maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[OpenMP] Initial implementation of code generation for pragma 'teams distribute parallel for' on host 

https://reviews.llvm.org/D40187

This patch implements code gen for 'teams distribute parallel for' on the host, including all its clauses and related regression tests.

llvm-svn: 318692
This commit is contained in:
Carlo Bertolli 2017-11-20 20:46:39 +00:00
parent eb6847a4af
commit 62fae15600
15 changed files with 3526 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
clang/lib/Basic/OpenMPKinds.cpp
View File

@ -897,6 +897,10 @@ void clang::getOpenMPCaptureRegions(
case OMPD_target_simd:
CaptureRegions.push_back(OMPD_target);
break;
case OMPD_teams_distribute_parallel_for:
CaptureRegions.push_back(OMPD_teams);
CaptureRegions.push_back(OMPD_parallel);
break;
case OMPD_teams:
case OMPD_simd:
case OMPD_for:
@ -919,7 +923,6 @@ void clang::getOpenMPCaptureRegions(
case OMPD_distribute_simd:
case OMPD_teams_distribute_simd:
case OMPD_teams_distribute_parallel_for_simd:
case OMPD_teams_distribute_parallel_for:
case OMPD_target_teams_distribute:
case OMPD_target_teams_distribute_parallel_for:
case OMPD_target_teams_distribute_parallel_for_simd:

34
clang/lib/CodeGen/CGStmtOpenMP.cpp
View File

@ -2083,18 +2083,6 @@ void CodeGenFunction::EmitOMPTeamsDistributeParallelForSimdDirective(
});
}
void CodeGenFunction::EmitOMPTeamsDistributeParallelForDirective(
const OMPTeamsDistributeParallelForDirective &S) {
OMPLexicalScope Scope(*this, S, /*AsInlined=*/true);
CGM.getOpenMPRuntime().emitInlinedDirective(
*this, OMPD_teams_distribute_parallel_for,
[&S](CodeGenFunction &CGF, PrePostActionTy &) {
OMPLoopScope PreInitScope(CGF, S);
CGF.EmitStmt(
cast<CapturedStmt>(S.getAssociatedStmt())->getCapturedStmt());
});
}
void CodeGenFunction::EmitOMPTargetTeamsDistributeDirective(
const OMPTargetTeamsDistributeDirective &S) {
OMPLexicalScope Scope(*this, S, /*AsInlined=*/true);
@ -3875,6 +3863,28 @@ void CodeGenFunction::EmitOMPTeamsDistributeDirective(
[](CodeGenFunction &) { return nullptr; });
}
void CodeGenFunction::EmitOMPTeamsDistributeParallelForDirective(
const OMPTeamsDistributeParallelForDirective &S) {
auto &&CodeGenDistribute = [&S](CodeGenFunction &CGF, PrePostActionTy &) {
CGF.EmitOMPDistributeLoop(S, emitInnerParallelForWhenCombined,
S.getDistInc());
};
// Emit teams region as a standalone region.
auto &&CodeGen = [&S, &CodeGenDistribute](CodeGenFunction &CGF,
PrePostActionTy &) {
OMPPrivateScope PrivateScope(CGF);
CGF.EmitOMPReductionClauseInit(S, PrivateScope);
(void)PrivateScope.Privatize();
CGF.CGM.getOpenMPRuntime().emitInlinedDirective(CGF, OMPD_distribute,
CodeGenDistribute);
CGF.EmitOMPReductionClauseFinal(S, /*ReductionKind=*/OMPD_teams);
};
emitCommonOMPTeamsDirective(*this, S, OMPD_distribute_parallel_for, CodeGen);
emitPostUpdateForReductionClause(*this, S,
[](CodeGenFunction &) { return nullptr; });
}
void CodeGenFunction::EmitOMPCancellationPointDirective(
const OMPCancellationPointDirective &S) {
CGM.getOpenMPRuntime().emitCancellationPointCall(*this, S.getLocStart(),

116
clang/lib/Sema/SemaOpenMP.cpp
View File

@ -2202,7 +2202,6 @@ void Sema::ActOnOpenMPRegionStart(OpenMPDirectiveKind DKind, Scope *CurScope) {
case OMPD_distribute_parallel_for:
case OMPD_teams_distribute_simd:
case OMPD_teams_distribute_parallel_for_simd:
case OMPD_teams_distribute_parallel_for:
case OMPD_target_teams_distribute:
case OMPD_target_teams_distribute_parallel_for:
case OMPD_target_teams_distribute_parallel_for_simd:
@ -2221,6 +2220,33 @@ void Sema::ActOnOpenMPRegionStart(OpenMPDirectiveKind DKind, Scope *CurScope) {
Params);
break;
}
case OMPD_teams_distribute_parallel_for: {
QualType KmpInt32Ty = Context.getIntTypeForBitwidth(32, 1);
QualType KmpInt32PtrTy =
Context.getPointerType(KmpInt32Ty).withConst().withRestrict();
Sema::CapturedParamNameType ParamsTeams[] = {
std::make_pair(".global_tid.", KmpInt32PtrTy),
std::make_pair(".bound_tid.", KmpInt32PtrTy),
std::make_pair(StringRef(), QualType()) // __context with shared vars
};
// Start a captured region for 'target' with no implicit parameters.
ActOnCapturedRegionStart(DSAStack->getConstructLoc(), CurScope, CR_OpenMP,
ParamsTeams);
Sema::CapturedParamNameType ParamsParallel[] = {
std::make_pair(".global_tid.", KmpInt32PtrTy),
std::make_pair(".bound_tid.", KmpInt32PtrTy),
std::make_pair(".previous.lb.", Context.getSizeType()),
std::make_pair(".previous.ub.", Context.getSizeType()),
std::make_pair(StringRef(), QualType()) // __context with shared vars
};
// Start a captured region for 'teams' or 'parallel'. Both regions have
// the same implicit parameters.
ActOnCapturedRegionStart(DSAStack->getConstructLoc(), CurScope, CR_OpenMP,
ParamsParallel);
break;
}
case OMPD_threadprivate:
case OMPD_taskyield:
case OMPD_barrier:
@ -7012,12 +7038,24 @@ StmtResult Sema::ActOnOpenMPTeamsDistributeParallelForDirective(
// longjmp() and throw() must not violate the entry/exit criteria.
CS->getCapturedDecl()->setNothrow();
for (int ThisCaptureLevel =
getOpenMPCaptureLevels(OMPD_teams_distribute_parallel_for);
ThisCaptureLevel > 1; --ThisCaptureLevel) {
CS = cast<CapturedStmt>(CS->getCapturedStmt());
// 1.2.2 OpenMP Language Terminology
// Structured block - An executable statement with a single entry at the
// top and a single exit at the bottom.
// The point of exit cannot be a branch out of the structured block.
// longjmp() and throw() must not violate the entry/exit criteria.
CS->getCapturedDecl()->setNothrow();
}
OMPLoopDirective::HelperExprs B;
// In presence of clause 'collapse' with number of loops, it will
// define the nested loops number.
unsigned NestedLoopCount = CheckOpenMPLoop(
OMPD_teams_distribute_parallel_for, getCollapseNumberExpr(Clauses),
nullptr /*ordered not a clause on distribute*/, AStmt, *this, *DSAStack,
nullptr /*ordered not a clause on distribute*/, CS, *this, *DSAStack,
VarsWithImplicitDSA, B);
if (NestedLoopCount == 0)
@ -7330,6 +7368,9 @@ static OpenMPDirectiveKind getOpenMPCaptureRegionForClause(
if (NameModifier == OMPD_unknown || NameModifier == OMPD_parallel)
CaptureRegion = OMPD_target;
break;
case OMPD_teams_distribute_parallel_for:
CaptureRegion = OMPD_teams;
break;
case OMPD_cancel:
case OMPD_parallel:
case OMPD_parallel_sections:
@ -7342,7 +7383,6 @@ static OpenMPDirectiveKind getOpenMPCaptureRegionForClause(
case OMPD_target_teams_distribute_simd:
case OMPD_target_teams_distribute_parallel_for:
case OMPD_target_teams_distribute_parallel_for_simd:
case OMPD_teams_distribute_parallel_for:
case OMPD_teams_distribute_parallel_for_simd:
case OMPD_distribute_parallel_for:
case OMPD_distribute_parallel_for_simd:
@ -7393,6 +7433,9 @@ static OpenMPDirectiveKind getOpenMPCaptureRegionForClause(
case OMPD_target_parallel_for_simd:
CaptureRegion = OMPD_target;
break;
case OMPD_teams_distribute_parallel_for:
CaptureRegion = OMPD_teams;
break;
case OMPD_cancel:
case OMPD_parallel:
case OMPD_parallel_sections:
@ -7405,7 +7448,6 @@ static OpenMPDirectiveKind getOpenMPCaptureRegionForClause(
case OMPD_target_teams_distribute_simd:
case OMPD_target_teams_distribute_parallel_for:
case OMPD_target_teams_distribute_parallel_for_simd:
case OMPD_teams_distribute_parallel_for:
case OMPD_teams_distribute_parallel_for_simd:
case OMPD_distribute_parallel_for:
case OMPD_distribute_parallel_for_simd:
@ -7581,11 +7623,13 @@ static OpenMPDirectiveKind getOpenMPCaptureRegionForClause(
case OMPD_target_parallel_for_simd:
CaptureRegion = OMPD_target;
break;
case OMPD_teams_distribute_parallel_for:
CaptureRegion = OMPD_teams;
break;
case OMPD_parallel_for:
case OMPD_parallel_for_simd:
case OMPD_target_teams_distribute_parallel_for:
case OMPD_target_teams_distribute_parallel_for_simd:
case OMPD_teams_distribute_parallel_for:
case OMPD_teams_distribute_parallel_for_simd:
case OMPD_distribute_parallel_for:
case OMPD_distribute_parallel_for_simd:
@ -7639,6 +7683,68 @@ static OpenMPDirectiveKind getOpenMPCaptureRegionForClause(
}
break;
case OMPC_dist_schedule:
switch (DKind) {
case OMPD_teams_distribute_parallel_for:
CaptureRegion = OMPD_teams;
break;
case OMPD_target_teams_distribute_parallel_for:
case OMPD_target_teams_distribute_parallel_for_simd:
case OMPD_teams_distribute_parallel_for_simd:
case OMPD_distribute_parallel_for:
case OMPD_distribute_parallel_for_simd:
case OMPD_teams_distribute:
case OMPD_teams_distribute_simd:
case OMPD_target_teams_distribute:
case OMPD_target_teams_distribute_simd:
case OMPD_distribute_simd:
// Do not capture thread_limit-clause expressions.
break;
case OMPD_parallel_for:
case OMPD_parallel_for_simd:
case OMPD_target_parallel_for_simd:
case OMPD_target_parallel_for:
case OMPD_task:
case OMPD_taskloop:
case OMPD_taskloop_simd:
case OMPD_target_data:
case OMPD_target_enter_data:
case OMPD_target_exit_data:
case OMPD_target_update:
case OMPD_teams:
case OMPD_target:
case OMPD_target_simd:
case OMPD_target_parallel:
case OMPD_cancel:
case OMPD_parallel:
case OMPD_parallel_sections:
case OMPD_threadprivate:
case OMPD_taskyield:
case OMPD_barrier:
case OMPD_taskwait:
case OMPD_cancellation_point:
case OMPD_flush:
case OMPD_declare_reduction:
case OMPD_declare_simd:
case OMPD_declare_target:
case OMPD_end_declare_target:
case OMPD_simd:
case OMPD_for:
case OMPD_for_simd:
case OMPD_sections:
case OMPD_section:
case OMPD_single:
case OMPD_master:
case OMPD_critical:
case OMPD_taskgroup:
case OMPD_distribute:
case OMPD_ordered:
case OMPD_atomic:
case OMPD_target_teams:
llvm_unreachable("Unexpected OpenMP directive with schedule clause");
case OMPD_unknown:
llvm_unreachable("Unknown OpenMP directive");
}
break;
case OMPC_firstprivate:
case OMPC_lastprivate:
case OMPC_reduction:

247
clang/test/OpenMP/teams_distribute_parallel_for_codegen.cpp Normal file
View File

