shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
llvm-project/clang/test/OpenMP/taskgroup_codegen.cpp
Tom Eccles f7daa9d302
[mlir][OpenMP] fix crash outlining infinite loop (#129872) 
Previously an extra block was created by splitting the previous exit
block. This produced incorrect results when the outlined region
statically never terminated because then there wouldn't be a valid exit
block for the outlined region, this caused this newly added block to
have an incoming edge from outside of the outlining region, which caused
outlining to fail.

So far as I can tell this extra block no longer serves any purpose. The
comment says it is supposed to collate multiple control flow edges into
one place, but the code as it is now does not achieve this. In fact, as
can be seen from the changes to lit tests, this block was not actually
outlined in the end. This is because there are actually two code
extractors: one in the callback for creating a parallel op which is used
to find what the input/output variables are (which does have this block
added to it), and another one which actually does the outlining (which
this block was not added to).

Tested with the gfortran and fujitsu test suites.

Fixes #112884
2025-03-07 11:02:52 +00:00

254 lines
13 KiB
C++
Raw Blame History

// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --function-signature --include-generated-funcs --replace-value-regex "__omp_offloading_[0-9a-z]+_[0-9a-z]+" "reduction_size[.].+[.]" "pl_cond[.].+[.|,]" --prefix-filecheck-ir-name _
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple x86_64-unknown-unknown -emit-llvm %s -fexceptions -fcxx-exceptions -o - | FileCheck %s --check-prefix=CHECK1
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK1
// RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -fopenmp -fexceptions -fcxx-exceptions -debug-info-kind=line-tables-only -x c++ -emit-llvm %s -o - | FileCheck %s --check-prefix=DEBUG1
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -emit-llvm %s -fexceptions -fcxx-exceptions -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -fopenmp-simd -fexceptions -fcxx-exceptions -debug-info-kind=line-tables-only -x c++ -emit-llvm %s -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-enable-irbuilder -x c++ -triple x86_64-unknown-unknown -emit-llvm %s -fexceptions -fcxx-exceptions -o - | FileCheck %s --check-prefix=CHECK2
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
void foo() { extern void mayThrow(); mayThrow(); }
int main() {
char a;
#pragma omp taskgroup
a = 2;
#pragma omp taskgroup
foo();
return a;
}
void parallel_taskgroup() {
#pragma omp parallel
#pragma omp taskgroup
foo();
}
#endif
// CHECK1-LABEL: define {{[^@]+}}@_Z3foov
// CHECK1-SAME: () #[[ATTR0:[0-9]+]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: call void @_Z8mayThrowv()
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@main
// CHECK1-SAME: () #[[ATTR2:[0-9]+]] personality ptr @__gxx_personality_v0 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[A:%.*]] = alloca i8, align 1
// CHECK1-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1:[0-9]+]])
// CHECK1-NEXT: store i32 0, ptr [[RETVAL]], align 4
