4376fbd793
Summary: We use this `dyn_ptr` argument in Clang/OpenMP to handle the `KernelLaunchEnvironment`. This is a per-kernel argument used to share some information. Currenetly, it's prepended to the argument list and we generate storage for it in the runtime. This is bad for a few reasons: 1. It changes the ABI by shifting user arguments 2. It cannot be trivially be left uninitialized if unused 3. The runtime must allocate its own memory for it This PR changes it to be appended instead. Additionally, space for this is always emitted. This means the OMPIRBuilder itself will provide the storage, we simply need to populate it in the runtime if it is used. This means that if it's unused we don't always pay the cost and it's easier for non-OpenMP users to ignore it. Backward compatibility is maintained by auto-upgrading the kernel arguments. In `libomptarget` we completely allocate a new buffer to store this in the new format. The plugins still need to respect the old ABI of the called device object, so we simply rotate it if it's the old version.
88 lines
5.7 KiB
C++
88 lines
5.7 KiB
C++
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --include-generated-funcs --replace-value-regex "__omp_offloading_[0-9a-z]+_[0-9a-z]+" "reduction_ size[.].+[.]" "pl_cond[.].+[.|,]" --prefix-filecheck-ir-name _ --version 2
|
|
// RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu -fopenmp -fopenmp-version=51 -emit-llvm %s -o - | FileCheck --check-prefix=OMP51 %s
|
|
// RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu -fopenmp -fopenmp-version=51 -x c++ -std=c++11 -emit-pch -o %t %s
|
|
// RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu -fopenmp -fopenmp-version=51 -x c++ -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix=OMP51
|
|
|
|
// expected-no-diagnostics
|
|
|
|
#ifndef HEADER
|
|
#define HEADER
|
|
|
|
int thread_limit_target_parallel() {
|
|
|
|
// Check that the offloading function is called after setting thread_limit in the task entry function
|
|
#pragma omp target parallel thread_limit(2)
|
|
{}
|
|
|
|
return 0;
|
|
}
|
|
|
|
#endif
|
|
// OMP51-LABEL: define dso_local noundef i32 @_Z28thread_limit_target_parallelv
|
|
// OMP51-SAME: () #[[ATTR0:[0-9]+]] {
|
|
// OMP51-NEXT: entry:
|
|
// OMP51-NEXT: [[AGG_CAPTURED:%.*]] = alloca [[STRUCT_ANON:%.*]], align 1
|
|
// OMP51-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1:[0-9]+]])
|
|
// OMP51-NEXT: [[TMP1:%.*]] = call ptr @__kmpc_omp_task_alloc(ptr @[[GLOB1]], i32 [[TMP0]], i32 1, i64 40, i64 1, ptr @.omp_task_entry.)
|
|
// OMP51-NEXT: [[TMP2:%.*]] = getelementptr inbounds nuw [[STRUCT_KMP_TASK_T_WITH_PRIVATES:%.*]], ptr [[TMP1]], i32 0, i32 0
|
|
// OMP51-NEXT: call void @__kmpc_omp_task_begin_if0(ptr @[[GLOB1]], i32 [[TMP0]], ptr [[TMP1]])
|
|
// OMP51-NEXT: [[TMP3:%.*]] = call i32 @.omp_task_entry.(i32 [[TMP0]], ptr [[TMP1]]) #[[ATTR2:[0-9]+]]
|
|
// OMP51-NEXT: call void @__kmpc_omp_task_complete_if0(ptr @[[GLOB1]], i32 [[TMP0]], ptr [[TMP1]])
|
|
// OMP51-NEXT: ret i32 0
|
|
//
|
|
//
|
|
// OMP51-LABEL: define internal void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z28thread_limit_target_parallelv_l14
|
|
// OMP51-SAME: (ptr noalias noundef [[DYN_PTR:%.*]]) #[[ATTR1:[0-9]+]] {
|
|
// OMP51-NEXT: entry:
|
|
// OMP51-NEXT: [[DYN_PTR_ADDR:%.*]] = alloca ptr, align 8
|
|
// OMP51-NEXT: store ptr [[DYN_PTR]], ptr [[DYN_PTR_ADDR]], align 8
|
|
// OMP51-NEXT: call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 0, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z28thread_limit_target_parallelv_l14.omp_outlined)
|
|
// OMP51-NEXT: ret void
|
|
//
|
|
//
|
|
// OMP51-LABEL: define internal void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z28thread_limit_target_parallelv_l14.omp_outlined
|
|
// OMP51-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]]) #[[ATTR1]] {
|
|
// OMP51-NEXT: entry:
|
|
// OMP51-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
|
|
// OMP51-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
|
|
// OMP51-NEXT: store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// OMP51-NEXT: store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
|
|
// OMP51-NEXT: ret void
|
|
//
|
|
//
|
|
// OMP51-LABEL: define internal noundef i32 @.omp_task_entry.
