llvm-project/clang/test/OpenMP/nvptx_target_parallel_num_t...

734 lines
49 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 _
// Test target codegen - host bc file has to be created first.
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix=CHECK1
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple i386-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm-bc %s -o %t-x86-host.bc
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix=CHECK2
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix=CHECK3
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-cuda-mode -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-cuda-mode -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix=CHECK4
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-cuda-mode -x c++ -triple i386-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm-bc %s -o %t-x86-host.bc
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-cuda-mode -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix=CHECK5
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-cuda-mode -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix=CHECK6
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
template<typename tx>
tx ftemplate(int n) {
tx a = 0;
short aa = 0;
tx b[10];
#pragma omp target parallel map(tofrom: aa) num_threads(1024)
{
aa += 1;
}
#pragma omp target parallel map(tofrom:a, aa, b) if(target: n>40) num_threads(n)
{
a += 1;
aa += 1;
b[2] += 1;
}
return a;
}
int bar(int n){
int a = 0;
a += ftemplate<int>(n);
return a;
}
#endif
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l25
// CHECK1-SAME: (i16* nonnull align 2 dereferenceable(2) [[AA:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[AA_ADDR:%.*]] = alloca i16*, align 8
// CHECK1-NEXT: [[CAPTURED_VARS_ADDRS:%.*]] = alloca [1 x i8*], align 8
// CHECK1-NEXT: store i16* [[AA]], i16** [[AA_ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load i16*, i16** [[AA_ADDR]], align 8
// CHECK1-NEXT: [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK1-NEXT: call void @__kmpc_spmd_kernel_init(i32 [[NVPTX_NUM_THREADS]], i16 1)
// CHECK1-NEXT: br label [[DOTEXECUTE:%.*]]
// CHECK1: .execute:
// CHECK1-NEXT: [[TMP1:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1:[0-9]+]])
// CHECK1-NEXT: [[TMP2:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[CAPTURED_VARS_ADDRS]], i64 0, i64 0
// CHECK1-NEXT: [[TMP3:%.*]] = bitcast i16* [[TMP0]] to i8*
// CHECK1-NEXT: store i8* [[TMP3]], i8** [[TMP2]], align 8
// CHECK1-NEXT: [[TMP4:%.*]] = bitcast [1 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8**
// CHECK1-NEXT: call void @__kmpc_parallel_51(%struct.ident_t* @[[GLOB1]], i32 [[TMP1]], i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*, i16*)* @__omp_outlined__ to i8*), i8* null, i8** [[TMP4]], i64 1)
// CHECK1-NEXT: br label [[DOTOMP_DEINIT:%.*]]
// CHECK1: .omp.deinit:
// CHECK1-NEXT: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
// CHECK1-NEXT: br label [[DOTEXIT:%.*]]
// CHECK1: .exit:
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@__omp_outlined__
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i16* nonnull align 2 dereferenceable(2) [[AA:%.*]]) #[[ATTR0]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: [[AA_ADDR:%.*]] = alloca i16*, 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 i16* [[AA]], i16** [[AA_ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load i16*, i16** [[AA_ADDR]], align 8
// CHECK1-NEXT: [[TMP1:%.*]] = load i16, i16* [[TMP0]], align 2
// CHECK1-NEXT: [[CONV:%.*]] = sext i16 [[TMP1]] to i32
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 [[CONV]], 1
// CHECK1-NEXT: [[CONV1:%.*]] = trunc i32 [[ADD]] to i16
// CHECK1-NEXT: store i16 [[CONV1]], i16* [[TMP0]], align 2
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l30
// CHECK1-SAME: (i32* nonnull align 4 dereferenceable(4) [[A:%.*]], i16* nonnull align 2 dereferenceable(2) [[AA:%.*]], [10 x i32]* nonnull align 4 dereferenceable(40) [[B:%.*]], i64 [[DOTCAPTURE_EXPR_:%.*]]) #[[ATTR0]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[A_ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: [[AA_ADDR:%.*]] = alloca i16*, align 8
// CHECK1-NEXT: [[B_ADDR:%.*]] = alloca [10 x i32]*, align 8
// CHECK1-NEXT: [[DOTCAPTURE_EXPR__ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT: [[CAPTURED_VARS_ADDRS:%.*]] = alloca [3 x i8*], align 8
// CHECK1-NEXT: store i32* [[A]], i32** [[A_ADDR]], align 8
// CHECK1-NEXT: store i16* [[AA]], i16** [[AA_ADDR]], align 8
// CHECK1-NEXT: store [10 x i32]* [[B]], [10 x i32]** [[B_ADDR]], align 8
// CHECK1-NEXT: store i64 [[DOTCAPTURE_EXPR_]], i64* [[DOTCAPTURE_EXPR__ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load i32*, i32** [[A_ADDR]], align 8
// CHECK1-NEXT: [[TMP1:%.*]] = load i16*, i16** [[AA_ADDR]], align 8
// CHECK1-NEXT: [[TMP2:%.*]] = load [10 x i32]*, [10 x i32]** [[B_ADDR]], align 8
// CHECK1-NEXT: [[CONV:%.*]] = bitcast i64* [[DOTCAPTURE_EXPR__ADDR]] to i32*
// CHECK1-NEXT: [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK1-NEXT: call void @__kmpc_spmd_kernel_init(i32 [[NVPTX_NUM_THREADS]], i16 1)
// CHECK1-NEXT: br label [[DOTEXECUTE:%.*]]
// CHECK1: .execute:
// CHECK1-NEXT: [[TMP3:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1]])
// CHECK1-NEXT: [[TMP4:%.*]] = load i32, i32* [[CONV]], align 8
// CHECK1-NEXT: [[TMP5:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[CAPTURED_VARS_ADDRS]], i64 0, i64 0
