forked from OSchip/llvm-project
2094 lines
150 KiB
C++
2094 lines
150 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 -no-opaque-pointers -verify -fopenmp -fopenmp-cuda-mode -x c++ \
|
|
// RUN: -triple powerpc64le-unknown-unknown -DCUDA \
|
|
// RUN: -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o \
|
|
// RUN: %t-ppc-host.bc
|
|
|
|
// RUN: %clang_cc1 -no-opaque-pointers -verify -fopenmp -fopenmp-cuda-mode -x c++ \
|
|
// RUN: -triple nvptx64-unknown-unknown -DCUA \
|
|
// RUN: -fopenmp-targets=nvptx64-nvidia-cuda -DCUDA -emit-llvm %s \
|
|
// RUN: -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc \
|
|
// RUN: -o - | FileCheck %s --check-prefix CHECK
|
|
|
|
// RUN: %clang_cc1 -no-opaque-pointers -verify -fopenmp -x c++ \
|
|
// RUN: -triple powerpc64le-unknown-unknown -DDIAG\
|
|
// RUN: -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm \
|
|
// RUN: %s -o - | FileCheck %s \
|
|
// RUN: --check-prefix=CHECK1
|
|
|
|
// RUN: %clang_cc1 -no-opaque-pointers -verify -fopenmp -x c++ \
|
|
// RUN: -triple i386-unknown-unknown \
|
|
// RUN: -fopenmp-targets=i386-pc-linux-gnu -emit-llvm \
|
|
// RUN: %s -o - | FileCheck %s \
|
|
// RUN: --check-prefix=CHECK2
|
|
|
|
|
|
#if defined(CUDA)
|
|
// expected-no-diagnostics
|
|
|
|
int foo(int n) {
|
|
double *e;
|
|
//no error and no implicit map generated for e[:1]
|
|
#pragma omp target parallel reduction(+: e[:1])
|
|
*e=10;
|
|
;
|
|
return 0;
|
|
}
|
|
// CHECK-NOT @.offload_maptypes
|
|
#elif defined(DIAG)
|
|
class S2 {
|
|
mutable int a;
|
|
public:
|
|
S2():a(0) { }
|
|
S2(S2 &s2):a(s2.a) { }
|
|
S2 &operator +(S2 &s);
|
|
};
|
|
int bar() {
|
|
S2 o[5];
|
|
//warnig "copyable and not guaranteed to be mapped correctly" and
|
|
//implicit map generated.
|
|
#pragma omp target parallel reduction(+:o[0]) //expected-warning {{Type 'S2' is not trivially copyable and not guaranteed to be mapped correctly}}
|
|
for (int i = 0; i < 10; i++);
|
|
double b[10][10][10];
|
|
//no error no implicit map generated, the map for b is generated but not
|
|
//for b[0:2][2:4][1].
|
|
#pragma omp target parallel for reduction(task, +: b[0:2][2:4][1])
|
|
for (long long i = 0; i < 10; ++i);
|
|
return 0;
|
|
}
|
|
// map for variable o
|
|
// map for b:
|
|
#else
|
|
// expected-no-diagnostics
|
|
|
|
// generate implicit map for array elements or array sections in reduction
|
|
// clause. In following case: the implicit map is generate for output[0]
|
|
// with map size 4 and output[:3] with map size 12.
|
|
void sum(int* input, int size, int* output)
|
|
{
|
|
#pragma omp target teams distribute parallel for reduction(+: output[0]) \
|
|
map(to: input [0:size])
|
|
for (int i = 0; i < size; i++)
|
|
output[0] += input[i];
|
|
#pragma omp target teams distribute parallel for reduction(+: output[:3]) \
|
|
map(to: input [0:size])
|
|
for (int i = 0; i < size; i++)
|
|
output[0] += input[i];
|
|
int a[10];
|
|
#pragma omp target parallel reduction(+: a[:2])
|
|
for (int i = 0; i < size; i++)
|
|
;
|
|
#pragma omp target parallel reduction(+: a[3])
|
|
for (int i = 0; i < size; i++)
|
|
;
|
|
}
|
|
#endif
|
|
int main()
|
|
{
|
|
#if defined(CUDA)
|
|
int a = foo(10);
|
|
#elif defined(DIAG)
|
|
int a = bar();
|
|
#else
|
|
const int size = 100;
|
|
int *array = new int[size];
|
|
int result = 0;
|
|
sum(array, size, &result);
|
|
#endif
|
|
return 0;
|
|
}
|
|
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l32
|
|
// CHECK-SAME: (double* noundef [[E:%.*]]) #[[ATTR0:[0-9]+]] {
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[E_ADDR:%.*]] = alloca double*, align 8
|
|
// CHECK-NEXT: [[CAPTURED_VARS_ADDRS:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK-NEXT: store double* [[E]], double** [[E_ADDR]], align 8
|
|
// CHECK-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_target_init(%struct.ident_t* @[[GLOB1:[0-9]+]], i8 2, i1 false, i1 true)
|
|
// CHECK-NEXT: [[EXEC_USER_CODE:%.*]] = icmp eq i32 [[TMP0]], -1
|
|
// CHECK-NEXT: br i1 [[EXEC_USER_CODE]], label [[USER_CODE_ENTRY:%.*]], label [[WORKER_EXIT:%.*]]
|
|
// CHECK: user_code.entry:
|
|
// CHECK-NEXT: [[TMP1:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2:[0-9]+]])
|
|
// CHECK-NEXT: [[TMP2:%.*]] = load double*, double** [[E_ADDR]], align 8
|
|
// CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[CAPTURED_VARS_ADDRS]], i64 0, i64 0
|
|
// CHECK-NEXT: [[TMP4:%.*]] = bitcast double* [[TMP2]] to i8*
|
|
// CHECK-NEXT: store i8* [[TMP4]], i8** [[TMP3]], align 8
|
|
// CHECK-NEXT: [[TMP5:%.*]] = bitcast [1 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8**
|
|
// CHECK-NEXT: call void @__kmpc_parallel_51(%struct.ident_t* @[[GLOB2]], i32 [[TMP1]], i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*, double*)* @__omp_outlined__ to i8*), i8* null, i8** [[TMP5]], i64 1)
|
|
// CHECK-NEXT: call void @__kmpc_target_deinit(%struct.ident_t* @[[GLOB1]], i8 2, i1 true)
|
|
// CHECK-NEXT: ret void
|
|
// CHECK: worker.exit:
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK-LABEL: define {{[^@]+}}@__omp_outlined__
|
|
// CHECK-SAME: (i32* noalias noundef [[DOTGLOBAL_TID_:%.*]], i32* noalias noundef [[DOTBOUND_TID_:%.*]], double* noundef [[E:%.*]]) #[[ATTR1:[0-9]+]] {
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK-NEXT: [[E_ADDR:%.*]] = alloca double*, align 8
|
|
// CHECK-NEXT: [[E2:%.*]] = alloca double, align 8
|
|
// CHECK-NEXT: [[TMP:%.*]] = alloca double*, align 8
|
|
// CHECK-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK-NEXT: store double* [[E]], double** [[E_ADDR]], align 8
|
|
// CHECK-NEXT: [[TMP0:%.*]] = load double*, double** [[E_ADDR]], align 8
|
|
// CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds double, double* [[TMP0]], i64 0
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load double*, double** [[E_ADDR]], align 8
|
|
// CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds double, double* [[TMP1]], i64 0
|
|
// CHECK-NEXT: store double 0.000000e+00, double* [[E2]], align 8
|
|
// CHECK-NEXT: [[TMP2:%.*]] = load double*, double** [[E_ADDR]], align 8
|
|
// CHECK-NEXT: [[TMP3:%.*]] = ptrtoint double* [[TMP2]] to i64
|
|
// CHECK-NEXT: [[TMP4:%.*]] = ptrtoint double* [[ARRAYIDX]] to i64
|
|
// CHECK-NEXT: [[TMP5:%.*]] = sub i64 [[TMP3]], [[TMP4]]
|
|
// CHECK-NEXT: [[TMP6:%.*]] = sdiv exact i64 [[TMP5]], ptrtoint (double* getelementptr (double, double* null, i32 1) to i64)
|
|
// CHECK-NEXT: [[TMP7:%.*]] = getelementptr double, double* [[E2]], i64 [[TMP6]]
|
|
// CHECK-NEXT: store double* [[TMP7]], double** [[TMP]], align 8
|
|
// CHECK-NEXT: [[TMP8:%.*]] = load double*, double** [[TMP]], align 8
|
|
// CHECK-NEXT: store double 1.000000e+01, double* [[TMP8]], align 8
|
|
// CHECK-NEXT: [[TMP9:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP9]], align 4
|
|
// CHECK-NEXT: [[TMP11:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK-NEXT: [[TMP12:%.*]] = bitcast double* [[E2]] to i8*
|
|
// CHECK-NEXT: store i8* [[TMP12]], i8** [[TMP11]], align 8
|
|
// CHECK-NEXT: [[TMP13:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK-NEXT: [[TMP14:%.*]] = call i32 @__kmpc_nvptx_parallel_reduce_nowait_v2(%struct.ident_t* @[[GLOB2]], i32 [[TMP10]], i32 1, i64 8, i8* [[TMP13]], void (i8*, i16, i16, i16)* @_omp_reduction_shuffle_and_reduce_func, void (i8*, i32)* @_omp_reduction_inter_warp_copy_func)
|
|
// CHECK-NEXT: [[TMP15:%.*]] = icmp eq i32 [[TMP14]], 1
|
|
// CHECK-NEXT: br i1 [[TMP15]], label [[DOTOMP_REDUCTION_THEN:%.*]], label [[DOTOMP_REDUCTION_DONE:%.*]]
|
|
// CHECK: .omp.reduction.then:
|
|
// CHECK-NEXT: [[TMP16:%.*]] = load double, double* [[ARRAYIDX]], align 8
|
|
// CHECK-NEXT: [[TMP17:%.*]] = load double, double* [[E2]], align 8
|
|
// CHECK-NEXT: [[ADD:%.*]] = fadd double [[TMP16]], [[TMP17]]
|
|
// CHECK-NEXT: store double [[ADD]], double* [[ARRAYIDX]], align 8
|
|
// CHECK-NEXT: call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP10]])
|
|
// CHECK-NEXT: br label [[DOTOMP_REDUCTION_DONE]]
|
|
// CHECK: .omp.reduction.done:
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK-LABEL: define {{[^@]+}}@_omp_reduction_shuffle_and_reduce_func
|
|
// CHECK-SAME: (i8* noundef [[TMP0:%.*]], i16 noundef signext [[TMP1:%.*]], i16 noundef signext [[TMP2:%.*]], i16 noundef signext [[TMP3:%.*]]) #[[ATTR2:[0-9]+]] {
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK-NEXT: [[DOTADDR1:%.*]] = alloca i16, align 2
|
|
// CHECK-NEXT: [[DOTADDR2:%.*]] = alloca i16, align 2
|
|
// CHECK-NEXT: [[DOTADDR3:%.*]] = alloca i16, align 2
|
|
// CHECK-NEXT: [[DOTOMP_REDUCTION_REMOTE_REDUCE_LIST:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK-NEXT: [[DOTOMP_REDUCTION_ELEMENT:%.*]] = alloca double, align 8
|
|
// CHECK-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK-NEXT: store i16 [[TMP1]], i16* [[DOTADDR1]], align 2
|
|
// CHECK-NEXT: store i16 [[TMP2]], i16* [[DOTADDR2]], align 2
|
|
// CHECK-NEXT: store i16 [[TMP3]], i16* [[DOTADDR3]], align 2
|
|
// CHECK-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK-NEXT: [[TMP6:%.*]] = load i16, i16* [[DOTADDR1]], align 2
|
|
// CHECK-NEXT: [[TMP7:%.*]] = load i16, i16* [[DOTADDR2]], align 2
|
|
// CHECK-NEXT: [[TMP8:%.*]] = load i16, i16* [[DOTADDR3]], align 2
|
|
// CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK-NEXT: [[TMP10:%.*]] = bitcast i8** [[TMP9]] to double**
|
|
// CHECK-NEXT: [[TMP11:%.*]] = load double*, double** [[TMP10]], align 8
|
|
// CHECK-NEXT: [[TMP12:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_REMOTE_REDUCE_LIST]], i64 0, i64 0
|
|
// CHECK-NEXT: [[TMP13:%.*]] = getelementptr double, double* [[TMP11]], i64 1
|
|
// CHECK-NEXT: [[TMP14:%.*]] = bitcast double* [[TMP13]] to i8*
|
|
// CHECK-NEXT: [[TMP15:%.*]] = bitcast double* [[TMP11]] to i64*
|
|
// CHECK-NEXT: [[TMP16:%.*]] = bitcast double* [[DOTOMP_REDUCTION_ELEMENT]] to i64*
|
|
// CHECK-NEXT: [[TMP17:%.*]] = load i64, i64* [[TMP15]], align 8
|
|
// CHECK-NEXT: [[TMP18:%.*]] = call i32 @__kmpc_get_warp_size()
|
|
// CHECK-NEXT: [[TMP19:%.*]] = trunc i32 [[TMP18]] to i16
|
|
// CHECK-NEXT: [[TMP20:%.*]] = call i64 @__kmpc_shuffle_int64(i64 [[TMP17]], i16 [[TMP7]], i16 [[TMP19]])
|
|
// CHECK-NEXT: store i64 [[TMP20]], i64* [[TMP16]], align 8
|
|
// CHECK-NEXT: [[TMP21:%.*]] = getelementptr i64, i64* [[TMP15]], i64 1
|
|
// CHECK-NEXT: [[TMP22:%.*]] = getelementptr i64, i64* [[TMP16]], i64 1
|
|
// CHECK-NEXT: [[TMP23:%.*]] = bitcast double* [[DOTOMP_REDUCTION_ELEMENT]] to i8*
|
|
// CHECK-NEXT: store i8* [[TMP23]], i8** [[TMP12]], align 8
|
|
// CHECK-NEXT: [[TMP24:%.*]] = icmp eq i16 [[TMP8]], 0
|
|
// CHECK-NEXT: [[TMP25:%.*]] = icmp eq i16 [[TMP8]], 1
|
|
// CHECK-NEXT: [[TMP26:%.*]] = icmp ult i16 [[TMP6]], [[TMP7]]
|
|
// CHECK-NEXT: [[TMP27:%.*]] = and i1 [[TMP25]], [[TMP26]]
|
|
// CHECK-NEXT: [[TMP28:%.*]] = icmp eq i16 [[TMP8]], 2
|
|
// CHECK-NEXT: [[TMP29:%.*]] = and i16 [[TMP6]], 1
|
|
// CHECK-NEXT: [[TMP30:%.*]] = icmp eq i16 [[TMP29]], 0
|
|
// CHECK-NEXT: [[TMP31:%.*]] = and i1 [[TMP28]], [[TMP30]]
|
|
// CHECK-NEXT: [[TMP32:%.*]] = icmp sgt i16 [[TMP7]], 0
|
|
// CHECK-NEXT: [[TMP33:%.*]] = and i1 [[TMP31]], [[TMP32]]
|
|
// CHECK-NEXT: [[TMP34:%.*]] = or i1 [[TMP24]], [[TMP27]]
|
|
// CHECK-NEXT: [[TMP35:%.*]] = or i1 [[TMP34]], [[TMP33]]
|
|
// CHECK-NEXT: br i1 [[TMP35]], label [[THEN:%.*]], label [[ELSE:%.*]]
|
|
// CHECK: then:
|
|
// CHECK-NEXT: [[TMP36:%.*]] = bitcast [1 x i8*]* [[TMP5]] to i8*
|
|