@ -0,0 +1,247 @@
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
// Test host codegen.
// RUN: %clang_cc1 -DCK1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CK1 --check-prefix CK1-64
// RUN: %clang_cc1 -DCK1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCK1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CK1 --check-prefix CK1-64
// RUN: %clang_cc1 -DCK1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CK1 --check-prefix CK1-32
// RUN: %clang_cc1 -DCK1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCK1 -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CK1 --check-prefix CK1-32
#ifdef CK1
int a[100];
// CK1: define {{.*}}i32 @{{.+}}teams_argument_globali(
int teams_argument_global(int n){
int te = n / 128;
int th = 128;
// discard n_addr
// CK1: alloca i32,
// CK1: [[TE:%.+]] = alloca i32,
// CK1: [[TH:%.+]] = alloca i32,
// CK1: [[TE_CAST:%.+]] = alloca i{{32|64}},
// CK1: [[TH_CAST:%.+]] = alloca i{{32|64}},
// CK1: [[TE_PAR:%.+]] = load{{.+}}, {{.+}} [[TE_CAST]],
// CK1: [[TH_PAR:%.+]] = load{{.+}}, {{.+}} [[TH_CAST]],
// CK1: call i32 @__tgt_target(i32 -1, i8* @{{[^,]+}}, i32 4, i8** %{{[^,]+}}, i8** %{{[^,]+}}, i{{64|32}}* {{.+}}@{{[^,]+}}, i32 0, i32 0), i32* {{.+}}@{{[^,]+}}, i32 0, i32 0))
// CK1: call void @[[OFFL1:.+]](i{{32|64}} [[TE_PAR]], i{{32|64}} [[TH_PAR]],
#pragma omp target
#pragma omp teams distribute parallel for num_teams(te), thread_limit(th)
for(int i = 0; i < n; i++) {
a[i] = 0;
}
// CK1: call i32 @__tgt_target(i32 -1, i8* @{{[^,]+}}, i32 2, i8** %{{[^,]+}}, i8** %{{[^,]+}}, i{{64|32}}* {{.+}}@{{[^,]+}}, i32 0, i32 0), i32* {{.+}}@{{[^,]+}}, i32 0, i32 0))
// CK1: call void @[[OFFL2:.+]](i{{64|32}} %{{.+}})
#pragma omp target
{{{
#pragma omp teams distribute parallel for
for(int i = 0; i < n; i++) {
a[i] = 0;
}
}}}
// outlined target regions
// CK1: define internal void @[[OFFL1]](i{{32|64}} [[TE_ARG:%.+]], i{{32|64}} [[TH_ARG:%.+]], i{{32|64}} {{.+}}, {{.+}})
// CK1: [[TE_ADDR:%.+]] = alloca i{{32|64}},
// CK1: [[TH_ADDR:%.+]] = alloca i{{32|64}},
// CK1: store{{.+}} [[TE_ARG]], {{.+}} [[TE_ADDR]],
// CK1: store{{.+}} [[TH_ARG]], {{.+}} [[TH_ADDR]],
// CK1-64: [[TE_CONV:%.+]] = bitcast{{.+}} [[TE_ADDR]] to
// CK1-64: [[TH_CONV:%.+]] = bitcast{{.+}} [[TH_ADDR]] to
// CK1-64: [[TE_VAL:%.+]] = load i32, i32* [[TE_CONV]],
// CK1-64: [[TH_VAL:%.+]] = load i32, i32* [[TH_CONV]],
// CK1-32: [[TE_VAL:%.+]] = load i32, i32* [[TE_ADDR]],
// CK1-32: [[TH_VAL:%.+]] = load i32, i32* [[TH_ADDR]],
// CK1: {{%.+}} = call i32 @__kmpc_push_num_teams({{.+}}, {{.+}}, i32 [[TE_VAL]], i32 [[TH_VAL]])
// CK1: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 2, {{.+}} @[[OUTL1:.+]] to {{.+}}, {{.+}}, {{.+}})
// CK1: ret void
// CK1: define internal void @[[OUTL1]]({{.+}})
// CK1: call void @__kmpc_for_static_init_4(
// CK1: call void {{.+}} @__kmpc_fork_call(
// CK1: call void @__kmpc_for_static_fini(
// CK1: ret void
// CK1: define internal void @[[OFFL2]]({{.+}}, {{.+}})
// CK1: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 2, {{.+}} @[[OUTL2:.+]] to {{.+}}, {{.+}}, {{.+}})
// CK1: ret void
// CK1: define internal void @[[OUTL2]]({{.+}})
// CK1: call void @__kmpc_for_static_init_4(
// CK1: call void {{.+}} @__kmpc_fork_call(
// CK1: call void @__kmpc_for_static_fini(
// CK1: ret void
return a[0];
}
#endif // CK1
// Test host codegen.
// RUN: %clang_cc1 -DCK2 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CK2 --check-prefix CK2-64
// RUN: %clang_cc1 -DCK2 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCK2 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CK2 --check-prefix CK2-64
// RUN: %clang_cc1 -DCK2 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CK2 --check-prefix CK2-32
// RUN: %clang_cc1 -DCK2 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCK2 -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CK2 --check-prefix CK2-32
#ifdef CK2
// CK2: define {{.*}}i32 @{{.+}}teams_local_argv(
int teams_local_arg(void) {
int n = 100;
int a[n];
// CK2: call i32 @__tgt_target(i32 -1, i8* @{{[^,]+}}, i32 3, i8** %{{[^,]+}}, i8** %{{[^,]+}}, i{{64|32}}* {{.+}}, i32* {{.+}}@{{[^,]+}}, i32 0, i32 0))
// CK2: call void @[[OFFL1:.+]](i{{64|32}} %{{.+}})
#pragma omp target
#pragma omp teams distribute parallel for
for(int i = 0; i < n; i++) {
a[i] = 0;
}
// outlined target region
// CK2: define internal void @[[OFFL1]]({{.+}}, {{.+}})
// CK2: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 3, {{.+}} @[[OUTL1:.+]] to {{.+}}, {{.+}}, {{.+}})
// CK2: ret void
// CK2: define internal void @[[OUTL1]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4(
// CK2: call void {{.+}} @__kmpc_fork_call(
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
return a[0];
}
#endif // CK2
// Test host codegen.
// RUN: %clang_cc1 -DCK3 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CK3 --check-prefix CK3-64
// RUN: %clang_cc1 -DCK3 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCK3 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CK3 --check-prefix CK3-64
// RUN: %clang_cc1 -DCK3 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CK3 --check-prefix CK3-32
// RUN: %clang_cc1 -DCK3 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCK3 -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CK3 --check-prefix CK3-32
#ifdef CK3
// CK3: [[SSI:%.+]] = type { [{{.+}} x i32], float }
template <typename T, int X, long long Y>
struct SS{
T a[X];
float b;
// CK3: define {{.*}}i32 @{{.+}}foo{{.+}}(
int foo(void) {
// CK3: call i32 @__tgt_target(i32 -1, i8* @{{[^,]+}}, i32 1, i8** %{{[^,]+}}, i8** %{{[^,]+}}, i{{64|32}}* {{.+}}@{{[^,]+}}, i32 0, i32 0), i32* {{.+}}@{{[^,]+}}, i32 0, i32 0))
// CK3: call void @[[OFFL1:.+]]([[SSI]]* %{{.+}})
#pragma omp target
#pragma omp teams distribute parallel for
for(int i = 0; i < X; i++) {
a[i] = (T)0;
}
// outlined target region
// CK3: define internal void @[[OFFL1]]([[SSI]]* {{.+}})
// CK3: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 1, {{.+}} @[[OUTL1:.+]] to {{.+}}, {{.+}}, {{.+}})
// CK3: ret void
// CK3: define internal void @[[OUTL1]]({{.+}})
// CK3: call void @__kmpc_for_static_init_4(
// CK3: call void {{.+}} @__kmpc_fork_call(
// CK3: call void @__kmpc_for_static_fini(
// CK3: ret void
return a[0];
}
};
int teams_template_struct(void) {
SS<int, 123, 456> V;
return V.foo();
}
#endif // CK3
// Test host codegen.
// RUN: %clang_cc1 -DCK4 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CK4 --check-prefix CK4-64
// RUN: %clang_cc1 -DCK4 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCK4 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CK4 --check-prefix CK4-64
// RUN: %clang_cc1 -DCK4 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CK4 --check-prefix CK4-32
// RUN: %clang_cc1 -DCK4 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCK4 -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CK4 --check-prefix CK4-32
#ifdef CK4
template <typename T, int n>
int tmain(T argc) {
T a[n];
int te = n/128;
int th = 128;
#pragma omp target
#pragma omp teams distribute parallel for num_teams(te) thread_limit(th)
for(int i = 0; i < n; i++) {
a[i] = (T)0;
}
return 0;
}
int main (int argc, char **argv) {
int n = 100;
int a[n];
#pragma omp target
#pragma omp teams distribute parallel for
for(int i = 0; i < n; i++) {
a[i] = 0;
}
return tmain<int, 10>(argc);
}
// CK4: define {{.*}}i32 @{{[^,]+}}(i{{.+}}{{.+}} %[[ARGC:.+]], {{.+}})
// CK4: call i32 @__tgt_target(i32 -1, i8* @{{[^,]+}}, i32 3, i8** %{{[^,]+}}, i8** %{{[^,]+}}, i{{64|32}}* {{.+}}, i32* {{.+}}@{{[^,]+}}, i32 0, i32 0)
// CK4: call void @[[OFFL1:.+]]({{.+}})
// CK4: {{%.+}} = call{{.*}} i32 @[[TMAIN:.+]]({{.+}})
// CK4: ret
// CK4: define {{.*}}void @[[OFFL1]]({{.+}})
// CK4: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 3, {{.+}} @[[OUTL1:.+]] to {{.+}}, {{.+}}, {{.+}})
// CK4: ret void
// CK4: define internal void @[[OUTL1]]({{.+}})
// CK4: call void @__kmpc_for_static_init_4(
// CK4: call void {{.+}} @__kmpc_fork_call(
// CK4: call void @__kmpc_for_static_fini(
// CK4: ret void
// CK4: define {{.*}}i32 @[[TMAIN]]({{.+}})
// CK4: call i32 @__tgt_target(i32 -1, i8* @{{[^,]+}}, i32 3, i8** %{{[^,]+}}, i8** %{{[^,]+}}, i{{64|32}}* {{.+}}@{{[^,]+}}, i32 0, i32 0), i32* {{.+}}@{{[^,]+}}, i32 0, i32 0))
// CK4: call void @[[OFFLT:.+]]({{.+}})
// CK4: ret
// CK4-NEXT: }
// CK4: define {{.*}}void @[[OFFLT]](i{{32|64}} [[TE_ARG:%.+]], i{{32|64}} [[TH_ARG:%.+]], {{.+}})
// CK4: [[TE_ADDR:%.+]] = alloca i{{32|64}},
// CK4: [[TH_ADDR:%.+]] = alloca i{{32|64}},
// CK4: store{{.+}} [[TE_ARG]], {{.+}} [[TE_ADDR]],
// CK4: store{{.+}} [[TH_ARG]], {{.+}} [[TH_ADDR]],
// CK4-64: [[TE_CONV:%.+]] = bitcast{{.+}} [[TE_ADDR]] to
// CK4-64: [[TH_CONV:%.+]] = bitcast{{.+}} [[TH_ADDR]] to
// CK4-64: [[TE_VAL:%.+]] = load i32, i32* [[TE_CONV]],
// CK4-64: [[TH_VAL:%.+]] = load i32, i32* [[TH_CONV]],
// CK4-32: [[TE_VAL:%.+]] = load i32, i32* [[TE_ADDR]],
// CK4-32: [[TH_VAL:%.+]] = load i32, i32* [[TH_ADDR]],
// CK4: {{%.+}} = call i32 @__kmpc_push_num_teams({{.+}}, {{.+}}, i32 [[TE_VAL]], i32 [[TH_VAL]])
// CK4: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 1, {{.+}} @[[OUTLT:.+]] to {{.+}}, {{.+}}, {{.+}})
// CK4: ret void
// CK4: define internal void @[[OUTLT]]({{.+}})
// CK4: call void @__kmpc_for_static_init_4(
// CK4: call void {{.+}} @__kmpc_fork_call(
// CK4: call void @__kmpc_for_static_fini(
// CK4: ret void
#endif // CK4
#endif

144
clang/test/OpenMP/teams_distribute_parallel_for_collapse_codegen.cpp Normal file
View File

@ -0,0 +1,144 @@
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
// Test host codegen.
// RUN: %clang_cc1 -DCK1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CK1 --check-prefix CK1-64
// RUN: %clang_cc1 -DCK1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCK1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CK1 --check-prefix CK1-64
// RUN: %clang_cc1 -DCK1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CK1 --check-prefix CK1-32
// RUN: %clang_cc1 -DCK1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCK1 -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CK1 --check-prefix CK1-32
#ifdef CK1
template <typename T, int X, long long Y>
struct SS{
T a[X][Y];
// CK1: define {{.*}}i32 @{{.+}}foo{{.+}}(
int foo(void) {
// CK1: call i32 @__tgt_target(
// CK1: call void @[[OFFL1:.+]](
#pragma omp target
#pragma omp teams distribute parallel for collapse(2)
for(int i = 0; i < X; i++) {
for(int j = 0; j < Y; j++) {
a[i][j] = (T)0;
}
}
// CK1: define internal void @[[OFFL1]](
// CK1: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 1, {{.+}} @[[OUTL1:.+]] to {{.+}},
// CK1: ret void
// CK1: define internal void @[[OUTL1]]({{.+}})
// discard loop variables not needed here
// CK1: [[OMP_UB:%.omp.comb.ub]] = alloca i32,
// CK1: store i32 56087, i32* [[OMP_UB]],
// CK1: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, i32 92, {{.+}}, {{.+}}, i32* [[OMP_UB]],
// CK1: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTL1:.+]] to
// CK1: call void @__kmpc_for_static_fini(
// CK1: ret void
// CK1: define internal void @[[PAR_OUTL1]]({{.+}})
// CK1: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, i32 34, {{.+}}, {{.+}},
// CK1: call void @__kmpc_for_static_fini(
// CK1: ret void
return a[0][0];
}
};
int teams_template_struct(void) {
SS<int, 123, 456> V;
return V.foo();
}
#endif // CK1
// Test host codegen.
// RUN: %clang_cc1 -DCK2 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CK2 --check-prefix CK2-64
// RUN: %clang_cc1 -DCK2 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCK2 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CK2 --check-prefix CK2-64
// RUN: %clang_cc1 -DCK2 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CK2 --check-prefix CK2-32
// RUN: %clang_cc1 -DCK2 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCK2 -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CK2 --check-prefix CK2-32
#ifdef CK2
template <typename T, int n, int m>
int tmain(T argc) {
T a[n][m];
#pragma omp target
#pragma omp teams distribute parallel for collapse(2)
for(int i = 0; i < n; i++) {
for(int j = 0; j < m; j++) {
a[i][j] = (T)0;
}
}
return 0;
}
int main (int argc, char **argv) {
int n = 100;
int m = 2;
int a[n][m];
#pragma omp target
#pragma omp teams distribute parallel for collapse(2)
for(int i = 0; i < n; i++) {
for(int j = 0; j < m; j++) {
a[i][j] = 0;
}
}
return tmain<int, 10, 2>(argc);
}
// CK2: define {{.*}}i32 @{{[^,]+}}(i{{.+}}{{.+}} %[[ARGC:.+]], {{.+}})
// CK2: call i32 @__tgt_target(
// CK2: call void @[[OFFL1:.+]]({{.+}})
// CK2: {{%.+}} = call{{.*}} i32 @[[TMAIN:.+]]({{.+}})
// CK2: ret
// CK2: define {{.*}}void @[[OFFL1]]({{.+}})
// CK2: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 5, {{.+}} @[[OUTL1:.+]] to {{.+}},
// CK2: ret void
// CK2: define internal void @[[OUTL1]]({{.+}})
// CK2: [[OMP_UB:%.omp.comb.ub]] = alloca i64,
// CK2: store i64 {{.+}}, i64* [[OMP_UB]],
// CK2: call void @__kmpc_for_static_init_8({{.+}}, {{.+}}, i32 92, {{.+}}, {{.+}}, i64* [[OMP_UB]],
// CK2: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTL1:.+]] to
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define internal void @[[PAR_OUTL1]]({{.+}})
// CK2: call void @__kmpc_for_static_init_{{[4|8]}}({{.+}}, {{.+}}, i32 34, {{.+}}, {{.+}},
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define {{.*}}i32 @[[TMAIN]]({{.+}})
// CK2: call i32 @__tgt_target(
// CK2: call void @[[OFFLT1:.+]]({{.+}})
// CK2: ret
// CK2-NEXT: }
// CK2: define {{.*}}void @[[OFFLT1]]({{.+}})
// CK2: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 1, {{.+}} @[[OUTLT1:.+]] to {{.+}},
// CK2: ret void
// CK2: define internal void @[[OUTLT1]]({{.+}})
// discard loop variables not needed here
// CK2: [[OMP_UB:%.omp.comb.ub]] = alloca i32,
// CK2: store i32 {{.+}}, i32* [[OMP_UB]],
// CK2: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, i32 92, {{.+}}, {{.+}}, i32* [[OMP_UB]],
// CK2: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[TPAR_OUTL1:.+]] to
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define internal void @[[TPAR_OUTL1]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, i32 34, {{.+}}, {{.+}},
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
#endif // CK2
#endif // #ifndef HEADER

199
clang/test/OpenMP/teams_distribute_parallel_for_copyin_codegen.cpp Normal file
View File

@ -0,0 +1,199 @@
// RUN: %clang_cc1 -DCHECK -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
// RUN: %clang_cc1 -DCHECK -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCHECK -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
// RUN: %clang_cc1 -DCHECK -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
// RUN: %clang_cc1 -DCHECK -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCHECK -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
// RUN: %clang_cc1 -DLAMBDA -verify -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix LAMBDA --check-prefix LAMBDA-64
// RUN: %clang_cc1 -DLAMBDA -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DLAMBDA -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix LAMBDA --check-prefix LAMBDA-64
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
int x;
#pragma omp threadprivate(x)
template <typename T>
T tmain() {
int a[2];
#pragma omp target
#pragma omp teams distribute parallel for copyin(x)
for (int i = 0; i < 2; ++i) {
a[i] = x;
}
return T();
}
int main() {
int a[2];
#ifdef LAMBDA
// LAMBDA-LABEL: @main
// LAMBDA: call void [[OUTER_LAMBDA:@.+]](
[&]() {
// LAMBDA: define{{.*}} internal{{.*}} void [[OUTER_LAMBDA]](
// LAMBDA: call i32 @__tgt_target(
// LAMBDA: call void @[[LOFFL1:.+]](
// LAMBDA: ret
#pragma omp target
#pragma omp teams distribute parallel for copyin(x)
for (int i = 0; i < 2; ++i) {
// LAMBDA: define{{.*}} internal{{.*}} void @[[LOFFL1]](
// LAMBDA: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 {{.+}}, {{.+}} @[[LOUTL1:.+]] to {{.+}})
// LAMBDA: ret void
// LAMBDA: define internal void @[[LOUTL1]](
// Skip global, bound tid and loop vars
// LAMBDA: {{.+}} = alloca i32*,
// LAMBDA: {{.+}} = alloca i32*,
// LAMBDA: alloca i32,
// LAMBDA: alloca i32,
// LAMBDA: alloca i32,
// LAMBDA: alloca i32,
// LAMBDA: alloca i32,
a[i] = x;
// LAMBDA: call void @__kmpc_for_static_init_4(
// LAMBDA: call void {{.+}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[LPAR_OUTL:.+]] to
// LAMBDA: call void @__kmpc_for_static_fini(
// LAMBDA: ret void
// LAMBDA: define internal void @[[LPAR_OUTL]]({{.+}})
// Skip global, bound tid and loop vars
// LAMBDA: {{.+}} = alloca i32*,
// LAMBDA: {{.+}} = alloca i32*,
// LAMBDA: alloca i{{[0-9]+}},
// LAMBDA: alloca i{{[0-9]+}},
// LAMBDA: {{%.+}} = alloca [2 x i{{[0-9]+}}]*,
// LAMBDA: [[X_ADDR:%.+]] = alloca i{{[0-9]+}}*,
// LAMBDA: alloca i32,
// LAMBDA: alloca i32,
// LAMBDA: alloca i32,
// LAMBDA: alloca i32,
// LAMBDA: alloca i32,
// LAMBDA: [[X_REF:%.+]] = load {{.+}}, {{.+}} [[X_ADDR]],
// LAMBDA: call void @__kmpc_for_static_init_4(
// LAMBDA: [[X_VAL:%.+]] = load {{.+}}, {{.+}} [[X_REF]],
// LAMBDA: store {{.+}} [[X_VAL]],
// LAMBDA: call void [[INNER_LAMBDA:@.+]](
// LAMBDA: call void @__kmpc_for_static_fini(
// LAMBDA: ret void
[&]() {
// LAMBDA: define {{.+}} void [[INNER_LAMBDA]](%{{.+}}* [[ARG_PTR:%.+]])
// LAMBDA: store %{{.+}}* [[ARG_PTR]], %{{.+}}** [[ARG_PTR_REF:%.+]],
a[i] = x;
}();
}
}();
return 0;
#else
#pragma omp target
#pragma omp teams distribute parallel for copyin(x)
for (int i = 0; i < 2; ++i) {
a[i] = x;
}
return tmain<int>();
//return 0;
#endif
}
// CHECK: define {{.*}}i{{[0-9]+}} @main()
// CHECK: call i32 @__tgt_target(
// CHECK: call void @[[OFFL1:.+]](i{{64|32}} %{{.+}})
// CHECK: {{%.+}} = call{{.*}} i32 @[[TMAIN_INT:.+]]()
// CHECK: ret
// CHECK: define{{.*}} void @[[OFFL1]]({{.+}})
// CHECK: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 {{.+}}, {{.+}} @[[OUTL1:.+]] to {{.+}})
// CHECK: ret void
// CHECK: define internal void @[[OUTL1]]({{.+}})
// Skip global, bound tid and loop vars
// CHECK: {{.+}} = alloca i32*,
// CHECK: {{.+}} = alloca i32*,
// CHECK: {{.+}} = alloca i32,
// CHECK: {{.+}} = alloca i32,
// CHECK: {{.+}} = alloca i32,
// CHECK: {{.+}} = alloca i32,
// CHECK: {{.+}} = alloca i32,
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void {{.+}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTL1:.+]] to
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
// CHECK: define internal void @[[PAR_OUTL1]]({{.+}})
// Skip global, bound tid and loop vars
// CHECK: {{.+}} = alloca i32*,
// CHECK: {{.+}} = alloca i32*,
// CHECK: {{.+}} = alloca i{{[0-9]+}},
// CHECK: {{.+}} = alloca i{{[0-9]+}},
// CHECK: {{%.+}} = alloca [2 x i{{[0-9]+}}]*,
// CHECK: [[X_ADDR:%.+]] = alloca i{{[0-9]+}}*,
// CHECK: {{.+}} = alloca i32,
// CHECK: {{.+}} = alloca i32,
// CHECK: {{.+}} = alloca i32,
// CHECK: {{.+}} = alloca i32,
// CHECK: {{.+}} = alloca i32,
// CHECK: [[X_REF:%.+]] = load {{.+}}, {{.+}} [[X_ADDR]],
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: [[X_VAL:%.+]] = load {{.+}}, {{.+}} [[X_REF]],
// CHECK: store {{.+}} [[X_VAL]],
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
// CHECK: define{{.*}} i{{[0-9]+}} @[[TMAIN_INT]]()
// CHECK: call i32 @__tgt_target(
// CHECK: call void @[[TOFFL1:.+]](
// CHECK: ret
// CHECK: define {{.*}}void @[[TOFFL1]](
// CHECK: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 {{.+}}, {{.+}} @[[TOUTL1:.+]] to {{.+}})
// CHECK: ret void
// CHECK: define internal void @[[TOUTL1]]({{.+}})
// Skip global, bound tid and loop vars
// CHECK: {{.+}} = alloca i32*,
// CHECK: {{.+}} = alloca i32*,
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void {{.+}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[TPAR_OUTL1:.+]] to
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
// CHECK: define internal void @[[TPAR_OUTL1]]({{.+}})
// Skip global, bound tid and loop vars
// CHECK: {{.+}} = alloca i32*,
// CHECK: {{.+}} = alloca i32*,
// prev lb and ub
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: {{%.+}} = alloca [2 x i{{[0-9]+}}]*,
// CHECK: [[X_ADDR:%.+]] = alloca i{{[0-9]+}}*,
// iter variables
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: [[X_REF:%.+]] = load {{.+}}, {{.+}} [[X_ADDR]],
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: [[X_VAL:%.+]] = load {{.+}}, {{.+}} [[X_REF]],
// CHECK: store {{.+}} [[X_VAL]],
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
#endif

