 4
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfEanERKS0_
|
|
// CHECK1-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], %struct.S* nonnull align 4 dereferenceable(4) [[TMP0:%.*]]) #[[ATTR7:[0-9]+]] align 2 {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK1-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: store %struct.S* [[TMP0]], %struct.S** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: ret %struct.S* [[THIS1]]
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfEcvfEv
|
|
// CHECK1-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) #[[ATTR7]] align 2 {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK1-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: ret float 0.000000e+00
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfED1Ev
|
|
// CHECK1-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK1-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: call void @_ZN1SIfED2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined..1
|
|
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.0* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.0*, align 8
|
|
// CHECK1-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[TMP:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[SAVED_STACK:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: [[__VLA_EXPR0:%.*]] = alloca i64, align 8
|
|
// CHECK1-NEXT: [[__VLA_EXPR1:%.*]] = alloca i64, align 8
|
|
// CHECK1-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [4 x i8*], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store %struct.anon.0* [[__CONTEXT]], %struct.anon.0** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load %struct.anon.0*, %struct.anon.0** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_0:%.*]], %struct.anon.0* [[TMP0]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load i64, i64* [[TMP1]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_ANON_0]], %struct.anon.0* [[TMP0]], i32 0, i32 1
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load i64, i64* [[TMP3]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_ANON_0]], %struct.anon.0* [[TMP0]], i32 0, i32 2
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = load i32*, i32** [[TMP5]], align 8
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = getelementptr inbounds [[STRUCT_ANON_0]], %struct.anon.0* [[TMP0]], i32 0, i32 3
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = load [2 x i32]*, [2 x i32]** [[TMP7]], align 8
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_ANON_0]], %struct.anon.0* [[TMP0]], i32 0, i32 4
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = load [10 x [4 x %struct.S]]*, [10 x [4 x %struct.S]]** [[TMP9]], align 8
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = mul nsw i64 1, [[TMP4]]
|
|
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[TMP6]], i64 [[TMP11]]
|
|
// CHECK1-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX]], i64 0
|
|
// CHECK1-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[TMP8]], i64 0, i64 1
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = load i32, i32* [[ARRAYIDX2]], align 4
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = sext i32 [[TMP12]] to i64
|
|
// CHECK1-NEXT: [[LB_ADD_LEN:%.*]] = add nsw i64 -1, [[TMP13]]
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = mul nsw i64 1, [[TMP4]]
|
|
// CHECK1-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[TMP6]], i64 [[TMP14]]
|
|
// CHECK1-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX3]], i64 [[LB_ADD_LEN]]
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = ptrtoint i32* [[ARRAYIDX4]] to i64
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = ptrtoint i32* [[ARRAYIDX1]] to i64
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = sub i64 [[TMP15]], [[TMP16]]
|
|
// CHECK1-NEXT: [[TMP18:%.*]] = sdiv exact i64 [[TMP17]], ptrtoint (i32* getelementptr (i32, i32* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[TMP19:%.*]] = add nuw i64 [[TMP18]], 1
|
|
// CHECK1-NEXT: [[TMP20:%.*]] = mul nuw i64 [[TMP19]], ptrtoint (i32* getelementptr (i32, i32* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[TMP21:%.*]] = call i8* @llvm.stacksave()
|
|
// CHECK1-NEXT: store i8* [[TMP21]], i8** [[SAVED_STACK]], align 8
|
|
// CHECK1-NEXT: [[VLA:%.*]] = alloca i32, i64 [[TMP19]], align 16
|
|
// CHECK1-NEXT: store i64 [[TMP19]], i64* [[__VLA_EXPR0]], align 8
|
|
// CHECK1-NEXT: [[TMP22:%.*]] = getelementptr i32, i32* [[VLA]], i64 [[TMP19]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq i32* [[VLA]], [[TMP22]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
|
|
// CHECK1: omp.arrayinit.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi i32* [ [[VLA]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
|
|
// CHECK1-NEXT: store i32 0, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 4
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP22]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK1: omp.arrayinit.done:
|
|
// CHECK1-NEXT: [[TMP23:%.*]] = ptrtoint i32* [[TMP6]] to i64
|
|
// CHECK1-NEXT: [[TMP24:%.*]] = ptrtoint i32* [[ARRAYIDX1]] to i64
|
|
// CHECK1-NEXT: [[TMP25:%.*]] = sub i64 [[TMP23]], [[TMP24]]
|
|
// CHECK1-NEXT: [[TMP26:%.*]] = sdiv exact i64 [[TMP25]], ptrtoint (i32* getelementptr (i32, i32* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[TMP27:%.*]] = getelementptr i32, i32* [[VLA]], i64 [[TMP26]]
|
|
// CHECK1-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds [10 x [4 x %struct.S]], [10 x [4 x %struct.S]]* [[TMP10]], i64 0, i64 1
|
|
// CHECK1-NEXT: [[ARRAYDECAY:%.*]] = getelementptr inbounds [4 x %struct.S], [4 x %struct.S]* [[ARRAYIDX5]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[ARRAYDECAY]], i64 1
|
|
// CHECK1-NEXT: [[ARRAYIDX7:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[TMP8]], i64 0, i64 1
|
|
// CHECK1-NEXT: [[TMP28:%.*]] = load i32, i32* [[ARRAYIDX7]], align 4
|
|
// CHECK1-NEXT: [[TMP29:%.*]] = sext i32 [[TMP28]] to i64
|
|
// CHECK1-NEXT: [[LB_ADD_LEN8:%.*]] = add nsw i64 0, [[TMP29]]
|
|
// CHECK1-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds [10 x [4 x %struct.S]], [10 x [4 x %struct.S]]* [[TMP10]], i64 0, i64 [[LB_ADD_LEN8]]
|
|
// CHECK1-NEXT: [[ARRAYDECAY10:%.*]] = getelementptr inbounds [4 x %struct.S], [4 x %struct.S]* [[ARRAYIDX9]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[ARRAYIDX11:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDECAY10]], i64 2
|
|
// CHECK1-NEXT: [[TMP30:%.*]] = ptrtoint %struct.S* [[ARRAYIDX11]] to i64
|
|
// CHECK1-NEXT: [[TMP31:%.*]] = ptrtoint %struct.S* [[ARRAYIDX6]] to i64
|
|
// CHECK1-NEXT: [[TMP32:%.*]] = sub i64 [[TMP30]], [[TMP31]]
|
|
// CHECK1-NEXT: [[TMP33:%.*]] = sdiv exact i64 [[TMP32]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[TMP34:%.*]] = add nuw i64 [[TMP33]], 1
|
|
// CHECK1-NEXT: [[TMP35:%.*]] = mul nuw i64 [[TMP34]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[VLA12:%.*]] = alloca [[STRUCT_S]], i64 [[TMP34]], align 16
|
|
// CHECK1-NEXT: store i64 [[TMP34]], i64* [[__VLA_EXPR1]], align 8
|
|
// CHECK1-NEXT: [[TMP36:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[VLA12]], i64 [[TMP34]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYINIT_ISEMPTY13:%.*]] = icmp eq %struct.S* [[VLA12]], [[TMP36]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY13]], label [[OMP_ARRAYINIT_DONE18:%.*]], label [[OMP_ARRAYINIT_BODY14:%.*]]
|
|
// CHECK1: omp.arrayinit.body14:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST15:%.*]] = phi %struct.S* [ [[VLA12]], [[OMP_ARRAYINIT_DONE]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT16:%.*]], [[OMP_ARRAYINIT_BODY14]] ]
|
|
// CHECK1-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST15]])
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT16]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST15]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE17:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT16]], [[TMP36]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE17]], label [[OMP_ARRAYINIT_DONE18]], label [[OMP_ARRAYINIT_BODY14]]
|
|
// CHECK1: omp.arrayinit.done18:
|
|
// CHECK1-NEXT: [[TMP37:%.*]] = bitcast [10 x [4 x %struct.S]]* [[TMP10]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP38:%.*]] = ptrtoint %struct.S* [[TMP37]] to i64
|
|
// CHECK1-NEXT: [[TMP39:%.*]] = ptrtoint %struct.S* [[ARRAYIDX6]] to i64
|
|
// CHECK1-NEXT: [[TMP40:%.*]] = sub i64 [[TMP38]], [[TMP39]]
|
|
// CHECK1-NEXT: [[TMP41:%.*]] = sdiv exact i64 [[TMP40]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[TMP42:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[VLA12]], i64 [[TMP41]]
|
|
// CHECK1-NEXT: [[TMP43:%.*]] = bitcast %struct.S* [[TMP42]] to [10 x [4 x %struct.S]]*
|
|
// CHECK1-NEXT: [[TMP44:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP45:%.*]] = load i32, i32* [[TMP44]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP45]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK1-NEXT: [[TMP46:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP46]], 9
|
|
// CHECK1-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK1: cond.true:
|
|
// CHECK1-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK1: cond.false:
|
|
// CHECK1-NEXT: [[TMP47:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END]]
|
|
// CHECK1: cond.end:
|
|
// CHECK1-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP47]], [[COND_FALSE]] ]
|
|
// CHECK1-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[TMP48:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 [[TMP48]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK1: omp.inner.for.cond:
|
|
// CHECK1-NEXT: [[TMP49:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[TMP50:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP19:%.*]] = icmp sle i32 [[TMP49]], [[TMP50]]
|
|
// CHECK1-NEXT: br i1 [[CMP19]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK1: omp.inner.for.cond.cleanup:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK1: omp.inner.for.body:
|
|
// CHECK1-NEXT: [[TMP51:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP51]], 1
|
|
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK1-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK1-NEXT: [[TMP52:%.*]] = mul nsw i64 1, [[TMP4]]
|
|
// CHECK1-NEXT: [[ARRAYIDX20:%.*]] = getelementptr inbounds i32, i32* [[TMP27]], i64 [[TMP52]]
|
|
// CHECK1-NEXT: [[TMP53:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK1-NEXT: [[IDXPROM:%.*]] = sext i32 [[TMP53]] to i64
|
|
// CHECK1-NEXT: [[ARRAYIDX21:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX20]], i64 [[IDXPROM]]
|
|
// CHECK1-NEXT: [[TMP54:%.*]] = load i32, i32* [[ARRAYIDX21]], align 4
|
|
// CHECK1-NEXT: [[INC:%.*]] = add nsw i32 [[TMP54]], 1
|
|
// CHECK1-NEXT: store i32 [[INC]], i32* [[ARRAYIDX21]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK1: omp.body.continue:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK1: omp.inner.for.inc:
|
|
// CHECK1-NEXT: [[TMP55:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[ADD22:%.*]] = add nsw i32 [[TMP55]], 1
|
|
// CHECK1-NEXT: store i32 [[ADD22]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK1: omp.inner.for.end:
|
|
// CHECK1-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK1: omp.loop.exit:
|
|
// CHECK1-NEXT: [[TMP56:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP57:%.*]] = load i32, i32* [[TMP56]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP57]])
|
|
// CHECK1-NEXT: [[TMP58:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP59:%.*]] = bitcast i32* [[VLA]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP59]], i8** [[TMP58]], align 8
|
|
// CHECK1-NEXT: [[TMP60:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 1
|
|
// CHECK1-NEXT: [[TMP61:%.*]] = inttoptr i64 [[TMP19]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP61]], i8** [[TMP60]], align 8
|
|
// CHECK1-NEXT: [[TMP62:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 2
|
|
// CHECK1-NEXT: [[TMP63:%.*]] = bitcast %struct.S* [[VLA12]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP63]], i8** [[TMP62]], align 8
|
|
// CHECK1-NEXT: [[TMP64:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 3
|
|
// CHECK1-NEXT: [[TMP65:%.*]] = inttoptr i64 [[TMP34]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP65]], i8** [[TMP64]], align 8
|
|
// CHECK1-NEXT: [[TMP66:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP67:%.*]] = load i32, i32* [[TMP66]], align 4
|
|
// CHECK1-NEXT: [[TMP68:%.*]] = bitcast [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK1-NEXT: [[TMP69:%.*]] = call i32 @__kmpc_reduce_nowait(%struct.ident_t* @[[GLOB2]], i32 [[TMP67]], i32 2, i64 32, i8* [[TMP68]], void (i8*, i8*)* @.omp.reduction.reduction_func.2, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: switch i32 [[TMP69]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK1-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK1-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK1-NEXT: ]
|
|
// CHECK1: .omp.reduction.case1:
|
|
// CHECK1-NEXT: [[TMP70:%.*]] = getelementptr i32, i32* [[ARRAYIDX1]], i64 [[TMP19]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq i32* [[ARRAYIDX1]], [[TMP70]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE27:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK1: omp.arraycpy.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi i32* [ [[VLA]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST23:%.*]] = phi i32* [ [[ARRAYIDX1]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT25:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[TMP71:%.*]] = load i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST23]], align 4
|
|
// CHECK1-NEXT: [[TMP72:%.*]] = load i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], align 4
|
|
// CHECK1-NEXT: [[ADD24:%.*]] = add nsw i32 [[TMP71]], [[TMP72]]
|
|
// CHECK1-NEXT: store i32 [[ADD24]], i32* [[OMP_ARRAYCPY_DESTELEMENTPAST23]], align 4
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT25]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST23]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE26:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT25]], [[TMP70]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE26]], label [[OMP_ARRAYCPY_DONE27]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK1: omp.arraycpy.done27:
|
|
// CHECK1-NEXT: [[TMP73:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX6]], i64 [[TMP34]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY28:%.*]] = icmp eq %struct.S* [[ARRAYIDX6]], [[TMP73]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY28]], label [[OMP_ARRAYCPY_DONE35:%.*]], label [[OMP_ARRAYCPY_BODY29:%.*]]
|
|
// CHECK1: omp.arraycpy.body29:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST30:%.*]] = phi %struct.S* [ [[VLA12]], [[OMP_ARRAYCPY_DONE27]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT33:%.*]], [[OMP_ARRAYCPY_BODY29]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST31:%.*]] = phi %struct.S* [ [[ARRAYIDX6]], [[OMP_ARRAYCPY_DONE27]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT32:%.*]], [[OMP_ARRAYCPY_BODY29]] ]
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST31]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST30]])
|
|
// CHECK1-NEXT: [[TMP74:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST31]] to i8*
|
|
// CHECK1-NEXT: [[TMP75:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP74]], i8* align 4 [[TMP75]], i64 4, i1 false)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT32]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST31]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT33]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST30]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE34:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT32]], [[TMP73]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE34]], label [[OMP_ARRAYCPY_DONE35]], label [[OMP_ARRAYCPY_BODY29]]
|
|
// CHECK1: omp.arraycpy.done35:
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce_nowait(%struct.ident_t* @[[GLOB2]], i32 [[TMP67]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.case2:
|
|
// CHECK1-NEXT: [[TMP76:%.*]] = getelementptr i32, i32* [[ARRAYIDX1]], i64 [[TMP19]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY36:%.*]] = icmp eq i32* [[ARRAYIDX1]], [[TMP76]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY36]], label [[OMP_ARRAYCPY_DONE43:%.*]], label [[OMP_ARRAYCPY_BODY37:%.*]]
|
|
// CHECK1: omp.arraycpy.body37:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST38:%.*]] = phi i32* [ [[VLA]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT41:%.*]], [[OMP_ARRAYCPY_BODY37]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST39:%.*]] = phi i32* [ [[ARRAYIDX1]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT40:%.*]], [[OMP_ARRAYCPY_BODY37]] ]
|
|
// CHECK1-NEXT: [[TMP77:%.*]] = load i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST38]], align 4
|
|
// CHECK1-NEXT: [[TMP78:%.*]] = atomicrmw add i32* [[OMP_ARRAYCPY_DESTELEMENTPAST39]], i32 [[TMP77]] monotonic, align 4
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT40]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST39]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT41]] = getelementptr i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST38]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE42:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT40]], [[TMP76]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE42]], label [[OMP_ARRAYCPY_DONE43]], label [[OMP_ARRAYCPY_BODY37]]
|
|
// CHECK1: omp.arraycpy.done43:
|
|
// CHECK1-NEXT: [[TMP79:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX6]], i64 [[TMP34]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY44:%.*]] = icmp eq %struct.S* [[ARRAYIDX6]], [[TMP79]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY44]], label [[OMP_ARRAYCPY_DONE52:%.*]], label [[OMP_ARRAYCPY_BODY45:%.*]]
|
|
// CHECK1: omp.arraycpy.body45:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST46:%.*]] = phi %struct.S* [ [[VLA12]], [[OMP_ARRAYCPY_DONE43]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT50:%.*]], [[OMP_ARRAYCPY_BODY45]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST47:%.*]] = phi %struct.S* [ [[ARRAYIDX6]], [[OMP_ARRAYCPY_DONE43]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT49:%.*]], [[OMP_ARRAYCPY_BODY45]] ]
|
|
// CHECK1-NEXT: [[TMP80:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP81:%.*]] = load i32, i32* [[TMP80]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP81]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[CALL48:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST47]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST46]])
|
|
// CHECK1-NEXT: [[TMP82:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST47]] to i8*
|
|
// CHECK1-NEXT: [[TMP83:%.*]] = bitcast %struct.S* [[CALL48]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP82]], i8* align 4 [[TMP83]], i64 4, i1 false)
|
|
// CHECK1-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP81]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT49]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST47]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT50]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST46]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE51:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT49]], [[TMP79]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE51]], label [[OMP_ARRAYCPY_DONE52]], label [[OMP_ARRAYCPY_BODY45]]
|
|
// CHECK1: omp.arraycpy.done52:
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.default:
|
|
// CHECK1-NEXT: [[TMP84:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[VLA12]], i64 [[TMP34]]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ISEMPTY:%.*]] = icmp eq %struct.S* [[VLA12]], [[TMP84]]
|
|
// CHECK1-NEXT: br i1 [[ARRAYDESTROY_ISEMPTY]], label [[ARRAYDESTROY_DONE53:%.*]], label [[ARRAYDESTROY_BODY:%.*]]
|
|
// CHECK1: arraydestroy.body:
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP84]], [[DOTOMP_REDUCTION_DEFAULT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
|
|
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[VLA12]]
|
|
// CHECK1-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE53]], label [[ARRAYDESTROY_BODY]]
|
|
// CHECK1: arraydestroy.done53:
|
|
// CHECK1-NEXT: [[TMP85:%.*]] = load i8*, i8** [[SAVED_STACK]], align 8
|
|
// CHECK1-NEXT: call void @llvm.stackrestore(i8* [[TMP85]])
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.2
|
|
// CHECK1-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [4 x i8*]*
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [4 x i8*]*
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to i32*
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i32*
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 1
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = load i8*, i8** [[TMP12]], align 8
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = ptrtoint i8* [[TMP13]] to i64
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 2
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = load i8*, i8** [[TMP15]], align 8
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = bitcast i8* [[TMP16]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP18:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 2
|
|
// CHECK1-NEXT: [[TMP19:%.*]] = load i8*, i8** [[TMP18]], align 8
|
|
// CHECK1-NEXT: [[TMP20:%.*]] = bitcast i8* [[TMP19]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP21:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 3
|
|
// CHECK1-NEXT: [[TMP22:%.*]] = load i8*, i8** [[TMP21]], align 8
|
|
// CHECK1-NEXT: [[TMP23:%.*]] = ptrtoint i8* [[TMP22]] to i64
|
|
// CHECK1-NEXT: [[TMP24:%.*]] = getelementptr i32, i32* [[TMP11]], i64 [[TMP14]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq i32* [[TMP11]], [[TMP24]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE2:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK1: omp.arraycpy.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi i32* [ [[TMP8]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi i32* [ [[TMP11]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[TMP25:%.*]] = load i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 4
|
|
// CHECK1-NEXT: [[TMP26:%.*]] = load i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], align 4
|
|
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP25]], [[TMP26]]
|
|
// CHECK1-NEXT: store i32 [[ADD]], i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 4
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP24]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE2]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK1: omp.arraycpy.done2:
|
|
// CHECK1-NEXT: [[TMP27:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[TMP20]], i64 [[TMP23]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY3:%.*]] = icmp eq %struct.S* [[TMP20]], [[TMP27]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY3]], label [[OMP_ARRAYCPY_DONE10:%.*]], label [[OMP_ARRAYCPY_BODY4:%.*]]
|
|
// CHECK1: omp.arraycpy.body4:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST5:%.*]] = phi %struct.S* [ [[TMP17]], [[OMP_ARRAYCPY_DONE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT8:%.*]], [[OMP_ARRAYCPY_BODY4]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST6:%.*]] = phi %struct.S* [ [[TMP20]], [[OMP_ARRAYCPY_DONE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT7:%.*]], [[OMP_ARRAYCPY_BODY4]] ]
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST6]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST5]])
|
|
// CHECK1-NEXT: [[TMP28:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST6]] to i8*
|
|
// CHECK1-NEXT: [[TMP29:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP28]], i8* align 4 [[TMP29]], i64 4, i1 false)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT7]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST6]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT8]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST5]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE9:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT7]], [[TMP27]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE9]], label [[OMP_ARRAYCPY_DONE10]], label [[OMP_ARRAYCPY_BODY4]]
|
|
// CHECK1: omp.arraycpy.done10:
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined..3
|
|
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.1* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.1*, align 8
|
|
// CHECK1-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[TMP:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[SAVED_STACK:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: [[__VLA_EXPR0:%.*]] = alloca i64, align 8
|
|
// CHECK1-NEXT: [[ARRS:%.*]] = alloca [10 x [4 x %struct.S]], align 16
|
|
// CHECK1-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [3 x i8*], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store %struct.anon.1* [[__CONTEXT]], %struct.anon.1** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load %struct.anon.1*, %struct.anon.1** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_1:%.*]], %struct.anon.1* [[TMP0]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load i64, i64* [[TMP1]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_ANON_1]], %struct.anon.1* [[TMP0]], i32 0, i32 1
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load i64, i64* [[TMP3]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_ANON_1]], %struct.anon.1* [[TMP0]], i32 0, i32 2
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = load i32*, i32** [[TMP5]], align 8
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = getelementptr inbounds [[STRUCT_ANON_1]], %struct.anon.1* [[TMP0]], i32 0, i32 3
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = load [10 x [4 x %struct.S]]*, [10 x [4 x %struct.S]]** [[TMP7]], align 8
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = mul nuw i64 [[TMP2]], [[TMP4]]
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = mul nuw i64 [[TMP9]], 4
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = udiv exact i64 [[TMP10]], ptrtoint (i32* getelementptr (i32, i32* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = call i8* @llvm.stacksave()
|
|
// CHECK1-NEXT: store i8* [[TMP12]], i8** [[SAVED_STACK]], align 8
|
|
// CHECK1-NEXT: [[VLA:%.*]] = alloca i32, i64 [[TMP11]], align 16
|
|
// CHECK1-NEXT: store i64 [[TMP11]], i64* [[__VLA_EXPR0]], align 8
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = getelementptr i32, i32* [[VLA]], i64 [[TMP11]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq i32* [[VLA]], [[TMP13]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
|
|
// CHECK1: omp.arrayinit.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi i32* [ [[VLA]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
|
|
// CHECK1-NEXT: store i32 0, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 4
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP13]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK1: omp.arrayinit.done:
|
|
// CHECK1-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [10 x [4 x %struct.S]], [10 x [4 x %struct.S]]* [[ARRS]], i32 0, i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[ARRAY_BEGIN]], i64 40
|
|
// CHECK1-NEXT: [[OMP_ARRAYINIT_ISEMPTY1:%.*]] = icmp eq %struct.S* [[ARRAY_BEGIN]], [[TMP14]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY1]], label [[OMP_ARRAYINIT_DONE6:%.*]], label [[OMP_ARRAYINIT_BODY2:%.*]]
|
|
// CHECK1: omp.arrayinit.body2:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST3:%.*]] = phi %struct.S* [ [[ARRAY_BEGIN]], [[OMP_ARRAYINIT_DONE]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT4:%.*]], [[OMP_ARRAYINIT_BODY2]] ]
|
|
// CHECK1-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST3]])
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT4]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST3]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE5:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT4]], [[TMP14]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE5]], label [[OMP_ARRAYINIT_DONE6]], label [[OMP_ARRAYINIT_BODY2]]
|
|
// CHECK1: omp.arrayinit.done6:
|
|
// CHECK1-NEXT: [[LHS_BEGIN:%.*]] = bitcast [10 x [4 x %struct.S]]* [[TMP8]] to %struct.S*
|
|
// CHECK1-NEXT: [[RHS_BEGIN:%.*]] = bitcast [10 x [4 x %struct.S]]* [[ARRS]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = load i32, i32* [[TMP15]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP16]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP17]], 9
|
|
// CHECK1-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK1: cond.true:
|
|
// CHECK1-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK1: cond.false:
|
|
// CHECK1-NEXT: [[TMP18:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END]]
|
|
// CHECK1: cond.end:
|
|
// CHECK1-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP18]], [[COND_FALSE]] ]
|
|
// CHECK1-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[TMP19:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 [[TMP19]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK1: omp.inner.for.cond:
|
|
// CHECK1-NEXT: [[TMP20:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[TMP21:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP7:%.*]] = icmp sle i32 [[TMP20]], [[TMP21]]
|
|
// CHECK1-NEXT: br i1 [[CMP7]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK1: omp.inner.for.cond.cleanup:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK1: omp.inner.for.body:
|
|
// CHECK1-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP22]], 1
|
|
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK1-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK1-NEXT: [[TMP23:%.*]] = mul nsw i64 1, [[TMP4]]
|
|
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP23]]
|
|
// CHECK1-NEXT: [[TMP24:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK1-NEXT: [[IDXPROM:%.*]] = sext i32 [[TMP24]] to i64
|
|
// CHECK1-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX]], i64 [[IDXPROM]]
|
|
// CHECK1-NEXT: [[TMP25:%.*]] = load i32, i32* [[ARRAYIDX8]], align 4
|
|
// CHECK1-NEXT: [[INC:%.*]] = add nsw i32 [[TMP25]], 1
|
|
// CHECK1-NEXT: store i32 [[INC]], i32* [[ARRAYIDX8]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK1: omp.body.continue:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK1: omp.inner.for.inc:
|
|
// CHECK1-NEXT: [[TMP26:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[ADD9:%.*]] = add nsw i32 [[TMP26]], 1
|
|
// CHECK1-NEXT: store i32 [[ADD9]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK1: omp.inner.for.end:
|
|
// CHECK1-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK1: omp.loop.exit:
|
|
// CHECK1-NEXT: [[TMP27:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP28:%.*]] = load i32, i32* [[TMP27]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP28]])
|
|
// CHECK1-NEXT: [[TMP29:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP30:%.*]] = bitcast i32* [[VLA]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP30]], i8** [[TMP29]], align 8
|
|
// CHECK1-NEXT: [[TMP31:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 1
|
|
// CHECK1-NEXT: [[TMP32:%.*]] = inttoptr i64 [[TMP11]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP32]], i8** [[TMP31]], align 8
|
|
// CHECK1-NEXT: [[TMP33:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 2
|
|
// CHECK1-NEXT: [[TMP34:%.*]] = bitcast %struct.S* [[RHS_BEGIN]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP34]], i8** [[TMP33]], align 8
|
|
// CHECK1-NEXT: [[TMP35:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP36:%.*]] = load i32, i32* [[TMP35]], align 4
|
|
// CHECK1-NEXT: [[TMP37:%.*]] = bitcast [3 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK1-NEXT: [[TMP38:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP36]], i32 2, i64 24, i8* [[TMP37]], void (i8*, i8*)* @.omp.reduction.reduction_func.4, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: switch i32 [[TMP38]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK1-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK1-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK1-NEXT: ]
|
|
// CHECK1: .omp.reduction.case1:
|
|
// CHECK1-NEXT: [[TMP39:%.*]] = getelementptr i32, i32* [[TMP6]], i64 [[TMP11]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq i32* [[TMP6]], [[TMP39]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE14:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK1: omp.arraycpy.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi i32* [ [[VLA]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST10:%.*]] = phi i32* [ [[TMP6]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT12:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[TMP40:%.*]] = load i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST10]], align 4
|
|
// CHECK1-NEXT: [[TMP41:%.*]] = load i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], align 4
|
|
// CHECK1-NEXT: [[ADD11:%.*]] = add nsw i32 [[TMP40]], [[TMP41]]
|
|
// CHECK1-NEXT: store i32 [[ADD11]], i32* [[OMP_ARRAYCPY_DESTELEMENTPAST10]], align 4
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT12]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST10]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE13:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT12]], [[TMP39]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE13]], label [[OMP_ARRAYCPY_DONE14]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK1: omp.arraycpy.done14:
|
|
// CHECK1-NEXT: [[TMP42:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[LHS_BEGIN]], i64 40
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY15:%.*]] = icmp eq %struct.S* [[LHS_BEGIN]], [[TMP42]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY15]], label [[OMP_ARRAYCPY_DONE22:%.*]], label [[OMP_ARRAYCPY_BODY16:%.*]]
|
|
// CHECK1: omp.arraycpy.body16:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST17:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[OMP_ARRAYCPY_DONE14]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT20:%.*]], [[OMP_ARRAYCPY_BODY16]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST18:%.*]] = phi %struct.S* [ [[LHS_BEGIN]], [[OMP_ARRAYCPY_DONE14]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT19:%.*]], [[OMP_ARRAYCPY_BODY16]] ]
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST18]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST17]])
|
|
// CHECK1-NEXT: [[TMP43:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST18]] to i8*
|
|
// CHECK1-NEXT: [[TMP44:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP43]], i8* align 4 [[TMP44]], i64 4, i1 false)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT19]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST18]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT20]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST17]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE21:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT19]], [[TMP42]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE21]], label [[OMP_ARRAYCPY_DONE22]], label [[OMP_ARRAYCPY_BODY16]]
|
|
// CHECK1: omp.arraycpy.done22:
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP36]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.case2:
|
|
// CHECK1-NEXT: [[TMP45:%.*]] = getelementptr i32, i32* [[TMP6]], i64 [[TMP11]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY23:%.*]] = icmp eq i32* [[TMP6]], [[TMP45]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY23]], label [[OMP_ARRAYCPY_DONE30:%.*]], label [[OMP_ARRAYCPY_BODY24:%.*]]
|
|
// CHECK1: omp.arraycpy.body24:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST25:%.*]] = phi i32* [ [[VLA]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT28:%.*]], [[OMP_ARRAYCPY_BODY24]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST26:%.*]] = phi i32* [ [[TMP6]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT27:%.*]], [[OMP_ARRAYCPY_BODY24]] ]
|
|
// CHECK1-NEXT: [[TMP46:%.*]] = load i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST25]], align 4
|
|
// CHECK1-NEXT: [[TMP47:%.*]] = atomicrmw add i32* [[OMP_ARRAYCPY_DESTELEMENTPAST26]], i32 [[TMP46]] monotonic, align 4
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT27]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST26]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT28]] = getelementptr i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST25]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE29:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT27]], [[TMP45]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE29]], label [[OMP_ARRAYCPY_DONE30]], label [[OMP_ARRAYCPY_BODY24]]
|
|
// CHECK1: omp.arraycpy.done30:
|
|
// CHECK1-NEXT: [[TMP48:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[LHS_BEGIN]], i64 40
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY31:%.*]] = icmp eq %struct.S* [[LHS_BEGIN]], [[TMP48]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY31]], label [[OMP_ARRAYCPY_DONE39:%.*]], label [[OMP_ARRAYCPY_BODY32:%.*]]
|
|
// CHECK1: omp.arraycpy.body32:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST33:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[OMP_ARRAYCPY_DONE30]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT37:%.*]], [[OMP_ARRAYCPY_BODY32]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST34:%.*]] = phi %struct.S* [ [[LHS_BEGIN]], [[OMP_ARRAYCPY_DONE30]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT36:%.*]], [[OMP_ARRAYCPY_BODY32]] ]
|
|
// CHECK1-NEXT: [[TMP49:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP50:%.*]] = load i32, i32* [[TMP49]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP50]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[CALL35:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST34]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST33]])
|
|
// CHECK1-NEXT: [[TMP51:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST34]] to i8*
|
|
// CHECK1-NEXT: [[TMP52:%.*]] = bitcast %struct.S* [[CALL35]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP51]], i8* align 4 [[TMP52]], i64 4, i1 false)
|
|
// CHECK1-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP50]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT36]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST34]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT37]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST33]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE38:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT36]], [[TMP48]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE38]], label [[OMP_ARRAYCPY_DONE39]], label [[OMP_ARRAYCPY_BODY32]]
|
|
// CHECK1: omp.arraycpy.done39:
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP36]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.default:
|
|
// CHECK1-NEXT: [[ARRAY_BEGIN40:%.*]] = getelementptr inbounds [10 x [4 x %struct.S]], [10 x [4 x %struct.S]]* [[ARRS]], i32 0, i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP53:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN40]], i64 40
|
|
// CHECK1-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
|
|
// CHECK1: arraydestroy.body:
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP53]], [[DOTOMP_REDUCTION_DEFAULT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
|
|
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN40]]
|
|
// CHECK1-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE41:%.*]], label [[ARRAYDESTROY_BODY]]
|
|
// CHECK1: arraydestroy.done41:
|
|
// CHECK1-NEXT: [[TMP54:%.*]] = load i8*, i8** [[SAVED_STACK]], align 8
|
|
// CHECK1-NEXT: call void @llvm.stackrestore(i8* [[TMP54]])
|
|
// CHECK1-NEXT: [[TMP55:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP56:%.*]] = load i32, i32* [[TMP55]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4]], i32 [[TMP56]])
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.4
|
|
// CHECK1-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [3 x i8*]*
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [3 x i8*]*
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to i32*
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i32*
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[TMP3]], i64 0, i64 1
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = load i8*, i8** [[TMP12]], align 8
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = ptrtoint i8* [[TMP13]] to i64
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[TMP5]], i64 0, i64 2
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = load i8*, i8** [[TMP15]], align 8
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = bitcast i8* [[TMP16]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP18:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[TMP3]], i64 0, i64 2
|
|
// CHECK1-NEXT: [[TMP19:%.*]] = load i8*, i8** [[TMP18]], align 8
|
|
// CHECK1-NEXT: [[TMP20:%.*]] = bitcast i8* [[TMP19]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP21:%.*]] = getelementptr i32, i32* [[TMP11]], i64 [[TMP14]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq i32* [[TMP11]], [[TMP21]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE2:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK1: omp.arraycpy.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi i32* [ [[TMP8]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi i32* [ [[TMP11]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[TMP22:%.*]] = load i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 4
|
|
// CHECK1-NEXT: [[TMP23:%.*]] = load i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], align 4
|
|
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP22]], [[TMP23]]
|
|
// CHECK1-NEXT: store i32 [[ADD]], i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 4
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP21]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE2]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK1: omp.arraycpy.done2:
|
|
// CHECK1-NEXT: [[TMP24:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[TMP20]], i64 40
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY3:%.*]] = icmp eq %struct.S* [[TMP20]], [[TMP24]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY3]], label [[OMP_ARRAYCPY_DONE10:%.*]], label [[OMP_ARRAYCPY_BODY4:%.*]]
|
|
// CHECK1: omp.arraycpy.body4:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST5:%.*]] = phi %struct.S* [ [[TMP17]], [[OMP_ARRAYCPY_DONE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT8:%.*]], [[OMP_ARRAYCPY_BODY4]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST6:%.*]] = phi %struct.S* [ [[TMP20]], [[OMP_ARRAYCPY_DONE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT7:%.*]], [[OMP_ARRAYCPY_BODY4]] ]
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST6]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST5]])
|
|
// CHECK1-NEXT: [[TMP25:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST6]] to i8*
|
|
// CHECK1-NEXT: [[TMP26:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP25]], i8* align 4 [[TMP26]], i64 4, i1 false)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT7]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST6]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT8]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST5]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE9:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT7]], [[TMP24]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE9]], label [[OMP_ARRAYCPY_DONE10]], label [[OMP_ARRAYCPY_BODY4]]
|
|
// CHECK1: omp.arraycpy.done10:
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined..5
|
|
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.2* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.2*, align 8
|
|
// CHECK1-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[TMP:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[ARR:%.*]] = alloca [1 x [2 x i32]], align 4
|
|
// CHECK1-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store %struct.anon.2* [[__CONTEXT]], %struct.anon.2** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load %struct.anon.2*, %struct.anon.2** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_2:%.*]], %struct.anon.2* [[TMP0]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load i64, i64* [[TMP1]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_ANON_2]], %struct.anon.2* [[TMP0]], i32 0, i32 1
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load i64, i64* [[TMP3]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_ANON_2]], %struct.anon.2* [[TMP0]], i32 0, i32 2
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = load i32*, i32** [[TMP5]], align 8
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = mul nsw i64 1, [[TMP4]]
|
|
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[TMP6]], i64 [[TMP7]]
|
|
// CHECK1-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX]], i64 0
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = mul nsw i64 1, [[TMP4]]
|
|
// CHECK1-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* [[TMP6]], i64 [[TMP8]]
|
|
// CHECK1-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX2]], i64 1
|
|
// CHECK1-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [1 x [2 x i32]], [1 x [2 x i32]]* [[ARR]], i32 0, i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr i32, i32* [[ARRAY_BEGIN]], i64 2
|
|
// CHECK1-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq i32* [[ARRAY_BEGIN]], [[TMP9]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
|
|
// CHECK1: omp.arrayinit.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi i32* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
|
|
// CHECK1-NEXT: store i32 0, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 4
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP9]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK1: omp.arrayinit.done:
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = ptrtoint i32* [[TMP6]] to i64
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = ptrtoint i32* [[ARRAYIDX1]] to i64
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = sub i64 [[TMP10]], [[TMP11]]
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = sdiv exact i64 [[TMP12]], ptrtoint (i32* getelementptr (i32, i32* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = bitcast [1 x [2 x i32]]* [[ARR]] to i32*
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = getelementptr i32, i32* [[TMP14]], i64 [[TMP13]]
|
|
// CHECK1-NEXT: [[RHS_BEGIN:%.*]] = bitcast [1 x [2 x i32]]* [[ARR]] to i32*
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = load i32, i32* [[TMP16]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP17]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK1-NEXT: [[TMP18:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP18]], 9
|
|
// CHECK1-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK1: cond.true:
|
|
// CHECK1-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK1: cond.false:
|
|
// CHECK1-NEXT: [[TMP19:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END]]
|
|
// CHECK1: cond.end:
|
|
// CHECK1-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP19]], [[COND_FALSE]] ]
|
|
// CHECK1-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[TMP20:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 [[TMP20]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK1: omp.inner.for.cond:
|
|
// CHECK1-NEXT: [[TMP21:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP4:%.*]] = icmp sle i32 [[TMP21]], [[TMP22]]
|
|
// CHECK1-NEXT: br i1 [[CMP4]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK1: omp.inner.for.body:
|
|
// CHECK1-NEXT: [[TMP23:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP23]], 1
|
|
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK1-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK1-NEXT: [[TMP24:%.*]] = mul nsw i64 1, [[TMP4]]
|
|
// CHECK1-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds i32, i32* [[TMP15]], i64 [[TMP24]]
|
|
// CHECK1-NEXT: [[TMP25:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK1-NEXT: [[IDXPROM:%.*]] = sext i32 [[TMP25]] to i64
|
|
// CHECK1-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX5]], i64 [[IDXPROM]]
|
|
// CHECK1-NEXT: [[TMP26:%.*]] = load i32, i32* [[ARRAYIDX6]], align 4
|
|
// CHECK1-NEXT: [[INC:%.*]] = add nsw i32 [[TMP26]], 1
|
|
// CHECK1-NEXT: store i32 [[INC]], i32* [[ARRAYIDX6]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK1: omp.body.continue:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK1: omp.inner.for.inc:
|
|
// CHECK1-NEXT: [[TMP27:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[ADD7:%.*]] = add nsw i32 [[TMP27]], 1
|
|
// CHECK1-NEXT: store i32 [[ADD7]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK1: omp.inner.for.end:
|
|
// CHECK1-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK1: omp.loop.exit:
|
|
// CHECK1-NEXT: [[TMP28:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP29:%.*]] = load i32, i32* [[TMP28]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP29]])
|
|
// CHECK1-NEXT: [[TMP30:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP31:%.*]] = bitcast i32* [[RHS_BEGIN]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP31]], i8** [[TMP30]], align 8
|
|
// CHECK1-NEXT: [[TMP32:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP33:%.*]] = load i32, i32* [[TMP32]], align 4
|
|
// CHECK1-NEXT: [[TMP34:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK1-NEXT: [[TMP35:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP33]], i32 1, i64 8, i8* [[TMP34]], void (i8*, i8*)* @.omp.reduction.reduction_func.6, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: switch i32 [[TMP35]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK1-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK1-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK1-NEXT: ]
|
|
// CHECK1: .omp.reduction.case1:
|
|
// CHECK1-NEXT: [[TMP36:%.*]] = getelementptr i32, i32* [[ARRAYIDX1]], i64 2
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq i32* [[ARRAYIDX1]], [[TMP36]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE12:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK1: omp.arraycpy.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi i32* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST8:%.*]] = phi i32* [ [[ARRAYIDX1]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT10:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[TMP37:%.*]] = load i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST8]], align 4
|
|
// CHECK1-NEXT: [[TMP38:%.*]] = load i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], align 4
|
|
// CHECK1-NEXT: [[ADD9:%.*]] = add nsw i32 [[TMP37]], [[TMP38]]
|
|
// CHECK1-NEXT: store i32 [[ADD9]], i32* [[OMP_ARRAYCPY_DESTELEMENTPAST8]], align 4
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT10]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST8]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE11:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT10]], [[TMP36]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE11]], label [[OMP_ARRAYCPY_DONE12]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK1: omp.arraycpy.done12:
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP33]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.case2:
|
|
// CHECK1-NEXT: [[TMP39:%.*]] = getelementptr i32, i32* [[ARRAYIDX1]], i64 2
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY13:%.*]] = icmp eq i32* [[ARRAYIDX1]], [[TMP39]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY13]], label [[OMP_ARRAYCPY_DONE20:%.*]], label [[OMP_ARRAYCPY_BODY14:%.*]]
|
|
// CHECK1: omp.arraycpy.body14:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST15:%.*]] = phi i32* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT18:%.*]], [[OMP_ARRAYCPY_BODY14]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST16:%.*]] = phi i32* [ [[ARRAYIDX1]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT17:%.*]], [[OMP_ARRAYCPY_BODY14]] ]
|
|
// CHECK1-NEXT: [[TMP40:%.*]] = load i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST15]], align 4
|
|
// CHECK1-NEXT: [[TMP41:%.*]] = atomicrmw add i32* [[OMP_ARRAYCPY_DESTELEMENTPAST16]], i32 [[TMP40]] monotonic, align 4
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT17]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST16]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT18]] = getelementptr i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST15]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE19:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT17]], [[TMP39]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE19]], label [[OMP_ARRAYCPY_DONE20]], label [[OMP_ARRAYCPY_BODY14]]
|
|
// CHECK1: omp.arraycpy.done20:
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP33]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.default:
|
|
// CHECK1-NEXT: [[TMP42:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP43:%.*]] = load i32, i32* [[TMP42]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4]], i32 [[TMP43]])
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.6
|
|
// CHECK1-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to i32*
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i32*
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = getelementptr i32, i32* [[TMP11]], i64 2
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq i32* [[TMP11]], [[TMP12]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE2:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK1: omp.arraycpy.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi i32* [ [[TMP8]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi i32* [ [[TMP11]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = load i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 4
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = load i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], align 4
|
|
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP13]], [[TMP14]]
|
|
// CHECK1-NEXT: store i32 [[ADD]], i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 4
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP12]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE2]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK1: omp.arraycpy.done2:
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined..7
|
|
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.3* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.3*, align 8
|
|
// CHECK1-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[TMP:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[SAVED_STACK:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: [[__VLA_EXPR0:%.*]] = alloca i64, align 8
|
|
// CHECK1-NEXT: [[_TMP4:%.*]] = alloca %struct.S**, align 8
|
|
// CHECK1-NEXT: [[_TMP5:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK1-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [2 x i8*], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store %struct.anon.3* [[__CONTEXT]], %struct.anon.3** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load %struct.anon.3*, %struct.anon.3** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_3:%.*]], %struct.anon.3* [[TMP0]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load %struct.S***, %struct.S**** [[TMP1]], align 8
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = load %struct.S**, %struct.S*** [[TMP2]], align 8
|
|
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds %struct.S*, %struct.S** [[TMP3]], i64 0
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load %struct.S*, %struct.S** [[ARRAYIDX]], align 8
|
|
// CHECK1-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[TMP4]], i64 1
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = load %struct.S**, %struct.S*** [[TMP2]], align 8
|
|
// CHECK1-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds %struct.S*, %struct.S** [[TMP5]], i64 4
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = load %struct.S*, %struct.S** [[ARRAYIDX2]], align 8
|
|
// CHECK1-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP6]], i64 6
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = ptrtoint %struct.S* [[ARRAYIDX3]] to i64
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = ptrtoint %struct.S* [[ARRAYIDX1]] to i64
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = sub i64 [[TMP7]], [[TMP8]]
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = sdiv exact i64 [[TMP9]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = add nuw i64 [[TMP10]], 1
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = mul nuw i64 [[TMP11]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = call i8* @llvm.stacksave()
|
|
// CHECK1-NEXT: store i8* [[TMP13]], i8** [[SAVED_STACK]], align 8
|
|
// CHECK1-NEXT: [[VLA:%.*]] = alloca [[STRUCT_S]], i64 [[TMP11]], align 16
|
|
// CHECK1-NEXT: store i64 [[TMP11]], i64* [[__VLA_EXPR0]], align 8
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[VLA]], i64 [[TMP11]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq %struct.S* [[VLA]], [[TMP14]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
|
|
// CHECK1: omp.arrayinit.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[VLA]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
|
|
// CHECK1-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]])
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP14]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK1: omp.arrayinit.done:
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = load %struct.S**, %struct.S*** [[TMP2]], align 8
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = load %struct.S*, %struct.S** [[TMP15]], align 8
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = ptrtoint %struct.S* [[TMP16]] to i64
|
|
// CHECK1-NEXT: [[TMP18:%.*]] = ptrtoint %struct.S* [[ARRAYIDX1]] to i64
|
|
// CHECK1-NEXT: [[TMP19:%.*]] = sub i64 [[TMP17]], [[TMP18]]
|
|
// CHECK1-NEXT: [[TMP20:%.*]] = sdiv exact i64 [[TMP19]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[TMP21:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[VLA]], i64 [[TMP20]]
|
|
// CHECK1-NEXT: store %struct.S** [[_TMP5]], %struct.S*** [[_TMP4]], align 8
|
|
// CHECK1-NEXT: store %struct.S* [[TMP21]], %struct.S** [[_TMP5]], align 8
|
|
// CHECK1-NEXT: [[TMP22:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP23:%.*]] = load i32, i32* [[TMP22]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP23]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK1-NEXT: [[TMP24:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP24]], 9
|
|
// CHECK1-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK1: cond.true:
|
|
// CHECK1-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK1: cond.false:
|
|
// CHECK1-NEXT: [[TMP25:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END]]
|
|
// CHECK1: cond.end:
|
|
// CHECK1-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP25]], [[COND_FALSE]] ]
|
|
// CHECK1-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[TMP26:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 [[TMP26]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK1: omp.inner.for.cond:
|
|
// CHECK1-NEXT: [[TMP27:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[TMP28:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP6:%.*]] = icmp sle i32 [[TMP27]], [[TMP28]]
|
|
// CHECK1-NEXT: br i1 [[CMP6]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK1: omp.inner.for.cond.cleanup:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK1: omp.inner.for.body:
|
|
// CHECK1-NEXT: [[TMP29:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP29]], 1
|
|
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK1-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK1: omp.body.continue:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK1: omp.inner.for.inc:
|
|
// CHECK1-NEXT: [[TMP30:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[ADD7:%.*]] = add nsw i32 [[TMP30]], 1
|
|
// CHECK1-NEXT: store i32 [[ADD7]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK1: omp.inner.for.end:
|
|
// CHECK1-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK1: omp.loop.exit:
|
|
// CHECK1-NEXT: [[TMP31:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP32:%.*]] = load i32, i32* [[TMP31]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP32]])
|
|
// CHECK1-NEXT: [[TMP33:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP34:%.*]] = bitcast %struct.S* [[VLA]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP34]], i8** [[TMP33]], align 8
|
|
// CHECK1-NEXT: [[TMP35:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 1
|
|
// CHECK1-NEXT: [[TMP36:%.*]] = inttoptr i64 [[TMP11]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP36]], i8** [[TMP35]], align 8
|
|
// CHECK1-NEXT: [[TMP37:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP38:%.*]] = load i32, i32* [[TMP37]], align 4
|
|
// CHECK1-NEXT: [[TMP39:%.*]] = bitcast [2 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK1-NEXT: [[TMP40:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP38]], i32 1, i64 16, i8* [[TMP39]], void (i8*, i8*)* @.omp.reduction.reduction_func.8, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: switch i32 [[TMP40]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK1-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK1-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK1-NEXT: ]
|
|
// CHECK1: .omp.reduction.case1:
|
|
// CHECK1-NEXT: [[TMP41:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX1]], i64 [[TMP11]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAYIDX1]], [[TMP41]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE11:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK1: omp.arraycpy.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[VLA]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST8:%.*]] = phi %struct.S* [ [[ARRAYIDX1]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT9:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST8]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK1-NEXT: [[TMP42:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST8]] to i8*
|
|
// CHECK1-NEXT: [[TMP43:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP42]], i8* align 4 [[TMP43]], i64 4, i1 false)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT9]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST8]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE10:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT9]], [[TMP41]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE10]], label [[OMP_ARRAYCPY_DONE11]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK1: omp.arraycpy.done11:
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP38]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.case2:
|
|
// CHECK1-NEXT: [[TMP44:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX1]], i64 [[TMP11]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY12:%.*]] = icmp eq %struct.S* [[ARRAYIDX1]], [[TMP44]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY12]], label [[OMP_ARRAYCPY_DONE20:%.*]], label [[OMP_ARRAYCPY_BODY13:%.*]]
|
|
// CHECK1: omp.arraycpy.body13:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST14:%.*]] = phi %struct.S* [ [[VLA]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT18:%.*]], [[OMP_ARRAYCPY_BODY13]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST15:%.*]] = phi %struct.S* [ [[ARRAYIDX1]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT17:%.*]], [[OMP_ARRAYCPY_BODY13]] ]
|
|
// CHECK1-NEXT: [[TMP45:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP46:%.*]] = load i32, i32* [[TMP45]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP46]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[CALL16:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST15]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST14]])
|
|
// CHECK1-NEXT: [[TMP47:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST15]] to i8*
|
|
// CHECK1-NEXT: [[TMP48:%.*]] = bitcast %struct.S* [[CALL16]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP47]], i8* align 4 [[TMP48]], i64 4, i1 false)
|
|
// CHECK1-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP46]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT17]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST15]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT18]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST14]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE19:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT17]], [[TMP44]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE19]], label [[OMP_ARRAYCPY_DONE20]], label [[OMP_ARRAYCPY_BODY13]]
|
|
// CHECK1: omp.arraycpy.done20:
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP38]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.default:
|
|
// CHECK1-NEXT: [[TMP49:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[VLA]], i64 [[TMP11]]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ISEMPTY:%.*]] = icmp eq %struct.S* [[VLA]], [[TMP49]]
|
|
// CHECK1-NEXT: br i1 [[ARRAYDESTROY_ISEMPTY]], label [[ARRAYDESTROY_DONE21:%.*]], label [[ARRAYDESTROY_BODY:%.*]]
|
|
// CHECK1: arraydestroy.body:
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP49]], [[DOTOMP_REDUCTION_DEFAULT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
|
|
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[VLA]]
|
|
// CHECK1-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE21]], label [[ARRAYDESTROY_BODY]]
|
|
// CHECK1: arraydestroy.done21:
|
|
// CHECK1-NEXT: [[TMP50:%.*]] = load i8*, i8** [[SAVED_STACK]], align 8
|
|
// CHECK1-NEXT: call void @llvm.stackrestore(i8* [[TMP50]])
|
|
// CHECK1-NEXT: [[TMP51:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP52:%.*]] = load i32, i32* [[TMP51]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4]], i32 [[TMP52]])
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.8
|
|
// CHECK1-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [2 x i8*]*
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [2 x i8*]*
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[TMP3]], i64 0, i64 1
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = load i8*, i8** [[TMP12]], align 8
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = ptrtoint i8* [[TMP13]] to i64
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[TMP11]], i64 [[TMP14]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[TMP11]], [[TMP15]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE2:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK1: omp.arraycpy.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP8]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP11]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]] to i8*
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP16]], i8* align 4 [[TMP17]], i64 4, i1 false)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP15]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE2]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK1: omp.arraycpy.done2:
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined..9
|
|
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.4* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.4*, align 8
|
|
// CHECK1-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[TMP:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[VAR2:%.*]] = alloca [1 x [6 x %struct.S]], align 16
|
|
// CHECK1-NEXT: [[_TMP4:%.*]] = alloca %struct.S**, align 8
|
|
// CHECK1-NEXT: [[_TMP5:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK1-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store %struct.anon.4* [[__CONTEXT]], %struct.anon.4** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load %struct.anon.4*, %struct.anon.4** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_4:%.*]], %struct.anon.4* [[TMP0]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load %struct.S***, %struct.S**** [[TMP1]], align 8
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = load %struct.S**, %struct.S*** [[TMP2]], align 8
|
|
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds %struct.S*, %struct.S** [[TMP3]], i64 1
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load %struct.S*, %struct.S** [[ARRAYIDX]], align 8
|
|
// CHECK1-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[TMP4]], i64 1
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = load %struct.S**, %struct.S*** [[TMP2]], align 8
|
|
// CHECK1-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds %struct.S*, %struct.S** [[TMP5]], i64 1
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = load %struct.S*, %struct.S** [[ARRAYIDX2]], align 8
|
|
// CHECK1-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP6]], i64 6
|
|
// CHECK1-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [1 x [6 x %struct.S]], [1 x [6 x %struct.S]]* [[VAR2]], i32 0, i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN]], i64 6
|
|
// CHECK1-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAY_BEGIN]], [[TMP7]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
|
|
// CHECK1: omp.arrayinit.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
|
|
// CHECK1-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]])
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP7]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK1: omp.arrayinit.done:
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = load %struct.S**, %struct.S*** [[TMP2]], align 8
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = load %struct.S*, %struct.S** [[TMP8]], align 8
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = ptrtoint %struct.S* [[TMP9]] to i64
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = ptrtoint %struct.S* [[ARRAYIDX1]] to i64
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = sub i64 [[TMP10]], [[TMP11]]
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = sdiv exact i64 [[TMP12]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = bitcast [1 x [6 x %struct.S]]* [[VAR2]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[TMP14]], i64 [[TMP13]]
|
|
// CHECK1-NEXT: store %struct.S** [[_TMP5]], %struct.S*** [[_TMP4]], align 8
|
|
// CHECK1-NEXT: store %struct.S* [[TMP15]], %struct.S** [[_TMP5]], align 8
|
|
// CHECK1-NEXT: [[RHS_BEGIN:%.*]] = bitcast [1 x [6 x %struct.S]]* [[VAR2]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = load i32, i32* [[TMP16]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP17]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK1-NEXT: [[TMP18:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP18]], 9
|
|
// CHECK1-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK1: cond.true:
|
|
// CHECK1-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK1: cond.false:
|
|
// CHECK1-NEXT: [[TMP19:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END]]
|
|
// CHECK1: cond.end:
|
|
// CHECK1-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP19]], [[COND_FALSE]] ]
|
|
// CHECK1-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[TMP20:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 [[TMP20]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK1: omp.inner.for.cond:
|
|
// CHECK1-NEXT: [[TMP21:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP6:%.*]] = icmp sle i32 [[TMP21]], [[TMP22]]
|
|
// CHECK1-NEXT: br i1 [[CMP6]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK1: omp.inner.for.cond.cleanup:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK1: omp.inner.for.body:
|
|
// CHECK1-NEXT: [[TMP23:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP23]], 1
|
|
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK1-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK1: omp.body.continue:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK1: omp.inner.for.inc:
|
|
// CHECK1-NEXT: [[TMP24:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[ADD7:%.*]] = add nsw i32 [[TMP24]], 1
|
|
// CHECK1-NEXT: store i32 [[ADD7]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK1: omp.inner.for.end:
|
|
// CHECK1-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK1: omp.loop.exit:
|
|
// CHECK1-NEXT: [[TMP25:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP26:%.*]] = load i32, i32* [[TMP25]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP26]])
|
|
// CHECK1-NEXT: [[TMP27:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP28:%.*]] = bitcast %struct.S* [[RHS_BEGIN]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP28]], i8** [[TMP27]], align 8
|
|
// CHECK1-NEXT: [[TMP29:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP30:%.*]] = load i32, i32* [[TMP29]], align 4
|
|
// CHECK1-NEXT: [[TMP31:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK1-NEXT: [[TMP32:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP30]], i32 1, i64 8, i8* [[TMP31]], void (i8*, i8*)* @.omp.reduction.reduction_func.10, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: switch i32 [[TMP32]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK1-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK1-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK1-NEXT: ]
|
|
// CHECK1: .omp.reduction.case1:
|
|
// CHECK1-NEXT: [[TMP33:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX1]], i64 6
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAYIDX1]], [[TMP33]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE11:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK1: omp.arraycpy.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST8:%.*]] = phi %struct.S* [ [[ARRAYIDX1]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT9:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST8]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK1-NEXT: [[TMP34:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST8]] to i8*
|
|
// CHECK1-NEXT: [[TMP35:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP34]], i8* align 4 [[TMP35]], i64 4, i1 false)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT9]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST8]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE10:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT9]], [[TMP33]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE10]], label [[OMP_ARRAYCPY_DONE11]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK1: omp.arraycpy.done11:
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP30]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.case2:
|
|
// CHECK1-NEXT: [[TMP36:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX1]], i64 6
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY12:%.*]] = icmp eq %struct.S* [[ARRAYIDX1]], [[TMP36]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY12]], label [[OMP_ARRAYCPY_DONE20:%.*]], label [[OMP_ARRAYCPY_BODY13:%.*]]
|
|
// CHECK1: omp.arraycpy.body13:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST14:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT18:%.*]], [[OMP_ARRAYCPY_BODY13]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST15:%.*]] = phi %struct.S* [ [[ARRAYIDX1]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT17:%.*]], [[OMP_ARRAYCPY_BODY13]] ]
|
|
// CHECK1-NEXT: [[TMP37:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP38:%.*]] = load i32, i32* [[TMP37]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP38]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[CALL16:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST15]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST14]])
|
|
// CHECK1-NEXT: [[TMP39:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST15]] to i8*
|
|
// CHECK1-NEXT: [[TMP40:%.*]] = bitcast %struct.S* [[CALL16]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP39]], i8* align 4 [[TMP40]], i64 4, i1 false)
|
|
// CHECK1-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP38]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT17]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST15]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT18]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST14]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE19:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT17]], [[TMP36]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE19]], label [[OMP_ARRAYCPY_DONE20]], label [[OMP_ARRAYCPY_BODY13]]
|
|
// CHECK1: omp.arraycpy.done20:
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP30]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.default:
|
|
// CHECK1-NEXT: [[ARRAY_BEGIN21:%.*]] = getelementptr inbounds [1 x [6 x %struct.S]], [1 x [6 x %struct.S]]* [[VAR2]], i32 0, i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP41:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN21]], i64 6
|
|
// CHECK1-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
|
|
// CHECK1: arraydestroy.body:
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP41]], [[DOTOMP_REDUCTION_DEFAULT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
|
|
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN21]]
|
|
// CHECK1-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE22:%.*]], label [[ARRAYDESTROY_BODY]]
|
|
// CHECK1: arraydestroy.done22:
|
|
// CHECK1-NEXT: [[TMP42:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP43:%.*]] = load i32, i32* [[TMP42]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4]], i32 [[TMP43]])
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.10
|
|
// CHECK1-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[TMP11]], i64 6
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[TMP11]], [[TMP12]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE2:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK1: omp.arraycpy.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP8]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP11]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]] to i8*
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP13]], i8* align 4 [[TMP14]], i64 4, i1 false)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP12]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE2]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK1: omp.arraycpy.done2:
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined..11
|
|
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.5* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.5*, align 8
|
|
// CHECK1-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[TMP:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[VAR2:%.*]] = alloca [1 x [6 x %struct.S]], align 16
|
|
// CHECK1-NEXT: [[_TMP4:%.*]] = alloca %struct.S**, align 8
|
|
// CHECK1-NEXT: [[_TMP5:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK1-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store %struct.anon.5* [[__CONTEXT]], %struct.anon.5** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load %struct.anon.5*, %struct.anon.5** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_5:%.*]], %struct.anon.5* [[TMP0]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load %struct.S***, %struct.S**** [[TMP1]], align 8
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = load %struct.S**, %struct.S*** [[TMP2]], align 8
|
|
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds %struct.S*, %struct.S** [[TMP3]], i64 1
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load %struct.S*, %struct.S** [[ARRAYIDX]], align 8
|
|
// CHECK1-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[TMP4]], i64 1
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = load %struct.S**, %struct.S*** [[TMP2]], align 8
|
|
// CHECK1-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds %struct.S*, %struct.S** [[TMP5]], i64 1
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = load %struct.S*, %struct.S** [[ARRAYIDX2]], align 8
|
|
// CHECK1-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP6]], i64 6
|
|
// CHECK1-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [1 x [6 x %struct.S]], [1 x [6 x %struct.S]]* [[VAR2]], i32 0, i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN]], i64 6
|
|
// CHECK1-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAY_BEGIN]], [[TMP7]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
|
|
// CHECK1: omp.arrayinit.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
|
|
// CHECK1-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]])
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP7]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK1: omp.arrayinit.done:
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = load %struct.S**, %struct.S*** [[TMP2]], align 8
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = load %struct.S*, %struct.S** [[TMP8]], align 8
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = ptrtoint %struct.S* [[TMP9]] to i64
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = ptrtoint %struct.S* [[ARRAYIDX1]] to i64
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = sub i64 [[TMP10]], [[TMP11]]
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = sdiv exact i64 [[TMP12]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = bitcast [1 x [6 x %struct.S]]* [[VAR2]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[TMP14]], i64 [[TMP13]]
|
|
// CHECK1-NEXT: store %struct.S** [[_TMP5]], %struct.S*** [[_TMP4]], align 8
|
|
// CHECK1-NEXT: store %struct.S* [[TMP15]], %struct.S** [[_TMP5]], align 8
|
|
// CHECK1-NEXT: [[RHS_BEGIN:%.*]] = bitcast [1 x [6 x %struct.S]]* [[VAR2]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = load i32, i32* [[TMP16]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP17]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK1-NEXT: [[TMP18:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP18]], 9
|
|
// CHECK1-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK1: cond.true:
|
|
// CHECK1-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK1: cond.false:
|
|
// CHECK1-NEXT: [[TMP19:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END]]
|
|
// CHECK1: cond.end:
|
|
// CHECK1-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP19]], [[COND_FALSE]] ]
|
|
// CHECK1-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[TMP20:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 [[TMP20]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK1: omp.inner.for.cond:
|
|
// CHECK1-NEXT: [[TMP21:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP6:%.*]] = icmp sle i32 [[TMP21]], [[TMP22]]
|
|
// CHECK1-NEXT: br i1 [[CMP6]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK1: omp.inner.for.cond.cleanup:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK1: omp.inner.for.body:
|
|
// CHECK1-NEXT: [[TMP23:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP23]], 1
|
|
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK1-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK1: omp.body.continue:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK1: omp.inner.for.inc:
|
|
// CHECK1-NEXT: [[TMP24:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[ADD7:%.*]] = add nsw i32 [[TMP24]], 1
|
|
// CHECK1-NEXT: store i32 [[ADD7]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK1: omp.inner.for.end:
|
|
// CHECK1-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK1: omp.loop.exit:
|
|
// CHECK1-NEXT: [[TMP25:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP26:%.*]] = load i32, i32* [[TMP25]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP26]])
|
|
// CHECK1-NEXT: [[TMP27:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP28:%.*]] = bitcast %struct.S* [[RHS_BEGIN]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP28]], i8** [[TMP27]], align 8
|
|
// CHECK1-NEXT: [[TMP29:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP30:%.*]] = load i32, i32* [[TMP29]], align 4
|
|
// CHECK1-NEXT: [[TMP31:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK1-NEXT: [[TMP32:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP30]], i32 1, i64 8, i8* [[TMP31]], void (i8*, i8*)* @.omp.reduction.reduction_func.12, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: switch i32 [[TMP32]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK1-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK1-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK1-NEXT: ]
|
|
// CHECK1: .omp.reduction.case1:
|
|
// CHECK1-NEXT: [[TMP33:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX1]], i64 6
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAYIDX1]], [[TMP33]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE11:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK1: omp.arraycpy.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST8:%.*]] = phi %struct.S* [ [[ARRAYIDX1]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT9:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST8]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK1-NEXT: [[TMP34:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST8]] to i8*
|
|
// CHECK1-NEXT: [[TMP35:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP34]], i8* align 4 [[TMP35]], i64 4, i1 false)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT9]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST8]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE10:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT9]], [[TMP33]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE10]], label [[OMP_ARRAYCPY_DONE11]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK1: omp.arraycpy.done11:
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP30]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.case2:
|
|
// CHECK1-NEXT: [[TMP36:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX1]], i64 6
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY12:%.*]] = icmp eq %struct.S* [[ARRAYIDX1]], [[TMP36]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY12]], label [[OMP_ARRAYCPY_DONE20:%.*]], label [[OMP_ARRAYCPY_BODY13:%.*]]
|
|
// CHECK1: omp.arraycpy.body13:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST14:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT18:%.*]], [[OMP_ARRAYCPY_BODY13]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST15:%.*]] = phi %struct.S* [ [[ARRAYIDX1]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT17:%.*]], [[OMP_ARRAYCPY_BODY13]] ]
|
|
// CHECK1-NEXT: [[TMP37:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP38:%.*]] = load i32, i32* [[TMP37]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP38]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[CALL16:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST15]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST14]])
|
|
// CHECK1-NEXT: [[TMP39:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST15]] to i8*
|
|
// CHECK1-NEXT: [[TMP40:%.*]] = bitcast %struct.S* [[CALL16]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP39]], i8* align 4 [[TMP40]], i64 4, i1 false)
|
|
// CHECK1-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP38]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT17]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST15]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT18]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST14]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE19:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT17]], [[TMP36]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE19]], label [[OMP_ARRAYCPY_DONE20]], label [[OMP_ARRAYCPY_BODY13]]
|
|
// CHECK1: omp.arraycpy.done20:
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP30]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.default:
|
|
// CHECK1-NEXT: [[ARRAY_BEGIN21:%.*]] = getelementptr inbounds [1 x [6 x %struct.S]], [1 x [6 x %struct.S]]* [[VAR2]], i32 0, i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP41:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN21]], i64 6
|
|
// CHECK1-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
|
|
// CHECK1: arraydestroy.body:
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP41]], [[DOTOMP_REDUCTION_DEFAULT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
|
|
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN21]]
|
|
// CHECK1-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE22:%.*]], label [[ARRAYDESTROY_BODY]]
|
|
// CHECK1: arraydestroy.done22:
|
|
// CHECK1-NEXT: [[TMP42:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP43:%.*]] = load i32, i32* [[TMP42]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4]], i32 [[TMP43]])
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.12
|
|
// CHECK1-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[TMP11]], i64 6
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[TMP11]], [[TMP12]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE2:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK1: omp.arraycpy.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP8]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP11]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]] to i8*
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP13]], i8* align 4 [[TMP14]], i64 4, i1 false)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP12]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE2]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK1: omp.arraycpy.done2:
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined..13
|
|
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.6* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.6*, align 8
|
|
// CHECK1-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[TMP:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[VAR2:%.*]] = alloca [[STRUCT_S:%.*]], align 4
|
|
// CHECK1-NEXT: [[_TMP4:%.*]] = alloca %struct.S**, align 8
|
|
// CHECK1-NEXT: [[_TMP5:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK1-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store %struct.anon.6* [[__CONTEXT]], %struct.anon.6** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load %struct.anon.6*, %struct.anon.6** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_6:%.*]], %struct.anon.6* [[TMP0]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load %struct.S***, %struct.S**** [[TMP1]], align 8
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = load %struct.S**, %struct.S*** [[TMP2]], align 8
|
|
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds %struct.S*, %struct.S** [[TMP3]], i64 1
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load %struct.S*, %struct.S** [[ARRAYIDX]], align 8
|
|
// CHECK1-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP4]], i64 1
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = load %struct.S**, %struct.S*** [[TMP2]], align 8
|
|
// CHECK1-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds %struct.S*, %struct.S** [[TMP5]], i64 1
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = load %struct.S*, %struct.S** [[ARRAYIDX2]], align 8
|
|
// CHECK1-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP6]], i64 1
|
|
// CHECK1-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[VAR2]])
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = load %struct.S**, %struct.S*** [[TMP2]], align 8
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = load %struct.S*, %struct.S** [[TMP7]], align 8
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = ptrtoint %struct.S* [[TMP8]] to i64
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = ptrtoint %struct.S* [[ARRAYIDX1]] to i64
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = sub i64 [[TMP9]], [[TMP10]]
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = sdiv exact i64 [[TMP11]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[VAR2]], i64 [[TMP12]]
|
|
// CHECK1-NEXT: store %struct.S** [[_TMP5]], %struct.S*** [[_TMP4]], align 8
|
|
// CHECK1-NEXT: store %struct.S* [[TMP13]], %struct.S** [[_TMP5]], align 8
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = load i32, i32* [[TMP14]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP15]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP16]], 9
|
|
// CHECK1-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK1: cond.true:
|
|
// CHECK1-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK1: cond.false:
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END]]
|
|
// CHECK1: cond.end:
|
|
// CHECK1-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP17]], [[COND_FALSE]] ]
|
|
// CHECK1-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[TMP18:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 [[TMP18]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK1: omp.inner.for.cond:
|
|
// CHECK1-NEXT: [[TMP19:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[TMP20:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP6:%.*]] = icmp sle i32 [[TMP19]], [[TMP20]]
|
|
// CHECK1-NEXT: br i1 [[CMP6]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK1: omp.inner.for.cond.cleanup:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK1: omp.inner.for.body:
|
|
// CHECK1-NEXT: [[TMP21:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP21]], 1
|
|
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK1-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK1: omp.body.continue:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK1: omp.inner.for.inc:
|
|
// CHECK1-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[ADD7:%.*]] = add nsw i32 [[TMP22]], 1
|
|
// CHECK1-NEXT: store i32 [[ADD7]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK1: omp.inner.for.end:
|
|
// CHECK1-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK1: omp.loop.exit:
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP15]])
|
|
// CHECK1-NEXT: [[TMP23:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP24:%.*]] = bitcast %struct.S* [[VAR2]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP24]], i8** [[TMP23]], align 8
|
|
// CHECK1-NEXT: [[TMP25:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK1-NEXT: [[TMP26:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP15]], i32 1, i64 8, i8* [[TMP25]], void (i8*, i8*)* @.omp.reduction.reduction_func.14, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: switch i32 [[TMP26]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK1-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK1-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK1-NEXT: ]
|
|
// CHECK1: .omp.reduction.case1:
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYIDX1]], %struct.S* nonnull align 4 dereferenceable(4) [[VAR2]])
|
|
// CHECK1-NEXT: [[TMP27:%.*]] = bitcast %struct.S* [[ARRAYIDX1]] to i8*
|
|
// CHECK1-NEXT: [[TMP28:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP27]], i8* align 4 [[TMP28]], i64 4, i1 false)
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP15]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.case2:
|
|
// CHECK1-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP15]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[CALL8:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYIDX1]], %struct.S* nonnull align 4 dereferenceable(4) [[VAR2]])
|
|
// CHECK1-NEXT: [[TMP29:%.*]] = bitcast %struct.S* [[ARRAYIDX1]] to i8*
|
|
// CHECK1-NEXT: [[TMP30:%.*]] = bitcast %struct.S* [[CALL8]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP29]], i8* align 4 [[TMP30]], i64 4, i1 false)
|
|
// CHECK1-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP15]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP15]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.default:
|
|
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[VAR2]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4]], i32 [[TMP15]])
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.14
|
|
// CHECK1-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to %struct.S*
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[TMP11]], %struct.S* nonnull align 4 dereferenceable(4) [[TMP8]])
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = bitcast %struct.S* [[TMP11]] to i8*
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP12]], i8* align 4 [[TMP13]], i64 4, i1 false)
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined..15
|
|
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.7* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.7*, align 8
|
|
// CHECK1-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[TMP:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[VVAR2:%.*]] = alloca [5 x %struct.S], align 16
|
|
// CHECK1-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store %struct.anon.7* [[__CONTEXT]], %struct.anon.7** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load %struct.anon.7*, %struct.anon.7** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_7:%.*]], %struct.anon.7* [[TMP0]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load [5 x %struct.S]*, [5 x %struct.S]** [[TMP1]], align 8
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [5 x %struct.S], [5 x %struct.S]* [[TMP2]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds [5 x %struct.S], [5 x %struct.S]* [[TMP2]], i64 0, i64 4
|
|
// CHECK1-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [5 x %struct.S], [5 x %struct.S]* [[VVAR2]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[ARRAY_BEGIN]], i64 5
|
|
// CHECK1-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAY_BEGIN]], [[TMP3]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
|
|
// CHECK1: omp.arrayinit.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
|
|
// CHECK1-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]])
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP3]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK1: omp.arrayinit.done:
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = bitcast [5 x %struct.S]* [[TMP2]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = ptrtoint %struct.S* [[TMP4]] to i64
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = ptrtoint %struct.S* [[ARRAYIDX]] to i64
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = sub i64 [[TMP5]], [[TMP6]]
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = sdiv exact i64 [[TMP7]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = bitcast [5 x %struct.S]* [[VVAR2]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[TMP9]], i64 [[TMP8]]
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = bitcast %struct.S* [[TMP10]] to [5 x %struct.S]*
|
|
// CHECK1-NEXT: [[RHS_BEGIN:%.*]] = bitcast [5 x %struct.S]* [[VVAR2]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = load i32, i32* [[TMP12]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP13]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP14]], 9
|
|
// CHECK1-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK1: cond.true:
|
|
// CHECK1-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK1: cond.false:
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END]]
|
|
// CHECK1: cond.end:
|
|
// CHECK1-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP15]], [[COND_FALSE]] ]
|
|
// CHECK1-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 [[TMP16]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK1: omp.inner.for.cond:
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[TMP18:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP2:%.*]] = icmp sle i32 [[TMP17]], [[TMP18]]
|
|
// CHECK1-NEXT: br i1 [[CMP2]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK1: omp.inner.for.cond.cleanup:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK1: omp.inner.for.body:
|
|
// CHECK1-NEXT: [[TMP19:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP19]], 1
|
|
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK1-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK1: omp.body.continue:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK1: omp.inner.for.inc:
|
|
// CHECK1-NEXT: [[TMP20:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[ADD3:%.*]] = add nsw i32 [[TMP20]], 1
|
|
// CHECK1-NEXT: store i32 [[ADD3]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK1: omp.inner.for.end:
|
|
// CHECK1-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK1: omp.loop.exit:
|
|
// CHECK1-NEXT: [[TMP21:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP22:%.*]] = load i32, i32* [[TMP21]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP22]])
|
|
// CHECK1-NEXT: [[TMP23:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP24:%.*]] = bitcast %struct.S* [[RHS_BEGIN]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP24]], i8** [[TMP23]], align 8
|
|
// CHECK1-NEXT: [[TMP25:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP26:%.*]] = load i32, i32* [[TMP25]], align 4
|
|
// CHECK1-NEXT: [[TMP27:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK1-NEXT: [[TMP28:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP26]], i32 1, i64 8, i8* [[TMP27]], void (i8*, i8*)* @.omp.reduction.reduction_func.16, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: switch i32 [[TMP28]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK1-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK1-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK1-NEXT: ]
|
|
// CHECK1: .omp.reduction.case1:
|
|
// CHECK1-NEXT: [[TMP29:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX]], i64 5
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAYIDX]], [[TMP29]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE7:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK1: omp.arraycpy.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST4:%.*]] = phi %struct.S* [ [[ARRAYIDX]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT5:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST4]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK1-NEXT: [[TMP30:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST4]] to i8*
|
|
// CHECK1-NEXT: [[TMP31:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP30]], i8* align 4 [[TMP31]], i64 4, i1 false)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT5]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST4]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE6:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT5]], [[TMP29]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE6]], label [[OMP_ARRAYCPY_DONE7]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK1: omp.arraycpy.done7:
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP26]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.case2:
|
|
// CHECK1-NEXT: [[TMP32:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX]], i64 5
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY8:%.*]] = icmp eq %struct.S* [[ARRAYIDX]], [[TMP32]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY8]], label [[OMP_ARRAYCPY_DONE16:%.*]], label [[OMP_ARRAYCPY_BODY9:%.*]]
|
|
// CHECK1: omp.arraycpy.body9:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST10:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT14:%.*]], [[OMP_ARRAYCPY_BODY9]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST11:%.*]] = phi %struct.S* [ [[ARRAYIDX]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT13:%.*]], [[OMP_ARRAYCPY_BODY9]] ]
|
|
// CHECK1-NEXT: [[TMP33:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP34:%.*]] = load i32, i32* [[TMP33]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP34]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[CALL12:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST11]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST10]])
|
|
// CHECK1-NEXT: [[TMP35:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST11]] to i8*
|
|
// CHECK1-NEXT: [[TMP36:%.*]] = bitcast %struct.S* [[CALL12]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP35]], i8* align 4 [[TMP36]], i64 4, i1 false)
|
|
// CHECK1-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP34]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT13]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST11]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT14]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST10]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE15:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT13]], [[TMP32]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE15]], label [[OMP_ARRAYCPY_DONE16]], label [[OMP_ARRAYCPY_BODY9]]
|
|
// CHECK1: omp.arraycpy.done16:
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP26]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.default:
|
|
// CHECK1-NEXT: [[ARRAY_BEGIN17:%.*]] = getelementptr inbounds [5 x %struct.S], [5 x %struct.S]* [[VVAR2]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP37:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN17]], i64 5
|
|
// CHECK1-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
|
|
// CHECK1: arraydestroy.body:
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP37]], [[DOTOMP_REDUCTION_DEFAULT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
|
|
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN17]]
|
|
// CHECK1-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE18:%.*]], label [[ARRAYDESTROY_BODY]]
|
|
// CHECK1: arraydestroy.done18:
|
|
// CHECK1-NEXT: [[TMP38:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP39:%.*]] = load i32, i32* [[TMP38]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4]], i32 [[TMP39]])
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.16
|
|
// CHECK1-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[TMP11]], i64 5
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[TMP11]], [[TMP12]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE2:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK1: omp.arraycpy.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP8]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP11]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]] to i8*
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP13]], i8* align 4 [[TMP14]], i64 4, i1 false)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP12]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE2]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK1: omp.arraycpy.done2:
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined..17
|
|
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.8* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.8*, align 8
|
|
// CHECK1-NEXT: [[TMP:%.*]] = alloca [4 x %struct.S]*, align 8
|
|
// CHECK1-NEXT: [[_TMP1:%.*]] = alloca [4 x %struct.S]*, align 8
|
|
// CHECK1-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[_TMP2:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[VAR3:%.*]] = alloca [2 x %struct.S], align 4
|
|
// CHECK1-NEXT: [[_TMP4:%.*]] = alloca [4 x %struct.S]*, align 8
|
|
// CHECK1-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store %struct.anon.8* [[__CONTEXT]], %struct.anon.8** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load %struct.anon.8*, %struct.anon.8** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_8:%.*]], %struct.anon.8* [[TMP0]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[TMP1]], align 8
|
|
// CHECK1-NEXT: store [4 x %struct.S]* [[TMP2]], [4 x %struct.S]** [[TMP]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[TMP]], align 8
|
|
// CHECK1-NEXT: store [4 x %struct.S]* [[TMP3]], [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [4 x %struct.S], [4 x %struct.S]* [[TMP4]], i64 0, i64 1
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK1-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds [4 x %struct.S], [4 x %struct.S]* [[TMP5]], i64 0, i64 2
|
|
// CHECK1-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[VAR3]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[ARRAY_BEGIN]], i64 2
|
|
// CHECK1-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAY_BEGIN]], [[TMP6]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
|
|
// CHECK1: omp.arrayinit.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
|
|
// CHECK1-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]])
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP6]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK1: omp.arrayinit.done:
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = bitcast [4 x %struct.S]* [[TMP7]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = ptrtoint %struct.S* [[TMP8]] to i64
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = ptrtoint %struct.S* [[ARRAYIDX]] to i64
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = sub i64 [[TMP9]], [[TMP10]]
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = sdiv exact i64 [[TMP11]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = bitcast [2 x %struct.S]* [[VAR3]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[TMP13]], i64 [[TMP12]]
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = bitcast %struct.S* [[TMP14]] to [4 x %struct.S]*
|
|
// CHECK1-NEXT: store [4 x %struct.S]* [[TMP15]], [4 x %struct.S]** [[_TMP4]], align 8
|
|
// CHECK1-NEXT: [[RHS_BEGIN:%.*]] = bitcast [2 x %struct.S]* [[VAR3]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = load i32, i32* [[TMP16]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP17]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK1-NEXT: [[TMP18:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP18]], 9
|
|
// CHECK1-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK1: cond.true:
|
|
// CHECK1-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK1: cond.false:
|
|
// CHECK1-NEXT: [[TMP19:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END]]
|
|
// CHECK1: cond.end:
|
|
// CHECK1-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP19]], [[COND_FALSE]] ]
|
|
// CHECK1-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[TMP20:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 [[TMP20]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK1: omp.inner.for.cond:
|
|
// CHECK1-NEXT: [[TMP21:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP5:%.*]] = icmp sle i32 [[TMP21]], [[TMP22]]
|
|
// CHECK1-NEXT: br i1 [[CMP5]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK1: omp.inner.for.cond.cleanup:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK1: omp.inner.for.body:
|
|
// CHECK1-NEXT: [[TMP23:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP23]], 1
|
|
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK1-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK1: omp.body.continue:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK1: omp.inner.for.inc:
|
|
// CHECK1-NEXT: [[TMP24:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[ADD6:%.*]] = add nsw i32 [[TMP24]], 1
|
|
// CHECK1-NEXT: store i32 [[ADD6]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK1: omp.inner.for.end:
|
|
// CHECK1-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK1: omp.loop.exit:
|
|
// CHECK1-NEXT: [[TMP25:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP26:%.*]] = load i32, i32* [[TMP25]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP26]])
|
|
// CHECK1-NEXT: [[TMP27:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP28:%.*]] = bitcast %struct.S* [[RHS_BEGIN]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP28]], i8** [[TMP27]], align 8
|
|
// CHECK1-NEXT: [[TMP29:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP30:%.*]] = load i32, i32* [[TMP29]], align 4
|
|
// CHECK1-NEXT: [[TMP31:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK1-NEXT: [[TMP32:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP30]], i32 1, i64 8, i8* [[TMP31]], void (i8*, i8*)* @.omp.reduction.reduction_func.18, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: switch i32 [[TMP32]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK1-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK1-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK1-NEXT: ]
|
|
// CHECK1: .omp.reduction.case1:
|
|
// CHECK1-NEXT: [[TMP33:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX]], i64 2
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAYIDX]], [[TMP33]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE10:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK1: omp.arraycpy.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST7:%.*]] = phi %struct.S* [ [[ARRAYIDX]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT8:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST7]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK1-NEXT: [[TMP34:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST7]] to i8*
|
|
// CHECK1-NEXT: [[TMP35:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP34]], i8* align 4 [[TMP35]], i64 4, i1 false)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT8]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST7]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE9:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT8]], [[TMP33]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE9]], label [[OMP_ARRAYCPY_DONE10]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK1: omp.arraycpy.done10:
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP30]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.case2:
|
|
// CHECK1-NEXT: [[TMP36:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX]], i64 2
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY11:%.*]] = icmp eq %struct.S* [[ARRAYIDX]], [[TMP36]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY11]], label [[OMP_ARRAYCPY_DONE19:%.*]], label [[OMP_ARRAYCPY_BODY12:%.*]]
|
|
// CHECK1: omp.arraycpy.body12:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST13:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT17:%.*]], [[OMP_ARRAYCPY_BODY12]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST14:%.*]] = phi %struct.S* [ [[ARRAYIDX]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT16:%.*]], [[OMP_ARRAYCPY_BODY12]] ]
|
|
// CHECK1-NEXT: [[TMP37:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP38:%.*]] = load i32, i32* [[TMP37]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP38]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[CALL15:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST14]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST13]])
|
|
// CHECK1-NEXT: [[TMP39:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST14]] to i8*
|
|
// CHECK1-NEXT: [[TMP40:%.*]] = bitcast %struct.S* [[CALL15]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP39]], i8* align 4 [[TMP40]], i64 4, i1 false)
|
|
// CHECK1-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP38]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT16]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST14]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT17]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST13]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE18:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT16]], [[TMP36]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE18]], label [[OMP_ARRAYCPY_DONE19]], label [[OMP_ARRAYCPY_BODY12]]
|
|
// CHECK1: omp.arraycpy.done19:
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP30]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.default:
|
|
// CHECK1-NEXT: [[ARRAY_BEGIN20:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[VAR3]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP41:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN20]], i64 2
|
|
// CHECK1-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
|
|
// CHECK1: arraydestroy.body:
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP41]], [[DOTOMP_REDUCTION_DEFAULT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
|
|
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN20]]
|
|
// CHECK1-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE21:%.*]], label [[ARRAYDESTROY_BODY]]
|
|
// CHECK1: arraydestroy.done21:
|
|
// CHECK1-NEXT: [[TMP42:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP43:%.*]] = load i32, i32* [[TMP42]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4]], i32 [[TMP43]])
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.18
|
|
// CHECK1-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[TMP11]], i64 2
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[TMP11]], [[TMP12]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE2:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK1: omp.arraycpy.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP8]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP11]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]] to i8*
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP13]], i8* align 4 [[TMP14]], i64 4, i1 false)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP12]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE2]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK1: omp.arraycpy.done2:
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined..19
|
|
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.9* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.9*, align 8
|
|
// CHECK1-NEXT: [[TMP:%.*]] = alloca [4 x %struct.S]*, align 8
|
|
// CHECK1-NEXT: [[_TMP1:%.*]] = alloca [4 x %struct.S]*, align 8
|
|
// CHECK1-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[_TMP2:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[VAR3:%.*]] = alloca [2 x %struct.S], align 4
|
|
// CHECK1-NEXT: [[_TMP4:%.*]] = alloca [4 x %struct.S]*, align 8
|
|
// CHECK1-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store %struct.anon.9* [[__CONTEXT]], %struct.anon.9** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load %struct.anon.9*, %struct.anon.9** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_9:%.*]], %struct.anon.9* [[TMP0]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[TMP1]], align 8
|
|
// CHECK1-NEXT: store [4 x %struct.S]* [[TMP2]], [4 x %struct.S]** [[TMP]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[TMP]], align 8
|
|
// CHECK1-NEXT: store [4 x %struct.S]* [[TMP3]], [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [4 x %struct.S], [4 x %struct.S]* [[TMP4]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK1-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds [4 x %struct.S], [4 x %struct.S]* [[TMP5]], i64 0, i64 1
|
|
// CHECK1-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[VAR3]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[ARRAY_BEGIN]], i64 2
|
|
// CHECK1-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAY_BEGIN]], [[TMP6]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
|
|
// CHECK1: omp.arrayinit.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
|
|
// CHECK1-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]])
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP6]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK1: omp.arrayinit.done:
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = bitcast [4 x %struct.S]* [[TMP7]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = ptrtoint %struct.S* [[TMP8]] to i64
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = ptrtoint %struct.S* [[ARRAYIDX]] to i64
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = sub i64 [[TMP9]], [[TMP10]]
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = sdiv exact i64 [[TMP11]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = bitcast [2 x %struct.S]* [[VAR3]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[TMP13]], i64 [[TMP12]]
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = bitcast %struct.S* [[TMP14]] to [4 x %struct.S]*
|
|
// CHECK1-NEXT: store [4 x %struct.S]* [[TMP15]], [4 x %struct.S]** [[_TMP4]], align 8
|
|
// CHECK1-NEXT: [[RHS_BEGIN:%.*]] = bitcast [2 x %struct.S]* [[VAR3]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = load i32, i32* [[TMP16]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP17]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK1-NEXT: [[TMP18:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP18]], 9
|
|
// CHECK1-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK1: cond.true:
|
|
// CHECK1-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK1: cond.false:
|
|
// CHECK1-NEXT: [[TMP19:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END]]
|
|
// CHECK1: cond.end:
|
|
// CHECK1-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP19]], [[COND_FALSE]] ]
|
|
// CHECK1-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[TMP20:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 [[TMP20]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK1: omp.inner.for.cond:
|
|