|
|
// OMP51-SAME: (i32 noundef [[TMP0:%.*]], ptr noalias noundef [[TMP1:%.*]]) #[[ATTR3:[0-9]+]] {
|
|
// OMP51-NEXT: entry:
|
|
// OMP51-NEXT: [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
|
|
// OMP51-NEXT: [[DOTPART_ID__ADDR_I:%.*]] = alloca ptr, align 8
|
|
// OMP51-NEXT: [[DOTPRIVATES__ADDR_I:%.*]] = alloca ptr, align 8
|
|
// OMP51-NEXT: [[DOTCOPY_FN__ADDR_I:%.*]] = alloca ptr, align 8
|
|
// OMP51-NEXT: [[DOTTASK_T__ADDR_I:%.*]] = alloca ptr, align 8
|
|
// OMP51-NEXT: [[__CONTEXT_ADDR_I:%.*]] = alloca ptr, align 8
|
|
// OMP51-NEXT: [[DOTADDR:%.*]] = alloca i32, align 4
|
|
// OMP51-NEXT: [[DOTADDR1:%.*]] = alloca ptr, align 8
|
|
// OMP51-NEXT: store i32 [[TMP0]], ptr [[DOTADDR]], align 4
|
|
// OMP51-NEXT: store ptr [[TMP1]], ptr [[DOTADDR1]], align 8
|
|
// OMP51-NEXT: [[TMP2:%.*]] = load i32, ptr [[DOTADDR]], align 4
|
|
// OMP51-NEXT: [[TMP3:%.*]] = load ptr, ptr [[DOTADDR1]], align 8
|
|
// OMP51-NEXT: [[TMP4:%.*]] = getelementptr inbounds nuw [[STRUCT_KMP_TASK_T_WITH_PRIVATES:%.*]], ptr [[TMP3]], i32 0, i32 0
|
|
// OMP51-NEXT: [[TMP5:%.*]] = getelementptr inbounds nuw [[STRUCT_KMP_TASK_T:%.*]], ptr [[TMP4]], i32 0, i32 2
|
|
// OMP51-NEXT: [[TMP6:%.*]] = getelementptr inbounds nuw [[STRUCT_KMP_TASK_T]], ptr [[TMP4]], i32 0, i32 0
|
|
// OMP51-NEXT: [[TMP7:%.*]] = load ptr, ptr [[TMP6]], align 8
|
|
// OMP51-NEXT: call void @llvm.experimental.noalias.scope.decl(metadata [[META4:![0-9]+]])
|
|
// OMP51-NEXT: call void @llvm.experimental.noalias.scope.decl(metadata [[META7:![0-9]+]])
|
|
// OMP51-NEXT: call void @llvm.experimental.noalias.scope.decl(metadata [[META9:![0-9]+]])
|
|
// OMP51-NEXT: call void @llvm.experimental.noalias.scope.decl(metadata [[META11:![0-9]+]])
|
|
// OMP51-NEXT: store i32 [[TMP2]], ptr [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias [[META13:![0-9]+]]
|
|
// OMP51-NEXT: store ptr [[TMP5]], ptr [[DOTPART_ID__ADDR_I]], align 8, !noalias [[META13]]
|
|
// OMP51-NEXT: store ptr null, ptr [[DOTPRIVATES__ADDR_I]], align 8, !noalias [[META13]]
|
|
// OMP51-NEXT: store ptr null, ptr [[DOTCOPY_FN__ADDR_I]], align 8, !noalias [[META13]]
|
|
// OMP51-NEXT: store ptr [[TMP3]], ptr [[DOTTASK_T__ADDR_I]], align 8, !noalias [[META13]]
|
|
// OMP51-NEXT: store ptr [[TMP7]], ptr [[__CONTEXT_ADDR_I]], align 8, !noalias [[META13]]
|
|
// OMP51-NEXT: [[TMP8:%.*]] = load ptr, ptr [[__CONTEXT_ADDR_I]], align 8, !noalias [[META13]]
|
|
// OMP51-NEXT: [[TMP9:%.*]] = load i32, ptr [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias [[META13]]
|
|
// OMP51-NEXT: call void @__kmpc_set_thread_limit(ptr @[[GLOB1]], i32 [[TMP9]], i32 2)
|
|
// OMP51-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z28thread_limit_target_parallelv_l14(ptr null) #[[ATTR2]]
|
|
// OMP51-NEXT: ret i32 0
|
|
//
|