263
clang/test/OpenMP/teams_distribute_parallel_for_dist_schedule_codegen.cpp Normal file
View File

@ -0,0 +1,263 @@
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
// Test host codegen.
// RUN: %clang_cc1 -DCK1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CK1 --check-prefix CK1-64
// RUN: %clang_cc1 -DCK1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCK1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CK1 --check-prefix CK1-64
// RUN: %clang_cc1 -DCK1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CK1 --check-prefix CK1-32
// RUN: %clang_cc1 -DCK1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCK1 -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CK1 --check-prefix CK1-32
#ifdef CK1
template <typename T, int X, long long Y>
struct SS{
T a[X];
float b;
// CK1: define {{.*}}i32 @{{.+}}foo{{.+}}(
int foo(void) {
// CK1: call i32 @__tgt_target(
// CK1: call void @[[OFFL1:.+]](
#pragma omp target
#pragma omp teams distribute parallel for
for(int i = 0; i < X; i++) {
a[i] = (T)0;
}
// CK1: call i32 @__tgt_target(
// CK1: call void @[[OFFL2:.+]](
#pragma omp target
#pragma omp teams distribute parallel for dist_schedule(static)
for(int i = 0; i < X; i++) {
a[i] = (T)0;
}
// CK1: call i32 @__tgt_target(
// CK1: call void @[[OFFL3:.+]](
#pragma omp target
#pragma omp teams distribute parallel for dist_schedule(static, X/2)
for(int i = 0; i < X; i++) {
a[i] = (T)0;
}
// CK1: define internal void @[[OFFL1]](
// CK1: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 1, {{.+}} @[[OUTL1:.+]] to {{.+}},
// CK1: ret void
// CK1: define internal void @[[OUTL1]]({{.+}})
// CK1: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, i32 92
// CK1: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTL1:.+]] to
// CK1: call void @__kmpc_for_static_fini(
// CK1: ret void
// CK1: define internal void @[[PAR_OUTL1]]({{.+}})
// CK1: call void @__kmpc_for_static_init_4(
// CK1: call void @__kmpc_for_static_fini(
// CK1: ret void
// CK1: define internal void @[[OFFL2]](
// CK1: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 1, {{.+}} @[[OUTL2:.+]] to {{.+}},
// CK1: ret void
// CK1: define internal void @[[OUTL2]]({{.+}})
// CK1: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, i32 92
// CK1: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTL2:.+]] to
// CK1: call void @__kmpc_for_static_fini(
// CK1: ret void
// CK1: define internal void @[[PAR_OUTL2]]({{.+}})
// CK1: call void @__kmpc_for_static_init_4(
// CK1: call void @__kmpc_for_static_fini(
// CK1: ret void
// CK1: define internal void @[[OFFL3]](
// CK1: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 1, {{.+}} @[[OUTL3:.+]] to {{.+}},
// CK1: ret void
// CK1: define internal void @[[OUTL3]]({{.+}})
// CK1: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, i32 91
// CK1: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTL3:.+]] to
// CK1: call void @__kmpc_for_static_fini(
// CK1: ret void
// CK1: define internal void @[[PAR_OUTL3]]({{.+}})
// CK1: call void @__kmpc_for_static_init_4(
// CK1: call void @__kmpc_for_static_fini(
// CK1: ret void
return a[0];
}
};
int teams_template_struct(void) {
SS<int, 123, 456> V;
return V.foo();
}
#endif // CK1
// Test host codegen.
// RUN: %clang_cc1 -DCK2 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CK2 --check-prefix CK2-64
// RUN: %clang_cc1 -DCK2 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCK2 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CK2 --check-prefix CK2-64
// RUN: %clang_cc1 -DCK2 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CK2 --check-prefix CK2-32
// RUN: %clang_cc1 -DCK2 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCK2 -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CK2 --check-prefix CK2-32
#ifdef CK2
template <typename T, int n>
int tmain(T argc) {
T a[n];
int m = 10;
#pragma omp target
#pragma omp teams distribute parallel for
for(int i = 0; i < n; i++) {
a[i] = (T)0;
}
#pragma omp target
#pragma omp teams distribute parallel for dist_schedule(static)
for(int i = 0; i < n; i++) {
a[i] = (T)0;
}
#pragma omp target
#pragma omp teams distribute parallel for dist_schedule(static, m)
for(int i = 0; i < n; i++) {
a[i] = (T)0;
}
return 0;
}
int main (int argc, char **argv) {
int n = 100;
int a[n];
int m = 10;
#pragma omp target
#pragma omp teams distribute parallel for
for(int i = 0; i < n; i++) {
a[i] = 0;
}
#pragma omp target
#pragma omp teams distribute parallel for dist_schedule(static)
for(int i = 0; i < n; i++) {
a[i] = 0;
}
#pragma omp target
#pragma omp teams distribute parallel for dist_schedule(static, m)
for(int i = 0; i < n; i++) {
a[i] = 0;
}
return tmain<int, 10>(argc);
}
// CK2: define {{.*}}i32 @{{[^,]+}}(i{{.+}}{{.+}} %[[ARGC:.+]], {{.+}})
// CK2: call i32 @__tgt_target(
// CK2: call void @[[OFFL1:.+]]({{.+}})
// CK2: call i32 @__tgt_target(
// CK2: call void @[[OFFL2:.+]]({{.+}})
// CK2: call i32 @__tgt_target(
// CK2: call void @[[OFFL3:.+]]({{.+}})
// CK2: {{%.+}} = call{{.*}} i32 @[[TMAIN:.+]]({{.+}})
// CK2: ret
// CK2: define {{.*}}void @[[OFFL1]]({{.+}})
// CK2: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 3, {{.+}} @[[OUTL1:.+]] to {{.+}},
// CK2: ret void
// CK2: define internal void @[[OUTL1]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, i32 92
// CK2: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTL1:.+]] to
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define internal void @[[PAR_OUTL1]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4(
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define {{.*}}void @[[OFFL2]]({{.+}})
// CK2: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 3, {{.+}} @[[OUTL2:.+]] to {{.+}},
// CK2: ret void
// CK2: define internal void @[[OUTL2]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, i32 92
// CK2: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTL2:.+]] to
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define internal void @[[PAR_OUTL2]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4(
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define {{.*}}void @[[OFFL3]]({{.+}})
// CK2: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 4, {{.+}} @[[OUTL3:.+]] to {{.+}},
// CK2: ret void
// CK2: define internal void @[[OUTL3]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, i32 91
// CK2: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTL3:.+]] to
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define internal void @[[PAR_OUTL3]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4(
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define {{.*}}i32 @[[TMAIN]]({{.+}})
// CK2: call i32 @__tgt_target(
// CK2: call void @[[OFFLT1:.+]]({{.+}})
// CK2: call i32 @__tgt_target(
// CK2: call void @[[OFFLT2:.+]]({{.+}})
// CK2: call i32 @__tgt_target(
// CK2: call void @[[OFFLT3:.+]]({{.+}})
// CK2: ret
// CK2-NEXT: }
// CK2: define {{.*}}void @[[OFFLT1]]({{.+}})
// CK2: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 1, {{.+}} @[[OUTLT1:.+]] to {{.+}},
// CK2: ret void
// CK2: define internal void @[[OUTLT1]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, i32 92
// CK2: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTLT1:.+]] to
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define internal void @[[PAR_OUTLT1]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4(
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define {{.*}}void @[[OFFLT2]]({{.+}})
// CK2: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 1, {{.+}} @[[OUTLT2:.+]] to {{.+}},
// CK2: ret void
// CK2: define internal void @[[OUTLT2]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, i32 92
// CK2: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTLT2:.+]] to
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define internal void @[[PAR_OUTLT2]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4(
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define {{.*}}void @[[OFFLT3]]({{.+}})
// CK2: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 {{.+}}, {{.+}} @[[OUTLT3:.+]] to {{.+}},
// CK2: ret void
// CK2: define internal void @[[OUTLT3]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, i32 91
// CK2: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTLT3:.+]] to
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define internal void @[[PAR_OUTLT3]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4(
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
#endif // CK2
#endif // #ifndef HEADER

495
clang/test/OpenMP/teams_distribute_parallel_for_firstprivate_codegen.cpp Normal file
View File