// CHECK-NEXT: [[TMP37:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_REMOTE_REDUCE_LIST]] to i8*
|
|
// CHECK-NEXT: call void @"_omp$reduction$reduction_func"(i8* [[TMP36]], i8* [[TMP37]]) #[[ATTR3:[0-9]+]]
|
|
// CHECK-NEXT: br label [[IFCONT:%.*]]
|
|
// CHECK: else:
|
|
// CHECK-NEXT: br label [[IFCONT]]
|
|
// CHECK: ifcont:
|
|
// CHECK-NEXT: [[TMP38:%.*]] = icmp eq i16 [[TMP8]], 1
|
|
// CHECK-NEXT: [[TMP39:%.*]] = icmp uge i16 [[TMP6]], [[TMP7]]
|
|
// CHECK-NEXT: [[TMP40:%.*]] = and i1 [[TMP38]], [[TMP39]]
|
|
// CHECK-NEXT: br i1 [[TMP40]], label [[THEN4:%.*]], label [[ELSE5:%.*]]
|
|
// CHECK: then4:
|
|
// CHECK-NEXT: [[TMP41:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_REMOTE_REDUCE_LIST]], i64 0, i64 0
|
|
// CHECK-NEXT: [[TMP42:%.*]] = bitcast i8** [[TMP41]] to double**
|
|
// CHECK-NEXT: [[TMP43:%.*]] = load double*, double** [[TMP42]], align 8
|
|
// CHECK-NEXT: [[TMP44:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i64 0, i64 0
|
|
// CHECK-NEXT: [[TMP45:%.*]] = bitcast i8** [[TMP44]] to double**
|
|
// CHECK-NEXT: [[TMP46:%.*]] = load double*, double** [[TMP45]], align 8
|
|
// CHECK-NEXT: [[TMP47:%.*]] = load double, double* [[TMP43]], align 8
|
|
// CHECK-NEXT: store double [[TMP47]], double* [[TMP46]], align 8
|
|
// CHECK-NEXT: br label [[IFCONT6:%.*]]
|
|
// CHECK: else5:
|
|
// CHECK-NEXT: br label [[IFCONT6]]
|
|
// CHECK: ifcont6:
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK-LABEL: define {{[^@]+}}@_omp_reduction_inter_warp_copy_func
|
|
// CHECK-SAME: (i8* noundef [[TMP0:%.*]], i32 noundef [[TMP1:%.*]]) #[[ATTR2]] {
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
|
|
// CHECK-NEXT: [[DOTADDR1:%.*]] = alloca i32, align 4
|
|
// CHECK-NEXT: [[DOTCNT_ADDR:%.*]] = alloca i32, align 4
|
|
// CHECK-NEXT: [[TMP2:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB2]])
|
|
// CHECK-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
|
|
// CHECK-NEXT: store i32 [[TMP1]], i32* [[DOTADDR1]], align 4
|
|
// CHECK-NEXT: [[TMP3:%.*]] = call i32 @__kmpc_get_hardware_thread_id_in_block()
|
|
// CHECK-NEXT: [[TMP4:%.*]] = call i32 @__kmpc_get_hardware_thread_id_in_block()
|
|
// CHECK-NEXT: [[NVPTX_LANE_ID:%.*]] = and i32 [[TMP4]], 31
|
|
// CHECK-NEXT: [[TMP5:%.*]] = call i32 @__kmpc_get_hardware_thread_id_in_block()
|
|
// CHECK-NEXT: [[NVPTX_WARP_ID:%.*]] = ashr i32 [[TMP5]], 5
|
|
// CHECK-NEXT: [[TMP6:%.*]] = load i8*, i8** [[DOTADDR]], align 8
|
|
// CHECK-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to [1 x i8*]*
|
|
// CHECK-NEXT: store i32 0, i32* [[DOTCNT_ADDR]], align 4
|
|
// CHECK-NEXT: br label [[PRECOND:%.*]]
|
|
// CHECK: precond:
|
|
// CHECK-NEXT: [[TMP8:%.*]] = load i32, i32* [[DOTCNT_ADDR]], align 4
|
|
// CHECK-NEXT: [[TMP9:%.*]] = icmp ult i32 [[TMP8]], 2
|
|
// CHECK-NEXT: br i1 [[TMP9]], label [[BODY:%.*]], label [[EXIT:%.*]]
|
|
// CHECK: body:
|
|
// CHECK-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB3:[0-9]+]], i32 [[TMP2]])
|
|
// CHECK-NEXT: [[WARP_MASTER:%.*]] = icmp eq i32 [[NVPTX_LANE_ID]], 0
|
|
// CHECK-NEXT: br i1 [[WARP_MASTER]], label [[THEN:%.*]], label [[ELSE:%.*]]
|
|
// CHECK: then:
|
|
// CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP7]], i64 0, i64 0
|
|
// CHECK-NEXT: [[TMP11:%.*]] = load i8*, i8** [[TMP10]], align 8
|
|
// CHECK-NEXT: [[TMP12:%.*]] = bitcast i8* [[TMP11]] to i32*
|
|
// CHECK-NEXT: [[TMP13:%.*]] = getelementptr i32, i32* [[TMP12]], i32 [[TMP8]]
|
|
// CHECK-NEXT: [[TMP14:%.*]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace(3)* @__openmp_nvptx_data_transfer_temporary_storage, i64 0, i32 [[NVPTX_WARP_ID]]
|
|
// CHECK-NEXT: [[TMP15:%.*]] = load i32, i32* [[TMP13]], align 4
|
|
// CHECK-NEXT: store volatile i32 [[TMP15]], i32 addrspace(3)* [[TMP14]], align 4
|
|
// CHECK-NEXT: br label [[IFCONT:%.*]]
|
|
// CHECK: else:
|
|
// CHECK-NEXT: br label [[IFCONT]]
|
|
// CHECK: ifcont:
|
|
// CHECK-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB3]], i32 [[TMP2]])
|
|
// CHECK-NEXT: [[TMP16:%.*]] = load i32, i32* [[DOTADDR1]], align 4
|
|
// CHECK-NEXT: [[IS_ACTIVE_THREAD:%.*]] = icmp ult i32 [[TMP3]], [[TMP16]]
|
|
// CHECK-NEXT: br i1 [[IS_ACTIVE_THREAD]], label [[THEN2:%.*]], label [[ELSE3:%.*]]
|
|
// CHECK: then2:
|
|
// CHECK-NEXT: [[TMP17:%.*]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace(3)* @__openmp_nvptx_data_transfer_temporary_storage, i64 0, i32 [[TMP3]]
|
|
// CHECK-NEXT: [[TMP18:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP7]], i64 0, i64 0
|
|
// CHECK-NEXT: [[TMP19:%.*]] = load i8*, i8** [[TMP18]], align 8
|
|
// CHECK-NEXT: [[TMP20:%.*]] = bitcast i8* [[TMP19]] to i32*
|
|
// CHECK-NEXT: [[TMP21:%.*]] = getelementptr i32, i32* [[TMP20]], i32 [[TMP8]]
|
|
// CHECK-NEXT: [[TMP22:%.*]] = load volatile i32, i32 addrspace(3)* [[TMP17]], align 4
|
|
// CHECK-NEXT: store i32 [[TMP22]], i32* [[TMP21]], align 4
|
|
// CHECK-NEXT: br label [[IFCONT4:%.*]]
|
|
// CHECK: else3:
|
|
// CHECK-NEXT: br label [[IFCONT4]]
|
|
// CHECK: ifcont4:
|
|
// CHECK-NEXT: [[TMP23:%.*]] = add nsw i32 [[TMP8]], 1
|
|
// CHECK-NEXT: store i32 [[TMP23]], i32* [[DOTCNT_ADDR]], align 4
|
|
// CHECK-NEXT: br label [[PRECOND]]
|
|
// CHECK: exit:
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@_Z3barv
|
|
// CHECK1-SAME: () #[[ATTR0:[0-9]+]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[O:%.*]] = alloca [5 x %class.S2], align 4
|
|
// CHECK1-NEXT: [[DOTOFFLOAD_BASEPTRS:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK1-NEXT: [[DOTOFFLOAD_PTRS:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK1-NEXT: [[DOTOFFLOAD_MAPPERS:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK1-NEXT: [[B:%.*]] = alloca [10 x [10 x [10 x double]]], align 8
|
|
// CHECK1-NEXT: [[DOTOFFLOAD_BASEPTRS1:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK1-NEXT: [[DOTOFFLOAD_PTRS2:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK1-NEXT: [[DOTOFFLOAD_MAPPERS3:%.*]] = alloca [1 x i8*], align 8
|
|
// CHECK1-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [5 x %class.S2], [5 x %class.S2]* [[O]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[ARRAYCTOR_END:%.*]] = getelementptr inbounds [[CLASS_S2:%.*]], %class.S2* [[ARRAY_BEGIN]], i64 5
|
|
// CHECK1-NEXT: br label [[ARRAYCTOR_LOOP:%.*]]
|
|
// CHECK1: arrayctor.loop:
|
|
// CHECK1-NEXT: [[ARRAYCTOR_CUR:%.*]] = phi %class.S2* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[ARRAYCTOR_NEXT:%.*]], [[ARRAYCTOR_LOOP]] ]
|
|
// CHECK1-NEXT: call void @_ZN2S2C1Ev(%class.S2* noundef nonnull align 4 dereferenceable(4) [[ARRAYCTOR_CUR]])
|
|
// CHECK1-NEXT: [[ARRAYCTOR_NEXT]] = getelementptr inbounds [[CLASS_S2]], %class.S2* [[ARRAYCTOR_CUR]], i64 1
|
|
// CHECK1-NEXT: [[ARRAYCTOR_DONE:%.*]] = icmp eq %class.S2* [[ARRAYCTOR_NEXT]], [[ARRAYCTOR_END]]
|
|
// CHECK1-NEXT: br i1 [[ARRAYCTOR_DONE]], label [[ARRAYCTOR_CONT:%.*]], label [[ARRAYCTOR_LOOP]]
|
|
// CHECK1: arrayctor.cont:
|
|
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [5 x %class.S2], [5 x %class.S2]* [[O]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP1:%.*]] = bitcast i8** [[TMP0]] to [5 x %class.S2]**
|
|
// CHECK1-NEXT: store [5 x %class.S2]* [[O]], [5 x %class.S2]** [[TMP1]], align 8
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = bitcast i8** [[TMP2]] to %class.S2**
|
|
// CHECK1-NEXT: store %class.S2* [[ARRAYIDX]], %class.S2** [[TMP3]], align 8
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOFFLOAD_MAPPERS]], i64 0, i64 0
|
|
// CHECK1-NEXT: store i8* null, i8** [[TMP4]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = call i32 @__tgt_target_teams_mapper(%struct.ident_t* @[[GLOB2:[0-9]+]], i64 -1, i8* @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3barv_l50.region_id, i32 1, i8** [[TMP5]], i8** [[TMP6]], i64* getelementptr inbounds ([1 x i64], [1 x i64]* @.offload_sizes, i32 0, i32 0), i64* getelementptr inbounds ([1 x i64], [1 x i64]* @.offload_maptypes, i32 0, i32 0), i8** null, i8** null, i32 1, i32 0)
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = icmp ne i32 [[TMP7]], 0
|
|
// CHECK1-NEXT: br i1 [[TMP8]], label [[OMP_OFFLOAD_FAILED:%.*]], label [[OMP_OFFLOAD_CONT:%.*]]
|
|
// CHECK1: omp_offload.failed:
|
|
// CHECK1-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3barv_l50([5 x %class.S2]* [[O]]) #[[ATTR8:[0-9]+]]
|
|
// CHECK1-NEXT: br label [[OMP_OFFLOAD_CONT]]
|
|
// CHECK1: omp_offload.cont:
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOFFLOAD_BASEPTRS1]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = bitcast i8** [[TMP9]] to [10 x [10 x [10 x double]]]**
|
|
// CHECK1-NEXT: store [10 x [10 x [10 x double]]]* [[B]], [10 x [10 x [10 x double]]]** [[TMP10]], align 8
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOFFLOAD_PTRS2]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = bitcast i8** [[TMP11]] to [10 x [10 x [10 x double]]]**
|
|
// CHECK1-NEXT: store [10 x [10 x [10 x double]]]* [[B]], [10 x [10 x [10 x double]]]** [[TMP12]], align 8
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOFFLOAD_MAPPERS3]], i64 0, i64 0
|
|
// CHECK1-NEXT: store i8* null, i8** [[TMP13]], align 8
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOFFLOAD_BASEPTRS1]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOFFLOAD_PTRS2]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = call i32 @__tgt_target_teams_mapper(%struct.ident_t* @[[GLOB2]], i64 -1, i8* @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3barv_l55.region_id, i32 1, i8** [[TMP14]], i8** [[TMP15]], i64* getelementptr inbounds ([1 x i64], [1 x i64]* @.offload_sizes.3, i32 0, i32 0), i64* getelementptr inbounds ([1 x i64], [1 x i64]* @.offload_maptypes.4, i32 0, i32 0), i8** null, i8** null, i32 1, i32 0)
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = icmp ne i32 [[TMP16]], 0
|
|
// CHECK1-NEXT: br i1 [[TMP17]], label [[OMP_OFFLOAD_FAILED4:%.*]], label [[OMP_OFFLOAD_CONT5:%.*]]
|
|
// CHECK1: omp_offload.failed4:
|
|
// CHECK1-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3barv_l55([10 x [10 x [10 x double]]]* [[B]]) #[[ATTR8]]
|
|
// CHECK1-NEXT: br label [[OMP_OFFLOAD_CONT5]]
|
|
// CHECK1: omp_offload.cont5:
|
|
// CHECK1-NEXT: ret i32 0
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@_ZN2S2C1Ev
|
|
// CHECK1-SAME: (%class.S2* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1:[0-9]+]] comdat align 2 {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %class.S2*, align 8
|
|
// CHECK1-NEXT: store %class.S2* [[THIS]], %class.S2** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: [[THIS1:%.*]] = load %class.S2*, %class.S2** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: call void @_ZN2S2C2Ev(%class.S2* noundef nonnull align 4 dereferenceable(4) [[THIS1]])
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3barv_l50
|
|
// CHECK1-SAME: ([5 x %class.S2]* noundef nonnull align 4 dereferenceable(20) [[O:%.*]]) #[[ATTR2:[0-9]+]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[O_ADDR:%.*]] = alloca [5 x %class.S2]*, align 8
|
|
// CHECK1-NEXT: store [5 x %class.S2]* [[O]], [5 x %class.S2]** [[O_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load [5 x %class.S2]*, [5 x %class.S2]** [[O_ADDR]], align 8
|
|
// CHECK1-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB2]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, [5 x %class.S2]*)* @.omp_outlined. to void (i32*, i32*, ...)*), [5 x %class.S2]* [[TMP0]])
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined.