// CHECK1-NEXT: [[TMP6:%.*]] = bitcast i32* [[TMP0]] to i8*
// CHECK1-NEXT: store i8* [[TMP6]], i8** [[TMP5]], align 8
// CHECK1-NEXT: [[TMP7:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[CAPTURED_VARS_ADDRS]], i64 0, i64 1
// CHECK1-NEXT: [[TMP8:%.*]] = bitcast i16* [[TMP1]] to i8*
// CHECK1-NEXT: store i8* [[TMP8]], i8** [[TMP7]], align 8
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[CAPTURED_VARS_ADDRS]], i64 0, i64 2
// CHECK1-NEXT: [[TMP10:%.*]] = bitcast [10 x i32]* [[TMP2]] to i8*
// CHECK1-NEXT: store i8* [[TMP10]], i8** [[TMP9]], align 8
// CHECK1-NEXT: [[TMP11:%.*]] = bitcast [3 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8**
// CHECK1-NEXT: call void @__kmpc_parallel_51(%struct.ident_t* @[[GLOB1]], i32 [[TMP3]], i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*, i32*, i16*, [10 x i32]*)* @__omp_outlined__1 to i8*), i8* null, i8** [[TMP11]], i64 3)
// CHECK1-NEXT: br label [[DOTOMP_DEINIT:%.*]]
// CHECK1: .omp.deinit:
// CHECK1-NEXT: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
// CHECK1-NEXT: br label [[DOTEXIT:%.*]]
// CHECK1: .exit:
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@__omp_outlined__1
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i32* nonnull align 4 dereferenceable(4) [[A:%.*]], i16* nonnull align 2 dereferenceable(2) [[AA:%.*]], [10 x i32]* nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR0]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: [[A_ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: [[AA_ADDR:%.*]] = alloca i16*, align 8
// CHECK1-NEXT: [[B_ADDR:%.*]] = alloca [10 x i32]*, 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 i32* [[A]], i32** [[A_ADDR]], align 8
// CHECK1-NEXT: store i16* [[AA]], i16** [[AA_ADDR]], align 8
// CHECK1-NEXT: store [10 x i32]* [[B]], [10 x i32]** [[B_ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load i32*, i32** [[A_ADDR]], align 8
// CHECK1-NEXT: [[TMP1:%.*]] = load i16*, i16** [[AA_ADDR]], align 8
// CHECK1-NEXT: [[TMP2:%.*]] = load [10 x i32]*, [10 x i32]** [[B_ADDR]], align 8
// CHECK1-NEXT: [[TMP3:%.*]] = load i32, i32* [[TMP0]], align 4
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP3]], 1
// CHECK1-NEXT: store i32 [[ADD]], i32* [[TMP0]], align 4
// CHECK1-NEXT: [[TMP4:%.*]] = load i16, i16* [[TMP1]], align 2
// CHECK1-NEXT: [[CONV:%.*]] = sext i16 [[TMP4]] to i32
// CHECK1-NEXT: [[ADD1:%.*]] = add nsw i32 [[CONV]], 1
// CHECK1-NEXT: [[CONV2:%.*]] = trunc i32 [[ADD1]] to i16
// CHECK1-NEXT: store i16 [[CONV2]], i16* [[TMP1]], align 2
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP2]], i64 0, i64 2
// CHECK1-NEXT: [[TMP5:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
// CHECK1-NEXT: [[ADD3:%.*]] = add nsw i32 [[TMP5]], 1
// CHECK1-NEXT: store i32 [[ADD3]], i32* [[ARRAYIDX]], align 4
// CHECK1-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l25
// CHECK2-SAME: (i16* nonnull align 2 dereferenceable(2) [[AA:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[AA_ADDR:%.*]] = alloca i16*, align 4
// CHECK2-NEXT: [[CAPTURED_VARS_ADDRS:%.*]] = alloca [1 x i8*], align 4
// CHECK2-NEXT: store i16* [[AA]], i16** [[AA_ADDR]], align 4
// CHECK2-NEXT: [[TMP0:%.*]] = load i16*, i16** [[AA_ADDR]], align 4
// CHECK2-NEXT: [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK2-NEXT: call void @__kmpc_spmd_kernel_init(i32 [[NVPTX_NUM_THREADS]], i16 1)
// CHECK2-NEXT: br label [[DOTEXECUTE:%.*]]
// CHECK2: .execute:
// CHECK2-NEXT: [[TMP1:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1:[0-9]+]])
// CHECK2-NEXT: [[TMP2:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[CAPTURED_VARS_ADDRS]], i32 0, i32 0
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i16* [[TMP0]] to i8*
// CHECK2-NEXT: store i8* [[TMP3]], i8** [[TMP2]], align 4
// CHECK2-NEXT: [[TMP4:%.*]] = bitcast [1 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8**
// CHECK2-NEXT: call void @__kmpc_parallel_51(%struct.ident_t* @[[GLOB1]], i32 [[TMP1]], i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*, i16*)* @__omp_outlined__ to i8*), i8* null, i8** [[TMP4]], i32 1)
// CHECK2-NEXT: br label [[DOTOMP_DEINIT:%.*]]
// CHECK2: .omp.deinit:
// CHECK2-NEXT: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
// CHECK2-NEXT: br label [[DOTEXIT:%.*]]
// CHECK2: .exit:
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@__omp_outlined__
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i16* nonnull align 2 dereferenceable(2) [[AA:%.*]]) #[[ATTR0]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK2-NEXT: [[AA_ADDR:%.*]] = alloca i16*, 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 i16* [[AA]], i16** [[AA_ADDR]], align 4
// CHECK2-NEXT: [[TMP0:%.*]] = load i16*, i16** [[AA_ADDR]], align 4
// CHECK2-NEXT: [[TMP1:%.*]] = load i16, i16* [[TMP0]], align 2
// CHECK2-NEXT: [[CONV:%.*]] = sext i16 [[TMP1]] to i32
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 [[CONV]], 1
// CHECK2-NEXT: [[CONV1:%.*]] = trunc i32 [[ADD]] to i16
// CHECK2-NEXT: store i16 [[CONV1]], i16* [[TMP0]], align 2
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l30
// CHECK2-SAME: (i32* nonnull align 4 dereferenceable(4) [[A:%.*]], i16* nonnull align 2 dereferenceable(2) [[AA:%.*]], [10 x i32]* nonnull align 4 dereferenceable(40) [[B:%.*]], i32 [[DOTCAPTURE_EXPR_:%.*]]) #[[ATTR0]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca i32*, align 4
// CHECK2-NEXT: [[AA_ADDR:%.*]] = alloca i16*, align 4