// CHECK1-NEXT: call void @__kmpc_taskgroup(ptr @[[GLOB1]], i32 [[TMP0]])
// CHECK1-NEXT: store i8 2, ptr [[A]], align 1
// CHECK1-NEXT: call void @__kmpc_end_taskgroup(ptr @[[GLOB1]], i32 [[TMP0]])
// CHECK1-NEXT: call void @__kmpc_taskgroup(ptr @[[GLOB1]], i32 [[TMP0]])
// CHECK1-NEXT: invoke void @_Z3foov()
// CHECK1-NEXT: to label [[INVOKE_CONT:%.*]] unwind label [[TERMINATE_LPAD:%.*]]
// CHECK1: invoke.cont:
// CHECK1-NEXT: call void @__kmpc_end_taskgroup(ptr @[[GLOB1]], i32 [[TMP0]])
// CHECK1-NEXT: [[TMP1:%.*]] = load i8, ptr [[A]], align 1
// CHECK1-NEXT: [[CONV:%.*]] = sext i8 [[TMP1]] to i32
// CHECK1-NEXT: ret i32 [[CONV]]
// CHECK1: terminate.lpad:
// CHECK1-NEXT: [[TMP2:%.*]] = landingpad { ptr, i32 }
// CHECK1-NEXT: catch ptr null
// CHECK1-NEXT: [[TMP3:%.*]] = extractvalue { ptr, i32 } [[TMP2]], 0
// CHECK1-NEXT: call void @__clang_call_terminate(ptr [[TMP3]]) #[[ATTR8:[0-9]+]]
// CHECK1-NEXT: unreachable
//
//
// CHECK1-LABEL: define {{[^@]+}}@__clang_call_terminate
// CHECK1-SAME: (ptr noundef [[TMP0:%.*]]) #[[ATTR5:[0-9]+]] comdat {
// CHECK1-NEXT: [[TMP2:%.*]] = call ptr @__cxa_begin_catch(ptr [[TMP0]]) #[[ATTR3:[0-9]+]]
// CHECK1-NEXT: call void @_ZSt9terminatev() #[[ATTR8]]
// CHECK1-NEXT: unreachable
//
//
// CHECK1-LABEL: define {{[^@]+}}@_Z18parallel_taskgroupv
// CHECK1-SAME: () #[[ATTR6:[0-9]+]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 0, ptr @_Z18parallel_taskgroupv.omp_outlined)
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_Z18parallel_taskgroupv.omp_outlined
// CHECK1-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]]) #[[ATTR7:[0-9]+]] personality ptr @__gxx_personality_v0 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT: store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: [[TMP1:%.*]] = load i32, ptr [[TMP0]], align 4
// CHECK1-NEXT: call void @__kmpc_taskgroup(ptr @[[GLOB1]], i32 [[TMP1]])
// CHECK1-NEXT: invoke void @_Z3foov()
// CHECK1-NEXT: to label [[INVOKE_CONT:%.*]] unwind label [[TERMINATE_LPAD:%.*]]
// CHECK1: invoke.cont:
// CHECK1-NEXT: call void @__kmpc_end_taskgroup(ptr @[[GLOB1]], i32 [[TMP1]])
// CHECK1-NEXT: ret void
// CHECK1: terminate.lpad:
// CHECK1-NEXT: [[TMP2:%.*]] = landingpad { ptr, i32 }
// CHECK1-NEXT: catch ptr null
// CHECK1-NEXT: [[TMP3:%.*]] = extractvalue { ptr, i32 } [[TMP2]], 0
// CHECK1-NEXT: call void @__clang_call_terminate(ptr [[TMP3]]) #[[ATTR8]]
// CHECK1-NEXT: unreachable
//
//
// DEBUG1-LABEL: define {{[^@]+}}@_Z3foov
// DEBUG1-SAME: () #[[ATTR0:[0-9]+]] !dbg [[DBG6:![0-9]+]] {
// DEBUG1-NEXT: entry:
// DEBUG1-NEXT: call void @_Z8mayThrowv(), !dbg [[DBG10:![0-9]+]]
// DEBUG1-NEXT: ret void, !dbg [[DBG11:![0-9]+]]
//
//
// DEBUG1-LABEL: define {{[^@]+}}@main
// DEBUG1-SAME: () #[[ATTR2:[0-9]+]] personality ptr @__gxx_personality_v0 !dbg [[DBG12:![0-9]+]] {
// DEBUG1-NEXT: entry:
// DEBUG1-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
// DEBUG1-NEXT: [[A:%.*]] = alloca i8, align 1
// DEBUG1-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1:[0-9]+]])
// DEBUG1-NEXT: store i32 0, ptr [[RETVAL]], align 4
// DEBUG1-NEXT: call void @__kmpc_taskgroup(ptr @[[GLOB1]], i32 [[TMP0]]), !dbg [[DBG13:![0-9]+]]
// DEBUG1-NEXT: store i8 2, ptr [[A]], align 1, !dbg [[DBG14:![0-9]+]]