|
|
// CHECK1-SAME: (i32* noalias noundef [[DOTGLOBAL_TID_:%.*]], i32* noalias noundef [[DOTBOUND_TID_:%.*]], [5 x %class.S2]* noundef nonnull align 4 dereferenceable(20) [[O:%.*]]) #[[ATTR3:[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: [[O_ADDR:%.*]] = alloca [5 x %class.S2]*, align 8
|
|
// CHECK1-NEXT: [[O1:%.*]] = alloca [[CLASS_S2:%.*]], 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 [5 x %class.S2]* [[O]], [5 x %class.S2]** [[O_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load [5 x %class.S2]*, [5 x %class.S2]** [[O_ADDR]], align 8
|
|
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [5 x %class.S2], [5 x %class.S2]* [[TMP0]], i64 0, i64 0
|
|
// CHECK1-NEXT: call void @_ZN2S2C1Ev(%class.S2* noundef nonnull align 4 dereferenceable(4) [[O1]])
|
|
// CHECK1-NEXT: [[TMP1:%.*]] = bitcast [5 x %class.S2]* [[TMP0]] to %class.S2*
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = ptrtoint %class.S2* [[TMP1]] to i64
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = ptrtoint %class.S2* [[ARRAYIDX]] to i64
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = sub i64 [[TMP2]], [[TMP3]]
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = sdiv exact i64 [[TMP4]], ptrtoint (%class.S2* getelementptr ([[CLASS_S2]], %class.S2* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr [[CLASS_S2]], %class.S2* [[O1]], i64 [[TMP5]]
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = bitcast %class.S2* [[TMP6]] to [5 x %class.S2]*
|
|
// CHECK1-NEXT: store i32 0, i32* [[I]], align 4
|
|
// CHECK1-NEXT: br label [[FOR_COND:%.*]]
|
|
// CHECK1: for.cond:
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK1-NEXT: [[CMP:%.*]] = icmp slt i32 [[TMP8]], 10
|
|
// CHECK1-NEXT: br i1 [[CMP]], label [[FOR_BODY:%.*]], label [[FOR_END:%.*]]
|
|
// CHECK1: for.body:
|
|
// CHECK1-NEXT: br label [[FOR_INC:%.*]]
|
|
// CHECK1: for.inc:
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK1-NEXT: [[INC:%.*]] = add nsw i32 [[TMP9]], 1
|
|
// CHECK1-NEXT: store i32 [[INC]], i32* [[I]], align 4
|
|
// CHECK1-NEXT: br label [[FOR_COND]], !llvm.loop [[LOOP5:![0-9]+]]
|
|
// CHECK1: for.end:
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = bitcast %class.S2* [[O1]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP11]], i8** [[TMP10]], align 8
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = load i32, i32* [[TMP12]], align 4
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = call i32 @__kmpc_reduce_nowait(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 [[TMP13]], i32 1, i64 8, i8* [[TMP14]], void (i8*, i8*)* @.omp.reduction.reduction_func, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: switch i32 [[TMP15]], 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 noundef nonnull align 4 dereferenceable(4) %class.S2* @_ZN2S2plERS_(%class.S2* noundef nonnull align 4 dereferenceable(4) [[ARRAYIDX]], %class.S2* noundef nonnull align 4 dereferenceable(4) [[O1]])
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = bitcast %class.S2* [[ARRAYIDX]] to i8*
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = bitcast %class.S2* [[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: call void @__kmpc_end_reduce_nowait(%struct.ident_t* @[[GLOB1]], i32 [[TMP13]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.case2:
|
|
// CHECK1-NEXT: [[TMP18:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP19:%.*]] = load i32, i32* [[TMP18]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB2]], i32 [[TMP19]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: [[CALL2:%.*]] = call noundef nonnull align 4 dereferenceable(4) %class.S2* @_ZN2S2plERS_(%class.S2* noundef nonnull align 4 dereferenceable(4) [[ARRAYIDX]], %class.S2* noundef nonnull align 4 dereferenceable(4) [[O1]])
|
|
// CHECK1-NEXT: [[TMP20:%.*]] = bitcast %class.S2* [[ARRAYIDX]] to i8*
|
|
// CHECK1-NEXT: [[TMP21:%.*]] = bitcast %class.S2* [[CALL2]] to i8*
|
|
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP20]], i8* align 4 [[TMP21]], i64 4, i1 false)
|
|
// CHECK1-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB2]], i32 [[TMP19]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.default:
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func
|
|
// CHECK1-SAME: (i8* noundef [[TMP0:%.*]], i8* noundef [[TMP1:%.*]]) #[[ATTR4:[0-9]+]] {
|
|
// 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 %class.S2*
|
|
// 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 %class.S2*
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call noundef nonnull align 4 dereferenceable(4) %class.S2* @_ZN2S2plERS_(%class.S2* noundef nonnull align 4 dereferenceable(4) [[TMP11]], %class.S2* noundef nonnull align 4 dereferenceable(4) [[TMP8]])
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = bitcast %class.S2* [[TMP11]] to i8*
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = bitcast %class.S2* [[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_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3barv_l55
|
|
// CHECK1-SAME: ([10 x [10 x [10 x double]]]* noundef nonnull align 8 dereferenceable(8000) [[B:%.*]]) #[[ATTR2]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[B_ADDR:%.*]] = alloca [10 x [10 x [10 x double]]]*, align 8
|
|
// CHECK1-NEXT: store [10 x [10 x [10 x double]]]* [[B]], [10 x [10 x [10 x double]]]** [[B_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load [10 x [10 x [10 x double]]]*, [10 x [10 x [10 x double]]]** [[B_ADDR]], align 8
|
|
// CHECK1-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB2]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, [10 x [10 x [10 x double]]]*)* @.omp_outlined..1 to void (i32*, i32*, ...)*), [10 x [10 x [10 x double]]]* [[TMP0]])
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined..1
|
|
// CHECK1-SAME: (i32* noalias noundef [[DOTGLOBAL_TID_:%.*]], i32* noalias noundef [[DOTBOUND_TID_:%.*]], [10 x [10 x [10 x double]]]* noundef nonnull align 8 dereferenceable(8000) [[B:%.*]]) #[[ATTR3]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[B_ADDR:%.*]] = alloca [10 x [10 x [10 x double]]]*, align 8
|
|
// CHECK1-NEXT: [[DOTOMP_IV:%.*]] = alloca i64, align 8
|
|
// CHECK1-NEXT: [[TMP:%.*]] = alloca i64, align 8
|
|
// CHECK1-NEXT: [[DOTOMP_LB:%.*]] = alloca i64, align 8
|
|
// CHECK1-NEXT: [[DOTOMP_UB:%.*]] = alloca i64, align 8
|
|
// CHECK1-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i64, align 8
|
|
// 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: [[DOTRD_INPUT_:%.*]] = alloca [1 x %struct.kmp_taskred_input_t], align 8
|
|
// CHECK1-NEXT: [[DOTTASK_RED_:%.*]] = alloca i8*, align 8
|
|
// CHECK1-NEXT: [[I:%.*]] = alloca i64, align 8
|
|
// CHECK1-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [2 x i8*], align 8
|
|
// CHECK1-NEXT: [[ATOMIC_TEMP:%.*]] = alloca double, align 8
|
|
// CHECK1-NEXT: [[_TMP30:%.*]] = alloca double, 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 [10 x [10 x [10 x double]]]* [[B]], [10 x [10 x [10 x double]]]** [[B_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load [10 x [10 x [10 x double]]]*, [10 x [10 x [10 x double]]]** [[B_ADDR]], align 8
|
|
// CHECK1-NEXT: store i64 0, i64* [[DOTOMP_LB]], align 8
|
|
// CHECK1-NEXT: store i64 9, i64* [[DOTOMP_UB]], align 8
|
|
// CHECK1-NEXT: store i64 1, i64* [[DOTOMP_STRIDE]], align 8
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x [10 x [10 x double]]], [10 x [10 x [10 x double]]]* [[TMP0]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[ARRAYDECAY:%.*]] = getelementptr inbounds [10 x [10 x double]], [10 x [10 x double]]* [[ARRAYIDX]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds [10 x double], [10 x double]* [[ARRAYDECAY]], i64 2
|
|
// CHECK1-NEXT: [[ARRAYDECAY2:%.*]] = getelementptr inbounds [10 x double], [10 x double]* [[ARRAYIDX1]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds double, double* [[ARRAYDECAY2]], i64 1
|
|
// CHECK1-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds [10 x [10 x [10 x double]]], [10 x [10 x [10 x double]]]* [[TMP0]], i64 0, i64 1
|
|
// CHECK1-NEXT: [[ARRAYDECAY5:%.*]] = getelementptr inbounds [10 x [10 x double]], [10 x [10 x double]]* [[ARRAYIDX4]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds [10 x double], [10 x double]* [[ARRAYDECAY5]], i64 5
|
|
// CHECK1-NEXT: [[ARRAYDECAY7:%.*]] = getelementptr inbounds [10 x double], [10 x double]* [[ARRAYIDX6]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds double, double* [[ARRAYDECAY7]], i64 1
|
|
// CHECK1-NEXT: [[TMP1:%.*]] = ptrtoint double* [[ARRAYIDX8]] to i64
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = ptrtoint double* [[ARRAYIDX3]] to i64
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = sub i64 [[TMP1]], [[TMP2]]
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = sdiv exact i64 [[TMP3]], ptrtoint (double* getelementptr (double, double* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = add nuw i64 [[TMP4]], 1
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = mul nuw i64 [[TMP5]], ptrtoint (double* getelementptr (double, double* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = call i8* @llvm.stacksave()
|
|
// CHECK1-NEXT: store i8* [[TMP7]], i8** [[SAVED_STACK]], align 8
|
|
// CHECK1-NEXT: [[VLA:%.*]] = alloca double, i64 [[TMP5]], align 8
|
|
// CHECK1-NEXT: store i64 [[TMP5]], i64* [[__VLA_EXPR0]], align 8
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = getelementptr double, double* [[VLA]], i64 [[TMP5]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq double* [[VLA]], [[TMP8]]
|
|
// 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 double* [ [[VLA]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
|
|
// CHECK1-NEXT: store double 0.000000e+00, double* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 8
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr double, double* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq double* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP8]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK1: omp.arrayinit.done:
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = bitcast [10 x [10 x [10 x double]]]* [[TMP0]] to double*
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = ptrtoint double* [[TMP9]] to i64
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = ptrtoint double* [[ARRAYIDX3]] to i64
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = sub i64 [[TMP10]], [[TMP11]]
|
|
// CHECK1-NEXT: [[TMP13:%.*]] = sdiv exact i64 [[TMP12]], ptrtoint (double* getelementptr (double, double* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[TMP14:%.*]] = getelementptr double, double* [[VLA]], i64 [[TMP13]]
|
|
// CHECK1-NEXT: [[TMP15:%.*]] = bitcast double* [[TMP14]] to [10 x [10 x [10 x double]]]*
|
|
// CHECK1-NEXT: [[DOTRD_INPUT_GEP_:%.*]] = getelementptr inbounds [1 x %struct.kmp_taskred_input_t], [1 x %struct.kmp_taskred_input_t]* [[DOTRD_INPUT_]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T:%.*]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_]], i32 0, i32 0
|
|
// CHECK1-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds [10 x [10 x [10 x double]]], [10 x [10 x [10 x double]]]* [[TMP0]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[ARRAYDECAY10:%.*]] = getelementptr inbounds [10 x [10 x double]], [10 x [10 x double]]* [[ARRAYIDX9]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[ARRAYIDX11:%.*]] = getelementptr inbounds [10 x double], [10 x double]* [[ARRAYDECAY10]], i64 2
|
|
// CHECK1-NEXT: [[ARRAYDECAY12:%.*]] = getelementptr inbounds [10 x double], [10 x double]* [[ARRAYIDX11]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[ARRAYIDX13:%.*]] = getelementptr inbounds double, double* [[ARRAYDECAY12]], i64 1
|
|
// CHECK1-NEXT: [[ARRAYIDX14:%.*]] = getelementptr inbounds [10 x [10 x [10 x double]]], [10 x [10 x [10 x double]]]* [[TMP0]], i64 0, i64 1
|
|
// CHECK1-NEXT: [[ARRAYDECAY15:%.*]] = getelementptr inbounds [10 x [10 x double]], [10 x [10 x double]]* [[ARRAYIDX14]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[ARRAYIDX16:%.*]] = getelementptr inbounds [10 x double], [10 x double]* [[ARRAYDECAY15]], i64 5
|
|
// CHECK1-NEXT: [[ARRAYDECAY17:%.*]] = getelementptr inbounds [10 x double], [10 x double]* [[ARRAYIDX16]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[ARRAYIDX18:%.*]] = getelementptr inbounds double, double* [[ARRAYDECAY17]], i64 1
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = bitcast double* [[VLA]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP17]], i8** [[TMP16]], align 8
|
|
// CHECK1-NEXT: [[TMP18:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_]], i32 0, i32 1
|
|
// CHECK1-NEXT: [[TMP19:%.*]] = bitcast double* [[ARRAYIDX13]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP19]], i8** [[TMP18]], align 8
|
|
// CHECK1-NEXT: [[TMP20:%.*]] = ptrtoint double* [[ARRAYIDX18]] to i64
|
|
// CHECK1-NEXT: [[TMP21:%.*]] = ptrtoint double* [[ARRAYIDX13]] to i64
|
|
// CHECK1-NEXT: [[TMP22:%.*]] = sub i64 [[TMP20]], [[TMP21]]
|
|
// CHECK1-NEXT: [[TMP23:%.*]] = sdiv exact i64 [[TMP22]], ptrtoint (double* getelementptr (double, double* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[TMP24:%.*]] = add nuw i64 [[TMP23]], 1
|
|
// CHECK1-NEXT: [[TMP25:%.*]] = mul nuw i64 [[TMP24]], ptrtoint (double* getelementptr (double, double* null, i32 1) to i64)
|
|
// CHECK1-NEXT: [[TMP26:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_]], i32 0, i32 2
|
|
// CHECK1-NEXT: store i64 [[TMP25]], i64* [[TMP26]], align 8
|
|
// CHECK1-NEXT: [[TMP27:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_]], i32 0, i32 3
|
|
// CHECK1-NEXT: store i8* bitcast (void (i8*, i8*)* @.red_init. to i8*), i8** [[TMP27]], align 8
|
|
// CHECK1-NEXT: [[TMP28:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_]], i32 0, i32 4
|
|
// CHECK1-NEXT: store i8* null, i8** [[TMP28]], align 8
|
|
// CHECK1-NEXT: [[TMP29:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_]], i32 0, i32 5
|
|
// CHECK1-NEXT: store i8* bitcast (void (i8*, i8*)* @.red_comb. to i8*), i8** [[TMP29]], align 8
|
|
// CHECK1-NEXT: [[TMP30:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_]], i32 0, i32 6
|
|
// CHECK1-NEXT: store i32 1, i32* [[TMP30]], align 8
|
|
// CHECK1-NEXT: [[TMP31:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP32:%.*]] = load i32, i32* [[TMP31]], align 4
|
|
// CHECK1-NEXT: [[TMP33:%.*]] = bitcast [1 x %struct.kmp_taskred_input_t]* [[DOTRD_INPUT_]] to i8*
|
|
// CHECK1-NEXT: [[TMP34:%.*]] = call i8* @__kmpc_taskred_modifier_init(%struct.ident_t* @[[GLOB2]], i32 [[TMP32]], i32 1, i32 1, i8* [[TMP33]])
|
|
// CHECK1-NEXT: store i8* [[TMP34]], i8** [[DOTTASK_RED_]], align 8
|
|
// CHECK1-NEXT: [[TMP35:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP36:%.*]] = load i32, i32* [[TMP35]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_init_8(%struct.ident_t* @[[GLOB3:[0-9]+]], i32 [[TMP36]], i32 34, i32* [[DOTOMP_IS_LAST]], i64* [[DOTOMP_LB]], i64* [[DOTOMP_UB]], i64* [[DOTOMP_STRIDE]], i64 1, i64 1)
|
|
// CHECK1-NEXT: [[TMP37:%.*]] = load i64, i64* [[DOTOMP_UB]], align 8
|
|
// CHECK1-NEXT: [[CMP:%.*]] = icmp sgt i64 [[TMP37]], 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: [[TMP38:%.*]] = load i64, i64* [[DOTOMP_UB]], align 8
|
|
// CHECK1-NEXT: br label [[COND_END]]
|
|
// CHECK1: cond.end:
|
|
// CHECK1-NEXT: [[COND:%.*]] = phi i64 [ 9, [[COND_TRUE]] ], [ [[TMP38]], [[COND_FALSE]] ]
|
|
// CHECK1-NEXT: store i64 [[COND]], i64* [[DOTOMP_UB]], align 8
|
|
// CHECK1-NEXT: [[TMP39:%.*]] = load i64, i64* [[DOTOMP_LB]], align 8
|
|
// CHECK1-NEXT: store i64 [[TMP39]], i64* [[DOTOMP_IV]], align 8
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK1: omp.inner.for.cond:
|
|
// CHECK1-NEXT: [[TMP40:%.*]] = load i64, i64* [[DOTOMP_IV]], align 8
|
|
// CHECK1-NEXT: [[TMP41:%.*]] = load i64, i64* [[DOTOMP_UB]], align 8
|
|