// CHECK1-NEXT: [[TMP21:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP5:%.*]] = icmp sle i32 [[TMP21]], [[TMP22]]
|
|
// CHECK1-NEXT: br i1 [[CMP5]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK1: omp.inner.for.cond.cleanup:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK1: omp.inner.for.body:
|
|
// CHECK1-NEXT: [[TMP23:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP23]], 1
|
|
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK1-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK1: omp.body.continue:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK1: omp.inner.for.inc:
|
|
// CHECK1-NEXT: [[TMP24:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[ADD6:%.*]] = add nsw i32 [[TMP24]], 1
|
|
// CHECK1-NEXT: store i32 [[ADD6]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK1: omp.inner.for.end:
|
|
// CHECK1-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK1: omp.loop.exit:
|
|
// CHECK1-NEXT: [[TMP25:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP26:%.*]] = load i32, i32* [[TMP25]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP26]])
|
|
// CHECK1-NEXT: [[TMP27:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP28:%.*]] = bitcast %struct.S* [[RHS_BEGIN]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP28]], i8** [[TMP27]], align 8
|
|
// CHECK1-NEXT: [[TMP29:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP30:%.*]] = load i32, i32* [[TMP29]], align 4
|
|
// CHECK1-NEXT: [[TMP31:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK1-NEXT: [[TMP32:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP30]], i32 1, i64 8, i8* [[TMP31]], void (i8*, i8*)* @.omp.reduction.reduction_func.20, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: switch i32 [[TMP32]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK1-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK1-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK1-NEXT: ]
|
|
// CHECK1: .omp.reduction.case1:
|
|
// CHECK1-NEXT: [[TMP33:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX]], i64 2
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAYIDX]], [[TMP33]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE10:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK1: omp.arraycpy.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST7:%.*]] = phi %struct.S* [ [[ARRAYIDX]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT8:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST7]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK1-NEXT: [[TMP34:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST7]] to i8*
|
|
// CHECK1-NEXT: [[TMP35:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP34]], i8* align 4 [[TMP35]], i64 4, i1 false)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT8]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST7]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE9:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT8]], [[TMP33]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE9]], label [[OMP_ARRAYCPY_DONE10]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK1: omp.arraycpy.done10:
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP30]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.case2:
|
|
// CHECK1-NEXT: [[TMP36:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX]], i64 2
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY11:%.*]] = icmp eq %struct.S* [[ARRAYIDX]], [[TMP36]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY11]], label [[OMP_ARRAYCPY_DONE19:%.*]], label [[OMP_ARRAYCPY_BODY12:%.*]]
|
|
// CHECK1: omp.arraycpy.body12:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST13:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT17:%.*]], [[OMP_ARRAYCPY_BODY12]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST14:%.*]] = phi %struct.S* [ [[ARRAYIDX]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT16:%.*]], [[OMP_ARRAYCPY_BODY12]] ]
|
|
// CHECK1-NEXT: [[TMP37:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP38:%.*]] = load i32, i32* [[TMP37]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP38]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[CALL15:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST14]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST13]])
|
|
// CHECK1-NEXT: [[TMP39:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST14]] to i8*
|
|
// CHECK1-NEXT: [[TMP40:%.*]] = bitcast %struct.S* [[CALL15]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP39]], i8* align 4 [[TMP40]], i64 4, i1 false)
|
|
// CHECK1-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP38]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT16]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST14]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT17]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST13]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE18:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT16]], [[TMP36]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE18]], label [[OMP_ARRAYCPY_DONE19]], label [[OMP_ARRAYCPY_BODY12]]
|
|
// CHECK1: omp.arraycpy.done19:
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP30]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.default:
|
|
// CHECK1-NEXT: [[ARRAY_BEGIN20:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[VAR3]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP41:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN20]], i64 2
|
|
// CHECK1-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
|
|
// CHECK1: arraydestroy.body:
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP41]], [[DOTOMP_REDUCTION_DEFAULT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
|
|
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN20]]
|
|
// CHECK1-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE21:%.*]], label [[ARRAYDESTROY_BODY]]
|
|
// CHECK1: arraydestroy.done21:
|
|
// CHECK1-NEXT: [[TMP42:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP43:%.*]] = load i32, i32* [[TMP42]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4]], i32 [[TMP43]])
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.20
|
|
// CHECK1-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[TMP11]], i64 2
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[TMP11]], [[TMP12]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE2:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK1: omp.arraycpy.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP8]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP11]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]] to i8*
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP13]], i8* align 4 [[TMP14]], i64 4, i1 false)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP12]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE2]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK1: omp.arraycpy.done2:
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined..21
|
|
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.10* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.10*, align 8
|
|
// CHECK1-NEXT: [[TMP:%.*]] = alloca [4 x %struct.S]*, align 8
|
|
// CHECK1-NEXT: [[_TMP1:%.*]] = alloca [4 x %struct.S]*, align 8
|
|
// CHECK1-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[_TMP2:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[SAVED_STACK:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: [[__VLA_EXPR0:%.*]] = alloca i64, align 8
|
|
// CHECK1-NEXT: [[_TMP4:%.*]] = alloca [4 x %struct.S]*, align 8
|
|
// CHECK1-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [2 x i8*], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store %struct.anon.10* [[__CONTEXT]], %struct.anon.10** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load %struct.anon.10*, %struct.anon.10** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_10:%.*]], %struct.anon.10* [[TMP0]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[TMP1]], align 8
|
|
// CHECK1-NEXT: store [4 x %struct.S]* [[TMP2]], [4 x %struct.S]** [[TMP]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[TMP]], align 8
|
|
// CHECK1-NEXT: store [4 x %struct.S]* [[TMP3]], [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [4 x %struct.S], [4 x %struct.S]* [[TMP4]], i64 0, i64 2
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK1-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds [4 x %struct.S], [4 x %struct.S]* [[TMP5]], i64 0, i64 3
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = ptrtoint %struct.S* [[ARRAYIDX3]] to i64
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = ptrtoint %struct.S* [[ARRAYIDX]] to i64
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = sub i64 [[TMP6]], [[TMP7]]
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = sdiv exact i64 [[TMP8]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = add nuw i64 [[TMP9]], 1
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = mul nuw i64 [[TMP10]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = call i8* @llvm.stacksave()
|
|
// CHECK1-NEXT: store i8* [[TMP12]], i8** [[SAVED_STACK]], align 8
|
|
// CHECK1-NEXT: [[VLA:%.*]] = alloca [[STRUCT_S:%.*]], i64 [[TMP10]], align 16
|
|
// CHECK1-NEXT: store i64 [[TMP10]], i64* [[__VLA_EXPR0]], align 8
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[VLA]], i64 [[TMP10]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq %struct.S* [[VLA]], [[TMP13]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
|
|
// CHECK1: omp.arrayinit.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[VLA]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
|
|
// CHECK1-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]])
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP13]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK1: omp.arrayinit.done:
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = bitcast [4 x %struct.S]* [[TMP14]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = ptrtoint %struct.S* [[TMP15]] to i64
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = ptrtoint %struct.S* [[ARRAYIDX]] to i64
|
|
// CHECK1-NEXT: [[TMP18:%.*]] = sub i64 [[TMP16]], [[TMP17]]
|
|
// CHECK1-NEXT: [[TMP19:%.*]] = sdiv exact i64 [[TMP18]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[TMP20:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[VLA]], i64 [[TMP19]]
|
|
// CHECK1-NEXT: [[TMP21:%.*]] = bitcast %struct.S* [[TMP20]] to [4 x %struct.S]*
|
|
// CHECK1-NEXT: store [4 x %struct.S]* [[TMP21]], [4 x %struct.S]** [[_TMP4]], align 8
|
|
// CHECK1-NEXT: [[TMP22:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP23:%.*]] = load i32, i32* [[TMP22]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP23]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK1-NEXT: [[TMP24:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP24]], 9
|
|
// CHECK1-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK1: cond.true:
|
|
// CHECK1-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK1: cond.false:
|
|
// CHECK1-NEXT: [[TMP25:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END]]
|
|
// CHECK1: cond.end:
|
|
// CHECK1-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP25]], [[COND_FALSE]] ]
|
|
// CHECK1-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[TMP26:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 [[TMP26]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK1: omp.inner.for.cond:
|
|
// CHECK1-NEXT: [[TMP27:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[TMP28:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP5:%.*]] = icmp sle i32 [[TMP27]], [[TMP28]]
|
|
// CHECK1-NEXT: br i1 [[CMP5]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK1: omp.inner.for.cond.cleanup:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK1: omp.inner.for.body:
|
|
// CHECK1-NEXT: [[TMP29:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP29]], 1
|
|
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK1-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK1: omp.body.continue:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK1: omp.inner.for.inc:
|
|
// CHECK1-NEXT: [[TMP30:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[ADD6:%.*]] = add nsw i32 [[TMP30]], 1
|
|
// CHECK1-NEXT: store i32 [[ADD6]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK1: omp.inner.for.end:
|
|
// CHECK1-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK1: omp.loop.exit:
|
|
// CHECK1-NEXT: [[TMP31:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP32:%.*]] = load i32, i32* [[TMP31]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP32]])
|
|
// CHECK1-NEXT: [[TMP33:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP34:%.*]] = bitcast %struct.S* [[VLA]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP34]], i8** [[TMP33]], align 8
|
|
// CHECK1-NEXT: [[TMP35:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 1
|
|
// CHECK1-NEXT: [[TMP36:%.*]] = inttoptr i64 [[TMP10]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP36]], i8** [[TMP35]], align 8
|
|
// CHECK1-NEXT: [[TMP37:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP38:%.*]] = load i32, i32* [[TMP37]], align 4
|
|
// CHECK1-NEXT: [[TMP39:%.*]] = bitcast [2 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK1-NEXT: [[TMP40:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP38]], i32 1, i64 16, i8* [[TMP39]], void (i8*, i8*)* @.omp.reduction.reduction_func.22, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: switch i32 [[TMP40]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK1-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK1-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK1-NEXT: ]
|
|
// CHECK1: .omp.reduction.case1:
|
|
// CHECK1-NEXT: [[TMP41:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX]], i64 [[TMP10]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAYIDX]], [[TMP41]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE10:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK1: omp.arraycpy.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[VLA]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST7:%.*]] = phi %struct.S* [ [[ARRAYIDX]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT8:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST7]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK1-NEXT: [[TMP42:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST7]] to i8*
|
|
// CHECK1-NEXT: [[TMP43:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP42]], i8* align 4 [[TMP43]], i64 4, i1 false)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT8]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST7]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE9:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT8]], [[TMP41]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE9]], label [[OMP_ARRAYCPY_DONE10]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK1: omp.arraycpy.done10:
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP38]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.case2:
|
|
// CHECK1-NEXT: [[TMP44:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX]], i64 [[TMP10]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY11:%.*]] = icmp eq %struct.S* [[ARRAYIDX]], [[TMP44]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY11]], label [[OMP_ARRAYCPY_DONE19:%.*]], label [[OMP_ARRAYCPY_BODY12:%.*]]
|
|
// CHECK1: omp.arraycpy.body12:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST13:%.*]] = phi %struct.S* [ [[VLA]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT17:%.*]], [[OMP_ARRAYCPY_BODY12]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST14:%.*]] = phi %struct.S* [ [[ARRAYIDX]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT16:%.*]], [[OMP_ARRAYCPY_BODY12]] ]
|
|
// CHECK1-NEXT: [[TMP45:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP46:%.*]] = load i32, i32* [[TMP45]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP46]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[CALL15:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST14]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST13]])
|
|
// CHECK1-NEXT: [[TMP47:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST14]] to i8*
|
|
// CHECK1-NEXT: [[TMP48:%.*]] = bitcast %struct.S* [[CALL15]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP47]], i8* align 4 [[TMP48]], i64 4, i1 false)
|
|
// CHECK1-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP46]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT16]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST14]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT17]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST13]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE18:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT16]], [[TMP44]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE18]], label [[OMP_ARRAYCPY_DONE19]], label [[OMP_ARRAYCPY_BODY12]]
|
|
// CHECK1: omp.arraycpy.done19:
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP38]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.default:
|
|
// CHECK1-NEXT: [[TMP49:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[VLA]], i64 [[TMP10]]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ISEMPTY:%.*]] = icmp eq %struct.S* [[VLA]], [[TMP49]]
|
|
// CHECK1-NEXT: br i1 [[ARRAYDESTROY_ISEMPTY]], label [[ARRAYDESTROY_DONE20:%.*]], label [[ARRAYDESTROY_BODY:%.*]]
|
|
// CHECK1: arraydestroy.body:
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP49]], [[DOTOMP_REDUCTION_DEFAULT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
|
|
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[VLA]]
|
|
// CHECK1-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE20]], label [[ARRAYDESTROY_BODY]]
|
|
// CHECK1: arraydestroy.done20:
|
|
// CHECK1-NEXT: [[TMP50:%.*]] = load i8*, i8** [[SAVED_STACK]], align 8
|
|
// CHECK1-NEXT: call void @llvm.stackrestore(i8* [[TMP50]])
|
|
// CHECK1-NEXT: [[TMP51:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP52:%.*]] = load i32, i32* [[TMP51]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4]], i32 [[TMP52]])
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.22
|
|
// CHECK1-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [2 x i8*]*
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [2 x i8*]*
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[TMP3]], i64 0, i64 1
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = load i8*, i8** [[TMP12]], align 8
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = ptrtoint i8* [[TMP13]] to i64
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[TMP11]], i64 [[TMP14]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[TMP11]], [[TMP15]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE2:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK1: omp.arraycpy.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP8]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP11]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]] to i8*
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP16]], i8* align 4 [[TMP17]], i64 4, i1 false)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP15]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE2]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK1: omp.arraycpy.done2:
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined..23
|
|
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.11* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.11*, align 8
|
|
// CHECK1-NEXT: [[TMP:%.*]] = alloca [4 x %struct.S]*, align 8
|
|
// CHECK1-NEXT: [[_TMP1:%.*]] = alloca [4 x %struct.S]*, align 8
|
|
// CHECK1-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[_TMP2:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[VAR3:%.*]] = alloca [4 x %struct.S], align 16
|
|
// CHECK1-NEXT: [[_TMP3:%.*]] = alloca [4 x %struct.S]*, align 8
|
|
// CHECK1-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store %struct.anon.11* [[__CONTEXT]], %struct.anon.11** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load %struct.anon.11*, %struct.anon.11** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_11:%.*]], %struct.anon.11* [[TMP0]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[TMP1]], align 8
|
|
// CHECK1-NEXT: store [4 x %struct.S]* [[TMP2]], [4 x %struct.S]** [[TMP]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[TMP]], align 8
|
|
// CHECK1-NEXT: store [4 x %struct.S]* [[TMP3]], [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK1-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [4 x %struct.S], [4 x %struct.S]* [[VAR3]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[ARRAY_BEGIN]], i64 4
|
|
// CHECK1-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAY_BEGIN]], [[TMP5]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
|
|
// CHECK1: omp.arrayinit.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
|
|
// CHECK1-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]])
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP5]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK1: omp.arrayinit.done:
|
|
// CHECK1-NEXT: store [4 x %struct.S]* [[VAR3]], [4 x %struct.S]** [[_TMP3]], align 8
|
|
// CHECK1-NEXT: [[LHS_BEGIN:%.*]] = bitcast [4 x %struct.S]* [[TMP4]] to %struct.S*
|
|
// CHECK1-NEXT: [[RHS_BEGIN:%.*]] = bitcast [4 x %struct.S]* [[VAR3]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = load i32, i32* [[TMP6]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP7]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP8]], 9
|
|
// CHECK1-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK1: cond.true:
|
|
// CHECK1-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK1: cond.false:
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END]]
|
|
// CHECK1: cond.end:
|
|
// CHECK1-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP9]], [[COND_FALSE]] ]
|
|
// CHECK1-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 [[TMP10]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK1: omp.inner.for.cond:
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP4:%.*]] = icmp sle i32 [[TMP11]], [[TMP12]]
|
|
// CHECK1-NEXT: br i1 [[CMP4]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK1: omp.inner.for.cond.cleanup:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK1: omp.inner.for.body:
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP13]], 1
|
|
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK1-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK1: omp.body.continue:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK1: omp.inner.for.inc:
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[ADD5:%.*]] = add nsw i32 [[TMP14]], 1
|
|
// CHECK1-NEXT: store i32 [[ADD5]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK1: omp.inner.for.end:
|
|
// CHECK1-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK1: omp.loop.exit:
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = load i32, i32* [[TMP15]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP16]])
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP18:%.*]] = bitcast %struct.S* [[RHS_BEGIN]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP18]], i8** [[TMP17]], align 8
|
|
// CHECK1-NEXT: [[TMP19:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP20:%.*]] = load i32, i32* [[TMP19]], align 4
|
|
// CHECK1-NEXT: [[TMP21:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK1-NEXT: [[TMP22:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP20]], i32 1, i64 8, i8* [[TMP21]], void (i8*, i8*)* @.omp.reduction.reduction_func.24, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: switch i32 [[TMP22]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK1-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK1-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK1-NEXT: ]
|
|
// CHECK1: .omp.reduction.case1:
|
|
// CHECK1-NEXT: [[TMP23:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[LHS_BEGIN]], i64 4
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[LHS_BEGIN]], [[TMP23]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE9:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK1: omp.arraycpy.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST6:%.*]] = phi %struct.S* [ [[LHS_BEGIN]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT7:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST6]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK1-NEXT: [[TMP24:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST6]] to i8*
|
|
// CHECK1-NEXT: [[TMP25:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP24]], i8* align 4 [[TMP25]], i64 4, i1 false)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT7]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST6]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE8:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT7]], [[TMP23]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE8]], label [[OMP_ARRAYCPY_DONE9]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK1: omp.arraycpy.done9:
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP20]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.case2:
|
|
// CHECK1-NEXT: [[TMP26:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[LHS_BEGIN]], i64 4
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY10:%.*]] = icmp eq %struct.S* [[LHS_BEGIN]], [[TMP26]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY10]], label [[OMP_ARRAYCPY_DONE18:%.*]], label [[OMP_ARRAYCPY_BODY11:%.*]]
|
|
// CHECK1: omp.arraycpy.body11:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST12:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT16:%.*]], [[OMP_ARRAYCPY_BODY11]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST13:%.*]] = phi %struct.S* [ [[LHS_BEGIN]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT15:%.*]], [[OMP_ARRAYCPY_BODY11]] ]
|
|
// CHECK1-NEXT: [[TMP27:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP28:%.*]] = load i32, i32* [[TMP27]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP28]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[CALL14:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST13]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST12]])
|
|
// CHECK1-NEXT: [[TMP29:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST13]] to i8*
|
|
// CHECK1-NEXT: [[TMP30:%.*]] = bitcast %struct.S* [[CALL14]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP29]], i8* align 4 [[TMP30]], i64 4, i1 false)
|
|
// CHECK1-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP28]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT15]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST13]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT16]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST12]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE17:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT15]], [[TMP26]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE17]], label [[OMP_ARRAYCPY_DONE18]], label [[OMP_ARRAYCPY_BODY11]]
|
|
// CHECK1: omp.arraycpy.done18:
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP20]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.default:
|
|
// CHECK1-NEXT: [[ARRAY_BEGIN19:%.*]] = getelementptr inbounds [4 x %struct.S], [4 x %struct.S]* [[VAR3]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP31:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN19]], i64 4
|
|
// CHECK1-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
|
|
// CHECK1: arraydestroy.body:
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP31]], [[DOTOMP_REDUCTION_DEFAULT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
|
|
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN19]]
|
|
// CHECK1-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE20:%.*]], label [[ARRAYDESTROY_BODY]]
|
|
// CHECK1: arraydestroy.done20:
|
|
// CHECK1-NEXT: [[TMP32:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP33:%.*]] = load i32, i32* [[TMP32]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4]], i32 [[TMP33]])
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.24
|
|
// CHECK1-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to %struct.S*
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[TMP11]], i64 4
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[TMP11]], [[TMP12]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE2:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK1: omp.arraycpy.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP8]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP11]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]] to i8*
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP13]], i8* align 4 [[TMP14]], i64 4, i1 false)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP12]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE2]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK1: omp.arraycpy.done2:
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@_Z5tmainIiLi42EET_v
|
|
// CHECK1-SAME: () #[[ATTR7]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[T:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[TEST:%.*]] = alloca [[STRUCT_S_12:%.*]], align 4
|
|
// CHECK1-NEXT: [[T_VAR:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[T_VAR1:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[VEC:%.*]] = alloca [2 x i32], align 4
|
|
// CHECK1-NEXT: [[S_ARR:%.*]] = alloca [2 x %struct.S.12], align 4
|
|
// CHECK1-NEXT: [[VAR:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK1-NEXT: [[VAR1:%.*]] = alloca [[STRUCT_S_12]], align 4
|
|
// CHECK1-NEXT: [[ARR:%.*]] = alloca [42 x %struct.S.12], align 16
|
|
// CHECK1-NEXT: [[OMP_OUTLINED_ARG_AGG_:%.*]] = alloca [[STRUCT_ANON_13:%.*]], align 8
|
|
// CHECK1-NEXT: [[OMP_OUTLINED_ARG_AGG_1:%.*]] = alloca [[STRUCT_ANON_14:%.*]], align 8
|
|
// CHECK1-NEXT: [[OMP_OUTLINED_ARG_AGG_2:%.*]] = alloca [[STRUCT_ANON_15:%.*]], align 8
|
|
// CHECK1-NEXT: call void @_ZN1SIiEC1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[TEST]])
|
|
// CHECK1-NEXT: store i32 0, i32* [[T_VAR]], align 4
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = bitcast [2 x i32]* [[VEC]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP0]], i8* align 4 bitcast ([2 x i32]* @__const._Z5tmainIiLi42EET_v.vec to i8*), i64 8, i1 false)
|
|
// CHECK1-NEXT: [[ARRAYINIT_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S.12], [2 x %struct.S.12]* [[S_ARR]], i64 0, i64 0
|
|
// CHECK1-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.12* nonnull align 4 dereferenceable(4) [[ARRAYINIT_BEGIN]], i32 1)
|
|
// CHECK1-NEXT: [[ARRAYINIT_ELEMENT:%.*]] = getelementptr inbounds [[STRUCT_S_12]], %struct.S.12* [[ARRAYINIT_BEGIN]], i64 1
|
|
// CHECK1-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.12* nonnull align 4 dereferenceable(4) [[ARRAYINIT_ELEMENT]], i32 2)
|
|
// CHECK1-NEXT: store %struct.S.12* [[TEST]], %struct.S.12** [[VAR]], align 8
|
|
// CHECK1-NEXT: call void @_ZN1SIiEC1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[VAR1]])
|
|
// CHECK1-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [42 x %struct.S.12], [42 x %struct.S.12]* [[ARR]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[ARRAYCTOR_END:%.*]] = getelementptr inbounds [[STRUCT_S_12]], %struct.S.12* [[ARRAY_BEGIN]], i64 42
|
|
// CHECK1-NEXT: br label [[ARRAYCTOR_LOOP:%.*]]
|
|
// CHECK1: arrayctor.loop:
|
|
// CHECK1-NEXT: [[ARRAYCTOR_CUR:%.*]] = phi %struct.S.12* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[ARRAYCTOR_NEXT:%.*]], [[ARRAYCTOR_LOOP]] ]
|
|
// CHECK1-NEXT: call void @_ZN1SIiEC1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[ARRAYCTOR_CUR]])
|
|
// CHECK1-NEXT: [[ARRAYCTOR_NEXT]] = getelementptr inbounds [[STRUCT_S_12]], %struct.S.12* [[ARRAYCTOR_CUR]], i64 1
|
|
// CHECK1-NEXT: [[ARRAYCTOR_DONE:%.*]] = icmp eq %struct.S.12* [[ARRAYCTOR_NEXT]], [[ARRAYCTOR_END]]
|
|
// CHECK1-NEXT: br i1 [[ARRAYCTOR_DONE]], label [[ARRAYCTOR_CONT:%.*]], label [[ARRAYCTOR_LOOP]]
|
|
// CHECK1: arrayctor.cont:
|
|
// CHECK1-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_13]], %struct.anon.13* [[OMP_OUTLINED_ARG_AGG_]], i32 0, i32 0
|
|
// CHECK1-NEXT: store i32* [[T_VAR]], i32** [[TMP1]], align 8
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = getelementptr inbounds [[STRUCT_ANON_13]], %struct.anon.13* [[OMP_OUTLINED_ARG_AGG_]], i32 0, i32 1
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = load %struct.S.12*, %struct.S.12** [[VAR]], align 8
|
|
// CHECK1-NEXT: store %struct.S.12* [[TMP3]], %struct.S.12** [[TMP2]], align 8
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_ANON_13]], %struct.anon.13* [[OMP_OUTLINED_ARG_AGG_]], i32 0, i32 2
|
|
// CHECK1-NEXT: store %struct.S.12* [[VAR1]], %struct.S.12** [[TMP4]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_ANON_13]], %struct.anon.13* [[OMP_OUTLINED_ARG_AGG_]], i32 0, i32 3
|
|
// CHECK1-NEXT: store i32* [[T_VAR1]], i32** [[TMP5]], align 8
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_ANON_13]], %struct.anon.13* [[OMP_OUTLINED_ARG_AGG_]], i32 0, i32 4
|
|
// CHECK1-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[TMP6]], align 8
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = getelementptr inbounds [[STRUCT_ANON_13]], %struct.anon.13* [[OMP_OUTLINED_ARG_AGG_]], i32 0, i32 5
|
|
// CHECK1-NEXT: store [2 x %struct.S.12]* [[S_ARR]], [2 x %struct.S.12]** [[TMP7]], align 8
|
|
// CHECK1-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.13*)* @.omp_outlined..25 to void (i32*, i32*, ...)*), %struct.anon.13* [[OMP_OUTLINED_ARG_AGG_]])
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = getelementptr inbounds [[STRUCT_ANON_14]], %struct.anon.14* [[OMP_OUTLINED_ARG_AGG_1]], i32 0, i32 0
|
|
// CHECK1-NEXT: store i32* [[T_VAR]], i32** [[TMP8]], align 8
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_ANON_14]], %struct.anon.14* [[OMP_OUTLINED_ARG_AGG_1]], i32 0, i32 1
|
|
// CHECK1-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[TMP9]], align 8
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = getelementptr inbounds [[STRUCT_ANON_14]], %struct.anon.14* [[OMP_OUTLINED_ARG_AGG_1]], i32 0, i32 2
|
|
// CHECK1-NEXT: store [2 x %struct.S.12]* [[S_ARR]], [2 x %struct.S.12]** [[TMP10]], align 8
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = getelementptr inbounds [[STRUCT_ANON_14]], %struct.anon.14* [[OMP_OUTLINED_ARG_AGG_1]], i32 0, i32 3
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = load %struct.S.12*, %struct.S.12** [[VAR]], align 8
|
|
// CHECK1-NEXT: store %struct.S.12* [[TMP12]], %struct.S.12** [[TMP11]], align 8
|
|
// CHECK1-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.14*)* @.omp_outlined..27 to void (i32*, i32*, ...)*), %struct.anon.14* [[OMP_OUTLINED_ARG_AGG_1]])
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = getelementptr inbounds [[STRUCT_ANON_15]], %struct.anon.15* [[OMP_OUTLINED_ARG_AGG_2]], i32 0, i32 0
|
|
// CHECK1-NEXT: store [42 x %struct.S.12]* [[ARR]], [42 x %struct.S.12]** [[TMP13]], align 8
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = getelementptr inbounds [[STRUCT_ANON_15]], %struct.anon.15* [[OMP_OUTLINED_ARG_AGG_2]], i32 0, i32 1
|
|
// CHECK1-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[TMP14]], align 8
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = getelementptr inbounds [[STRUCT_ANON_15]], %struct.anon.15* [[OMP_OUTLINED_ARG_AGG_2]], i32 0, i32 2
|
|
// CHECK1-NEXT: store i32* [[T_VAR]], i32** [[TMP15]], align 8
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = getelementptr inbounds [[STRUCT_ANON_15]], %struct.anon.15* [[OMP_OUTLINED_ARG_AGG_2]], i32 0, i32 3
|
|
// CHECK1-NEXT: store [2 x %struct.S.12]* [[S_ARR]], [2 x %struct.S.12]** [[TMP16]], align 8
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = getelementptr inbounds [[STRUCT_ANON_15]], %struct.anon.15* [[OMP_OUTLINED_ARG_AGG_2]], i32 0, i32 4
|
|
// CHECK1-NEXT: [[TMP18:%.*]] = load %struct.S.12*, %struct.S.12** [[VAR]], align 8
|
|
// CHECK1-NEXT: store %struct.S.12* [[TMP18]], %struct.S.12** [[TMP17]], align 8
|
|
// CHECK1-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.15*)* @.omp_outlined..29 to void (i32*, i32*, ...)*), %struct.anon.15* [[OMP_OUTLINED_ARG_AGG_2]])
|
|
// CHECK1-NEXT: store i32 0, i32* [[RETVAL]], align 4
|
|
// CHECK1-NEXT: [[ARRAY_BEGIN3:%.*]] = getelementptr inbounds [42 x %struct.S.12], [42 x %struct.S.12]* [[ARR]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP19:%.*]] = getelementptr inbounds [[STRUCT_S_12]], %struct.S.12* [[ARRAY_BEGIN3]], i64 42
|
|
// CHECK1-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
|
|
// CHECK1: arraydestroy.body:
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S.12* [ [[TMP19]], [[ARRAYCTOR_CONT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S_12]], %struct.S.12* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
|
|
// CHECK1-NEXT: call void @_ZN1SIiED1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S.12* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN3]]
|
|
// CHECK1-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE4:%.*]], label [[ARRAYDESTROY_BODY]]
|
|
// CHECK1: arraydestroy.done4:
|
|
// CHECK1-NEXT: call void @_ZN1SIiED1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[VAR1]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: [[ARRAY_BEGIN5:%.*]] = getelementptr inbounds [2 x %struct.S.12], [2 x %struct.S.12]* [[S_ARR]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP20:%.*]] = getelementptr inbounds [[STRUCT_S_12]], %struct.S.12* [[ARRAY_BEGIN5]], i64 2
|
|
// CHECK1-NEXT: br label [[ARRAYDESTROY_BODY6:%.*]]
|
|
// CHECK1: arraydestroy.body6:
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENTPAST7:%.*]] = phi %struct.S.12* [ [[TMP20]], [[ARRAYDESTROY_DONE4]] ], [ [[ARRAYDESTROY_ELEMENT8:%.*]], [[ARRAYDESTROY_BODY6]] ]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENT8]] = getelementptr inbounds [[STRUCT_S_12]], %struct.S.12* [[ARRAYDESTROY_ELEMENTPAST7]], i64 -1
|
|
// CHECK1-NEXT: call void @_ZN1SIiED1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT8]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_DONE9:%.*]] = icmp eq %struct.S.12* [[ARRAYDESTROY_ELEMENT8]], [[ARRAY_BEGIN5]]
|
|
// CHECK1-NEXT: br i1 [[ARRAYDESTROY_DONE9]], label [[ARRAYDESTROY_DONE10:%.*]], label [[ARRAYDESTROY_BODY6]]
|
|
// CHECK1: arraydestroy.done10:
|
|
// CHECK1-NEXT: call void @_ZN1SIiED1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[TEST]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: [[TMP21:%.*]] = load i32, i32* [[RETVAL]], align 4
|
|
// CHECK1-NEXT: ret i32 [[TMP21]]
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfEC2Ev
|
|
// CHECK1-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK1-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load volatile double, double* @g, align 8
|
|
// CHECK1-NEXT: [[CONV:%.*]] = fptrunc double [[TMP0]] to float
|
|
// CHECK1-NEXT: store float [[CONV]], float* [[F]], align 4
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfEC2Ef
|
|
// CHECK1-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], float [[A:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK1-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
|
|
// CHECK1-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: store float [[A]], float* [[A_ADDR]], align 4
|
|
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load float, float* [[A_ADDR]], align 4
|
|
// CHECK1-NEXT: [[CONV:%.*]] = fpext float [[TMP0]] to double
|
|
// CHECK1-NEXT: [[TMP1:%.*]] = load volatile double, double* @g, align 8
|
|
// CHECK1-NEXT: [[ADD:%.*]] = fadd double [[CONV]], [[TMP1]]
|
|
// CHECK1-NEXT: [[CONV2:%.*]] = fptrunc double [[ADD]] to float
|
|
// CHECK1-NEXT: store float [[CONV2]], float* [[F]], align 4
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfED2Ev
|
|
// CHECK1-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK1-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiEC1Ev
|
|
// CHECK1-SAME: (%struct.S.12* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK1-NEXT: store %struct.S.12* [[THIS]], %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S.12*, %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: call void @_ZN1SIiEC2Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[THIS1]])
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiEC1Ei
|
|
// CHECK1-SAME: (%struct.S.12* nonnull align 4 dereferenceable(4) [[THIS:%.*]], i32 [[A:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK1-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: store %struct.S.12* [[THIS]], %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: store i32 [[A]], i32* [[A_ADDR]], align 4
|
|
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S.12*, %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load i32, i32* [[A_ADDR]], align 4
|
|
// CHECK1-NEXT: call void @_ZN1SIiEC2Ei(%struct.S.12* nonnull align 4 dereferenceable(4) [[THIS1]], i32 [[TMP0]])
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined..25
|
|
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.13* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.13*, align 8
|
|
// CHECK1-NEXT: [[TMP:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK1-NEXT: [[_TMP1:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK1-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[_TMP2:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[T_VAR:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[VAR:%.*]] = alloca [[STRUCT_S_12:%.*]], align 4
|
|
// CHECK1-NEXT: [[_TMP3:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK1-NEXT: [[VAR1:%.*]] = alloca [[STRUCT_S_12]], align 4
|
|
// CHECK1-NEXT: [[T_VAR1:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [4 x i8*], align 8
|
|
// CHECK1-NEXT: [[REF_TMP:%.*]] = alloca [[STRUCT_S_12]], align 4
|
|
// CHECK1-NEXT: [[REF_TMP18:%.*]] = alloca [[STRUCT_S_12]], align 4
|
|
// CHECK1-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store %struct.anon.13* [[__CONTEXT]], %struct.anon.13** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load %struct.anon.13*, %struct.anon.13** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_13:%.*]], %struct.anon.13* [[TMP0]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load i32*, i32** [[TMP1]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_ANON_13]], %struct.anon.13* [[TMP0]], i32 0, i32 1
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load %struct.S.12*, %struct.S.12** [[TMP3]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_ANON_13]], %struct.anon.13* [[TMP0]], i32 0, i32 2
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = load %struct.S.12*, %struct.S.12** [[TMP5]], align 8
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = getelementptr inbounds [[STRUCT_ANON_13]], %struct.anon.13* [[TMP0]], i32 0, i32 3
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = load i32*, i32** [[TMP7]], align 8
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_ANON_13]], %struct.anon.13* [[TMP0]], i32 0, i32 4
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = load [2 x i32]*, [2 x i32]** [[TMP9]], align 8
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = getelementptr inbounds [[STRUCT_ANON_13]], %struct.anon.13* [[TMP0]], i32 0, i32 5
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = load [2 x %struct.S.12]*, [2 x %struct.S.12]** [[TMP11]], align 8
|
|
// CHECK1-NEXT: store %struct.S.12* [[TMP4]], %struct.S.12** [[TMP]], align 8
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = load %struct.S.12*, %struct.S.12** [[TMP]], align 8
|
|
// CHECK1-NEXT: store %struct.S.12* [[TMP13]], %struct.S.12** [[_TMP1]], align 8
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK1-NEXT: store i32 0, i32* [[T_VAR]], align 4
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = load %struct.S.12*, %struct.S.12** [[_TMP1]], align 8
|
|
// CHECK1-NEXT: call void @_ZN1SIiEC1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[VAR]])
|
|
// CHECK1-NEXT: store %struct.S.12* [[VAR]], %struct.S.12** [[_TMP3]], align 8
|
|
// CHECK1-NEXT: call void @_ZN1SIiEC1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[VAR1]])
|
|
// CHECK1-NEXT: store i32 2147483647, i32* [[T_VAR1]], align 4
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = load i32, i32* [[TMP15]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP16]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP17]], 1
|
|
// CHECK1-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK1: cond.true:
|
|
// CHECK1-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK1: cond.false:
|
|
// CHECK1-NEXT: [[TMP18:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END]]
|
|
// CHECK1: cond.end:
|
|
// CHECK1-NEXT: [[COND:%.*]] = phi i32 [ 1, [[COND_TRUE]] ], [ [[TMP18]], [[COND_FALSE]] ]
|
|
// CHECK1-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[TMP19:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 [[TMP19]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK1: omp.inner.for.cond:
|
|
// CHECK1-NEXT: [[TMP20:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[TMP21:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP4:%.*]] = icmp sle i32 [[TMP20]], [[TMP21]]
|
|
// CHECK1-NEXT: br i1 [[CMP4]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK1: omp.inner.for.cond.cleanup:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK1: omp.inner.for.body:
|
|
// CHECK1-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP22]], 1
|
|
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK1-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK1-NEXT: [[TMP23:%.*]] = load i32, i32* [[T_VAR]], align 4
|
|
// CHECK1-NEXT: [[TMP24:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK1-NEXT: [[IDXPROM:%.*]] = sext i32 [[TMP24]] to i64
|
|
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[TMP10]], i64 0, i64 [[IDXPROM]]
|
|
// CHECK1-NEXT: store i32 [[TMP23]], i32* [[ARRAYIDX]], align 4
|
|
// CHECK1-NEXT: [[TMP25:%.*]] = load %struct.S.12*, %struct.S.12** [[_TMP3]], align 8
|
|
// CHECK1-NEXT: [[TMP26:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK1-NEXT: [[IDXPROM5:%.*]] = sext i32 [[TMP26]] to i64
|
|
// CHECK1-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds [2 x %struct.S.12], [2 x %struct.S.12]* [[TMP12]], i64 0, i64 [[IDXPROM5]]
|
|
// CHECK1-NEXT: [[TMP27:%.*]] = bitcast %struct.S.12* [[ARRAYIDX6]] to i8*
|
|
// CHECK1-NEXT: [[TMP28:%.*]] = bitcast %struct.S.12* [[TMP25]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP27]], i8* align 4 [[TMP28]], i64 4, i1 false)
|
|
// CHECK1-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK1: omp.body.continue:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK1: omp.inner.for.inc:
|
|
// CHECK1-NEXT: [[TMP29:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[ADD7:%.*]] = add nsw i32 [[TMP29]], 1
|
|
// CHECK1-NEXT: store i32 [[ADD7]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK1: omp.inner.for.end:
|
|
// CHECK1-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK1: omp.loop.exit:
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP16]])
|
|
// CHECK1-NEXT: [[TMP30:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP31:%.*]] = bitcast i32* [[T_VAR]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP31]], i8** [[TMP30]], align 8
|
|
// CHECK1-NEXT: [[TMP32:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 1
|
|
// CHECK1-NEXT: [[TMP33:%.*]] = bitcast %struct.S.12* [[VAR]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP33]], i8** [[TMP32]], align 8
|
|
// CHECK1-NEXT: [[TMP34:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 2
|
|
// CHECK1-NEXT: [[TMP35:%.*]] = bitcast %struct.S.12* [[VAR1]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP35]], i8** [[TMP34]], align 8
|
|
// CHECK1-NEXT: [[TMP36:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 3
|
|
// CHECK1-NEXT: [[TMP37:%.*]] = bitcast i32* [[T_VAR1]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP37]], i8** [[TMP36]], align 8
|
|
// CHECK1-NEXT: [[TMP38:%.*]] = bitcast [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK1-NEXT: [[TMP39:%.*]] = call i32 @__kmpc_reduce_nowait(%struct.ident_t* @[[GLOB2]], i32 [[TMP16]], i32 4, i64 32, i8* [[TMP38]], void (i8*, i8*)* @.omp.reduction.reduction_func.26, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: switch i32 [[TMP39]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK1-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK1-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK1-NEXT: ]
|
|
// CHECK1: .omp.reduction.case1:
|
|
// CHECK1-NEXT: [[TMP40:%.*]] = load i32, i32* [[TMP2]], align 4
|
|
// CHECK1-NEXT: [[TMP41:%.*]] = load i32, i32* [[T_VAR]], align 4
|
|
// CHECK1-NEXT: [[ADD8:%.*]] = add nsw i32 [[TMP40]], [[TMP41]]
|
|
// CHECK1-NEXT: store i32 [[ADD8]], i32* [[TMP2]], align 4
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S.12* @_ZN1SIiEanERKS0_(%struct.S.12* nonnull align 4 dereferenceable(4) [[TMP14]], %struct.S.12* nonnull align 4 dereferenceable(4) [[VAR]])
|
|
// CHECK1-NEXT: [[TMP42:%.*]] = bitcast %struct.S.12* [[TMP14]] to i8*
|
|
// CHECK1-NEXT: [[TMP43:%.*]] = bitcast %struct.S.12* [[CALL]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP42]], i8* align 4 [[TMP43]], i64 4, i1 false)
|
|
// CHECK1-NEXT: [[CALL9:%.*]] = call i32 @_ZN1SIiEcviEv(%struct.S.12* nonnull align 4 dereferenceable(4) [[TMP6]])
|
|
// CHECK1-NEXT: [[TOBOOL:%.*]] = icmp ne i32 [[CALL9]], 0
|
|
// CHECK1-NEXT: br i1 [[TOBOOL]], label [[LAND_RHS:%.*]], label [[LAND_END:%.*]]
|
|
// CHECK1: land.rhs:
|
|
// CHECK1-NEXT: [[CALL10:%.*]] = call i32 @_ZN1SIiEcviEv(%struct.S.12* nonnull align 4 dereferenceable(4) [[VAR1]])
|
|
// CHECK1-NEXT: [[TOBOOL11:%.*]] = icmp ne i32 [[CALL10]], 0
|
|
// CHECK1-NEXT: br label [[LAND_END]]
|
|
// CHECK1: land.end:
|
|
// CHECK1-NEXT: [[TMP44:%.*]] = phi i1 [ false, [[DOTOMP_REDUCTION_CASE1]] ], [ [[TOBOOL11]], [[LAND_RHS]] ]
|
|
// CHECK1-NEXT: [[CONV:%.*]] = zext i1 [[TMP44]] to i32
|
|
// CHECK1-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.12* nonnull align 4 dereferenceable(4) [[REF_TMP]], i32 [[CONV]])
|
|
// CHECK1-NEXT: [[TMP45:%.*]] = bitcast %struct.S.12* [[TMP6]] to i8*
|
|
// CHECK1-NEXT: [[TMP46:%.*]] = bitcast %struct.S.12* [[REF_TMP]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP45]], i8* align 4 [[TMP46]], i64 4, i1 false)
|
|
// CHECK1-NEXT: call void @_ZN1SIiED1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[REF_TMP]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: [[TMP47:%.*]] = load i32, i32* [[TMP8]], align 4
|
|
// CHECK1-NEXT: [[TMP48:%.*]] = load i32, i32* [[T_VAR1]], align 4
|
|
// CHECK1-NEXT: [[CMP12:%.*]] = icmp slt i32 [[TMP47]], [[TMP48]]
|
|
// CHECK1-NEXT: br i1 [[CMP12]], label [[COND_TRUE13:%.*]], label [[COND_FALSE14:%.*]]
|
|
// CHECK1: cond.true13:
|
|
// CHECK1-NEXT: [[TMP49:%.*]] = load i32, i32* [[TMP8]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END15:%.*]]
|
|
// CHECK1: cond.false14:
|
|
// CHECK1-NEXT: [[TMP50:%.*]] = load i32, i32* [[T_VAR1]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END15]]
|
|
// CHECK1: cond.end15:
|
|
// CHECK1-NEXT: [[COND16:%.*]] = phi i32 [ [[TMP49]], [[COND_TRUE13]] ], [ [[TMP50]], [[COND_FALSE14]] ]
|
|
// CHECK1-NEXT: store i32 [[COND16]], i32* [[TMP8]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce_nowait(%struct.ident_t* @[[GLOB2]], i32 [[TMP16]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.case2:
|
|
// CHECK1-NEXT: [[TMP51:%.*]] = load i32, i32* [[T_VAR]], align 4
|
|
// CHECK1-NEXT: [[TMP52:%.*]] = atomicrmw add i32* [[TMP2]], i32 [[TMP51]] monotonic, align 4
|
|
// CHECK1-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP16]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[CALL17:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S.12* @_ZN1SIiEanERKS0_(%struct.S.12* nonnull align 4 dereferenceable(4) [[TMP14]], %struct.S.12* nonnull align 4 dereferenceable(4) [[VAR]])
|
|
// CHECK1-NEXT: [[TMP53:%.*]] = bitcast %struct.S.12* [[TMP14]] to i8*
|
|
// CHECK1-NEXT: [[TMP54:%.*]] = bitcast %struct.S.12* [[CALL17]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP53]], i8* align 4 [[TMP54]], i64 4, i1 false)
|
|
// CHECK1-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP16]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP16]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[CALL19:%.*]] = call i32 @_ZN1SIiEcviEv(%struct.S.12* nonnull align 4 dereferenceable(4) [[TMP6]])
|
|
// CHECK1-NEXT: [[TOBOOL20:%.*]] = icmp ne i32 [[CALL19]], 0
|
|
// CHECK1-NEXT: br i1 [[TOBOOL20]], label [[LAND_RHS21:%.*]], label [[LAND_END24:%.*]]
|
|
// CHECK1: land.rhs21:
|
|
// CHECK1-NEXT: [[CALL22:%.*]] = call i32 @_ZN1SIiEcviEv(%struct.S.12* nonnull align 4 dereferenceable(4) [[VAR1]])
|
|
// CHECK1-NEXT: [[TOBOOL23:%.*]] = icmp ne i32 [[CALL22]], 0
|
|
// CHECK1-NEXT: br label [[LAND_END24]]
|
|
// CHECK1: land.end24:
|
|
// CHECK1-NEXT: [[TMP55:%.*]] = phi i1 [ false, [[DOTOMP_REDUCTION_CASE2]] ], [ [[TOBOOL23]], [[LAND_RHS21]] ]
|
|
// CHECK1-NEXT: [[CONV25:%.*]] = zext i1 [[TMP55]] to i32
|
|
// CHECK1-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.12* nonnull align 4 dereferenceable(4) [[REF_TMP18]], i32 [[CONV25]])
|
|
// CHECK1-NEXT: [[TMP56:%.*]] = bitcast %struct.S.12* [[TMP6]] to i8*
|
|
// CHECK1-NEXT: [[TMP57:%.*]] = bitcast %struct.S.12* [[REF_TMP18]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP56]], i8* align 4 [[TMP57]], i64 4, i1 false)
|
|
// CHECK1-NEXT: call void @_ZN1SIiED1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[REF_TMP18]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP16]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[TMP58:%.*]] = load i32, i32* [[T_VAR1]], align 4
|
|
// CHECK1-NEXT: [[TMP59:%.*]] = atomicrmw min i32* [[TMP8]], i32 [[TMP58]] monotonic, align 4
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.default:
|
|
// CHECK1-NEXT: call void @_ZN1SIiED1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[VAR1]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: call void @_ZN1SIiED1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[VAR]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.26
|
|
// CHECK1-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: [[REF_TMP:%.*]] = alloca [[STRUCT_S_12:%.*]], align 4
|
|
// CHECK1-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [4 x i8*]*
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [4 x i8*]*
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to i32*
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i32*
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 1
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = load i8*, i8** [[TMP12]], align 8
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = bitcast i8* [[TMP13]] to %struct.S.12*
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 1
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = load i8*, i8** [[TMP15]], align 8
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = bitcast i8* [[TMP16]] to %struct.S.12*
|
|
// CHECK1-NEXT: [[TMP18:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 2
|
|
// CHECK1-NEXT: [[TMP19:%.*]] = load i8*, i8** [[TMP18]], align 8
|
|
// CHECK1-NEXT: [[TMP20:%.*]] = bitcast i8* [[TMP19]] to %struct.S.12*
|
|
// CHECK1-NEXT: [[TMP21:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 2
|
|
// CHECK1-NEXT: [[TMP22:%.*]] = load i8*, i8** [[TMP21]], align 8
|
|
// CHECK1-NEXT: [[TMP23:%.*]] = bitcast i8* [[TMP22]] to %struct.S.12*
|
|
// CHECK1-NEXT: [[TMP24:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 3
|
|
// CHECK1-NEXT: [[TMP25:%.*]] = load i8*, i8** [[TMP24]], align 8
|
|
// CHECK1-NEXT: [[TMP26:%.*]] = bitcast i8* [[TMP25]] to i32*
|
|
// CHECK1-NEXT: [[TMP27:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 3
|
|
// CHECK1-NEXT: [[TMP28:%.*]] = load i8*, i8** [[TMP27]], align 8
|
|
// CHECK1-NEXT: [[TMP29:%.*]] = bitcast i8* [[TMP28]] to i32*
|
|
// CHECK1-NEXT: [[TMP30:%.*]] = load i32, i32* [[TMP11]], align 4
|
|
// CHECK1-NEXT: [[TMP31:%.*]] = load i32, i32* [[TMP8]], align 4
|
|
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP30]], [[TMP31]]
|
|
// CHECK1-NEXT: store i32 [[ADD]], i32* [[TMP11]], align 4
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S.12* @_ZN1SIiEanERKS0_(%struct.S.12* nonnull align 4 dereferenceable(4) [[TMP17]], %struct.S.12* nonnull align 4 dereferenceable(4) [[TMP14]])
|
|
// CHECK1-NEXT: [[TMP32:%.*]] = bitcast %struct.S.12* [[TMP17]] to i8*
|
|
// CHECK1-NEXT: [[TMP33:%.*]] = bitcast %struct.S.12* [[CALL]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP32]], i8* align 4 [[TMP33]], i64 4, i1 false)
|
|
// CHECK1-NEXT: [[CALL2:%.*]] = call i32 @_ZN1SIiEcviEv(%struct.S.12* nonnull align 4 dereferenceable(4) [[TMP23]])
|
|
// CHECK1-NEXT: [[TOBOOL:%.*]] = icmp ne i32 [[CALL2]], 0
|
|
// CHECK1-NEXT: br i1 [[TOBOOL]], label [[LAND_RHS:%.*]], label [[LAND_END:%.*]]
|
|
// CHECK1: land.rhs:
|
|
// CHECK1-NEXT: [[CALL3:%.*]] = call i32 @_ZN1SIiEcviEv(%struct.S.12* nonnull align 4 dereferenceable(4) [[TMP20]])
|
|
// CHECK1-NEXT: [[TOBOOL4:%.*]] = icmp ne i32 [[CALL3]], 0
|
|
// CHECK1-NEXT: br label [[LAND_END]]
|
|
// CHECK1: land.end:
|
|
// CHECK1-NEXT: [[TMP34:%.*]] = phi i1 [ false, [[ENTRY:%.*]] ], [ [[TOBOOL4]], [[LAND_RHS]] ]
|
|
// CHECK1-NEXT: [[CONV:%.*]] = zext i1 [[TMP34]] to i32
|
|
// CHECK1-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.12* nonnull align 4 dereferenceable(4) [[REF_TMP]], i32 [[CONV]])
|
|
// CHECK1-NEXT: [[TMP35:%.*]] = bitcast %struct.S.12* [[TMP23]] to i8*
|
|
// CHECK1-NEXT: [[TMP36:%.*]] = bitcast %struct.S.12* [[REF_TMP]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP35]], i8* align 4 [[TMP36]], i64 4, i1 false)
|
|
// CHECK1-NEXT: call void @_ZN1SIiED1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[REF_TMP]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: [[TMP37:%.*]] = load i32, i32* [[TMP29]], align 4
|
|
// CHECK1-NEXT: [[TMP38:%.*]] = load i32, i32* [[TMP26]], align 4
|
|
// CHECK1-NEXT: [[CMP:%.*]] = icmp slt i32 [[TMP37]], [[TMP38]]
|
|
// CHECK1-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK1: cond.true:
|
|
// CHECK1-NEXT: [[TMP39:%.*]] = load i32, i32* [[TMP29]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK1: cond.false:
|
|
// CHECK1-NEXT: [[TMP40:%.*]] = load i32, i32* [[TMP26]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END]]
|
|
// CHECK1: cond.end:
|
|
// CHECK1-NEXT: [[COND:%.*]] = phi i32 [ [[TMP39]], [[COND_TRUE]] ], [ [[TMP40]], [[COND_FALSE]] ]
|
|
// CHECK1-NEXT: store i32 [[COND]], i32* [[TMP29]], align 4
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiEanERKS0_
|
|
// CHECK1-SAME: (%struct.S.12* nonnull align 4 dereferenceable(4) [[THIS:%.*]], %struct.S.12* nonnull align 4 dereferenceable(4) [[TMP0:%.*]]) #[[ATTR7]] align 2 {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK1-NEXT: store %struct.S.12* [[THIS]], %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: store %struct.S.12* [[TMP0]], %struct.S.12** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S.12*, %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: ret %struct.S.12* [[THIS1]]
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiEcviEv
|
|
// CHECK1-SAME: (%struct.S.12* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) #[[ATTR7]] align 2 {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK1-NEXT: store %struct.S.12* [[THIS]], %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S.12*, %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: ret i32 0
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiED1Ev
|
|
// CHECK1-SAME: (%struct.S.12* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK1-NEXT: store %struct.S.12* [[THIS]], %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S.12*, %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: call void @_ZN1SIiED2Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[THIS1]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined..27
|
|
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.14* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.14*, align 8
|
|