@ -0,0 +1,495 @@
// RUN: %clang_cc1 -DCHECK -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
// RUN: %clang_cc1 -DCHECK -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCHECK -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
// RUN: %clang_cc1 -DCHECK -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
// RUN: %clang_cc1 -DCHECK -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCHECK -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
// RUN: %clang_cc1 -DLAMBDA -verify -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix LAMBDA --check-prefix LAMBDA-64
// RUN: %clang_cc1 -DLAMBDA -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DLAMBDA -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix LAMBDA --check-prefix LAMBDA-64
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
struct St {
int a, b;
St() : a(0), b(0) {}
St(const St &st) : a(st.a + st.b), b(0) {}
~St() {}
};
volatile int g = 1212;
volatile int &g1 = g;
template <class T>
struct S {
T f;
S(T a) : f(a + g) {}
S() : f(g) {}
S(const S &s, St t = St()) : f(s.f + t.a) {}
operator T() { return T(); }
~S() {}
};
// CHECK-DAG: [[S_FLOAT_TY:%.+]] = type { float }
// CHECK-DAG: [[S_INT_TY:%.+]] = type { i{{[0-9]+}} }
// CHECK-DAG: [[ST_TY:%.+]] = type { i{{[0-9]+}}, i{{[0-9]+}} }
template <typename T>
T tmain() {
S<T> test;
T t_var = T();
T vec[] = {1, 2};
S<T> s_arr[] = {1, 2};
S<T> &var = test;
#pragma omp target
#pragma omp teams distribute parallel for firstprivate(t_var, vec, s_arr, var)
for (int i = 0; i < 2; ++i) {
vec[i] = t_var;
s_arr[i] = var;
}
return T();
}
// CHECK-DAG: [[TEST:@.+]] = global [[S_FLOAT_TY]] zeroinitializer,
S<float> test;
// CHECK-DAG: [[T_VAR:@.+]] = global i{{[0-9]+}} 333,
int t_var = 333;
// CHECK-DAG: [[VEC:@.+]] = global [2 x i{{[0-9]+}}] [i{{[0-9]+}} 1, i{{[0-9]+}} 2],
int vec[] = {1, 2};
// CHECK-DAG: [[S_ARR:@.+]] = global [2 x [[S_FLOAT_TY]]] zeroinitializer,
S<float> s_arr[] = {1, 2};
// CHECK-DAG: [[VAR:@.+]] = global [[S_FLOAT_TY]] zeroinitializer,
S<float> var(3);
// CHECK-DAG: [[SIVAR:@.+]] = internal global i{{[0-9]+}} 0,
int main() {
static int sivar;
#ifdef LAMBDA
// LAMBDA: [[G:@.+]] = global i{{[0-9]+}} 1212,
// LAMBDA-LABEL: @main
// LAMBDA: call void [[OUTER_LAMBDA:@.+]](
[&]() {
// LAMBDA: define{{.*}} internal{{.*}} void [[OUTER_LAMBDA]](
// LAMBDA: call i32 @__tgt_target(i32 -1, i8* @{{[^,]+}}, i32 3, i8** %{{[^,]+}}, i8** %{{[^,]+}}, i{{64|32}}* {{.+}}@{{[^,]+}}, i32 0, i32 0), i32* {{.+}}@{{[^,]+}}, i32 0, i32 0))
// LAMBDA: call void @[[LOFFL1:.+]](i{{64|32}} %{{.+}})
// LAMBDA: ret
#pragma omp target
#pragma omp teams distribute parallel for firstprivate(g, g1, sivar)
for (int i = 0; i < 2; ++i) {
// LAMBDA: define{{.*}} internal{{.*}} void @[[LOFFL1]](i{{64|32}} {{%.+}}, i{{64|32}} {{%.+}})
// LAMBDA: {{%.+}} = alloca i{{[0-9]+}},
// LAMBDA: {{%.+}} = alloca i{{[0-9]+}},
// LAMBDA: {{%.+}} = alloca i{{[0-9]+}},
// LAMBDA: [[G_CAST:%.+]] = alloca i{{[0-9]+}},
// LAMBDA: [[G1_CAST:%.+]] = alloca i{{[0-9]+}},
// LAMBDA: [[SIVAR_CAST:%.+]] = alloca i{{[0-9]+}},
// LAMBDA-DAG: [[G_CAST_VAL:%.+]] = load{{.+}} [[G_CAST]],
// LAMBDA-DAG: [[G1_CAST_VAL:%.+]] = load{{.+}} [[G1_CAST]],
// LAMBDA-DAG: [[SIVAR_CAST_VAL:%.+]] = load{{.+}} [[SIVAR_CAST]],
// LAMBDA: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 3, {{.+}} @[[LOUTL1:.+]] to {{.+}}, {{.+}} [[G_CAST_VAL]], {{.+}} [[G1_CAST_VAL]], {{.+}} [[SIVAR_CAST_VAL]])
// LAMBDA: ret void
// LAMBDA: define internal void @[[LOUTL1]]({{.+}})
// Skip global and bound tid vars
// LAMBDA: {{.+}} = alloca i32*,
// LAMBDA: {{.+}} = alloca i32*,
// LAMBDA: [[G_ADDR:%.+]] = alloca i{{[0-9]+}},
// LAMBDA: [[G1_ADDR:%.+]] = alloca i{{[0-9]+}},
// LAMBDA: [[SIVAR_ADDR:%.+]] = alloca i{{[0-9]+}},
// LAMBDA: [[G1_TMP:%.+]] = alloca i32*,
// skip loop vars
// LAMBDA-DAG: store {{.+}}, {{.+}} [[G_ADDR]],
// LAMBDA-DAG: store {{.+}}, {{.+}} [[G1_ADDR]],
// LAMBDA-DAG: store {{.+}}, {{.+}} [[SIVAR_ADDR]],
// LAMBDA-DAG: [[G_CONV:%.+]] = bitcast {{.+}} [[G_ADDR]] to
// LAMBDA-DAG: [[G1_CONV:%.+]] = bitcast {{.+}} [[G1_ADDR]] to
// LAMBDA-DAG: [[SIVAR_CONV:%.+]] = bitcast {{.+}} [[SIVAR_ADDR]] to
// LAMBDA-DAG: store{{.+}} [[G1_CONV]], {{.+}} [[G1_TMP]],
g = 1;
g1 = 1;
sivar = 2;
// LAMBDA: call void @__kmpc_for_static_init_4(
// LAMBDA: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[LPAR_OUTL:.+]] to
// LAMBDA: call void @__kmpc_for_static_fini(
// LAMBDA: ret void
// LAMBDA: define internal void @[[LPAR_OUTL]]({{.+}})
// Skip global and bound tid vars, and prev lb and ub vars
// LAMBDA: {{.+}} = alloca i32*,
// LAMBDA: {{.+}} = alloca i32*,
// LAMBDA: {{.+}} = alloca i{{[0-9]+}},
// LAMBDA: {{.+}} = alloca i{{[0-9]+}},
// LAMBDA: [[G_ADDR:%.+]] = alloca i{{[0-9]+}},
// LAMBDA: [[G1_ADDR:%.+]] = alloca i{{[0-9]+}},
// LAMBDA: [[SIVAR_ADDR:%.+]] = alloca i{{[0-9]+}},
// LAMBDA: [[G1_TMP:%.+]] = alloca i32*,
// skip loop vars
// LAMBDA: alloca i32,
// LAMBDA: alloca i32,
// LAMBDA: alloca i32,
// LAMBDA: alloca i32,
// LAMBDA: alloca i32,
// LAMBDA: [[G_PRIV:%.+]] = alloca i{{[0-9]+}},
// LAMBDA: [[G1_PRIV:%.+]] = alloca i{{[0-9]+}},
// LAMBDA: [[G1_TMP_PRIV:%.+]] = alloca i{{[0-9]+}}*,
// LAMBDA: [[SIVAR_PRIV:%.+]] = alloca i{{[0-9]+}},
// LAMBDA-DAG: store {{.+}}, {{.+}} [[G_ADDR]],
// LAMBDA-DAG: store {{.+}}, {{.+}} [[G1_ADDR]],
// LAMBDA-DAG: store {{.+}}, {{.+}} [[SIVAR_ADDR]],
// LAMBDA-DAG: [[G_CONV:%.+]] = bitcast {{.+}} [[G_ADDR]] to
// LAMBDA-DAG: [[G1_CONV:%.+]] = bitcast {{.+}} [[G1_ADDR]] to
// LAMBDA-DAG: [[SIVAR_CONV:%.+]] = bitcast {{.+}} [[SIVAR_ADDR]] to
// LAMBDA-DAG: store{{.+}} [[G1_CONV]], {{.+}} [[G1_TMP]],
// use of private vars
// LAMBDA-DAG: store{{.+}} 1, {{.+}} [[G_PRIV]],
// LAMBDA-DAG: [[G1:%.+]] = load{{.+}}, {{.+}}* [[G1_TMP_PRIV]]
// LAMBDA-DAG: store{{.+}} 1, {{.+}} [[G1]],
// LAMBDA-DAG: store{{.+}} 2, {{.+}} [[SIVAR_PRIV]],
// LAMBDA-DAG: [[G1_REF:%.+]] = load{{.+}}, {{.+}} [[G1_TMP]],
// LAMBDA: call void [[INNER_LAMBDA:@.+]](
// LAMBDA: call void @__kmpc_for_static_fini(
// LAMBDA: ret void
[&]() {
// LAMBDA: define {{.+}} void [[INNER_LAMBDA]](%{{.+}}* [[ARG_PTR:%.+]])
// LAMBDA: store %{{.+}}* [[ARG_PTR]], %{{.+}}** [[ARG_PTR_REF:%.+]],
g = 2;
g1 = 2;
sivar = 4;
// LAMBDA: [[ARG_PTR:%.+]] = load %{{.+}}*, %{{.+}}** [[ARG_PTR_REF]]
// LAMBDA: [[G_PTR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG_PTR]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
// LAMBDA: [[G_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[G_PTR_REF]]
// LAMBDA: store i{{[0-9]+}} 2, i{{[0-9]+}}* [[G_REF]]
// LAMBDA: [[G1_PTR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG_PTR]], i{{[0-9]+}} 0, i{{[0-9]+}} 1
// LAMBDA: [[G1_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[G1_PTR_REF]]
// LAMBDA: store i{{[0-9]+}} 2, i{{[0-9]+}}* [[G1_REF]]
// LAMBDA: [[SIVAR_PTR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG_PTR]], i{{[0-9]+}} 0, i{{[0-9]+}} 2
// LAMBDA: [[SIVAR_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[SIVAR_PTR_REF]]
// LAMBDA: store i{{[0-9]+}} 4, i{{[0-9]+}}* [[SIVAR_REF]]
}();
}
}();
return 0;
#else
#pragma omp target
#pragma omp teams distribute parallel for firstprivate(t_var, vec, s_arr, var, sivar)
for (int i = 0; i < 2; ++i) {
vec[i] = t_var;
s_arr[i] = var;
sivar += i;
}
return tmain<int>();
#endif
}
// CHECK: define {{.*}}i{{[0-9]+}} @main()
// CHECK: call i32 @__tgt_target(i32 -1, i8* @{{[^,]+}}, i32 5, i8** %{{[^,]+}}, i8** %{{[^,]+}}, i{{64|32}}* {{.+}}@{{[^,]+}}, i32 0, i32 0), i32* {{.+}}@{{[^,]+}}, i32 0, i32 0))
// CHECK: call void @[[OFFL1:.+]](i{{64|32}} %{{.+}})
// CHECK: {{%.+}} = call{{.*}} i32 @[[TMAIN_INT:.+]]()
// CHECK: ret
// CHECK: define{{.*}} void @[[OFFL1]]({{.+}})
// CHECK: [[T_VAR_PRIV:%.+]] = alloca i{{[0-9]+}},
// CHECK: [[VEC_PRIV:%.+]] = alloca [2 x i{{[0-9]+}}]*,
// CHECK: [[S_ARR_PRIV:%.+]] = alloca [2 x [[S_FLOAT_TY]]]*,
// CHECK: [[VAR_PRIV:%.+]] = alloca [[S_FLOAT_TY]]*,
// CHECK: [[SIVAR_PRIV:%.+]] = alloca i{{[0-9]+}},
// CHECK: [[T_VAR_CAST:%.+]] = alloca i{{[0-9]+}},
// CHECK: [[SIVAR_CAST:%.+]] = alloca i{{[0-9]+}},
// CHECK-DAG: [[VEC_TE_PAR:%.+]] = load [2 x i{{[0-9]+}}]*, [2 x i{{[0-9]+}}]** [[VEC_PRIV]],
// CHECK-DAG: [[T_VAR_TE_PAR:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[T_VAR_CAST]],
// CHECK-DAG: [[S_ARR_TE_PAR:%.+]] = load [2 x [[S_FLOAT_TY]]]*, [2 x [[S_FLOAT_TY]]]** [[S_ARR_PRIV]],
// CHECK-DAG: [[VAR_TE_PAR:%.+]] = load [[S_FLOAT_TY]]*, [[S_FLOAT_TY]]** [[VAR_PRIV]],
// CHECK-DAG: [[SIVAR_TE_PAR:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[SIVAR_CAST]],
// CHECK: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 5, {{.+}} @[[OUTL1:.+]] to {{.+}}, [2 x i{{[0-9]+}}]* [[VEC_TE_PAR]], i{{[0-9]+}} [[T_VAR_TE_PAR]], [2 x [[S_FLOAT_TY]]]* [[S_ARR_TE_PAR]], [[S_FLOAT_TY]]* [[VAR_TE_PAR]], i{{[0-9]+}} [[SIVAR_TE_PAR]])
// CHECK: ret void
// CHECK: define internal void @[[OUTL1]]({{.+}})
// Skip global and bound tid vars
// CHECK: {{.+}} = alloca i32*,
// CHECK: {{.+}} = alloca i32*,
// CHECK: [[VEC_ADDR:%.+]] = alloca [2 x i{{[0-9]+}}]*,
// CHECK: [[T_VAR_ADDR:%.+]] = alloca i{{[0-9]+}},
// CHECK: [[S_ARR_ADDR:%.+]] = alloca [2 x [[S_FLOAT_TY]]]*,
// CHECK: [[VAR_ADDR:%.+]] = alloca [[S_FLOAT_TY]]*,
// CHECK: [[SIVAR_ADDR:%.+]] = alloca i{{[0-9]+}},
// Skip temp vars for loop
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: [[VEC_PRIV:%.+]] = alloca [2 x i{{[0-9]+}}],
// CHECK: [[S_ARR_PRIV:%.+]] = alloca [2 x [[S_FLOAT_TY]]],
// CHECK: [[AGG_TMP1:%.+]] = alloca [[ST_TY]],
// CHECK: [[VAR_PRIV:%.+]] = alloca [[S_FLOAT_TY]],
// CHECK: [[AGG_TMP2:%.+]] = alloca [[ST_TY]],
// param copy
// CHECK: store [2 x i{{[0-9]+}}]* {{.+}}, [2 x i{{[0-9]+}}]** [[VEC_ADDR]],
// CHECK: store i{{[0-9]+}} {{.+}}, i{{[0-9]+}}* [[T_VAR_ADDR]],
// CHECK: store [2 x [[S_FLOAT_TY]]]* {{.+}}, [2 x [[S_FLOAT_TY]]]** [[S_ARR_ADDR]],
// CHECK: store [[S_FLOAT_TY]]* {{.+}}, [[S_FLOAT_TY]]** [[VAR_ADDR]],
// CHECK: store i{{[0-9]+}} {{.+}}, i{{[0-9]+}}* [[SIVAR_ADDR]],
// T_VAR and SIVAR
// CHECK-DAG-64: [[CONV_TVAR:%.+]] = bitcast i64* [[T_VAR_ADDR]] to i32*
// CHECK-DAG-64: [[CONV_SIVAR:%.+]] = bitcast i64* [[SIVAR_ADDR]] to i32*
// preparation vars
// CHECK-DAG: [[VEC_ADDR_VAL:%.+]] = load [2 x i{{[0-9]+}}]*, [2 x i{{[0-9]+}}]** [[VEC_ADDR]],
// CHECK-DAG: [[S_ARR_ADDR_REF:%.+]] = load [2 x [[S_FLOAT_TY]]]*, [2 x [[S_FLOAT_TY]]]** [[S_ARR_ADDR]],
// CHECK-DAG: [[VAR_ADDR_REF:%.+]] = load{{.+}} [[VAR_ADDR]],
// firstprivate vec(vec): copy from *_addr into priv1 and then from priv1 into priv2
// CHECK-DAG: [[VEC_DEST_PRIV:%.+]] = bitcast [2 x i{{[0-9]+}}]* [[VEC_PRIV]] to i8*
// CHECK-DAG: [[VEC_SRC:%.+]] = bitcast [2 x i{{[0-9]+}}]* [[VEC_ADDR_VAL]] to i8*
// CHECK: call void @llvm.memcpy.{{.+}}(i8* [[VEC_DEST_PRIV]], i8* [[VEC_SRC]], {{.+}})
// firstprivate(s_arr)
// CHECK-DAG: [[S_ARR_PRIV_BGN:%.+]] = getelementptr{{.*}} [2 x [[S_FLOAT_TY]]], [2 x [[S_FLOAT_TY]]]* [[S_ARR_PRIV]],
// CHECK-DAG: [[S_ARR_ADDR_BGN:%.+]] = bitcast [2 x [[S_FLOAT_TY]]]* [[S_ARR_ADDR_REF]] to
// CHECK-DAG: [[S_ARR_FIN:%.+]] = icmp{{.+}} [[S_ARR_PRIV_BGN]],
// CHECK-DAG: [[S_ARR_SRC_COPY:%.+]] = phi{{.+}} [ [[S_ARR_ADDR_BGN]], {{.+}} ], [ [[S_ARR_SRC:%.+]], {{.+}} ]
// CHECK-DAG: [[S_ARR_DST_COPY:%.+]] = phi{{.+}} [ [[S_ARR_PRIV_BGN]], {{.+}}], [ [[S_ARR_DST:%.+]], {{.+}} ]
// CHECK-DAG: call void @{{.+}}({{.+}} [[AGG_TMP1]])
// CHECK-DAG: call void @{{.+}}({{.+}} [[S_ARR_DST_COPY]], {{.+}} [[S_ARR_SRC_COPY]], {{.+}} [[AGG_TMP1]])
// CHECK-DAG: call void @{{.+}}({{.+}} [[AGG_TMP1]])
// CHECK-DAG: [[S_ARR_DST]] = getelementptr {{.+}} [[S_ARR_DST_COPY]],