// CHECK1-NEXT: [[CMP19:%.*]] = icmp sle i64 [[TMP40]], [[TMP41]]
|
|
// 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: [[TMP42:%.*]] = load i64, i64* [[DOTOMP_IV]], align 8
|
|
// CHECK1-NEXT: [[MUL:%.*]] = mul nsw i64 [[TMP42]], 1
|
|
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i64 0, [[MUL]]
|
|
// CHECK1-NEXT: store i64 [[ADD]], i64* [[I]], align 8
|
|
// 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: [[TMP43:%.*]] = load i64, i64* [[DOTOMP_IV]], align 8
|
|
// CHECK1-NEXT: [[ADD20:%.*]] = add nsw i64 [[TMP43]], 1
|
|
// CHECK1-NEXT: store i64 [[ADD20]], i64* [[DOTOMP_IV]], align 8
|
|
// 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: [[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_fini(%struct.ident_t* @[[GLOB3]], i32 [[TMP45]])
|
|
// CHECK1-NEXT: [[TMP46:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP47:%.*]] = load i32, i32* [[TMP46]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_task_reduction_modifier_fini(%struct.ident_t* @[[GLOB2]], i32 [[TMP47]], i32 1)
|
|
// CHECK1-NEXT: [[TMP48:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
|
|
// CHECK1-NEXT: [[TMP49:%.*]] = bitcast double* [[VLA]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP49]], i8** [[TMP48]], align 8
|
|
// CHECK1-NEXT: [[TMP50:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 1
|
|
// CHECK1-NEXT: [[TMP51:%.*]] = inttoptr i64 [[TMP5]] to i8*
|
|
// CHECK1-NEXT: store i8* [[TMP51]], i8** [[TMP50]], align 8
|
|
// CHECK1-NEXT: [[TMP52:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP53:%.*]] = load i32, i32* [[TMP52]], align 4
|
|
// CHECK1-NEXT: [[TMP54:%.*]] = bitcast [2 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK1-NEXT: [[TMP55:%.*]] = call i32 @__kmpc_reduce_nowait(%struct.ident_t* @[[GLOB1]], i32 [[TMP53]], i32 1, i64 16, i8* [[TMP54]], void (i8*, i8*)* @.omp.reduction.reduction_func.2, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: switch i32 [[TMP55]], 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: [[TMP56:%.*]] = getelementptr double, double* [[ARRAYIDX3]], i64 [[TMP5]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq double* [[ARRAYIDX3]], [[TMP56]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE25:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
|
|
// CHECK1: omp.arraycpy.body:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi double* [ [[VLA]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST21:%.*]] = phi double* [ [[ARRAYIDX3]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT23:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[TMP57:%.*]] = load double, double* [[OMP_ARRAYCPY_DESTELEMENTPAST21]], align 8
|
|
// CHECK1-NEXT: [[TMP58:%.*]] = load double, double* [[OMP_ARRAYCPY_SRCELEMENTPAST]], align 8
|
|
// CHECK1-NEXT: [[ADD22:%.*]] = fadd double [[TMP57]], [[TMP58]]
|
|
// CHECK1-NEXT: store double [[ADD22]], double* [[OMP_ARRAYCPY_DESTELEMENTPAST21]], align 8
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT23]] = getelementptr double, double* [[OMP_ARRAYCPY_DESTELEMENTPAST21]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr double, double* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE24:%.*]] = icmp eq double* [[OMP_ARRAYCPY_DEST_ELEMENT23]], [[TMP56]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE24]], label [[OMP_ARRAYCPY_DONE25]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK1: omp.arraycpy.done25:
|
|
// CHECK1-NEXT: call void @__kmpc_end_reduce_nowait(%struct.ident_t* @[[GLOB1]], i32 [[TMP53]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.case2:
|
|
// CHECK1-NEXT: [[TMP59:%.*]] = getelementptr double, double* [[ARRAYIDX3]], i64 [[TMP5]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY26:%.*]] = icmp eq double* [[ARRAYIDX3]], [[TMP59]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY26]], label [[OMP_ARRAYCPY_DONE35:%.*]], label [[OMP_ARRAYCPY_BODY27:%.*]]
|
|
// CHECK1: omp.arraycpy.body27:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST28:%.*]] = phi double* [ [[VLA]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT33:%.*]], [[ATOMIC_EXIT:%.*]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST29:%.*]] = phi double* [ [[ARRAYIDX3]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT32:%.*]], [[ATOMIC_EXIT]] ]
|
|
// CHECK1-NEXT: [[TMP60:%.*]] = load double, double* [[OMP_ARRAYCPY_SRCELEMENTPAST28]], align 8
|
|
// CHECK1-NEXT: [[TMP61:%.*]] = bitcast double* [[OMP_ARRAYCPY_DESTELEMENTPAST29]] to i64*
|
|
// CHECK1-NEXT: [[ATOMIC_LOAD:%.*]] = load atomic i64, i64* [[TMP61]] monotonic, align 8
|
|
// CHECK1-NEXT: br label [[ATOMIC_CONT:%.*]]
|
|
// CHECK1: atomic_cont:
|
|
// CHECK1-NEXT: [[TMP62:%.*]] = phi i64 [ [[ATOMIC_LOAD]], [[OMP_ARRAYCPY_BODY27]] ], [ [[TMP70:%.*]], [[ATOMIC_CONT]] ]
|
|
// CHECK1-NEXT: [[TMP63:%.*]] = bitcast double* [[ATOMIC_TEMP]] to i64*
|
|
// CHECK1-NEXT: [[TMP64:%.*]] = bitcast i64 [[TMP62]] to double
|
|
// CHECK1-NEXT: store double [[TMP64]], double* [[_TMP30]], align 8
|
|
// CHECK1-NEXT: [[TMP65:%.*]] = load double, double* [[_TMP30]], align 8
|
|
// CHECK1-NEXT: [[TMP66:%.*]] = load double, double* [[OMP_ARRAYCPY_SRCELEMENTPAST28]], align 8
|
|
// CHECK1-NEXT: [[ADD31:%.*]] = fadd double [[TMP65]], [[TMP66]]
|
|
// CHECK1-NEXT: store double [[ADD31]], double* [[ATOMIC_TEMP]], align 8
|
|
// CHECK1-NEXT: [[TMP67:%.*]] = load i64, i64* [[TMP63]], align 8
|
|
// CHECK1-NEXT: [[TMP68:%.*]] = bitcast double* [[OMP_ARRAYCPY_DESTELEMENTPAST29]] to i64*
|
|
// CHECK1-NEXT: [[TMP69:%.*]] = cmpxchg i64* [[TMP68]], i64 [[TMP62]], i64 [[TMP67]] monotonic monotonic, align 8
|
|
// CHECK1-NEXT: [[TMP70]] = extractvalue { i64, i1 } [[TMP69]], 0
|
|
// CHECK1-NEXT: [[TMP71:%.*]] = extractvalue { i64, i1 } [[TMP69]], 1
|
|
// CHECK1-NEXT: br i1 [[TMP71]], label [[ATOMIC_EXIT]], label [[ATOMIC_CONT]]
|
|
// CHECK1: atomic_exit:
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT32]] = getelementptr double, double* [[OMP_ARRAYCPY_DESTELEMENTPAST29]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT33]] = getelementptr double, double* [[OMP_ARRAYCPY_SRCELEMENTPAST28]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE34:%.*]] = icmp eq double* [[OMP_ARRAYCPY_DEST_ELEMENT32]], [[TMP59]]
|
|
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE34]], label [[OMP_ARRAYCPY_DONE35]], label [[OMP_ARRAYCPY_BODY27]]
|
|
// CHECK1: omp.arraycpy.done35:
|
|
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK1: .omp.reduction.default:
|
|
// CHECK1-NEXT: [[TMP72:%.*]] = load i8*, i8** [[SAVED_STACK]], align 8
|
|
// CHECK1-NEXT: call void @llvm.stackrestore(i8* [[TMP72]])
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.red_init.
|
|
// CHECK1-SAME: (i8* noalias noundef [[TMP0:%.*]], i8* noalias noundef [[TMP1:%.*]]) #[[ATTR4]] {
|
|
// 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:%.*]] = bitcast i8** [[DOTADDR]] to double**
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = load double*, double** [[TMP2]], align 8
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load i64, i64* @{{reduction_size[.].+[.]}}, align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = getelementptr double, double* [[TMP3]], i64 [[TMP4]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq double* [[TMP3]], [[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 double* [ [[TMP3]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
|
|
// CHECK1-NEXT: store double 0.000000e+00, double* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 8
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr double, double* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq double* [[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: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.red_comb.
|
|
// CHECK1-SAME: (i8* noundef [[TMP0:%.*]], i8* noundef [[TMP1:%.*]]) #[[ATTR4]] {
|
|
// 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 i64, i64* @{{reduction_size[.].+[.]}}, align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = bitcast i8** [[DOTADDR]] to double**
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load double*, double** [[TMP3]], align 8
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = bitcast i8** [[DOTADDR1]] to double**
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = load double*, double** [[TMP5]], align 8
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = getelementptr double, double* [[TMP4]], i64 [[TMP2]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq double* [[TMP4]], [[TMP7]]
|
|
// 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 double* [ [[TMP6]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi double* [ [[TMP4]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = load double, double* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 8
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = load double, double* [[OMP_ARRAYCPY_SRCELEMENTPAST]], align 8
|
|
// CHECK1-NEXT: [[ADD:%.*]] = fadd double [[TMP8]], [[TMP9]]
|
|
// CHECK1-NEXT: store double [[ADD]], double* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 8
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr double, double* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr double, double* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq double* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP7]]
|
|
// 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.reduction.reduction_func.2
|
|
// CHECK1-SAME: (i8* noundef [[TMP0:%.*]], i8* noundef [[TMP1:%.*]]) #[[ATTR4]] {
|
|
// 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 double*
|
|
// 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 double*
|
|
// 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 double, double* [[TMP11]], i64 [[TMP14]]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq double* [[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 double* [ [[TMP8]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi double* [ [[TMP11]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK1-NEXT: [[TMP16:%.*]] = load double, double* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 8
|
|
// CHECK1-NEXT: [[TMP17:%.*]] = load double, double* [[OMP_ARRAYCPY_SRCELEMENTPAST]], align 8
|
|
// CHECK1-NEXT: [[ADD:%.*]] = fadd double [[TMP16]], [[TMP17]]
|
|
// CHECK1-NEXT: store double [[ADD]], double* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 8
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr double, double* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr double, double* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq double* [[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 {{[^@]+}}@_ZN2S2C2Ev
|
|
// CHECK1-SAME: (%class.S2* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %class.S2*, align 8
|
|
// CHECK1-NEXT: store %class.S2* [[THIS]], %class.S2** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: [[THIS1:%.*]] = load %class.S2*, %class.S2** [[THIS_ADDR]], align 8
|
|
// CHECK1-NEXT: [[A:%.*]] = getelementptr inbounds [[CLASS_S2:%.*]], %class.S2* [[THIS1]], i32 0, i32 0
|
|
// CHECK1-NEXT: store i32 0, i32* [[A]], align 4
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@main
|
|
// CHECK1-SAME: () #[[ATTR10:[0-9]+]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[A:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: store i32 0, i32* [[RETVAL]], align 4
|
|
// CHECK1-NEXT: [[CALL:%.*]] = call noundef signext i32 @_Z3barv()
|
|
// CHECK1-NEXT: store i32 [[CALL]], i32* [[A]], align 4
|
|
// CHECK1-NEXT: ret i32 0
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp_offloading.requires_reg
|
|
// CHECK1-SAME: () #[[ATTR11:[0-9]+]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: call void @__tgt_register_requires(i64 1)
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@_Z3sumPiiS_
|
|
// CHECK2-SAME: (i32* noundef [[INPUT:%.*]], i32 noundef [[SIZE:%.*]], i32* noundef [[OUTPUT:%.*]]) #[[ATTR0:[0-9]+]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[INPUT_ADDR:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[SIZE_ADDR:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[OUTPUT_ADDR:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[SIZE_CASTED:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOFFLOAD_BASEPTRS:%.*]] = alloca [3 x i8*], align 4
|
|
// CHECK2-NEXT: [[DOTOFFLOAD_PTRS:%.*]] = alloca [3 x i8*], align 4
|
|
// CHECK2-NEXT: [[DOTOFFLOAD_MAPPERS:%.*]] = alloca [3 x i8*], align 4
|
|
// CHECK2-NEXT: [[DOTOFFLOAD_SIZES:%.*]] = alloca [3 x i64], align 4
|
|
// CHECK2-NEXT: [[TMP:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTCAPTURE_EXPR_:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTCAPTURE_EXPR_2:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[SIZE_CASTED4:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOFFLOAD_BASEPTRS7:%.*]] = alloca [3 x i8*], align 4
|
|
// CHECK2-NEXT: [[DOTOFFLOAD_PTRS8:%.*]] = alloca [3 x i8*], align 4
|
|
// CHECK2-NEXT: [[DOTOFFLOAD_MAPPERS9:%.*]] = alloca [3 x i8*], align 4
|
|
// CHECK2-NEXT: [[DOTOFFLOAD_SIZES10:%.*]] = alloca [3 x i64], align 4
|
|
// CHECK2-NEXT: [[_TMP11:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTCAPTURE_EXPR_12:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTCAPTURE_EXPR_13:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[A:%.*]] = alloca [10 x i32], align 4
|
|
// CHECK2-NEXT: [[SIZE_CASTED20:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOFFLOAD_BASEPTRS22:%.*]] = alloca [2 x i8*], align 4
|
|
// CHECK2-NEXT: [[DOTOFFLOAD_PTRS23:%.*]] = alloca [2 x i8*], align 4
|
|
// CHECK2-NEXT: [[DOTOFFLOAD_MAPPERS24:%.*]] = alloca [2 x i8*], align 4
|
|
// CHECK2-NEXT: [[SIZE_CASTED27:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOFFLOAD_BASEPTRS29:%.*]] = alloca [2 x i8*], align 4
|
|
// CHECK2-NEXT: [[DOTOFFLOAD_PTRS30:%.*]] = alloca [2 x i8*], align 4
|
|
// CHECK2-NEXT: [[DOTOFFLOAD_MAPPERS31:%.*]] = alloca [2 x i8*], align 4
|
|
// CHECK2-NEXT: store i32* [[INPUT]], i32** [[INPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[SIZE]], i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32* [[OUTPUT]], i32** [[OUTPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load i32, i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP0]], i32* [[SIZE_CASTED]], align 4
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = load i32, i32* [[SIZE_CASTED]], align 4
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i32*, i32** [[OUTPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = load i32*, i32** [[INPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i32*, i32** [[OUTPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = load i32*, i32** [[OUTPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[TMP5]], i32 0
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = load i32*, i32** [[INPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i32*, i32** [[INPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, i32* [[TMP7]], i32 0
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = load i32, i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = mul nuw i32 [[TMP8]], 4
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = sext i32 [[TMP9]] to i64
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast [3 x i64]* [[DOTOFFLOAD_SIZES]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 [[TMP11]], i8* align 4 bitcast ([3 x i64]* @.offload_sizes to i8*), i32 24, i1 false)
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = bitcast i8** [[TMP12]] to i32*
|
|
// CHECK2-NEXT: store i32 [[TMP1]], i32* [[TMP13]], align 4
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = bitcast i8** [[TMP14]] to i32*
|
|
// CHECK2-NEXT: store i32 [[TMP1]], i32* [[TMP15]], align 4
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOFFLOAD_MAPPERS]], i32 0, i32 0
|
|
// CHECK2-NEXT: store i8* null, i8** [[TMP16]], align 4