// CHECK1-NEXT: [[TMP:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK1-NEXT: [[_TMP1:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK1-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[_TMP2:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[T_VAR:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK1-NEXT: [[ATOMIC_TEMP:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[_TMP9:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store %struct.anon.14* [[__CONTEXT]], %struct.anon.14** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load %struct.anon.14*, %struct.anon.14** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_14:%.*]], %struct.anon.14* [[TMP0]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load i32*, i32** [[TMP1]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_ANON_14]], %struct.anon.14* [[TMP0]], i32 0, i32 1
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load [2 x i32]*, [2 x i32]** [[TMP3]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_ANON_14]], %struct.anon.14* [[TMP0]], i32 0, i32 2
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = load [2 x %struct.S.12]*, [2 x %struct.S.12]** [[TMP5]], align 8
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = getelementptr inbounds [[STRUCT_ANON_14]], %struct.anon.14* [[TMP0]], i32 0, i32 3
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = load %struct.S.12*, %struct.S.12** [[TMP7]], align 8
|
|
// CHECK1-NEXT: store %struct.S.12* [[TMP8]], %struct.S.12** [[TMP]], align 8
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = load %struct.S.12*, %struct.S.12** [[TMP]], align 8
|
|
// CHECK1-NEXT: store %struct.S.12* [[TMP9]], %struct.S.12** [[_TMP1]], align 8
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK1-NEXT: store i32 1, i32* [[T_VAR]], align 4
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = load i32, i32* [[TMP10]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP11]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP12]], 1
|
|
// CHECK1-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK1: cond.true:
|
|
// CHECK1-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK1: cond.false:
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END]]
|
|
// CHECK1: cond.end:
|
|
// CHECK1-NEXT: [[COND:%.*]] = phi i32 [ 1, [[COND_TRUE]] ], [ [[TMP13]], [[COND_FALSE]] ]
|
|
// CHECK1-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 [[TMP14]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK1: omp.inner.for.cond:
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP3:%.*]] = icmp sle i32 [[TMP15]], [[TMP16]]
|
|
// CHECK1-NEXT: br i1 [[CMP3]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK1: omp.inner.for.body:
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP17]], 1
|
|
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK1-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK1-NEXT: [[TMP18:%.*]] = load i32, i32* [[T_VAR]], align 4
|
|
// CHECK1-NEXT: [[TMP19:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK1-NEXT: [[IDXPROM:%.*]] = sext i32 [[TMP19]] to i64
|
|
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[TMP4]], i64 0, i64 [[IDXPROM]]
|
|
// CHECK1-NEXT: store i32 [[TMP18]], i32* [[ARRAYIDX]], align 4
|
|
// CHECK1-NEXT: [[TMP20:%.*]] = load %struct.S.12*, %struct.S.12** [[_TMP1]], align 8
|
|
// CHECK1-NEXT: [[TMP21:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK1-NEXT: [[IDXPROM4:%.*]] = sext i32 [[TMP21]] to i64
|
|
// CHECK1-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds [2 x %struct.S.12], [2 x %struct.S.12]* [[TMP6]], i64 0, i64 [[IDXPROM4]]
|
|
// CHECK1-NEXT: [[TMP22:%.*]] = bitcast %struct.S.12* [[ARRAYIDX5]] to i8*
|
|
// CHECK1-NEXT: [[TMP23:%.*]] = bitcast %struct.S.12* [[TMP20]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP22]], i8* align 4 [[TMP23]], i64 4, i1 false)
|
|
// CHECK1-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK1: omp.body.continue:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK1: omp.inner.for.inc:
|
|
// CHECK1-NEXT: [[TMP24:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[ADD6:%.*]] = add nsw i32 [[TMP24]], 1
|
|
// CHECK1-NEXT: store i32 [[ADD6]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK1: omp.inner.for.end:
|
|
// CHECK1-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK1: omp.loop.exit:
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP11]])
|
|
// CHECK1-NEXT: [[TMP25:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP26:%.*]] = bitcast i32* [[T_VAR]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP26]], i8** [[TMP25]], align 8
|
|
// CHECK1-NEXT: [[TMP27:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK1-NEXT: [[TMP28:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP11]], i32 1, i64 8, i8* [[TMP27]], void (i8*, i8*)* @.omp.reduction.reduction_func.28, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: switch i32 [[TMP28]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK1-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK1-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK1-NEXT: ]
|
|
// CHECK1: .omp.reduction.case1:
|
|
// CHECK1-NEXT: [[TMP29:%.*]] = load i32, i32* [[TMP2]], align 4
|
|
// CHECK1-NEXT: [[TOBOOL:%.*]] = icmp ne i32 [[TMP29]], 0
|
|
// CHECK1-NEXT: br i1 [[TOBOOL]], label [[LAND_RHS:%.*]], label [[LAND_END:%.*]]
|
|
// CHECK1: land.rhs:
|
|
// CHECK1-NEXT: [[TMP30:%.*]] = load i32, i32* [[T_VAR]], align 4
|
|
// CHECK1-NEXT: [[TOBOOL7:%.*]] = icmp ne i32 [[TMP30]], 0
|
|
// CHECK1-NEXT: br label [[LAND_END]]
|
|
// CHECK1: land.end:
|
|
// CHECK1-NEXT: [[TMP31:%.*]] = phi i1 [ false, [[DOTOMP_REDUCTION_CASE1]] ], [ [[TOBOOL7]], [[LAND_RHS]] ]
|
|
// CHECK1-NEXT: [[CONV:%.*]] = zext i1 [[TMP31]] to i32
|
|
// CHECK1-NEXT: store i32 [[CONV]], i32* [[TMP2]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP11]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.case2:
|
|
// CHECK1-NEXT: [[TMP32:%.*]] = load i32, i32* [[T_VAR]], align 4
|
|
// CHECK1-NEXT: [[TOBOOL8:%.*]] = icmp ne i32 [[TMP32]], 0
|
|
// CHECK1-NEXT: [[ATOMIC_LOAD:%.*]] = load atomic i32, i32* [[TMP2]] monotonic, align 4
|
|
// CHECK1-NEXT: br label [[ATOMIC_CONT:%.*]]
|
|
// CHECK1: atomic_cont:
|
|
// CHECK1-NEXT: [[TMP33:%.*]] = phi i32 [ [[ATOMIC_LOAD]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[TMP39:%.*]], [[LAND_END13:%.*]] ]
|
|
// CHECK1-NEXT: store i32 [[TMP33]], i32* [[_TMP9]], align 4
|
|
// CHECK1-NEXT: [[TMP34:%.*]] = load i32, i32* [[_TMP9]], align 4
|
|
// CHECK1-NEXT: [[TOBOOL10:%.*]] = icmp ne i32 [[TMP34]], 0
|
|
// CHECK1-NEXT: br i1 [[TOBOOL10]], label [[LAND_RHS11:%.*]], label [[LAND_END13]]
|
|
// CHECK1: land.rhs11:
|
|
// CHECK1-NEXT: [[TMP35:%.*]] = load i32, i32* [[T_VAR]], align 4
|
|
// CHECK1-NEXT: [[TOBOOL12:%.*]] = icmp ne i32 [[TMP35]], 0
|
|
// CHECK1-NEXT: br label [[LAND_END13]]
|
|
// CHECK1: land.end13:
|
|
// CHECK1-NEXT: [[TMP36:%.*]] = phi i1 [ false, [[ATOMIC_CONT]] ], [ [[TOBOOL12]], [[LAND_RHS11]] ]
|
|
// CHECK1-NEXT: [[CONV14:%.*]] = zext i1 [[TMP36]] to i32
|
|
// CHECK1-NEXT: store i32 [[CONV14]], i32* [[ATOMIC_TEMP]], align 4
|
|
// CHECK1-NEXT: [[TMP37:%.*]] = load i32, i32* [[ATOMIC_TEMP]], align 4
|
|
// CHECK1-NEXT: [[TMP38:%.*]] = cmpxchg i32* [[TMP2]], i32 [[TMP33]], i32 [[TMP37]] monotonic monotonic, align 4
|
|
// CHECK1-NEXT: [[TMP39]] = extractvalue { i32, i1 } [[TMP38]], 0
|
|
// CHECK1-NEXT: [[TMP40:%.*]] = extractvalue { i32, i1 } [[TMP38]], 1
|
|
// CHECK1-NEXT: br i1 [[TMP40]], label [[ATOMIC_EXIT:%.*]], label [[ATOMIC_CONT]]
|
|
// CHECK1: atomic_exit:
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP11]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.default:
|
|
// CHECK1-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4]], i32 [[TMP11]])
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.28
|
|
// CHECK1-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to i32*
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i32*
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = load i32, i32* [[TMP11]], align 4
|
|
// CHECK1-NEXT: [[TOBOOL:%.*]] = icmp ne i32 [[TMP12]], 0
|
|
// CHECK1-NEXT: br i1 [[TOBOOL]], label [[LAND_RHS:%.*]], label [[LAND_END:%.*]]
|
|
// CHECK1: land.rhs:
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = load i32, i32* [[TMP8]], align 4
|
|
// CHECK1-NEXT: [[TOBOOL2:%.*]] = icmp ne i32 [[TMP13]], 0
|
|
// CHECK1-NEXT: br label [[LAND_END]]
|
|
// CHECK1: land.end:
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = phi i1 [ false, [[ENTRY:%.*]] ], [ [[TOBOOL2]], [[LAND_RHS]] ]
|
|
// CHECK1-NEXT: [[CONV:%.*]] = zext i1 [[TMP14]] to i32
|
|
// CHECK1-NEXT: store i32 [[CONV]], i32* [[TMP11]], align 4
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined..29
|
|
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.15* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.15*, align 8
|
|
// CHECK1-NEXT: [[TMP:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK1-NEXT: [[_TMP1:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK1-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[_TMP2:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[ARR:%.*]] = alloca [40 x %struct.S.12], align 16
|
|
// CHECK1-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK1-NEXT: [[REF_TMP:%.*]] = alloca [[STRUCT_S_12:%.*]], align 4
|
|
// CHECK1-NEXT: [[REF_TMP19:%.*]] = alloca [[STRUCT_S_12]], align 4
|
|
// CHECK1-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store %struct.anon.15* [[__CONTEXT]], %struct.anon.15** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load %struct.anon.15*, %struct.anon.15** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_15:%.*]], %struct.anon.15* [[TMP0]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load [42 x %struct.S.12]*, [42 x %struct.S.12]** [[TMP1]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_ANON_15]], %struct.anon.15* [[TMP0]], i32 0, i32 1
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load [2 x i32]*, [2 x i32]** [[TMP3]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_ANON_15]], %struct.anon.15* [[TMP0]], i32 0, i32 2
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = load i32*, i32** [[TMP5]], align 8
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = getelementptr inbounds [[STRUCT_ANON_15]], %struct.anon.15* [[TMP0]], i32 0, i32 3
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = load [2 x %struct.S.12]*, [2 x %struct.S.12]** [[TMP7]], align 8
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_ANON_15]], %struct.anon.15* [[TMP0]], i32 0, i32 4
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = load %struct.S.12*, %struct.S.12** [[TMP9]], align 8
|
|
// CHECK1-NEXT: store %struct.S.12* [[TMP10]], %struct.S.12** [[TMP]], align 8
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = load %struct.S.12*, %struct.S.12** [[TMP]], align 8
|
|
// CHECK1-NEXT: store %struct.S.12* [[TMP11]], %struct.S.12** [[_TMP1]], align 8
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [42 x %struct.S.12], [42 x %struct.S.12]* [[TMP2]], i64 0, i64 1
|
|
// CHECK1-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds [42 x %struct.S.12], [42 x %struct.S.12]* [[TMP2]], i64 0, i64 40
|
|
// CHECK1-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [40 x %struct.S.12], [40 x %struct.S.12]* [[ARR]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = getelementptr [[STRUCT_S_12]], %struct.S.12* [[ARRAY_BEGIN]], i64 40
|
|
// CHECK1-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq %struct.S.12* [[ARRAY_BEGIN]], [[TMP12]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
|
|
// CHECK1: omp.arrayinit.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S.12* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
|
|
// CHECK1-NEXT: call void @_ZN1SIiEC1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]])
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S_12]], %struct.S.12* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S.12* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP12]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK1: omp.arrayinit.done:
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = bitcast [42 x %struct.S.12]* [[TMP2]] to %struct.S.12*
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = ptrtoint %struct.S.12* [[TMP13]] to i64
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = ptrtoint %struct.S.12* [[ARRAYIDX]] to i64
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = sub i64 [[TMP14]], [[TMP15]]
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = sdiv exact i64 [[TMP16]], ptrtoint (i32* getelementptr (i32, i32* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[TMP18:%.*]] = bitcast [40 x %struct.S.12]* [[ARR]] to %struct.S.12*
|
|
// CHECK1-NEXT: [[TMP19:%.*]] = getelementptr [[STRUCT_S_12]], %struct.S.12* [[TMP18]], i64 [[TMP17]]
|
|
// CHECK1-NEXT: [[TMP20:%.*]] = bitcast %struct.S.12* [[TMP19]] to [42 x %struct.S.12]*
|
|
// CHECK1-NEXT: [[RHS_BEGIN:%.*]] = bitcast [40 x %struct.S.12]* [[ARR]] to %struct.S.12*
|
|
// CHECK1-NEXT: [[TMP21:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP22:%.*]] = load i32, i32* [[TMP21]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP22]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK1-NEXT: [[TMP23:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP23]], 1
|
|
// CHECK1-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK1: cond.true:
|
|
// CHECK1-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK1: cond.false:
|
|
// CHECK1-NEXT: [[TMP24:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END]]
|
|
// CHECK1: cond.end:
|
|
// CHECK1-NEXT: [[COND:%.*]] = phi i32 [ 1, [[COND_TRUE]] ], [ [[TMP24]], [[COND_FALSE]] ]
|
|
// CHECK1-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[TMP25:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 [[TMP25]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK1: omp.inner.for.cond:
|
|
// CHECK1-NEXT: [[TMP26:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[TMP27:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP4:%.*]] = icmp sle i32 [[TMP26]], [[TMP27]]
|
|
// CHECK1-NEXT: br i1 [[CMP4]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK1: omp.inner.for.cond.cleanup:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK1: omp.inner.for.body:
|
|
// CHECK1-NEXT: [[TMP28:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP28]], 1
|
|
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK1-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK1-NEXT: [[TMP29:%.*]] = load i32, i32* [[TMP6]], align 4
|
|
// CHECK1-NEXT: [[TMP30:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK1-NEXT: [[IDXPROM:%.*]] = sext i32 [[TMP30]] to i64
|
|
// CHECK1-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[TMP4]], i64 0, i64 [[IDXPROM]]
|
|
// CHECK1-NEXT: store i32 [[TMP29]], i32* [[ARRAYIDX5]], align 4
|
|
// CHECK1-NEXT: [[TMP31:%.*]] = load %struct.S.12*, %struct.S.12** [[_TMP1]], align 8
|
|
// CHECK1-NEXT: [[TMP32:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK1-NEXT: [[IDXPROM6:%.*]] = sext i32 [[TMP32]] to i64
|
|
// CHECK1-NEXT: [[ARRAYIDX7:%.*]] = getelementptr inbounds [2 x %struct.S.12], [2 x %struct.S.12]* [[TMP8]], i64 0, i64 [[IDXPROM6]]
|
|
// CHECK1-NEXT: [[TMP33:%.*]] = bitcast %struct.S.12* [[ARRAYIDX7]] to i8*
|
|
// CHECK1-NEXT: [[TMP34:%.*]] = bitcast %struct.S.12* [[TMP31]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP33]], i8* align 4 [[TMP34]], i64 4, i1 false)
|
|
// CHECK1-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK1: omp.body.continue:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK1: omp.inner.for.inc:
|
|
// CHECK1-NEXT: [[TMP35:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: [[ADD8:%.*]] = add nsw i32 [[TMP35]], 1
|
|
// CHECK1-NEXT: store i32 [[ADD8]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK1: omp.inner.for.end:
|
|
// CHECK1-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK1: omp.loop.exit:
|
|
// CHECK1-NEXT: [[TMP36:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP37:%.*]] = load i32, i32* [[TMP36]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP37]])
|
|
// CHECK1-NEXT: [[TMP38:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP39:%.*]] = bitcast %struct.S.12* [[RHS_BEGIN]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP39]], i8** [[TMP38]], align 8
|
|
// CHECK1-NEXT: [[TMP40:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP41:%.*]] = load i32, i32* [[TMP40]], align 4
|
|
// CHECK1-NEXT: [[TMP42:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK1-NEXT: [[TMP43:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP41]], i32 1, i64 8, i8* [[TMP42]], void (i8*, i8*)* @.omp.reduction.reduction_func.30, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: switch i32 [[TMP43]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK1-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK1-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK1-NEXT: ]
|
|
// CHECK1: .omp.reduction.case1:
|
|
// CHECK1-NEXT: [[TMP44:%.*]] = getelementptr [[STRUCT_S_12]], %struct.S.12* [[ARRAYIDX]], i64 40
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S.12* [[ARRAYIDX]], [[TMP44]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE14:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK1: omp.arraycpy.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S.12* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST9:%.*]] = phi %struct.S.12* [ [[ARRAYIDX]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT12:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call i32 @_ZN1SIiEcviEv(%struct.S.12* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST9]])
|
|
// CHECK1-NEXT: [[CALL10:%.*]] = call i32 @_ZN1SIiEcviEv(%struct.S.12* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK1-NEXT: [[ADD11:%.*]] = add nsw i32 [[CALL]], [[CALL10]]
|
|
// CHECK1-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.12* nonnull align 4 dereferenceable(4) [[REF_TMP]], i32 [[ADD11]])
|
|
// CHECK1-NEXT: [[TMP45:%.*]] = bitcast %struct.S.12* [[OMP_ARRAYCPY_DESTELEMENTPAST9]] to i8*
|
|
// CHECK1-NEXT: [[TMP46:%.*]] = bitcast %struct.S.12* [[REF_TMP]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP45]], i8* align 4 [[TMP46]], i64 4, i1 false)
|
|
// CHECK1-NEXT: call void @_ZN1SIiED1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[REF_TMP]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT12]] = getelementptr [[STRUCT_S_12]], %struct.S.12* [[OMP_ARRAYCPY_DESTELEMENTPAST9]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S_12]], %struct.S.12* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE13:%.*]] = icmp eq %struct.S.12* [[OMP_ARRAYCPY_DEST_ELEMENT12]], [[TMP44]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE13]], label [[OMP_ARRAYCPY_DONE14]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK1: omp.arraycpy.done14:
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP41]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.case2:
|
|
// CHECK1-NEXT: [[TMP47:%.*]] = getelementptr [[STRUCT_S_12]], %struct.S.12* [[ARRAYIDX]], i64 40
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY15:%.*]] = icmp eq %struct.S.12* [[ARRAYIDX]], [[TMP47]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY15]], label [[OMP_ARRAYCPY_DONE26:%.*]], label [[OMP_ARRAYCPY_BODY16:%.*]]
|
|
// CHECK1: omp.arraycpy.body16:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST17:%.*]] = phi %struct.S.12* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT24:%.*]], [[OMP_ARRAYCPY_BODY16]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST18:%.*]] = phi %struct.S.12* [ [[ARRAYIDX]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT23:%.*]], [[OMP_ARRAYCPY_BODY16]] ]
|
|
// CHECK1-NEXT: [[TMP48:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP49:%.*]] = load i32, i32* [[TMP48]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP49]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[CALL20:%.*]] = call i32 @_ZN1SIiEcviEv(%struct.S.12* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST18]])
|
|
// CHECK1-NEXT: [[CALL21:%.*]] = call i32 @_ZN1SIiEcviEv(%struct.S.12* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST17]])
|
|
// CHECK1-NEXT: [[ADD22:%.*]] = add nsw i32 [[CALL20]], [[CALL21]]
|
|
// CHECK1-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.12* nonnull align 4 dereferenceable(4) [[REF_TMP19]], i32 [[ADD22]])
|
|
// CHECK1-NEXT: [[TMP50:%.*]] = bitcast %struct.S.12* [[OMP_ARRAYCPY_DESTELEMENTPAST18]] to i8*
|
|
// CHECK1-NEXT: [[TMP51:%.*]] = bitcast %struct.S.12* [[REF_TMP19]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP50]], i8* align 4 [[TMP51]], i64 4, i1 false)
|
|
// CHECK1-NEXT: call void @_ZN1SIiED1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[REF_TMP19]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP49]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT23]] = getelementptr [[STRUCT_S_12]], %struct.S.12* [[OMP_ARRAYCPY_DESTELEMENTPAST18]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT24]] = getelementptr [[STRUCT_S_12]], %struct.S.12* [[OMP_ARRAYCPY_SRCELEMENTPAST17]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE25:%.*]] = icmp eq %struct.S.12* [[OMP_ARRAYCPY_DEST_ELEMENT23]], [[TMP47]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE25]], label [[OMP_ARRAYCPY_DONE26]], label [[OMP_ARRAYCPY_BODY16]]
|
|
// CHECK1: omp.arraycpy.done26:
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP41]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.default:
|
|
// CHECK1-NEXT: [[ARRAY_BEGIN27:%.*]] = getelementptr inbounds [40 x %struct.S.12], [40 x %struct.S.12]* [[ARR]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP52:%.*]] = getelementptr inbounds [[STRUCT_S_12]], %struct.S.12* [[ARRAY_BEGIN27]], i64 40
|
|
// CHECK1-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
|
|
// CHECK1: arraydestroy.body:
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S.12* [ [[TMP52]], [[DOTOMP_REDUCTION_DEFAULT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S_12]], %struct.S.12* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
|
|
// CHECK1-NEXT: call void @_ZN1SIiED1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S.12* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN27]]
|
|
// CHECK1-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE28:%.*]], label [[ARRAYDESTROY_BODY]]
|
|
// CHECK1: arraydestroy.done28:
|
|
// CHECK1-NEXT: [[TMP53:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP54:%.*]] = load i32, i32* [[TMP53]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4]], i32 [[TMP54]])
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.30
|
|
// CHECK1-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: [[REF_TMP:%.*]] = alloca [[STRUCT_S_12:%.*]], align 4
|
|
// CHECK1-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.S.12*
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to %struct.S.12*
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = getelementptr [[STRUCT_S_12]], %struct.S.12* [[TMP11]], i64 40
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S.12* [[TMP11]], [[TMP12]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE3:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK1: omp.arraycpy.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S.12* [ [[TMP8]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S.12* [ [[TMP11]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call i32 @_ZN1SIiEcviEv(%struct.S.12* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]])
|
|
// CHECK1-NEXT: [[CALL2:%.*]] = call i32 @_ZN1SIiEcviEv(%struct.S.12* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 [[CALL]], [[CALL2]]
|
|
// CHECK1-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.12* nonnull align 4 dereferenceable(4) [[REF_TMP]], i32 [[ADD]])
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = bitcast %struct.S.12* [[OMP_ARRAYCPY_DESTELEMENTPAST]] to i8*
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = bitcast %struct.S.12* [[REF_TMP]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP13]], i8* align 4 [[TMP14]], i64 4, i1 false)
|
|
// CHECK1-NEXT: call void @_ZN1SIiED1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[REF_TMP]]) #[[ATTR5]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S_12]], %struct.S.12* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S_12]], %struct.S.12* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S.12* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP12]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE3]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK1: omp.arraycpy.done3:
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiEC2Ev
|
|
// CHECK1-SAME: (%struct.S.12* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK1-NEXT: store %struct.S.12* [[THIS]], %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S.12*, %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S_12:%.*]], %struct.S.12* [[THIS1]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load volatile double, double* @g, align 8
|
|
// CHECK1-NEXT: [[CONV:%.*]] = fptosi double [[TMP0]] to i32
|
|
// CHECK1-NEXT: store i32 [[CONV]], i32* [[F]], align 4
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiEC2Ei
|
|
// CHECK1-SAME: (%struct.S.12* nonnull align 4 dereferenceable(4) [[THIS:%.*]], i32 [[A:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK1-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: store %struct.S.12* [[THIS]], %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: store i32 [[A]], i32* [[A_ADDR]], align 4
|
|
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S.12*, %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S_12:%.*]], %struct.S.12* [[THIS1]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load i32, i32* [[A_ADDR]], align 4
|
|
// CHECK1-NEXT: [[CONV:%.*]] = sitofp i32 [[TMP0]] to double
|
|
// CHECK1-NEXT: [[TMP1:%.*]] = load volatile double, double* @g, align 8
|
|
// CHECK1-NEXT: [[ADD:%.*]] = fadd double [[CONV]], [[TMP1]]
|
|
// CHECK1-NEXT: [[CONV2:%.*]] = fptosi double [[ADD]] to i32
|
|
// CHECK1-NEXT: store i32 [[CONV2]], i32* [[F]], align 4
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiED2Ev
|
|
// CHECK1-SAME: (%struct.S.12* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK1-NEXT: store %struct.S.12* [[THIS]], %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S.12*, %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@main
|
|
// CHECK2-SAME: () #[[ATTR0:[0-9]+]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[TEST:%.*]] = alloca [[STRUCT_S:%.*]], align 4
|
|
// CHECK2-NEXT: [[T_VAR:%.*]] = alloca float, align 4
|
|
// CHECK2-NEXT: [[T_VAR1:%.*]] = alloca float, align 4
|
|
// CHECK2-NEXT: [[VEC:%.*]] = alloca [2 x i32], align 4
|
|
// CHECK2-NEXT: [[S_ARR:%.*]] = alloca [4 x %struct.S], align 16
|
|
// CHECK2-NEXT: [[VAR:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK2-NEXT: [[VAR1:%.*]] = alloca [[STRUCT_S]], align 4
|
|
// CHECK2-NEXT: [[ARRS:%.*]] = alloca [10 x [4 x %struct.S]], align 16
|
|
// CHECK2-NEXT: [[VAR2:%.*]] = alloca %struct.S**, align 8
|
|
// CHECK2-NEXT: [[VVAR2:%.*]] = alloca [5 x %struct.S], align 16
|
|
// CHECK2-NEXT: [[VAR3:%.*]] = alloca [4 x %struct.S]*, align 8
|
|
// CHECK2-NEXT: [[OMP_OUTLINED_ARG_AGG_:%.*]] = alloca [[STRUCT_ANON:%.*]], align 8
|
|
// CHECK2-NEXT: [[SAVED_STACK:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: [[__VLA_EXPR0:%.*]] = alloca i64, align 8
|
|
// CHECK2-NEXT: [[OMP_OUTLINED_ARG_AGG_10:%.*]] = alloca [[STRUCT_ANON_0:%.*]], align 8
|
|
// CHECK2-NEXT: [[OMP_OUTLINED_ARG_AGG_11:%.*]] = alloca [[STRUCT_ANON_1:%.*]], align 8
|
|
// CHECK2-NEXT: [[OMP_OUTLINED_ARG_AGG_12:%.*]] = alloca [[STRUCT_ANON_2:%.*]], align 8
|
|
// CHECK2-NEXT: [[OMP_OUTLINED_ARG_AGG_13:%.*]] = alloca [[STRUCT_ANON_3:%.*]], align 8
|
|
// CHECK2-NEXT: [[OMP_OUTLINED_ARG_AGG_14:%.*]] = alloca [[STRUCT_ANON_4:%.*]], align 8
|
|
// CHECK2-NEXT: [[OMP_OUTLINED_ARG_AGG_15:%.*]] = alloca [[STRUCT_ANON_5:%.*]], align 8
|
|
// CHECK2-NEXT: [[OMP_OUTLINED_ARG_AGG_16:%.*]] = alloca [[STRUCT_ANON_6:%.*]], align 8
|
|
// CHECK2-NEXT: [[OMP_OUTLINED_ARG_AGG_17:%.*]] = alloca [[STRUCT_ANON_7:%.*]], align 8
|
|
// CHECK2-NEXT: [[OMP_OUTLINED_ARG_AGG_18:%.*]] = alloca [[STRUCT_ANON_8:%.*]], align 8
|
|
// CHECK2-NEXT: [[OMP_OUTLINED_ARG_AGG_19:%.*]] = alloca [[STRUCT_ANON_9:%.*]], align 8
|
|
// CHECK2-NEXT: [[OMP_OUTLINED_ARG_AGG_20:%.*]] = alloca [[STRUCT_ANON_10:%.*]], align 8
|
|
// CHECK2-NEXT: [[OMP_OUTLINED_ARG_AGG_21:%.*]] = alloca [[STRUCT_ANON_11:%.*]], align 8
|
|
// CHECK2-NEXT: store i32 0, i32* [[RETVAL]], align 4
|
|
// CHECK2-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[TEST]])
|
|
// CHECK2-NEXT: store float 0.000000e+00, float* [[T_VAR]], align 4
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = bitcast [2 x i32]* [[VEC]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP0]], i8* align 4 bitcast ([2 x i32]* @__const.main.vec to i8*), i64 8, i1 false)
|
|
// CHECK2-NEXT: [[ARRAYINIT_BEGIN:%.*]] = getelementptr inbounds [4 x %struct.S], [4 x %struct.S]* [[S_ARR]], i64 0, i64 0
|
|
// CHECK2-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYINIT_BEGIN]], float 1.000000e+00)
|
|
// CHECK2-NEXT: [[ARRAYINIT_ELEMENT:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYINIT_BEGIN]], i64 1
|
|
// CHECK2-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYINIT_ELEMENT]], float 2.000000e+00)
|
|
// CHECK2-NEXT: [[ARRAYINIT_ELEMENT1:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYINIT_ELEMENT]], i64 1
|
|
// CHECK2-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYINIT_ELEMENT1]], float 3.000000e+00)
|
|
// CHECK2-NEXT: [[ARRAYINIT_ELEMENT2:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYINIT_ELEMENT1]], i64 1
|
|
// CHECK2-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYINIT_ELEMENT2]], float 4.000000e+00)
|
|
// CHECK2-NEXT: store %struct.S* [[TEST]], %struct.S** [[VAR]], align 8
|
|
// CHECK2-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[VAR1]])
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [10 x [4 x %struct.S]], [10 x [4 x %struct.S]]* [[ARRS]], i32 0, i32 0, i32 0
|
|
// CHECK2-NEXT: [[ARRAYCTOR_END:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN]], i64 40
|
|
// CHECK2-NEXT: br label [[ARRAYCTOR_LOOP:%.*]]
|
|
// CHECK2: arrayctor.loop:
|
|
// CHECK2-NEXT: [[ARRAYCTOR_CUR:%.*]] = phi %struct.S* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[ARRAYCTOR_NEXT:%.*]], [[ARRAYCTOR_LOOP]] ]
|
|
// CHECK2-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYCTOR_CUR]])
|
|
// CHECK2-NEXT: [[ARRAYCTOR_NEXT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYCTOR_CUR]], i64 1
|
|
// CHECK2-NEXT: [[ARRAYCTOR_DONE:%.*]] = icmp eq %struct.S* [[ARRAYCTOR_NEXT]], [[ARRAYCTOR_END]]
|
|
// CHECK2-NEXT: br i1 [[ARRAYCTOR_DONE]], label [[ARRAYCTOR_CONT:%.*]], label [[ARRAYCTOR_LOOP]]
|
|
// CHECK2: arrayctor.cont:
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call %struct.S** @_Z3foov()
|
|
// CHECK2-NEXT: store %struct.S** [[CALL]], %struct.S*** [[VAR2]], align 8
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN3:%.*]] = getelementptr inbounds [5 x %struct.S], [5 x %struct.S]* [[VVAR2]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[ARRAYCTOR_END4:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN3]], i64 5
|
|
// CHECK2-NEXT: br label [[ARRAYCTOR_LOOP5:%.*]]
|
|
// CHECK2: arrayctor.loop5:
|
|
// CHECK2-NEXT: [[ARRAYCTOR_CUR6:%.*]] = phi %struct.S* [ [[ARRAY_BEGIN3]], [[ARRAYCTOR_CONT]] ], [ [[ARRAYCTOR_NEXT7:%.*]], [[ARRAYCTOR_LOOP5]] ]
|
|
// CHECK2-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYCTOR_CUR6]])
|
|
// CHECK2-NEXT: [[ARRAYCTOR_NEXT7]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYCTOR_CUR6]], i64 1
|
|
// CHECK2-NEXT: [[ARRAYCTOR_DONE8:%.*]] = icmp eq %struct.S* [[ARRAYCTOR_NEXT7]], [[ARRAYCTOR_END4]]
|
|
// CHECK2-NEXT: br i1 [[ARRAYCTOR_DONE8]], label [[ARRAYCTOR_CONT9:%.*]], label [[ARRAYCTOR_LOOP5]]
|
|
// CHECK2: arrayctor.cont9:
|
|
// CHECK2-NEXT: store [4 x %struct.S]* [[S_ARR]], [4 x %struct.S]** [[VAR3]], align 8
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[OMP_OUTLINED_ARG_AGG_]], i32 0, i32 0
|
|
// CHECK2-NEXT: store float* [[T_VAR]], float** [[TMP1]], align 8
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[OMP_OUTLINED_ARG_AGG_]], i32 0, i32 1
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = load %struct.S*, %struct.S** [[VAR]], align 8
|
|
// CHECK2-NEXT: store %struct.S* [[TMP3]], %struct.S** [[TMP2]], align 8
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[OMP_OUTLINED_ARG_AGG_]], i32 0, i32 2
|
|
// CHECK2-NEXT: store %struct.S* [[VAR1]], %struct.S** [[TMP4]], align 8
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[OMP_OUTLINED_ARG_AGG_]], i32 0, i32 3
|
|
// CHECK2-NEXT: store float* [[T_VAR1]], float** [[TMP5]], align 8
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[OMP_OUTLINED_ARG_AGG_]], i32 0, i32 4
|
|
// CHECK2-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[TMP6]], align 8
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[OMP_OUTLINED_ARG_AGG_]], i32 0, i32 5
|
|
// CHECK2-NEXT: store [4 x %struct.S]* [[S_ARR]], [4 x %struct.S]** [[TMP7]], align 8
|
|
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3:[0-9]+]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon*)* @.omp_outlined. to void (i32*, i32*, ...)*), %struct.anon* [[OMP_OUTLINED_ARG_AGG_]])
|
|
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[VEC]], i64 0, i64 1
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = zext i32 [[TMP8]] to i64
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = call i8* @llvm.stacksave()
|
|
// CHECK2-NEXT: store i8* [[TMP10]], i8** [[SAVED_STACK]], align 8
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = mul nuw i64 10, [[TMP9]]
|
|
// CHECK2-NEXT: [[VLA:%.*]] = alloca i32, i64 [[TMP11]], align 16
|
|
// CHECK2-NEXT: store i64 [[TMP9]], i64* [[__VLA_EXPR0]], align 8
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = getelementptr inbounds [[STRUCT_ANON_0]], %struct.anon.0* [[OMP_OUTLINED_ARG_AGG_10]], i32 0, i32 0
|
|
// CHECK2-NEXT: store i64 10, i64* [[TMP12]], align 8
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = getelementptr inbounds [[STRUCT_ANON_0]], %struct.anon.0* [[OMP_OUTLINED_ARG_AGG_10]], i32 0, i32 1
|
|
// CHECK2-NEXT: store i64 [[TMP9]], i64* [[TMP13]], align 8
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = getelementptr inbounds [[STRUCT_ANON_0]], %struct.anon.0* [[OMP_OUTLINED_ARG_AGG_10]], i32 0, i32 2
|
|
// CHECK2-NEXT: store i32* [[VLA]], i32** [[TMP14]], align 8
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = getelementptr inbounds [[STRUCT_ANON_0]], %struct.anon.0* [[OMP_OUTLINED_ARG_AGG_10]], i32 0, i32 3
|
|
// CHECK2-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[TMP15]], align 8
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = getelementptr inbounds [[STRUCT_ANON_0]], %struct.anon.0* [[OMP_OUTLINED_ARG_AGG_10]], i32 0, i32 4
|
|
// CHECK2-NEXT: store [10 x [4 x %struct.S]]* [[ARRS]], [10 x [4 x %struct.S]]** [[TMP16]], align 8
|
|
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.0*)* @.omp_outlined..1 to void (i32*, i32*, ...)*), %struct.anon.0* [[OMP_OUTLINED_ARG_AGG_10]])
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = getelementptr inbounds [[STRUCT_ANON_1]], %struct.anon.1* [[OMP_OUTLINED_ARG_AGG_11]], i32 0, i32 0
|
|
// CHECK2-NEXT: store i64 10, i64* [[TMP17]], align 8
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = getelementptr inbounds [[STRUCT_ANON_1]], %struct.anon.1* [[OMP_OUTLINED_ARG_AGG_11]], i32 0, i32 1
|
|
// CHECK2-NEXT: store i64 [[TMP9]], i64* [[TMP18]], align 8
|
|
// CHECK2-NEXT: [[TMP19:%.*]] = getelementptr inbounds [[STRUCT_ANON_1]], %struct.anon.1* [[OMP_OUTLINED_ARG_AGG_11]], i32 0, i32 2
|
|
// CHECK2-NEXT: store i32* [[VLA]], i32** [[TMP19]], align 8
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = getelementptr inbounds [[STRUCT_ANON_1]], %struct.anon.1* [[OMP_OUTLINED_ARG_AGG_11]], i32 0, i32 3
|
|
// CHECK2-NEXT: store [10 x [4 x %struct.S]]* [[ARRS]], [10 x [4 x %struct.S]]** [[TMP20]], align 8
|
|
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.1*)* @.omp_outlined..3 to void (i32*, i32*, ...)*), %struct.anon.1* [[OMP_OUTLINED_ARG_AGG_11]])
|
|
// CHECK2-NEXT: [[TMP21:%.*]] = getelementptr inbounds [[STRUCT_ANON_2]], %struct.anon.2* [[OMP_OUTLINED_ARG_AGG_12]], i32 0, i32 0
|
|
// CHECK2-NEXT: store i64 10, i64* [[TMP21]], align 8
|
|
// CHECK2-NEXT: [[TMP22:%.*]] = getelementptr inbounds [[STRUCT_ANON_2]], %struct.anon.2* [[OMP_OUTLINED_ARG_AGG_12]], i32 0, i32 1
|
|
// CHECK2-NEXT: store i64 [[TMP9]], i64* [[TMP22]], align 8
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = getelementptr inbounds [[STRUCT_ANON_2]], %struct.anon.2* [[OMP_OUTLINED_ARG_AGG_12]], i32 0, i32 2
|
|
// CHECK2-NEXT: store i32* [[VLA]], i32** [[TMP23]], align 8
|
|
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.2*)* @.omp_outlined..5 to void (i32*, i32*, ...)*), %struct.anon.2* [[OMP_OUTLINED_ARG_AGG_12]])
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = getelementptr inbounds [[STRUCT_ANON_3]], %struct.anon.3* [[OMP_OUTLINED_ARG_AGG_13]], i32 0, i32 0
|
|
// CHECK2-NEXT: store %struct.S*** [[VAR2]], %struct.S**** [[TMP24]], align 8
|
|
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.3*)* @.omp_outlined..7 to void (i32*, i32*, ...)*), %struct.anon.3* [[OMP_OUTLINED_ARG_AGG_13]])
|
|
// CHECK2-NEXT: [[TMP25:%.*]] = getelementptr inbounds [[STRUCT_ANON_4]], %struct.anon.4* [[OMP_OUTLINED_ARG_AGG_14]], i32 0, i32 0
|
|
// CHECK2-NEXT: store %struct.S*** [[VAR2]], %struct.S**** [[TMP25]], align 8
|
|
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.4*)* @.omp_outlined..9 to void (i32*, i32*, ...)*), %struct.anon.4* [[OMP_OUTLINED_ARG_AGG_14]])
|
|
// CHECK2-NEXT: [[TMP26:%.*]] = getelementptr inbounds [[STRUCT_ANON_5]], %struct.anon.5* [[OMP_OUTLINED_ARG_AGG_15]], i32 0, i32 0
|
|
// CHECK2-NEXT: store %struct.S*** [[VAR2]], %struct.S**** [[TMP26]], align 8
|
|
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.5*)* @.omp_outlined..11 to void (i32*, i32*, ...)*), %struct.anon.5* [[OMP_OUTLINED_ARG_AGG_15]])
|
|
// CHECK2-NEXT: [[TMP27:%.*]] = getelementptr inbounds [[STRUCT_ANON_6]], %struct.anon.6* [[OMP_OUTLINED_ARG_AGG_16]], i32 0, i32 0
|
|
// CHECK2-NEXT: store %struct.S*** [[VAR2]], %struct.S**** [[TMP27]], align 8
|
|
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.6*)* @.omp_outlined..13 to void (i32*, i32*, ...)*), %struct.anon.6* [[OMP_OUTLINED_ARG_AGG_16]])
|
|
// CHECK2-NEXT: [[TMP28:%.*]] = getelementptr inbounds [[STRUCT_ANON_7]], %struct.anon.7* [[OMP_OUTLINED_ARG_AGG_17]], i32 0, i32 0
|
|
// CHECK2-NEXT: store [5 x %struct.S]* [[VVAR2]], [5 x %struct.S]** [[TMP28]], align 8
|
|
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.7*)* @.omp_outlined..15 to void (i32*, i32*, ...)*), %struct.anon.7* [[OMP_OUTLINED_ARG_AGG_17]])
|
|
// CHECK2-NEXT: [[TMP29:%.*]] = getelementptr inbounds [[STRUCT_ANON_8]], %struct.anon.8* [[OMP_OUTLINED_ARG_AGG_18]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP30:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[VAR3]], align 8
|
|
// CHECK2-NEXT: store [4 x %struct.S]* [[TMP30]], [4 x %struct.S]** [[TMP29]], align 8
|
|
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.8*)* @.omp_outlined..17 to void (i32*, i32*, ...)*), %struct.anon.8* [[OMP_OUTLINED_ARG_AGG_18]])
|
|
// CHECK2-NEXT: [[TMP31:%.*]] = getelementptr inbounds [[STRUCT_ANON_9]], %struct.anon.9* [[OMP_OUTLINED_ARG_AGG_19]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP32:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[VAR3]], align 8
|
|
// CHECK2-NEXT: store [4 x %struct.S]* [[TMP32]], [4 x %struct.S]** [[TMP31]], align 8
|
|
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.9*)* @.omp_outlined..19 to void (i32*, i32*, ...)*), %struct.anon.9* [[OMP_OUTLINED_ARG_AGG_19]])
|
|
// CHECK2-NEXT: [[TMP33:%.*]] = getelementptr inbounds [[STRUCT_ANON_10]], %struct.anon.10* [[OMP_OUTLINED_ARG_AGG_20]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP34:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[VAR3]], align 8
|
|
// CHECK2-NEXT: store [4 x %struct.S]* [[TMP34]], [4 x %struct.S]** [[TMP33]], align 8
|
|
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.10*)* @.omp_outlined..21 to void (i32*, i32*, ...)*), %struct.anon.10* [[OMP_OUTLINED_ARG_AGG_20]])
|
|
// CHECK2-NEXT: [[TMP35:%.*]] = getelementptr inbounds [[STRUCT_ANON_11]], %struct.anon.11* [[OMP_OUTLINED_ARG_AGG_21]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP36:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[VAR3]], align 8
|
|
// CHECK2-NEXT: store [4 x %struct.S]* [[TMP36]], [4 x %struct.S]** [[TMP35]], align 8
|
|
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.11*)* @.omp_outlined..23 to void (i32*, i32*, ...)*), %struct.anon.11* [[OMP_OUTLINED_ARG_AGG_21]])
|
|
// CHECK2-NEXT: [[CALL22:%.*]] = call i32 @_Z5tmainIiLi42EET_v()
|
|
// CHECK2-NEXT: store i32 [[CALL22]], i32* [[RETVAL]], align 4
|
|
// CHECK2-NEXT: [[TMP37:%.*]] = load i8*, i8** [[SAVED_STACK]], align 8
|
|
// CHECK2-NEXT: call void @llvm.stackrestore(i8* [[TMP37]])
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN23:%.*]] = getelementptr inbounds [5 x %struct.S], [5 x %struct.S]* [[VVAR2]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP38:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN23]], i64 5
|
|
// CHECK2-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
|
|
// CHECK2: arraydestroy.body:
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP38]], [[ARRAYCTOR_CONT9]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
|
|
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5:[0-9]+]]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN23]]
|
|
// CHECK2-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE24:%.*]], label [[ARRAYDESTROY_BODY]]
|
|
// CHECK2: arraydestroy.done24:
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN25:%.*]] = getelementptr inbounds [10 x [4 x %struct.S]], [10 x [4 x %struct.S]]* [[ARRS]], i32 0, i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP39:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN25]], i64 40
|
|
// CHECK2-NEXT: br label [[ARRAYDESTROY_BODY26:%.*]]
|
|
// CHECK2: arraydestroy.body26:
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENTPAST27:%.*]] = phi %struct.S* [ [[TMP39]], [[ARRAYDESTROY_DONE24]] ], [ [[ARRAYDESTROY_ELEMENT28:%.*]], [[ARRAYDESTROY_BODY26]] ]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENT28]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST27]], i64 -1
|
|
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT28]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_DONE29:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT28]], [[ARRAY_BEGIN25]]
|
|
// CHECK2-NEXT: br i1 [[ARRAYDESTROY_DONE29]], label [[ARRAYDESTROY_DONE30:%.*]], label [[ARRAYDESTROY_BODY26]]
|
|
// CHECK2: arraydestroy.done30:
|
|
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[VAR1]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN31:%.*]] = getelementptr inbounds [4 x %struct.S], [4 x %struct.S]* [[S_ARR]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP40:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN31]], i64 4
|
|
// CHECK2-NEXT: br label [[ARRAYDESTROY_BODY32:%.*]]
|
|
// CHECK2: arraydestroy.body32:
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENTPAST33:%.*]] = phi %struct.S* [ [[TMP40]], [[ARRAYDESTROY_DONE30]] ], [ [[ARRAYDESTROY_ELEMENT34:%.*]], [[ARRAYDESTROY_BODY32]] ]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENT34]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST33]], i64 -1
|
|
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT34]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_DONE35:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT34]], [[ARRAY_BEGIN31]]
|
|
// CHECK2-NEXT: br i1 [[ARRAYDESTROY_DONE35]], label [[ARRAYDESTROY_DONE36:%.*]], label [[ARRAYDESTROY_BODY32]]
|
|
// CHECK2: arraydestroy.done36:
|
|
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[TEST]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: [[TMP41:%.*]] = load i32, i32* [[RETVAL]], align 4
|
|
// CHECK2-NEXT: ret i32 [[TMP41]]
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfEC1Ev
|
|
// CHECK2-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1:[0-9]+]] align 2 {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK2-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: call void @_ZN1SIfEC2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]])
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfEC1Ef
|
|
// CHECK2-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], float [[A:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
|
|
// CHECK2-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: store float [[A]], float* [[A_ADDR]], align 4
|
|
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load float, float* [[A_ADDR]], align 4
|
|
// CHECK2-NEXT: call void @_ZN1SIfEC2Ef(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]], float [[TMP0]])
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined.
|
|
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon* noalias [[__CONTEXT:%.*]]) #[[ATTR4:[0-9]+]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon*, align 8
|
|
// CHECK2-NEXT: [[TMP:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK2-NEXT: [[_TMP1:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK2-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[_TMP2:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[T_VAR:%.*]] = alloca float, align 4
|
|
// CHECK2-NEXT: [[VAR:%.*]] = alloca [[STRUCT_S:%.*]], align 4
|
|
// CHECK2-NEXT: [[_TMP3:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK2-NEXT: [[VAR1:%.*]] = alloca [[STRUCT_S]], align 4
|
|
// CHECK2-NEXT: [[T_VAR1:%.*]] = alloca float, align 4
|
|
// CHECK2-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [4 x i8*], align 8
|
|
// CHECK2-NEXT: [[REF_TMP:%.*]] = alloca [[STRUCT_S]], align 4
|
|
// CHECK2-NEXT: [[ATOMIC_TEMP:%.*]] = alloca float, align 4
|
|
// CHECK2-NEXT: [[_TMP18:%.*]] = alloca float, align 4
|
|
// CHECK2-NEXT: [[REF_TMP21:%.*]] = alloca [[STRUCT_S]], align 4
|
|
// CHECK2-NEXT: [[ATOMIC_TEMP31:%.*]] = alloca float, align 4
|
|
// CHECK2-NEXT: [[_TMP32:%.*]] = alloca float, align 4
|
|
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store %struct.anon* [[__CONTEXT]], %struct.anon** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load %struct.anon*, %struct.anon** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON:%.*]], %struct.anon* [[TMP0]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load float*, float** [[TMP1]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[TMP0]], i32 0, i32 1
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load %struct.S*, %struct.S** [[TMP3]], align 8
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[TMP0]], i32 0, i32 2
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = load %struct.S*, %struct.S** [[TMP5]], align 8
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[TMP0]], i32 0, i32 3
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = load float*, float** [[TMP7]], align 8
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[TMP0]], i32 0, i32 4
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load [2 x i32]*, [2 x i32]** [[TMP9]], align 8
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[TMP0]], i32 0, i32 5
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[TMP11]], align 8
|
|
// CHECK2-NEXT: store %struct.S* [[TMP4]], %struct.S** [[TMP]], align 8
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = load %struct.S*, %struct.S** [[TMP]], align 8
|
|
// CHECK2-NEXT: store %struct.S* [[TMP13]], %struct.S** [[_TMP1]], align 8
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK2-NEXT: store float 0.000000e+00, float* [[T_VAR]], align 4
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = load %struct.S*, %struct.S** [[_TMP1]], align 8
|
|
// CHECK2-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[VAR]])
|
|
// CHECK2-NEXT: store %struct.S* [[VAR]], %struct.S** [[_TMP3]], align 8
|
|
// CHECK2-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[VAR1]])
|
|
// CHECK2-NEXT: store float 0x47EFFFFFE0000000, float* [[T_VAR1]], align 4
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = load i32, i32* [[TMP15]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 [[TMP16]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP17]], 1
|
|
// CHECK2-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK2: cond.true:
|
|
// CHECK2-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK2: cond.false:
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END]]
|
|
// CHECK2: cond.end:
|
|
// CHECK2-NEXT: [[COND:%.*]] = phi i32 [ 1, [[COND_TRUE]] ], [ [[TMP18]], [[COND_FALSE]] ]
|
|
// CHECK2-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP19:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP19]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK2: omp.inner.for.cond:
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[TMP21:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP4:%.*]] = icmp sle i32 [[TMP20]], [[TMP21]]
|
|
// CHECK2-NEXT: br i1 [[CMP4]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK2: omp.inner.for.cond.cleanup:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK2: omp.inner.for.body:
|
|
// CHECK2-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP22]], 1
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = load float, float* [[T_VAR]], align 4
|
|
// CHECK2-NEXT: [[CONV:%.*]] = fptosi float [[TMP23]] to i32
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK2-NEXT: [[IDXPROM:%.*]] = sext i32 [[TMP24]] to i64
|
|
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[TMP10]], i64 0, i64 [[IDXPROM]]
|
|
// CHECK2-NEXT: store i32 [[CONV]], i32* [[ARRAYIDX]], align 4
|
|
// CHECK2-NEXT: [[TMP25:%.*]] = load %struct.S*, %struct.S** [[_TMP3]], align 8
|
|
// CHECK2-NEXT: [[TMP26:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK2-NEXT: [[IDXPROM5:%.*]] = sext i32 [[TMP26]] to i64
|
|
// CHECK2-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds [4 x %struct.S], [4 x %struct.S]* [[TMP12]], i64 0, i64 [[IDXPROM5]]
|
|
// CHECK2-NEXT: [[TMP27:%.*]] = bitcast %struct.S* [[ARRAYIDX6]] to i8*
|
|
// CHECK2-NEXT: [[TMP28:%.*]] = bitcast %struct.S* [[TMP25]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP27]], i8* align 4 [[TMP28]], i64 4, i1 false)
|
|
// CHECK2-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK2: omp.body.continue:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK2: omp.inner.for.inc:
|
|
// CHECK2-NEXT: [[TMP29:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[ADD7:%.*]] = add nsw i32 [[TMP29]], 1
|
|
// CHECK2-NEXT: store i32 [[ADD7]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK2: omp.inner.for.end:
|
|
// CHECK2-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK2: omp.loop.exit:
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP16]])
|
|
// CHECK2-NEXT: [[TMP30:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP31:%.*]] = bitcast float* [[T_VAR]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP31]], i8** [[TMP30]], align 8
|
|
// CHECK2-NEXT: [[TMP32:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 1
|
|
// CHECK2-NEXT: [[TMP33:%.*]] = bitcast %struct.S* [[VAR]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP33]], i8** [[TMP32]], align 8
|
|
// CHECK2-NEXT: [[TMP34:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 2
|
|
// CHECK2-NEXT: [[TMP35:%.*]] = bitcast %struct.S* [[VAR1]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP35]], i8** [[TMP34]], align 8
|
|
// CHECK2-NEXT: [[TMP36:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 3
|
|
// CHECK2-NEXT: [[TMP37:%.*]] = bitcast float* [[T_VAR1]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP37]], i8** [[TMP36]], align 8
|
|
// CHECK2-NEXT: [[TMP38:%.*]] = bitcast [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK2-NEXT: [[TMP39:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2:[0-9]+]], i32 [[TMP16]], i32 4, i64 32, i8* [[TMP38]], void (i8*, i8*)* @.omp.reduction.reduction_func, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: switch i32 [[TMP39]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK2-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK2-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK2-NEXT: ]
|
|
// CHECK2: .omp.reduction.case1:
|
|
// CHECK2-NEXT: [[TMP40:%.*]] = load float, float* [[TMP2]], align 4
|
|
// CHECK2-NEXT: [[TMP41:%.*]] = load float, float* [[T_VAR]], align 4
|
|
// CHECK2-NEXT: [[ADD8:%.*]] = fadd float [[TMP40]], [[TMP41]]
|
|
// CHECK2-NEXT: store float [[ADD8]], float* [[TMP2]], align 4
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[TMP14]], %struct.S* nonnull align 4 dereferenceable(4) [[VAR]])
|
|
// CHECK2-NEXT: [[TMP42:%.*]] = bitcast %struct.S* [[TMP14]] to i8*
|
|
// CHECK2-NEXT: [[TMP43:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP42]], i8* align 4 [[TMP43]], i64 4, i1 false)
|
|
// CHECK2-NEXT: [[CALL9:%.*]] = call float @_ZN1SIfEcvfEv(%struct.S* nonnull align 4 dereferenceable(4) [[TMP6]])
|
|
// CHECK2-NEXT: [[TOBOOL:%.*]] = fcmp une float [[CALL9]], 0.000000e+00
|
|
// CHECK2-NEXT: br i1 [[TOBOOL]], label [[LAND_RHS:%.*]], label [[LAND_END:%.*]]
|
|
// CHECK2: land.rhs:
|
|
// CHECK2-NEXT: [[CALL10:%.*]] = call float @_ZN1SIfEcvfEv(%struct.S* nonnull align 4 dereferenceable(4) [[VAR1]])
|
|
// CHECK2-NEXT: [[TOBOOL11:%.*]] = fcmp une float [[CALL10]], 0.000000e+00
|
|
// CHECK2-NEXT: br label [[LAND_END]]
|
|
// CHECK2: land.end:
|
|
// CHECK2-NEXT: [[TMP44:%.*]] = phi i1 [ false, [[DOTOMP_REDUCTION_CASE1]] ], [ [[TOBOOL11]], [[LAND_RHS]] ]
|
|
// CHECK2-NEXT: [[CONV12:%.*]] = uitofp i1 [[TMP44]] to float
|
|
// CHECK2-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) [[REF_TMP]], float [[CONV12]])
|
|
// CHECK2-NEXT: [[TMP45:%.*]] = bitcast %struct.S* [[TMP6]] to i8*
|
|
// CHECK2-NEXT: [[TMP46:%.*]] = bitcast %struct.S* [[REF_TMP]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP45]], i8* align 4 [[TMP46]], i64 4, i1 false)
|
|
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[REF_TMP]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: [[TMP47:%.*]] = load float, float* [[TMP8]], align 4
|
|
// CHECK2-NEXT: [[TMP48:%.*]] = load float, float* [[T_VAR1]], align 4
|
|
// CHECK2-NEXT: [[CMP13:%.*]] = fcmp olt float [[TMP47]], [[TMP48]]
|
|
// CHECK2-NEXT: br i1 [[CMP13]], label [[COND_TRUE14:%.*]], label [[COND_FALSE15:%.*]]
|
|
// CHECK2: cond.true14:
|
|
// CHECK2-NEXT: [[TMP49:%.*]] = load float, float* [[TMP8]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END16:%.*]]
|
|
// CHECK2: cond.false15:
|
|
// CHECK2-NEXT: [[TMP50:%.*]] = load float, float* [[T_VAR1]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END16]]
|
|
// CHECK2: cond.end16:
|
|
// CHECK2-NEXT: [[COND17:%.*]] = phi float [ [[TMP49]], [[COND_TRUE14]] ], [ [[TMP50]], [[COND_FALSE15]] ]
|
|
// CHECK2-NEXT: store float [[COND17]], float* [[TMP8]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP16]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.case2:
|
|
// CHECK2-NEXT: [[TMP51:%.*]] = load float, float* [[T_VAR]], align 4
|
|
// CHECK2-NEXT: [[TMP52:%.*]] = bitcast float* [[TMP2]] to i32*
|
|
// CHECK2-NEXT: [[ATOMIC_LOAD:%.*]] = load atomic i32, i32* [[TMP52]] monotonic, align 4
|
|
// CHECK2-NEXT: br label [[ATOMIC_CONT:%.*]]
|
|
// CHECK2: atomic_cont:
|
|
// CHECK2-NEXT: [[TMP53:%.*]] = phi i32 [ [[ATOMIC_LOAD]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[TMP61:%.*]], [[ATOMIC_CONT]] ]
|
|
// CHECK2-NEXT: [[TMP54:%.*]] = bitcast float* [[ATOMIC_TEMP]] to i32*
|
|
// CHECK2-NEXT: [[TMP55:%.*]] = bitcast i32 [[TMP53]] to float
|
|
// CHECK2-NEXT: store float [[TMP55]], float* [[_TMP18]], align 4
|
|
// CHECK2-NEXT: [[TMP56:%.*]] = load float, float* [[_TMP18]], align 4
|
|
// CHECK2-NEXT: [[TMP57:%.*]] = load float, float* [[T_VAR]], align 4
|
|
// CHECK2-NEXT: [[ADD19:%.*]] = fadd float [[TMP56]], [[TMP57]]
|
|
// CHECK2-NEXT: store float [[ADD19]], float* [[ATOMIC_TEMP]], align 4
|
|
// CHECK2-NEXT: [[TMP58:%.*]] = load i32, i32* [[TMP54]], align 4
|
|
// CHECK2-NEXT: [[TMP59:%.*]] = bitcast float* [[TMP2]] to i32*
|
|
// CHECK2-NEXT: [[TMP60:%.*]] = cmpxchg i32* [[TMP59]], i32 [[TMP53]], i32 [[TMP58]] monotonic monotonic, align 4
|
|
// CHECK2-NEXT: [[TMP61]] = extractvalue { i32, i1 } [[TMP60]], 0
|
|
// CHECK2-NEXT: [[TMP62:%.*]] = extractvalue { i32, i1 } [[TMP60]], 1
|
|
// CHECK2-NEXT: br i1 [[TMP62]], label [[ATOMIC_EXIT:%.*]], label [[ATOMIC_CONT]]
|
|
// CHECK2: atomic_exit:
|
|
// CHECK2-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP16]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[CALL20:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[TMP14]], %struct.S* nonnull align 4 dereferenceable(4) [[VAR]])
|
|
// CHECK2-NEXT: [[TMP63:%.*]] = bitcast %struct.S* [[TMP14]] to i8*
|
|
// CHECK2-NEXT: [[TMP64:%.*]] = bitcast %struct.S* [[CALL20]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP63]], i8* align 4 [[TMP64]], i64 4, i1 false)
|
|
// CHECK2-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP16]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP16]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[CALL22:%.*]] = call float @_ZN1SIfEcvfEv(%struct.S* nonnull align 4 dereferenceable(4) [[TMP6]])
|
|
// CHECK2-NEXT: [[TOBOOL23:%.*]] = fcmp une float [[CALL22]], 0.000000e+00
|
|
// CHECK2-NEXT: br i1 [[TOBOOL23]], label [[LAND_RHS24:%.*]], label [[LAND_END27:%.*]]
|
|
// CHECK2: land.rhs24:
|
|
// CHECK2-NEXT: [[CALL25:%.*]] = call float @_ZN1SIfEcvfEv(%struct.S* nonnull align 4 dereferenceable(4) [[VAR1]])
|
|
// CHECK2-NEXT: [[TOBOOL26:%.*]] = fcmp une float [[CALL25]], 0.000000e+00
|
|
// CHECK2-NEXT: br label [[LAND_END27]]
|
|
// CHECK2: land.end27:
|
|
// CHECK2-NEXT: [[TMP65:%.*]] = phi i1 [ false, [[ATOMIC_EXIT]] ], [ [[TOBOOL26]], [[LAND_RHS24]] ]
|
|
// CHECK2-NEXT: [[CONV28:%.*]] = uitofp i1 [[TMP65]] to float
|
|
// CHECK2-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) [[REF_TMP21]], float [[CONV28]])
|
|
// CHECK2-NEXT: [[TMP66:%.*]] = bitcast %struct.S* [[TMP6]] to i8*
|
|
// CHECK2-NEXT: [[TMP67:%.*]] = bitcast %struct.S* [[REF_TMP21]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP66]], i8* align 4 [[TMP67]], i64 4, i1 false)
|
|
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[REF_TMP21]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP16]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[TMP68:%.*]] = load float, float* [[T_VAR1]], align 4
|
|
// CHECK2-NEXT: [[TMP69:%.*]] = bitcast float* [[TMP8]] to i32*
|
|
// CHECK2-NEXT: [[ATOMIC_LOAD29:%.*]] = load atomic i32, i32* [[TMP69]] monotonic, align 4
|
|
// CHECK2-NEXT: br label [[ATOMIC_CONT30:%.*]]
|
|
// CHECK2: atomic_cont30:
|
|
// CHECK2-NEXT: [[TMP70:%.*]] = phi i32 [ [[ATOMIC_LOAD29]], [[LAND_END27]] ], [ [[TMP80:%.*]], [[COND_END36:%.*]] ]
|
|
// CHECK2-NEXT: [[TMP71:%.*]] = bitcast float* [[ATOMIC_TEMP31]] to i32*
|
|
// CHECK2-NEXT: [[TMP72:%.*]] = bitcast i32 [[TMP70]] to float
|
|
// CHECK2-NEXT: store float [[TMP72]], float* [[_TMP32]], align 4
|
|
// CHECK2-NEXT: [[TMP73:%.*]] = load float, float* [[_TMP32]], align 4
|
|
// CHECK2-NEXT: [[TMP74:%.*]] = load float, float* [[T_VAR1]], align 4
|
|
// CHECK2-NEXT: [[CMP33:%.*]] = fcmp olt float [[TMP73]], [[TMP74]]
|
|
// CHECK2-NEXT: br i1 [[CMP33]], label [[COND_TRUE34:%.*]], label [[COND_FALSE35:%.*]]
|
|
// CHECK2: cond.true34:
|
|
// CHECK2-NEXT: [[TMP75:%.*]] = load float, float* [[_TMP32]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END36]]
|
|
// CHECK2: cond.false35:
|
|
// CHECK2-NEXT: [[TMP76:%.*]] = load float, float* [[T_VAR1]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END36]]
|
|
// CHECK2: cond.end36:
|
|
// CHECK2-NEXT: [[COND37:%.*]] = phi float [ [[TMP75]], [[COND_TRUE34]] ], [ [[TMP76]], [[COND_FALSE35]] ]
|
|
// CHECK2-NEXT: store float [[COND37]], float* [[ATOMIC_TEMP31]], align 4
|
|
// CHECK2-NEXT: [[TMP77:%.*]] = load i32, i32* [[TMP71]], align 4
|
|
// CHECK2-NEXT: [[TMP78:%.*]] = bitcast float* [[TMP8]] to i32*
|
|
// CHECK2-NEXT: [[TMP79:%.*]] = cmpxchg i32* [[TMP78]], i32 [[TMP70]], i32 [[TMP77]] monotonic monotonic, align 4
|
|