// CHECK2-NEXT: [[B_ADDR:%.*]] = alloca [10 x i32]*, align 4
// CHECK2-NEXT: [[DOTCAPTURE_EXPR__ADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[CAPTURED_VARS_ADDRS:%.*]] = alloca [3 x i8*], align 4
// CHECK2-NEXT: store i32* [[A]], i32** [[A_ADDR]], align 4
// CHECK2-NEXT: store i16* [[AA]], i16** [[AA_ADDR]], align 4
// CHECK2-NEXT: store [10 x i32]* [[B]], [10 x i32]** [[B_ADDR]], align 4
// CHECK2-NEXT: store i32 [[DOTCAPTURE_EXPR_]], i32* [[DOTCAPTURE_EXPR__ADDR]], align 4
// CHECK2-NEXT: [[TMP0:%.*]] = load i32*, i32** [[A_ADDR]], align 4
// CHECK2-NEXT: [[TMP1:%.*]] = load i16*, i16** [[AA_ADDR]], align 4
// CHECK2-NEXT: [[TMP2:%.*]] = load [10 x i32]*, [10 x i32]** [[B_ADDR]], align 4
// CHECK2-NEXT: [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK2-NEXT: call void @__kmpc_spmd_kernel_init(i32 [[NVPTX_NUM_THREADS]], i16 1)
// CHECK2-NEXT: br label [[DOTEXECUTE:%.*]]
// CHECK2: .execute:
// CHECK2-NEXT: [[TMP3:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1]])
// CHECK2-NEXT: [[TMP4:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR__ADDR]], align 4
// CHECK2-NEXT: [[TMP5:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[CAPTURED_VARS_ADDRS]], i32 0, i32 0
// CHECK2-NEXT: [[TMP6:%.*]] = bitcast i32* [[TMP0]] to i8*
// CHECK2-NEXT: store i8* [[TMP6]], i8** [[TMP5]], align 4
// CHECK2-NEXT: [[TMP7:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[CAPTURED_VARS_ADDRS]], i32 0, i32 1
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i16* [[TMP1]] to i8*
// CHECK2-NEXT: store i8* [[TMP8]], i8** [[TMP7]], align 4
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[CAPTURED_VARS_ADDRS]], i32 0, i32 2
// CHECK2-NEXT: [[TMP10:%.*]] = bitcast [10 x i32]* [[TMP2]] to i8*
// CHECK2-NEXT: store i8* [[TMP10]], i8** [[TMP9]], align 4
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast [3 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8**
// CHECK2-NEXT: call void @__kmpc_parallel_51(%struct.ident_t* @[[GLOB1]], i32 [[TMP3]], i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*, i32*, i16*, [10 x i32]*)* @__omp_outlined__1 to i8*), i8* null, i8** [[TMP11]], i32 3)
// CHECK2-NEXT: br label [[DOTOMP_DEINIT:%.*]]
// CHECK2: .omp.deinit:
// CHECK2-NEXT: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
// CHECK2-NEXT: br label [[DOTEXIT:%.*]]
// CHECK2: .exit:
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@__omp_outlined__1
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i32* nonnull align 4 dereferenceable(4) [[A:%.*]], i16* nonnull align 2 dereferenceable(2) [[AA:%.*]], [10 x i32]* nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR0]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca i32*, align 4
// CHECK2-NEXT: [[AA_ADDR:%.*]] = alloca i16*, align 4
// CHECK2-NEXT: [[B_ADDR:%.*]] = alloca [10 x i32]*, 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* [[A]], i32** [[A_ADDR]], align 4
// CHECK2-NEXT: store i16* [[AA]], i16** [[AA_ADDR]], align 4
// CHECK2-NEXT: store [10 x i32]* [[B]], [10 x i32]** [[B_ADDR]], align 4
// CHECK2-NEXT: [[TMP0:%.*]] = load i32*, i32** [[A_ADDR]], align 4
// CHECK2-NEXT: [[TMP1:%.*]] = load i16*, i16** [[AA_ADDR]], align 4
// CHECK2-NEXT: [[TMP2:%.*]] = load [10 x i32]*, [10 x i32]** [[B_ADDR]], align 4
// CHECK2-NEXT: [[TMP3:%.*]] = load i32, i32* [[TMP0]], align 4
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP3]], 1
// CHECK2-NEXT: store i32 [[ADD]], i32* [[TMP0]], align 4
// CHECK2-NEXT: [[TMP4:%.*]] = load i16, i16* [[TMP1]], align 2
// CHECK2-NEXT: [[CONV:%.*]] = sext i16 [[TMP4]] to i32
// CHECK2-NEXT: [[ADD1:%.*]] = add nsw i32 [[CONV]], 1
// CHECK2-NEXT: [[CONV2:%.*]] = trunc i32 [[ADD1]] to i16
// CHECK2-NEXT: store i16 [[CONV2]], i16* [[TMP1]], align 2
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP2]], i32 0, i32 2
// CHECK2-NEXT: [[TMP5:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
// CHECK2-NEXT: [[ADD3:%.*]] = add nsw i32 [[TMP5]], 1
// CHECK2-NEXT: store i32 [[ADD3]], i32* [[ARRAYIDX]], align 4
// CHECK2-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l25
// CHECK3-SAME: (i16* nonnull align 2 dereferenceable(2) [[AA:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[AA_ADDR:%.*]] = alloca i16*, align 4
// CHECK3-NEXT: [[CAPTURED_VARS_ADDRS:%.*]] = alloca [1 x i8*], align 4
// CHECK3-NEXT: store i16* [[AA]], i16** [[AA_ADDR]], align 4
// CHECK3-NEXT: [[TMP0:%.*]] = load i16*, i16** [[AA_ADDR]], align 4
// CHECK3-NEXT: [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK3-NEXT: call void @__kmpc_spmd_kernel_init(i32 [[NVPTX_NUM_THREADS]], i16 1)
// CHECK3-NEXT: br label [[DOTEXECUTE:%.*]]
// CHECK3: .execute:
// CHECK3-NEXT: [[TMP1:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1:[0-9]+]])
// CHECK3-NEXT: [[TMP2:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[CAPTURED_VARS_ADDRS]], i32 0, i32 0
// CHECK3-NEXT: [[TMP3:%.*]] = bitcast i16* [[TMP0]] to i8*
// CHECK3-NEXT: store i8* [[TMP3]], i8** [[TMP2]], align 4
// CHECK3-NEXT: [[TMP4:%.*]] = bitcast [1 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8**
// CHECK3-NEXT: call void @__kmpc_parallel_51(%struct.ident_t* @[[GLOB1]], i32 [[TMP1]], i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*, i16*)* @__omp_outlined__ to i8*), i8* null, i8** [[TMP4]], i32 1)
// CHECK3-NEXT: br label [[DOTOMP_DEINIT:%.*]]
// CHECK3: .omp.deinit:
// CHECK3-NEXT: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