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 1
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = bitcast i8** [[TMP17]] to i32**
|
|
// CHECK2-NEXT: store i32* [[TMP4]], i32** [[TMP18]], align 4
|
|
// CHECK2-NEXT: [[TMP19:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 1
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = bitcast i8** [[TMP19]] to i32**
|
|
// CHECK2-NEXT: store i32* [[ARRAYIDX]], i32** [[TMP20]], align 4
|
|
// CHECK2-NEXT: [[TMP21:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOFFLOAD_MAPPERS]], i32 0, i32 1
|
|
// CHECK2-NEXT: store i8* null, i8** [[TMP21]], align 4
|
|
// CHECK2-NEXT: [[TMP22:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 2
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = bitcast i8** [[TMP22]] to i32**
|
|
// CHECK2-NEXT: store i32* [[TMP6]], i32** [[TMP23]], align 4
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 2
|
|
// CHECK2-NEXT: [[TMP25:%.*]] = bitcast i8** [[TMP24]] to i32**
|
|
// CHECK2-NEXT: store i32* [[ARRAYIDX1]], i32** [[TMP25]], align 4
|
|
// CHECK2-NEXT: [[TMP26:%.*]] = getelementptr inbounds [3 x i64], [3 x i64]* [[DOTOFFLOAD_SIZES]], i32 0, i32 2
|
|
// CHECK2-NEXT: store i64 [[TMP10]], i64* [[TMP26]], align 4
|
|
// CHECK2-NEXT: [[TMP27:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOFFLOAD_MAPPERS]], i32 0, i32 2
|
|
// CHECK2-NEXT: store i8* null, i8** [[TMP27]], align 4
|
|
// CHECK2-NEXT: [[TMP28:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP29:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP30:%.*]] = getelementptr inbounds [3 x i64], [3 x i64]* [[DOTOFFLOAD_SIZES]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP31:%.*]] = load i32, i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP31]], i32* [[DOTCAPTURE_EXPR_]], align 4
|
|
// CHECK2-NEXT: [[TMP32:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_]], align 4
|
|
// CHECK2-NEXT: [[SUB:%.*]] = sub nsw i32 [[TMP32]], 0
|
|
// CHECK2-NEXT: [[DIV:%.*]] = sdiv i32 [[SUB]], 1
|
|
// CHECK2-NEXT: [[SUB3:%.*]] = sub nsw i32 [[DIV]], 1
|
|
// CHECK2-NEXT: store i32 [[SUB3]], i32* [[DOTCAPTURE_EXPR_2]], align 4
|
|
// CHECK2-NEXT: [[TMP33:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_2]], align 4
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP33]], 1
|
|
// CHECK2-NEXT: [[TMP34:%.*]] = zext i32 [[ADD]] to i64
|
|
// CHECK2-NEXT: call void @__kmpc_push_target_tripcount_mapper(%struct.ident_t* @[[GLOB4:[0-9]+]], i64 -1, i64 [[TMP34]])
|
|
// CHECK2-NEXT: [[TMP35:%.*]] = call i32 @__tgt_target_teams_mapper(%struct.ident_t* @[[GLOB4]], i64 -1, i8* @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3sumPiiS__l69.region_id, i32 3, i8** [[TMP28]], i8** [[TMP29]], i64* [[TMP30]], i64* getelementptr inbounds ([3 x i64], [3 x i64]* @.offload_maptypes, i32 0, i32 0), i8** null, i8** null, i32 0, i32 0)
|
|
// CHECK2-NEXT: [[TMP36:%.*]] = icmp ne i32 [[TMP35]], 0
|
|
// CHECK2-NEXT: br i1 [[TMP36]], label [[OMP_OFFLOAD_FAILED:%.*]], label [[OMP_OFFLOAD_CONT:%.*]]
|
|
// CHECK2: omp_offload.failed:
|
|
// CHECK2-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3sumPiiS__l69(i32 [[TMP1]], i32* [[TMP2]], i32* [[TMP3]]) #[[ATTR2:[0-9]+]]
|
|
// CHECK2-NEXT: br label [[OMP_OFFLOAD_CONT]]
|
|
// CHECK2: omp_offload.cont:
|
|
// CHECK2-NEXT: [[TMP37:%.*]] = load i32, i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP37]], i32* [[SIZE_CASTED4]], align 4
|
|
// CHECK2-NEXT: [[TMP38:%.*]] = load i32, i32* [[SIZE_CASTED4]], align 4
|
|
// CHECK2-NEXT: [[TMP39:%.*]] = load i32*, i32** [[OUTPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP40:%.*]] = load i32*, i32** [[INPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP41:%.*]] = load i32*, i32** [[OUTPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP42:%.*]] = load i32*, i32** [[OUTPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds i32, i32* [[TMP42]], i32 0
|
|
// CHECK2-NEXT: [[TMP43:%.*]] = load i32*, i32** [[INPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP44:%.*]] = load i32*, i32** [[INPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds i32, i32* [[TMP44]], i32 0
|
|
// CHECK2-NEXT: [[TMP45:%.*]] = load i32, i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP46:%.*]] = mul nuw i32 [[TMP45]], 4
|
|
// CHECK2-NEXT: [[TMP47:%.*]] = sext i32 [[TMP46]] to i64
|
|
// CHECK2-NEXT: [[TMP48:%.*]] = bitcast [3 x i64]* [[DOTOFFLOAD_SIZES10]] to i8*
|
|
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 [[TMP48]], i8* align 4 bitcast ([3 x i64]* @.offload_sizes.7 to i8*), i32 24, i1 false)
|
|
// CHECK2-NEXT: [[TMP49:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOFFLOAD_BASEPTRS7]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP50:%.*]] = bitcast i8** [[TMP49]] to i32*
|
|
// CHECK2-NEXT: store i32 [[TMP38]], i32* [[TMP50]], align 4
|
|
// CHECK2-NEXT: [[TMP51:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOFFLOAD_PTRS8]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP52:%.*]] = bitcast i8** [[TMP51]] to i32*
|
|
// CHECK2-NEXT: store i32 [[TMP38]], i32* [[TMP52]], align 4
|
|
// CHECK2-NEXT: [[TMP53:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOFFLOAD_MAPPERS9]], i32 0, i32 0
|
|
// CHECK2-NEXT: store i8* null, i8** [[TMP53]], align 4
|
|
// CHECK2-NEXT: [[TMP54:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOFFLOAD_BASEPTRS7]], i32 0, i32 1
|
|
// CHECK2-NEXT: [[TMP55:%.*]] = bitcast i8** [[TMP54]] to i32**
|
|
// CHECK2-NEXT: store i32* [[TMP41]], i32** [[TMP55]], align 4
|
|
// CHECK2-NEXT: [[TMP56:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOFFLOAD_PTRS8]], i32 0, i32 1
|
|
// CHECK2-NEXT: [[TMP57:%.*]] = bitcast i8** [[TMP56]] to i32**
|
|
// CHECK2-NEXT: store i32* [[ARRAYIDX5]], i32** [[TMP57]], align 4
|
|
// CHECK2-NEXT: [[TMP58:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOFFLOAD_MAPPERS9]], i32 0, i32 1
|
|
// CHECK2-NEXT: store i8* null, i8** [[TMP58]], align 4
|
|
// CHECK2-NEXT: [[TMP59:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOFFLOAD_BASEPTRS7]], i32 0, i32 2
|
|
// CHECK2-NEXT: [[TMP60:%.*]] = bitcast i8** [[TMP59]] to i32**
|
|
// CHECK2-NEXT: store i32* [[TMP43]], i32** [[TMP60]], align 4
|
|
// CHECK2-NEXT: [[TMP61:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOFFLOAD_PTRS8]], i32 0, i32 2
|
|
// CHECK2-NEXT: [[TMP62:%.*]] = bitcast i8** [[TMP61]] to i32**
|
|
// CHECK2-NEXT: store i32* [[ARRAYIDX6]], i32** [[TMP62]], align 4
|
|
// CHECK2-NEXT: [[TMP63:%.*]] = getelementptr inbounds [3 x i64], [3 x i64]* [[DOTOFFLOAD_SIZES10]], i32 0, i32 2
|
|
// CHECK2-NEXT: store i64 [[TMP47]], i64* [[TMP63]], align 4
|
|
// CHECK2-NEXT: [[TMP64:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOFFLOAD_MAPPERS9]], i32 0, i32 2
|
|
// CHECK2-NEXT: store i8* null, i8** [[TMP64]], align 4
|
|
// CHECK2-NEXT: [[TMP65:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOFFLOAD_BASEPTRS7]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP66:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOFFLOAD_PTRS8]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP67:%.*]] = getelementptr inbounds [3 x i64], [3 x i64]* [[DOTOFFLOAD_SIZES10]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP68:%.*]] = load i32, i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP68]], i32* [[DOTCAPTURE_EXPR_12]], align 4
|
|
// CHECK2-NEXT: [[TMP69:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_12]], align 4
|
|
// CHECK2-NEXT: [[SUB14:%.*]] = sub nsw i32 [[TMP69]], 0
|
|
// CHECK2-NEXT: [[DIV15:%.*]] = sdiv i32 [[SUB14]], 1
|
|
// CHECK2-NEXT: [[SUB16:%.*]] = sub nsw i32 [[DIV15]], 1
|
|
// CHECK2-NEXT: store i32 [[SUB16]], i32* [[DOTCAPTURE_EXPR_13]], align 4
|
|
// CHECK2-NEXT: [[TMP70:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_13]], align 4
|
|
// CHECK2-NEXT: [[ADD17:%.*]] = add nsw i32 [[TMP70]], 1
|
|
// CHECK2-NEXT: [[TMP71:%.*]] = zext i32 [[ADD17]] to i64
|
|
// CHECK2-NEXT: call void @__kmpc_push_target_tripcount_mapper(%struct.ident_t* @[[GLOB4]], i64 -1, i64 [[TMP71]])
|
|
// CHECK2-NEXT: [[TMP72:%.*]] = call i32 @__tgt_target_teams_mapper(%struct.ident_t* @[[GLOB4]], i64 -1, i8* @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3sumPiiS__l73.region_id, i32 3, i8** [[TMP65]], i8** [[TMP66]], i64* [[TMP67]], i64* getelementptr inbounds ([3 x i64], [3 x i64]* @.offload_maptypes.8, i32 0, i32 0), i8** null, i8** null, i32 0, i32 0)
|
|
// CHECK2-NEXT: [[TMP73:%.*]] = icmp ne i32 [[TMP72]], 0
|
|
// CHECK2-NEXT: br i1 [[TMP73]], label [[OMP_OFFLOAD_FAILED18:%.*]], label [[OMP_OFFLOAD_CONT19:%.*]]
|
|
// CHECK2: omp_offload.failed18:
|
|
// CHECK2-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3sumPiiS__l73(i32 [[TMP38]], i32* [[TMP39]], i32* [[TMP40]]) #[[ATTR2]]
|
|
// CHECK2-NEXT: br label [[OMP_OFFLOAD_CONT19]]
|
|
// CHECK2: omp_offload.cont19:
|
|
// CHECK2-NEXT: [[TMP74:%.*]] = load i32, i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP74]], i32* [[SIZE_CASTED20]], align 4
|
|
// CHECK2-NEXT: [[TMP75:%.*]] = load i32, i32* [[SIZE_CASTED20]], align 4
|
|
// CHECK2-NEXT: [[ARRAYIDX21:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[A]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP76:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOFFLOAD_BASEPTRS22]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP77:%.*]] = bitcast i8** [[TMP76]] to i32*
|
|
// CHECK2-NEXT: store i32 [[TMP75]], i32* [[TMP77]], align 4
|
|
// CHECK2-NEXT: [[TMP78:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOFFLOAD_PTRS23]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP79:%.*]] = bitcast i8** [[TMP78]] to i32*
|
|
// CHECK2-NEXT: store i32 [[TMP75]], i32* [[TMP79]], align 4
|
|
// CHECK2-NEXT: [[TMP80:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOFFLOAD_MAPPERS24]], i32 0, i32 0
|
|
// CHECK2-NEXT: store i8* null, i8** [[TMP80]], align 4
|
|
// CHECK2-NEXT: [[TMP81:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOFFLOAD_BASEPTRS22]], i32 0, i32 1
|
|
// CHECK2-NEXT: [[TMP82:%.*]] = bitcast i8** [[TMP81]] to [10 x i32]**
|
|
// CHECK2-NEXT: store [10 x i32]* [[A]], [10 x i32]** [[TMP82]], align 4
|
|
// CHECK2-NEXT: [[TMP83:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOFFLOAD_PTRS23]], i32 0, i32 1
|
|
// CHECK2-NEXT: [[TMP84:%.*]] = bitcast i8** [[TMP83]] to i32**
|
|
// CHECK2-NEXT: store i32* [[ARRAYIDX21]], i32** [[TMP84]], align 4
|
|
// CHECK2-NEXT: [[TMP85:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOFFLOAD_MAPPERS24]], i32 0, i32 1
|
|
// CHECK2-NEXT: store i8* null, i8** [[TMP85]], align 4
|
|
// CHECK2-NEXT: [[TMP86:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOFFLOAD_BASEPTRS22]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP87:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOFFLOAD_PTRS23]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP88:%.*]] = call i32 @__tgt_target_teams_mapper(%struct.ident_t* @[[GLOB4]], i64 -1, i8* @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3sumPiiS__l78.region_id, i32 2, i8** [[TMP86]], i8** [[TMP87]], i64* getelementptr inbounds ([2 x i64], [2 x i64]* @.offload_sizes.11, i32 0, i32 0), i64* getelementptr inbounds ([2 x i64], [2 x i64]* @.offload_maptypes.12, i32 0, i32 0), i8** null, i8** null, i32 1, i32 0)
|
|
// CHECK2-NEXT: [[TMP89:%.*]] = icmp ne i32 [[TMP88]], 0
|
|
// CHECK2-NEXT: br i1 [[TMP89]], label [[OMP_OFFLOAD_FAILED25:%.*]], label [[OMP_OFFLOAD_CONT26:%.*]]
|
|
// CHECK2: omp_offload.failed25:
|
|
// CHECK2-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3sumPiiS__l78(i32 [[TMP75]], [10 x i32]* [[A]]) #[[ATTR2]]
|
|
// CHECK2-NEXT: br label [[OMP_OFFLOAD_CONT26]]
|
|
// CHECK2: omp_offload.cont26:
|
|
// CHECK2-NEXT: [[TMP90:%.*]] = load i32, i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP90]], i32* [[SIZE_CASTED27]], align 4
|
|
// CHECK2-NEXT: [[TMP91:%.*]] = load i32, i32* [[SIZE_CASTED27]], align 4
|
|
// CHECK2-NEXT: [[ARRAYIDX28:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[A]], i32 0, i32 3
|
|
// CHECK2-NEXT: [[TMP92:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOFFLOAD_BASEPTRS29]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP93:%.*]] = bitcast i8** [[TMP92]] to i32*
|
|
// CHECK2-NEXT: store i32 [[TMP91]], i32* [[TMP93]], align 4
|
|
// CHECK2-NEXT: [[TMP94:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOFFLOAD_PTRS30]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP95:%.*]] = bitcast i8** [[TMP94]] to i32*
|
|
// CHECK2-NEXT: store i32 [[TMP91]], i32* [[TMP95]], align 4
|
|
// CHECK2-NEXT: [[TMP96:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOFFLOAD_MAPPERS31]], i32 0, i32 0
|
|
// CHECK2-NEXT: store i8* null, i8** [[TMP96]], align 4
|
|
// CHECK2-NEXT: [[TMP97:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOFFLOAD_BASEPTRS29]], i32 0, i32 1
|
|
// CHECK2-NEXT: [[TMP98:%.*]] = bitcast i8** [[TMP97]] to [10 x i32]**
|
|
// CHECK2-NEXT: store [10 x i32]* [[A]], [10 x i32]** [[TMP98]], align 4
|
|
// CHECK2-NEXT: [[TMP99:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOFFLOAD_PTRS30]], i32 0, i32 1
|
|
// CHECK2-NEXT: [[TMP100:%.*]] = bitcast i8** [[TMP99]] to i32**
|
|
// CHECK2-NEXT: store i32* [[ARRAYIDX28]], i32** [[TMP100]], align 4
|
|
// CHECK2-NEXT: [[TMP101:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOFFLOAD_MAPPERS31]], i32 0, i32 1
|
|
// CHECK2-NEXT: store i8* null, i8** [[TMP101]], align 4
|
|
// CHECK2-NEXT: [[TMP102:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOFFLOAD_BASEPTRS29]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP103:%.*]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[DOTOFFLOAD_PTRS30]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP104:%.*]] = call i32 @__tgt_target_teams_mapper(%struct.ident_t* @[[GLOB4]], i64 -1, i8* @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3sumPiiS__l81.region_id, i32 2, i8** [[TMP102]], i8** [[TMP103]], i64* getelementptr inbounds ([2 x i64], [2 x i64]* @.offload_sizes.15, i32 0, i32 0), i64* getelementptr inbounds ([2 x i64], [2 x i64]* @.offload_maptypes.16, i32 0, i32 0), i8** null, i8** null, i32 1, i32 0)
|
|
// CHECK2-NEXT: [[TMP105:%.*]] = icmp ne i32 [[TMP104]], 0
|
|
// CHECK2-NEXT: br i1 [[TMP105]], label [[OMP_OFFLOAD_FAILED32:%.*]], label [[OMP_OFFLOAD_CONT33:%.*]]
|
|
// CHECK2: omp_offload.failed32:
|
|
// CHECK2-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3sumPiiS__l81(i32 [[TMP91]], [10 x i32]* [[A]]) #[[ATTR2]]
|
|
// CHECK2-NEXT: br label [[OMP_OFFLOAD_CONT33]]
|
|
// CHECK2: omp_offload.cont33:
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3sumPiiS__l69
|
|
// CHECK2-SAME: (i32 noundef [[SIZE:%.*]], i32* noundef [[OUTPUT:%.*]], i32* noundef [[INPUT:%.*]]) #[[ATTR1:[0-9]+]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[SIZE_ADDR:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[OUTPUT_ADDR:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[INPUT_ADDR:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[SIZE_CASTED:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: store i32 [[SIZE]], i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32* [[OUTPUT]], i32** [[OUTPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32* [[INPUT]], i32** [[INPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load i32, i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP0]], i32* [[SIZE_CASTED]], align 4
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = load i32, i32* [[SIZE_CASTED]], align 4
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i32*, i32** [[OUTPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = load i32*, i32** [[INPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_teams(%struct.ident_t* @[[GLOB4]], i32 3, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i32, i32*, i32*)* @.omp_outlined. to void (i32*, i32*, ...)*), i32 [[TMP1]], i32* [[TMP2]], i32* [[TMP3]])
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined.