// CHECK2-NEXT: [[TMP80]] = extractvalue { i32, i1 } [[TMP79]], 0
|
|
// CHECK2-NEXT: [[TMP81:%.*]] = extractvalue { i32, i1 } [[TMP79]], 1
|
|
// CHECK2-NEXT: br i1 [[TMP81]], label [[ATOMIC_EXIT38:%.*]], label [[ATOMIC_CONT30]]
|
|
// CHECK2: atomic_exit38:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP16]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.default:
|
|
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[VAR1]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[VAR]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4:[0-9]+]], i32 [[TMP16]])
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func
|
|
// CHECK2-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6:[0-9]+]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: [[REF_TMP:%.*]] = alloca [[STRUCT_S:%.*]], align 4
|
|
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [4 x i8*]*
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [4 x i8*]*
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to float*
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to float*
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 1
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = load i8*, i8** [[TMP12]], align 8
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = bitcast i8* [[TMP13]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 1
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = load i8*, i8** [[TMP15]], align 8
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = bitcast i8* [[TMP16]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 2
|
|
// CHECK2-NEXT: [[TMP19:%.*]] = load i8*, i8** [[TMP18]], align 8
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = bitcast i8* [[TMP19]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP21:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 2
|
|
// CHECK2-NEXT: [[TMP22:%.*]] = load i8*, i8** [[TMP21]], align 8
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = bitcast i8* [[TMP22]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 3
|
|
// CHECK2-NEXT: [[TMP25:%.*]] = load i8*, i8** [[TMP24]], align 8
|
|
// CHECK2-NEXT: [[TMP26:%.*]] = bitcast i8* [[TMP25]] to float*
|
|
// CHECK2-NEXT: [[TMP27:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 3
|
|
// CHECK2-NEXT: [[TMP28:%.*]] = load i8*, i8** [[TMP27]], align 8
|
|
// CHECK2-NEXT: [[TMP29:%.*]] = bitcast i8* [[TMP28]] to float*
|
|
// CHECK2-NEXT: [[TMP30:%.*]] = load float, float* [[TMP11]], align 4
|
|
// CHECK2-NEXT: [[TMP31:%.*]] = load float, float* [[TMP8]], align 4
|
|
// CHECK2-NEXT: [[ADD:%.*]] = fadd float [[TMP30]], [[TMP31]]
|
|
// CHECK2-NEXT: store float [[ADD]], float* [[TMP11]], align 4
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[TMP17]], %struct.S* nonnull align 4 dereferenceable(4) [[TMP14]])
|
|
// CHECK2-NEXT: [[TMP32:%.*]] = bitcast %struct.S* [[TMP17]] to i8*
|
|
// CHECK2-NEXT: [[TMP33:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP32]], i8* align 4 [[TMP33]], i64 4, i1 false)
|
|
// CHECK2-NEXT: [[CALL2:%.*]] = call float @_ZN1SIfEcvfEv(%struct.S* nonnull align 4 dereferenceable(4) [[TMP23]])
|
|
// CHECK2-NEXT: [[TOBOOL:%.*]] = fcmp une float [[CALL2]], 0.000000e+00
|
|
// CHECK2-NEXT: br i1 [[TOBOOL]], label [[LAND_RHS:%.*]], label [[LAND_END:%.*]]
|
|
// CHECK2: land.rhs:
|
|
// CHECK2-NEXT: [[CALL3:%.*]] = call float @_ZN1SIfEcvfEv(%struct.S* nonnull align 4 dereferenceable(4) [[TMP20]])
|
|
// CHECK2-NEXT: [[TOBOOL4:%.*]] = fcmp une float [[CALL3]], 0.000000e+00
|
|
// CHECK2-NEXT: br label [[LAND_END]]
|
|
// CHECK2: land.end:
|
|
// CHECK2-NEXT: [[TMP34:%.*]] = phi i1 [ false, [[ENTRY:%.*]] ], [ [[TOBOOL4]], [[LAND_RHS]] ]
|
|
// CHECK2-NEXT: [[CONV:%.*]] = uitofp i1 [[TMP34]] to float
|
|
// CHECK2-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) [[REF_TMP]], float [[CONV]])
|
|
// CHECK2-NEXT: [[TMP35:%.*]] = bitcast %struct.S* [[TMP23]] to i8*
|
|
// CHECK2-NEXT: [[TMP36:%.*]] = bitcast %struct.S* [[REF_TMP]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP35]], i8* align 4 [[TMP36]], i64 4, i1 false)
|
|
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[REF_TMP]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: [[TMP37:%.*]] = load float, float* [[TMP29]], align 4
|
|
// CHECK2-NEXT: [[TMP38:%.*]] = load float, float* [[TMP26]], align 4
|
|
// CHECK2-NEXT: [[CMP:%.*]] = fcmp olt float [[TMP37]], [[TMP38]]
|
|
// CHECK2-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK2: cond.true:
|
|
// CHECK2-NEXT: [[TMP39:%.*]] = load float, float* [[TMP29]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK2: cond.false:
|
|
// CHECK2-NEXT: [[TMP40:%.*]] = load float, float* [[TMP26]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END]]
|
|
// CHECK2: cond.end:
|
|
// CHECK2-NEXT: [[COND:%.*]] = phi float [ [[TMP39]], [[COND_TRUE]] ], [ [[TMP40]], [[COND_FALSE]] ]
|
|
// CHECK2-NEXT: store float [[COND]], float* [[TMP29]], align 4
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfEanERKS0_
|
|
// CHECK2-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], %struct.S* nonnull align 4 dereferenceable(4) [[TMP0:%.*]]) #[[ATTR7:[0-9]+]] align 2 {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK2-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: store %struct.S* [[TMP0]], %struct.S** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: ret %struct.S* [[THIS1]]
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfEcvfEv
|
|
// CHECK2-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) #[[ATTR7]] align 2 {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK2-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: ret float 0.000000e+00
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfED1Ev
|
|
// CHECK2-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK2-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: call void @_ZN1SIfED2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined..1
|
|
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.0* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.0*, align 8
|
|
// CHECK2-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[TMP:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[SAVED_STACK:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: [[__VLA_EXPR0:%.*]] = alloca i64, align 8
|
|
// CHECK2-NEXT: [[__VLA_EXPR1:%.*]] = alloca i64, align 8
|
|
// CHECK2-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [4 x i8*], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store %struct.anon.0* [[__CONTEXT]], %struct.anon.0** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load %struct.anon.0*, %struct.anon.0** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_0:%.*]], %struct.anon.0* [[TMP0]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i64, i64* [[TMP1]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_ANON_0]], %struct.anon.0* [[TMP0]], i32 0, i32 1
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i64, i64* [[TMP3]], align 8
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_ANON_0]], %struct.anon.0* [[TMP0]], i32 0, i32 2
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = load i32*, i32** [[TMP5]], align 8
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = getelementptr inbounds [[STRUCT_ANON_0]], %struct.anon.0* [[TMP0]], i32 0, i32 3
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = load [2 x i32]*, [2 x i32]** [[TMP7]], align 8
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_ANON_0]], %struct.anon.0* [[TMP0]], i32 0, i32 4
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load [10 x [4 x %struct.S]]*, [10 x [4 x %struct.S]]** [[TMP9]], align 8
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = mul nsw i64 1, [[TMP4]]
|
|
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[TMP6]], i64 [[TMP11]]
|
|
// CHECK2-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX]], i64 0
|
|
// CHECK2-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[TMP8]], i64 0, i64 1
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = load i32, i32* [[ARRAYIDX2]], align 4
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = sext i32 [[TMP12]] to i64
|
|
// CHECK2-NEXT: [[LB_ADD_LEN:%.*]] = add nsw i64 -1, [[TMP13]]
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = mul nsw i64 1, [[TMP4]]
|
|
// CHECK2-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[TMP6]], i64 [[TMP14]]
|
|
// CHECK2-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX3]], i64 [[LB_ADD_LEN]]
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = ptrtoint i32* [[ARRAYIDX4]] to i64
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = ptrtoint i32* [[ARRAYIDX1]] to i64
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = sub i64 [[TMP15]], [[TMP16]]
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = sdiv exact i64 [[TMP17]], ptrtoint (i32* getelementptr (i32, i32* null, i32 1) to i64)
|
|
// CHECK2-NEXT: [[TMP19:%.*]] = add nuw i64 [[TMP18]], 1
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = mul nuw i64 [[TMP19]], ptrtoint (i32* getelementptr (i32, i32* null, i32 1) to i64)
|
|
// CHECK2-NEXT: [[TMP21:%.*]] = call i8* @llvm.stacksave()
|
|
// CHECK2-NEXT: store i8* [[TMP21]], i8** [[SAVED_STACK]], align 8
|
|
// CHECK2-NEXT: [[VLA:%.*]] = alloca i32, i64 [[TMP19]], align 16
|
|
// CHECK2-NEXT: store i64 [[TMP19]], i64* [[__VLA_EXPR0]], align 8
|
|
// CHECK2-NEXT: [[TMP22:%.*]] = getelementptr i32, i32* [[VLA]], i64 [[TMP19]]
|
|
// CHECK2-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq i32* [[VLA]], [[TMP22]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
|
|
// CHECK2: omp.arrayinit.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi i32* [ [[VLA]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
|
|
// CHECK2-NEXT: store i32 0, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 4
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP22]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK2: omp.arrayinit.done:
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = ptrtoint i32* [[TMP6]] to i64
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = ptrtoint i32* [[ARRAYIDX1]] to i64
|
|
// CHECK2-NEXT: [[TMP25:%.*]] = sub i64 [[TMP23]], [[TMP24]]
|
|
// CHECK2-NEXT: [[TMP26:%.*]] = sdiv exact i64 [[TMP25]], ptrtoint (i32* getelementptr (i32, i32* null, i32 1) to i64)
|
|
// CHECK2-NEXT: [[TMP27:%.*]] = getelementptr i32, i32* [[VLA]], i64 [[TMP26]]
|
|
// CHECK2-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds [10 x [4 x %struct.S]], [10 x [4 x %struct.S]]* [[TMP10]], i64 0, i64 1
|
|
// CHECK2-NEXT: [[ARRAYDECAY:%.*]] = getelementptr inbounds [4 x %struct.S], [4 x %struct.S]* [[ARRAYIDX5]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[ARRAYDECAY]], i64 1
|
|
// CHECK2-NEXT: [[ARRAYIDX7:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[TMP8]], i64 0, i64 1
|
|
// CHECK2-NEXT: [[TMP28:%.*]] = load i32, i32* [[ARRAYIDX7]], align 4
|
|
// CHECK2-NEXT: [[TMP29:%.*]] = sext i32 [[TMP28]] to i64
|
|
// CHECK2-NEXT: [[LB_ADD_LEN8:%.*]] = add nsw i64 0, [[TMP29]]
|
|
// CHECK2-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds [10 x [4 x %struct.S]], [10 x [4 x %struct.S]]* [[TMP10]], i64 0, i64 [[LB_ADD_LEN8]]
|
|
// CHECK2-NEXT: [[ARRAYDECAY10:%.*]] = getelementptr inbounds [4 x %struct.S], [4 x %struct.S]* [[ARRAYIDX9]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[ARRAYIDX11:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDECAY10]], i64 2
|
|
// CHECK2-NEXT: [[TMP30:%.*]] = ptrtoint %struct.S* [[ARRAYIDX11]] to i64
|
|
// CHECK2-NEXT: [[TMP31:%.*]] = ptrtoint %struct.S* [[ARRAYIDX6]] to i64
|
|
// CHECK2-NEXT: [[TMP32:%.*]] = sub i64 [[TMP30]], [[TMP31]]
|
|
// CHECK2-NEXT: [[TMP33:%.*]] = sdiv exact i64 [[TMP32]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK2-NEXT: [[TMP34:%.*]] = add nuw i64 [[TMP33]], 1
|
|
// CHECK2-NEXT: [[TMP35:%.*]] = mul nuw i64 [[TMP34]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK2-NEXT: [[VLA12:%.*]] = alloca [[STRUCT_S]], i64 [[TMP34]], align 16
|
|
// CHECK2-NEXT: store i64 [[TMP34]], i64* [[__VLA_EXPR1]], align 8
|
|
// CHECK2-NEXT: [[TMP36:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[VLA12]], i64 [[TMP34]]
|
|
// CHECK2-NEXT: [[OMP_ARRAYINIT_ISEMPTY13:%.*]] = icmp eq %struct.S* [[VLA12]], [[TMP36]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY13]], label [[OMP_ARRAYINIT_DONE18:%.*]], label [[OMP_ARRAYINIT_BODY14:%.*]]
|
|
// CHECK2: omp.arrayinit.body14:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST15:%.*]] = phi %struct.S* [ [[VLA12]], [[OMP_ARRAYINIT_DONE]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT16:%.*]], [[OMP_ARRAYINIT_BODY14]] ]
|
|
// CHECK2-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST15]])
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT16]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST15]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE17:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT16]], [[TMP36]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE17]], label [[OMP_ARRAYINIT_DONE18]], label [[OMP_ARRAYINIT_BODY14]]
|
|
// CHECK2: omp.arrayinit.done18:
|
|
// CHECK2-NEXT: [[TMP37:%.*]] = bitcast [10 x [4 x %struct.S]]* [[TMP10]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP38:%.*]] = ptrtoint %struct.S* [[TMP37]] to i64
|
|
// CHECK2-NEXT: [[TMP39:%.*]] = ptrtoint %struct.S* [[ARRAYIDX6]] to i64
|
|
// CHECK2-NEXT: [[TMP40:%.*]] = sub i64 [[TMP38]], [[TMP39]]
|
|
// CHECK2-NEXT: [[TMP41:%.*]] = sdiv exact i64 [[TMP40]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK2-NEXT: [[TMP42:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[VLA12]], i64 [[TMP41]]
|
|
// CHECK2-NEXT: [[TMP43:%.*]] = bitcast %struct.S* [[TMP42]] to [10 x [4 x %struct.S]]*
|
|
// CHECK2-NEXT: [[TMP44:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP45:%.*]] = load i32, i32* [[TMP44]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP45]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK2-NEXT: [[TMP46:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP46]], 9
|
|
// CHECK2-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK2: cond.true:
|
|
// CHECK2-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK2: cond.false:
|
|
// CHECK2-NEXT: [[TMP47:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END]]
|
|
// CHECK2: cond.end:
|
|
// CHECK2-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP47]], [[COND_FALSE]] ]
|
|
// CHECK2-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP48:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP48]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK2: omp.inner.for.cond:
|
|
// CHECK2-NEXT: [[TMP49:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[TMP50:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP19:%.*]] = icmp sle i32 [[TMP49]], [[TMP50]]
|
|
// CHECK2-NEXT: br i1 [[CMP19]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK2: omp.inner.for.cond.cleanup:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK2: omp.inner.for.body:
|
|
// CHECK2-NEXT: [[TMP51:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP51]], 1
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK2-NEXT: [[TMP52:%.*]] = mul nsw i64 1, [[TMP4]]
|
|
// CHECK2-NEXT: [[ARRAYIDX20:%.*]] = getelementptr inbounds i32, i32* [[TMP27]], i64 [[TMP52]]
|
|
// CHECK2-NEXT: [[TMP53:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK2-NEXT: [[IDXPROM:%.*]] = sext i32 [[TMP53]] to i64
|
|
// CHECK2-NEXT: [[ARRAYIDX21:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX20]], i64 [[IDXPROM]]
|
|
// CHECK2-NEXT: [[TMP54:%.*]] = load i32, i32* [[ARRAYIDX21]], align 4
|
|
// CHECK2-NEXT: [[INC:%.*]] = add nsw i32 [[TMP54]], 1
|
|
// CHECK2-NEXT: store i32 [[INC]], i32* [[ARRAYIDX21]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK2: omp.body.continue:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK2: omp.inner.for.inc:
|
|
// CHECK2-NEXT: [[TMP55:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[ADD22:%.*]] = add nsw i32 [[TMP55]], 1
|
|
// CHECK2-NEXT: store i32 [[ADD22]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK2: omp.inner.for.end:
|
|
// CHECK2-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK2: omp.loop.exit:
|
|
// CHECK2-NEXT: [[TMP56:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP57:%.*]] = load i32, i32* [[TMP56]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP57]])
|
|
// CHECK2-NEXT: [[TMP58:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP59:%.*]] = bitcast i32* [[VLA]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP59]], i8** [[TMP58]], align 8
|
|
// CHECK2-NEXT: [[TMP60:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 1
|
|
// CHECK2-NEXT: [[TMP61:%.*]] = inttoptr i64 [[TMP19]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP61]], i8** [[TMP60]], align 8
|
|
// CHECK2-NEXT: [[TMP62:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 2
|
|
// CHECK2-NEXT: [[TMP63:%.*]] = bitcast %struct.S* [[VLA12]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP63]], i8** [[TMP62]], align 8
|
|
// CHECK2-NEXT: [[TMP64:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 3
|
|
// CHECK2-NEXT: [[TMP65:%.*]] = inttoptr i64 [[TMP34]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP65]], i8** [[TMP64]], align 8
|
|
// CHECK2-NEXT: [[TMP66:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP67:%.*]] = load i32, i32* [[TMP66]], align 4
|
|
// CHECK2-NEXT: [[TMP68:%.*]] = bitcast [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK2-NEXT: [[TMP69:%.*]] = call i32 @__kmpc_reduce_nowait(%struct.ident_t* @[[GLOB2]], i32 [[TMP67]], i32 2, i64 32, i8* [[TMP68]], void (i8*, i8*)* @.omp.reduction.reduction_func.2, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: switch i32 [[TMP69]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK2-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK2-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK2-NEXT: ]
|
|
// CHECK2: .omp.reduction.case1:
|
|
// CHECK2-NEXT: [[TMP70:%.*]] = getelementptr i32, i32* [[ARRAYIDX1]], i64 [[TMP19]]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq i32* [[ARRAYIDX1]], [[TMP70]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE27:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK2: omp.arraycpy.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi i32* [ [[VLA]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST23:%.*]] = phi i32* [ [[ARRAYIDX1]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT25:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[TMP71:%.*]] = load i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST23]], align 4
|
|
// CHECK2-NEXT: [[TMP72:%.*]] = load i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], align 4
|
|
// CHECK2-NEXT: [[ADD24:%.*]] = add nsw i32 [[TMP71]], [[TMP72]]
|
|
// CHECK2-NEXT: store i32 [[ADD24]], i32* [[OMP_ARRAYCPY_DESTELEMENTPAST23]], align 4
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT25]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST23]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE26:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT25]], [[TMP70]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE26]], label [[OMP_ARRAYCPY_DONE27]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done27:
|
|
// CHECK2-NEXT: [[TMP73:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX6]], i64 [[TMP34]]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY28:%.*]] = icmp eq %struct.S* [[ARRAYIDX6]], [[TMP73]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY28]], label [[OMP_ARRAYCPY_DONE35:%.*]], label [[OMP_ARRAYCPY_BODY29:%.*]]
|
|
// CHECK2: omp.arraycpy.body29:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST30:%.*]] = phi %struct.S* [ [[VLA12]], [[OMP_ARRAYCPY_DONE27]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT33:%.*]], [[OMP_ARRAYCPY_BODY29]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST31:%.*]] = phi %struct.S* [ [[ARRAYIDX6]], [[OMP_ARRAYCPY_DONE27]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT32:%.*]], [[OMP_ARRAYCPY_BODY29]] ]
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST31]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST30]])
|
|
// CHECK2-NEXT: [[TMP74:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST31]] to i8*
|
|
// CHECK2-NEXT: [[TMP75:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP74]], i8* align 4 [[TMP75]], i64 4, i1 false)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT32]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST31]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT33]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST30]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE34:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT32]], [[TMP73]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE34]], label [[OMP_ARRAYCPY_DONE35]], label [[OMP_ARRAYCPY_BODY29]]
|
|
// CHECK2: omp.arraycpy.done35:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce_nowait(%struct.ident_t* @[[GLOB2]], i32 [[TMP67]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.case2:
|
|
// CHECK2-NEXT: [[TMP76:%.*]] = getelementptr i32, i32* [[ARRAYIDX1]], i64 [[TMP19]]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY36:%.*]] = icmp eq i32* [[ARRAYIDX1]], [[TMP76]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY36]], label [[OMP_ARRAYCPY_DONE43:%.*]], label [[OMP_ARRAYCPY_BODY37:%.*]]
|
|
// CHECK2: omp.arraycpy.body37:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST38:%.*]] = phi i32* [ [[VLA]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT41:%.*]], [[OMP_ARRAYCPY_BODY37]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST39:%.*]] = phi i32* [ [[ARRAYIDX1]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT40:%.*]], [[OMP_ARRAYCPY_BODY37]] ]
|
|
// CHECK2-NEXT: [[TMP77:%.*]] = load i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST38]], align 4
|
|
// CHECK2-NEXT: [[TMP78:%.*]] = atomicrmw add i32* [[OMP_ARRAYCPY_DESTELEMENTPAST39]], i32 [[TMP77]] monotonic, align 4
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT40]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST39]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT41]] = getelementptr i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST38]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE42:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT40]], [[TMP76]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE42]], label [[OMP_ARRAYCPY_DONE43]], label [[OMP_ARRAYCPY_BODY37]]
|
|
// CHECK2: omp.arraycpy.done43:
|
|
// CHECK2-NEXT: [[TMP79:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX6]], i64 [[TMP34]]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY44:%.*]] = icmp eq %struct.S* [[ARRAYIDX6]], [[TMP79]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY44]], label [[OMP_ARRAYCPY_DONE52:%.*]], label [[OMP_ARRAYCPY_BODY45:%.*]]
|
|
// CHECK2: omp.arraycpy.body45:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST46:%.*]] = phi %struct.S* [ [[VLA12]], [[OMP_ARRAYCPY_DONE43]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT50:%.*]], [[OMP_ARRAYCPY_BODY45]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST47:%.*]] = phi %struct.S* [ [[ARRAYIDX6]], [[OMP_ARRAYCPY_DONE43]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT49:%.*]], [[OMP_ARRAYCPY_BODY45]] ]
|
|
// CHECK2-NEXT: [[TMP80:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP81:%.*]] = load i32, i32* [[TMP80]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP81]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[CALL48:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST47]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST46]])
|
|
// CHECK2-NEXT: [[TMP82:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST47]] to i8*
|
|
// CHECK2-NEXT: [[TMP83:%.*]] = bitcast %struct.S* [[CALL48]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP82]], i8* align 4 [[TMP83]], i64 4, i1 false)
|
|
// CHECK2-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP81]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT49]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST47]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT50]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST46]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE51:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT49]], [[TMP79]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE51]], label [[OMP_ARRAYCPY_DONE52]], label [[OMP_ARRAYCPY_BODY45]]
|
|
// CHECK2: omp.arraycpy.done52:
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.default:
|
|
// CHECK2-NEXT: [[TMP84:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[VLA12]], i64 [[TMP34]]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ISEMPTY:%.*]] = icmp eq %struct.S* [[VLA12]], [[TMP84]]
|
|
// CHECK2-NEXT: br i1 [[ARRAYDESTROY_ISEMPTY]], label [[ARRAYDESTROY_DONE53:%.*]], label [[ARRAYDESTROY_BODY:%.*]]
|
|
// CHECK2: arraydestroy.body:
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP84]], [[DOTOMP_REDUCTION_DEFAULT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
|
|
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[VLA12]]
|
|
// CHECK2-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE53]], label [[ARRAYDESTROY_BODY]]
|
|
// CHECK2: arraydestroy.done53:
|
|
// CHECK2-NEXT: [[TMP85:%.*]] = load i8*, i8** [[SAVED_STACK]], align 8
|
|
// CHECK2-NEXT: call void @llvm.stackrestore(i8* [[TMP85]])
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.2
|
|
// CHECK2-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [4 x i8*]*
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [4 x i8*]*
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to i32*
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i32*
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 1
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = load i8*, i8** [[TMP12]], align 8
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = ptrtoint i8* [[TMP13]] to i64
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 2
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = load i8*, i8** [[TMP15]], align 8
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = bitcast i8* [[TMP16]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 2
|
|
// CHECK2-NEXT: [[TMP19:%.*]] = load i8*, i8** [[TMP18]], align 8
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = bitcast i8* [[TMP19]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP21:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 3
|
|
// CHECK2-NEXT: [[TMP22:%.*]] = load i8*, i8** [[TMP21]], align 8
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = ptrtoint i8* [[TMP22]] to i64
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = getelementptr i32, i32* [[TMP11]], i64 [[TMP14]]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq i32* [[TMP11]], [[TMP24]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE2:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK2: omp.arraycpy.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi i32* [ [[TMP8]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi i32* [ [[TMP11]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[TMP25:%.*]] = load i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 4
|
|
// CHECK2-NEXT: [[TMP26:%.*]] = load i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], align 4
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP25]], [[TMP26]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 4
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP24]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE2]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done2:
|
|
// CHECK2-NEXT: [[TMP27:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[TMP20]], i64 [[TMP23]]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY3:%.*]] = icmp eq %struct.S* [[TMP20]], [[TMP27]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY3]], label [[OMP_ARRAYCPY_DONE10:%.*]], label [[OMP_ARRAYCPY_BODY4:%.*]]
|
|
// CHECK2: omp.arraycpy.body4:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST5:%.*]] = phi %struct.S* [ [[TMP17]], [[OMP_ARRAYCPY_DONE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT8:%.*]], [[OMP_ARRAYCPY_BODY4]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST6:%.*]] = phi %struct.S* [ [[TMP20]], [[OMP_ARRAYCPY_DONE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT7:%.*]], [[OMP_ARRAYCPY_BODY4]] ]
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST6]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST5]])
|
|
// CHECK2-NEXT: [[TMP28:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST6]] to i8*
|
|
// CHECK2-NEXT: [[TMP29:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP28]], i8* align 4 [[TMP29]], i64 4, i1 false)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT7]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST6]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT8]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST5]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE9:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT7]], [[TMP27]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE9]], label [[OMP_ARRAYCPY_DONE10]], label [[OMP_ARRAYCPY_BODY4]]
|
|
// CHECK2: omp.arraycpy.done10:
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined..3
|
|
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.1* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.1*, align 8
|
|
// CHECK2-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[TMP:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[SAVED_STACK:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: [[__VLA_EXPR0:%.*]] = alloca i64, align 8
|
|
// CHECK2-NEXT: [[ARRS:%.*]] = alloca [10 x [4 x %struct.S]], align 16
|
|
// CHECK2-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [3 x i8*], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store %struct.anon.1* [[__CONTEXT]], %struct.anon.1** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load %struct.anon.1*, %struct.anon.1** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_1:%.*]], %struct.anon.1* [[TMP0]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i64, i64* [[TMP1]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_ANON_1]], %struct.anon.1* [[TMP0]], i32 0, i32 1
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i64, i64* [[TMP3]], align 8
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_ANON_1]], %struct.anon.1* [[TMP0]], i32 0, i32 2
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = load i32*, i32** [[TMP5]], align 8
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = getelementptr inbounds [[STRUCT_ANON_1]], %struct.anon.1* [[TMP0]], i32 0, i32 3
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = load [10 x [4 x %struct.S]]*, [10 x [4 x %struct.S]]** [[TMP7]], align 8
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = mul nuw i64 [[TMP2]], [[TMP4]]
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = mul nuw i64 [[TMP9]], 4
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = udiv exact i64 [[TMP10]], ptrtoint (i32* getelementptr (i32, i32* null, i32 1) to i64)
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = call i8* @llvm.stacksave()
|
|
// CHECK2-NEXT: store i8* [[TMP12]], i8** [[SAVED_STACK]], align 8
|
|
// CHECK2-NEXT: [[VLA:%.*]] = alloca i32, i64 [[TMP11]], align 16
|
|
// CHECK2-NEXT: store i64 [[TMP11]], i64* [[__VLA_EXPR0]], align 8
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = getelementptr i32, i32* [[VLA]], i64 [[TMP11]]
|
|
// CHECK2-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq i32* [[VLA]], [[TMP13]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
|
|
// CHECK2: omp.arrayinit.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi i32* [ [[VLA]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
|
|
// CHECK2-NEXT: store i32 0, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 4
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP13]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK2: omp.arrayinit.done:
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [10 x [4 x %struct.S]], [10 x [4 x %struct.S]]* [[ARRS]], i32 0, i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[ARRAY_BEGIN]], i64 40
|
|
// CHECK2-NEXT: [[OMP_ARRAYINIT_ISEMPTY1:%.*]] = icmp eq %struct.S* [[ARRAY_BEGIN]], [[TMP14]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY1]], label [[OMP_ARRAYINIT_DONE6:%.*]], label [[OMP_ARRAYINIT_BODY2:%.*]]
|
|
// CHECK2: omp.arrayinit.body2:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST3:%.*]] = phi %struct.S* [ [[ARRAY_BEGIN]], [[OMP_ARRAYINIT_DONE]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT4:%.*]], [[OMP_ARRAYINIT_BODY2]] ]
|
|
// CHECK2-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST3]])
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT4]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST3]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE5:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT4]], [[TMP14]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE5]], label [[OMP_ARRAYINIT_DONE6]], label [[OMP_ARRAYINIT_BODY2]]
|
|
// CHECK2: omp.arrayinit.done6:
|
|
// CHECK2-NEXT: [[LHS_BEGIN:%.*]] = bitcast [10 x [4 x %struct.S]]* [[TMP8]] to %struct.S*
|
|
// CHECK2-NEXT: [[RHS_BEGIN:%.*]] = bitcast [10 x [4 x %struct.S]]* [[ARRS]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = load i32, i32* [[TMP15]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP16]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP17]], 9
|
|
// CHECK2-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK2: cond.true:
|
|
// CHECK2-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK2: cond.false:
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END]]
|
|
// CHECK2: cond.end:
|
|
// CHECK2-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP18]], [[COND_FALSE]] ]
|
|
// CHECK2-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP19:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP19]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK2: omp.inner.for.cond:
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[TMP21:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP7:%.*]] = icmp sle i32 [[TMP20]], [[TMP21]]
|
|
// CHECK2-NEXT: br i1 [[CMP7]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK2: omp.inner.for.cond.cleanup:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK2: omp.inner.for.body:
|
|
// CHECK2-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP22]], 1
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = mul nsw i64 1, [[TMP4]]
|
|
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP23]]
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK2-NEXT: [[IDXPROM:%.*]] = sext i32 [[TMP24]] to i64
|
|
// CHECK2-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX]], i64 [[IDXPROM]]
|
|
// CHECK2-NEXT: [[TMP25:%.*]] = load i32, i32* [[ARRAYIDX8]], align 4
|
|
// CHECK2-NEXT: [[INC:%.*]] = add nsw i32 [[TMP25]], 1
|
|
// CHECK2-NEXT: store i32 [[INC]], i32* [[ARRAYIDX8]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK2: omp.body.continue:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK2: omp.inner.for.inc:
|
|
// CHECK2-NEXT: [[TMP26:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[ADD9:%.*]] = add nsw i32 [[TMP26]], 1
|
|
// CHECK2-NEXT: store i32 [[ADD9]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK2: omp.inner.for.end:
|
|
// CHECK2-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK2: omp.loop.exit:
|
|
// CHECK2-NEXT: [[TMP27:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP28:%.*]] = load i32, i32* [[TMP27]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP28]])
|
|
// CHECK2-NEXT: [[TMP29:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP30:%.*]] = bitcast i32* [[VLA]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP30]], i8** [[TMP29]], align 8
|
|
// CHECK2-NEXT: [[TMP31:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 1
|
|
// CHECK2-NEXT: [[TMP32:%.*]] = inttoptr i64 [[TMP11]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP32]], i8** [[TMP31]], align 8
|
|
// CHECK2-NEXT: [[TMP33:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 2
|
|
// CHECK2-NEXT: [[TMP34:%.*]] = bitcast %struct.S* [[RHS_BEGIN]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP34]], i8** [[TMP33]], align 8
|
|
// CHECK2-NEXT: [[TMP35:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP36:%.*]] = load i32, i32* [[TMP35]], align 4
|
|
// CHECK2-NEXT: [[TMP37:%.*]] = bitcast [3 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK2-NEXT: [[TMP38:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP36]], i32 2, i64 24, i8* [[TMP37]], void (i8*, i8*)* @.omp.reduction.reduction_func.4, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: switch i32 [[TMP38]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK2-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK2-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK2-NEXT: ]
|
|
// CHECK2: .omp.reduction.case1:
|
|
// CHECK2-NEXT: [[TMP39:%.*]] = getelementptr i32, i32* [[TMP6]], i64 [[TMP11]]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq i32* [[TMP6]], [[TMP39]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE14:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK2: omp.arraycpy.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi i32* [ [[VLA]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST10:%.*]] = phi i32* [ [[TMP6]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT12:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[TMP40:%.*]] = load i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST10]], align 4
|
|
// CHECK2-NEXT: [[TMP41:%.*]] = load i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], align 4
|
|
// CHECK2-NEXT: [[ADD11:%.*]] = add nsw i32 [[TMP40]], [[TMP41]]
|
|
// CHECK2-NEXT: store i32 [[ADD11]], i32* [[OMP_ARRAYCPY_DESTELEMENTPAST10]], align 4
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT12]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST10]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE13:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT12]], [[TMP39]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE13]], label [[OMP_ARRAYCPY_DONE14]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done14:
|
|
// CHECK2-NEXT: [[TMP42:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[LHS_BEGIN]], i64 40
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY15:%.*]] = icmp eq %struct.S* [[LHS_BEGIN]], [[TMP42]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY15]], label [[OMP_ARRAYCPY_DONE22:%.*]], label [[OMP_ARRAYCPY_BODY16:%.*]]
|
|
// CHECK2: omp.arraycpy.body16:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST17:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[OMP_ARRAYCPY_DONE14]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT20:%.*]], [[OMP_ARRAYCPY_BODY16]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST18:%.*]] = phi %struct.S* [ [[LHS_BEGIN]], [[OMP_ARRAYCPY_DONE14]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT19:%.*]], [[OMP_ARRAYCPY_BODY16]] ]
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST18]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST17]])
|
|
// CHECK2-NEXT: [[TMP43:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST18]] to i8*
|
|
// CHECK2-NEXT: [[TMP44:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP43]], i8* align 4 [[TMP44]], i64 4, i1 false)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT19]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST18]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT20]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST17]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE21:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT19]], [[TMP42]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE21]], label [[OMP_ARRAYCPY_DONE22]], label [[OMP_ARRAYCPY_BODY16]]
|
|
// CHECK2: omp.arraycpy.done22:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP36]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.case2:
|
|
// CHECK2-NEXT: [[TMP45:%.*]] = getelementptr i32, i32* [[TMP6]], i64 [[TMP11]]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY23:%.*]] = icmp eq i32* [[TMP6]], [[TMP45]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY23]], label [[OMP_ARRAYCPY_DONE30:%.*]], label [[OMP_ARRAYCPY_BODY24:%.*]]
|
|
// CHECK2: omp.arraycpy.body24:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST25:%.*]] = phi i32* [ [[VLA]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT28:%.*]], [[OMP_ARRAYCPY_BODY24]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST26:%.*]] = phi i32* [ [[TMP6]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT27:%.*]], [[OMP_ARRAYCPY_BODY24]] ]
|
|
// CHECK2-NEXT: [[TMP46:%.*]] = load i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST25]], align 4
|
|
// CHECK2-NEXT: [[TMP47:%.*]] = atomicrmw add i32* [[OMP_ARRAYCPY_DESTELEMENTPAST26]], i32 [[TMP46]] monotonic, align 4
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT27]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST26]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT28]] = getelementptr i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST25]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE29:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT27]], [[TMP45]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE29]], label [[OMP_ARRAYCPY_DONE30]], label [[OMP_ARRAYCPY_BODY24]]
|
|
// CHECK2: omp.arraycpy.done30:
|
|
// CHECK2-NEXT: [[TMP48:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[LHS_BEGIN]], i64 40
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY31:%.*]] = icmp eq %struct.S* [[LHS_BEGIN]], [[TMP48]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY31]], label [[OMP_ARRAYCPY_DONE39:%.*]], label [[OMP_ARRAYCPY_BODY32:%.*]]
|
|
// CHECK2: omp.arraycpy.body32:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST33:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[OMP_ARRAYCPY_DONE30]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT37:%.*]], [[OMP_ARRAYCPY_BODY32]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST34:%.*]] = phi %struct.S* [ [[LHS_BEGIN]], [[OMP_ARRAYCPY_DONE30]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT36:%.*]], [[OMP_ARRAYCPY_BODY32]] ]
|
|
// CHECK2-NEXT: [[TMP49:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP50:%.*]] = load i32, i32* [[TMP49]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP50]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[CALL35:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST34]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST33]])
|
|
// CHECK2-NEXT: [[TMP51:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST34]] to i8*
|
|
// CHECK2-NEXT: [[TMP52:%.*]] = bitcast %struct.S* [[CALL35]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP51]], i8* align 4 [[TMP52]], i64 4, i1 false)
|
|
// CHECK2-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP50]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT36]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST34]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT37]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST33]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE38:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT36]], [[TMP48]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE38]], label [[OMP_ARRAYCPY_DONE39]], label [[OMP_ARRAYCPY_BODY32]]
|
|
// CHECK2: omp.arraycpy.done39:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP36]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.default:
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN40:%.*]] = getelementptr inbounds [10 x [4 x %struct.S]], [10 x [4 x %struct.S]]* [[ARRS]], i32 0, i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP53:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN40]], i64 40
|
|
// CHECK2-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
|
|
// CHECK2: arraydestroy.body:
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP53]], [[DOTOMP_REDUCTION_DEFAULT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
|
|
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN40]]
|
|
// CHECK2-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE41:%.*]], label [[ARRAYDESTROY_BODY]]
|
|
// CHECK2: arraydestroy.done41:
|
|
// CHECK2-NEXT: [[TMP54:%.*]] = load i8*, i8** [[SAVED_STACK]], align 8
|
|
// CHECK2-NEXT: call void @llvm.stackrestore(i8* [[TMP54]])
|
|
// CHECK2-NEXT: [[TMP55:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP56:%.*]] = load i32, i32* [[TMP55]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4]], i32 [[TMP56]])
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.4
|
|
// CHECK2-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [3 x i8*]*
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [3 x i8*]*
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to i32*
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i32*
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[TMP3]], i64 0, i64 1
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = load i8*, i8** [[TMP12]], align 8
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = ptrtoint i8* [[TMP13]] to i64
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[TMP5]], i64 0, i64 2
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = load i8*, i8** [[TMP15]], align 8
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = bitcast i8* [[TMP16]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[TMP3]], i64 0, i64 2
|
|
// CHECK2-NEXT: [[TMP19:%.*]] = load i8*, i8** [[TMP18]], align 8
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = bitcast i8* [[TMP19]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP21:%.*]] = getelementptr i32, i32* [[TMP11]], i64 [[TMP14]]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq i32* [[TMP11]], [[TMP21]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE2:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK2: omp.arraycpy.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi i32* [ [[TMP8]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi i32* [ [[TMP11]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[TMP22:%.*]] = load i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 4
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = load i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], align 4
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP22]], [[TMP23]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 4
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP21]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE2]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done2:
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[TMP20]], i64 40
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY3:%.*]] = icmp eq %struct.S* [[TMP20]], [[TMP24]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY3]], label [[OMP_ARRAYCPY_DONE10:%.*]], label [[OMP_ARRAYCPY_BODY4:%.*]]
|
|
// CHECK2: omp.arraycpy.body4:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST5:%.*]] = phi %struct.S* [ [[TMP17]], [[OMP_ARRAYCPY_DONE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT8:%.*]], [[OMP_ARRAYCPY_BODY4]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST6:%.*]] = phi %struct.S* [ [[TMP20]], [[OMP_ARRAYCPY_DONE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT7:%.*]], [[OMP_ARRAYCPY_BODY4]] ]
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST6]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST5]])
|
|
// CHECK2-NEXT: [[TMP25:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST6]] to i8*
|
|
// CHECK2-NEXT: [[TMP26:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP25]], i8* align 4 [[TMP26]], i64 4, i1 false)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT7]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST6]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT8]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST5]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE9:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT7]], [[TMP24]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE9]], label [[OMP_ARRAYCPY_DONE10]], label [[OMP_ARRAYCPY_BODY4]]
|
|
// CHECK2: omp.arraycpy.done10:
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined..5
|
|
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.2* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.2*, align 8
|
|
// CHECK2-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[TMP:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[ARR:%.*]] = alloca [1 x [2 x i32]], align 4
|
|
// CHECK2-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store %struct.anon.2* [[__CONTEXT]], %struct.anon.2** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load %struct.anon.2*, %struct.anon.2** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_2:%.*]], %struct.anon.2* [[TMP0]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i64, i64* [[TMP1]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_ANON_2]], %struct.anon.2* [[TMP0]], i32 0, i32 1
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i64, i64* [[TMP3]], align 8
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_ANON_2]], %struct.anon.2* [[TMP0]], i32 0, i32 2
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = load i32*, i32** [[TMP5]], align 8
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = mul nsw i64 1, [[TMP4]]
|
|
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[TMP6]], i64 [[TMP7]]
|
|
// CHECK2-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX]], i64 0
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = mul nsw i64 1, [[TMP4]]
|
|
// CHECK2-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* [[TMP6]], i64 [[TMP8]]
|
|
// CHECK2-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX2]], i64 1
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [1 x [2 x i32]], [1 x [2 x i32]]* [[ARR]], i32 0, i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr i32, i32* [[ARRAY_BEGIN]], i64 2
|
|
// CHECK2-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq i32* [[ARRAY_BEGIN]], [[TMP9]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
|
|
// CHECK2: omp.arrayinit.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi i32* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
|
|
// CHECK2-NEXT: store i32 0, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 4
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP9]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK2: omp.arrayinit.done:
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = ptrtoint i32* [[TMP6]] to i64
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = ptrtoint i32* [[ARRAYIDX1]] to i64
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = sub i64 [[TMP10]], [[TMP11]]
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = sdiv exact i64 [[TMP12]], ptrtoint (i32* getelementptr (i32, i32* null, i32 1) to i64)
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = bitcast [1 x [2 x i32]]* [[ARR]] to i32*
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = getelementptr i32, i32* [[TMP14]], i64 [[TMP13]]
|
|
// CHECK2-NEXT: [[RHS_BEGIN:%.*]] = bitcast [1 x [2 x i32]]* [[ARR]] to i32*
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = load i32, i32* [[TMP16]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP17]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP18]], 9
|
|
// CHECK2-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK2: cond.true:
|
|
// CHECK2-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK2: cond.false:
|
|
// CHECK2-NEXT: [[TMP19:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END]]
|
|
// CHECK2: cond.end:
|
|
// CHECK2-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP19]], [[COND_FALSE]] ]
|
|
// CHECK2-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP20]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK2: omp.inner.for.cond:
|
|
// CHECK2-NEXT: [[TMP21:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP4:%.*]] = icmp sle i32 [[TMP21]], [[TMP22]]
|
|
// CHECK2-NEXT: br i1 [[CMP4]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK2: omp.inner.for.body:
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP23]], 1
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = mul nsw i64 1, [[TMP4]]
|
|
// CHECK2-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds i32, i32* [[TMP15]], i64 [[TMP24]]
|
|
// CHECK2-NEXT: [[TMP25:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK2-NEXT: [[IDXPROM:%.*]] = sext i32 [[TMP25]] to i64
|
|
// CHECK2-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX5]], i64 [[IDXPROM]]
|
|
// CHECK2-NEXT: [[TMP26:%.*]] = load i32, i32* [[ARRAYIDX6]], align 4
|
|
// CHECK2-NEXT: [[INC:%.*]] = add nsw i32 [[TMP26]], 1
|
|
// CHECK2-NEXT: store i32 [[INC]], i32* [[ARRAYIDX6]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK2: omp.body.continue:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK2: omp.inner.for.inc:
|
|
// CHECK2-NEXT: [[TMP27:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[ADD7:%.*]] = add nsw i32 [[TMP27]], 1
|
|
// CHECK2-NEXT: store i32 [[ADD7]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK2: omp.inner.for.end:
|
|
// CHECK2-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK2: omp.loop.exit:
|
|
// CHECK2-NEXT: [[TMP28:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP29:%.*]] = load i32, i32* [[TMP28]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP29]])
|
|
// CHECK2-NEXT: [[TMP30:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP31:%.*]] = bitcast i32* [[RHS_BEGIN]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP31]], i8** [[TMP30]], align 8
|
|
// CHECK2-NEXT: [[TMP32:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP33:%.*]] = load i32, i32* [[TMP32]], align 4
|
|
// CHECK2-NEXT: [[TMP34:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK2-NEXT: [[TMP35:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP33]], i32 1, i64 8, i8* [[TMP34]], void (i8*, i8*)* @.omp.reduction.reduction_func.6, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: switch i32 [[TMP35]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK2-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK2-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK2-NEXT: ]
|
|
// CHECK2: .omp.reduction.case1:
|
|
// CHECK2-NEXT: [[TMP36:%.*]] = getelementptr i32, i32* [[ARRAYIDX1]], i64 2
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq i32* [[ARRAYIDX1]], [[TMP36]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE12:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK2: omp.arraycpy.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi i32* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST8:%.*]] = phi i32* [ [[ARRAYIDX1]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT10:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[TMP37:%.*]] = load i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST8]], align 4
|
|
// CHECK2-NEXT: [[TMP38:%.*]] = load i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], align 4
|
|
// CHECK2-NEXT: [[ADD9:%.*]] = add nsw i32 [[TMP37]], [[TMP38]]
|
|
// CHECK2-NEXT: store i32 [[ADD9]], i32* [[OMP_ARRAYCPY_DESTELEMENTPAST8]], align 4
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT10]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST8]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE11:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT10]], [[TMP36]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE11]], label [[OMP_ARRAYCPY_DONE12]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done12:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP33]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.case2:
|
|
// CHECK2-NEXT: [[TMP39:%.*]] = getelementptr i32, i32* [[ARRAYIDX1]], i64 2
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY13:%.*]] = icmp eq i32* [[ARRAYIDX1]], [[TMP39]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY13]], label [[OMP_ARRAYCPY_DONE20:%.*]], label [[OMP_ARRAYCPY_BODY14:%.*]]
|
|
// CHECK2: omp.arraycpy.body14:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST15:%.*]] = phi i32* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT18:%.*]], [[OMP_ARRAYCPY_BODY14]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST16:%.*]] = phi i32* [ [[ARRAYIDX1]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT17:%.*]], [[OMP_ARRAYCPY_BODY14]] ]
|
|
// CHECK2-NEXT: [[TMP40:%.*]] = load i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST15]], align 4
|
|
// CHECK2-NEXT: [[TMP41:%.*]] = atomicrmw add i32* [[OMP_ARRAYCPY_DESTELEMENTPAST16]], i32 [[TMP40]] monotonic, align 4
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT17]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST16]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT18]] = getelementptr i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST15]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE19:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT17]], [[TMP39]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE19]], label [[OMP_ARRAYCPY_DONE20]], label [[OMP_ARRAYCPY_BODY14]]
|
|
// CHECK2: omp.arraycpy.done20:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP33]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.default:
|
|
// CHECK2-NEXT: [[TMP42:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP43:%.*]] = load i32, i32* [[TMP42]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4]], i32 [[TMP43]])
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.6
|
|
// CHECK2-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to i32*
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i32*
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = getelementptr i32, i32* [[TMP11]], i64 2
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq i32* [[TMP11]], [[TMP12]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE2:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK2: omp.arraycpy.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi i32* [ [[TMP8]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi i32* [ [[TMP11]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = load i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 4
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = load i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], align 4
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP13]], [[TMP14]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 4
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP12]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE2]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done2:
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined..7
|
|
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.3* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.3*, align 8
|
|
// CHECK2-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[TMP:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[SAVED_STACK:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: [[__VLA_EXPR0:%.*]] = alloca i64, align 8
|
|
// CHECK2-NEXT: [[_TMP4:%.*]] = alloca %struct.S**, align 8
|
|
// CHECK2-NEXT: [[_TMP5:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK2-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [2 x i8*], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store %struct.anon.3* [[__CONTEXT]], %struct.anon.3** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load %struct.anon.3*, %struct.anon.3** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_3:%.*]], %struct.anon.3* [[TMP0]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load %struct.S***, %struct.S**** [[TMP1]], align 8
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = load %struct.S**, %struct.S*** [[TMP2]], align 8
|
|
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds %struct.S*, %struct.S** [[TMP3]], i64 0
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load %struct.S*, %struct.S** [[ARRAYIDX]], align 8
|
|
// CHECK2-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[TMP4]], i64 1
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = load %struct.S**, %struct.S*** [[TMP2]], align 8
|
|