// CHECK-DAG: [[S_ARR_SRC]] = getelementptr {{.+}} [[S_ARR_SRC_COPY]],
// firstprivate(var)
// CHECK-DAG: call void @{{.+}}({{.+}} [[AGG_TMP2]])
// CHECK-DAG: call void @{{.+}}({{.+}} [[VAR_PRIV]], {{.+}} [[VAR_ADDR_REF]], {{.+}} [[AGG_TMP2]])
// CHECK-DAG: call void @{{.+}}({{.+}} [[AGG_TMP2]])
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTL:.+]] to
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
// CHECK: define internal void @[[PAR_OUTL]]({{.+}})
// Skip global and bound tid vars, and prev lb ub vars
// CHECK: {{.+}} = alloca i32*,
// CHECK: {{.+}} = alloca i32*,
// CHECK: {{.+}} = alloca i{{[0-9]+}},
// CHECK: {{.+}} = alloca i{{[0-9]+}},
// CHECK: [[VEC_ADDR:%.+]] = alloca [2 x i{{[0-9]+}}]*,
// CHECK: [[T_VAR_ADDR:%.+]] = alloca i{{[0-9]+}},
// CHECK: [[S_ARR_ADDR:%.+]] = alloca [2 x [[S_FLOAT_TY]]]*,
// CHECK: [[VAR_ADDR:%.+]] = alloca [[S_FLOAT_TY]]*,
// CHECK: [[SIVAR_ADDR:%.+]] = alloca i{{[0-9]+}},
// Skip temp vars for loop
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: [[VEC_PRIV:%.+]] = alloca [2 x i{{[0-9]+}}],
// CHECK: [[S_ARR_PRIV:%.+]] = alloca [2 x [[S_FLOAT_TY]]],
// CHECK: [[AGG_TMP1:%.+]] = alloca [[ST_TY]],
// CHECK: [[VAR_PRIV:%.+]] = alloca [[S_FLOAT_TY]],
// CHECK: [[AGG_TMP2:%.+]] = alloca [[ST_TY]],
// param copy
// CHECK: store [2 x i{{[0-9]+}}]* {{.+}}, [2 x i{{[0-9]+}}]** [[VEC_ADDR]],
// CHECK: store i{{[0-9]+}} {{.+}}, i{{[0-9]+}}* [[T_VAR_ADDR]],
// CHECK: store [2 x [[S_FLOAT_TY]]]* {{.+}}, [2 x [[S_FLOAT_TY]]]** [[S_ARR_ADDR]],
// CHECK: store [[S_FLOAT_TY]]* {{.+}}, [[S_FLOAT_TY]]** [[VAR_ADDR]],
// CHECK: store i{{[0-9]+}} {{.+}}, i{{[0-9]+}}* [[SIVAR_ADDR]],
// T_VAR and SIVAR
// CHECK-DAG-64: [[CONV_TVAR:%.+]] = bitcast i64* [[T_VAR_ADDR]] to i32*
// CHECK-DAG-64: [[CONV_SIVAR:%.+]] = bitcast i64* [[SIVAR_ADDR]] to i32*
// preparation vars
// CHECK-DAG: [[VEC_ADDR_VAL:%.+]] = load [2 x i{{[0-9]+}}]*, [2 x i{{[0-9]+}}]** [[VEC_ADDR]],
// CHECK-DAG: [[S_ARR_ADDR_REF:%.+]] = load [2 x [[S_FLOAT_TY]]]*, [2 x [[S_FLOAT_TY]]]** [[S_ARR_ADDR]],
// CHECK-DAG: [[VAR_ADDR_REF:%.+]] = load{{.+}} [[VAR_ADDR]],
// firstprivate vec(vec): copy from *_addr into priv1 and then from priv1 into priv2
// CHECK-DAG: [[VEC_DEST_PRIV:%.+]] = bitcast [2 x i{{[0-9]+}}]* [[VEC_PRIV]] to i8*
// CHECK-DAG: [[VEC_SRC:%.+]] = bitcast [2 x i{{[0-9]+}}]* [[VEC_ADDR_VAL]] to i8*
// CHECK: call void @llvm.memcpy.{{.+}}(i8* [[VEC_DEST_PRIV]], i8* [[VEC_SRC]], {{.+}})
// firstprivate(s_arr)
// CHECK-DAG: [[S_ARR_PRIV_BGN:%.+]] = getelementptr{{.*}} [2 x [[S_FLOAT_TY]]], [2 x [[S_FLOAT_TY]]]* [[S_ARR_PRIV]],
// CHECK-DAG: [[S_ARR_ADDR_BGN:%.+]] = bitcast [2 x [[S_FLOAT_TY]]]* [[S_ARR_ADDR_REF]] to
// CHECK-DAG: [[S_ARR_FIN:%.+]] = icmp{{.+}} [[S_ARR_PRIV_BGN]],
// CHECK-DAG: [[S_ARR_SRC_COPY:%.+]] = phi{{.+}} [ [[S_ARR_ADDR_BGN]], {{.+}} ], [ [[S_ARR_SRC:%.+]], {{.+}} ]
// CHECK-DAG: [[S_ARR_DST_COPY:%.+]] = phi{{.+}} [ [[S_ARR_PRIV_BGN]], {{.+}}], [ [[S_ARR_DST:%.+]], {{.+}} ]
// CHECK-DAG: call void @{{.+}}({{.+}} [[AGG_TMP1]])
// CHECK-DAG: call void @{{.+}}({{.+}} [[S_ARR_DST_COPY]], {{.+}} [[S_ARR_SRC_COPY]], {{.+}} [[AGG_TMP1]])
// CHECK-DAG: call void @{{.+}}({{.+}} [[AGG_TMP1]])
// CHECK-DAG: [[S_ARR_DST]] = getelementptr {{.+}} [[S_ARR_DST_COPY]],
// CHECK-DAG: [[S_ARR_SRC]] = getelementptr {{.+}} [[S_ARR_SRC_COPY]],
// firstprivate(var)
// CHECK-DAG: call void @{{.+}}({{.+}} [[AGG_TMP2]])
// CHECK-DAG: call void @{{.+}}({{.+}} [[VAR_PRIV]], {{.+}} [[VAR_ADDR_REF]], {{.+}} [[AGG_TMP2]])
// CHECK-DAG: call void @{{.+}}({{.+}} [[AGG_TMP2]])
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK-DAG-32: {{.+}} = {{.+}} [[T_VAR_ADDR]]
// CHECK-DAG-64: {{.+}} = {{.+}} [[CONV_TVAR]]
// CHECK-DAG: {{.+}} = {{.+}} [[VEC_PRIV]]
// CHECK-DAG: {{.+}} = {{.+}} [[S_ARR_PRIV]]
// CHECK-DAG: {{.+}} = {{.+}} [[VAR_PRIV]]
// CHECK-DAG-32: {{.+}} = {{.+}} [[SIVAR_ADDR]]
// CHECK-DAG-64: {{.+}} = {{.+}} [[CONV_SIVAR]]
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
// CHECK: define{{.*}} i{{[0-9]+}} @[[TMAIN_INT]]()
// CHECK: call i32 @__tgt_target(i32 -1, i8* @{{[^,]+}}, i32 4, i8** %{{[^,]+}}, i8** %{{[^,]+}}, i{{64|32}}* {{.+}}@{{[^,]+}}, i32 0, i32 0), i32* {{.+}}@{{[^,]+}}, i32 0, i32 0))
// CHECK: call void @[[TOFFL1:.+]](i{{64|32}} %{{.+}})
// CHECK: ret
// CHECK: define {{.*}}void @[[TOFFL1]]({{.+}})
// CHECK: [[TT_VAR_PRIV:%.+]] = alloca i{{[0-9]+}},
// CHECK: [[TVEC_PRIV:%.+]] = alloca [2 x i{{[0-9]+}}]*,
// CHECK: [[TS_ARR_PRIV:%.+]] = alloca [2 x [[S_INT_TY]]]*,
// CHECK: [[TVAR_PRIV:%.+]] = alloca [[S_INT_TY]]*,
// CHECK: [[TT_VAR_CAST:%.+]] = alloca i{{[0-9]+}},
// CHECK-DAG: [[TVEC_TE_PAR:%.+]] = load [2 x i{{[0-9]+}}]*, [2 x i{{[0-9]+}}]** [[TVEC_PRIV]],
// CHECK-DAG: [[TT_VAR_TE_PAR:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[TT_VAR_CAST]],
// CHECK-DAG: [[TS_ARR_TE_PAR:%.+]] = load [2 x [[S_INT_TY]]]*, [2 x [[S_INT_TY]]]** [[TS_ARR_PRIV]],
// CHECK-DAG: [[TVAR_TE_PAR:%.+]] = load [[S_INT_TY]]*, [[S_INT_TY]]** [[TVAR_PRIV]],
// CHECK: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 4, {{.+}} @[[TOUTL1:.+]] to {{.+}}, [2 x i{{[0-9]+}}]* [[TVEC_TE_PAR]], i{{[0-9]+}} [[TT_VAR_TE_PAR]], [2 x [[S_INT_TY]]]* [[TS_ARR_TE_PAR]], [[S_INT_TY]]* [[TVAR_TE_PAR]])
// CHECK: ret void
// CHECK: define internal void @[[TOUTL1]]({{.+}})
// Skip global and bound tid vars
// CHECK: {{.+}} = alloca i32*,
// CHECK: {{.+}} = alloca i32*,
// CHECK: [[VEC_ADDR:%.+]] = alloca [2 x i{{[0-9]+}}]*,
// CHECK: [[T_VAR_ADDR:%.+]] = alloca i{{[0-9]+}},
// CHECK: [[S_ARR_ADDR:%.+]] = alloca [2 x [[S_INT_TY]]]*,
// CHECK: [[VAR_ADDR:%.+]] = alloca [[S_INT_TY]]*,
// Skip temp vars for loop
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: [[VEC_PRIV:%.+]] = alloca [2 x i{{[0-9]+}}],
// CHECK: [[S_ARR_PRIV:%.+]] = alloca [2 x [[S_INT_TY]]],
// CHECK: [[AGG_TMP1:%.+]] = alloca [[ST_TY]],
// CHECK: [[VAR_PRIV:%.+]] = alloca [[S_INT_TY]],
// CHECK: [[AGG_TMP2:%.+]] = alloca [[ST_TY]],
// CHECK: [[TMP:%.+]] = alloca [[S_INT_TY]]*,
// param copy
// CHECK: store [2 x i{{[0-9]+}}]* {{.+}}, [2 x i{{[0-9]+}}]** [[VEC_ADDR]],
// CHECK: store i{{[0-9]+}} {{.+}}, i{{[0-9]+}}* [[T_VAR_ADDR]],
// CHECK: store [2 x [[S_INT_TY]]]* {{.+}}, [2 x [[S_INT_TY]]]** [[S_ARR_ADDR]],
// CHECK: store [[S_INT_TY]]* {{.+}}, [[S_INT_TY]]** [[VAR_ADDR]],
// T_VAR and preparation variables
// CHECK: [[VEC_ADDR_VAL:%.+]] = load [2 x i{{[0-9]+}}]*, [2 x i{{[0-9]+}}]** [[VEC_ADDR]],
// CHECK-64: [[CONV_TVAR:%.+]] = bitcast i64* [[T_VAR_ADDR]] to i32*
// CHECK: [[S_ARR_ADDR_REF:%.+]] = load [2 x [[S_INT_TY]]]*, [2 x [[S_INT_TY]]]** [[S_ARR_ADDR]],
// firstprivate vec(vec): copy from *_addr into priv1 and then from priv1 into priv2
// CHECK-DAG: [[VEC_DEST_PRIV:%.+]] = bitcast [2 x i{{[0-9]+}}]* [[VEC_PRIV]] to i8*
// CHECK-DAG: [[VEC_SRC:%.+]] = bitcast [2 x i{{[0-9]+}}]* [[VEC_ADDR_VAL]] to i8*
// CHECK: call void @llvm.memcpy.{{.+}}(i8* [[VEC_DEST_PRIV]], i8* [[VEC_SRC]], {{.+}})
// firstprivate(s_arr)
// CHECK-DAG: [[S_ARR_PRIV_BGN:%.+]] = getelementptr{{.*}} [2 x [[S_INT_TY]]], [2 x [[S_INT_TY]]]* [[S_ARR_PRIV]],
// CHECK-DAG: [[S_ARR_ADDR_BGN:%.+]] = bitcast [2 x [[S_INT_TY]]]* [[S_ARR_ADDR_REF]] to
// CHECK-DAG: [[S_ARR_FIN:%.+]] = icmp{{.+}} [[S_ARR_PRIV_BGN]],
// CHECK-DAG: [[S_ARR_SRC_COPY:%.+]] = phi{{.+}} [ [[S_ARR_ADDR_BGN]], {{.+}} ], [ [[S_ARR_SRC:%.+]], {{.+}} ]
// CHECK-DAG: [[S_ARR_DST_COPY:%.+]] = phi{{.+}} [ [[S_ARR_PRIV_BGN]], {{.+}} ], [ [[S_ARR_DST:%.+]], {{.+}} ]
// CHECK-DAG: call void @{{.+}}({{.+}} [[AGG_TMP1]])
// CHECK-DAG: call void @{{.+}}({{.+}} [[S_ARR_DST_COPY]], {{.+}} [[S_ARR_SRC_COPY]], {{.+}} [[AGG_TMP1]])
// CHECK-DAG: call void @{{.+}}({{.+}} [[AGG_TMP1]])
// CHECK-DAG: [[S_ARR_DST]] = getelementptr {{.+}} [[S_ARR_DST_COPY]],
// CHECK-DAG: [[S_ARR_SRC]] = getelementptr {{.+}} [[S_ARR_SRC_COPY]],
// firstprivate(var)
// CHECK-DAG: [[VAR_ADDR_REF:%.+]] = load{{.+}} [[VAR_ADDR]],
// CHECK-DAG: call void @{{.+}}({{.+}} [[AGG_TMP2]])
// CHECK-DAG: call void @{{.+}}({{.+}} [[VAR_PRIV]], {{.+}} [[VAR_ADDR_REF]], {{.+}} [[AGG_TMP2]])
// CHECK-DAG: call void @{{.+}}({{.+}} [[AGG_TMP2]])
// CHECK-DAG: store [[S_INT_TY]]* [[VAR_PRIV]], [[S_INT_TY]]** [[TMP]],
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[TPAR_OUTL:.+]] to
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
// CHECK: define internal void @[[TPAR_OUTL]]({{.+}})
// Skip global and bound tid vars
// CHECK: {{.+}} = alloca i32*,
// CHECK: {{.+}} = alloca i32*,
// CHECK: [[VEC_ADDR:%.+]] = alloca [2 x i{{[0-9]+}}]*,
// CHECK: [[T_VAR_ADDR:%.+]] = alloca i{{[0-9]+}},
// CHECK: [[S_ARR_ADDR:%.+]] = alloca [2 x [[S_INT_TY]]]*,
// CHECK: [[VAR_ADDR:%.+]] = alloca [[S_INT_TY]]*,
// Skip temp vars for loop
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: [[VEC_PRIV:%.+]] = alloca [2 x i{{[0-9]+}}],
// CHECK: [[S_ARR_PRIV:%.+]] = alloca [2 x [[S_INT_TY]]],
// CHECK: [[AGG_TMP1:%.+]] = alloca [[ST_TY]],
// CHECK: [[VAR_PRIV:%.+]] = alloca [[S_INT_TY]],
// CHECK: [[AGG_TMP2:%.+]] = alloca [[ST_TY]],
// CHECK: [[TMP:%.+]] = alloca [[S_INT_TY]]*,
// param copy
// CHECK: store [2 x i{{[0-9]+}}]* {{.+}}, [2 x i{{[0-9]+}}]** [[VEC_ADDR]],
// CHECK: store i{{[0-9]+}} {{.+}}, i{{[0-9]+}}* [[T_VAR_ADDR]],
// CHECK: store [2 x [[S_INT_TY]]]* {{.+}}, [2 x [[S_INT_TY]]]** [[S_ARR_ADDR]],
// CHECK: store [[S_INT_TY]]* {{.+}}, [[S_INT_TY]]** [[VAR_ADDR]],
// T_VAR and preparation variables
// CHECK: [[VEC_ADDR_VAL:%.+]] = load [2 x i{{[0-9]+}}]*, [2 x i{{[0-9]+}}]** [[VEC_ADDR]],
// CHECK-64: [[CONV_TVAR:%.+]] = bitcast i64* [[T_VAR_ADDR]] to i32*
// CHECK: [[S_ARR_ADDR_REF:%.+]] = load [2 x [[S_INT_TY]]]*, [2 x [[S_INT_TY]]]** [[S_ARR_ADDR]],
// firstprivate vec(vec): copy from *_addr into priv1 and then from priv1 into priv2
// CHECK-DAG: [[VEC_DEST_PRIV:%.+]] = bitcast [2 x i{{[0-9]+}}]* [[VEC_PRIV]] to i8*
// CHECK-DAG: [[VEC_SRC:%.+]] = bitcast [2 x i{{[0-9]+}}]* [[VEC_ADDR_VAL]] to i8*
// CHECK: call void @llvm.memcpy.{{.+}}(i8* [[VEC_DEST_PRIV]], i8* [[VEC_SRC]], {{.+}})
// firstprivate(s_arr)
// CHECK-DAG: [[S_ARR_PRIV_BGN:%.+]] = getelementptr{{.*}} [2 x [[S_INT_TY]]], [2 x [[S_INT_TY]]]* [[S_ARR_PRIV]],
// CHECK-DAG: [[S_ARR_ADDR_BGN:%.+]] = bitcast [2 x [[S_INT_TY]]]* [[S_ARR_ADDR_REF]] to
// CHECK-DAG: [[S_ARR_FIN:%.+]] = icmp{{.+}} [[S_ARR_PRIV_BGN]],
// CHECK-DAG: [[S_ARR_SRC_COPY:%.+]] = phi{{.+}} [ [[S_ARR_ADDR_BGN]], {{.+}} ], [ [[S_ARR_SRC:%.+]], {{.+}} ]
// CHECK-DAG: [[S_ARR_DST_COPY:%.+]] = phi{{.+}} [ [[S_ARR_PRIV_BGN]], {{.+}} ], [ [[S_ARR_DST:%.+]], {{.+}} ]
// CHECK-DAG: call void @{{.+}}({{.+}} [[AGG_TMP1]])
// CHECK-DAG: call void @{{.+}}({{.+}} [[S_ARR_DST_COPY]], {{.+}} [[S_ARR_SRC_COPY]], {{.+}} [[AGG_TMP1]])
// CHECK-DAG: call void @{{.+}}({{.+}} [[AGG_TMP1]])
// CHECK-DAG: [[S_ARR_DST]] = getelementptr {{.+}} [[S_ARR_DST_COPY]],
// CHECK-DAG: [[S_ARR_SRC]] = getelementptr {{.+}} [[S_ARR_SRC_COPY]],
// firstprivate(var)
// CHECK-DAG: [[VAR_ADDR_REF:%.+]] = load{{.+}} [[VAR_ADDR]],
// CHECK-DAG: call void @{{.+}}({{.+}} [[AGG_TMP2]])
// CHECK-DAG: call void @{{.+}}({{.+}} [[VAR_PRIV]], {{.+}} [[VAR_ADDR_REF]], {{.+}} [[AGG_TMP2]])
// CHECK-DAG: call void @{{.+}}({{.+}} [[AGG_TMP2]])
// CHECK-DAG: store [[S_INT_TY]]* [[VAR_PRIV]], [[S_INT_TY]]** [[TMP]],
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK-DAG-32: {{.+}} = {{.+}} [[T_VAR_ADDR]]
// CHECK-DAG-64: {{.+}} = {{.+}} [[CONV_TVAR]]
// CHECK-DAG: {{.+}} = {{.+}} [[VEC_PRIV]]
// CHECK-DAG: {{.+}} = {{.+}} [[TMP]]
// CHECK-DAG: {{.+}} = {{.+}} [[S_ARR_PRIV]]
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
#endif