|
|
// CHECK2-SAME: (i32* noalias noundef [[DOTGLOBAL_TID_:%.*]], i32* noalias noundef [[DOTBOUND_TID_:%.*]], i32 noundef [[SIZE:%.*]], i32* noundef [[OUTPUT:%.*]], i32* noundef [[INPUT:%.*]]) #[[ATTR1]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[SIZE_ADDR:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[OUTPUT_ADDR:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[INPUT_ADDR:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[OUTPUT1:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[TMP:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[_TMP2:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTCAPTURE_EXPR_:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTCAPTURE_EXPR_3:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_COMB_LB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_COMB_UB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[I5:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[SIZE_CASTED:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 4
|
|
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 4
|
|
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[SIZE]], i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32* [[OUTPUT]], i32** [[OUTPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32* [[INPUT]], i32** [[INPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load i32*, i32** [[OUTPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i32 0
|
|
// CHECK2-NEXT: store i32 0, i32* [[OUTPUT1]], align 4
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = load i32*, i32** [[OUTPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = ptrtoint i32* [[TMP1]] to i64
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = ptrtoint i32* [[ARRAYIDX]] to i64
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = sub i64 [[TMP2]], [[TMP3]]
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = sdiv exact i64 [[TMP4]], ptrtoint (i32* getelementptr (i32, i32* null, i32 1) to i64)
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr i32, i32* [[OUTPUT1]], i64 [[TMP5]]
|
|
// CHECK2-NEXT: store i32* [[TMP6]], i32** [[TMP]], align 4
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i32, i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP7]], i32* [[DOTCAPTURE_EXPR_]], align 4
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_]], align 4
|
|
// CHECK2-NEXT: [[SUB:%.*]] = sub nsw i32 [[TMP8]], 0
|
|
// CHECK2-NEXT: [[DIV:%.*]] = sdiv i32 [[SUB]], 1
|
|
// CHECK2-NEXT: [[SUB4:%.*]] = sub nsw i32 [[DIV]], 1
|
|
// CHECK2-NEXT: store i32 [[SUB4]], i32* [[DOTCAPTURE_EXPR_3]], align 4
|
|
// CHECK2-NEXT: store i32 0, i32* [[I]], align 4
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_]], align 4
|
|
// CHECK2-NEXT: [[CMP:%.*]] = icmp slt i32 0, [[TMP9]]
|
|
// CHECK2-NEXT: br i1 [[CMP]], label [[OMP_PRECOND_THEN:%.*]], label [[OMP_PRECOND_END:%.*]]
|
|
// CHECK2: omp.precond.then:
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_COMB_LB]], align 4
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_3]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP10]], i32* [[DOTOMP_COMB_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:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = load i32, i32* [[TMP11]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 [[TMP12]], i32 92, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_COMB_LB]], i32* [[DOTOMP_COMB_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = load i32, i32* [[DOTOMP_COMB_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_3]], align 4
|
|
// CHECK2-NEXT: [[CMP6:%.*]] = icmp sgt i32 [[TMP13]], [[TMP14]]
|
|
// CHECK2-NEXT: br i1 [[CMP6]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK2: cond.true:
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_3]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK2: cond.false:
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = load i32, i32* [[DOTOMP_COMB_UB]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END]]
|
|
// CHECK2: cond.end:
|
|
// CHECK2-NEXT: [[COND:%.*]] = phi i32 [ [[TMP15]], [[COND_TRUE]] ], [ [[TMP16]], [[COND_FALSE]] ]
|
|
// CHECK2-NEXT: store i32 [[COND]], i32* [[DOTOMP_COMB_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = load i32, i32* [[DOTOMP_COMB_LB]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP17]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK2: omp.inner.for.cond:
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[TMP19:%.*]] = load i32, i32* [[DOTOMP_COMB_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP7:%.*]] = icmp sle i32 [[TMP18]], [[TMP19]]
|
|
// CHECK2-NEXT: br i1 [[CMP7]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK2: omp.inner.for.body:
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = load i32, i32* [[DOTOMP_COMB_LB]], align 4
|
|
// CHECK2-NEXT: [[TMP21:%.*]] = load i32, i32* [[DOTOMP_COMB_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP22:%.*]] = load i32, i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP22]], i32* [[SIZE_CASTED]], align 4
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = load i32, i32* [[SIZE_CASTED]], align 4
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = load i32*, i32** [[TMP]], align 4
|
|
// CHECK2-NEXT: [[TMP25:%.*]] = load i32*, i32** [[INPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB4]], i32 5, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i32, i32, i32, i32*, i32*)* @.omp_outlined..1 to void (i32*, i32*, ...)*), i32 [[TMP20]], i32 [[TMP21]], i32 [[TMP23]], i32* [[TMP24]], i32* [[TMP25]])
|
|
// 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: [[TMP27:%.*]] = load i32, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP26]], [[TMP27]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], 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 4
|
|
// 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: br label [[OMP_PRECOND_END]]
|
|
// CHECK2: omp.precond.end:
|
|
// CHECK2-NEXT: [[TMP30:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP31:%.*]] = bitcast i32* [[OUTPUT1]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP31]], i8** [[TMP30]], align 4
|
|
// CHECK2-NEXT: [[TMP32:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 4
|
|
// 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_nowait(%struct.ident_t* @[[GLOB3:[0-9]+]], i32 [[TMP33]], i32 1, i32 4, i8* [[TMP34]], void (i8*, i8*)* @.omp.reduction.reduction_func.2, [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:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
|
|
// CHECK2-NEXT: [[TMP37:%.*]] = load i32, i32* [[OUTPUT1]], align 4
|
|
// CHECK2-NEXT: [[ADD8:%.*]] = add nsw i32 [[TMP36]], [[TMP37]]
|
|
// CHECK2-NEXT: store i32 [[ADD8]], i32* [[ARRAYIDX]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce_nowait(%struct.ident_t* @[[GLOB3]], i32 [[TMP33]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.case2:
|
|
// CHECK2-NEXT: [[TMP38:%.*]] = load i32, i32* [[OUTPUT1]], align 4
|
|
// CHECK2-NEXT: [[TMP39:%.*]] = atomicrmw add i32* [[ARRAYIDX]], i32 [[TMP38]] monotonic, align 4
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.default:
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined..1
|
|
// CHECK2-SAME: (i32* noalias noundef [[DOTGLOBAL_TID_:%.*]], i32* noalias noundef [[DOTBOUND_TID_:%.*]], i32 noundef [[DOTPREVIOUS_LB_:%.*]], i32 noundef [[DOTPREVIOUS_UB_:%.*]], i32 noundef [[SIZE:%.*]], i32* noundef [[OUTPUT:%.*]], i32* noundef [[INPUT:%.*]]) #[[ATTR1]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[DOTPREVIOUS_LB__ADDR:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTPREVIOUS_UB__ADDR:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[SIZE_ADDR:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[OUTPUT_ADDR:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[INPUT_ADDR:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[TMP:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTCAPTURE_EXPR_:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTCAPTURE_EXPR_1:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[I:%.*]] = 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: [[OUTPUT3:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[_TMP4:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[I5:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 4
|
|
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 4
|
|
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[DOTPREVIOUS_LB_]], i32* [[DOTPREVIOUS_LB__ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[DOTPREVIOUS_UB_]], i32* [[DOTPREVIOUS_UB__ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[SIZE]], i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32* [[OUTPUT]], i32** [[OUTPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32* [[INPUT]], i32** [[INPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load i32, i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP0]], i32* [[DOTCAPTURE_EXPR_]], align 4
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_]], align 4
|
|
// CHECK2-NEXT: [[SUB:%.*]] = sub nsw i32 [[TMP1]], 0
|
|
// CHECK2-NEXT: [[DIV:%.*]] = sdiv i32 [[SUB]], 1
|
|
// CHECK2-NEXT: [[SUB2:%.*]] = sub nsw i32 [[DIV]], 1
|
|
// CHECK2-NEXT: store i32 [[SUB2]], i32* [[DOTCAPTURE_EXPR_1]], align 4
|
|
// CHECK2-NEXT: store i32 0, i32* [[I]], align 4
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_]], align 4
|
|
// CHECK2-NEXT: [[CMP:%.*]] = icmp slt i32 0, [[TMP2]]
|
|
// CHECK2-NEXT: br i1 [[CMP]], label [[OMP_PRECOND_THEN:%.*]], label [[OMP_PRECOND_END:%.*]]
|
|
// CHECK2: omp.precond.then:
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_1]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP3]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i32, i32* [[DOTPREVIOUS_LB__ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = load i32, i32* [[DOTPREVIOUS_UB__ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP4]], i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP5]], 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: [[TMP6:%.*]] = load i32*, i32** [[OUTPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[TMP6]], i32 0
|
|
// CHECK2-NEXT: store i32 0, i32* [[OUTPUT3]], align 4
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i32*, i32** [[OUTPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = ptrtoint i32* [[TMP7]] to i64
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = ptrtoint i32* [[ARRAYIDX]] to i64
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = sub i64 [[TMP8]], [[TMP9]]
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = sdiv exact i64 [[TMP10]], ptrtoint (i32* getelementptr (i32, i32* null, i32 1) to i64)
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = getelementptr i32, i32* [[OUTPUT3]], i64 [[TMP11]]
|
|
// CHECK2-NEXT: store i32* [[TMP12]], i32** [[_TMP4]], align 4
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = load i32, i32* [[TMP13]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB2:[0-9]+]], i32 [[TMP14]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_1]], align 4
|
|
// CHECK2-NEXT: [[CMP6:%.*]] = icmp sgt i32 [[TMP15]], [[TMP16]]
|
|
// CHECK2-NEXT: br i1 [[CMP6]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK2: cond.true:
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_1]], align 4
|
|
// 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 [ [[TMP17]], [[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_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* [[I5]], align 4
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = load i32*, i32** [[INPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = load i32, i32* [[I5]], align 4
|
|
// CHECK2-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds i32, i32* [[TMP23]], i32 [[TMP24]]
|
|
// CHECK2-NEXT: [[TMP25:%.*]] = load i32, i32* [[ARRAYIDX8]], align 4
|
|
// CHECK2-NEXT: [[TMP26:%.*]] = load i32*, i32** [[_TMP4]], align 4
|
|
// CHECK2-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds i32, i32* [[TMP26]], i32 0
|
|
// CHECK2-NEXT: [[TMP27:%.*]] = load i32, i32* [[ARRAYIDX9]], align 4
|
|
// CHECK2-NEXT: [[ADD10:%.*]] = add nsw i32 [[TMP27]], [[TMP25]]
|
|
// CHECK2-NEXT: store i32 [[ADD10]], i32* [[ARRAYIDX9]], 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: [[TMP28:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[ADD11:%.*]] = add nsw i32 [[TMP28]], 1
|
|
// CHECK2-NEXT: store i32 [[ADD11]], 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: [[TMP29:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP30:%.*]] = load i32, i32* [[TMP29]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP30]])
|
|
// CHECK2-NEXT: [[TMP31:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP32:%.*]] = bitcast i32* [[OUTPUT3]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP32]], i8** [[TMP31]], align 4
|
|
// CHECK2-NEXT: [[TMP33:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP34:%.*]] = load i32, i32* [[TMP33]], align 4
|
|
// CHECK2-NEXT: [[TMP35:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK2-NEXT: [[TMP36:%.*]] = call i32 @__kmpc_reduce_nowait(%struct.ident_t* @[[GLOB3]], i32 [[TMP34]], i32 1, i32 4, i8* [[TMP35]], void (i8*, i8*)* @.omp.reduction.reduction_func, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: switch i32 [[TMP36]], 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: [[TMP37:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
|
|
// CHECK2-NEXT: [[TMP38:%.*]] = load i32, i32* [[OUTPUT3]], align 4
|
|
// CHECK2-NEXT: [[ADD12:%.*]] = add nsw i32 [[TMP37]], [[TMP38]]
|
|
// CHECK2-NEXT: store i32 [[ADD12]], i32* [[ARRAYIDX]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce_nowait(%struct.ident_t* @[[GLOB3]], i32 [[TMP34]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.case2:
|
|
// CHECK2-NEXT: [[TMP39:%.*]] = load i32, i32* [[OUTPUT3]], align 4
|
|
// CHECK2-NEXT: [[TMP40:%.*]] = atomicrmw add i32* [[ARRAYIDX]], i32 [[TMP39]] monotonic, align 4
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.default:
|
|
// CHECK2-NEXT: br label [[OMP_PRECOND_END]]
|
|
// CHECK2: omp.precond.end:
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func
|
|
// CHECK2-SAME: (i8* noundef [[TMP0:%.*]], i8* noundef [[TMP1:%.*]]) #[[ATTR3:[0-9]+]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 4
|
|
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 4
|
|
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 4
|
|
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 4
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 4
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 4
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to i32*
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 4
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i32*
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = load i32, i32* [[TMP11]], align 4
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = load i32, i32* [[TMP8]], align 4
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP12]], [[TMP13]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[TMP11]], align 4
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.2
|
|
// CHECK2-SAME: (i8* noundef [[TMP0:%.*]], i8* noundef [[TMP1:%.*]]) #[[ATTR3]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 4
|
|
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 4
|
|
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 4
|
|
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 4
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 4
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 4
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to i32*
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 4
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i32*
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = load i32, i32* [[TMP11]], align 4
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = load i32, i32* [[TMP8]], align 4
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP12]], [[TMP13]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[TMP11]], align 4
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3sumPiiS__l73
|
|
// CHECK2-SAME: (i32 noundef [[SIZE:%.*]], i32* noundef [[OUTPUT:%.*]], i32* noundef [[INPUT:%.*]]) #[[ATTR1]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[SIZE_ADDR:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[OUTPUT_ADDR:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[INPUT_ADDR:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[SIZE_CASTED:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: store i32 [[SIZE]], i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32* [[OUTPUT]], i32** [[OUTPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32* [[INPUT]], i32** [[INPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load i32, i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP0]], i32* [[SIZE_CASTED]], align 4
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = load i32, i32* [[SIZE_CASTED]], align 4
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i32*, i32** [[OUTPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = load i32*, i32** [[INPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_teams(%struct.ident_t* @[[GLOB4]], i32 3, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i32, i32*, i32*)* @.omp_outlined..3 to void (i32*, i32*, ...)*), i32 [[TMP1]], i32* [[TMP2]], i32* [[TMP3]])
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined..3
|
|
// CHECK2-SAME: (i32* noalias noundef [[DOTGLOBAL_TID_:%.*]], i32* noalias noundef [[DOTBOUND_TID_:%.*]], i32 noundef [[SIZE:%.*]], i32* noundef [[OUTPUT:%.*]], i32* noundef [[INPUT:%.*]]) #[[ATTR1]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[SIZE_ADDR:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[OUTPUT_ADDR:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[INPUT_ADDR:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[OUTPUT2:%.*]] = alloca [3 x i32], align 4
|
|
// CHECK2-NEXT: [[TMP:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[_TMP3:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTCAPTURE_EXPR_:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTCAPTURE_EXPR_4:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_COMB_LB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_COMB_UB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[I6:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[SIZE_CASTED:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 4