// DEBUG1-NEXT: call void @__kmpc_end_taskgroup(ptr @[[GLOB1]], i32 [[TMP0]]), !dbg [[DBG15:![0-9]+]]
// DEBUG1-NEXT: call void @__kmpc_taskgroup(ptr @[[GLOB3:[0-9]+]], i32 [[TMP0]]), !dbg [[DBG16:![0-9]+]]
// DEBUG1-NEXT: invoke void @_Z3foov()
// DEBUG1-NEXT: to label [[INVOKE_CONT:%.*]] unwind label [[TERMINATE_LPAD:%.*]], !dbg [[DBG17:![0-9]+]]
// DEBUG1: invoke.cont:
// DEBUG1-NEXT: call void @__kmpc_end_taskgroup(ptr @[[GLOB3]], i32 [[TMP0]]), !dbg [[DBG17]]
// DEBUG1-NEXT: [[TMP1:%.*]] = load i8, ptr [[A]], align 1, !dbg [[DBG18:![0-9]+]]
// DEBUG1-NEXT: [[CONV:%.*]] = sext i8 [[TMP1]] to i32, !dbg [[DBG18]]
// DEBUG1-NEXT: ret i32 [[CONV]], !dbg [[DBG19:![0-9]+]]
// DEBUG1: terminate.lpad:
// DEBUG1-NEXT: [[TMP2:%.*]] = landingpad { ptr, i32 }
// DEBUG1-NEXT: catch ptr null, !dbg [[DBG17]]
// DEBUG1-NEXT: [[TMP3:%.*]] = extractvalue { ptr, i32 } [[TMP2]], 0, !dbg [[DBG17]]
// DEBUG1-NEXT: call void @__clang_call_terminate(ptr [[TMP3]]) #[[ATTR8:[0-9]+]], !dbg [[DBG17]]
// DEBUG1-NEXT: unreachable, !dbg [[DBG17]]
//
//
// DEBUG1-LABEL: define {{[^@]+}}@__clang_call_terminate
// DEBUG1-SAME: (ptr noundef [[TMP0:%.*]]) #[[ATTR5:[0-9]+]] {
// DEBUG1-NEXT: [[TMP2:%.*]] = call ptr @__cxa_begin_catch(ptr [[TMP0]]) #[[ATTR3:[0-9]+]]
// DEBUG1-NEXT: call void @_ZSt9terminatev() #[[ATTR8]]
// DEBUG1-NEXT: unreachable
//
//
// DEBUG1-LABEL: define {{[^@]+}}@_Z18parallel_taskgroupv
// DEBUG1-SAME: () #[[ATTR6:[0-9]+]] !dbg [[DBG20:![0-9]+]] {
// DEBUG1-NEXT: entry:
// DEBUG1-NEXT: call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB7:[0-9]+]], i32 0, ptr @_Z18parallel_taskgroupv.omp_outlined), !dbg [[DBG21:![0-9]+]]
// DEBUG1-NEXT: ret void, !dbg [[DBG22:![0-9]+]]
//
//
// DEBUG1-LABEL: define {{[^@]+}}@_Z18parallel_taskgroupv.omp_outlined
// DEBUG1-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]]) #[[ATTR7:[0-9]+]] personality ptr @__gxx_personality_v0 !dbg [[DBG23:![0-9]+]] {
// DEBUG1-NEXT: entry:
// DEBUG1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// DEBUG1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// DEBUG1-NEXT: store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// DEBUG1-NEXT: store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// DEBUG1-NEXT: [[TMP0:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8, !dbg [[DBG24:![0-9]+]]
// DEBUG1-NEXT: [[TMP1:%.*]] = load i32, ptr [[TMP0]], align 4, !dbg [[DBG24]]
// DEBUG1-NEXT: call void @__kmpc_taskgroup(ptr @[[GLOB5:[0-9]+]], i32 [[TMP1]]), !dbg [[DBG24]]
// DEBUG1-NEXT: invoke void @_Z3foov()
// DEBUG1-NEXT: to label [[INVOKE_CONT:%.*]] unwind label [[TERMINATE_LPAD:%.*]], !dbg [[DBG25:![0-9]+]]
// DEBUG1: invoke.cont:
// DEBUG1-NEXT: call void @__kmpc_end_taskgroup(ptr @[[GLOB5]], i32 [[TMP1]]), !dbg [[DBG25]]
// DEBUG1-NEXT: ret void, !dbg [[DBG26:![0-9]+]]
// DEBUG1: terminate.lpad:
// DEBUG1-NEXT: [[TMP2:%.*]] = landingpad { ptr, i32 }
// DEBUG1-NEXT: catch ptr null, !dbg [[DBG25]]
// DEBUG1-NEXT: [[TMP3:%.*]] = extractvalue { ptr, i32 } [[TMP2]], 0, !dbg [[DBG25]]
// DEBUG1-NEXT: call void @__clang_call_terminate(ptr [[TMP3]]) #[[ATTR8]], !dbg [[DBG25]]
// DEBUG1-NEXT: unreachable, !dbg [[DBG25]]
//
//
// CHECK2-LABEL: define {{[^@]+}}@_Z3foov