// CHECK2-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds %struct.S*, %struct.S** [[TMP5]], i64 4
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = load %struct.S*, %struct.S** [[ARRAYIDX2]], align 8
|
|
// CHECK2-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP6]], i64 6
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = ptrtoint %struct.S* [[ARRAYIDX3]] to i64
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = ptrtoint %struct.S* [[ARRAYIDX1]] to i64
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = sub i64 [[TMP7]], [[TMP8]]
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = sdiv exact i64 [[TMP9]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = add nuw i64 [[TMP10]], 1
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = mul nuw i64 [[TMP11]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = call i8* @llvm.stacksave()
|
|
// CHECK2-NEXT: store i8* [[TMP13]], i8** [[SAVED_STACK]], align 8
|
|
// CHECK2-NEXT: [[VLA:%.*]] = alloca [[STRUCT_S]], i64 [[TMP11]], align 16
|
|
// CHECK2-NEXT: store i64 [[TMP11]], i64* [[__VLA_EXPR0]], align 8
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[VLA]], i64 [[TMP11]]
|
|
// CHECK2-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq %struct.S* [[VLA]], [[TMP14]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
|
|
// CHECK2: omp.arrayinit.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[VLA]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
|
|
// CHECK2-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]])
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP14]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK2: omp.arrayinit.done:
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = load %struct.S**, %struct.S*** [[TMP2]], align 8
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = load %struct.S*, %struct.S** [[TMP15]], align 8
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = ptrtoint %struct.S* [[TMP16]] to i64
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = ptrtoint %struct.S* [[ARRAYIDX1]] to i64
|
|
// CHECK2-NEXT: [[TMP19:%.*]] = sub i64 [[TMP17]], [[TMP18]]
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = sdiv exact i64 [[TMP19]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK2-NEXT: [[TMP21:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[VLA]], i64 [[TMP20]]
|
|
// CHECK2-NEXT: store %struct.S** [[_TMP5]], %struct.S*** [[_TMP4]], align 8
|
|
// CHECK2-NEXT: store %struct.S* [[TMP21]], %struct.S** [[_TMP5]], align 8
|
|
// CHECK2-NEXT: [[TMP22:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = load i32, i32* [[TMP22]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP23]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP24]], 9
|
|
// CHECK2-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK2: cond.true:
|
|
// CHECK2-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK2: cond.false:
|
|
// CHECK2-NEXT: [[TMP25:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END]]
|
|
// CHECK2: cond.end:
|
|
// CHECK2-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP25]], [[COND_FALSE]] ]
|
|
// CHECK2-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP26:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP26]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK2: omp.inner.for.cond:
|
|
// CHECK2-NEXT: [[TMP27:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[TMP28:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP6:%.*]] = icmp sle i32 [[TMP27]], [[TMP28]]
|
|
// CHECK2-NEXT: br i1 [[CMP6]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK2: omp.inner.for.cond.cleanup:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK2: omp.inner.for.body:
|
|
// CHECK2-NEXT: [[TMP29:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP29]], 1
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK2: omp.body.continue:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK2: omp.inner.for.inc:
|
|
// CHECK2-NEXT: [[TMP30:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[ADD7:%.*]] = add nsw i32 [[TMP30]], 1
|
|
// CHECK2-NEXT: store i32 [[ADD7]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK2: omp.inner.for.end:
|
|
// CHECK2-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK2: omp.loop.exit:
|
|
// CHECK2-NEXT: [[TMP31:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP32:%.*]] = load i32, i32* [[TMP31]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP32]])
|
|
// CHECK2-NEXT: [[TMP33:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP34:%.*]] = bitcast %struct.S* [[VLA]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP34]], i8** [[TMP33]], align 8
|
|
// CHECK2-NEXT: [[TMP35:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 1
|
|
// CHECK2-NEXT: [[TMP36:%.*]] = inttoptr i64 [[TMP11]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP36]], i8** [[TMP35]], align 8
|
|
// CHECK2-NEXT: [[TMP37:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP38:%.*]] = load i32, i32* [[TMP37]], align 4
|
|
// CHECK2-NEXT: [[TMP39:%.*]] = bitcast [2 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK2-NEXT: [[TMP40:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP38]], i32 1, i64 16, i8* [[TMP39]], void (i8*, i8*)* @.omp.reduction.reduction_func.8, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: switch i32 [[TMP40]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK2-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK2-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK2-NEXT: ]
|
|
// CHECK2: .omp.reduction.case1:
|
|
// CHECK2-NEXT: [[TMP41:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX1]], i64 [[TMP11]]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAYIDX1]], [[TMP41]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE11:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK2: omp.arraycpy.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[VLA]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST8:%.*]] = phi %struct.S* [ [[ARRAYIDX1]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT9:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST8]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK2-NEXT: [[TMP42:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST8]] to i8*
|
|
// CHECK2-NEXT: [[TMP43:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP42]], i8* align 4 [[TMP43]], i64 4, i1 false)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT9]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST8]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE10:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT9]], [[TMP41]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE10]], label [[OMP_ARRAYCPY_DONE11]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done11:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP38]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.case2:
|
|
// CHECK2-NEXT: [[TMP44:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX1]], i64 [[TMP11]]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY12:%.*]] = icmp eq %struct.S* [[ARRAYIDX1]], [[TMP44]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY12]], label [[OMP_ARRAYCPY_DONE20:%.*]], label [[OMP_ARRAYCPY_BODY13:%.*]]
|
|
// CHECK2: omp.arraycpy.body13:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST14:%.*]] = phi %struct.S* [ [[VLA]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT18:%.*]], [[OMP_ARRAYCPY_BODY13]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST15:%.*]] = phi %struct.S* [ [[ARRAYIDX1]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT17:%.*]], [[OMP_ARRAYCPY_BODY13]] ]
|
|
// CHECK2-NEXT: [[TMP45:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP46:%.*]] = load i32, i32* [[TMP45]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP46]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[CALL16:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST15]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST14]])
|
|
// CHECK2-NEXT: [[TMP47:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST15]] to i8*
|
|
// CHECK2-NEXT: [[TMP48:%.*]] = bitcast %struct.S* [[CALL16]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP47]], i8* align 4 [[TMP48]], i64 4, i1 false)
|
|
// CHECK2-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP46]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT17]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST15]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT18]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST14]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE19:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT17]], [[TMP44]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE19]], label [[OMP_ARRAYCPY_DONE20]], label [[OMP_ARRAYCPY_BODY13]]
|
|
// CHECK2: omp.arraycpy.done20:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP38]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.default:
|
|
// CHECK2-NEXT: [[TMP49:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[VLA]], i64 [[TMP11]]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ISEMPTY:%.*]] = icmp eq %struct.S* [[VLA]], [[TMP49]]
|
|
// CHECK2-NEXT: br i1 [[ARRAYDESTROY_ISEMPTY]], label [[ARRAYDESTROY_DONE21:%.*]], label [[ARRAYDESTROY_BODY:%.*]]
|
|
// CHECK2: arraydestroy.body:
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP49]], [[DOTOMP_REDUCTION_DEFAULT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
|
|
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[VLA]]
|
|
// CHECK2-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE21]], label [[ARRAYDESTROY_BODY]]
|
|
// CHECK2: arraydestroy.done21:
|
|
// CHECK2-NEXT: [[TMP50:%.*]] = load i8*, i8** [[SAVED_STACK]], align 8
|
|
// CHECK2-NEXT: call void @llvm.stackrestore(i8* [[TMP50]])
|
|
// CHECK2-NEXT: [[TMP51:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP52:%.*]] = load i32, i32* [[TMP51]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4]], i32 [[TMP52]])
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.8
|
|
// CHECK2-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [2 x i8*]*
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [2 x i8*]*
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[TMP3]], i64 0, i64 1
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = load i8*, i8** [[TMP12]], align 8
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = ptrtoint i8* [[TMP13]] to i64
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[TMP11]], i64 [[TMP14]]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[TMP11]], [[TMP15]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE2:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK2: omp.arraycpy.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP8]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP11]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]] to i8*
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP16]], i8* align 4 [[TMP17]], i64 4, i1 false)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP15]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE2]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done2:
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined..9
|
|
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.4* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.4*, align 8
|
|
// CHECK2-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[TMP:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[VAR2:%.*]] = alloca [1 x [6 x %struct.S]], align 16
|
|
// CHECK2-NEXT: [[_TMP4:%.*]] = alloca %struct.S**, align 8
|
|
// CHECK2-NEXT: [[_TMP5:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK2-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store %struct.anon.4* [[__CONTEXT]], %struct.anon.4** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load %struct.anon.4*, %struct.anon.4** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_4:%.*]], %struct.anon.4* [[TMP0]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load %struct.S***, %struct.S**** [[TMP1]], align 8
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = load %struct.S**, %struct.S*** [[TMP2]], align 8
|
|
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds %struct.S*, %struct.S** [[TMP3]], i64 1
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load %struct.S*, %struct.S** [[ARRAYIDX]], align 8
|
|
// CHECK2-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[TMP4]], i64 1
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = load %struct.S**, %struct.S*** [[TMP2]], align 8
|
|
// CHECK2-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds %struct.S*, %struct.S** [[TMP5]], i64 1
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = load %struct.S*, %struct.S** [[ARRAYIDX2]], align 8
|
|
// CHECK2-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP6]], i64 6
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [1 x [6 x %struct.S]], [1 x [6 x %struct.S]]* [[VAR2]], i32 0, i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN]], i64 6
|
|
// CHECK2-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAY_BEGIN]], [[TMP7]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
|
|
// CHECK2: omp.arrayinit.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
|
|
// CHECK2-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]])
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP7]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK2: omp.arrayinit.done:
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = load %struct.S**, %struct.S*** [[TMP2]], align 8
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = load %struct.S*, %struct.S** [[TMP8]], align 8
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = ptrtoint %struct.S* [[TMP9]] to i64
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = ptrtoint %struct.S* [[ARRAYIDX1]] to i64
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = sub i64 [[TMP10]], [[TMP11]]
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = sdiv exact i64 [[TMP12]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = bitcast [1 x [6 x %struct.S]]* [[VAR2]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[TMP14]], i64 [[TMP13]]
|
|
// CHECK2-NEXT: store %struct.S** [[_TMP5]], %struct.S*** [[_TMP4]], align 8
|
|
// CHECK2-NEXT: store %struct.S* [[TMP15]], %struct.S** [[_TMP5]], align 8
|
|
// CHECK2-NEXT: [[RHS_BEGIN:%.*]] = bitcast [1 x [6 x %struct.S]]* [[VAR2]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = load i32, i32* [[TMP16]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP17]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP18]], 9
|
|
// CHECK2-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK2: cond.true:
|
|
// CHECK2-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK2: cond.false:
|
|
// CHECK2-NEXT: [[TMP19:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END]]
|
|
// CHECK2: cond.end:
|
|
// CHECK2-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP19]], [[COND_FALSE]] ]
|
|
// CHECK2-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP20]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK2: omp.inner.for.cond:
|
|
// CHECK2-NEXT: [[TMP21:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP6:%.*]] = icmp sle i32 [[TMP21]], [[TMP22]]
|
|
// CHECK2-NEXT: br i1 [[CMP6]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK2: omp.inner.for.cond.cleanup:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK2: omp.inner.for.body:
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP23]], 1
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK2: omp.body.continue:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK2: omp.inner.for.inc:
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[ADD7:%.*]] = add nsw i32 [[TMP24]], 1
|
|
// CHECK2-NEXT: store i32 [[ADD7]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK2: omp.inner.for.end:
|
|
// CHECK2-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK2: omp.loop.exit:
|
|
// CHECK2-NEXT: [[TMP25:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP26:%.*]] = load i32, i32* [[TMP25]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP26]])
|
|
// CHECK2-NEXT: [[TMP27:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP28:%.*]] = bitcast %struct.S* [[RHS_BEGIN]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP28]], i8** [[TMP27]], align 8
|
|
// CHECK2-NEXT: [[TMP29:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP30:%.*]] = load i32, i32* [[TMP29]], align 4
|
|
// CHECK2-NEXT: [[TMP31:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK2-NEXT: [[TMP32:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP30]], i32 1, i64 8, i8* [[TMP31]], void (i8*, i8*)* @.omp.reduction.reduction_func.10, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: switch i32 [[TMP32]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK2-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK2-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK2-NEXT: ]
|
|
// CHECK2: .omp.reduction.case1:
|
|
// CHECK2-NEXT: [[TMP33:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX1]], i64 6
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAYIDX1]], [[TMP33]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE11:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK2: omp.arraycpy.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST8:%.*]] = phi %struct.S* [ [[ARRAYIDX1]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT9:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST8]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK2-NEXT: [[TMP34:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST8]] to i8*
|
|
// CHECK2-NEXT: [[TMP35:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP34]], i8* align 4 [[TMP35]], i64 4, i1 false)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT9]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST8]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE10:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT9]], [[TMP33]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE10]], label [[OMP_ARRAYCPY_DONE11]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done11:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP30]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.case2:
|
|
// CHECK2-NEXT: [[TMP36:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX1]], i64 6
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY12:%.*]] = icmp eq %struct.S* [[ARRAYIDX1]], [[TMP36]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY12]], label [[OMP_ARRAYCPY_DONE20:%.*]], label [[OMP_ARRAYCPY_BODY13:%.*]]
|
|
// CHECK2: omp.arraycpy.body13:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST14:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT18:%.*]], [[OMP_ARRAYCPY_BODY13]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST15:%.*]] = phi %struct.S* [ [[ARRAYIDX1]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT17:%.*]], [[OMP_ARRAYCPY_BODY13]] ]
|
|
// CHECK2-NEXT: [[TMP37:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP38:%.*]] = load i32, i32* [[TMP37]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP38]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[CALL16:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST15]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST14]])
|
|
// CHECK2-NEXT: [[TMP39:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST15]] to i8*
|
|
// CHECK2-NEXT: [[TMP40:%.*]] = bitcast %struct.S* [[CALL16]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP39]], i8* align 4 [[TMP40]], i64 4, i1 false)
|
|
// CHECK2-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP38]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT17]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST15]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT18]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST14]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE19:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT17]], [[TMP36]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE19]], label [[OMP_ARRAYCPY_DONE20]], label [[OMP_ARRAYCPY_BODY13]]
|
|
// CHECK2: omp.arraycpy.done20:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP30]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.default:
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN21:%.*]] = getelementptr inbounds [1 x [6 x %struct.S]], [1 x [6 x %struct.S]]* [[VAR2]], i32 0, i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP41:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN21]], i64 6
|
|
// CHECK2-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
|
|
// CHECK2: arraydestroy.body:
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP41]], [[DOTOMP_REDUCTION_DEFAULT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
|
|
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN21]]
|
|
// CHECK2-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE22:%.*]], label [[ARRAYDESTROY_BODY]]
|
|
// CHECK2: arraydestroy.done22:
|
|
// CHECK2-NEXT: [[TMP42:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP43:%.*]] = load i32, i32* [[TMP42]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4]], i32 [[TMP43]])
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.10
|
|
// CHECK2-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[TMP11]], i64 6
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[TMP11]], [[TMP12]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE2:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK2: omp.arraycpy.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP8]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP11]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]] to i8*
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP13]], i8* align 4 [[TMP14]], i64 4, i1 false)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP12]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE2]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done2:
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined..11
|
|
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.5* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.5*, align 8
|
|
// CHECK2-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[TMP:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[VAR2:%.*]] = alloca [1 x [6 x %struct.S]], align 16
|
|
// CHECK2-NEXT: [[_TMP4:%.*]] = alloca %struct.S**, align 8
|
|
// CHECK2-NEXT: [[_TMP5:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK2-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store %struct.anon.5* [[__CONTEXT]], %struct.anon.5** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load %struct.anon.5*, %struct.anon.5** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_5:%.*]], %struct.anon.5* [[TMP0]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load %struct.S***, %struct.S**** [[TMP1]], align 8
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = load %struct.S**, %struct.S*** [[TMP2]], align 8
|
|
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds %struct.S*, %struct.S** [[TMP3]], i64 1
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load %struct.S*, %struct.S** [[ARRAYIDX]], align 8
|
|
// CHECK2-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[TMP4]], i64 1
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = load %struct.S**, %struct.S*** [[TMP2]], align 8
|
|
// CHECK2-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds %struct.S*, %struct.S** [[TMP5]], i64 1
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = load %struct.S*, %struct.S** [[ARRAYIDX2]], align 8
|
|
// CHECK2-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP6]], i64 6
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [1 x [6 x %struct.S]], [1 x [6 x %struct.S]]* [[VAR2]], i32 0, i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN]], i64 6
|
|
// CHECK2-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAY_BEGIN]], [[TMP7]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
|
|
// CHECK2: omp.arrayinit.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
|
|
// CHECK2-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]])
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP7]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK2: omp.arrayinit.done:
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = load %struct.S**, %struct.S*** [[TMP2]], align 8
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = load %struct.S*, %struct.S** [[TMP8]], align 8
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = ptrtoint %struct.S* [[TMP9]] to i64
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = ptrtoint %struct.S* [[ARRAYIDX1]] to i64
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = sub i64 [[TMP10]], [[TMP11]]
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = sdiv exact i64 [[TMP12]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = bitcast [1 x [6 x %struct.S]]* [[VAR2]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[TMP14]], i64 [[TMP13]]
|
|
// CHECK2-NEXT: store %struct.S** [[_TMP5]], %struct.S*** [[_TMP4]], align 8
|
|
// CHECK2-NEXT: store %struct.S* [[TMP15]], %struct.S** [[_TMP5]], align 8
|
|
// CHECK2-NEXT: [[RHS_BEGIN:%.*]] = bitcast [1 x [6 x %struct.S]]* [[VAR2]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = load i32, i32* [[TMP16]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP17]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP18]], 9
|
|
// CHECK2-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK2: cond.true:
|
|
// CHECK2-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK2: cond.false:
|
|
// CHECK2-NEXT: [[TMP19:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END]]
|
|
// CHECK2: cond.end:
|
|
// CHECK2-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP19]], [[COND_FALSE]] ]
|
|
// CHECK2-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP20]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK2: omp.inner.for.cond:
|
|
// CHECK2-NEXT: [[TMP21:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP6:%.*]] = icmp sle i32 [[TMP21]], [[TMP22]]
|
|
// CHECK2-NEXT: br i1 [[CMP6]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK2: omp.inner.for.cond.cleanup:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK2: omp.inner.for.body:
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP23]], 1
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK2: omp.body.continue:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK2: omp.inner.for.inc:
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[ADD7:%.*]] = add nsw i32 [[TMP24]], 1
|
|
// CHECK2-NEXT: store i32 [[ADD7]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK2: omp.inner.for.end:
|
|
// CHECK2-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK2: omp.loop.exit:
|
|
// CHECK2-NEXT: [[TMP25:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP26:%.*]] = load i32, i32* [[TMP25]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP26]])
|
|
// CHECK2-NEXT: [[TMP27:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP28:%.*]] = bitcast %struct.S* [[RHS_BEGIN]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP28]], i8** [[TMP27]], align 8
|
|
// CHECK2-NEXT: [[TMP29:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP30:%.*]] = load i32, i32* [[TMP29]], align 4
|
|
// CHECK2-NEXT: [[TMP31:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK2-NEXT: [[TMP32:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP30]], i32 1, i64 8, i8* [[TMP31]], void (i8*, i8*)* @.omp.reduction.reduction_func.12, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: switch i32 [[TMP32]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK2-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK2-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK2-NEXT: ]
|
|
// CHECK2: .omp.reduction.case1:
|
|
// CHECK2-NEXT: [[TMP33:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX1]], i64 6
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAYIDX1]], [[TMP33]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE11:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK2: omp.arraycpy.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST8:%.*]] = phi %struct.S* [ [[ARRAYIDX1]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT9:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST8]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK2-NEXT: [[TMP34:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST8]] to i8*
|
|
// CHECK2-NEXT: [[TMP35:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP34]], i8* align 4 [[TMP35]], i64 4, i1 false)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT9]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST8]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE10:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT9]], [[TMP33]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE10]], label [[OMP_ARRAYCPY_DONE11]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done11:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP30]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.case2:
|
|
// CHECK2-NEXT: [[TMP36:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX1]], i64 6
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY12:%.*]] = icmp eq %struct.S* [[ARRAYIDX1]], [[TMP36]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY12]], label [[OMP_ARRAYCPY_DONE20:%.*]], label [[OMP_ARRAYCPY_BODY13:%.*]]
|
|
// CHECK2: omp.arraycpy.body13:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST14:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT18:%.*]], [[OMP_ARRAYCPY_BODY13]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST15:%.*]] = phi %struct.S* [ [[ARRAYIDX1]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT17:%.*]], [[OMP_ARRAYCPY_BODY13]] ]
|
|
// CHECK2-NEXT: [[TMP37:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP38:%.*]] = load i32, i32* [[TMP37]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP38]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[CALL16:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST15]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST14]])
|
|
// CHECK2-NEXT: [[TMP39:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST15]] to i8*
|
|
// CHECK2-NEXT: [[TMP40:%.*]] = bitcast %struct.S* [[CALL16]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP39]], i8* align 4 [[TMP40]], i64 4, i1 false)
|
|
// CHECK2-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP38]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT17]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST15]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT18]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST14]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE19:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT17]], [[TMP36]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE19]], label [[OMP_ARRAYCPY_DONE20]], label [[OMP_ARRAYCPY_BODY13]]
|
|
// CHECK2: omp.arraycpy.done20:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP30]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.default:
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN21:%.*]] = getelementptr inbounds [1 x [6 x %struct.S]], [1 x [6 x %struct.S]]* [[VAR2]], i32 0, i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP41:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN21]], i64 6
|
|
// CHECK2-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
|
|
// CHECK2: arraydestroy.body:
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP41]], [[DOTOMP_REDUCTION_DEFAULT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
|
|
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN21]]
|
|
// CHECK2-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE22:%.*]], label [[ARRAYDESTROY_BODY]]
|
|
// CHECK2: arraydestroy.done22:
|
|
// CHECK2-NEXT: [[TMP42:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP43:%.*]] = load i32, i32* [[TMP42]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4]], i32 [[TMP43]])
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.12
|
|
// CHECK2-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[TMP11]], i64 6
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[TMP11]], [[TMP12]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE2:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK2: omp.arraycpy.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP8]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP11]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]] to i8*
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP13]], i8* align 4 [[TMP14]], i64 4, i1 false)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP12]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE2]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done2:
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined..13
|
|
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.6* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.6*, align 8
|
|
// CHECK2-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[TMP:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[VAR2:%.*]] = alloca [[STRUCT_S:%.*]], align 4
|
|
// CHECK2-NEXT: [[_TMP4:%.*]] = alloca %struct.S**, align 8
|
|
// CHECK2-NEXT: [[_TMP5:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK2-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store %struct.anon.6* [[__CONTEXT]], %struct.anon.6** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load %struct.anon.6*, %struct.anon.6** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_6:%.*]], %struct.anon.6* [[TMP0]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load %struct.S***, %struct.S**** [[TMP1]], align 8
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = load %struct.S**, %struct.S*** [[TMP2]], align 8
|
|
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds %struct.S*, %struct.S** [[TMP3]], i64 1
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load %struct.S*, %struct.S** [[ARRAYIDX]], align 8
|
|
// CHECK2-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP4]], i64 1
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = load %struct.S**, %struct.S*** [[TMP2]], align 8
|
|
// CHECK2-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds %struct.S*, %struct.S** [[TMP5]], i64 1
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = load %struct.S*, %struct.S** [[ARRAYIDX2]], align 8
|
|
// CHECK2-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP6]], i64 1
|
|
// CHECK2-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[VAR2]])
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load %struct.S**, %struct.S*** [[TMP2]], align 8
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = load %struct.S*, %struct.S** [[TMP7]], align 8
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = ptrtoint %struct.S* [[TMP8]] to i64
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = ptrtoint %struct.S* [[ARRAYIDX1]] to i64
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = sub i64 [[TMP9]], [[TMP10]]
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = sdiv exact i64 [[TMP11]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[VAR2]], i64 [[TMP12]]
|
|
// CHECK2-NEXT: store %struct.S** [[_TMP5]], %struct.S*** [[_TMP4]], align 8
|
|
// CHECK2-NEXT: store %struct.S* [[TMP13]], %struct.S** [[_TMP5]], align 8
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = load i32, i32* [[TMP14]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP15]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP16]], 9
|
|
// CHECK2-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK2: cond.true:
|
|
// CHECK2-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK2: cond.false:
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END]]
|
|
// CHECK2: cond.end:
|
|
// CHECK2-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP17]], [[COND_FALSE]] ]
|
|
// CHECK2-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP18]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK2: omp.inner.for.cond:
|
|
// CHECK2-NEXT: [[TMP19:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP6:%.*]] = icmp sle i32 [[TMP19]], [[TMP20]]
|
|
// CHECK2-NEXT: br i1 [[CMP6]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK2: omp.inner.for.cond.cleanup:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK2: omp.inner.for.body:
|
|
// CHECK2-NEXT: [[TMP21:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP21]], 1
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK2: omp.body.continue:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK2: omp.inner.for.inc:
|
|
// CHECK2-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[ADD7:%.*]] = add nsw i32 [[TMP22]], 1
|
|
// CHECK2-NEXT: store i32 [[ADD7]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK2: omp.inner.for.end:
|
|
// CHECK2-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK2: omp.loop.exit:
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP15]])
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = bitcast %struct.S* [[VAR2]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP24]], i8** [[TMP23]], align 8
|
|
// CHECK2-NEXT: [[TMP25:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK2-NEXT: [[TMP26:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP15]], i32 1, i64 8, i8* [[TMP25]], void (i8*, i8*)* @.omp.reduction.reduction_func.14, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: switch i32 [[TMP26]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK2-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK2-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK2-NEXT: ]
|
|
// CHECK2: .omp.reduction.case1:
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYIDX1]], %struct.S* nonnull align 4 dereferenceable(4) [[VAR2]])
|
|
// CHECK2-NEXT: [[TMP27:%.*]] = bitcast %struct.S* [[ARRAYIDX1]] to i8*
|
|
// CHECK2-NEXT: [[TMP28:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP27]], i8* align 4 [[TMP28]], i64 4, i1 false)
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP15]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.case2:
|
|
// CHECK2-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP15]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[CALL8:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYIDX1]], %struct.S* nonnull align 4 dereferenceable(4) [[VAR2]])
|
|
// CHECK2-NEXT: [[TMP29:%.*]] = bitcast %struct.S* [[ARRAYIDX1]] to i8*
|
|
// CHECK2-NEXT: [[TMP30:%.*]] = bitcast %struct.S* [[CALL8]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP29]], i8* align 4 [[TMP30]], i64 4, i1 false)
|
|
// CHECK2-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP15]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP15]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.default:
|
|
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[VAR2]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4]], i32 [[TMP15]])
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.14
|
|
// CHECK2-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to %struct.S*
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[TMP11]], %struct.S* nonnull align 4 dereferenceable(4) [[TMP8]])
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = bitcast %struct.S* [[TMP11]] to i8*
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP12]], i8* align 4 [[TMP13]], i64 4, i1 false)
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined..15
|
|
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.7* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.7*, align 8
|
|
// CHECK2-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[TMP:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[VVAR2:%.*]] = alloca [5 x %struct.S], align 16
|
|
// CHECK2-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store %struct.anon.7* [[__CONTEXT]], %struct.anon.7** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load %struct.anon.7*, %struct.anon.7** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_7:%.*]], %struct.anon.7* [[TMP0]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load [5 x %struct.S]*, [5 x %struct.S]** [[TMP1]], align 8
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [5 x %struct.S], [5 x %struct.S]* [[TMP2]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds [5 x %struct.S], [5 x %struct.S]* [[TMP2]], i64 0, i64 4
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [5 x %struct.S], [5 x %struct.S]* [[VVAR2]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[ARRAY_BEGIN]], i64 5
|
|
// CHECK2-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAY_BEGIN]], [[TMP3]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
|
|
// CHECK2: omp.arrayinit.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
|
|
// CHECK2-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]])
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP3]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK2: omp.arrayinit.done:
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = bitcast [5 x %struct.S]* [[TMP2]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = ptrtoint %struct.S* [[TMP4]] to i64
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = ptrtoint %struct.S* [[ARRAYIDX]] to i64
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = sub i64 [[TMP5]], [[TMP6]]
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = sdiv exact i64 [[TMP7]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = bitcast [5 x %struct.S]* [[VVAR2]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[TMP9]], i64 [[TMP8]]
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast %struct.S* [[TMP10]] to [5 x %struct.S]*
|
|
// CHECK2-NEXT: [[RHS_BEGIN:%.*]] = bitcast [5 x %struct.S]* [[VVAR2]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = load i32, i32* [[TMP12]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP13]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP14]], 9
|
|
// CHECK2-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK2: cond.true:
|
|
// CHECK2-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK2: cond.false:
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END]]
|
|
// CHECK2: cond.end:
|
|
// CHECK2-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP15]], [[COND_FALSE]] ]
|
|
// CHECK2-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP16]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK2: omp.inner.for.cond:
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP2:%.*]] = icmp sle i32 [[TMP17]], [[TMP18]]
|
|
// CHECK2-NEXT: br i1 [[CMP2]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK2: omp.inner.for.cond.cleanup:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK2: omp.inner.for.body:
|
|
// CHECK2-NEXT: [[TMP19:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP19]], 1
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK2: omp.body.continue:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK2: omp.inner.for.inc:
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[ADD3:%.*]] = add nsw i32 [[TMP20]], 1
|
|
// CHECK2-NEXT: store i32 [[ADD3]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK2: omp.inner.for.end:
|
|
// CHECK2-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK2: omp.loop.exit:
|
|
// CHECK2-NEXT: [[TMP21:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP22:%.*]] = load i32, i32* [[TMP21]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP22]])
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = bitcast %struct.S* [[RHS_BEGIN]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP24]], i8** [[TMP23]], align 8
|
|
// CHECK2-NEXT: [[TMP25:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP26:%.*]] = load i32, i32* [[TMP25]], align 4
|
|
// CHECK2-NEXT: [[TMP27:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK2-NEXT: [[TMP28:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP26]], i32 1, i64 8, i8* [[TMP27]], void (i8*, i8*)* @.omp.reduction.reduction_func.16, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: switch i32 [[TMP28]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK2-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK2-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK2-NEXT: ]
|
|
// CHECK2: .omp.reduction.case1:
|
|
// CHECK2-NEXT: [[TMP29:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX]], i64 5
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAYIDX]], [[TMP29]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE7:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK2: omp.arraycpy.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST4:%.*]] = phi %struct.S* [ [[ARRAYIDX]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT5:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST4]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK2-NEXT: [[TMP30:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST4]] to i8*
|
|
// CHECK2-NEXT: [[TMP31:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP30]], i8* align 4 [[TMP31]], i64 4, i1 false)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT5]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST4]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE6:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT5]], [[TMP29]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE6]], label [[OMP_ARRAYCPY_DONE7]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done7:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP26]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.case2:
|
|
// CHECK2-NEXT: [[TMP32:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX]], i64 5
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY8:%.*]] = icmp eq %struct.S* [[ARRAYIDX]], [[TMP32]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY8]], label [[OMP_ARRAYCPY_DONE16:%.*]], label [[OMP_ARRAYCPY_BODY9:%.*]]
|
|
// CHECK2: omp.arraycpy.body9:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST10:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT14:%.*]], [[OMP_ARRAYCPY_BODY9]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST11:%.*]] = phi %struct.S* [ [[ARRAYIDX]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT13:%.*]], [[OMP_ARRAYCPY_BODY9]] ]
|
|
// CHECK2-NEXT: [[TMP33:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP34:%.*]] = load i32, i32* [[TMP33]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP34]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[CALL12:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST11]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST10]])
|
|
// CHECK2-NEXT: [[TMP35:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST11]] to i8*
|
|
// CHECK2-NEXT: [[TMP36:%.*]] = bitcast %struct.S* [[CALL12]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP35]], i8* align 4 [[TMP36]], i64 4, i1 false)
|
|
// CHECK2-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP34]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT13]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST11]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT14]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST10]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE15:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT13]], [[TMP32]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE15]], label [[OMP_ARRAYCPY_DONE16]], label [[OMP_ARRAYCPY_BODY9]]
|
|
// CHECK2: omp.arraycpy.done16:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP26]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.default:
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN17:%.*]] = getelementptr inbounds [5 x %struct.S], [5 x %struct.S]* [[VVAR2]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP37:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN17]], i64 5
|
|
// CHECK2-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
|
|
// CHECK2: arraydestroy.body:
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP37]], [[DOTOMP_REDUCTION_DEFAULT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
|
|
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN17]]
|
|
// CHECK2-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE18:%.*]], label [[ARRAYDESTROY_BODY]]
|
|
// CHECK2: arraydestroy.done18:
|
|
// CHECK2-NEXT: [[TMP38:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP39:%.*]] = load i32, i32* [[TMP38]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4]], i32 [[TMP39]])
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.16
|
|
// CHECK2-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[TMP11]], i64 5
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[TMP11]], [[TMP12]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE2:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK2: omp.arraycpy.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP8]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP11]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]] to i8*
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP13]], i8* align 4 [[TMP14]], i64 4, i1 false)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP12]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE2]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done2:
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined..17
|
|
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.8* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.8*, align 8
|
|
// CHECK2-NEXT: [[TMP:%.*]] = alloca [4 x %struct.S]*, align 8
|
|
// CHECK2-NEXT: [[_TMP1:%.*]] = alloca [4 x %struct.S]*, align 8
|
|
// CHECK2-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[_TMP2:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[VAR3:%.*]] = alloca [2 x %struct.S], align 4
|
|
// CHECK2-NEXT: [[_TMP4:%.*]] = alloca [4 x %struct.S]*, align 8
|
|
// CHECK2-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store %struct.anon.8* [[__CONTEXT]], %struct.anon.8** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load %struct.anon.8*, %struct.anon.8** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_8:%.*]], %struct.anon.8* [[TMP0]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[TMP1]], align 8
|
|
// CHECK2-NEXT: store [4 x %struct.S]* [[TMP2]], [4 x %struct.S]** [[TMP]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[TMP]], align 8
|
|
// CHECK2-NEXT: store [4 x %struct.S]* [[TMP3]], [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [4 x %struct.S], [4 x %struct.S]* [[TMP4]], i64 0, i64 1
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK2-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds [4 x %struct.S], [4 x %struct.S]* [[TMP5]], i64 0, i64 2
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[VAR3]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[ARRAY_BEGIN]], i64 2
|
|
// CHECK2-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAY_BEGIN]], [[TMP6]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
|
|
// CHECK2: omp.arrayinit.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
|
|
// CHECK2-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]])
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP6]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK2: omp.arrayinit.done:
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast [4 x %struct.S]* [[TMP7]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = ptrtoint %struct.S* [[TMP8]] to i64
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = ptrtoint %struct.S* [[ARRAYIDX]] to i64
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = sub i64 [[TMP9]], [[TMP10]]
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = sdiv exact i64 [[TMP11]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = bitcast [2 x %struct.S]* [[VAR3]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[TMP13]], i64 [[TMP12]]
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = bitcast %struct.S* [[TMP14]] to [4 x %struct.S]*
|
|
// CHECK2-NEXT: store [4 x %struct.S]* [[TMP15]], [4 x %struct.S]** [[_TMP4]], align 8
|
|
// CHECK2-NEXT: [[RHS_BEGIN:%.*]] = bitcast [2 x %struct.S]* [[VAR3]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = load i32, i32* [[TMP16]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP17]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP18]], 9
|
|
// CHECK2-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK2: cond.true:
|
|
// CHECK2-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK2: cond.false:
|
|
// CHECK2-NEXT: [[TMP19:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END]]
|
|
// CHECK2: cond.end:
|
|
// CHECK2-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP19]], [[COND_FALSE]] ]
|
|
// CHECK2-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP20]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK2: omp.inner.for.cond:
|
|
// CHECK2-NEXT: [[TMP21:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP5:%.*]] = icmp sle i32 [[TMP21]], [[TMP22]]
|
|
// CHECK2-NEXT: br i1 [[CMP5]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK2: omp.inner.for.cond.cleanup:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK2: omp.inner.for.body:
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP23]], 1
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK2: omp.body.continue:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK2: omp.inner.for.inc:
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[ADD6:%.*]] = add nsw i32 [[TMP24]], 1
|
|
// CHECK2-NEXT: store i32 [[ADD6]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK2: omp.inner.for.end:
|
|
// CHECK2-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK2: omp.loop.exit:
|
|
// CHECK2-NEXT: [[TMP25:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP26:%.*]] = load i32, i32* [[TMP25]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP26]])
|
|
// CHECK2-NEXT: [[TMP27:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP28:%.*]] = bitcast %struct.S* [[RHS_BEGIN]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP28]], i8** [[TMP27]], align 8
|
|
// CHECK2-NEXT: [[TMP29:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP30:%.*]] = load i32, i32* [[TMP29]], align 4
|
|
// CHECK2-NEXT: [[TMP31:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK2-NEXT: [[TMP32:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP30]], i32 1, i64 8, i8* [[TMP31]], void (i8*, i8*)* @.omp.reduction.reduction_func.18, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: switch i32 [[TMP32]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK2-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK2-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK2-NEXT: ]
|
|
// CHECK2: .omp.reduction.case1:
|
|
// CHECK2-NEXT: [[TMP33:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX]], i64 2
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAYIDX]], [[TMP33]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE10:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK2: omp.arraycpy.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST7:%.*]] = phi %struct.S* [ [[ARRAYIDX]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT8:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST7]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK2-NEXT: [[TMP34:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST7]] to i8*
|
|
// CHECK2-NEXT: [[TMP35:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP34]], i8* align 4 [[TMP35]], i64 4, i1 false)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT8]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST7]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE9:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT8]], [[TMP33]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE9]], label [[OMP_ARRAYCPY_DONE10]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done10:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP30]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.case2:
|
|
// CHECK2-NEXT: [[TMP36:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX]], i64 2
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY11:%.*]] = icmp eq %struct.S* [[ARRAYIDX]], [[TMP36]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY11]], label [[OMP_ARRAYCPY_DONE19:%.*]], label [[OMP_ARRAYCPY_BODY12:%.*]]
|
|
// CHECK2: omp.arraycpy.body12:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST13:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT17:%.*]], [[OMP_ARRAYCPY_BODY12]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST14:%.*]] = phi %struct.S* [ [[ARRAYIDX]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT16:%.*]], [[OMP_ARRAYCPY_BODY12]] ]
|
|
// CHECK2-NEXT: [[TMP37:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP38:%.*]] = load i32, i32* [[TMP37]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP38]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[CALL15:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST14]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST13]])
|
|
// CHECK2-NEXT: [[TMP39:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST14]] to i8*
|
|
// CHECK2-NEXT: [[TMP40:%.*]] = bitcast %struct.S* [[CALL15]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP39]], i8* align 4 [[TMP40]], i64 4, i1 false)
|
|
// CHECK2-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP38]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT16]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST14]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT17]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST13]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE18:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT16]], [[TMP36]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE18]], label [[OMP_ARRAYCPY_DONE19]], label [[OMP_ARRAYCPY_BODY12]]
|
|
// CHECK2: omp.arraycpy.done19:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP30]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.default:
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN20:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[VAR3]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP41:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN20]], i64 2
|
|
// CHECK2-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
|
|
// CHECK2: arraydestroy.body:
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP41]], [[DOTOMP_REDUCTION_DEFAULT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
|
|
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN20]]
|
|
// CHECK2-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE21:%.*]], label [[ARRAYDESTROY_BODY]]
|
|
// CHECK2: arraydestroy.done21:
|
|
// CHECK2-NEXT: [[TMP42:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP43:%.*]] = load i32, i32* [[TMP42]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4]], i32 [[TMP43]])
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.18
|
|
// CHECK2-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[TMP11]], i64 2
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[TMP11]], [[TMP12]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE2:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK2: omp.arraycpy.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP8]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP11]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]] to i8*
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP13]], i8* align 4 [[TMP14]], i64 4, i1 false)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP12]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE2]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done2:
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined..19
|
|
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.9* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.9*, align 8
|
|
// CHECK2-NEXT: [[TMP:%.*]] = alloca [4 x %struct.S]*, align 8
|
|
// CHECK2-NEXT: [[_TMP1:%.*]] = alloca [4 x %struct.S]*, align 8
|
|
// CHECK2-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[_TMP2:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[VAR3:%.*]] = alloca [2 x %struct.S], align 4
|
|
// CHECK2-NEXT: [[_TMP4:%.*]] = alloca [4 x %struct.S]*, align 8
|
|
// CHECK2-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store %struct.anon.9* [[__CONTEXT]], %struct.anon.9** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load %struct.anon.9*, %struct.anon.9** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_9:%.*]], %struct.anon.9* [[TMP0]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[TMP1]], align 8