|
|
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 4
|
|
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[SIZE]], i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32* [[OUTPUT]], i32** [[OUTPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32* [[INPUT]], i32** [[INPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load i32*, i32** [[OUTPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i32 0
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = load i32*, i32** [[OUTPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i32 2
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [3 x i32], [3 x i32]* [[OUTPUT2]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = getelementptr i32, i32* [[ARRAY_BEGIN]], i32 3
|
|
// CHECK2-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq i32* [[ARRAY_BEGIN]], [[TMP2]]
|
|
// 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]], [[TMP2]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK2: omp.arrayinit.done:
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = load i32*, i32** [[OUTPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = ptrtoint i32* [[TMP3]] to i64
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = ptrtoint i32* [[ARRAYIDX]] to i64
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = sub i64 [[TMP4]], [[TMP5]]
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = sdiv exact i64 [[TMP6]], ptrtoint (i32* getelementptr (i32, i32* null, i32 1) to i64)
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast [3 x i32]* [[OUTPUT2]] to i32*
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr i32, i32* [[TMP8]], i64 [[TMP7]]
|
|
// CHECK2-NEXT: store i32* [[TMP9]], i32** [[TMP]], align 4
|
|
// CHECK2-NEXT: [[RHS_BEGIN:%.*]] = bitcast [3 x i32]* [[OUTPUT2]] to i32*
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i32, i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP10]], i32* [[DOTCAPTURE_EXPR_]], align 4
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_]], align 4
|
|
// CHECK2-NEXT: [[SUB:%.*]] = sub nsw i32 [[TMP11]], 0
|
|
// CHECK2-NEXT: [[DIV:%.*]] = sdiv i32 [[SUB]], 1
|
|
// CHECK2-NEXT: [[SUB5:%.*]] = sub nsw i32 [[DIV]], 1
|
|
// CHECK2-NEXT: store i32 [[SUB5]], i32* [[DOTCAPTURE_EXPR_4]], align 4
|
|
// CHECK2-NEXT: store i32 0, i32* [[I]], align 4
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_]], align 4
|
|
// CHECK2-NEXT: [[CMP:%.*]] = icmp slt i32 0, [[TMP12]]
|
|
// CHECK2-NEXT: br i1 [[CMP]], label [[OMP_PRECOND_THEN:%.*]], label [[OMP_PRECOND_END:%.*]]
|
|
// CHECK2: omp.precond.then:
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_COMB_LB]], align 4
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_4]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP13]], i32* [[DOTOMP_COMB_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: [[TMP14:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 4
|
|
// 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 92, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_COMB_LB]], i32* [[DOTOMP_COMB_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = load i32, i32* [[DOTOMP_COMB_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_4]], align 4
|
|
// CHECK2-NEXT: [[CMP7:%.*]] = icmp sgt i32 [[TMP16]], [[TMP17]]
|
|
// CHECK2-NEXT: br i1 [[CMP7]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK2: cond.true:
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_4]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK2: cond.false:
|
|
// CHECK2-NEXT: [[TMP19:%.*]] = load i32, i32* [[DOTOMP_COMB_UB]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END]]
|
|
// CHECK2: cond.end:
|
|
// CHECK2-NEXT: [[COND:%.*]] = phi i32 [ [[TMP18]], [[COND_TRUE]] ], [ [[TMP19]], [[COND_FALSE]] ]
|
|
// CHECK2-NEXT: store i32 [[COND]], i32* [[DOTOMP_COMB_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = load i32, i32* [[DOTOMP_COMB_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_COMB_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP8:%.*]] = icmp sle i32 [[TMP21]], [[TMP22]]
|
|
// CHECK2-NEXT: br i1 [[CMP8]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK2: omp.inner.for.body:
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = load i32, i32* [[DOTOMP_COMB_LB]], align 4
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = load i32, i32* [[DOTOMP_COMB_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP25:%.*]] = load i32, i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP25]], i32* [[SIZE_CASTED]], align 4
|
|
// CHECK2-NEXT: [[TMP26:%.*]] = load i32, i32* [[SIZE_CASTED]], align 4
|
|
// CHECK2-NEXT: [[TMP27:%.*]] = load i32*, i32** [[TMP]], align 4
|
|
// CHECK2-NEXT: [[TMP28:%.*]] = load i32*, i32** [[INPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB4]], i32 5, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i32, i32, i32, i32*, i32*)* @.omp_outlined..4 to void (i32*, i32*, ...)*), i32 [[TMP23]], i32 [[TMP24]], i32 [[TMP26]], i32* [[TMP27]], i32* [[TMP28]])
|
|
// 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: [[TMP30:%.*]] = load i32, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP29]], [[TMP30]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], 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 4
|
|
// 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: br label [[OMP_PRECOND_END]]
|
|
// CHECK2: omp.precond.end:
|
|
// CHECK2-NEXT: [[TMP33:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP34:%.*]] = bitcast i32* [[RHS_BEGIN]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP34]], i8** [[TMP33]], align 4
|
|
// CHECK2-NEXT: [[TMP35:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP36:%.*]] = load i32, i32* [[TMP35]], align 4
|
|
// CHECK2-NEXT: [[TMP37:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK2-NEXT: [[TMP38:%.*]] = call i32 @__kmpc_reduce_nowait(%struct.ident_t* @[[GLOB3]], i32 [[TMP36]], i32 1, i32 4, i8* [[TMP37]], void (i8*, i8*)* @.omp.reduction.reduction_func.6, [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* [[ARRAYIDX]], i32 3
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq i32* [[ARRAYIDX]], [[TMP39]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE13:%.*]], 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_DESTELEMENTPAST9:%.*]] = phi i32* [ [[ARRAYIDX]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT11:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[TMP40:%.*]] = load i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST9]], align 4
|
|
// CHECK2-NEXT: [[TMP41:%.*]] = load i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], align 4
|
|
// CHECK2-NEXT: [[ADD10:%.*]] = add nsw i32 [[TMP40]], [[TMP41]]
|
|
// CHECK2-NEXT: store i32 [[ADD10]], i32* [[OMP_ARRAYCPY_DESTELEMENTPAST9]], align 4
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT11]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST9]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE12:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT11]], [[TMP39]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE12]], label [[OMP_ARRAYCPY_DONE13]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done13:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce_nowait(%struct.ident_t* @[[GLOB3]], i32 [[TMP36]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.case2:
|
|
// CHECK2-NEXT: [[TMP42:%.*]] = getelementptr i32, i32* [[ARRAYIDX]], i32 3
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY14:%.*]] = icmp eq i32* [[ARRAYIDX]], [[TMP42]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY14]], label [[OMP_ARRAYCPY_DONE21:%.*]], label [[OMP_ARRAYCPY_BODY15:%.*]]
|
|
// CHECK2: omp.arraycpy.body15:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST16:%.*]] = phi i32* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT19:%.*]], [[OMP_ARRAYCPY_BODY15]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST17:%.*]] = phi i32* [ [[ARRAYIDX]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT18:%.*]], [[OMP_ARRAYCPY_BODY15]] ]
|
|
// CHECK2-NEXT: [[TMP43:%.*]] = load i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST16]], align 4
|
|
// CHECK2-NEXT: [[TMP44:%.*]] = atomicrmw add i32* [[OMP_ARRAYCPY_DESTELEMENTPAST17]], i32 [[TMP43]] monotonic, align 4
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT18]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST17]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT19]] = getelementptr i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST16]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE20:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT18]], [[TMP42]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE20]], label [[OMP_ARRAYCPY_DONE21]], label [[OMP_ARRAYCPY_BODY15]]
|
|
// CHECK2: omp.arraycpy.done21:
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.default:
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined..4
|
|
// CHECK2-SAME: (i32* noalias noundef [[DOTGLOBAL_TID_:%.*]], i32* noalias noundef [[DOTBOUND_TID_:%.*]], i32 noundef [[DOTPREVIOUS_LB_:%.*]], i32 noundef [[DOTPREVIOUS_UB_:%.*]], i32 noundef [[SIZE:%.*]], i32* noundef [[OUTPUT:%.*]], i32* noundef [[INPUT:%.*]]) #[[ATTR1]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[DOTPREVIOUS_LB__ADDR:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTPREVIOUS_UB__ADDR:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[SIZE_ADDR:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[OUTPUT_ADDR:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[INPUT_ADDR:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[TMP:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTCAPTURE_EXPR_:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTCAPTURE_EXPR_1:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[I:%.*]] = 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: [[OUTPUT4:%.*]] = alloca [3 x i32], align 4
|
|
// CHECK2-NEXT: [[_TMP5:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[I6:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 4
|
|
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 4
|
|
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[DOTPREVIOUS_LB_]], i32* [[DOTPREVIOUS_LB__ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[DOTPREVIOUS_UB_]], i32* [[DOTPREVIOUS_UB__ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[SIZE]], i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32* [[OUTPUT]], i32** [[OUTPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32* [[INPUT]], i32** [[INPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load i32, i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP0]], i32* [[DOTCAPTURE_EXPR_]], align 4
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_]], align 4
|
|
// CHECK2-NEXT: [[SUB:%.*]] = sub nsw i32 [[TMP1]], 0
|
|
// CHECK2-NEXT: [[DIV:%.*]] = sdiv i32 [[SUB]], 1
|
|
// CHECK2-NEXT: [[SUB2:%.*]] = sub nsw i32 [[DIV]], 1
|
|
// CHECK2-NEXT: store i32 [[SUB2]], i32* [[DOTCAPTURE_EXPR_1]], align 4
|
|
// CHECK2-NEXT: store i32 0, i32* [[I]], align 4
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_]], align 4
|
|
// CHECK2-NEXT: [[CMP:%.*]] = icmp slt i32 0, [[TMP2]]
|
|
// CHECK2-NEXT: br i1 [[CMP]], label [[OMP_PRECOND_THEN:%.*]], label [[OMP_PRECOND_END:%.*]]
|
|
// CHECK2: omp.precond.then:
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_1]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP3]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i32, i32* [[DOTPREVIOUS_LB__ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = load i32, i32* [[DOTPREVIOUS_UB__ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP4]], i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP5]], 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: [[TMP6:%.*]] = load i32*, i32** [[OUTPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[TMP6]], i32 0
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i32*, i32** [[OUTPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[TMP7]], i32 2
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [3 x i32], [3 x i32]* [[OUTPUT4]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = getelementptr i32, i32* [[ARRAY_BEGIN]], i32 3
|
|
// CHECK2-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq i32* [[ARRAY_BEGIN]], [[TMP8]]
|
|
// 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]], [[OMP_PRECOND_THEN]] ], [ [[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]], [[TMP8]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK2: omp.arrayinit.done:
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = load i32*, i32** [[OUTPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = ptrtoint i32* [[TMP9]] to i64
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = ptrtoint i32* [[ARRAYIDX]] 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 [3 x i32]* [[OUTPUT4]] to i32*
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = getelementptr i32, i32* [[TMP14]], i64 [[TMP13]]
|
|
// CHECK2-NEXT: store i32* [[TMP15]], i32** [[_TMP5]], align 4
|
|
// CHECK2-NEXT: [[RHS_BEGIN:%.*]] = bitcast [3 x i32]* [[OUTPUT4]] to i32*
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = load i32, i32* [[TMP16]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB2]], 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: [[TMP19:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_1]], align 4
|
|
// CHECK2-NEXT: [[CMP7:%.*]] = icmp sgt i32 [[TMP18]], [[TMP19]]
|
|
// CHECK2-NEXT: br i1 [[CMP7]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK2: cond.true:
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR_1]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK2: cond.false:
|
|
// CHECK2-NEXT: [[TMP21:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END]]
|
|
// CHECK2: cond.end:
|
|
// CHECK2-NEXT: [[COND:%.*]] = phi i32 [ [[TMP20]], [[COND_TRUE]] ], [ [[TMP21]], [[COND_FALSE]] ]
|
|
// CHECK2-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP22]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK2: omp.inner.for.cond:
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP8:%.*]] = icmp sle i32 [[TMP23]], [[TMP24]]
|
|
// CHECK2-NEXT: br i1 [[CMP8]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK2: omp.inner.for.body:
|
|
// CHECK2-NEXT: [[TMP25:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP25]], 1
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[I6]], align 4
|
|
// CHECK2-NEXT: [[TMP26:%.*]] = load i32*, i32** [[INPUT_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP27:%.*]] = load i32, i32* [[I6]], align 4
|
|
// CHECK2-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds i32, i32* [[TMP26]], i32 [[TMP27]]
|
|
// CHECK2-NEXT: [[TMP28:%.*]] = load i32, i32* [[ARRAYIDX9]], align 4
|
|
// CHECK2-NEXT: [[TMP29:%.*]] = load i32*, i32** [[_TMP5]], align 4
|
|
// CHECK2-NEXT: [[ARRAYIDX10:%.*]] = getelementptr inbounds i32, i32* [[TMP29]], i32 0
|
|
// CHECK2-NEXT: [[TMP30:%.*]] = load i32, i32* [[ARRAYIDX10]], align 4
|
|
// CHECK2-NEXT: [[ADD11:%.*]] = add nsw i32 [[TMP30]], [[TMP28]]
|
|
// CHECK2-NEXT: store i32 [[ADD11]], i32* [[ARRAYIDX10]], 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: [[TMP31:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: [[ADD12:%.*]] = add nsw i32 [[TMP31]], 1
|
|
// CHECK2-NEXT: store i32 [[ADD12]], 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: [[TMP32:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP33:%.*]] = load i32, i32* [[TMP32]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP33]])
|
|
// CHECK2-NEXT: [[TMP34:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP35:%.*]] = bitcast i32* [[RHS_BEGIN]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP35]], i8** [[TMP34]], align 4
|
|
// CHECK2-NEXT: [[TMP36:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP37:%.*]] = load i32, i32* [[TMP36]], align 4
|
|
// CHECK2-NEXT: [[TMP38:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK2-NEXT: [[TMP39:%.*]] = call i32 @__kmpc_reduce_nowait(%struct.ident_t* @[[GLOB3]], i32 [[TMP37]], i32 1, i32 4, i8* [[TMP38]], void (i8*, i8*)* @.omp.reduction.reduction_func.5, [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:%.*]] = getelementptr i32, i32* [[ARRAYIDX]], i32 3
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq i32* [[ARRAYIDX]], [[TMP40]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE17:%.*]], 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_DESTELEMENTPAST13:%.*]] = phi i32* [ [[ARRAYIDX]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT15:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[TMP41:%.*]] = load i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST13]], align 4
|
|
// CHECK2-NEXT: [[TMP42:%.*]] = load i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], align 4
|
|
// CHECK2-NEXT: [[ADD14:%.*]] = add nsw i32 [[TMP41]], [[TMP42]]
|
|
// CHECK2-NEXT: store i32 [[ADD14]], i32* [[OMP_ARRAYCPY_DESTELEMENTPAST13]], align 4
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT15]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST13]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE16:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT15]], [[TMP40]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE16]], label [[OMP_ARRAYCPY_DONE17]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done17:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce_nowait(%struct.ident_t* @[[GLOB3]], i32 [[TMP37]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.case2:
|
|
// CHECK2-NEXT: [[TMP43:%.*]] = getelementptr i32, i32* [[ARRAYIDX]], i32 3
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY18:%.*]] = icmp eq i32* [[ARRAYIDX]], [[TMP43]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY18]], label [[OMP_ARRAYCPY_DONE25:%.*]], label [[OMP_ARRAYCPY_BODY19:%.*]]
|
|
// CHECK2: omp.arraycpy.body19:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST20:%.*]] = phi i32* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT23:%.*]], [[OMP_ARRAYCPY_BODY19]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST21:%.*]] = phi i32* [ [[ARRAYIDX]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT22:%.*]], [[OMP_ARRAYCPY_BODY19]] ]