// CHECK2-SAME: () #[[ATTR0:[0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: call void @_Z8mayThrowv()
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@main
// CHECK2-SAME: () #[[ATTR2:[0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[A:%.*]] = alloca i8, align 1
// CHECK2-NEXT: store i32 0, ptr [[RETVAL]], align 4
// CHECK2-NEXT: [[OMP_GLOBAL_THREAD_NUM:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1:[0-9]+]])
// CHECK2-NEXT: call void @__kmpc_taskgroup(ptr @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM]])
// CHECK2-NEXT: store i8 2, ptr [[A]], align 1
// CHECK2-NEXT: br label [[TASKGROUP_EXIT:%.*]]
// CHECK2: taskgroup.exit:
// CHECK2-NEXT: call void @__kmpc_end_taskgroup(ptr @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM]])
// CHECK2-NEXT: [[OMP_GLOBAL_THREAD_NUM1:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1]])
// CHECK2-NEXT: call void @__kmpc_taskgroup(ptr @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM1]])
// CHECK2-NEXT: call void @_Z3foov()
// CHECK2-NEXT: br label [[TASKGROUP_EXIT2:%.*]]
// CHECK2: taskgroup.exit2:
// CHECK2-NEXT: call void @__kmpc_end_taskgroup(ptr @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM1]])
// CHECK2-NEXT: [[TMP0:%.*]] = load i8, ptr [[A]], align 1
// CHECK2-NEXT: [[CONV:%.*]] = sext i8 [[TMP0]] to i32
// CHECK2-NEXT: ret i32 [[CONV]]
//
//
// CHECK2-LABEL: define {{[^@]+}}@_Z18parallel_taskgroupv
// CHECK2-SAME: () #[[ATTR0]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[OMP_GLOBAL_THREAD_NUM:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1]])
// CHECK2-NEXT: br label [[OMP_PARALLEL:%.*]]
// CHECK2: omp_parallel:
// CHECK2-NEXT: call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 0, ptr @_Z18parallel_taskgroupv..omp_par)
// CHECK2-NEXT: br label [[OMP_PAR_OUTLINED_EXIT:%.*]]
// CHECK2: omp.par.exit:
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_Z18parallel_taskgroupv..omp_par
// CHECK2-SAME: (ptr noalias [[TID_ADDR:%.*]], ptr noalias [[ZERO_ADDR:%.*]]) #[[ATTR5:[0-9]+]] {
// CHECK2-NEXT: omp.par.entry:
// CHECK2-NEXT: [[TID_ADDR_LOCAL:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[TMP0:%.*]] = load i32, ptr [[TID_ADDR]], align 4
// CHECK2-NEXT: store i32 [[TMP0]], ptr [[TID_ADDR_LOCAL]], align 4
// CHECK2-NEXT: [[TID:%.*]] = load i32, ptr [[TID_ADDR_LOCAL]], align 4
// CHECK2-NEXT: br label [[OMP_PAR_REGION:%.*]]
// CHECK2: omp.par.region:
// CHECK2-NEXT: [[OMP_GLOBAL_THREAD_NUM1:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1]])
// CHECK2-NEXT: call void @__kmpc_taskgroup(ptr @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM1]])
// CHECK2-NEXT: call void @_Z3foov()
// CHECK2-NEXT: br label [[TASKGROUP_EXIT:%.*]]
// CHECK2: taskgroup.exit:
// CHECK2-NEXT: call void @__kmpc_end_taskgroup(ptr @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM1]])
// CHECK2-NEXT: br label [[OMP_PAR_REGION_PARALLEL_AFTER:%.*]]
// CHECK2: omp.par.region.parallel.after:
// CHECK2-NEXT: br label [[OMP_PAR_PRE_FINALIZE:%.*]]
// CHECK2: omp.par.pre_finalize:
// CHECK2-NEXT: br label [[OMP_PAR_OUTLINED_EXIT_EXITSTUB:%.*]]
// CHECK2: omp.par.exit.exitStub:
// CHECK2-NEXT: ret void
//
Reference in New Issue View Git Blame Copy Permalink