// CHECK3-NEXT: br label [[DOTEXIT:%.*]]
// CHECK3: .exit:
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@__omp_outlined__
// CHECK3-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i16* nonnull align 2 dereferenceable(2) [[AA:%.*]]) #[[ATTR0]] {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK3-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK3-NEXT: [[AA_ADDR:%.*]] = alloca i16*, align 4
// CHECK3-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK3-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 4
// CHECK3-NEXT: store i16* [[AA]], i16** [[AA_ADDR]], align 4
// CHECK3-NEXT: [[TMP0:%.*]] = load i16*, i16** [[AA_ADDR]], align 4
// CHECK3-NEXT: [[TMP1:%.*]] = load i16, i16* [[TMP0]], align 2
// CHECK3-NEXT: [[CONV:%.*]] = sext i16 [[TMP1]] to i32
// CHECK3-NEXT: [[ADD:%.*]] = add nsw i32 [[CONV]], 1
// CHECK3-NEXT: [[CONV1:%.*]] = trunc i32 [[ADD]] to i16
// CHECK3-NEXT: store i16 [[CONV1]], i16* [[TMP0]], align 2
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l30
// CHECK3-SAME: (i32* nonnull align 4 dereferenceable(4) [[A:%.*]], i16* nonnull align 2 dereferenceable(2) [[AA:%.*]], [10 x i32]* nonnull align 4 dereferenceable(40) [[B:%.*]], i32 [[DOTCAPTURE_EXPR_:%.*]]) #[[ATTR0]] {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[A_ADDR:%.*]] = alloca i32*, align 4
// CHECK3-NEXT: [[AA_ADDR:%.*]] = alloca i16*, align 4
// CHECK3-NEXT: [[B_ADDR:%.*]] = alloca [10 x i32]*, align 4
// CHECK3-NEXT: [[DOTCAPTURE_EXPR__ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[CAPTURED_VARS_ADDRS:%.*]] = alloca [3 x i8*], align 4
// CHECK3-NEXT: store i32* [[A]], i32** [[A_ADDR]], align 4
// CHECK3-NEXT: store i16* [[AA]], i16** [[AA_ADDR]], align 4
// CHECK3-NEXT: store [10 x i32]* [[B]], [10 x i32]** [[B_ADDR]], align 4
// CHECK3-NEXT: store i32 [[DOTCAPTURE_EXPR_]], i32* [[DOTCAPTURE_EXPR__ADDR]], align 4
// CHECK3-NEXT: [[TMP0:%.*]] = load i32*, i32** [[A_ADDR]], align 4
// CHECK3-NEXT: [[TMP1:%.*]] = load i16*, i16** [[AA_ADDR]], align 4
// CHECK3-NEXT: [[TMP2:%.*]] = load [10 x i32]*, [10 x i32]** [[B_ADDR]], align 4
// CHECK3-NEXT: [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK3-NEXT: call void @__kmpc_spmd_kernel_init(i32 [[NVPTX_NUM_THREADS]], i16 1)
// CHECK3-NEXT: br label [[DOTEXECUTE:%.*]]
// CHECK3: .execute:
// CHECK3-NEXT: [[TMP3:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1]])
// CHECK3-NEXT: [[TMP4:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR__ADDR]], align 4
// CHECK3-NEXT: [[TMP5:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[CAPTURED_VARS_ADDRS]], i32 0, i32 0
// CHECK3-NEXT: [[TMP6:%.*]] = bitcast i32* [[TMP0]] to i8*
// CHECK3-NEXT: store i8* [[TMP6]], i8** [[TMP5]], align 4
// CHECK3-NEXT: [[TMP7:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[CAPTURED_VARS_ADDRS]], i32 0, i32 1
// CHECK3-NEXT: [[TMP8:%.*]] = bitcast i16* [[TMP1]] to i8*
// CHECK3-NEXT: store i8* [[TMP8]], i8** [[TMP7]], align 4
// CHECK3-NEXT: [[TMP9:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[CAPTURED_VARS_ADDRS]], i32 0, i32 2
// CHECK3-NEXT: [[TMP10:%.*]] = bitcast [10 x i32]* [[TMP2]] to i8*
// CHECK3-NEXT: store i8* [[TMP10]], i8** [[TMP9]], align 4
// CHECK3-NEXT: [[TMP11:%.*]] = bitcast [3 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8**
// CHECK3-NEXT: call void @__kmpc_parallel_51(%struct.ident_t* @[[GLOB1]], i32 [[TMP3]], i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*, i32*, i16*, [10 x i32]*)* @__omp_outlined__1 to i8*), i8* null, i8** [[TMP11]], i32 3)
// CHECK3-NEXT: br label [[DOTOMP_DEINIT:%.*]]
// CHECK3: .omp.deinit:
// CHECK3-NEXT: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
// CHECK3-NEXT: br label [[DOTEXIT:%.*]]
// CHECK3: .exit:
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@__omp_outlined__1
// CHECK3-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i32* nonnull align 4 dereferenceable(4) [[A:%.*]], i16* nonnull align 2 dereferenceable(2) [[AA:%.*]], [10 x i32]* nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR0]] {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK3-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK3-NEXT: [[A_ADDR:%.*]] = alloca i32*, align 4
// CHECK3-NEXT: [[AA_ADDR:%.*]] = alloca i16*, align 4
// CHECK3-NEXT: [[B_ADDR:%.*]] = alloca [10 x i32]*, align 4
// CHECK3-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK3-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 4
// CHECK3-NEXT: store i32* [[A]], i32** [[A_ADDR]], align 4
// CHECK3-NEXT: store i16* [[AA]], i16** [[AA_ADDR]], align 4
// CHECK3-NEXT: store [10 x i32]* [[B]], [10 x i32]** [[B_ADDR]], align 4
// CHECK3-NEXT: [[TMP0:%.*]] = load i32*, i32** [[A_ADDR]], align 4
// CHECK3-NEXT: [[TMP1:%.*]] = load i16*, i16** [[AA_ADDR]], align 4
// CHECK3-NEXT: [[TMP2:%.*]] = load [10 x i32]*, [10 x i32]** [[B_ADDR]], align 4
// CHECK3-NEXT: [[TMP3:%.*]] = load i32, i32* [[TMP0]], align 4
// CHECK3-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP3]], 1
// CHECK3-NEXT: store i32 [[ADD]], i32* [[TMP0]], align 4
// CHECK3-NEXT: [[TMP4:%.*]] = load i16, i16* [[TMP1]], align 2
// CHECK3-NEXT: [[CONV:%.*]] = sext i16 [[TMP4]] to i32
// CHECK3-NEXT: [[ADD1:%.*]] = add nsw i32 [[CONV]], 1
// CHECK3-NEXT: [[CONV2:%.*]] = trunc i32 [[ADD1]] to i16
// CHECK3-NEXT: store i16 [[CONV2]], i16* [[TMP1]], align 2
// CHECK3-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP2]], i32 0, i32 2