|
|
// CHECK2-NEXT: [[TMP44:%.*]] = load i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST20]], align 4
|
|
// CHECK2-NEXT: [[TMP45:%.*]] = atomicrmw add i32* [[OMP_ARRAYCPY_DESTELEMENTPAST21]], i32 [[TMP44]] monotonic, align 4
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT22]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST21]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT23]] = getelementptr i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST20]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE24:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT22]], [[TMP43]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE24]], label [[OMP_ARRAYCPY_DONE25]], label [[OMP_ARRAYCPY_BODY19]]
|
|
// CHECK2: omp.arraycpy.done25:
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.default:
|
|
// CHECK2-NEXT: br label [[OMP_PRECOND_END]]
|
|
// CHECK2: omp.precond.end:
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.5
|
|
// CHECK2-SAME: (i8* noundef [[TMP0:%.*]], i8* noundef [[TMP1:%.*]]) #[[ATTR3]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 4
|
|
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 4
|
|
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 4
|
|
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 4
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 4
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 4
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to i32*
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 4
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i32*
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = getelementptr i32, i32* [[TMP11]], i32 3
|
|
// 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.reduction.reduction_func.6
|
|
// CHECK2-SAME: (i8* noundef [[TMP0:%.*]], i8* noundef [[TMP1:%.*]]) #[[ATTR3]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 4
|
|
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 4
|
|
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 4
|
|
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 4
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 4
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 4
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to i32*
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 4
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i32*
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = getelementptr i32, i32* [[TMP11]], i32 3
|
|
// 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_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3sumPiiS__l78
|
|
// CHECK2-SAME: (i32 noundef [[SIZE:%.*]], [10 x i32]* noundef nonnull align 4 dereferenceable(40) [[A:%.*]]) #[[ATTR6:[0-9]+]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[SIZE_ADDR:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca [10 x i32]*, align 4
|
|
// CHECK2-NEXT: [[SIZE_CASTED:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: store i32 [[SIZE]], i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store [10 x i32]* [[A]], [10 x i32]** [[A_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load [10 x i32]*, [10 x i32]** [[A_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = load i32, i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP1]], i32* [[SIZE_CASTED]], align 4
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i32, i32* [[SIZE_CASTED]], align 4
|
|
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB4]], i32 2, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i32, [10 x i32]*)* @.omp_outlined..9 to void (i32*, i32*, ...)*), i32 [[TMP2]], [10 x i32]* [[TMP0]])
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined..9
|
|
// CHECK2-SAME: (i32* noalias noundef [[DOTGLOBAL_TID_:%.*]], i32* noalias noundef [[DOTBOUND_TID_:%.*]], i32 noundef [[SIZE:%.*]], [10 x i32]* noundef nonnull align 4 dereferenceable(40) [[A:%.*]]) #[[ATTR1]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[SIZE_ADDR:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca [10 x i32]*, align 4
|
|
// CHECK2-NEXT: [[A2:%.*]] = alloca [2 x i32], align 4
|
|
// CHECK2-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 4
|
|
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 4
|
|
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[SIZE]], i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store [10 x i32]* [[A]], [10 x i32]** [[A_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load [10 x i32]*, [10 x i32]** [[A_ADDR]], align 4
|
|
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP0]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP0]], i32 0, i32 1
|
|
// CHECK2-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[A2]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = getelementptr i32, i32* [[ARRAY_BEGIN]], i32 2
|
|
// CHECK2-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq i32* [[ARRAY_BEGIN]], [[TMP1]]
|
|
// 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]], [[TMP1]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
|
|
// CHECK2: omp.arrayinit.done:
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = bitcast [10 x i32]* [[TMP0]] to i32*
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = ptrtoint i32* [[TMP2]] to i64
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = ptrtoint i32* [[ARRAYIDX]] to i64
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = sub i64 [[TMP3]], [[TMP4]]
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = sdiv exact i64 [[TMP5]], ptrtoint (i32* getelementptr (i32, i32* null, i32 1) to i64)
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = bitcast [2 x i32]* [[A2]] to i32*
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = getelementptr i32, i32* [[TMP7]], i64 [[TMP6]]
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = bitcast i32* [[TMP8]] to [10 x i32]*
|
|
// CHECK2-NEXT: [[RHS_BEGIN:%.*]] = bitcast [2 x i32]* [[A2]] to i32*
|
|
// CHECK2-NEXT: store i32 0, i32* [[I]], align 4
|
|
// CHECK2-NEXT: br label [[FOR_COND:%.*]]
|
|
// CHECK2: for.cond:
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = load i32, i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: [[CMP:%.*]] = icmp slt i32 [[TMP10]], [[TMP11]]
|
|
// CHECK2-NEXT: br i1 [[CMP]], label [[FOR_BODY:%.*]], label [[FOR_END:%.*]]
|
|
// CHECK2: for.body:
|
|
// CHECK2-NEXT: br label [[FOR_INC:%.*]]
|
|
// CHECK2: for.inc:
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK2-NEXT: [[INC:%.*]] = add nsw i32 [[TMP12]], 1
|
|
// CHECK2-NEXT: store i32 [[INC]], i32* [[I]], align 4
|
|
// CHECK2-NEXT: br label [[FOR_COND]], !llvm.loop [[LOOP10:![0-9]+]]
|
|
// CHECK2: for.end:
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = bitcast i32* [[RHS_BEGIN]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP14]], i8** [[TMP13]], align 4
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = load i32, i32* [[TMP15]], align 4
|
|
// CHECK2-NEXT: [[TMP17:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = call i32 @__kmpc_reduce_nowait(%struct.ident_t* @[[GLOB3]], i32 [[TMP16]], i32 1, i32 4, i8* [[TMP17]], void (i8*, i8*)* @.omp.reduction.reduction_func.10, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: switch i32 [[TMP18]], 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: [[TMP19:%.*]] = getelementptr i32, i32* [[ARRAYIDX]], i32 2
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq i32* [[ARRAYIDX]], [[TMP19]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE6:%.*]], 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_DESTELEMENTPAST3:%.*]] = phi i32* [ [[ARRAYIDX]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT4:%.*]], [[OMP_ARRAYCPY_BODY]] ]
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = load i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST3]], align 4
|
|
// CHECK2-NEXT: [[TMP21:%.*]] = load i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], align 4
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP20]], [[TMP21]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[OMP_ARRAYCPY_DESTELEMENTPAST3]], align 4
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT4]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST3]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE5:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT4]], [[TMP19]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE5]], label [[OMP_ARRAYCPY_DONE6]], label [[OMP_ARRAYCPY_BODY]]
|
|
// CHECK2: omp.arraycpy.done6:
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce_nowait(%struct.ident_t* @[[GLOB3]], i32 [[TMP16]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.case2:
|
|
// CHECK2-NEXT: [[TMP22:%.*]] = getelementptr i32, i32* [[ARRAYIDX]], i32 2
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY7:%.*]] = icmp eq i32* [[ARRAYIDX]], [[TMP22]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY7]], label [[OMP_ARRAYCPY_DONE14:%.*]], label [[OMP_ARRAYCPY_BODY8:%.*]]
|
|
// CHECK2: omp.arraycpy.body8:
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST9:%.*]] = phi i32* [ [[RHS_BEGIN]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT12:%.*]], [[OMP_ARRAYCPY_BODY8]] ]
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST10:%.*]] = phi i32* [ [[ARRAYIDX]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT11:%.*]], [[OMP_ARRAYCPY_BODY8]] ]
|
|
// CHECK2-NEXT: [[TMP23:%.*]] = load i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST9]], align 4
|
|
// CHECK2-NEXT: [[TMP24:%.*]] = atomicrmw add i32* [[OMP_ARRAYCPY_DESTELEMENTPAST10]], i32 [[TMP23]] monotonic, align 4
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT11]] = getelementptr i32, i32* [[OMP_ARRAYCPY_DESTELEMENTPAST10]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT12]] = getelementptr i32, i32* [[OMP_ARRAYCPY_SRCELEMENTPAST9]], i32 1
|
|
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE13:%.*]] = icmp eq i32* [[OMP_ARRAYCPY_DEST_ELEMENT11]], [[TMP22]]
|
|
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE13]], label [[OMP_ARRAYCPY_DONE14]], label [[OMP_ARRAYCPY_BODY8]]
|
|
// CHECK2: omp.arraycpy.done14:
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.default:
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.10
|
|
// CHECK2-SAME: (i8* noundef [[TMP0:%.*]], i8* noundef [[TMP1:%.*]]) #[[ATTR3]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 4
|
|
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 4
|
|
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 4
|
|
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 4
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 4
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 4
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to i32*
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 4
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i32*
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = getelementptr i32, i32* [[TMP11]], i32 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_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3sumPiiS__l81
|
|
// CHECK2-SAME: (i32 noundef [[SIZE:%.*]], [10 x i32]* noundef nonnull align 4 dereferenceable(40) [[A:%.*]]) #[[ATTR6]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[SIZE_ADDR:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca [10 x i32]*, align 4
|
|
// CHECK2-NEXT: [[SIZE_CASTED:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: store i32 [[SIZE]], i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store [10 x i32]* [[A]], [10 x i32]** [[A_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load [10 x i32]*, [10 x i32]** [[A_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = load i32, i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP1]], i32* [[SIZE_CASTED]], align 4
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i32, i32* [[SIZE_CASTED]], align 4
|
|
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB4]], i32 2, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i32, [10 x i32]*)* @.omp_outlined..13 to void (i32*, i32*, ...)*), i32 [[TMP2]], [10 x i32]* [[TMP0]])
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined..13
|
|
// CHECK2-SAME: (i32* noalias noundef [[DOTGLOBAL_TID_:%.*]], i32* noalias noundef [[DOTBOUND_TID_:%.*]], i32 noundef [[SIZE:%.*]], [10 x i32]* noundef nonnull align 4 dereferenceable(40) [[A:%.*]]) #[[ATTR1]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[SIZE_ADDR:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca [10 x i32]*, align 4
|
|
// CHECK2-NEXT: [[A1:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 4
|
|
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 4
|
|
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 4
|
|
// CHECK2-NEXT: store i32 [[SIZE]], i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: store [10 x i32]* [[A]], [10 x i32]** [[A_ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load [10 x i32]*, [10 x i32]** [[A_ADDR]], align 4
|
|
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP0]], i32 0, i32 3
|
|
// CHECK2-NEXT: store i32 0, i32* [[A1]], align 4
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = bitcast [10 x i32]* [[TMP0]] to i32*
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = ptrtoint i32* [[TMP1]] to i64
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = ptrtoint i32* [[ARRAYIDX]] to i64
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = sub i64 [[TMP2]], [[TMP3]]
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = sdiv exact i64 [[TMP4]], ptrtoint (i32* getelementptr (i32, i32* null, i32 1) to i64)
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr i32, i32* [[A1]], i64 [[TMP5]]
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = bitcast i32* [[TMP6]] to [10 x i32]*
|
|
// CHECK2-NEXT: store i32 0, i32* [[I]], align 4
|
|
// CHECK2-NEXT: br label [[FOR_COND:%.*]]
|
|
// CHECK2: for.cond:
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = load i32, i32* [[SIZE_ADDR]], align 4
|
|
// CHECK2-NEXT: [[CMP:%.*]] = icmp slt i32 [[TMP8]], [[TMP9]]
|
|
// CHECK2-NEXT: br i1 [[CMP]], label [[FOR_BODY:%.*]], label [[FOR_END:%.*]]
|
|
// CHECK2: for.body:
|
|
// CHECK2-NEXT: br label [[FOR_INC:%.*]]
|
|
// CHECK2: for.inc:
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i32, i32* [[I]], align 4
|
|
// CHECK2-NEXT: [[INC:%.*]] = add nsw i32 [[TMP10]], 1
|
|
// CHECK2-NEXT: store i32 [[INC]], i32* [[I]], align 4
|
|
// CHECK2-NEXT: br label [[FOR_COND]], !llvm.loop [[LOOP12:![0-9]+]]
|
|
// CHECK2: for.end:
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = bitcast i32* [[A1]] to i8*
|
|
// CHECK2-NEXT: store i8* [[TMP12]], i8** [[TMP11]], align 4
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP14:%.*]] = load i32, i32* [[TMP13]], align 4
|
|
// CHECK2-NEXT: [[TMP15:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
|
|
// CHECK2-NEXT: [[TMP16:%.*]] = call i32 @__kmpc_reduce_nowait(%struct.ident_t* @[[GLOB3]], i32 [[TMP14]], i32 1, i32 4, i8* [[TMP15]], void (i8*, i8*)* @.omp.reduction.reduction_func.14, [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: switch i32 [[TMP16]], 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: [[TMP17:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
|
|
// CHECK2-NEXT: [[TMP18:%.*]] = load i32, i32* [[A1]], align 4
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP17]], [[TMP18]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[ARRAYIDX]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_end_reduce_nowait(%struct.ident_t* @[[GLOB3]], i32 [[TMP14]], [8 x i32]* @.gomp_critical_user_.reduction.var)
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.case2:
|
|
// CHECK2-NEXT: [[TMP19:%.*]] = load i32, i32* [[A1]], align 4
|
|
// CHECK2-NEXT: [[TMP20:%.*]] = atomicrmw add i32* [[ARRAYIDX]], i32 [[TMP19]] monotonic, align 4
|
|
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
|
|
// CHECK2: .omp.reduction.default:
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.14
|
|
// CHECK2-SAME: (i8* noundef [[TMP0:%.*]], i8* noundef [[TMP1:%.*]]) #[[ATTR3]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 4
|
|
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 4
|
|
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 4
|
|
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 4
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 4
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 4
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 4
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to i32*
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i32 0, i32 0
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 4
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i32*
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = load i32, i32* [[TMP11]], align 4
|
|
// CHECK2-NEXT: [[TMP13:%.*]] = load i32, i32* [[TMP8]], align 4
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP12]], [[TMP13]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[TMP11]], align 4
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@main
|
|
// CHECK2-SAME: () #[[ATTR7:[0-9]+]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[SIZE:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[ARRAY:%.*]] = alloca i32*, align 4
|
|
// CHECK2-NEXT: [[RESULT:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: store i32 0, i32* [[RETVAL]], align 4
|
|
// CHECK2-NEXT: store i32 100, i32* [[SIZE]], align 4
|
|
// CHECK2-NEXT: [[CALL:%.*]] = call noalias noundef nonnull i8* @_Znaj(i32 noundef 400) #[[ATTR10:[0-9]+]]
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = bitcast i8* [[CALL]] to i32*
|
|
// CHECK2-NEXT: store i32* [[TMP0]], i32** [[ARRAY]], align 4
|
|
// CHECK2-NEXT: store i32 0, i32* [[RESULT]], align 4
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = load i32*, i32** [[ARRAY]], align 4
|
|
// CHECK2-NEXT: call void @_Z3sumPiiS_(i32* noundef [[TMP1]], i32 noundef 100, i32* noundef [[RESULT]])
|
|
// CHECK2-NEXT: ret i32 0
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp_offloading.requires_reg
|
|
// CHECK2-SAME: () #[[ATTR9:[0-9]+]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: call void @__tgt_register_requires(i64 1)
|
|
// CHECK2-NEXT: ret void
|
|
//
|