184
clang/test/OpenMP/teams_distribute_parallel_for_if_codegen.cpp Normal file
View File

@ -0,0 +1,184 @@
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple %itanium_abi_triple -emit-llvm %s -o - | FileCheck %s
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple %itanium_abi_triple -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple %itanium_abi_triple -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
void fn1();
void fn2();
void fn3();
void fn4();
void fn5();
void fn6();
int Arg;
// CHECK-LABEL: define {{.*}}void @{{.+}}gtid_test
void gtid_test() {
#pragma omp target
// CHECK: call i{{[0-9]+}} @__tgt_target(
// CHECK: call void [[OFFLOADING_FUN_0:@.+]](
// CHECK: call i{{[0-9]+}} @__tgt_target(
// CHECK: call void [[OFFLOADING_FUN_1:@.+]](
#pragma omp teams distribute parallel for
for(int i = 0 ; i < 100; i++) {}
// CHECK: define internal void [[OFFLOADING_FUN_0]](
// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_teams({{.+}}, i32 0, {{.+}}* [[OMP_TEAMS_OUTLINED_0:@.+]] to {{.+}})
// CHECK: define{{.+}} void [[OMP_TEAMS_OUTLINED_0]](
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void {{.+}} @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{.+}} 2, {{.+}}* [[OMP_OUTLINED_0:@.+]] to void
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: define{{.+}} void [[OMP_OUTLINED_0]](
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret
#pragma omp target
#pragma omp teams distribute parallel for if (parallel: false)
for(int i = 0 ; i < 100; i++) {
// CHECK: define internal void [[OFFLOADING_FUN_1]](
// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_teams({{.+}}, i32 0, {{.+}}* [[OMP_TEAMS_OUTLINED_1:@.+]] to {{.+}})
// CHECK: define{{.+}} void [[OMP_TEAMS_OUTLINED_1]](
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void @__kmpc_serialized_parallel(
// CHECK: call void [[OMP_OUTLINED_1:@.+]](
// CHECK: call void @__kmpc_end_serialized_parallel(
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: define{{.+}} void [[OMP_OUTLINED_1]](
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void @{{.+}}gtid_test
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret
gtid_test();
}
}
template <typename T>
int tmain(T Arg) {
#pragma omp target
#pragma omp teams distribute parallel for if (true)
for(int i = 0 ; i < 100; i++) {
fn1();
}
#pragma omp target
#pragma omp teams distribute parallel for if (false)
for(int i = 0 ; i < 100; i++) {
fn2();
}
#pragma omp target
#pragma omp teams distribute parallel for if (parallel: Arg)
for(int i = 0 ; i < 100; i++) {
fn3();
}
return 0;
}
// CHECK-LABEL: define {{.*}}i{{[0-9]+}} @main()
int main() {
// CHECK: call i{{[0-9]+}} @__tgt_target(
// CHECK: call void [[OFFLOADING_FUN_0:@.+]](
// CHECK: call i{{[0-9]+}} @__tgt_target(
// CHECK: call void [[OFFLOADING_FUN_1:@.+]](
// CHECK: call i{{[0-9]+}} @__tgt_target(
// CHECK: call void [[OFFLOADING_FUN_2:@.+]](
// CHECK: = call {{.*}}i{{.+}} @{{.+}}tmain
#pragma omp target
#pragma omp teams distribute parallel for if (true)
for(int i = 0 ; i < 100; i++) {
// CHECK: define internal void [[OFFLOADING_FUN_0]](
// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_teams({{.+}}, i32 0, {{.+}}* [[OMP_TEAMS_OUTLINED_0:@.+]] to {{.+}})
// CHECK: define{{.+}} void [[OMP_TEAMS_OUTLINED_0]](
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void {{.+}} @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{.+}} 2, {{.+}}* [[OMP_OUTLINED_2:@.+]] to void
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: define{{.+}} void [[OMP_OUTLINED_2]](
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call {{.*}}void @{{.+}}fn4
// CHECK: call void @__kmpc_for_static_fini(
fn4();
}
#pragma omp target
#pragma omp teams distribute parallel for if (false)
for(int i = 0 ; i < 100; i++) {
// CHECK: define internal void [[OFFLOADING_FUN_1]](
// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_teams({{.+}}, i32 0, {{.+}}* [[OMP_TEAMS_OUTLINED_1:@.+]] to {{.+}})
// CHECK: define{{.+}} void [[OMP_TEAMS_OUTLINED_1]](
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void @__kmpc_serialized_parallel(
// CHECK: call void [[OMP_OUTLINED_3:@.+]](
// CHECK: call void @__kmpc_end_serialized_parallel(
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: define{{.+}} void [[OMP_OUTLINED_3]](
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call {{.*}}void @{{.+}}fn5
// CHECK: call void @__kmpc_for_static_fini(
fn5();
}
#pragma omp target
#pragma omp teams distribute parallel for if (Arg)
for(int i = 0 ; i < 100; i++) {
// CHECK: define internal void [[OFFLOADING_FUN_2]](
// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_teams({{.+}}, i32 1, {{.+}}* [[OMP_TEAMS_OUTLINED_2:@.+]] to {{.+}})
// CHECK: define{{.+}} void [[OMP_TEAMS_OUTLINED_2]](
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void {{.+}} @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{.+}} 2, {{.+}}* [[OMP_OUTLINED_4:@.+]] to void
// CHECK: call void @__kmpc_serialized_parallel(
// CHECK: call void [[OMP_OUTLINED_4:@.+]](
// CHECK: call void @__kmpc_end_serialized_parallel(
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: define{{.+}} void [[OMP_OUTLINED_4]](
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call {{.*}}void @{{.+}}fn6
// CHECK: call void @__kmpc_for_static_fini(
fn6();
}
return tmain(Arg);
}
// CHECK-LABEL: define {{.+}} @{{.+}}tmain
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{.+}} 2, void {{.+}}* [[T_OUTLINE_FUN_1:@.+]] to void
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: define internal {{.*}}void [[T_OUTLINE_FUN_1]]
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call {{.*}}void @{{.+}}fn1
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call {{.*}}void @__kmpc_serialized_parallel(
// CHECK: call void [[T_OUTLINE_FUN_2:@.+]](
// CHECK: call {{.*}}void @__kmpc_end_serialized_parallel(
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: define internal {{.*}}void [[T_OUTLINE_FUN_2]]
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call {{.*}}void @{{.+}}fn2
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{.+}} 2, void {{.+}}* [[T_OUTLINE_FUN_3:@.+]] to void
// CHECK: call {{.*}}void @__kmpc_serialized_parallel(
// call void [[T_OUTLINE_FUN_3:@.+]](
// CHECK: call {{.*}}void @__kmpc_end_serialized_parallel(
// CHECK: define internal {{.*}}void [[T_OUTLINE_FUN_3]]
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call {{.*}}void @{{.+}}fn3
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
#endif

578
clang/test/OpenMP/teams_distribute_parallel_for_lastprivate_codegen.cpp Normal file
View File