// CHECK3-NEXT: [[TMP5:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
// CHECK3-NEXT: [[ADD3:%.*]] = add nsw i32 [[TMP5]], 1
// CHECK3-NEXT: store i32 [[ADD3]], i32* [[ARRAYIDX]], align 4
// CHECK3-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l25
// CHECK4-SAME: (i16* nonnull align 2 dereferenceable(2) [[AA:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[AA_ADDR:%.*]] = alloca i16*, align 8
// CHECK4-NEXT: [[CAPTURED_VARS_ADDRS:%.*]] = alloca [1 x i8*], align 8
// CHECK4-NEXT: store i16* [[AA]], i16** [[AA_ADDR]], align 8
// CHECK4-NEXT: [[TMP0:%.*]] = load i16*, i16** [[AA_ADDR]], align 8
// CHECK4-NEXT: [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK4-NEXT: call void @__kmpc_spmd_kernel_init(i32 [[NVPTX_NUM_THREADS]], i16 1)
// CHECK4-NEXT: br label [[DOTEXECUTE:%.*]]
// CHECK4: .execute:
// CHECK4-NEXT: [[TMP1:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1:[0-9]+]])
// CHECK4-NEXT: [[TMP2:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[CAPTURED_VARS_ADDRS]], i64 0, i64 0
// CHECK4-NEXT: [[TMP3:%.*]] = bitcast i16* [[TMP0]] to i8*
// CHECK4-NEXT: store i8* [[TMP3]], i8** [[TMP2]], align 8
// CHECK4-NEXT: [[TMP4:%.*]] = bitcast [1 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8**
// CHECK4-NEXT: call void @__kmpc_parallel_51(%struct.ident_t* @[[GLOB1]], i32 [[TMP1]], i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*, i16*)* @__omp_outlined__ to i8*), i8* null, i8** [[TMP4]], i64 1)
// CHECK4-NEXT: br label [[DOTOMP_DEINIT:%.*]]
// CHECK4: .omp.deinit:
// CHECK4-NEXT: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
// CHECK4-NEXT: br label [[DOTEXIT:%.*]]
// CHECK4: .exit:
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@__omp_outlined__
// CHECK4-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i16* nonnull align 2 dereferenceable(2) [[AA:%.*]]) #[[ATTR0]] {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK4-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK4-NEXT: [[AA_ADDR:%.*]] = alloca i16*, align 8
// CHECK4-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK4-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK4-NEXT: store i16* [[AA]], i16** [[AA_ADDR]], align 8
// CHECK4-NEXT: [[TMP0:%.*]] = load i16*, i16** [[AA_ADDR]], align 8
// CHECK4-NEXT: [[TMP1:%.*]] = load i16, i16* [[TMP0]], align 2
// CHECK4-NEXT: [[CONV:%.*]] = sext i16 [[TMP1]] to i32
// CHECK4-NEXT: [[ADD:%.*]] = add nsw i32 [[CONV]], 1
// CHECK4-NEXT: [[CONV1:%.*]] = trunc i32 [[ADD]] to i16
// CHECK4-NEXT: store i16 [[CONV1]], i16* [[TMP0]], align 2
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l30
// CHECK4-SAME: (i32* nonnull align 4 dereferenceable(4) [[A:%.*]], i16* nonnull align 2 dereferenceable(2) [[AA:%.*]], [10 x i32]* nonnull align 4 dereferenceable(40) [[B:%.*]], i64 [[DOTCAPTURE_EXPR_:%.*]]) #[[ATTR0]] {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[A_ADDR:%.*]] = alloca i32*, align 8
// CHECK4-NEXT: [[AA_ADDR:%.*]] = alloca i16*, align 8
// CHECK4-NEXT: [[B_ADDR:%.*]] = alloca [10 x i32]*, align 8
// CHECK4-NEXT: [[DOTCAPTURE_EXPR__ADDR:%.*]] = alloca i64, align 8
// CHECK4-NEXT: [[CAPTURED_VARS_ADDRS:%.*]] = alloca [3 x i8*], align 8
// CHECK4-NEXT: store i32* [[A]], i32** [[A_ADDR]], align 8
// CHECK4-NEXT: store i16* [[AA]], i16** [[AA_ADDR]], align 8
// CHECK4-NEXT: store [10 x i32]* [[B]], [10 x i32]** [[B_ADDR]], align 8
// CHECK4-NEXT: store i64 [[DOTCAPTURE_EXPR_]], i64* [[DOTCAPTURE_EXPR__ADDR]], align 8
// CHECK4-NEXT: [[TMP0:%.*]] = load i32*, i32** [[A_ADDR]], align 8
// CHECK4-NEXT: [[TMP1:%.*]] = load i16*, i16** [[AA_ADDR]], align 8
// CHECK4-NEXT: [[TMP2:%.*]] = load [10 x i32]*, [10 x i32]** [[B_ADDR]], align 8
// CHECK4-NEXT: [[CONV:%.*]] = bitcast i64* [[DOTCAPTURE_EXPR__ADDR]] to i32*
// CHECK4-NEXT: [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK4-NEXT: call void @__kmpc_spmd_kernel_init(i32 [[NVPTX_NUM_THREADS]], i16 1)
// CHECK4-NEXT: br label [[DOTEXECUTE:%.*]]
// CHECK4: .execute:
// CHECK4-NEXT: [[TMP3:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1]])
// CHECK4-NEXT: [[TMP4:%.*]] = load i32, i32* [[CONV]], align 8
// CHECK4-NEXT: [[TMP5:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[CAPTURED_VARS_ADDRS]], i64 0, i64 0
// CHECK4-NEXT: [[TMP6:%.*]] = bitcast i32* [[TMP0]] to i8*
// CHECK4-NEXT: store i8* [[TMP6]], i8** [[TMP5]], align 8
// CHECK4-NEXT: [[TMP7:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[CAPTURED_VARS_ADDRS]], i64 0, i64 1
// CHECK4-NEXT: [[TMP8:%.*]] = bitcast i16* [[TMP1]] to i8*
// CHECK4-NEXT: store i8* [[TMP8]], i8** [[TMP7]], align 8
// CHECK4-NEXT: [[TMP9:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[CAPTURED_VARS_ADDRS]], i64 0, i64 2
// CHECK4-NEXT: [[TMP10:%.*]] = bitcast [10 x i32]* [[TMP2]] to i8*
// CHECK4-NEXT: store i8* [[TMP10]], i8** [[TMP9]], align 8
// CHECK4-NEXT: [[TMP11:%.*]] = bitcast [3 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8**
// CHECK4-NEXT: call void @__kmpc_parallel_51(%struct.ident_t* @[[GLOB1]], i32 [[TMP3]], i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*, i32*, i16*, [10 x i32]*)* @__omp_outlined__1 to i8*), i8* null, i8** [[TMP11]], i64 3)
// CHECK4-NEXT: br label [[DOTOMP_DEINIT:%.*]]
// CHECK4: .omp.deinit:
// CHECK4-NEXT: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
// CHECK4-NEXT: br label [[DOTEXIT:%.*]]
// CHECK4: .exit:
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@__omp_outlined__1