|
|
// CHECK2-NEXT: store [4 x %struct.S]* [[TMP2]], [4 x %struct.S]** [[TMP]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[TMP]], align 8
|
|
// CHECK2-NEXT: store [4 x %struct.S]* [[TMP3]], [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [4 x %struct.S], [4 x %struct.S]* [[TMP4]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK2-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds [4 x %struct.S], [4 x %struct.S]* [[TMP5]], i64 0, i64 1
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[VAR3]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[ARRAY_BEGIN]], i64 2
|
|
// CHECK2-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAY_BEGIN]], [[TMP6]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
|
|
// CHECK2: omp.arrayinit.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
|
|
// CHECK2-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]])
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP6]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK2: omp.arrayinit.done:
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast [4 x %struct.S]* [[TMP7]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = ptrtoint %struct.S* [[TMP8]] to i64
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = ptrtoint %struct.S* [[ARRAYIDX]] to i64
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = sub i64 [[TMP9]], [[TMP10]]
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = sdiv exact i64 [[TMP11]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = bitcast [2 x %struct.S]* [[VAR3]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[TMP13]], i64 [[TMP12]]
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = bitcast %struct.S* [[TMP14]] to [4 x %struct.S]*
|
|
// CHECK2-NEXT: store [4 x %struct.S]* [[TMP15]], [4 x %struct.S]** [[_TMP4]], align 8
|
|
// CHECK2-NEXT: [[RHS_BEGIN:%.*]] = bitcast [2 x %struct.S]* [[VAR3]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = load i32, i32* [[TMP16]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP17]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP18]], 9
|
|
// CHECK2-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK2: cond.true:
|
|
// CHECK2-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK2: cond.false:
|
|
// CHECK2-NEXT: [[TMP19:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END]]
|
|
// CHECK2: cond.end:
|
|
// CHECK2-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP19]], [[COND_FALSE]] ]
|
|
// CHECK2-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP20]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK2: omp.inner.for.cond:
|
|
// CHECK2-NEXT: [[TMP21:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP5:%.*]] = icmp sle i32 [[TMP21]], [[TMP22]]
|
|
// CHECK2-NEXT: br i1 [[CMP5]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK2: omp.inner.for.cond.cleanup:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK2: omp.inner.for.body:
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP23]], 1
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK2: omp.body.continue:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK2: omp.inner.for.inc:
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[ADD6:%.*]] = add nsw i32 [[TMP24]], 1
|
|
// CHECK2-NEXT: store i32 [[ADD6]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK2: omp.inner.for.end:
|
|
// CHECK2-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK2: omp.loop.exit:
|
|
// CHECK2-NEXT: [[TMP25:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP26:%.*]] = load i32, i32* [[TMP25]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP26]])
|
|
// CHECK2-NEXT: [[TMP27:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP28:%.*]] = bitcast %struct.S* [[RHS_BEGIN]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP28]], i8** [[TMP27]], align 8
|
|
// CHECK2-NEXT: [[TMP29:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP30:%.*]] = load i32, i32* [[TMP29]], align 4
|
|
// CHECK2-NEXT: [[TMP31:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK2-NEXT: [[TMP32:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP30]], i32 1, i64 8, i8* [[TMP31]], void (i8*, i8*)* @.omp.reduction.reduction_func.20, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: switch i32 [[TMP32]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK2-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK2-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK2-NEXT: ]
|
|
// CHECK2: .omp.reduction.case1:
|
|
// CHECK2-NEXT: [[TMP33:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX]], i64 2
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAYIDX]], [[TMP33]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE10:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK2: omp.arraycpy.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST7:%.*]] = phi %struct.S* [ [[ARRAYIDX]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT8:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST7]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK2-NEXT: [[TMP34:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST7]] to i8*
|
|
// CHECK2-NEXT: [[TMP35:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP34]], i8* align 4 [[TMP35]], i64 4, i1 false)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT8]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST7]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE9:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT8]], [[TMP33]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE9]], label [[OMP_ARRAYCPY_DONE10]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done10:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP30]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.case2:
|
|
// CHECK2-NEXT: [[TMP36:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX]], i64 2
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY11:%.*]] = icmp eq %struct.S* [[ARRAYIDX]], [[TMP36]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY11]], label [[OMP_ARRAYCPY_DONE19:%.*]], label [[OMP_ARRAYCPY_BODY12:%.*]]
|
|
// CHECK2: omp.arraycpy.body12:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST13:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT17:%.*]], [[OMP_ARRAYCPY_BODY12]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST14:%.*]] = phi %struct.S* [ [[ARRAYIDX]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT16:%.*]], [[OMP_ARRAYCPY_BODY12]] ]
|
|
// CHECK2-NEXT: [[TMP37:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP38:%.*]] = load i32, i32* [[TMP37]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP38]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[CALL15:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST14]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST13]])
|
|
// CHECK2-NEXT: [[TMP39:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST14]] to i8*
|
|
// CHECK2-NEXT: [[TMP40:%.*]] = bitcast %struct.S* [[CALL15]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP39]], i8* align 4 [[TMP40]], i64 4, i1 false)
|
|
// CHECK2-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP38]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT16]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST14]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT17]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST13]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE18:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT16]], [[TMP36]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE18]], label [[OMP_ARRAYCPY_DONE19]], label [[OMP_ARRAYCPY_BODY12]]
|
|
// CHECK2: omp.arraycpy.done19:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP30]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.default:
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN20:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[VAR3]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP41:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN20]], i64 2
|
|
// CHECK2-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
|
|
// CHECK2: arraydestroy.body:
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP41]], [[DOTOMP_REDUCTION_DEFAULT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
|
|
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN20]]
|
|
// CHECK2-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE21:%.*]], label [[ARRAYDESTROY_BODY]]
|
|
// CHECK2: arraydestroy.done21:
|
|
// CHECK2-NEXT: [[TMP42:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP43:%.*]] = load i32, i32* [[TMP42]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4]], i32 [[TMP43]])
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.20
|
|
// CHECK2-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[TMP11]], i64 2
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[TMP11]], [[TMP12]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE2:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK2: omp.arraycpy.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP8]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP11]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]] to i8*
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP13]], i8* align 4 [[TMP14]], i64 4, i1 false)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP12]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE2]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done2:
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined..21
|
|
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.10* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.10*, align 8
|
|
// CHECK2-NEXT: [[TMP:%.*]] = alloca [4 x %struct.S]*, align 8
|
|
// CHECK2-NEXT: [[_TMP1:%.*]] = alloca [4 x %struct.S]*, align 8
|
|
// CHECK2-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[_TMP2:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[SAVED_STACK:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: [[__VLA_EXPR0:%.*]] = alloca i64, align 8
|
|
// CHECK2-NEXT: [[_TMP4:%.*]] = alloca [4 x %struct.S]*, align 8
|
|
// CHECK2-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [2 x i8*], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store %struct.anon.10* [[__CONTEXT]], %struct.anon.10** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load %struct.anon.10*, %struct.anon.10** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_10:%.*]], %struct.anon.10* [[TMP0]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[TMP1]], align 8
|
|
// CHECK2-NEXT: store [4 x %struct.S]* [[TMP2]], [4 x %struct.S]** [[TMP]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[TMP]], align 8
|
|
// CHECK2-NEXT: store [4 x %struct.S]* [[TMP3]], [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [4 x %struct.S], [4 x %struct.S]* [[TMP4]], i64 0, i64 2
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK2-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds [4 x %struct.S], [4 x %struct.S]* [[TMP5]], i64 0, i64 3
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = ptrtoint %struct.S* [[ARRAYIDX3]] to i64
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = ptrtoint %struct.S* [[ARRAYIDX]] to i64
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = sub i64 [[TMP6]], [[TMP7]]
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = sdiv exact i64 [[TMP8]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = add nuw i64 [[TMP9]], 1
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = mul nuw i64 [[TMP10]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = call i8* @llvm.stacksave()
|
|
// CHECK2-NEXT: store i8* [[TMP12]], i8** [[SAVED_STACK]], align 8
|
|
// CHECK2-NEXT: [[VLA:%.*]] = alloca [[STRUCT_S:%.*]], i64 [[TMP10]], align 16
|
|
// CHECK2-NEXT: store i64 [[TMP10]], i64* [[__VLA_EXPR0]], align 8
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[VLA]], i64 [[TMP10]]
|
|
// CHECK2-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq %struct.S* [[VLA]], [[TMP13]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
|
|
// CHECK2: omp.arrayinit.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[VLA]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
|
|
// CHECK2-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]])
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP13]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK2: omp.arrayinit.done:
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = bitcast [4 x %struct.S]* [[TMP14]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = ptrtoint %struct.S* [[TMP15]] to i64
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = ptrtoint %struct.S* [[ARRAYIDX]] to i64
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = sub i64 [[TMP16]], [[TMP17]]
|
|
// CHECK2-NEXT: [[TMP19:%.*]] = sdiv exact i64 [[TMP18]], ptrtoint (float* getelementptr (float, float* null, i32 1) to i64)
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[VLA]], i64 [[TMP19]]
|
|
// CHECK2-NEXT: [[TMP21:%.*]] = bitcast %struct.S* [[TMP20]] to [4 x %struct.S]*
|
|
// CHECK2-NEXT: store [4 x %struct.S]* [[TMP21]], [4 x %struct.S]** [[_TMP4]], align 8
|
|
// CHECK2-NEXT: [[TMP22:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = load i32, i32* [[TMP22]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP23]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP24]], 9
|
|
// CHECK2-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK2: cond.true:
|
|
// CHECK2-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK2: cond.false:
|
|
// CHECK2-NEXT: [[TMP25:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END]]
|
|
// CHECK2: cond.end:
|
|
// CHECK2-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP25]], [[COND_FALSE]] ]
|
|
// CHECK2-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP26:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP26]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK2: omp.inner.for.cond:
|
|
// CHECK2-NEXT: [[TMP27:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[TMP28:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP5:%.*]] = icmp sle i32 [[TMP27]], [[TMP28]]
|
|
// CHECK2-NEXT: br i1 [[CMP5]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK2: omp.inner.for.cond.cleanup:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK2: omp.inner.for.body:
|
|
// CHECK2-NEXT: [[TMP29:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP29]], 1
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK2: omp.body.continue:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK2: omp.inner.for.inc:
|
|
// CHECK2-NEXT: [[TMP30:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[ADD6:%.*]] = add nsw i32 [[TMP30]], 1
|
|
// CHECK2-NEXT: store i32 [[ADD6]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK2: omp.inner.for.end:
|
|
// CHECK2-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK2: omp.loop.exit:
|
|
// CHECK2-NEXT: [[TMP31:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP32:%.*]] = load i32, i32* [[TMP31]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP32]])
|
|
// CHECK2-NEXT: [[TMP33:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP34:%.*]] = bitcast %struct.S* [[VLA]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP34]], i8** [[TMP33]], align 8
|
|
// CHECK2-NEXT: [[TMP35:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 1
|
|
// CHECK2-NEXT: [[TMP36:%.*]] = inttoptr i64 [[TMP10]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP36]], i8** [[TMP35]], align 8
|
|
// CHECK2-NEXT: [[TMP37:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP38:%.*]] = load i32, i32* [[TMP37]], align 4
|
|
// CHECK2-NEXT: [[TMP39:%.*]] = bitcast [2 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK2-NEXT: [[TMP40:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP38]], i32 1, i64 16, i8* [[TMP39]], void (i8*, i8*)* @.omp.reduction.reduction_func.22, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: switch i32 [[TMP40]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK2-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK2-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK2-NEXT: ]
|
|
// CHECK2: .omp.reduction.case1:
|
|
// CHECK2-NEXT: [[TMP41:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX]], i64 [[TMP10]]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAYIDX]], [[TMP41]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE10:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK2: omp.arraycpy.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[VLA]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST7:%.*]] = phi %struct.S* [ [[ARRAYIDX]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT8:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST7]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK2-NEXT: [[TMP42:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST7]] to i8*
|
|
// CHECK2-NEXT: [[TMP43:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP42]], i8* align 4 [[TMP43]], i64 4, i1 false)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT8]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST7]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE9:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT8]], [[TMP41]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE9]], label [[OMP_ARRAYCPY_DONE10]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done10:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP38]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.case2:
|
|
// CHECK2-NEXT: [[TMP44:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAYIDX]], i64 [[TMP10]]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY11:%.*]] = icmp eq %struct.S* [[ARRAYIDX]], [[TMP44]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY11]], label [[OMP_ARRAYCPY_DONE19:%.*]], label [[OMP_ARRAYCPY_BODY12:%.*]]
|
|
// CHECK2: omp.arraycpy.body12:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST13:%.*]] = phi %struct.S* [ [[VLA]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT17:%.*]], [[OMP_ARRAYCPY_BODY12]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST14:%.*]] = phi %struct.S* [ [[ARRAYIDX]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT16:%.*]], [[OMP_ARRAYCPY_BODY12]] ]
|
|
// CHECK2-NEXT: [[TMP45:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP46:%.*]] = load i32, i32* [[TMP45]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP46]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[CALL15:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST14]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST13]])
|
|
// CHECK2-NEXT: [[TMP47:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST14]] to i8*
|
|
// CHECK2-NEXT: [[TMP48:%.*]] = bitcast %struct.S* [[CALL15]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP47]], i8* align 4 [[TMP48]], i64 4, i1 false)
|
|
// CHECK2-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP46]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT16]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST14]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT17]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST13]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE18:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT16]], [[TMP44]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE18]], label [[OMP_ARRAYCPY_DONE19]], label [[OMP_ARRAYCPY_BODY12]]
|
|
// CHECK2: omp.arraycpy.done19:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP38]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.default:
|
|
// CHECK2-NEXT: [[TMP49:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[VLA]], i64 [[TMP10]]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ISEMPTY:%.*]] = icmp eq %struct.S* [[VLA]], [[TMP49]]
|
|
// CHECK2-NEXT: br i1 [[ARRAYDESTROY_ISEMPTY]], label [[ARRAYDESTROY_DONE20:%.*]], label [[ARRAYDESTROY_BODY:%.*]]
|
|
// CHECK2: arraydestroy.body:
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP49]], [[DOTOMP_REDUCTION_DEFAULT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
|
|
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[VLA]]
|
|
// CHECK2-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE20]], label [[ARRAYDESTROY_BODY]]
|
|
// CHECK2: arraydestroy.done20:
|
|
// CHECK2-NEXT: [[TMP50:%.*]] = load i8*, i8** [[SAVED_STACK]], align 8
|
|
// CHECK2-NEXT: call void @llvm.stackrestore(i8* [[TMP50]])
|
|
// CHECK2-NEXT: [[TMP51:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP52:%.*]] = load i32, i32* [[TMP51]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4]], i32 [[TMP52]])
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.22
|
|
// CHECK2-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [2 x i8*]*
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [2 x i8*]*
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[TMP3]], i64 0, i64 1
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = load i8*, i8** [[TMP12]], align 8
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = ptrtoint i8* [[TMP13]] to i64
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[TMP11]], i64 [[TMP14]]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[TMP11]], [[TMP15]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE2:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK2: omp.arraycpy.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP8]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP11]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]] to i8*
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP16]], i8* align 4 [[TMP17]], i64 4, i1 false)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP15]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE2]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done2:
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined..23
|
|
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.11* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.11*, align 8
|
|
// CHECK2-NEXT: [[TMP:%.*]] = alloca [4 x %struct.S]*, align 8
|
|
// CHECK2-NEXT: [[_TMP1:%.*]] = alloca [4 x %struct.S]*, align 8
|
|
// CHECK2-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[_TMP2:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[VAR3:%.*]] = alloca [4 x %struct.S], align 16
|
|
// CHECK2-NEXT: [[_TMP3:%.*]] = alloca [4 x %struct.S]*, align 8
|
|
// CHECK2-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store %struct.anon.11* [[__CONTEXT]], %struct.anon.11** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load %struct.anon.11*, %struct.anon.11** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_11:%.*]], %struct.anon.11* [[TMP0]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[TMP1]], align 8
|
|
// CHECK2-NEXT: store [4 x %struct.S]* [[TMP2]], [4 x %struct.S]** [[TMP]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[TMP]], align 8
|
|
// CHECK2-NEXT: store [4 x %struct.S]* [[TMP3]], [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load [4 x %struct.S]*, [4 x %struct.S]** [[_TMP1]], align 8
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [4 x %struct.S], [4 x %struct.S]* [[VAR3]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[ARRAY_BEGIN]], i64 4
|
|
// CHECK2-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAY_BEGIN]], [[TMP5]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
|
|
// CHECK2: omp.arrayinit.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
|
|
// CHECK2-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]])
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP5]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK2: omp.arrayinit.done:
|
|
// CHECK2-NEXT: store [4 x %struct.S]* [[VAR3]], [4 x %struct.S]** [[_TMP3]], align 8
|
|
// CHECK2-NEXT: [[LHS_BEGIN:%.*]] = bitcast [4 x %struct.S]* [[TMP4]] to %struct.S*
|
|
// CHECK2-NEXT: [[RHS_BEGIN:%.*]] = bitcast [4 x %struct.S]* [[VAR3]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i32, i32* [[TMP6]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP7]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP8]], 9
|
|
// CHECK2-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK2: cond.true:
|
|
// CHECK2-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK2: cond.false:
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END]]
|
|
// CHECK2: cond.end:
|
|
// CHECK2-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP9]], [[COND_FALSE]] ]
|
|
// CHECK2-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP10]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK2: omp.inner.for.cond:
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP4:%.*]] = icmp sle i32 [[TMP11]], [[TMP12]]
|
|
// CHECK2-NEXT: br i1 [[CMP4]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK2: omp.inner.for.cond.cleanup:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK2: omp.inner.for.body:
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP13]], 1
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK2: omp.body.continue:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK2: omp.inner.for.inc:
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[ADD5:%.*]] = add nsw i32 [[TMP14]], 1
|
|
// CHECK2-NEXT: store i32 [[ADD5]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK2: omp.inner.for.end:
|
|
// CHECK2-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK2: omp.loop.exit:
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = load i32, i32* [[TMP15]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP16]])
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = bitcast %struct.S* [[RHS_BEGIN]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP18]], i8** [[TMP17]], align 8
|
|
// CHECK2-NEXT: [[TMP19:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = load i32, i32* [[TMP19]], align 4
|
|
// CHECK2-NEXT: [[TMP21:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK2-NEXT: [[TMP22:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP20]], i32 1, i64 8, i8* [[TMP21]], void (i8*, i8*)* @.omp.reduction.reduction_func.24, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: switch i32 [[TMP22]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK2-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK2-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK2-NEXT: ]
|
|
// CHECK2: .omp.reduction.case1:
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[LHS_BEGIN]], i64 4
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[LHS_BEGIN]], [[TMP23]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE9:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK2: omp.arraycpy.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST6:%.*]] = phi %struct.S* [ [[LHS_BEGIN]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT7:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST6]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST6]] to i8*
|
|
// CHECK2-NEXT: [[TMP25:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP24]], i8* align 4 [[TMP25]], i64 4, i1 false)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT7]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST6]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE8:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT7]], [[TMP23]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE8]], label [[OMP_ARRAYCPY_DONE9]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done9:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP20]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.case2:
|
|
// CHECK2-NEXT: [[TMP26:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[LHS_BEGIN]], i64 4
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY10:%.*]] = icmp eq %struct.S* [[LHS_BEGIN]], [[TMP26]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY10]], label [[OMP_ARRAYCPY_DONE18:%.*]], label [[OMP_ARRAYCPY_BODY11:%.*]]
|
|
// CHECK2: omp.arraycpy.body11:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST12:%.*]] = phi %struct.S* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT16:%.*]], [[OMP_ARRAYCPY_BODY11]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST13:%.*]] = phi %struct.S* [ [[LHS_BEGIN]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT15:%.*]], [[OMP_ARRAYCPY_BODY11]] ]
|
|
// CHECK2-NEXT: [[TMP27:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP28:%.*]] = load i32, i32* [[TMP27]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP28]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[CALL14:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST13]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST12]])
|
|
// CHECK2-NEXT: [[TMP29:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST13]] to i8*
|
|
// CHECK2-NEXT: [[TMP30:%.*]] = bitcast %struct.S* [[CALL14]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP29]], i8* align 4 [[TMP30]], i64 4, i1 false)
|
|
// CHECK2-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP28]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT15]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST13]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT16]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST12]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE17:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT15]], [[TMP26]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE17]], label [[OMP_ARRAYCPY_DONE18]], label [[OMP_ARRAYCPY_BODY11]]
|
|
// CHECK2: omp.arraycpy.done18:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP20]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.default:
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN19:%.*]] = getelementptr inbounds [4 x %struct.S], [4 x %struct.S]* [[VAR3]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP31:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN19]], i64 4
|
|
// CHECK2-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
|
|
// CHECK2: arraydestroy.body:
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP31]], [[DOTOMP_REDUCTION_DEFAULT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
|
|
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN19]]
|
|
// CHECK2-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE20:%.*]], label [[ARRAYDESTROY_BODY]]
|
|
// CHECK2: arraydestroy.done20:
|
|
// CHECK2-NEXT: [[TMP32:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP33:%.*]] = load i32, i32* [[TMP32]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4]], i32 [[TMP33]])
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.24
|
|
// CHECK2-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to %struct.S*
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = getelementptr [[STRUCT_S:%.*]], %struct.S* [[TMP11]], i64 4
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[TMP11]], [[TMP12]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE2:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK2: omp.arraycpy.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP8]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP11]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = bitcast %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]] to i8*
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = bitcast %struct.S* [[CALL]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP13]], i8* align 4 [[TMP14]], i64 4, i1 false)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP12]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE2]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done2:
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@_Z5tmainIiLi42EET_v
|
|
// CHECK2-SAME: () #[[ATTR7]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[T:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[TEST:%.*]] = alloca [[STRUCT_S_12:%.*]], align 4
|
|
// CHECK2-NEXT: [[T_VAR:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[T_VAR1:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[VEC:%.*]] = alloca [2 x i32], align 4
|
|
// CHECK2-NEXT: [[S_ARR:%.*]] = alloca [2 x %struct.S.12], align 4
|
|
// CHECK2-NEXT: [[VAR:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK2-NEXT: [[VAR1:%.*]] = alloca [[STRUCT_S_12]], align 4
|
|
// CHECK2-NEXT: [[ARR:%.*]] = alloca [42 x %struct.S.12], align 16
|
|
// CHECK2-NEXT: [[OMP_OUTLINED_ARG_AGG_:%.*]] = alloca [[STRUCT_ANON_13:%.*]], align 8
|
|
// CHECK2-NEXT: [[OMP_OUTLINED_ARG_AGG_1:%.*]] = alloca [[STRUCT_ANON_14:%.*]], align 8
|
|
// CHECK2-NEXT: [[OMP_OUTLINED_ARG_AGG_2:%.*]] = alloca [[STRUCT_ANON_15:%.*]], align 8
|
|
// CHECK2-NEXT: call void @_ZN1SIiEC1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[TEST]])
|
|
// CHECK2-NEXT: store i32 0, i32* [[T_VAR]], align 4
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = bitcast [2 x i32]* [[VEC]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP0]], i8* align 4 bitcast ([2 x i32]* @__const._Z5tmainIiLi42EET_v.vec to i8*), i64 8, i1 false)
|
|
// CHECK2-NEXT: [[ARRAYINIT_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S.12], [2 x %struct.S.12]* [[S_ARR]], i64 0, i64 0
|
|
// CHECK2-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.12* nonnull align 4 dereferenceable(4) [[ARRAYINIT_BEGIN]], i32 1)
|
|
// CHECK2-NEXT: [[ARRAYINIT_ELEMENT:%.*]] = getelementptr inbounds [[STRUCT_S_12]], %struct.S.12* [[ARRAYINIT_BEGIN]], i64 1
|
|
// CHECK2-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.12* nonnull align 4 dereferenceable(4) [[ARRAYINIT_ELEMENT]], i32 2)
|
|
// CHECK2-NEXT: store %struct.S.12* [[TEST]], %struct.S.12** [[VAR]], align 8
|
|
// CHECK2-NEXT: call void @_ZN1SIiEC1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[VAR1]])
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [42 x %struct.S.12], [42 x %struct.S.12]* [[ARR]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[ARRAYCTOR_END:%.*]] = getelementptr inbounds [[STRUCT_S_12]], %struct.S.12* [[ARRAY_BEGIN]], i64 42
|
|
// CHECK2-NEXT: br label [[ARRAYCTOR_LOOP:%.*]]
|
|
// CHECK2: arrayctor.loop:
|
|
// CHECK2-NEXT: [[ARRAYCTOR_CUR:%.*]] = phi %struct.S.12* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[ARRAYCTOR_NEXT:%.*]], [[ARRAYCTOR_LOOP]] ]
|
|
// CHECK2-NEXT: call void @_ZN1SIiEC1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[ARRAYCTOR_CUR]])
|
|
// CHECK2-NEXT: [[ARRAYCTOR_NEXT]] = getelementptr inbounds [[STRUCT_S_12]], %struct.S.12* [[ARRAYCTOR_CUR]], i64 1
|
|
// CHECK2-NEXT: [[ARRAYCTOR_DONE:%.*]] = icmp eq %struct.S.12* [[ARRAYCTOR_NEXT]], [[ARRAYCTOR_END]]
|
|
// CHECK2-NEXT: br i1 [[ARRAYCTOR_DONE]], label [[ARRAYCTOR_CONT:%.*]], label [[ARRAYCTOR_LOOP]]
|
|
// CHECK2: arrayctor.cont:
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_13]], %struct.anon.13* [[OMP_OUTLINED_ARG_AGG_]], i32 0, i32 0
|
|
// CHECK2-NEXT: store i32* [[T_VAR]], i32** [[TMP1]], align 8
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = getelementptr inbounds [[STRUCT_ANON_13]], %struct.anon.13* [[OMP_OUTLINED_ARG_AGG_]], i32 0, i32 1
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = load %struct.S.12*, %struct.S.12** [[VAR]], align 8
|
|
// CHECK2-NEXT: store %struct.S.12* [[TMP3]], %struct.S.12** [[TMP2]], align 8
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_ANON_13]], %struct.anon.13* [[OMP_OUTLINED_ARG_AGG_]], i32 0, i32 2
|
|
// CHECK2-NEXT: store %struct.S.12* [[VAR1]], %struct.S.12** [[TMP4]], align 8
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_ANON_13]], %struct.anon.13* [[OMP_OUTLINED_ARG_AGG_]], i32 0, i32 3
|
|
// CHECK2-NEXT: store i32* [[T_VAR1]], i32** [[TMP5]], align 8
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_ANON_13]], %struct.anon.13* [[OMP_OUTLINED_ARG_AGG_]], i32 0, i32 4
|
|
// CHECK2-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[TMP6]], align 8
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = getelementptr inbounds [[STRUCT_ANON_13]], %struct.anon.13* [[OMP_OUTLINED_ARG_AGG_]], i32 0, i32 5
|
|
// CHECK2-NEXT: store [2 x %struct.S.12]* [[S_ARR]], [2 x %struct.S.12]** [[TMP7]], align 8
|
|
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.13*)* @.omp_outlined..25 to void (i32*, i32*, ...)*), %struct.anon.13* [[OMP_OUTLINED_ARG_AGG_]])
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = getelementptr inbounds [[STRUCT_ANON_14]], %struct.anon.14* [[OMP_OUTLINED_ARG_AGG_1]], i32 0, i32 0
|
|
// CHECK2-NEXT: store i32* [[T_VAR]], i32** [[TMP8]], align 8
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_ANON_14]], %struct.anon.14* [[OMP_OUTLINED_ARG_AGG_1]], i32 0, i32 1
|
|
// CHECK2-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[TMP9]], align 8
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = getelementptr inbounds [[STRUCT_ANON_14]], %struct.anon.14* [[OMP_OUTLINED_ARG_AGG_1]], i32 0, i32 2
|
|
// CHECK2-NEXT: store [2 x %struct.S.12]* [[S_ARR]], [2 x %struct.S.12]** [[TMP10]], align 8
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = getelementptr inbounds [[STRUCT_ANON_14]], %struct.anon.14* [[OMP_OUTLINED_ARG_AGG_1]], i32 0, i32 3
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = load %struct.S.12*, %struct.S.12** [[VAR]], align 8
|
|
// CHECK2-NEXT: store %struct.S.12* [[TMP12]], %struct.S.12** [[TMP11]], align 8
|
|
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.14*)* @.omp_outlined..27 to void (i32*, i32*, ...)*), %struct.anon.14* [[OMP_OUTLINED_ARG_AGG_1]])
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = getelementptr inbounds [[STRUCT_ANON_15]], %struct.anon.15* [[OMP_OUTLINED_ARG_AGG_2]], i32 0, i32 0
|
|
// CHECK2-NEXT: store [42 x %struct.S.12]* [[ARR]], [42 x %struct.S.12]** [[TMP13]], align 8
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = getelementptr inbounds [[STRUCT_ANON_15]], %struct.anon.15* [[OMP_OUTLINED_ARG_AGG_2]], i32 0, i32 1
|
|
// CHECK2-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[TMP14]], align 8
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = getelementptr inbounds [[STRUCT_ANON_15]], %struct.anon.15* [[OMP_OUTLINED_ARG_AGG_2]], i32 0, i32 2
|
|
// CHECK2-NEXT: store i32* [[T_VAR]], i32** [[TMP15]], align 8
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = getelementptr inbounds [[STRUCT_ANON_15]], %struct.anon.15* [[OMP_OUTLINED_ARG_AGG_2]], i32 0, i32 3
|
|
// CHECK2-NEXT: store [2 x %struct.S.12]* [[S_ARR]], [2 x %struct.S.12]** [[TMP16]], align 8
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = getelementptr inbounds [[STRUCT_ANON_15]], %struct.anon.15* [[OMP_OUTLINED_ARG_AGG_2]], i32 0, i32 4
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = load %struct.S.12*, %struct.S.12** [[VAR]], align 8
|
|
// CHECK2-NEXT: store %struct.S.12* [[TMP18]], %struct.S.12** [[TMP17]], align 8
|
|
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon.15*)* @.omp_outlined..29 to void (i32*, i32*, ...)*), %struct.anon.15* [[OMP_OUTLINED_ARG_AGG_2]])
|
|
// CHECK2-NEXT: store i32 0, i32* [[RETVAL]], align 4
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN3:%.*]] = getelementptr inbounds [42 x %struct.S.12], [42 x %struct.S.12]* [[ARR]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP19:%.*]] = getelementptr inbounds [[STRUCT_S_12]], %struct.S.12* [[ARRAY_BEGIN3]], i64 42
|
|
// CHECK2-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
|
|
// CHECK2: arraydestroy.body:
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S.12* [ [[TMP19]], [[ARRAYCTOR_CONT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S_12]], %struct.S.12* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
|
|
// CHECK2-NEXT: call void @_ZN1SIiED1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S.12* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN3]]
|
|
// CHECK2-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE4:%.*]], label [[ARRAYDESTROY_BODY]]
|
|
// CHECK2: arraydestroy.done4:
|
|
// CHECK2-NEXT: call void @_ZN1SIiED1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[VAR1]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN5:%.*]] = getelementptr inbounds [2 x %struct.S.12], [2 x %struct.S.12]* [[S_ARR]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = getelementptr inbounds [[STRUCT_S_12]], %struct.S.12* [[ARRAY_BEGIN5]], i64 2
|
|
// CHECK2-NEXT: br label [[ARRAYDESTROY_BODY6:%.*]]
|
|
// CHECK2: arraydestroy.body6:
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENTPAST7:%.*]] = phi %struct.S.12* [ [[TMP20]], [[ARRAYDESTROY_DONE4]] ], [ [[ARRAYDESTROY_ELEMENT8:%.*]], [[ARRAYDESTROY_BODY6]] ]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENT8]] = getelementptr inbounds [[STRUCT_S_12]], %struct.S.12* [[ARRAYDESTROY_ELEMENTPAST7]], i64 -1
|
|
// CHECK2-NEXT: call void @_ZN1SIiED1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT8]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_DONE9:%.*]] = icmp eq %struct.S.12* [[ARRAYDESTROY_ELEMENT8]], [[ARRAY_BEGIN5]]
|
|
// CHECK2-NEXT: br i1 [[ARRAYDESTROY_DONE9]], label [[ARRAYDESTROY_DONE10:%.*]], label [[ARRAYDESTROY_BODY6]]
|
|
// CHECK2: arraydestroy.done10:
|
|
// CHECK2-NEXT: call void @_ZN1SIiED1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[TEST]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: [[TMP21:%.*]] = load i32, i32* [[RETVAL]], align 4
|
|
// CHECK2-NEXT: ret i32 [[TMP21]]
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfEC2Ev
|
|
// CHECK2-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK2-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load volatile double, double* @g, align 8
|
|
// CHECK2-NEXT: [[CONV:%.*]] = fptrunc double [[TMP0]] to float
|
|
// CHECK2-NEXT: store float [[CONV]], float* [[F]], align 4
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfEC2Ef
|
|
// CHECK2-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], float [[A:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
|
|
// CHECK2-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: store float [[A]], float* [[A_ADDR]], align 4
|
|
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load float, float* [[A_ADDR]], align 4
|
|
// CHECK2-NEXT: [[CONV:%.*]] = fpext float [[TMP0]] to double
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = load volatile double, double* @g, align 8
|
|
// CHECK2-NEXT: [[ADD:%.*]] = fadd double [[CONV]], [[TMP1]]
|
|
// CHECK2-NEXT: [[CONV2:%.*]] = fptrunc double [[ADD]] to float
|
|
// CHECK2-NEXT: store float [[CONV2]], float* [[F]], align 4
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfED2Ev
|
|
// CHECK2-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
|
|
// CHECK2-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiEC1Ev
|
|
// CHECK2-SAME: (%struct.S.12* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK2-NEXT: store %struct.S.12* [[THIS]], %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S.12*, %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: call void @_ZN1SIiEC2Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[THIS1]])
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiEC1Ei
|
|
// CHECK2-SAME: (%struct.S.12* nonnull align 4 dereferenceable(4) [[THIS:%.*]], i32 [[A:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: store %struct.S.12* [[THIS]], %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: store i32 [[A]], i32* [[A_ADDR]], align 4
|
|
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S.12*, %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load i32, i32* [[A_ADDR]], align 4
|
|
// CHECK2-NEXT: call void @_ZN1SIiEC2Ei(%struct.S.12* nonnull align 4 dereferenceable(4) [[THIS1]], i32 [[TMP0]])
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined..25
|
|
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.13* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.13*, align 8
|
|
// CHECK2-NEXT: [[TMP:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK2-NEXT: [[_TMP1:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK2-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[_TMP2:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[T_VAR:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[VAR:%.*]] = alloca [[STRUCT_S_12:%.*]], align 4
|
|
// CHECK2-NEXT: [[_TMP3:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK2-NEXT: [[VAR1:%.*]] = alloca [[STRUCT_S_12]], align 4
|
|
// CHECK2-NEXT: [[T_VAR1:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [4 x i8*], align 8
|
|
// CHECK2-NEXT: [[REF_TMP:%.*]] = alloca [[STRUCT_S_12]], align 4
|
|
// CHECK2-NEXT: [[REF_TMP18:%.*]] = alloca [[STRUCT_S_12]], align 4
|
|
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store %struct.anon.13* [[__CONTEXT]], %struct.anon.13** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load %struct.anon.13*, %struct.anon.13** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_13:%.*]], %struct.anon.13* [[TMP0]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i32*, i32** [[TMP1]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_ANON_13]], %struct.anon.13* [[TMP0]], i32 0, i32 1
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load %struct.S.12*, %struct.S.12** [[TMP3]], align 8
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_ANON_13]], %struct.anon.13* [[TMP0]], i32 0, i32 2
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = load %struct.S.12*, %struct.S.12** [[TMP5]], align 8
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = getelementptr inbounds [[STRUCT_ANON_13]], %struct.anon.13* [[TMP0]], i32 0, i32 3
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = load i32*, i32** [[TMP7]], align 8
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_ANON_13]], %struct.anon.13* [[TMP0]], i32 0, i32 4
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load [2 x i32]*, [2 x i32]** [[TMP9]], align 8
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = getelementptr inbounds [[STRUCT_ANON_13]], %struct.anon.13* [[TMP0]], i32 0, i32 5
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = load [2 x %struct.S.12]*, [2 x %struct.S.12]** [[TMP11]], align 8
|
|
// CHECK2-NEXT: store %struct.S.12* [[TMP4]], %struct.S.12** [[TMP]], align 8
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = load %struct.S.12*, %struct.S.12** [[TMP]], align 8
|
|
// CHECK2-NEXT: store %struct.S.12* [[TMP13]], %struct.S.12** [[_TMP1]], align 8
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK2-NEXT: store i32 0, i32* [[T_VAR]], align 4
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = load %struct.S.12*, %struct.S.12** [[_TMP1]], align 8
|
|
// CHECK2-NEXT: call void @_ZN1SIiEC1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[VAR]])
|
|
// CHECK2-NEXT: store %struct.S.12* [[VAR]], %struct.S.12** [[_TMP3]], align 8
|
|
// CHECK2-NEXT: call void @_ZN1SIiEC1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[VAR1]])
|
|
// CHECK2-NEXT: store i32 2147483647, i32* [[T_VAR1]], align 4
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = load i32, i32* [[TMP15]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP16]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP17]], 1
|
|
// CHECK2-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK2: cond.true:
|
|
// CHECK2-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK2: cond.false:
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END]]
|
|
// CHECK2: cond.end:
|
|
// CHECK2-NEXT: [[COND:%.*]] = phi i32 [ 1, [[COND_TRUE]] ], [ [[TMP18]], [[COND_FALSE]] ]
|
|
// CHECK2-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP19:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP19]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK2: omp.inner.for.cond:
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[TMP21:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP4:%.*]] = icmp sle i32 [[TMP20]], [[TMP21]]
|
|
// CHECK2-NEXT: br i1 [[CMP4]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK2: omp.inner.for.cond.cleanup:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK2: omp.inner.for.body:
|
|
// CHECK2-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP22]], 1
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = load i32, i32* [[T_VAR]], align 4
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK2-NEXT: [[IDXPROM:%.*]] = sext i32 [[TMP24]] to i64
|
|
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[TMP10]], i64 0, i64 [[IDXPROM]]
|
|
// CHECK2-NEXT: store i32 [[TMP23]], i32* [[ARRAYIDX]], align 4
|
|
// CHECK2-NEXT: [[TMP25:%.*]] = load %struct.S.12*, %struct.S.12** [[_TMP3]], align 8
|
|
// CHECK2-NEXT: [[TMP26:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK2-NEXT: [[IDXPROM5:%.*]] = sext i32 [[TMP26]] to i64
|
|
// CHECK2-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds [2 x %struct.S.12], [2 x %struct.S.12]* [[TMP12]], i64 0, i64 [[IDXPROM5]]
|
|
// CHECK2-NEXT: [[TMP27:%.*]] = bitcast %struct.S.12* [[ARRAYIDX6]] to i8*
|
|
// CHECK2-NEXT: [[TMP28:%.*]] = bitcast %struct.S.12* [[TMP25]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP27]], i8* align 4 [[TMP28]], i64 4, i1 false)
|
|
// CHECK2-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK2: omp.body.continue:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK2: omp.inner.for.inc:
|
|
// CHECK2-NEXT: [[TMP29:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[ADD7:%.*]] = add nsw i32 [[TMP29]], 1
|
|
// CHECK2-NEXT: store i32 [[ADD7]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK2: omp.inner.for.end:
|
|
// CHECK2-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK2: omp.loop.exit:
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP16]])
|
|
// CHECK2-NEXT: [[TMP30:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP31:%.*]] = bitcast i32* [[T_VAR]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP31]], i8** [[TMP30]], align 8
|
|
// CHECK2-NEXT: [[TMP32:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 1
|
|
// CHECK2-NEXT: [[TMP33:%.*]] = bitcast %struct.S.12* [[VAR]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP33]], i8** [[TMP32]], align 8
|
|
// CHECK2-NEXT: [[TMP34:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 2
|
|
// CHECK2-NEXT: [[TMP35:%.*]] = bitcast %struct.S.12* [[VAR1]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP35]], i8** [[TMP34]], align 8
|
|
// CHECK2-NEXT: [[TMP36:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 3
|
|
// CHECK2-NEXT: [[TMP37:%.*]] = bitcast i32* [[T_VAR1]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP37]], i8** [[TMP36]], align 8
|
|
// CHECK2-NEXT: [[TMP38:%.*]] = bitcast [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK2-NEXT: [[TMP39:%.*]] = call i32 @__kmpc_reduce_nowait(%struct.ident_t* @[[GLOB2]], i32 [[TMP16]], i32 4, i64 32, i8* [[TMP38]], void (i8*, i8*)* @.omp.reduction.reduction_func.26, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: switch i32 [[TMP39]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK2-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK2-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK2-NEXT: ]
|
|
// CHECK2: .omp.reduction.case1:
|
|
// CHECK2-NEXT: [[TMP40:%.*]] = load i32, i32* [[TMP2]], align 4
|
|
// CHECK2-NEXT: [[TMP41:%.*]] = load i32, i32* [[T_VAR]], align 4
|
|
// CHECK2-NEXT: [[ADD8:%.*]] = add nsw i32 [[TMP40]], [[TMP41]]
|
|
// CHECK2-NEXT: store i32 [[ADD8]], i32* [[TMP2]], align 4
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S.12* @_ZN1SIiEanERKS0_(%struct.S.12* nonnull align 4 dereferenceable(4) [[TMP14]], %struct.S.12* nonnull align 4 dereferenceable(4) [[VAR]])
|
|
// CHECK2-NEXT: [[TMP42:%.*]] = bitcast %struct.S.12* [[TMP14]] to i8*
|
|
// CHECK2-NEXT: [[TMP43:%.*]] = bitcast %struct.S.12* [[CALL]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP42]], i8* align 4 [[TMP43]], i64 4, i1 false)
|
|
// CHECK2-NEXT: [[CALL9:%.*]] = call i32 @_ZN1SIiEcviEv(%struct.S.12* nonnull align 4 dereferenceable(4) [[TMP6]])
|
|
// CHECK2-NEXT: [[TOBOOL:%.*]] = icmp ne i32 [[CALL9]], 0
|
|
// CHECK2-NEXT: br i1 [[TOBOOL]], label [[LAND_RHS:%.*]], label [[LAND_END:%.*]]
|
|
// CHECK2: land.rhs:
|
|
// CHECK2-NEXT: [[CALL10:%.*]] = call i32 @_ZN1SIiEcviEv(%struct.S.12* nonnull align 4 dereferenceable(4) [[VAR1]])
|
|
// CHECK2-NEXT: [[TOBOOL11:%.*]] = icmp ne i32 [[CALL10]], 0
|
|
// CHECK2-NEXT: br label [[LAND_END]]
|
|
// CHECK2: land.end:
|
|
// CHECK2-NEXT: [[TMP44:%.*]] = phi i1 [ false, [[DOTOMP_REDUCTION_CASE1]] ], [ [[TOBOOL11]], [[LAND_RHS]] ]
|
|
// CHECK2-NEXT: [[CONV:%.*]] = zext i1 [[TMP44]] to i32
|
|
// CHECK2-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.12* nonnull align 4 dereferenceable(4) [[REF_TMP]], i32 [[CONV]])
|
|
// CHECK2-NEXT: [[TMP45:%.*]] = bitcast %struct.S.12* [[TMP6]] to i8*
|
|
// CHECK2-NEXT: [[TMP46:%.*]] = bitcast %struct.S.12* [[REF_TMP]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP45]], i8* align 4 [[TMP46]], i64 4, i1 false)
|
|
// CHECK2-NEXT: call void @_ZN1SIiED1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[REF_TMP]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: [[TMP47:%.*]] = load i32, i32* [[TMP8]], align 4
|
|
// CHECK2-NEXT: [[TMP48:%.*]] = load i32, i32* [[T_VAR1]], align 4
|
|
// CHECK2-NEXT: [[CMP12:%.*]] = icmp slt i32 [[TMP47]], [[TMP48]]
|
|
// CHECK2-NEXT: br i1 [[CMP12]], label [[COND_TRUE13:%.*]], label [[COND_FALSE14:%.*]]
|
|
// CHECK2: cond.true13:
|
|
// CHECK2-NEXT: [[TMP49:%.*]] = load i32, i32* [[TMP8]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END15:%.*]]
|
|
// CHECK2: cond.false14:
|
|
// CHECK2-NEXT: [[TMP50:%.*]] = load i32, i32* [[T_VAR1]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END15]]
|
|
// CHECK2: cond.end15:
|
|
// CHECK2-NEXT: [[COND16:%.*]] = phi i32 [ [[TMP49]], [[COND_TRUE13]] ], [ [[TMP50]], [[COND_FALSE14]] ]
|
|
// CHECK2-NEXT: store i32 [[COND16]], i32* [[TMP8]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce_nowait(%struct.ident_t* @[[GLOB2]], i32 [[TMP16]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.case2:
|
|
// CHECK2-NEXT: [[TMP51:%.*]] = load i32, i32* [[T_VAR]], align 4
|
|
// CHECK2-NEXT: [[TMP52:%.*]] = atomicrmw add i32* [[TMP2]], i32 [[TMP51]] monotonic, align 4
|
|
// CHECK2-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP16]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[CALL17:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S.12* @_ZN1SIiEanERKS0_(%struct.S.12* nonnull align 4 dereferenceable(4) [[TMP14]], %struct.S.12* nonnull align 4 dereferenceable(4) [[VAR]])
|
|
// CHECK2-NEXT: [[TMP53:%.*]] = bitcast %struct.S.12* [[TMP14]] to i8*
|
|
// CHECK2-NEXT: [[TMP54:%.*]] = bitcast %struct.S.12* [[CALL17]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP53]], i8* align 4 [[TMP54]], i64 4, i1 false)
|
|
// CHECK2-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP16]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP16]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[CALL19:%.*]] = call i32 @_ZN1SIiEcviEv(%struct.S.12* nonnull align 4 dereferenceable(4) [[TMP6]])
|
|
// CHECK2-NEXT: [[TOBOOL20:%.*]] = icmp ne i32 [[CALL19]], 0
|
|
// CHECK2-NEXT: br i1 [[TOBOOL20]], label [[LAND_RHS21:%.*]], label [[LAND_END24:%.*]]
|
|
// CHECK2: land.rhs21:
|
|
// CHECK2-NEXT: [[CALL22:%.*]] = call i32 @_ZN1SIiEcviEv(%struct.S.12* nonnull align 4 dereferenceable(4) [[VAR1]])
|
|
// CHECK2-NEXT: [[TOBOOL23:%.*]] = icmp ne i32 [[CALL22]], 0
|
|
// CHECK2-NEXT: br label [[LAND_END24]]
|
|
// CHECK2: land.end24:
|
|
// CHECK2-NEXT: [[TMP55:%.*]] = phi i1 [ false, [[DOTOMP_REDUCTION_CASE2]] ], [ [[TOBOOL23]], [[LAND_RHS21]] ]
|
|
// CHECK2-NEXT: [[CONV25:%.*]] = zext i1 [[TMP55]] to i32
|
|
// CHECK2-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.12* nonnull align 4 dereferenceable(4) [[REF_TMP18]], i32 [[CONV25]])
|
|
// CHECK2-NEXT: [[TMP56:%.*]] = bitcast %struct.S.12* [[TMP6]] to i8*
|
|
// CHECK2-NEXT: [[TMP57:%.*]] = bitcast %struct.S.12* [[REF_TMP18]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP56]], i8* align 4 [[TMP57]], i64 4, i1 false)
|
|
// CHECK2-NEXT: call void @_ZN1SIiED1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[REF_TMP18]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP16]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[TMP58:%.*]] = load i32, i32* [[T_VAR1]], align 4
|
|
// CHECK2-NEXT: [[TMP59:%.*]] = atomicrmw min i32* [[TMP8]], i32 [[TMP58]] monotonic, align 4
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.default:
|
|
// CHECK2-NEXT: call void @_ZN1SIiED1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[VAR1]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: call void @_ZN1SIiED1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[VAR]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.26
|
|
// CHECK2-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: [[REF_TMP:%.*]] = alloca [[STRUCT_S_12:%.*]], align 4
|
|
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [4 x i8*]*
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [4 x i8*]*
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to i32*
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i32*
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 1
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = load i8*, i8** [[TMP12]], align 8
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = bitcast i8* [[TMP13]] to %struct.S.12*
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 1
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = load i8*, i8** [[TMP15]], align 8
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = bitcast i8* [[TMP16]] to %struct.S.12*
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 2
|
|
// CHECK2-NEXT: [[TMP19:%.*]] = load i8*, i8** [[TMP18]], align 8
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = bitcast i8* [[TMP19]] to %struct.S.12*
|
|
// CHECK2-NEXT: [[TMP21:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 2
|
|
// CHECK2-NEXT: [[TMP22:%.*]] = load i8*, i8** [[TMP21]], align 8
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = bitcast i8* [[TMP22]] to %struct.S.12*
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 3
|
|
// CHECK2-NEXT: [[TMP25:%.*]] = load i8*, i8** [[TMP24]], align 8
|
|
// CHECK2-NEXT: [[TMP26:%.*]] = bitcast i8* [[TMP25]] to i32*
|
|
// CHECK2-NEXT: [[TMP27:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 3
|
|
// CHECK2-NEXT: [[TMP28:%.*]] = load i8*, i8** [[TMP27]], align 8
|
|
// CHECK2-NEXT: [[TMP29:%.*]] = bitcast i8* [[TMP28]] to i32*
|
|
// CHECK2-NEXT: [[TMP30:%.*]] = load i32, i32* [[TMP11]], align 4
|
|
// CHECK2-NEXT: [[TMP31:%.*]] = load i32, i32* [[TMP8]], align 4
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP30]], [[TMP31]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[TMP11]], align 4
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 4 dereferenceable(4) %struct.S.12* @_ZN1SIiEanERKS0_(%struct.S.12* nonnull align 4 dereferenceable(4) [[TMP17]], %struct.S.12* nonnull align 4 dereferenceable(4) [[TMP14]])
|
|
// CHECK2-NEXT: [[TMP32:%.*]] = bitcast %struct.S.12* [[TMP17]] to i8*
|
|
// CHECK2-NEXT: [[TMP33:%.*]] = bitcast %struct.S.12* [[CALL]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP32]], i8* align 4 [[TMP33]], i64 4, i1 false)
|
|
// CHECK2-NEXT: [[CALL2:%.*]] = call i32 @_ZN1SIiEcviEv(%struct.S.12* nonnull align 4 dereferenceable(4) [[TMP23]])
|
|
// CHECK2-NEXT: [[TOBOOL:%.*]] = icmp ne i32 [[CALL2]], 0
|
|
// CHECK2-NEXT: br i1 [[TOBOOL]], label [[LAND_RHS:%.*]], label [[LAND_END:%.*]]
|
|
// CHECK2: land.rhs:
|
|
// CHECK2-NEXT: [[CALL3:%.*]] = call i32 @_ZN1SIiEcviEv(%struct.S.12* nonnull align 4 dereferenceable(4) [[TMP20]])
|
|
// CHECK2-NEXT: [[TOBOOL4:%.*]] = icmp ne i32 [[CALL3]], 0
|
|
// CHECK2-NEXT: br label [[LAND_END]]
|
|
// CHECK2: land.end:
|
|
// CHECK2-NEXT: [[TMP34:%.*]] = phi i1 [ false, [[ENTRY:%.*]] ], [ [[TOBOOL4]], [[LAND_RHS]] ]
|
|
// CHECK2-NEXT: [[CONV:%.*]] = zext i1 [[TMP34]] to i32
|
|
// CHECK2-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.12* nonnull align 4 dereferenceable(4) [[REF_TMP]], i32 [[CONV]])
|
|
// CHECK2-NEXT: [[TMP35:%.*]] = bitcast %struct.S.12* [[TMP23]] to i8*
|
|
// CHECK2-NEXT: [[TMP36:%.*]] = bitcast %struct.S.12* [[REF_TMP]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP35]], i8* align 4 [[TMP36]], i64 4, i1 false)
|
|
// CHECK2-NEXT: call void @_ZN1SIiED1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[REF_TMP]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: [[TMP37:%.*]] = load i32, i32* [[TMP29]], align 4
|
|
// CHECK2-NEXT: [[TMP38:%.*]] = load i32, i32* [[TMP26]], align 4
|
|
// CHECK2-NEXT: [[CMP:%.*]] = icmp slt i32 [[TMP37]], [[TMP38]]
|
|
// CHECK2-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK2: cond.true:
|
|
// CHECK2-NEXT: [[TMP39:%.*]] = load i32, i32* [[TMP29]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK2: cond.false:
|
|
// CHECK2-NEXT: [[TMP40:%.*]] = load i32, i32* [[TMP26]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END]]
|
|
// CHECK2: cond.end:
|
|
// CHECK2-NEXT: [[COND:%.*]] = phi i32 [ [[TMP39]], [[COND_TRUE]] ], [ [[TMP40]], [[COND_FALSE]] ]
|
|
// CHECK2-NEXT: store i32 [[COND]], i32* [[TMP29]], align 4
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiEanERKS0_
|
|
// CHECK2-SAME: (%struct.S.12* nonnull align 4 dereferenceable(4) [[THIS:%.*]], %struct.S.12* nonnull align 4 dereferenceable(4) [[TMP0:%.*]]) #[[ATTR7]] align 2 {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK2-NEXT: store %struct.S.12* [[THIS]], %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: store %struct.S.12* [[TMP0]], %struct.S.12** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S.12*, %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: ret %struct.S.12* [[THIS1]]
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiEcviEv
|
|
// CHECK2-SAME: (%struct.S.12* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) #[[ATTR7]] align 2 {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK2-NEXT: store %struct.S.12* [[THIS]], %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S.12*, %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: ret i32 0
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiED1Ev
|
|
// CHECK2-SAME: (%struct.S.12* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK2-NEXT: store %struct.S.12* [[THIS]], %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S.12*, %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: call void @_ZN1SIiED2Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[THIS1]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined..27
|
|
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.14* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.14*, align 8
|
|
// CHECK2-NEXT: [[TMP:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK2-NEXT: [[_TMP1:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK2-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[_TMP2:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[T_VAR:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK2-NEXT: [[ATOMIC_TEMP:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[_TMP9:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store %struct.anon.14* [[__CONTEXT]], %struct.anon.14** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load %struct.anon.14*, %struct.anon.14** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_14:%.*]], %struct.anon.14* [[TMP0]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i32*, i32** [[TMP1]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_ANON_14]], %struct.anon.14* [[TMP0]], i32 0, i32 1
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load [2 x i32]*, [2 x i32]** [[TMP3]], align 8
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_ANON_14]], %struct.anon.14* [[TMP0]], i32 0, i32 2
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = load [2 x %struct.S.12]*, [2 x %struct.S.12]** [[TMP5]], align 8
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = getelementptr inbounds [[STRUCT_ANON_14]], %struct.anon.14* [[TMP0]], i32 0, i32 3
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = load %struct.S.12*, %struct.S.12** [[TMP7]], align 8
|
|
// CHECK2-NEXT: store %struct.S.12* [[TMP8]], %struct.S.12** [[TMP]], align 8
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = load %struct.S.12*, %struct.S.12** [[TMP]], align 8
|
|
// CHECK2-NEXT: store %struct.S.12* [[TMP9]], %struct.S.12** [[_TMP1]], align 8
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK2-NEXT: store i32 1, i32* [[T_VAR]], align 4
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = load i32, i32* [[TMP10]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP11]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP12]], 1
|
|
// CHECK2-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK2: cond.true:
|
|
// CHECK2-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK2: cond.false:
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END]]
|
|
// CHECK2: cond.end:
|
|
// CHECK2-NEXT: [[COND:%.*]] = phi i32 [ 1, [[COND_TRUE]] ], [ [[TMP13]], [[COND_FALSE]] ]
|
|
// CHECK2-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP14]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK2: omp.inner.for.cond:
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP3:%.*]] = icmp sle i32 [[TMP15]], [[TMP16]]
|
|
// CHECK2-NEXT: br i1 [[CMP3]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK2: omp.inner.for.body:
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP17]], 1
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = load i32, i32* [[T_VAR]], align 4
|
|
// CHECK2-NEXT: [[TMP19:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK2-NEXT: [[IDXPROM:%.*]] = sext i32 [[TMP19]] to i64
|
|
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[TMP4]], i64 0, i64 [[IDXPROM]]
|
|
// CHECK2-NEXT: store i32 [[TMP18]], i32* [[ARRAYIDX]], align 4
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = load %struct.S.12*, %struct.S.12** [[_TMP1]], align 8
|
|
// CHECK2-NEXT: [[TMP21:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK2-NEXT: [[IDXPROM4:%.*]] = sext i32 [[TMP21]] to i64
|
|
// CHECK2-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds [2 x %struct.S.12], [2 x %struct.S.12]* [[TMP6]], i64 0, i64 [[IDXPROM4]]
|
|
// CHECK2-NEXT: [[TMP22:%.*]] = bitcast %struct.S.12* [[ARRAYIDX5]] to i8*
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = bitcast %struct.S.12* [[TMP20]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP22]], i8* align 4 [[TMP23]], i64 4, i1 false)
|
|
// CHECK2-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK2: omp.body.continue:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK2: omp.inner.for.inc:
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[ADD6:%.*]] = add nsw i32 [[TMP24]], 1
|
|
// CHECK2-NEXT: store i32 [[ADD6]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK2: omp.inner.for.end:
|
|
// CHECK2-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK2: omp.loop.exit:
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP11]])
|
|
// CHECK2-NEXT: [[TMP25:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP26:%.*]] = bitcast i32* [[T_VAR]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP26]], i8** [[TMP25]], align 8
|
|
// CHECK2-NEXT: [[TMP27:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK2-NEXT: [[TMP28:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP11]], i32 1, i64 8, i8* [[TMP27]], void (i8*, i8*)* @.omp.reduction.reduction_func.28, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: switch i32 [[TMP28]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK2-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK2-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK2-NEXT: ]
|
|
// CHECK2: .omp.reduction.case1:
|
|
// CHECK2-NEXT: [[TMP29:%.*]] = load i32, i32* [[TMP2]], align 4
|
|
// CHECK2-NEXT: [[TOBOOL:%.*]] = icmp ne i32 [[TMP29]], 0
|
|
// CHECK2-NEXT: br i1 [[TOBOOL]], label [[LAND_RHS:%.*]], label [[LAND_END:%.*]]
|
|
// CHECK2: land.rhs:
|
|
// CHECK2-NEXT: [[TMP30:%.*]] = load i32, i32* [[T_VAR]], align 4
|
|
// CHECK2-NEXT: [[TOBOOL7:%.*]] = icmp ne i32 [[TMP30]], 0
|
|
// CHECK2-NEXT: br label [[LAND_END]]
|
|
// CHECK2: land.end:
|
|
// CHECK2-NEXT: [[TMP31:%.*]] = phi i1 [ false, [[DOTOMP_REDUCTION_CASE1]] ], [ [[TOBOOL7]], [[LAND_RHS]] ]
|
|
// CHECK2-NEXT: [[CONV:%.*]] = zext i1 [[TMP31]] to i32
|
|
// CHECK2-NEXT: store i32 [[CONV]], i32* [[TMP2]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP11]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.case2:
|
|
// CHECK2-NEXT: [[TMP32:%.*]] = load i32, i32* [[T_VAR]], align 4
|
|
// CHECK2-NEXT: [[TOBOOL8:%.*]] = icmp ne i32 [[TMP32]], 0
|
|
// CHECK2-NEXT: [[ATOMIC_LOAD:%.*]] = load atomic i32, i32* [[TMP2]] monotonic, align 4
|
|
// CHECK2-NEXT: br label [[ATOMIC_CONT:%.*]]
|
|
// CHECK2: atomic_cont:
|
|
// CHECK2-NEXT: [[TMP33:%.*]] = phi i32 [ [[ATOMIC_LOAD]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[TMP39:%.*]], [[LAND_END13:%.*]] ]
|
|
// CHECK2-NEXT: store i32 [[TMP33]], i32* [[_TMP9]], align 4
|
|
// CHECK2-NEXT: [[TMP34:%.*]] = load i32, i32* [[_TMP9]], align 4
|
|
// CHECK2-NEXT: [[TOBOOL10:%.*]] = icmp ne i32 [[TMP34]], 0
|
|
// CHECK2-NEXT: br i1 [[TOBOOL10]], label [[LAND_RHS11:%.*]], label [[LAND_END13]]
|
|
// CHECK2: land.rhs11:
|
|
// CHECK2-NEXT: [[TMP35:%.*]] = load i32, i32* [[T_VAR]], align 4
|
|
// CHECK2-NEXT: [[TOBOOL12:%.*]] = icmp ne i32 [[TMP35]], 0
|
|
// CHECK2-NEXT: br label [[LAND_END13]]
|
|
// CHECK2: land.end13:
|
|
// CHECK2-NEXT: [[TMP36:%.*]] = phi i1 [ false, [[ATOMIC_CONT]] ], [ [[TOBOOL12]], [[LAND_RHS11]] ]
|
|
// CHECK2-NEXT: [[CONV14:%.*]] = zext i1 [[TMP36]] to i32
|
|
// CHECK2-NEXT: store i32 [[CONV14]], i32* [[ATOMIC_TEMP]], align 4
|
|
// CHECK2-NEXT: [[TMP37:%.*]] = load i32, i32* [[ATOMIC_TEMP]], align 4
|
|
// CHECK2-NEXT: [[TMP38:%.*]] = cmpxchg i32* [[TMP2]], i32 [[TMP33]], i32 [[TMP37]] monotonic monotonic, align 4
|
|
// CHECK2-NEXT: [[TMP39]] = extractvalue { i32, i1 } [[TMP38]], 0
|
|
// CHECK2-NEXT: [[TMP40:%.*]] = extractvalue { i32, i1 } [[TMP38]], 1
|
|
// CHECK2-NEXT: br i1 [[TMP40]], label [[ATOMIC_EXIT:%.*]], label [[ATOMIC_CONT]]
|
|
// CHECK2: atomic_exit:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP11]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.default:
|
|
// CHECK2-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4]], i32 [[TMP11]])
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.28
|
|
// CHECK2-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to i32*
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i32*
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = load i32, i32* [[TMP11]], align 4
|
|
// CHECK2-NEXT: [[TOBOOL:%.*]] = icmp ne i32 [[TMP12]], 0
|
|
// CHECK2-NEXT: br i1 [[TOBOOL]], label [[LAND_RHS:%.*]], label [[LAND_END:%.*]]
|
|
// CHECK2: land.rhs:
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = load i32, i32* [[TMP8]], align 4
|
|
// CHECK2-NEXT: [[TOBOOL2:%.*]] = icmp ne i32 [[TMP13]], 0
|
|
// CHECK2-NEXT: br label [[LAND_END]]
|
|
// CHECK2: land.end:
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = phi i1 [ false, [[ENTRY:%.*]] ], [ [[TOBOOL2]], [[LAND_RHS]] ]
|
|
// CHECK2-NEXT: [[CONV:%.*]] = zext i1 [[TMP14]] to i32
|
|
// CHECK2-NEXT: store i32 [[CONV]], i32* [[TMP11]], align 4
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined..29
|
|
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon.15* noalias [[__CONTEXT:%.*]]) #[[ATTR4]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon.15*, align 8
|
|
// CHECK2-NEXT: [[TMP:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK2-NEXT: [[_TMP1:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK2-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[_TMP2:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[ARR:%.*]] = alloca [40 x %struct.S.12], align 16
|
|
// CHECK2-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK2-NEXT: [[REF_TMP:%.*]] = alloca [[STRUCT_S_12:%.*]], align 4
|
|
// CHECK2-NEXT: [[REF_TMP19:%.*]] = alloca [[STRUCT_S_12]], align 4
|
|
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store %struct.anon.15* [[__CONTEXT]], %struct.anon.15** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load %struct.anon.15*, %struct.anon.15** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_15:%.*]], %struct.anon.15* [[TMP0]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load [42 x %struct.S.12]*, [42 x %struct.S.12]** [[TMP1]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_ANON_15]], %struct.anon.15* [[TMP0]], i32 0, i32 1
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load [2 x i32]*, [2 x i32]** [[TMP3]], align 8
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_ANON_15]], %struct.anon.15* [[TMP0]], i32 0, i32 2
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = load i32*, i32** [[TMP5]], align 8
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = getelementptr inbounds [[STRUCT_ANON_15]], %struct.anon.15* [[TMP0]], i32 0, i32 3
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = load [2 x %struct.S.12]*, [2 x %struct.S.12]** [[TMP7]], align 8
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_ANON_15]], %struct.anon.15* [[TMP0]], i32 0, i32 4
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load %struct.S.12*, %struct.S.12** [[TMP9]], align 8
|
|
// CHECK2-NEXT: store %struct.S.12* [[TMP10]], %struct.S.12** [[TMP]], align 8
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = load %struct.S.12*, %struct.S.12** [[TMP]], align 8
|
|
// CHECK2-NEXT: store %struct.S.12* [[TMP11]], %struct.S.12** [[_TMP1]], align 8
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [42 x %struct.S.12], [42 x %struct.S.12]* [[TMP2]], i64 0, i64 1
|
|
// CHECK2-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds [42 x %struct.S.12], [42 x %struct.S.12]* [[TMP2]], i64 0, i64 40
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [40 x %struct.S.12], [40 x %struct.S.12]* [[ARR]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = getelementptr [[STRUCT_S_12]], %struct.S.12* [[ARRAY_BEGIN]], i64 40
|
|
// CHECK2-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq %struct.S.12* [[ARRAY_BEGIN]], [[TMP12]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
|
|
// CHECK2: omp.arrayinit.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S.12* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
|
|
// CHECK2-NEXT: call void @_ZN1SIiEC1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]])
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S_12]], %struct.S.12* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S.12* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP12]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK2: omp.arrayinit.done:
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = bitcast [42 x %struct.S.12]* [[TMP2]] to %struct.S.12*
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = ptrtoint %struct.S.12* [[TMP13]] to i64
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = ptrtoint %struct.S.12* [[ARRAYIDX]] to i64
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = sub i64 [[TMP14]], [[TMP15]]
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = sdiv exact i64 [[TMP16]], ptrtoint (i32* getelementptr (i32, i32* null, i32 1) to i64)
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = bitcast [40 x %struct.S.12]* [[ARR]] to %struct.S.12*
|
|
// CHECK2-NEXT: [[TMP19:%.*]] = getelementptr [[STRUCT_S_12]], %struct.S.12* [[TMP18]], i64 [[TMP17]]
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = bitcast %struct.S.12* [[TMP19]] to [42 x %struct.S.12]*
|
|
// CHECK2-NEXT: [[RHS_BEGIN:%.*]] = bitcast [40 x %struct.S.12]* [[ARR]] to %struct.S.12*
|
|
// CHECK2-NEXT: [[TMP21:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP22:%.*]] = load i32, i32* [[TMP21]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP22]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP23]], 1
|
|
// CHECK2-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK2: cond.true:
|
|
// CHECK2-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK2: cond.false:
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END]]
|
|
// CHECK2: cond.end:
|
|
// CHECK2-NEXT: [[COND:%.*]] = phi i32 [ 1, [[COND_TRUE]] ], [ [[TMP24]], [[COND_FALSE]] ]
|
|
// CHECK2-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP25:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP25]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK2: omp.inner.for.cond:
|
|
// CHECK2-NEXT: [[TMP26:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[TMP27:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP4:%.*]] = icmp sle i32 [[TMP26]], [[TMP27]]
|
|
// CHECK2-NEXT: br i1 [[CMP4]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
|
|
// CHECK2: omp.inner.for.cond.cleanup:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK2: omp.inner.for.body:
|
|
// CHECK2-NEXT: [[TMP28:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP28]], 1
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK2-NEXT: [[TMP29:%.*]] = load i32, i32* [[TMP6]], align 4
|
|
// CHECK2-NEXT: [[TMP30:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK2-NEXT: [[IDXPROM:%.*]] = sext i32 [[TMP30]] to i64
|
|
// CHECK2-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[TMP4]], i64 0, i64 [[IDXPROM]]
|
|
// CHECK2-NEXT: store i32 [[TMP29]], i32* [[ARRAYIDX5]], align 4
|
|
// CHECK2-NEXT: [[TMP31:%.*]] = load %struct.S.12*, %struct.S.12** [[_TMP1]], align 8
|
|
// CHECK2-NEXT: [[TMP32:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK2-NEXT: [[IDXPROM6:%.*]] = sext i32 [[TMP32]] to i64
|
|
// CHECK2-NEXT: [[ARRAYIDX7:%.*]] = getelementptr inbounds [2 x %struct.S.12], [2 x %struct.S.12]* [[TMP8]], i64 0, i64 [[IDXPROM6]]
|
|
// CHECK2-NEXT: [[TMP33:%.*]] = bitcast %struct.S.12* [[ARRAYIDX7]] to i8*
|
|
// CHECK2-NEXT: [[TMP34:%.*]] = bitcast %struct.S.12* [[TMP31]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP33]], i8* align 4 [[TMP34]], i64 4, i1 false)
|
|
// CHECK2-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK2: omp.body.continue:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK2: omp.inner.for.inc:
|
|
// CHECK2-NEXT: [[TMP35:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[ADD8:%.*]] = add nsw i32 [[TMP35]], 1
|
|
// CHECK2-NEXT: store i32 [[ADD8]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK2: omp.inner.for.end:
|
|
// CHECK2-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK2: omp.loop.exit:
|
|
// CHECK2-NEXT: [[TMP36:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP37:%.*]] = load i32, i32* [[TMP36]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP37]])
|
|
// CHECK2-NEXT: [[TMP38:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP39:%.*]] = bitcast %struct.S.12* [[RHS_BEGIN]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP39]], i8** [[TMP38]], align 8
|
|
// CHECK2-NEXT: [[TMP40:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP41:%.*]] = load i32, i32* [[TMP40]], align 4
|
|
// CHECK2-NEXT: [[TMP42:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK2-NEXT: [[TMP43:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP41]], i32 1, i64 8, i8* [[TMP42]], void (i8*, i8*)* @.omp.reduction.reduction_func.30, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: switch i32 [[TMP43]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK2-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK2-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK2-NEXT: ]
|
|
// CHECK2: .omp.reduction.case1:
|
|
// CHECK2-NEXT: [[TMP44:%.*]] = getelementptr [[STRUCT_S_12]], %struct.S.12* [[ARRAYIDX]], i64 40
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S.12* [[ARRAYIDX]], [[TMP44]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE14:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK2: omp.arraycpy.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S.12* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST9:%.*]] = phi %struct.S.12* [ [[ARRAYIDX]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT12:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call i32 @_ZN1SIiEcviEv(%struct.S.12* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST9]])
|
|
// CHECK2-NEXT: [[CALL10:%.*]] = call i32 @_ZN1SIiEcviEv(%struct.S.12* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK2-NEXT: [[ADD11:%.*]] = add nsw i32 [[CALL]], [[CALL10]]
|
|
// CHECK2-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.12* nonnull align 4 dereferenceable(4) [[REF_TMP]], i32 [[ADD11]])
|
|
// CHECK2-NEXT: [[TMP45:%.*]] = bitcast %struct.S.12* [[OMP_ARRAYCPY_DESTELEMENTPAST9]] to i8*
|
|
// CHECK2-NEXT: [[TMP46:%.*]] = bitcast %struct.S.12* [[REF_TMP]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP45]], i8* align 4 [[TMP46]], i64 4, i1 false)
|
|
// CHECK2-NEXT: call void @_ZN1SIiED1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[REF_TMP]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT12]] = getelementptr [[STRUCT_S_12]], %struct.S.12* [[OMP_ARRAYCPY_DESTELEMENTPAST9]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S_12]], %struct.S.12* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE13:%.*]] = icmp eq %struct.S.12* [[OMP_ARRAYCPY_DEST_ELEMENT12]], [[TMP44]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE13]], label [[OMP_ARRAYCPY_DONE14]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done14:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP41]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.case2:
|
|
// CHECK2-NEXT: [[TMP47:%.*]] = getelementptr [[STRUCT_S_12]], %struct.S.12* [[ARRAYIDX]], i64 40
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY15:%.*]] = icmp eq %struct.S.12* [[ARRAYIDX]], [[TMP47]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY15]], label [[OMP_ARRAYCPY_DONE26:%.*]], label [[OMP_ARRAYCPY_BODY16:%.*]]
|
|
// CHECK2: omp.arraycpy.body16:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST17:%.*]] = phi %struct.S.12* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT24:%.*]], [[OMP_ARRAYCPY_BODY16]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST18:%.*]] = phi %struct.S.12* [ [[ARRAYIDX]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT23:%.*]], [[OMP_ARRAYCPY_BODY16]] ]
|
|
// CHECK2-NEXT: [[TMP48:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP49:%.*]] = load i32, i32* [[TMP48]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP49]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[CALL20:%.*]] = call i32 @_ZN1SIiEcviEv(%struct.S.12* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST18]])
|
|
// CHECK2-NEXT: [[CALL21:%.*]] = call i32 @_ZN1SIiEcviEv(%struct.S.12* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST17]])
|
|
// CHECK2-NEXT: [[ADD22:%.*]] = add nsw i32 [[CALL20]], [[CALL21]]
|
|
// CHECK2-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.12* nonnull align 4 dereferenceable(4) [[REF_TMP19]], i32 [[ADD22]])
|
|
// CHECK2-NEXT: [[TMP50:%.*]] = bitcast %struct.S.12* [[OMP_ARRAYCPY_DESTELEMENTPAST18]] to i8*
|
|
// CHECK2-NEXT: [[TMP51:%.*]] = bitcast %struct.S.12* [[REF_TMP19]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP50]], i8* align 4 [[TMP51]], i64 4, i1 false)
|
|
// CHECK2-NEXT: call void @_ZN1SIiED1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[REF_TMP19]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP49]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT23]] = getelementptr [[STRUCT_S_12]], %struct.S.12* [[OMP_ARRAYCPY_DESTELEMENTPAST18]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT24]] = getelementptr [[STRUCT_S_12]], %struct.S.12* [[OMP_ARRAYCPY_SRCELEMENTPAST17]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE25:%.*]] = icmp eq %struct.S.12* [[OMP_ARRAYCPY_DEST_ELEMENT23]], [[TMP47]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE25]], label [[OMP_ARRAYCPY_DONE26]], label [[OMP_ARRAYCPY_BODY16]]
|
|
// CHECK2: omp.arraycpy.done26:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP41]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.default:
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN27:%.*]] = getelementptr inbounds [40 x %struct.S.12], [40 x %struct.S.12]* [[ARR]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP52:%.*]] = getelementptr inbounds [[STRUCT_S_12]], %struct.S.12* [[ARRAY_BEGIN27]], i64 40
|
|
// CHECK2-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
|
|
// CHECK2: arraydestroy.body:
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S.12* [ [[TMP52]], [[DOTOMP_REDUCTION_DEFAULT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S_12]], %struct.S.12* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
|
|
// CHECK2-NEXT: call void @_ZN1SIiED1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S.12* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN27]]
|
|
// CHECK2-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE28:%.*]], label [[ARRAYDESTROY_BODY]]
|
|
// CHECK2: arraydestroy.done28:
|
|
// CHECK2-NEXT: [[TMP53:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP54:%.*]] = load i32, i32* [[TMP53]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4]], i32 [[TMP54]])
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.30
|
|
// CHECK2-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR6]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK2-NEXT: [[REF_TMP:%.*]] = alloca [[STRUCT_S_12:%.*]], align 4
|
|
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.S.12*
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to %struct.S.12*
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = getelementptr [[STRUCT_S_12]], %struct.S.12* [[TMP11]], i64 40
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S.12* [[TMP11]], [[TMP12]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE3:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK2: omp.arraycpy.body:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S.12* [ [[TMP8]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S.12* [ [[TMP11]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call i32 @_ZN1SIiEcviEv(%struct.S.12* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]])
|
|
// CHECK2-NEXT: [[CALL2:%.*]] = call i32 @_ZN1SIiEcviEv(%struct.S.12* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]])
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 [[CALL]], [[CALL2]]
|
|
// CHECK2-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.12* nonnull align 4 dereferenceable(4) [[REF_TMP]], i32 [[ADD]])
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = bitcast %struct.S.12* [[OMP_ARRAYCPY_DESTELEMENTPAST]] to i8*
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = bitcast %struct.S.12* [[REF_TMP]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP13]], i8* align 4 [[TMP14]], i64 4, i1 false)
|
|
// CHECK2-NEXT: call void @_ZN1SIiED1Ev(%struct.S.12* nonnull align 4 dereferenceable(4) [[REF_TMP]]) #[[ATTR5]]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S_12]], %struct.S.12* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S_12]], %struct.S.12* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S.12* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP12]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE3]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done3:
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiEC2Ev
|
|
// CHECK2-SAME: (%struct.S.12* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK2-NEXT: store %struct.S.12* [[THIS]], %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S.12*, %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S_12:%.*]], %struct.S.12* [[THIS1]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load volatile double, double* @g, align 8
|
|
// CHECK2-NEXT: [[CONV:%.*]] = fptosi double [[TMP0]] to i32
|
|
// CHECK2-NEXT: store i32 [[CONV]], i32* [[F]], align 4
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiEC2Ei
|
|
// CHECK2-SAME: (%struct.S.12* nonnull align 4 dereferenceable(4) [[THIS:%.*]], i32 [[A:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: store %struct.S.12* [[THIS]], %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: store i32 [[A]], i32* [[A_ADDR]], align 4
|
|
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S.12*, %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S_12:%.*]], %struct.S.12* [[THIS1]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load i32, i32* [[A_ADDR]], align 4
|
|
// CHECK2-NEXT: [[CONV:%.*]] = sitofp i32 [[TMP0]] to double
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = load volatile double, double* @g, align 8
|
|
// CHECK2-NEXT: [[ADD:%.*]] = fadd double [[CONV]], [[TMP1]]
|
|
// CHECK2-NEXT: [[CONV2:%.*]] = fptosi double [[ADD]] to i32
|
|
// CHECK2-NEXT: store i32 [[CONV2]], i32* [[F]], align 4
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiED2Ev
|
|
// CHECK2-SAME: (%struct.S.12* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.12*, align 8
|
|
// CHECK2-NEXT: store %struct.S.12* [[THIS]], %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S.12*, %struct.S.12** [[THIS_ADDR]], align 8
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK3-LABEL: define {{[^@]+}}@main
|
|
// CHECK3-SAME: () #[[ATTR0:[0-9]+]] {
|
|
// CHECK3-NEXT: entry:
|
|
// CHECK3-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
|
|
// CHECK3-NEXT: [[REF_TMP:%.*]] = alloca [[CLASS_ANON:%.*]], align 1
|
|
// CHECK3-NEXT: store i32 0, i32* [[RETVAL]], align 4
|
|
// CHECK3-NEXT: call void @"_ZZ4mainENK3$_0clEv"(%class.anon* nonnull align 1 dereferenceable(1) [[REF_TMP]])
|
|
// CHECK3-NEXT: ret i32 0
|
|
//
|
|
//
|
|
// CHECK3-LABEL: define {{[^@]+}}@.omp_outlined.
|
|
// CHECK3-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon* noalias [[__CONTEXT:%.*]]) #[[ATTR2:[0-9]+]] {
|
|
// CHECK3-NEXT: entry:
|
|
// CHECK3-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK3-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK3-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon*, align 8
|
|
// CHECK3-NEXT: [[TMP:%.*]] = alloca double*, align 8
|
|
// CHECK3-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK3-NEXT: [[_TMP1:%.*]] = alloca i32, align 4
|
|
// CHECK3-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK3-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK3-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK3-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK3-NEXT: [[G:%.*]] = alloca double, align 8
|
|
// CHECK3-NEXT: [[G1:%.*]] = alloca double, align 8
|
|
// CHECK3-NEXT: [[_TMP2:%.*]] = alloca double*, align 8
|
|
// CHECK3-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK3-NEXT: [[REF_TMP:%.*]] = alloca [[CLASS_ANON_0:%.*]], align 8
|
|
// CHECK3-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [2 x i8*], align 8
|
|
// CHECK3-NEXT: [[ATOMIC_TEMP:%.*]] = alloca double, align 8
|
|
// CHECK3-NEXT: [[_TMP7:%.*]] = alloca double, align 8
|
|
// CHECK3-NEXT: [[ATOMIC_TEMP11:%.*]] = alloca double, align 8
|
|
// CHECK3-NEXT: [[_TMP12:%.*]] = alloca double, align 8
|
|
// CHECK3-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK3-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK3-NEXT: store %struct.anon* [[__CONTEXT]], %struct.anon** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK3-NEXT: [[TMP0:%.*]] = load %struct.anon*, %struct.anon** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK3-NEXT: [[TMP1:%.*]] = load double*, double** @g1, align 8
|
|
// CHECK3-NEXT: store double* [[TMP1]], double** [[TMP]], align 8
|
|
// CHECK3-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK3-NEXT: store i32 1, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK3-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK3-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK3-NEXT: store double 0.000000e+00, double* [[G]], align 8
|
|
// CHECK3-NEXT: [[TMP2:%.*]] = load double*, double** @g1, align 8
|
|
// CHECK3-NEXT: store double 0.000000e+00, double* [[G1]], align 8
|
|
// CHECK3-NEXT: store double* [[G1]], double** [[_TMP2]], align 8
|
|
// CHECK3-NEXT: [[TMP3:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK3-NEXT: [[TMP4:%.*]] = load i32, i32* [[TMP3]], align 4
|
|
// CHECK3-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 [[TMP4]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK3-NEXT: [[TMP5:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK3-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP5]], 1
|
|
// CHECK3-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK3: cond.true:
|
|
// CHECK3-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK3: cond.false:
|
|
// CHECK3-NEXT: [[TMP6:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK3-NEXT: br label [[COND_END]]
|
|
// CHECK3: cond.end:
|
|
// CHECK3-NEXT: [[COND:%.*]] = phi i32 [ 1, [[COND_TRUE]] ], [ [[TMP6]], [[COND_FALSE]] ]
|
|
// CHECK3-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK3-NEXT: [[TMP7:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK3-NEXT: store i32 [[TMP7]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK3-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK3: omp.inner.for.cond:
|
|
// CHECK3-NEXT: [[TMP8:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK3-NEXT: [[TMP9:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK3-NEXT: [[CMP3:%.*]] = icmp sle i32 [[TMP8]], [[TMP9]]
|
|
// CHECK3-NEXT: br i1 [[CMP3]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK3: omp.inner.for.body:
|
|
// CHECK3-NEXT: [[TMP10:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK3-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP10]], 1
|
|
// CHECK3-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK3-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK3-NEXT: store double 1.000000e+00, double* [[G]], align 8
|
|
// CHECK3-NEXT: [[TMP11:%.*]] = load double*, double** [[_TMP2]], align 8
|
|
// CHECK3-NEXT: store volatile double 1.000000e+00, double* [[TMP11]], align 8
|
|
// CHECK3-NEXT: [[TMP12:%.*]] = getelementptr inbounds [[CLASS_ANON_0]], %class.anon.0* [[REF_TMP]], i32 0, i32 0
|
|
// CHECK3-NEXT: store double* [[G]], double** [[TMP12]], align 8
|
|
// CHECK3-NEXT: [[TMP13:%.*]] = getelementptr inbounds [[CLASS_ANON_0]], %class.anon.0* [[REF_TMP]], i32 0, i32 1
|
|
// CHECK3-NEXT: [[TMP14:%.*]] = load double*, double** [[_TMP2]], align 8
|
|
// CHECK3-NEXT: store double* [[TMP14]], double** [[TMP13]], align 8
|
|
// CHECK3-NEXT: call void @"_ZZZ4mainENK3$_0clEvENKUlvE_clEv"(%class.anon.0* nonnull align 8 dereferenceable(16) [[REF_TMP]])
|
|
// CHECK3-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK3: omp.body.continue:
|
|
// CHECK3-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK3: omp.inner.for.inc:
|
|
// CHECK3-NEXT: [[TMP15:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK3-NEXT: [[ADD4:%.*]] = add nsw i32 [[TMP15]], 1
|
|
// CHECK3-NEXT: store i32 [[ADD4]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK3-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK3: omp.inner.for.end:
|
|
// CHECK3-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK3: omp.loop.exit:
|
|
// CHECK3-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP4]])
|
|
// CHECK3-NEXT: [[TMP16:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK3-NEXT: [[TMP17:%.*]] = bitcast double* [[G]] to i8*
|
|
// CHECK3-NEXT: store i8* [[TMP17]], i8** [[TMP16]], align 8
|
|
// CHECK3-NEXT: [[TMP18:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 1
|
|
// CHECK3-NEXT: [[TMP19:%.*]] = bitcast double* [[G1]] to i8*
|
|
// CHECK3-NEXT: store i8* [[TMP19]], i8** [[TMP18]], align 8
|
|
// CHECK3-NEXT: [[TMP20:%.*]] = bitcast [2 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK3-NEXT: [[TMP21:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2:[0-9]+]], i32 [[TMP4]], i32 2, i64 16, i8* [[TMP20]], void (i8*, i8*)* @.omp.reduction.reduction_func, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK3-NEXT: switch i32 [[TMP21]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK3-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK3-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK3-NEXT: ]
|
|
// CHECK3: .omp.reduction.case1:
|
|
// CHECK3-NEXT: [[TMP22:%.*]] = load double, double* @g, align 8
|
|
// CHECK3-NEXT: [[TMP23:%.*]] = load double, double* [[G]], align 8
|
|
// CHECK3-NEXT: [[ADD5:%.*]] = fadd double [[TMP22]], [[TMP23]]
|
|
// CHECK3-NEXT: store double [[ADD5]], double* @g, align 8
|
|
// CHECK3-NEXT: [[TMP24:%.*]] = load double, double* [[TMP2]], align 8
|
|
// CHECK3-NEXT: [[TMP25:%.*]] = load double, double* [[G1]], align 8
|
|
// CHECK3-NEXT: [[ADD6:%.*]] = fadd double [[TMP24]], [[TMP25]]
|
|
// CHECK3-NEXT: store double [[ADD6]], double* [[TMP2]], align 8
|
|
// CHECK3-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP4]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK3-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK3: .omp.reduction.case2:
|
|
// CHECK3-NEXT: [[TMP26:%.*]] = load double, double* [[G]], align 8
|
|
// CHECK3-NEXT: [[ATOMIC_LOAD:%.*]] = load atomic i64, i64* bitcast (double* @g to i64*) monotonic, align 8
|
|
// CHECK3-NEXT: br label [[ATOMIC_CONT:%.*]]
|
|
// CHECK3: atomic_cont:
|
|
// CHECK3-NEXT: [[TMP27:%.*]] = phi i64 [ [[ATOMIC_LOAD]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[TMP34:%.*]], [[ATOMIC_CONT]] ]
|
|
// CHECK3-NEXT: [[TMP28:%.*]] = bitcast double* [[ATOMIC_TEMP]] to i64*
|
|
// CHECK3-NEXT: [[TMP29:%.*]] = bitcast i64 [[TMP27]] to double
|
|
// CHECK3-NEXT: store double [[TMP29]], double* [[_TMP7]], align 8
|
|
// CHECK3-NEXT: [[TMP30:%.*]] = load double, double* [[_TMP7]], align 8
|
|
// CHECK3-NEXT: [[TMP31:%.*]] = load double, double* [[G]], align 8
|
|
// CHECK3-NEXT: [[ADD8:%.*]] = fadd double [[TMP30]], [[TMP31]]
|
|
// CHECK3-NEXT: store double [[ADD8]], double* [[ATOMIC_TEMP]], align 8
|
|
// CHECK3-NEXT: [[TMP32:%.*]] = load i64, i64* [[TMP28]], align 8
|
|
// CHECK3-NEXT: [[TMP33:%.*]] = cmpxchg i64* bitcast (double* @g to i64*), i64 [[TMP27]], i64 [[TMP32]] monotonic monotonic, align 8
|
|
// CHECK3-NEXT: [[TMP34]] = extractvalue { i64, i1 } [[TMP33]], 0
|
|
// CHECK3-NEXT: [[TMP35:%.*]] = extractvalue { i64, i1 } [[TMP33]], 1
|
|
// CHECK3-NEXT: br i1 [[TMP35]], label [[ATOMIC_EXIT:%.*]], label [[ATOMIC_CONT]]
|
|
// CHECK3: atomic_exit:
|
|
// CHECK3-NEXT: [[TMP36:%.*]] = load double, double* [[G1]], align 8
|
|
// CHECK3-NEXT: [[TMP37:%.*]] = bitcast double* [[TMP2]] to i64*
|
|
// CHECK3-NEXT: [[ATOMIC_LOAD9:%.*]] = load atomic i64, i64* [[TMP37]] monotonic, align 8
|
|
// CHECK3-NEXT: br label [[ATOMIC_CONT10:%.*]]
|
|
// CHECK3: atomic_cont10:
|
|
// CHECK3-NEXT: [[TMP38:%.*]] = phi i64 [ [[ATOMIC_LOAD9]], [[ATOMIC_EXIT]] ], [ [[TMP46:%.*]], [[ATOMIC_CONT10]] ]
|
|
// CHECK3-NEXT: [[TMP39:%.*]] = bitcast double* [[ATOMIC_TEMP11]] to i64*
|
|
// CHECK3-NEXT: [[TMP40:%.*]] = bitcast i64 [[TMP38]] to double
|
|
// CHECK3-NEXT: store double [[TMP40]], double* [[_TMP12]], align 8
|
|
// CHECK3-NEXT: [[TMP41:%.*]] = load double, double* [[_TMP12]], align 8
|
|
// CHECK3-NEXT: [[TMP42:%.*]] = load double, double* [[G1]], align 8
|
|
// CHECK3-NEXT: [[ADD13:%.*]] = fadd double [[TMP41]], [[TMP42]]
|
|
// CHECK3-NEXT: store double [[ADD13]], double* [[ATOMIC_TEMP11]], align 8
|
|
// CHECK3-NEXT: [[TMP43:%.*]] = load i64, i64* [[TMP39]], align 8
|
|
// CHECK3-NEXT: [[TMP44:%.*]] = bitcast double* [[TMP2]] to i64*
|
|
// CHECK3-NEXT: [[TMP45:%.*]] = cmpxchg i64* [[TMP44]], i64 [[TMP38]], i64 [[TMP43]] monotonic monotonic, align 8
|
|
// CHECK3-NEXT: [[TMP46]] = extractvalue { i64, i1 } [[TMP45]], 0
|
|
// CHECK3-NEXT: [[TMP47:%.*]] = extractvalue { i64, i1 } [[TMP45]], 1
|
|
// CHECK3-NEXT: br i1 [[TMP47]], label [[ATOMIC_EXIT14:%.*]], label [[ATOMIC_CONT10]]
|
|
// CHECK3: atomic_exit14:
|
|
// CHECK3-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP4]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK3-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK3: .omp.reduction.default:
|
|
// CHECK3-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB3:[0-9]+]], i32 [[TMP4]])
|
|
// CHECK3-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK3-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func
|
|
// CHECK3-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR4:[0-9]+]] {
|
|
// CHECK3-NEXT: entry:
|
|
// CHECK3-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK3-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK3-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK3-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK3-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK3-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [2 x i8*]*
|
|
// CHECK3-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK3-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [2 x i8*]*
|
|
// CHECK3-NEXT: [[TMP6:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK3-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK3-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to double*
|
|
// CHECK3-NEXT: [[TMP9:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK3-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK3-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to double*
|
|
// CHECK3-NEXT: [[TMP12:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[TMP5]], i64 0, i64 1
|
|
// CHECK3-NEXT: [[TMP13:%.*]] = load i8*, i8** [[TMP12]], align 8
|
|
// CHECK3-NEXT: [[TMP14:%.*]] = bitcast i8* [[TMP13]] to double*
|
|
// CHECK3-NEXT: [[TMP15:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[TMP3]], i64 0, i64 1
|
|
// CHECK3-NEXT: [[TMP16:%.*]] = load i8*, i8** [[TMP15]], align 8
|
|
// CHECK3-NEXT: [[TMP17:%.*]] = bitcast i8* [[TMP16]] to double*
|
|
// CHECK3-NEXT: [[TMP18:%.*]] = load double, double* [[TMP11]], align 8
|
|
// CHECK3-NEXT: [[TMP19:%.*]] = load double, double* [[TMP8]], align 8
|
|
// CHECK3-NEXT: [[ADD:%.*]] = fadd double [[TMP18]], [[TMP19]]
|
|
// CHECK3-NEXT: store double [[ADD]], double* [[TMP11]], align 8
|
|
// CHECK3-NEXT: [[TMP20:%.*]] = load double, double* [[TMP17]], align 8
|
|
// CHECK3-NEXT: [[TMP21:%.*]] = load double, double* [[TMP14]], align 8
|
|
// CHECK3-NEXT: [[ADD2:%.*]] = fadd double [[TMP20]], [[TMP21]]
|
|
// CHECK3-NEXT: store double [[ADD2]], double* [[TMP17]], align 8
|
|
// CHECK3-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK4-LABEL: define {{[^@]+}}@main
|
|
// CHECK4-SAME: () #[[ATTR1:[0-9]+]] {
|
|
// CHECK4-NEXT: entry:
|
|
// CHECK4-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
|
|
// CHECK4-NEXT: store i32 0, i32* [[RETVAL]], align 4
|
|
// CHECK4-NEXT: [[TMP0:%.*]] = load i8*, i8** getelementptr inbounds ([[STRUCT___BLOCK_LITERAL_GENERIC:%.*]], %struct.__block_literal_generic* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor* }* @__block_literal_global to %struct.__block_literal_generic*), i32 0, i32 3), align 8
|
|
// CHECK4-NEXT: [[TMP1:%.*]] = bitcast i8* [[TMP0]] to void (i8*)*
|
|
// CHECK4-NEXT: call void [[TMP1]](i8* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor* }* @__block_literal_global to i8*))
|
|
// CHECK4-NEXT: ret i32 0
|
|
//
|
|
//
|
|
// CHECK4-LABEL: define {{[^@]+}}@__main_block_invoke
|
|
// CHECK4-SAME: (i8* [[DOTBLOCK_DESCRIPTOR:%.*]]) #[[ATTR2:[0-9]+]] {
|
|
// CHECK4-NEXT: entry:
|
|
// CHECK4-NEXT: [[DOTBLOCK_DESCRIPTOR_ADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK4-NEXT: [[BLOCK_ADDR:%.*]] = alloca <{ i8*, i32, i32, i8*, %struct.__block_descriptor* }>*, align 8
|
|
// CHECK4-NEXT: [[OMP_OUTLINED_ARG_AGG_:%.*]] = alloca [[STRUCT_ANON:%.*]], align 1
|
|
// CHECK4-NEXT: store i8* [[DOTBLOCK_DESCRIPTOR]], i8** [[DOTBLOCK_DESCRIPTOR_ADDR]], align 8
|
|
// CHECK4-NEXT: [[BLOCK:%.*]] = bitcast i8* [[DOTBLOCK_DESCRIPTOR]] to <{ i8*, i32, i32, i8*, %struct.__block_descriptor* }>*
|
|
// CHECK4-NEXT: store <{ i8*, i32, i32, i8*, %struct.__block_descriptor* }>* [[BLOCK]], <{ i8*, i32, i32, i8*, %struct.__block_descriptor* }>** [[BLOCK_ADDR]], align 8
|
|
// CHECK4-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB4:[0-9]+]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.anon*)* @.omp_outlined. to void (i32*, i32*, ...)*), %struct.anon* [[OMP_OUTLINED_ARG_AGG_]])
|
|
// CHECK4-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK4-LABEL: define {{[^@]+}}@.omp_outlined.
|
|
// CHECK4-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.anon* noalias [[__CONTEXT:%.*]]) #[[ATTR3:[0-9]+]] {
|
|
// CHECK4-NEXT: entry:
|
|
// CHECK4-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK4-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK4-NEXT: [[__CONTEXT_ADDR:%.*]] = alloca %struct.anon*, align 8
|
|
// CHECK4-NEXT: [[TMP:%.*]] = alloca double*, align 8
|
|
// CHECK4-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK4-NEXT: [[_TMP1:%.*]] = alloca i32, align 4
|
|
// CHECK4-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK4-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK4-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK4-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK4-NEXT: [[G:%.*]] = alloca double, align 8
|
|
// CHECK4-NEXT: [[G1:%.*]] = alloca double, align 8
|
|
// CHECK4-NEXT: [[_TMP2:%.*]] = alloca double*, align 8
|
|
// CHECK4-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK4-NEXT: [[BLOCK:%.*]] = alloca <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double, double* }>, align 8
|
|
// CHECK4-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [2 x i8*], align 8
|
|
// CHECK4-NEXT: [[ATOMIC_TEMP:%.*]] = alloca double, align 8
|
|
// CHECK4-NEXT: [[_TMP8:%.*]] = alloca double, align 8
|
|
// CHECK4-NEXT: [[ATOMIC_TEMP12:%.*]] = alloca double, align 8
|
|
// CHECK4-NEXT: [[_TMP13:%.*]] = alloca double, align 8
|
|
// CHECK4-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK4-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK4-NEXT: store %struct.anon* [[__CONTEXT]], %struct.anon** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK4-NEXT: [[TMP0:%.*]] = load %struct.anon*, %struct.anon** [[__CONTEXT_ADDR]], align 8
|
|
// CHECK4-NEXT: [[TMP1:%.*]] = load double*, double** @g1, align 8
|
|
// CHECK4-NEXT: store double* [[TMP1]], double** [[TMP]], align 8
|
|
// CHECK4-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK4-NEXT: store i32 1, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK4-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK4-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK4-NEXT: store double 0.000000e+00, double* [[G]], align 8
|
|
// CHECK4-NEXT: [[TMP2:%.*]] = load double*, double** @g1, align 8
|
|
// CHECK4-NEXT: store double 0.000000e+00, double* [[G1]], align 8
|
|
// CHECK4-NEXT: store double* [[G1]], double** [[_TMP2]], align 8
|
|
// CHECK4-NEXT: [[TMP3:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK4-NEXT: [[TMP4:%.*]] = load i32, i32* [[TMP3]], align 4
|
|
// CHECK4-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 [[TMP4]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK4-NEXT: [[TMP5:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK4-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP5]], 1
|
|
// CHECK4-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK4: cond.true:
|
|
// CHECK4-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK4: cond.false:
|
|
// CHECK4-NEXT: [[TMP6:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK4-NEXT: br label [[COND_END]]
|
|
// CHECK4: cond.end:
|
|
// CHECK4-NEXT: [[COND:%.*]] = phi i32 [ 1, [[COND_TRUE]] ], [ [[TMP6]], [[COND_FALSE]] ]
|
|
// CHECK4-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK4-NEXT: [[TMP7:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK4-NEXT: store i32 [[TMP7]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK4-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK4: omp.inner.for.cond:
|
|
// CHECK4-NEXT: [[TMP8:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK4-NEXT: [[TMP9:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK4-NEXT: [[CMP3:%.*]] = icmp sle i32 [[TMP8]], [[TMP9]]
|
|
// CHECK4-NEXT: br i1 [[CMP3]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK4: omp.inner.for.body:
|
|
// CHECK4-NEXT: [[TMP10:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK4-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP10]], 1
|
|
// CHECK4-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK4-NEXT: store i32 [[ADD]], i32* [[I]], align 4
|
|
// CHECK4-NEXT: store double 1.000000e+00, double* [[G]], align 8
|
|
// CHECK4-NEXT: [[TMP11:%.*]] = load double*, double** [[_TMP2]], align 8
|
|
// CHECK4-NEXT: store volatile double 1.000000e+00, double* [[TMP11]], align 8
|
|
// CHECK4-NEXT: [[BLOCK_ISA:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double, double* }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double, double* }>* [[BLOCK]], i32 0, i32 0
|
|
// CHECK4-NEXT: store i8* bitcast (i8** @_NSConcreteStackBlock to i8*), i8** [[BLOCK_ISA]], align 8
|
|
// CHECK4-NEXT: [[BLOCK_FLAGS:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double, double* }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double, double* }>* [[BLOCK]], i32 0, i32 1
|
|
// CHECK4-NEXT: store i32 1073741824, i32* [[BLOCK_FLAGS]], align 8
|
|
// CHECK4-NEXT: [[BLOCK_RESERVED:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double, double* }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double, double* }>* [[BLOCK]], i32 0, i32 2
|
|
// CHECK4-NEXT: store i32 0, i32* [[BLOCK_RESERVED]], align 4
|
|
// CHECK4-NEXT: [[BLOCK_INVOKE:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double, double* }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double, double* }>* [[BLOCK]], i32 0, i32 3
|
|
// CHECK4-NEXT: store i8* bitcast (void (i8*)* @g1_block_invoke to i8*), i8** [[BLOCK_INVOKE]], align 8
|
|
// CHECK4-NEXT: [[BLOCK_DESCRIPTOR:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double, double* }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double, double* }>* [[BLOCK]], i32 0, i32 4
|
|
// CHECK4-NEXT: store %struct.__block_descriptor* bitcast ({ i64, i64, i8*, i8* }* @__block_descriptor_tmp.1 to %struct.__block_descriptor*), %struct.__block_descriptor** [[BLOCK_DESCRIPTOR]], align 8
|
|
// CHECK4-NEXT: [[BLOCK_CAPTURED:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double, double* }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double, double* }>* [[BLOCK]], i32 0, i32 5
|
|
// CHECK4-NEXT: [[TMP12:%.*]] = load volatile double, double* [[G]], align 8
|
|
// CHECK4-NEXT: store volatile double [[TMP12]], double* [[BLOCK_CAPTURED]], align 8
|
|
// CHECK4-NEXT: [[BLOCK_CAPTURED4:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double, double* }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double, double* }>* [[BLOCK]], i32 0, i32 6
|
|
// CHECK4-NEXT: [[TMP13:%.*]] = load double*, double** [[_TMP2]], align 8
|
|
// CHECK4-NEXT: store double* [[TMP13]], double** [[BLOCK_CAPTURED4]], align 8
|
|
// CHECK4-NEXT: [[TMP14:%.*]] = bitcast <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double, double* }>* [[BLOCK]] to void ()*
|
|
// CHECK4-NEXT: [[BLOCK_LITERAL:%.*]] = bitcast void ()* [[TMP14]] to %struct.__block_literal_generic*
|
|
// CHECK4-NEXT: [[TMP15:%.*]] = getelementptr inbounds [[STRUCT___BLOCK_LITERAL_GENERIC:%.*]], %struct.__block_literal_generic* [[BLOCK_LITERAL]], i32 0, i32 3
|
|
// CHECK4-NEXT: [[TMP16:%.*]] = bitcast %struct.__block_literal_generic* [[BLOCK_LITERAL]] to i8*
|
|
// CHECK4-NEXT: [[TMP17:%.*]] = load i8*, i8** [[TMP15]], align 8
|
|
// CHECK4-NEXT: [[TMP18:%.*]] = bitcast i8* [[TMP17]] to void (i8*)*
|
|
// CHECK4-NEXT: call void [[TMP18]](i8* [[TMP16]])
|
|
// CHECK4-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK4: omp.body.continue:
|
|
// CHECK4-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK4: omp.inner.for.inc:
|
|
// CHECK4-NEXT: [[TMP19:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK4-NEXT: [[ADD5:%.*]] = add nsw i32 [[TMP19]], 1
|
|
// CHECK4-NEXT: store i32 [[ADD5]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK4-NEXT: br label [[OMP_INNER_FOR_COND]]
|
|
// CHECK4: omp.inner.for.end:
|
|
// CHECK4-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK4: omp.loop.exit:
|
|
// CHECK4-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP4]])
|
|
// CHECK4-NEXT: [[TMP20:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK4-NEXT: [[TMP21:%.*]] = bitcast double* [[G]] to i8*
|
|
// CHECK4-NEXT: store i8* [[TMP21]], i8** [[TMP20]], align 8
|
|
// CHECK4-NEXT: [[TMP22:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 1
|
|
// CHECK4-NEXT: [[TMP23:%.*]] = bitcast double* [[G1]] to i8*
|
|
// CHECK4-NEXT: store i8* [[TMP23]], i8** [[TMP22]], align 8
|
|
// CHECK4-NEXT: [[TMP24:%.*]] = bitcast [2 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK4-NEXT: [[TMP25:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2:[0-9]+]], i32 [[TMP4]], i32 2, i64 16, i8* [[TMP24]], void (i8*, i8*)* @.omp.reduction.reduction_func, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK4-NEXT: switch i32 [[TMP25]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
|
|
// CHECK4-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
|
|
// CHECK4-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
|
|
// CHECK4-NEXT: ]
|
|
// CHECK4: .omp.reduction.case1:
|
|
// CHECK4-NEXT: [[TMP26:%.*]] = load double, double* @g, align 8
|
|
// CHECK4-NEXT: [[TMP27:%.*]] = load double, double* [[G]], align 8
|
|
// CHECK4-NEXT: [[ADD6:%.*]] = fadd double [[TMP26]], [[TMP27]]
|
|
// CHECK4-NEXT: store double [[ADD6]], double* @g, align 8
|
|
// CHECK4-NEXT: [[TMP28:%.*]] = load double, double* [[TMP2]], align 8
|
|
// CHECK4-NEXT: [[TMP29:%.*]] = load double, double* [[G1]], align 8
|
|
// CHECK4-NEXT: [[ADD7:%.*]] = fadd double [[TMP28]], [[TMP29]]
|
|
// CHECK4-NEXT: store double [[ADD7]], double* [[TMP2]], align 8
|
|
// CHECK4-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP4]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK4-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK4: .omp.reduction.case2:
|
|
// CHECK4-NEXT: [[TMP30:%.*]] = load double, double* [[G]], align 8
|
|
// CHECK4-NEXT: [[ATOMIC_LOAD:%.*]] = load atomic i64, i64* bitcast (double* @g to i64*) monotonic, align 8
|
|
// CHECK4-NEXT: br label [[ATOMIC_CONT:%.*]]
|
|
// CHECK4: atomic_cont:
|
|
// CHECK4-NEXT: [[TMP31:%.*]] = phi i64 [ [[ATOMIC_LOAD]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[TMP38:%.*]], [[ATOMIC_CONT]] ]
|
|
// CHECK4-NEXT: [[TMP32:%.*]] = bitcast double* [[ATOMIC_TEMP]] to i64*
|
|
// CHECK4-NEXT: [[TMP33:%.*]] = bitcast i64 [[TMP31]] to double
|
|
// CHECK4-NEXT: store double [[TMP33]], double* [[_TMP8]], align 8
|
|
// CHECK4-NEXT: [[TMP34:%.*]] = load double, double* [[_TMP8]], align 8
|
|
// CHECK4-NEXT: [[TMP35:%.*]] = load double, double* [[G]], align 8
|
|
// CHECK4-NEXT: [[ADD9:%.*]] = fadd double [[TMP34]], [[TMP35]]
|
|
// CHECK4-NEXT: store double [[ADD9]], double* [[ATOMIC_TEMP]], align 8
|
|
// CHECK4-NEXT: [[TMP36:%.*]] = load i64, i64* [[TMP32]], align 8
|
|
// CHECK4-NEXT: [[TMP37:%.*]] = cmpxchg i64* bitcast (double* @g to i64*), i64 [[TMP31]], i64 [[TMP36]] monotonic monotonic, align 8
|
|
// CHECK4-NEXT: [[TMP38]] = extractvalue { i64, i1 } [[TMP37]], 0
|
|
// CHECK4-NEXT: [[TMP39:%.*]] = extractvalue { i64, i1 } [[TMP37]], 1
|
|
// CHECK4-NEXT: br i1 [[TMP39]], label [[ATOMIC_EXIT:%.*]], label [[ATOMIC_CONT]]
|
|
// CHECK4: atomic_exit:
|
|
// CHECK4-NEXT: [[TMP40:%.*]] = load double, double* [[G1]], align 8
|
|
// CHECK4-NEXT: [[TMP41:%.*]] = bitcast double* [[TMP2]] to i64*
|
|
// CHECK4-NEXT: [[ATOMIC_LOAD10:%.*]] = load atomic i64, i64* [[TMP41]] monotonic, align 8
|
|
// CHECK4-NEXT: br label [[ATOMIC_CONT11:%.*]]
|
|
// CHECK4: atomic_cont11:
|
|
// CHECK4-NEXT: [[TMP42:%.*]] = phi i64 [ [[ATOMIC_LOAD10]], [[ATOMIC_EXIT]] ], [ [[TMP50:%.*]], [[ATOMIC_CONT11]] ]
|
|
// CHECK4-NEXT: [[TMP43:%.*]] = bitcast double* [[ATOMIC_TEMP12]] to i64*
|
|
// CHECK4-NEXT: [[TMP44:%.*]] = bitcast i64 [[TMP42]] to double
|
|
// CHECK4-NEXT: store double [[TMP44]], double* [[_TMP13]], align 8
|
|
// CHECK4-NEXT: [[TMP45:%.*]] = load double, double* [[_TMP13]], align 8
|
|
// CHECK4-NEXT: [[TMP46:%.*]] = load double, double* [[G1]], align 8
|
|
// CHECK4-NEXT: [[ADD14:%.*]] = fadd double [[TMP45]], [[TMP46]]
|
|
// CHECK4-NEXT: store double [[ADD14]], double* [[ATOMIC_TEMP12]], align 8
|
|
// CHECK4-NEXT: [[TMP47:%.*]] = load i64, i64* [[TMP43]], align 8
|
|
// CHECK4-NEXT: [[TMP48:%.*]] = bitcast double* [[TMP2]] to i64*
|
|
// CHECK4-NEXT: [[TMP49:%.*]] = cmpxchg i64* [[TMP48]], i64 [[TMP42]], i64 [[TMP47]] monotonic monotonic, align 8
|
|
// CHECK4-NEXT: [[TMP50]] = extractvalue { i64, i1 } [[TMP49]], 0
|
|
// CHECK4-NEXT: [[TMP51:%.*]] = extractvalue { i64, i1 } [[TMP49]], 1
|
|
// CHECK4-NEXT: br i1 [[TMP51]], label [[ATOMIC_EXIT15:%.*]], label [[ATOMIC_CONT11]]
|
|
// CHECK4: atomic_exit15:
|
|
// CHECK4-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP4]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK4-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK4: .omp.reduction.default:
|
|
// CHECK4-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB3:[0-9]+]], i32 [[TMP4]])
|
|
// CHECK4-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK4-LABEL: define {{[^@]+}}@g1_block_invoke
|
|
// CHECK4-SAME: (i8* [[DOTBLOCK_DESCRIPTOR:%.*]]) #[[ATTR2]] {
|
|
// CHECK4-NEXT: entry:
|
|
// CHECK4-NEXT: [[DOTBLOCK_DESCRIPTOR_ADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK4-NEXT: [[BLOCK_ADDR:%.*]] = alloca <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double, double* }>*, align 8
|
|
// CHECK4-NEXT: store i8* [[DOTBLOCK_DESCRIPTOR]], i8** [[DOTBLOCK_DESCRIPTOR_ADDR]], align 8
|
|
// CHECK4-NEXT: [[BLOCK:%.*]] = bitcast i8* [[DOTBLOCK_DESCRIPTOR]] to <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double, double* }>*
|
|
// CHECK4-NEXT: store <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double, double* }>* [[BLOCK]], <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double, double* }>** [[BLOCK_ADDR]], align 8
|
|
// CHECK4-NEXT: [[BLOCK_CAPTURE_ADDR:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double, double* }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double, double* }>* [[BLOCK]], i32 0, i32 5
|
|
// CHECK4-NEXT: store double 2.000000e+00, double* [[BLOCK_CAPTURE_ADDR]], align 8
|
|
// CHECK4-NEXT: [[BLOCK_CAPTURE_ADDR1:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double, double* }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double, double* }>* [[BLOCK]], i32 0, i32 6
|
|
// CHECK4-NEXT: [[TMP0:%.*]] = load double*, double** [[BLOCK_CAPTURE_ADDR1]], align 8
|
|
// CHECK4-NEXT: store double 2.000000e+00, double* [[TMP0]], align 8
|
|
// CHECK4-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK4-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func
|
|
// CHECK4-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR5:[0-9]+]] {
|
|
// CHECK4-NEXT: entry:
|
|
// CHECK4-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK4-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
|
|
// CHECK4-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK4-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
|
|
// CHECK4-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK4-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [2 x i8*]*
|
|
// CHECK4-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
|
|
// CHECK4-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [2 x i8*]*
|
|
// CHECK4-NEXT: [[TMP6:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK4-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
|
|
// CHECK4-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to double*
|
|
// CHECK4-NEXT: [[TMP9:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[TMP3]], i64 0, i64 0
|
|
// CHECK4-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
|
|
// CHECK4-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to double*
|
|
// CHECK4-NEXT: [[TMP12:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[TMP5]], i64 0, i64 1
|
|
// CHECK4-NEXT: [[TMP13:%.*]] = load i8*, i8** [[TMP12]], align 8
|
|
// CHECK4-NEXT: [[TMP14:%.*]] = bitcast i8* [[TMP13]] to double*
|
|
// CHECK4-NEXT: [[TMP15:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[TMP3]], i64 0, i64 1
|
|
// CHECK4-NEXT: [[TMP16:%.*]] = load i8*, i8** [[TMP15]], align 8
|
|
// CHECK4-NEXT: [[TMP17:%.*]] = bitcast i8* [[TMP16]] to double*
|
|
// CHECK4-NEXT: [[TMP18:%.*]] = load double, double* [[TMP11]], align 8
|
|
// CHECK4-NEXT: [[TMP19:%.*]] = load double, double* [[TMP8]], align 8
|
|
// CHECK4-NEXT: [[ADD:%.*]] = fadd double [[TMP18]], [[TMP19]]
|
|
// CHECK4-NEXT: store double [[ADD]], double* [[TMP11]], align 8
|
|
// CHECK4-NEXT: [[TMP20:%.*]] = load double, double* [[TMP17]], align 8
|
|
// CHECK4-NEXT: [[TMP21:%.*]] = load double, double* [[TMP14]], align 8
|
|
// CHECK4-NEXT: [[ADD2:%.*]] = fadd double [[TMP20]], [[TMP21]]
|
|
// CHECK4-NEXT: store double [[ADD2]], double* [[TMP17]], align 8
|
|
// CHECK4-NEXT: ret void
|
|
//
|