// CHECK4-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i32* nonnull align 4 dereferenceable(4) [[A:%.*]], i16* nonnull align 2 dereferenceable(2) [[AA:%.*]], [10 x i32]* nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR0]] {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK4-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK4-NEXT: [[A_ADDR:%.*]] = alloca i32*, align 8
// CHECK4-NEXT: [[AA_ADDR:%.*]] = alloca i16*, align 8
// CHECK4-NEXT: [[B_ADDR:%.*]] = alloca [10 x i32]*, align 8
// CHECK4-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK4-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK4-NEXT: store i32* [[A]], i32** [[A_ADDR]], align 8
// CHECK4-NEXT: store i16* [[AA]], i16** [[AA_ADDR]], align 8
// CHECK4-NEXT: store [10 x i32]* [[B]], [10 x i32]** [[B_ADDR]], align 8
// CHECK4-NEXT: [[TMP0:%.*]] = load i32*, i32** [[A_ADDR]], align 8
// CHECK4-NEXT: [[TMP1:%.*]] = load i16*, i16** [[AA_ADDR]], align 8
// CHECK4-NEXT: [[TMP2:%.*]] = load [10 x i32]*, [10 x i32]** [[B_ADDR]], align 8
// CHECK4-NEXT: [[TMP3:%.*]] = load i32, i32* [[TMP0]], align 4
// CHECK4-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP3]], 1
// CHECK4-NEXT: store i32 [[ADD]], i32* [[TMP0]], align 4
// CHECK4-NEXT: [[TMP4:%.*]] = load i16, i16* [[TMP1]], align 2
// CHECK4-NEXT: [[CONV:%.*]] = sext i16 [[TMP4]] to i32
// CHECK4-NEXT: [[ADD1:%.*]] = add nsw i32 [[CONV]], 1
// CHECK4-NEXT: [[CONV2:%.*]] = trunc i32 [[ADD1]] to i16
// CHECK4-NEXT: store i16 [[CONV2]], i16* [[TMP1]], align 2
// CHECK4-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP2]], i64 0, i64 2
// CHECK4-NEXT: [[TMP5:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
// CHECK4-NEXT: [[ADD3:%.*]] = add nsw i32 [[TMP5]], 1
// CHECK4-NEXT: store i32 [[ADD3]], i32* [[ARRAYIDX]], align 4
// CHECK4-NEXT: ret void
//
//
// CHECK5-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l25
// CHECK5-SAME: (i16* nonnull align 2 dereferenceable(2) [[AA:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK5-NEXT: entry:
// CHECK5-NEXT: [[AA_ADDR:%.*]] = alloca i16*, align 4
// CHECK5-NEXT: [[CAPTURED_VARS_ADDRS:%.*]] = alloca [1 x i8*], align 4
// CHECK5-NEXT: store i16* [[AA]], i16** [[AA_ADDR]], align 4
// CHECK5-NEXT: [[TMP0:%.*]] = load i16*, i16** [[AA_ADDR]], align 4
// CHECK5-NEXT: [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK5-NEXT: call void @__kmpc_spmd_kernel_init(i32 [[NVPTX_NUM_THREADS]], i16 1)
// CHECK5-NEXT: br label [[DOTEXECUTE:%.*]]
// CHECK5: .execute:
// CHECK5-NEXT: [[TMP1:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1:[0-9]+]])
// CHECK5-NEXT: [[TMP2:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[CAPTURED_VARS_ADDRS]], i32 0, i32 0
// CHECK5-NEXT: [[TMP3:%.*]] = bitcast i16* [[TMP0]] to i8*
// CHECK5-NEXT: store i8* [[TMP3]], i8** [[TMP2]], align 4
// CHECK5-NEXT: [[TMP4:%.*]] = bitcast [1 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8**
// CHECK5-NEXT: call void @__kmpc_parallel_51(%struct.ident_t* @[[GLOB1]], i32 [[TMP1]], i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*, i16*)* @__omp_outlined__ to i8*), i8* null, i8** [[TMP4]], i32 1)
// CHECK5-NEXT: br label [[DOTOMP_DEINIT:%.*]]
// CHECK5: .omp.deinit:
// CHECK5-NEXT: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
// CHECK5-NEXT: br label [[DOTEXIT:%.*]]
// CHECK5: .exit:
// CHECK5-NEXT: ret void
//
//
// CHECK5-LABEL: define {{[^@]+}}@__omp_outlined__
// CHECK5-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i16* nonnull align 2 dereferenceable(2) [[AA:%.*]]) #[[ATTR0]] {
// CHECK5-NEXT: entry:
// CHECK5-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK5-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK5-NEXT: [[AA_ADDR:%.*]] = alloca i16*, align 4
// CHECK5-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK5-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 4
// CHECK5-NEXT: store i16* [[AA]], i16** [[AA_ADDR]], align 4
// CHECK5-NEXT: [[TMP0:%.*]] = load i16*, i16** [[AA_ADDR]], align 4
// CHECK5-NEXT: [[TMP1:%.*]] = load i16, i16* [[TMP0]], align 2
// CHECK5-NEXT: [[CONV:%.*]] = sext i16 [[TMP1]] to i32
// CHECK5-NEXT: [[ADD:%.*]] = add nsw i32 [[CONV]], 1
// CHECK5-NEXT: [[CONV1:%.*]] = trunc i32 [[ADD]] to i16
// CHECK5-NEXT: store i16 [[CONV1]], i16* [[TMP0]], align 2
// CHECK5-NEXT: ret void
//
//
// CHECK5-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l30
// CHECK5-SAME: (i32* nonnull align 4 dereferenceable(4) [[A:%.*]], i16* nonnull align 2 dereferenceable(2) [[AA:%.*]], [10 x i32]* nonnull align 4 dereferenceable(40) [[B:%.*]], i32 [[DOTCAPTURE_EXPR_:%.*]]) #[[ATTR0]] {
// CHECK5-NEXT: entry:
// CHECK5-NEXT: [[A_ADDR:%.*]] = alloca i32*, align 4
// CHECK5-NEXT: [[AA_ADDR:%.*]] = alloca i16*, align 4
// CHECK5-NEXT: [[B_ADDR:%.*]] = alloca [10 x i32]*, align 4
// CHECK5-NEXT: [[DOTCAPTURE_EXPR__ADDR:%.*]] = alloca i32, align 4
// CHECK5-NEXT: [[CAPTURED_VARS_ADDRS:%.*]] = alloca [3 x i8*], align 4
// CHECK5-NEXT: store i32* [[A]], i32** [[A_ADDR]], align 4
// CHECK5-NEXT: store i16* [[AA]], i16** [[AA_ADDR]], align 4
// CHECK5-NEXT: store [10 x i32]* [[B]], [10 x i32]** [[B_ADDR]], align 4
// CHECK5-NEXT: store i32 [[DOTCAPTURE_EXPR_]], i32* [[DOTCAPTURE_EXPR__ADDR]], align 4
// CHECK5-NEXT: [[TMP0:%.*]] = load i32*, i32** [[A_ADDR]], align 4
// CHECK5-NEXT: [[TMP1:%.*]] = load i16*, i16** [[AA_ADDR]], align 4
// CHECK5-NEXT: [[TMP2:%.*]] = load [10 x i32]*, [10 x i32]** [[B_ADDR]], align 4
// CHECK5-NEXT: [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK5-NEXT: call void @__kmpc_spmd_kernel_init(i32 [[NVPTX_NUM_THREADS]], i16 1)
// CHECK5-NEXT: br label [[DOTEXECUTE:%.*]]
// CHECK5: .execute:
// CHECK5-NEXT: [[TMP3:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1]])
// CHECK5-NEXT: [[TMP4:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR__ADDR]], align 4
// CHECK5-NEXT: [[TMP5:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[CAPTURED_VARS_ADDRS]], i32 0, i32 0
// CHECK5-NEXT: [[TMP6:%.*]] = bitcast i32* [[TMP0]] to i8*
// CHECK5-NEXT: store i8* [[TMP6]], i8** [[TMP5]], align 4
// CHECK5-NEXT: [[TMP7:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[CAPTURED_VARS_ADDRS]], i32 0, i32 1
// CHECK5-NEXT: [[TMP8:%.*]] = bitcast i16* [[TMP1]] to i8*
// CHECK5-NEXT: store i8* [[TMP8]], i8** [[TMP7]], align 4
// CHECK5-NEXT: [[TMP9:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[CAPTURED_VARS_ADDRS]], i32 0, i32 2
// CHECK5-NEXT: [[TMP10:%.*]] = bitcast [10 x i32]* [[TMP2]] to i8*
// CHECK5-NEXT: store i8* [[TMP10]], i8** [[TMP9]], align 4
// CHECK5-NEXT: [[TMP11:%.*]] = bitcast [3 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8**
// CHECK5-NEXT: call void @__kmpc_parallel_51(%struct.ident_t* @[[GLOB1]], i32 [[TMP3]], i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*, i32*, i16*, [10 x i32]*)* @__omp_outlined__1 to i8*), i8* null, i8** [[TMP11]], i32 3)
// CHECK5-NEXT: br label [[DOTOMP_DEINIT:%.*]]
// CHECK5: .omp.deinit:
// CHECK5-NEXT: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
// CHECK5-NEXT: br label [[DOTEXIT:%.*]]
// CHECK5: .exit:
// CHECK5-NEXT: ret void
//
//
// CHECK5-LABEL: define {{[^@]+}}@__omp_outlined__1
// CHECK5-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i32* nonnull align 4 dereferenceable(4) [[A:%.*]], i16* nonnull align 2 dereferenceable(2) [[AA:%.*]], [10 x i32]* nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR0]] {
// CHECK5-NEXT: entry:
// CHECK5-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK5-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK5-NEXT: [[A_ADDR:%.*]] = alloca i32*, align 4
// CHECK5-NEXT: [[AA_ADDR:%.*]] = alloca i16*, align 4
// CHECK5-NEXT: [[B_ADDR:%.*]] = alloca [10 x i32]*, align 4
// CHECK5-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK5-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 4
// CHECK5-NEXT: store i32* [[A]], i32** [[A_ADDR]], align 4
// CHECK5-NEXT: store i16* [[AA]], i16** [[AA_ADDR]], align 4
// CHECK5-NEXT: store [10 x i32]* [[B]], [10 x i32]** [[B_ADDR]], align 4
// CHECK5-NEXT: [[TMP0:%.*]] = load i32*, i32** [[A_ADDR]], align 4
// CHECK5-NEXT: [[TMP1:%.*]] = load i16*, i16** [[AA_ADDR]], align 4
// CHECK5-NEXT: [[TMP2:%.*]] = load [10 x i32]*, [10 x i32]** [[B_ADDR]], align 4
// CHECK5-NEXT: [[TMP3:%.*]] = load i32, i32* [[TMP0]], align 4
// CHECK5-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP3]], 1
// CHECK5-NEXT: store i32 [[ADD]], i32* [[TMP0]], align 4
// CHECK5-NEXT: [[TMP4:%.*]] = load i16, i16* [[TMP1]], align 2
// CHECK5-NEXT: [[CONV:%.*]] = sext i16 [[TMP4]] to i32
// CHECK5-NEXT: [[ADD1:%.*]] = add nsw i32 [[CONV]], 1
// CHECK5-NEXT: [[CONV2:%.*]] = trunc i32 [[ADD1]] to i16
// CHECK5-NEXT: store i16 [[CONV2]], i16* [[TMP1]], align 2
// CHECK5-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP2]], i32 0, i32 2
// CHECK5-NEXT: [[TMP5:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
// CHECK5-NEXT: [[ADD3:%.*]] = add nsw i32 [[TMP5]], 1
// CHECK5-NEXT: store i32 [[ADD3]], i32* [[ARRAYIDX]], align 4
// CHECK5-NEXT: ret void
//
//
// CHECK6-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l25
// CHECK6-SAME: (i16* nonnull align 2 dereferenceable(2) [[AA:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK6-NEXT: entry:
// CHECK6-NEXT: [[AA_ADDR:%.*]] = alloca i16*, align 4
// CHECK6-NEXT: [[CAPTURED_VARS_ADDRS:%.*]] = alloca [1 x i8*], align 4
// CHECK6-NEXT: store i16* [[AA]], i16** [[AA_ADDR]], align 4
// CHECK6-NEXT: [[TMP0:%.*]] = load i16*, i16** [[AA_ADDR]], align 4
// CHECK6-NEXT: [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK6-NEXT: call void @__kmpc_spmd_kernel_init(i32 [[NVPTX_NUM_THREADS]], i16 1)
// CHECK6-NEXT: br label [[DOTEXECUTE:%.*]]
// CHECK6: .execute:
// CHECK6-NEXT: [[TMP1:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1:[0-9]+]])
// CHECK6-NEXT: [[TMP2:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[CAPTURED_VARS_ADDRS]], i32 0, i32 0
// CHECK6-NEXT: [[TMP3:%.*]] = bitcast i16* [[TMP0]] to i8*
// CHECK6-NEXT: store i8* [[TMP3]], i8** [[TMP2]], align 4
// CHECK6-NEXT: [[TMP4:%.*]] = bitcast [1 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8**
// CHECK6-NEXT: call void @__kmpc_parallel_51(%struct.ident_t* @[[GLOB1]], i32 [[TMP1]], i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*, i16*)* @__omp_outlined__ to i8*), i8* null, i8** [[TMP4]], i32 1)
// CHECK6-NEXT: br label [[DOTOMP_DEINIT:%.*]]
// CHECK6: .omp.deinit:
// CHECK6-NEXT: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
// CHECK6-NEXT: br label [[DOTEXIT:%.*]]
// CHECK6: .exit:
// CHECK6-NEXT: ret void
//
//
// CHECK6-LABEL: define {{[^@]+}}@__omp_outlined__
// CHECK6-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i16* nonnull align 2 dereferenceable(2) [[AA:%.*]]) #[[ATTR0]] {
// CHECK6-NEXT: entry:
// CHECK6-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK6-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK6-NEXT: [[AA_ADDR:%.*]] = alloca i16*, align 4
// CHECK6-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK6-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 4
// CHECK6-NEXT: store i16* [[AA]], i16** [[AA_ADDR]], align 4
// CHECK6-NEXT: [[TMP0:%.*]] = load i16*, i16** [[AA_ADDR]], align 4
// CHECK6-NEXT: [[TMP1:%.*]] = load i16, i16* [[TMP0]], align 2
// CHECK6-NEXT: [[CONV:%.*]] = sext i16 [[TMP1]] to i32
// CHECK6-NEXT: [[ADD:%.*]] = add nsw i32 [[CONV]], 1
// CHECK6-NEXT: [[CONV1:%.*]] = trunc i32 [[ADD]] to i16
// CHECK6-NEXT: store i16 [[CONV1]], i16* [[TMP0]], align 2
// CHECK6-NEXT: ret void
//
//
// CHECK6-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l30
// CHECK6-SAME: (i32* nonnull align 4 dereferenceable(4) [[A:%.*]], i16* nonnull align 2 dereferenceable(2) [[AA:%.*]], [10 x i32]* nonnull align 4 dereferenceable(40) [[B:%.*]], i32 [[DOTCAPTURE_EXPR_:%.*]]) #[[ATTR0]] {
// CHECK6-NEXT: entry:
// CHECK6-NEXT: [[A_ADDR:%.*]] = alloca i32*, align 4
// CHECK6-NEXT: [[AA_ADDR:%.*]] = alloca i16*, align 4
// CHECK6-NEXT: [[B_ADDR:%.*]] = alloca [10 x i32]*, align 4
// CHECK6-NEXT: [[DOTCAPTURE_EXPR__ADDR:%.*]] = alloca i32, align 4
// CHECK6-NEXT: [[CAPTURED_VARS_ADDRS:%.*]] = alloca [3 x i8*], align 4
// CHECK6-NEXT: store i32* [[A]], i32** [[A_ADDR]], align 4
// CHECK6-NEXT: store i16* [[AA]], i16** [[AA_ADDR]], align 4
// CHECK6-NEXT: store [10 x i32]* [[B]], [10 x i32]** [[B_ADDR]], align 4
// CHECK6-NEXT: store i32 [[DOTCAPTURE_EXPR_]], i32* [[DOTCAPTURE_EXPR__ADDR]], align 4
// CHECK6-NEXT: [[TMP0:%.*]] = load i32*, i32** [[A_ADDR]], align 4
// CHECK6-NEXT: [[TMP1:%.*]] = load i16*, i16** [[AA_ADDR]], align 4
// CHECK6-NEXT: [[TMP2:%.*]] = load [10 x i32]*, [10 x i32]** [[B_ADDR]], align 4
// CHECK6-NEXT: [[NVPTX_NUM_THREADS:%.*]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
// CHECK6-NEXT: call void @__kmpc_spmd_kernel_init(i32 [[NVPTX_NUM_THREADS]], i16 1)
// CHECK6-NEXT: br label [[DOTEXECUTE:%.*]]
// CHECK6: .execute:
// CHECK6-NEXT: [[TMP3:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1]])
// CHECK6-NEXT: [[TMP4:%.*]] = load i32, i32* [[DOTCAPTURE_EXPR__ADDR]], align 4
// CHECK6-NEXT: [[TMP5:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[CAPTURED_VARS_ADDRS]], i32 0, i32 0
// CHECK6-NEXT: [[TMP6:%.*]] = bitcast i32* [[TMP0]] to i8*
// CHECK6-NEXT: store i8* [[TMP6]], i8** [[TMP5]], align 4
// CHECK6-NEXT: [[TMP7:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[CAPTURED_VARS_ADDRS]], i32 0, i32 1
// CHECK6-NEXT: [[TMP8:%.*]] = bitcast i16* [[TMP1]] to i8*
// CHECK6-NEXT: store i8* [[TMP8]], i8** [[TMP7]], align 4
// CHECK6-NEXT: [[TMP9:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[CAPTURED_VARS_ADDRS]], i32 0, i32 2
// CHECK6-NEXT: [[TMP10:%.*]] = bitcast [10 x i32]* [[TMP2]] to i8*
// CHECK6-NEXT: store i8* [[TMP10]], i8** [[TMP9]], align 4
// CHECK6-NEXT: [[TMP11:%.*]] = bitcast [3 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8**
// CHECK6-NEXT: call void @__kmpc_parallel_51(%struct.ident_t* @[[GLOB1]], i32 [[TMP3]], i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*, i32*, i16*, [10 x i32]*)* @__omp_outlined__1 to i8*), i8* null, i8** [[TMP11]], i32 3)
// CHECK6-NEXT: br label [[DOTOMP_DEINIT:%.*]]
// CHECK6: .omp.deinit:
// CHECK6-NEXT: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
// CHECK6-NEXT: br label [[DOTEXIT:%.*]]
// CHECK6: .exit:
// CHECK6-NEXT: ret void
//
//
// CHECK6-LABEL: define {{[^@]+}}@__omp_outlined__1
// CHECK6-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i32* nonnull align 4 dereferenceable(4) [[A:%.*]], i16* nonnull align 2 dereferenceable(2) [[AA:%.*]], [10 x i32]* nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR0]] {
// CHECK6-NEXT: entry:
// CHECK6-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK6-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK6-NEXT: [[A_ADDR:%.*]] = alloca i32*, align 4
// CHECK6-NEXT: [[AA_ADDR:%.*]] = alloca i16*, align 4
// CHECK6-NEXT: [[B_ADDR:%.*]] = alloca [10 x i32]*, align 4
// CHECK6-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK6-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 4
// CHECK6-NEXT: store i32* [[A]], i32** [[A_ADDR]], align 4
// CHECK6-NEXT: store i16* [[AA]], i16** [[AA_ADDR]], align 4
// CHECK6-NEXT: store [10 x i32]* [[B]], [10 x i32]** [[B_ADDR]], align 4
// CHECK6-NEXT: [[TMP0:%.*]] = load i32*, i32** [[A_ADDR]], align 4
// CHECK6-NEXT: [[TMP1:%.*]] = load i16*, i16** [[AA_ADDR]], align 4
// CHECK6-NEXT: [[TMP2:%.*]] = load [10 x i32]*, [10 x i32]** [[B_ADDR]], align 4
// CHECK6-NEXT: [[TMP3:%.*]] = load i32, i32* [[TMP0]], align 4
// CHECK6-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP3]], 1
// CHECK6-NEXT: store i32 [[ADD]], i32* [[TMP0]], align 4
// CHECK6-NEXT: [[TMP4:%.*]] = load i16, i16* [[TMP1]], align 2
// CHECK6-NEXT: [[CONV:%.*]] = sext i16 [[TMP4]] to i32
// CHECK6-NEXT: [[ADD1:%.*]] = add nsw i32 [[CONV]], 1
// CHECK6-NEXT: [[CONV2:%.*]] = trunc i32 [[ADD1]] to i16
// CHECK6-NEXT: store i16 [[CONV2]], i16* [[TMP1]], align 2
// CHECK6-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [10 x i32], [10 x i32]* [[TMP2]], i32 0, i32 2
// CHECK6-NEXT: [[TMP5:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
// CHECK6-NEXT: [[ADD3:%.*]] = add nsw i32 [[TMP5]], 1
// CHECK6-NEXT: store i32 [[ADD3]], i32* [[ARRAYIDX]], align 4
// CHECK6-NEXT: ret void
//