@ -0,0 +1,578 @@
// RUN: %clang_cc1 -DLAMBDA -verify -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix LAMBDA --check-prefix LAMBDA-64
// RUN: %clang_cc1 -DLAMBDA -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DLAMBDA -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix LAMBDA --check-prefix LAMBDA-64
// RUN: %clang_cc1 -DLAMBDA -verify -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix LAMBDA --check-prefix LAMBDA-32
// RUN: %clang_cc1 -DLAMBDA -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DLAMBDA -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix LAMBDA --check-prefix LAMBDA-32
// RUN: %clang_cc1 -verify -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
// RUN: %clang_cc1 -verify -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
template <class T>
struct S {
T f;
S(T a) : f(a) {}
S() : f() {}
operator T() { return T(); }
~S() {}
};
// CHECK: [[S_FLOAT_TY:%.+]] = type { float }
// CHECK: [[S_INT_TY:%.+]] = type { i{{[0-9]+}} }
template <typename T>
T tmain() {
S<T> test;
T t_var = T();
T vec[] = {1, 2};
S<T> s_arr[] = {1, 2};
S<T> &var = test;
#pragma omp target
#pragma omp teams distribute parallel for lastprivate(t_var, vec, s_arr, s_arr, var, var)
for (int i = 0; i < 2; ++i) {
vec[i] = t_var;
s_arr[i] = var;
}
return T();
}
int main() {
static int svar;
volatile double g;
volatile double &g1 = g;
#ifdef LAMBDA
// LAMBDA-LABEL: @main
// LAMBDA: call{{.*}} void [[OUTER_LAMBDA:@.+]](
[&]() {
static float sfvar;
// LAMBDA: define{{.*}} internal{{.*}} void [[OUTER_LAMBDA]](
// LAMBDA: call i{{[0-9]+}} @__tgt_target(
// LAMBDA: call void [[OFFLOADING_FUN:@.+]](
// LAMBDA: define{{.+}} void [[OFFLOADING_FUN]](
// LAMBDA: call {{.*}}void {{.+}} @__kmpc_fork_teams({{.+}}, i32 4, {{.+}}* [[OMP_OUTLINED:@.+]] to {{.+}})
#pragma omp target
#pragma omp teams distribute parallel for lastprivate(g, g1, svar, sfvar)
for (int i = 0; i < 2; ++i) {
// LAMBDA: define{{.*}} internal{{.*}} void [[OMP_OUTLINED]](i32* noalias %{{.+}}, i32* noalias %{{.+}}, double*{{.+}} [[G_IN:%.+]], double*{{.+}} [[G1_IN:%.+]], i{{[0-9]+}}*{{.+}} [[SVAR_IN:%.+]], float*{{.+}} [[SFVAR_IN:%.+]])
// LAMBDA: [[G_PRIVATE_ADDR:%.+]] = alloca double*,
// LAMBDA: [[G1_PRIVATE_ADDR:%.+]] = alloca double*,
// LAMBDA: [[SVAR_PRIVATE_ADDR:%.+]] = alloca i{{[0-9]+}}*,
// LAMBDA: [[SFVAR_PRIVATE_ADDR:%.+]] = alloca float*,
// loop variables
// LAMBDA: {{.+}} = alloca i{{[0-9]+}},
// LAMBDA: {{.+}} = alloca i{{[0-9]+}},
// LAMBDA: {{.+}} = alloca i{{[0-9]+}},
// LAMBDA: {{.+}} = alloca i{{[0-9]+}},
// LAMBDA: [[OMP_IS_LAST:%.+]] = alloca i{{[0-9]+}},
// LAMBDA: [[G_PRIVATE:%.+]] = alloca double,
// LAMBDA: [[G1_PRIVATE:%.+]] = alloca double,
// LAMBDA: [[TMP_G1_PRIVATE:%.+]] = alloca double*,
// LAMBDA: [[SVAR_PRIVATE:%.+]] = alloca i{{[0-9]+}},
// LAMBDA: [[SFVAR_PRIVATE:%.+]] = alloca float,
// LAMBDA: store double* [[G_IN]], double** [[G_PRIVATE_ADDR]],
// LAMBDA: store double* [[G1_IN]], double** [[G1_PRIVATE_ADDR]],
// LAMBDA: store i{{[0-9]+}}* [[SVAR_IN]], i{{[0-9]+}}** [[SVAR_PRIVATE_ADDR]],
// LAMBDA: store float* [[SFVAR_IN]], float** [[SFVAR_PRIVATE_ADDR]],
// init private variables
// LAMBDA: [[G_IN_REF:%.+]] = load double*, double** [[G_PRIVATE_ADDR]],
// LAMBDA: [[SVAR_IN_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[SVAR_PRIVATE_ADDR]],
// LAMBDA: [[SFVAR_IN_REF:%.+]] = load float*, float** [[SFVAR_PRIVATE_ADDR]],
// LAMBDA: [[G1_IN_REF:%.+]] = load double*, double** [[G1_PRIVATE_ADDR]],
// LAMBDA: store double* [[G1_PRIVATE]], double** [[TMP_G1_PRIVATE]],
g = 1;
g1 = 1;
svar = 3;
sfvar = 4.0;
// LAMBDA: call {{.*}}void @__kmpc_for_static_init_4(
// LAMBDA: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[LPAR_OUTL:.+]] to
// LAMBDA: call {{.*}}void @__kmpc_for_static_fini(
// LAMBDA: [[OMP_IS_LAST_VAL:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[OMP_IS_LAST]],
// LAMBDA: [[IS_LAST_IT:%.+]] = icmp ne i{{[0-9]+}} [[OMP_IS_LAST_VAL]], 0
// LAMBDA: br i1 [[IS_LAST_IT]], label %[[OMP_LASTPRIV_BLOCK:.+]], label %[[OMP_LASTPRIV_DONE:.+]]
// LAMBDA: [[OMP_LASTPRIV_BLOCK]]:
// LAMBDA: [[G_PRIV_VAL:%.+]] = load double, double* [[G_PRIVATE]],
// LAMBDA: store{{.*}} double [[G_PRIV_VAL]], double* [[G_IN_REF]],
// LAMBDA: [[TMP_G1_PRIV_REF:%.+]] = load double*, double** [[TMP_G1_PRIVATE]],
// LAMBDA: [[TMP_G1_PRIV_VAL:%.+]] = load double, double* [[TMP_G1_PRIV_REF]],
// LAMBDA: store{{.*}} double [[TMP_G1_PRIV_VAL]], double* [[G1_IN_REF]],
// LAMBDA: [[SVAR_PRIV_VAL:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[SVAR_PRIVATE]],
// LAMBDA: store i{{[0-9]+}} [[SVAR_PRIV_VAL]], i{{[0-9]+}}* [[SVAR_IN_REF]],
// LAMBDA: [[SFVAR_PRIV_VAL:%.+]] = load float, float* [[SFVAR_PRIVATE]],
// LAMBDA: store float [[SFVAR_PRIV_VAL]], float* [[SFVAR_IN_REF]],
// LAMBDA: br label %[[OMP_LASTPRIV_DONE]]
// LAMBDA: [[OMP_LASTPRIV_DONE]]:
// LAMBDA: ret
// LAMBDA: define{{.*}} internal{{.*}} void @[[LPAR_OUTL]](i32* noalias %{{.+}}, i32* noalias %{{.+}}, {{.+}}, {{.+}}, double*{{.+}} [[G_IN:%.+]], double*{{.+}} [[G1_IN:%.+]], i{{[0-9]+}}*{{.+}} [[SVAR_IN:%.+]], float*{{.+}} [[SFVAR_IN:%.+]])
// LAMBDA: [[G_PRIVATE_ADDR:%.+]] = alloca double*,
// LAMBDA: [[G1_PRIVATE_ADDR:%.+]] = alloca double*,
// LAMBDA: [[SVAR_PRIVATE_ADDR:%.+]] = alloca i{{[0-9]+}}*,
// LAMBDA: [[SFVAR_PRIVATE_ADDR:%.+]] = alloca float*,
// loop variables
// LAMBDA: {{.+}} = alloca i{{[0-9]+}},
// LAMBDA: {{.+}} = alloca i{{[0-9]+}},
// LAMBDA: {{.+}} = alloca i{{[0-9]+}},
// LAMBDA: {{.+}} = alloca i{{[0-9]+}},
// LAMBDA: [[OMP_IS_LAST:%.+]] = alloca i{{[0-9]+}},
// LAMBDA: [[G_PRIVATE:%.+]] = alloca double,
// LAMBDA: [[G1_PRIVATE:%.+]] = alloca double,
// LAMBDA: [[TMP_G1_PRIVATE:%.+]] = alloca double*,
// LAMBDA: [[SVAR_PRIVATE:%.+]] = alloca i{{[0-9]+}},
// LAMBDA: [[SFVAR_PRIVATE:%.+]] = alloca float,
// LAMBDA: store double* [[G_IN]], double** [[G_PRIVATE_ADDR]],
// LAMBDA: store double* [[G1_IN]], double** [[G1_PRIVATE_ADDR]],
// LAMBDA: store i{{[0-9]+}}* [[SVAR_IN]], i{{[0-9]+}}** [[SVAR_PRIVATE_ADDR]],
// LAMBDA: store float* [[SFVAR_IN]], float** [[SFVAR_PRIVATE_ADDR]],
// init private variables
// LAMBDA: [[G_IN_REF:%.+]] = load double*, double** [[G_PRIVATE_ADDR]],
// LAMBDA: [[SVAR_IN_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[SVAR_PRIVATE_ADDR]],
// LAMBDA: [[SFVAR_IN_REF:%.+]] = load float*, float** [[SFVAR_PRIVATE_ADDR]],
// LAMBDA: [[G1_IN_REF:%.+]] = load double*, double** [[G1_PRIVATE_ADDR]],
// LAMBDA: store double* [[G1_PRIVATE]], double** [[TMP_G1_PRIVATE]],
// LAMBDA: call {{.*}}void @__kmpc_for_static_init_4(
// LAMBDA: store double 1.0{{.+}}, double* [[G_PRIVATE]],
// LAMBDA: [[TMP_G1_REF:%.+]] = load double*, double** [[TMP_G1_PRIVATE]],
// LAMBDA: store{{.+}} double 1.0{{.+}}, double* [[TMP_G1_REF]],
// LAMBDA: store i{{[0-9]+}} 3, i{{[0-9]+}}* [[SVAR_PRIVATE]],
// LAMBDA: store float 4.0{{.+}}, float* [[SFVAR_PRIVATE]],
// LAMBDA: [[G_PRIVATE_ADDR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG:%.+]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
// LAMBDA: store double* [[G_PRIVATE]], double** [[G_PRIVATE_ADDR_REF]],
// LAMBDA: [[TMP_PRIVATE_ADDR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG:%.+]], i{{[0-9]+}} 0, i{{[0-9]+}} 1
// LAMBDA: [[G1_PRIVATE_ADDR_FROM_TMP:%.+]] = load double*, double** [[TMP_G1_PRIVATE]],
// LAMBDA: store double* [[G1_PRIVATE_ADDR_FROM_TMP]], double** [[TMP_PRIVATE_ADDR_REF]],
// LAMBDA: [[SVAR_PRIVATE_ADDR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG:%.+]], i{{[0-9]+}} 0, i{{[0-9]+}} 2
// LAMBDA: store i{{[0-9]+}}* [[SVAR_PRIVATE]], i{{[0-9]+}}** [[SVAR_PRIVATE_ADDR_REF]]
// LAMBDA: [[SFVAR_PRIVATE_ADDR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG:%.+]], i{{[0-9]+}} 0, i{{[0-9]+}} 3
// LAMBDA: store float* [[SFVAR_PRIVATE]], float** [[SFVAR_PRIVATE_ADDR_REF]]
// LAMBDA: call{{.*}} void [[INNER_LAMBDA:@.+]](%{{.+}}* [[ARG]])
// LAMBDA: call {{.*}}void @__kmpc_for_static_fini(
// LAMBDA: [[OMP_IS_LAST_VAL:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[OMP_IS_LAST]],
// LAMBDA: [[IS_LAST_IT:%.+]] = icmp ne i{{[0-9]+}} [[OMP_IS_LAST_VAL]], 0
// LAMBDA: br i1 [[IS_LAST_IT]], label %[[OMP_LASTPRIV_BLOCK:.+]], label %[[OMP_LASTPRIV_DONE:.+]]
// LAMBDA: [[OMP_LASTPRIV_BLOCK]]:
// LAMBDA: [[G_PRIV_VAL:%.+]] = load double, double* [[G_PRIVATE]],
// LAMBDA: store{{.*}} double [[G_PRIV_VAL]], double* [[G_IN_REF]],
// LAMBDA: [[TMP_G1_PRIV_REF:%.+]] = load double*, double** [[TMP_G1_PRIVATE]],
// LAMBDA: [[TMP_G1_PRIV_VAL:%.+]] = load double, double* [[TMP_G1_PRIV_REF]],
// LAMBDA: store{{.*}} double [[TMP_G1_PRIV_VAL]], double* [[G1_IN_REF]],
// LAMBDA: [[SVAR_PRIV_VAL:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[SVAR_PRIVATE]],
// LAMBDA: store i{{[0-9]+}} [[SVAR_PRIV_VAL]], i{{[0-9]+}}* [[SVAR_IN_REF]],
// LAMBDA: [[SFVAR_PRIV_VAL:%.+]] = load float, float* [[SFVAR_PRIVATE]],
// LAMBDA: store float [[SFVAR_PRIV_VAL]], float* [[SFVAR_IN_REF]],
// LAMBDA: br label %[[OMP_LASTPRIV_DONE]]
// LAMBDA: [[OMP_LASTPRIV_DONE]]:
// LAMBDA: ret
[&]() {
// LAMBDA: define {{.+}} void [[INNER_LAMBDA]](%{{.+}}* [[ARG_PTR:%.+]])
// LAMBDA: store %{{.+}}* [[ARG_PTR]], %{{.+}}** [[ARG_PTR_REF:%.+]],
g = 2;
g1 = 2;
svar = 4;
sfvar = 8.0;
// LAMBDA: [[ARG_PTR:%.+]] = load %{{.+}}*, %{{.+}}** [[ARG_PTR_REF]]
// LAMBDA: [[G_PTR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG_PTR]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
// LAMBDA: [[G_REF:%.+]] = load double*, double** [[G_PTR_REF]]
// LAMBDA: store double 2.0{{.+}}, double* [[G_REF]]
// LAMBDA: [[TMP_PTR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG_PTR]], i{{[0-9]+}} 0, i{{[0-9]+}} 1
// LAMBDA: [[G1_REF:%.+]] = load double*, double** [[TMP_PTR_REF]]
// LAMBDA: store double 2.0{{.+}}, double* [[G1_REF]],
// LAMBDA: [[SVAR_PTR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG_PTR]], i{{[0-9]+}} 0, i{{[0-9]+}} 2
// LAMBDA: [[SVAR_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[SVAR_PTR_REF]]
// LAMBDA: store i{{[0-9]+}} 4, i{{[0-9]+}}* [[SVAR_REF]]
// LAMBDA: [[SFVAR_PTR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG_PTR]], i{{[0-9]+}} 0, i{{[0-9]+}} 3
// LAMBDA: [[SFVAR_REF:%.+]] = load float*, float** [[SFVAR_PTR_REF]]
// LAMBDA: store float 8.0{{.+}}, float* [[SFVAR_REF]]
}();
}
}();
return 0;
#else
S<float> test;
int t_var = 0;
int vec[] = {1, 2};
S<float> s_arr[] = {1, 2};
S<float> &var = test;
#pragma omp target
#pragma omp teams distribute parallel for lastprivate(t_var, vec, s_arr, s_arr, var, var, svar)
for (int i = 0; i < 2; ++i) {
vec[i] = t_var;
s_arr[i] = var;
}
int i;
return tmain<int>();
#endif
}
// CHECK: define{{.*}} i{{[0-9]+}} @main()
// CHECK: [[TEST:%.+]] = alloca [[S_FLOAT_TY]],
// CHECK: call {{.*}} [[S_FLOAT_TY_DEF_CONSTR:@.+]]([[S_FLOAT_TY]]* [[TEST]])
// CHECK: call i{{[0-9]+}} @__tgt_target(
// CHECK: call void [[OFFLOAD_FUN:@.+]](i{{[0-9]+}} {{.+}}, [2 x i{{[0-9]+}}]* {{.+}}, [2 x [[S_FLOAT_TY]]]* {{.+}}, [[S_FLOAT_TY]]* {{.+}}, i{{[0-9]+}} {{.+}})
// CHECK: ret
// CHECK: define{{.+}} [[OFFLOAD_FUN]](i{{[0-9]+}} {{.+}}, [2 x i{{[0-9]+}}]*{{.+}} {{.+}}, [2 x [[S_FLOAT_TY]]]*{{.+}} {{.+}}, [[S_FLOAT_TY]]*{{.+}} {{.+}}, i{{[0-9]+}} {{.+}})
// CHECK: call void (%{{.+}}*, i{{[0-9]+}}, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)*, ...) @__kmpc_fork_teams(
// CHECK: ret
//
// CHECK: define internal void [[OMP_OUTLINED:@.+]](i{{[0-9]+}}* noalias [[GTID_ADDR:%.+]], i{{[0-9]+}}* noalias %{{.+}}, [2 x i{{[0-9]+}}]*{{.+}} [[VEC_IN:%.+]], i{{[0-9]+}}*{{.+}} [[T_VAR_IN:%.+]], [2 x [[S_FLOAT_TY]]]*{{.+}} [[S_ARR_IN:%.+]], [[S_FLOAT_TY]]*{{.+}} [[VAR_IN:%.+]], i{{[0-9]+}}*{{.*}} [[S_VAR_IN:%.+]])
// CHECK: {{.+}} = alloca i{{[0-9]+}}*,
// CHECK: {{.+}} = alloca i{{[0-9]+}}*,
// CHECK: [[VEC_ADDR:%.+]] = alloca [2 x i{{[0-9]+}}]*,
// CHECK: [[T_VAR_ADDR:%.+]] = alloca i{{[0-9]+}}*,
// CHECK: [[S_ARR_ADDR:%.+]] = alloca [2 x [[S_FLOAT_TY]]]*,
// CHECK: [[VAR_ADDR:%.+]] = alloca [[S_FLOAT_TY]]*,
// CHECK: [[SVAR_ADDR:%.+]] = alloca i{{[0-9]+}}*,
// skip loop variables
// CHECK: {{.+}} = alloca i{{[0-9]+}},
// CHECK: {{.+}} = alloca i{{[0-9]+}},
// CHECK: {{.+}} = alloca i{{[0-9]+}},
// CHECK: {{.+}} = alloca i{{[0-9]+}},
// CHECK: [[OMP_IS_LAST:%.+]] = alloca i{{[0-9]+}},
// CHECK: [[T_VAR_PRIV:%.+]] = alloca i{{[0-9]+}},
// CHECK: [[VEC_PRIV:%.+]] = alloca [2 x i{{[0-9]+}}],
// CHECK: [[S_ARR_PRIV:%.+]] = alloca [2 x [[S_FLOAT_TY]]],
// CHECK: [[VAR_PRIV:%.+]] = alloca [[S_FLOAT_TY]],
// CHECK: [[TMP_PRIV:%.+]] = alloca [[S_FLOAT_TY]]*,
// CHECK: [[S_VAR_PRIV:%.+]] = alloca i{{[0-9]+}},
// copy from parameters to local address variables
// CHECK: store [2 x i{{[0-9]+}}]* [[VEC_IN]], [2 x i{{[0-9]+}}]** [[VEC_ADDR]],
// CHECK: store i{{[0-9]+}}* [[T_VAR_IN]], i{{[0-9]+}}** [[T_VAR_ADDR]],
// CHECK: store [2 x [[S_FLOAT_TY]]]* [[S_ARR_IN]], [2 x [[S_FLOAT_TY]]]** [[S_ARR_ADDR]],
// CHECK: store [[S_FLOAT_TY]]* [[VAR_IN]], [[S_FLOAT_TY]]** [[VAR_ADDR]],
// CHECK: store i{{[0-9]+}}* [[S_VAR_IN]], i{{[0-9]+}}** [[SVAR_ADDR]],
// load content of local address variables
// CHECK: [[VEC_ADDR_REF:%.+]] = load [2 x i{{[0-9]+}}]*, [2 x i{{[0-9]+}}]** [[VEC_ADDR]],
// CHECK: [[T_VAR_ADDR_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[T_VAR_ADDR]],
// CHECK: [[S_ARR_ADDR_REF:%.+]] = load [2 x [[S_FLOAT_TY]]]*, [2 x [[S_FLOAT_TY]]]** [[S_ARR_ADDR]],
// CHECK: [[SVAR_ADDR_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[SVAR_ADDR]],
// CHECK: store i{{[0-9]+}} 0, i{{[0-9]+}}* [[OMP_IS_LAST]],
// CHECK: [[VAR_ADDR_REF:%.+]] = load {{.+}}, {{.+}} [[VAR_ADDR]],
// the distribute loop
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTL:.+]] to
// CHECK: call void @__kmpc_for_static_fini(
// lastprivates
// CHECK: [[OMP_IS_LAST_VAL:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[OMP_IS_LAST]],
// CHECK: [[IS_LAST_IT:%.+]] = icmp ne i{{[0-9]+}} [[OMP_IS_LAST_VAL]], 0
// CHECK: br i1 [[IS_LAST_IT]], label %[[OMP_LASTPRIV_BLOCK:.+]], label %[[OMP_LASTPRIV_DONE:.+]]
// CHECK: [[OMP_LASTPRIV_BLOCK]]:
// CHECK: [[T_VAR_VAL:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[T_VAR_PRIV]],
// CHECK: store i{{[0-9]+}} [[T_VAR_VAL]], i{{[0-9]+}}* [[T_VAR_ADDR_REF]],
// CHECK: [[BCAST_VEC_ADDR_REF:%.+]] = bitcast [2 x i{{[0-9]+}}]* [[VEC_ADDR_REF]] to i8*
// CHECK: [[BCAST_VEC_PRIV:%.+]] = bitcast [2 x i{{[0-9]+}}]* [[VEC_PRIV]] to i8*
// CHECK: call void @llvm.memcpy.{{.+}}(i8* [[BCAST_VEC_ADDR_REF]], i8* [[BCAST_VEC_PRIV]],
// CHECK: [[S_ARR_BEGIN:%.+]] = getelementptr inbounds [2 x [[S_FLOAT_TY]]], [2 x [[S_FLOAT_TY]]]* [[S_ARR_ADDR_REF]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
// CHECK: [[S_ARR_PRIV_BCAST:%.+]] = bitcast [2 x [[S_FLOAT_TY]]]* [[S_ARR_PRIV]] to [[S_FLOAT_TY]]*
// CHECK: [[S_ARR_BEGIN_GEP:%.+]] = getelementptr [[S_FLOAT_TY]], [[S_FLOAT_TY]]* [[S_ARR_BEGIN]], i{{[0-9]+}} 2
// CHECK: [[S_ARR_IS_EMPTY:%.+]] = icmp eq [[S_FLOAT_TY]]* [[S_ARR_BEGIN]], [[S_ARR_BEGIN_GEP]]
// CHECK: br i1 [[S_ARR_IS_EMPTY]], label %[[S_ARR_COPY_DONE:.+]], label %[[S_ARR_COPY_BLOCK:.+]]
// CHECK: [[S_ARR_COPY_BLOCK]]:
// CHECK: [[S_ARR_SRC_EL:%.+]] = phi [[S_FLOAT_TY]]*{{.+}}
// CHECK: [[S_ARR_DST_EL:%.+]] = phi [[S_FLOAT_TY]]*{{.+}}
// CHECK: [[S_ARR_DST_BCAST:%.+]] = bitcast [[S_FLOAT_TY]]* [[S_ARR_DST_EL]] to i8*
// CHECK: [[S_ARR_SRC_BCAST:%.+]] = bitcast [[S_FLOAT_TY]]* [[S_ARR_SRC_EL]] to i8*
// CHECK: call void @llvm.memcpy.{{.+}}(i8* [[S_ARR_DST_BCAST]], i8* [[S_ARR_SRC_BCAST]]{{.+}})
// CHECK: [[S_ARR_DST_NEXT:%.+]] = getelementptr [[S_FLOAT_TY]], [[S_FLOAT_TY]]* [[S_ARR_DST_EL]], i{{[0-9]+}} 1
// CHECK: [[S_ARR_SRC_NEXT:%.+]] = getelementptr{{.+}}
// CHECK: [[CPY_IS_FINISHED:%.+]] = icmp eq [[S_FLOAT_TY]]* [[S_ARR_DST_NEXT]], [[S_ARR_BEGIN_GEP]]
// CHECK: br i1 [[CPY_IS_FINISHED]], label %[[S_ARR_COPY_DONE]], label %[[S_ARR_COPY_BLOCK]]
// CHECK: [[S_ARR_COPY_DONE]]:
// CHECK: [[TMP_VAL1:%.+]] = load [[S_FLOAT_TY]]*, [[S_FLOAT_TY]]** [[TMP_PRIV]],
// CHECK: [[VAR_ADDR_REF_BCAST:%.+]] = bitcast [[S_FLOAT_TY]]* [[VAR_ADDR_REF]] to i8*
// CHECK: [[TMP_VAL1_BCAST:%.+]] = bitcast [[S_FLOAT_TY]]* [[TMP_VAL1]] to i8*
// CHECK: call void @llvm.memcpy.{{.+}}(i8* [[VAR_ADDR_REF_BCAST]], i8* [[TMP_VAL1_BCAST]],{{.+}})
// CHECK: [[SVAR_VAL:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[S_VAR_PRIV]],
// CHECK: store i{{[0-9]+}} [[SVAR_VAL]], i{{[0-9]+}}* [[SVAR_ADDR_REF]],
// CHECK: ret void
// CHECK: define internal void [[OMP_OUTLINED:@.+]](i{{[0-9]+}}* noalias [[GTID_ADDR:%.+]], i{{[0-9]+}}* noalias %{{.+}}, {{.+}}, {{.+}}, [2 x i{{[0-9]+}}]*{{.+}} [[VEC_IN:%.+]], i{{[0-9]+}}*{{.+}} [[T_VAR_IN:%.+]], [2 x [[S_FLOAT_TY]]]*{{.+}} [[S_ARR_IN:%.+]], [[S_FLOAT_TY]]*{{.+}} [[VAR_IN:%.+]], i{{[0-9]+}}*{{.*}} [[S_VAR_IN:%.+]])
// gbl and bound tid vars, prev lb and ub vars
// CHECK: {{.+}} = alloca i{{[0-9]+}}*,
// CHECK: {{.+}} = alloca i{{[0-9]+}}*,
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: [[VEC_ADDR:%.+]] = alloca [2 x i{{[0-9]+}}]*,
// CHECK: [[T_VAR_ADDR:%.+]] = alloca i{{[0-9]+}}*,
// CHECK: [[S_ARR_ADDR:%.+]] = alloca [2 x [[S_FLOAT_TY]]]*,
// CHECK: [[VAR_ADDR:%.+]] = alloca [[S_FLOAT_TY]]*,
// CHECK: [[SVAR_ADDR:%.+]] = alloca i{{[0-9]+}}*,
// skip loop variables
// CHECK: {{.+}} = alloca i{{[0-9]+}},
// CHECK: {{.+}} = alloca i{{[0-9]+}},
// CHECK: {{.+}} = alloca i{{[0-9]+}},
// CHECK: {{.+}} = alloca i{{[0-9]+}},
// CHECK: [[OMP_IS_LAST:%.+]] = alloca i{{[0-9]+}},
// CHECK: [[T_VAR_PRIV:%.+]] = alloca i{{[0-9]+}},
// CHECK: [[VEC_PRIV:%.+]] = alloca [2 x i{{[0-9]+}}],
// CHECK: [[S_ARR_PRIV:%.+]] = alloca [2 x [[S_FLOAT_TY]]],
// CHECK: [[VAR_PRIV:%.+]] = alloca [[S_FLOAT_TY]],
// CHECK: [[TMP_PRIV:%.+]] = alloca [[S_FLOAT_TY]]*,
// CHECK: [[S_VAR_PRIV:%.+]] = alloca i{{[0-9]+}},
// copy from parameters to local address variables
// CHECK: store [2 x i{{[0-9]+}}]* [[VEC_IN]], [2 x i{{[0-9]+}}]** [[VEC_ADDR]],
// CHECK: store i{{[0-9]+}}* [[T_VAR_IN]], i{{[0-9]+}}** [[T_VAR_ADDR]],
// CHECK: store [2 x [[S_FLOAT_TY]]]* [[S_ARR_IN]], [2 x [[S_FLOAT_TY]]]** [[S_ARR_ADDR]],
// CHECK: store [[S_FLOAT_TY]]* [[VAR_IN]], [[S_FLOAT_TY]]** [[VAR_ADDR]],
// CHECK: store i{{[0-9]+}}* [[S_VAR_IN]], i{{[0-9]+}}** [[SVAR_ADDR]],
// load content of local address variables
// CHECK: [[VEC_ADDR_REF:%.+]] = load [2 x i{{[0-9]+}}]*, [2 x i{{[0-9]+}}]** [[VEC_ADDR]],
// CHECK: [[T_VAR_ADDR_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[T_VAR_ADDR]],
// CHECK: [[S_ARR_ADDR_REF:%.+]] = load [2 x [[S_FLOAT_TY]]]*, [2 x [[S_FLOAT_TY]]]** [[S_ARR_ADDR]],
// CHECK: [[SVAR_ADDR_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[SVAR_ADDR]],
// CHECK: store i{{[0-9]+}} 0, i{{[0-9]+}}* [[OMP_IS_LAST]],
// CHECK: [[VAR_ADDR_REF:%.+]] = load {{.+}}, {{.+}} [[VAR_ADDR]],
// the distribute loop
// CHECK: call void @__kmpc_for_static_init_4(
// assignment: vec[i] = t_var;
// CHECK: [[T_VAR_PRIV_VAL:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[T_VAR_PRIV]],
// CHECK: [[VEC_PTR:%.+]] = getelementptr inbounds [2 x i{{[0-9]+}}], [2 x i{{[0-9]+}}]* [[VEC_PRIV]], i{{[0-9]+}} 0, i{{[0-9]+}} {{.+}}
// CHECK: store i{{[0-9]+}} [[T_VAR_PRIV_VAL]], i{{[0-9]+}}* [[VEC_PTR]],
// assignment: s_arr[i] = var;
// CHECK-DAG: [[S_ARR_PTR:%.+]] = getelementptr inbounds [2 x [[S_FLOAT_TY]]], [2 x [[S_FLOAT_TY]]]* [[S_ARR_PRIV]],
// CHECK-DAG: [[TMP_VAL:%.+]] = load [[S_FLOAT_TY]]*, [[S_FLOAT_TY]]** [[TMP_PRIV]],
// CHECK-DAG: [[S_ARR_PTR_BCAST:%.+]] = bitcast [[S_FLOAT_TY]]* [[S_ARR_PTR]] to i8*
// CHECK-DAG: [[TMP_VAL_BCAST:%.+]] = bitcast [[S_FLOAT_TY]]* [[TMP_VAL]] to i8*
// CHECK: call void @llvm.memcpy.{{.+}}(i8* [[S_ARR_PTR_BCAST]], i8* [[TMP_VAL_BCAST]],
// CHECK: call void @__kmpc_for_static_fini(
// lastprivates
// CHECK: [[OMP_IS_LAST_VAL:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[OMP_IS_LAST]],
// CHECK: [[IS_LAST_IT:%.+]] = icmp ne i{{[0-9]+}} [[OMP_IS_LAST_VAL]], 0
// CHECK: br i1 [[IS_LAST_IT]], label %[[OMP_LASTPRIV_BLOCK:.+]], label %[[OMP_LASTPRIV_DONE:.+]]
// CHECK: [[OMP_LASTPRIV_BLOCK]]:
// CHECK: [[T_VAR_VAL:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[T_VAR_PRIV]],
// CHECK: store i{{[0-9]+}} [[T_VAR_VAL]], i{{[0-9]+}}* [[T_VAR_ADDR_REF]],
// CHECK: [[BCAST_VEC_ADDR_REF:%.+]] = bitcast [2 x i{{[0-9]+}}]* [[VEC_ADDR_REF]] to i8*
// CHECK: [[BCAST_VEC_PRIV:%.+]] = bitcast [2 x i{{[0-9]+}}]* [[VEC_PRIV]] to i8*
// CHECK: call void @llvm.memcpy.{{.+}}(i8* [[BCAST_VEC_ADDR_REF]], i8* [[BCAST_VEC_PRIV]],
// CHECK: [[S_ARR_BEGIN:%.+]] = getelementptr inbounds [2 x [[S_FLOAT_TY]]], [2 x [[S_FLOAT_TY]]]* [[S_ARR_ADDR_REF]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
// CHECK: [[S_ARR_PRIV_BCAST:%.+]] = bitcast [2 x [[S_FLOAT_TY]]]* [[S_ARR_PRIV]] to [[S_FLOAT_TY]]*
// CHECK: [[S_ARR_BEGIN_GEP:%.+]] = getelementptr [[S_FLOAT_TY]], [[S_FLOAT_TY]]* [[S_ARR_BEGIN]], i{{[0-9]+}} 2
// CHECK: [[S_ARR_IS_EMPTY:%.+]] = icmp eq [[S_FLOAT_TY]]* [[S_ARR_BEGIN]], [[S_ARR_BEGIN_GEP]]
// CHECK: br i1 [[S_ARR_IS_EMPTY]], label %[[S_ARR_COPY_DONE:.+]], label %[[S_ARR_COPY_BLOCK:.+]]
// CHECK: [[S_ARR_COPY_BLOCK]]:
// CHECK: [[S_ARR_SRC_EL:%.+]] = phi [[S_FLOAT_TY]]*{{.+}}
// CHECK: [[S_ARR_DST_EL:%.+]] = phi [[S_FLOAT_TY]]*{{.+}}
// CHECK: [[S_ARR_DST_BCAST:%.+]] = bitcast [[S_FLOAT_TY]]* [[S_ARR_DST_EL]] to i8*
// CHECK: [[S_ARR_SRC_BCAST:%.+]] = bitcast [[S_FLOAT_TY]]* [[S_ARR_SRC_EL]] to i8*
// CHECK: call void @llvm.memcpy.{{.+}}(i8* [[S_ARR_DST_BCAST]], i8* [[S_ARR_SRC_BCAST]]{{.+}})
// CHECK: [[S_ARR_DST_NEXT:%.+]] = getelementptr [[S_FLOAT_TY]], [[S_FLOAT_TY]]* [[S_ARR_DST_EL]], i{{[0-9]+}} 1
// CHECK: [[S_ARR_SRC_NEXT:%.+]] = getelementptr{{.+}}
// CHECK: [[CPY_IS_FINISHED:%.+]] = icmp eq [[S_FLOAT_TY]]* [[S_ARR_DST_NEXT]], [[S_ARR_BEGIN_GEP]]
// CHECK: br i1 [[CPY_IS_FINISHED]], label %[[S_ARR_COPY_DONE]], label %[[S_ARR_COPY_BLOCK]]
// CHECK: [[S_ARR_COPY_DONE]]:
// CHECK: [[TMP_VAL1:%.+]] = load [[S_FLOAT_TY]]*, [[S_FLOAT_TY]]** [[TMP_PRIV]],
// CHECK: [[VAR_ADDR_REF_BCAST:%.+]] = bitcast [[S_FLOAT_TY]]* [[VAR_ADDR_REF]] to i8*
// CHECK: [[TMP_VAL1_BCAST:%.+]] = bitcast [[S_FLOAT_TY]]* [[TMP_VAL1]] to i8*
// CHECK: call void @llvm.memcpy.{{.+}}(i8* [[VAR_ADDR_REF_BCAST]], i8* [[TMP_VAL1_BCAST]],{{.+}})
// CHECK: [[SVAR_VAL:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[S_VAR_PRIV]],
// CHECK: store i{{[0-9]+}} [[SVAR_VAL]], i{{[0-9]+}}* [[SVAR_ADDR_REF]],
// CHECK: ret void
// template tmain
// CHECK: define{{.*}} i{{[0-9]+}} [[TMAIN_INT:@.+]]()
// CHECK: [[TEST:%.+]] = alloca [[S_INT_TY]],
// CHECK: call {{.*}} [[S_INT_TY_DEF_CONSTR:@.+]]([[S_INT_TY]]* [[TEST]])
// CHECK: call i{{[0-9]+}} @__tgt_target(
// CHECK: call void [[OFFLOAD_FUN_1:@.+]](i{{[0-9]+}} {{.+}}, [2 x i{{[0-9]+}}]* {{.+}}, [2 x [[S_INT_TY]]]* {{.+}}, [[S_INT_TY]]* {{.+}})
// CHECK: ret
// CHECK: define internal void [[OFFLOAD_FUN_1]](
// CHECK: call void (%{{.+}}*, i{{[0-9]+}}, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)*, ...) @__kmpc_fork_teams(%{{.+}}* @{{.+}}, i{{[0-9]+}} 4,
// CHECK: ret
// CHECK: define internal void [[OMP_OUTLINED_1:@.+]](i{{[0-9]+}}* noalias [[GTID_ADDR1:%.+]], i{{[0-9]+}}* noalias %{{.+}}, [2 x i{{[0-9]+}}]*{{.+}} [[VEC_IN1:%.+]], i{{[0-9]+}}*{{.+}} [[T_VAR_IN1:%.+]], [2 x [[S_INT_TY]]]*{{.+}} [[S_ARR_IN1:%.+]], [[S_INT_TY]]*{{.+}} [[VAR_IN1:%.+]])
// skip alloca of global_tid and bound_tid
// CHECK: {{.+}} = alloca i{{[0-9]+}}*,
// CHECK: {{.+}} = alloca i{{[0-9]+}}*,
// CHECK: [[VEC_ADDR1:%.+]] = alloca [2 x i{{[0-9]+}}]*,
// CHECK: [[T_VAR_ADDR1:%.+]] = alloca i{{[0-9]+}}*,
// CHECK: [[S_ARR_ADDR1:%.+]] = alloca [2 x [[S_INT_TY]]]*,
// CHECK: [[VAR_ADDR1:%.+]] = alloca [[S_INT_TY]]*,
// skip loop variables
// CHECK: {{.+}} = alloca i{{[0-9]+}},
// CHECK: {{.+}} = alloca i{{[0-9]+}},
// CHECK: {{.+}} = alloca i{{[0-9]+}},
// CHECK: {{.+}} = alloca i{{[0-9]+}},
// CHECK: [[OMP_IS_LAST1:%.+]] = alloca i{{[0-9]+}},
// CHECK: [[T_VAR_PRIV1:%.+]] = alloca i{{[0-9]+}},
// CHECK: [[VEC_PRIV1:%.+]] = alloca [2 x i{{[0-9]+}}],
// CHECK: [[S_ARR_PRIV1:%.+]] = alloca [2 x [[S_INT_TY]]],
// CHECK: [[VAR_PRIV1:%.+]] = alloca [[S_INT_TY]],
// CHECK: [[TMP_PRIV1:%.+]] = alloca [[S_INT_TY]]*,
// skip init of bound and global tid
// CHECK: store i{{[0-9]+}}* {{.*}},
// CHECK: store i{{[0-9]+}}* {{.*}},
// copy from parameters to local address variables
// CHECK: store [2 x i{{[0-9]+}}]* [[VEC_IN1]], [2 x i{{[0-9]+}}]** [[VEC_ADDR1]],
// CHECK: store i{{[0-9]+}}* [[T_VAR_IN1]], i{{[0-9]+}}** [[T_VAR_ADDR1]],
// CHECK: store [2 x [[S_INT_TY]]]* [[S_ARR_IN1]], [2 x [[S_INT_TY]]]** [[S_ARR_ADDR1]],
// CHECK: store [[S_INT_TY]]* [[VAR_IN1]], [[S_INT_TY]]** [[VAR_ADDR1]],
// load content of local address variables
// CHECK: [[VEC_ADDR_REF1:%.+]] = load [2 x i{{[0-9]+}}]*, [2 x i{{[0-9]+}}]** [[VEC_ADDR1]],
// CHECK: [[T_VAR_ADDR_REF1:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[T_VAR_ADDR1]],
// CHECK: [[S_ARR_ADDR_REF1:%.+]] = load [2 x [[S_INT_TY]]]*, [2 x [[S_INT_TY]]]** [[S_ARR_ADDR1]],
// CHECK-DAG: store i{{[0-9]+}} 0, i{{[0-9]+}}* [[OMP_IS_LAST1]],
// CHECK: [[VAR_ADDR1_REF:%.+]] = load [[S_INT_TY]]*, [[S_INT_TY]]** [[VAR_ADDR1]],
// CHECK-DAG: store [[S_INT_TY]]* [[VAR_PRIV1]], [[S_INT_TY]]** [[TMP_PRIV1]],
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[TPAR_OUTL:.+]] to
// CHECK: call void @__kmpc_for_static_fini(
// lastprivates
// CHECK: [[OMP_IS_LAST_VAL:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[OMP_IS_LAST1]],
// CHECK: [[IS_LAST_IT:%.+]] = icmp ne i{{[0-9]+}} [[OMP_IS_LAST_VAL]], 0
// CHECK: br i1 [[IS_LAST_IT]], label %[[OMP_LASTPRIV_BLOCK:.+]], label %[[OMP_LASTPRIV_DONE:.+]]
// CHECK: [[OMP_LASTPRIV_BLOCK]]:
// CHECK: [[T_VAR_VAL:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[T_VAR_PRIV1]],
// CHECK: store i{{[0-9]+}} [[T_VAR_VAL]], i{{[0-9]+}}* [[T_VAR_ADDR_REF1]],
// CHECK: [[BCAST_VEC_ADDR_REF:%.+]] = bitcast [2 x i{{[0-9]+}}]* [[VEC_ADDR_REF1]] to i8*
// CHECK: [[BCAST_VEC_PRIV:%.+]] = bitcast [2 x i{{[0-9]+}}]* [[VEC_PRIV1]] to i8*
// CHECK: call void @llvm.memcpy.{{.+}}(i8* [[BCAST_VEC_ADDR_REF]], i8* [[BCAST_VEC_PRIV]],
// CHECK: [[S_ARR_BEGIN:%.+]] = getelementptr inbounds [2 x [[S_INT_TY]]], [2 x [[S_INT_TY]]]* [[S_ARR_ADDR_REF]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
// CHECK: [[S_ARR_PRIV_BCAST:%.+]] = bitcast [2 x [[S_INT_TY]]]* [[S_ARR_PRIV1]] to [[S_INT_TY]]*
// CHECK: [[S_ARR_BEGIN_GEP:%.+]] = getelementptr [[S_INT_TY]], [[S_INT_TY]]* [[S_ARR_BEGIN]], i{{[0-9]+}} 2
// CHECK: [[S_ARR_IS_EMPTY:%.+]] = icmp eq [[S_INT_TY]]* [[S_ARR_BEGIN]], [[S_ARR_BEGIN_GEP]]
// CHECK: br i1 [[S_ARR_IS_EMPTY]], label %[[S_ARR_COPY_DONE:.+]], label %[[S_ARR_COPY_BLOCK:.+]]
// CHECK: [[S_ARR_COPY_BLOCK]]:
// CHECK: [[S_ARR_SRC_EL:%.+]] = phi [[S_INT_TY]]*{{.+}}
// CHECK: [[S_ARR_DST_EL:%.+]] = phi [[S_INT_TY]]*{{.+}}
// CHECK: [[S_ARR_DST_BCAST:%.+]] = bitcast [[S_INT_TY]]* [[S_ARR_DST_EL]] to i8*
// CHECK: [[S_ARR_SRC_BCAST:%.+]] = bitcast [[S_INT_TY]]* [[S_ARR_SRC_EL]] to i8*
// CHECK: call void @llvm.memcpy.{{.+}}(i8* [[S_ARR_DST_BCAST]], i8* [[S_ARR_SRC_BCAST]]{{.+}})
// CHECK: [[S_ARR_DST_NEXT:%.+]] = getelementptr [[S_INT_TY]], [[S_INT_TY]]* [[S_ARR_DST_EL]], i{{[0-9]+}} 1
// CHECK: [[S_ARR_SRC_NEXT:%.+]] = getelementptr{{.+}}
// CHECK: [[CPY_IS_FINISHED:%.+]] = icmp eq [[S_INT_TY]]* [[S_ARR_DST_NEXT]], [[S_ARR_BEGIN_GEP]]
// CHECK: br i1 [[CPY_IS_FINISHED]], label %[[S_ARR_COPY_DONE]], label %[[S_ARR_COPY_BLOCK]]
// CHECK: [[S_ARR_COPY_DONE]]:
// CHECK: [[TMP_VAL1:%.+]] = load [[S_INT_TY]]*, [[S_INT_TY]]** [[TMP_PRIV1]],
// CHECK: [[VAR_ADDR_REF_BCAST:%.+]] = bitcast [[S_INT_TY]]* [[VAR_ADDR1_REF]] to i8*
// CHECK: [[TMP_VAL1_BCAST:%.+]] = bitcast [[S_INT_TY]]* [[TMP_VAL1]] to i8*
// CHECK: call void @llvm.memcpy.{{.+}}(i8* [[VAR_ADDR_REF_BCAST]], i8* [[TMP_VAL1_BCAST]],{{.+}})
// CHECK: ret void
// CHECK: define internal void [[TPAR_OUTL:@.+]](i{{[0-9]+}}* noalias [[GTID_ADDR1:%.+]], i{{[0-9]+}}* noalias %{{.+}}, {{.+}}, {{.+}}, [2 x i{{[0-9]+}}]*{{.+}} [[VEC_IN1:%.+]], i{{[0-9]+}}*{{.+}} [[T_VAR_IN1:%.+]], [2 x [[S_INT_TY]]]*{{.+}} [[S_ARR_IN1:%.+]], [[S_INT_TY]]*{{.+}} [[VAR_IN1:%.+]])
// skip alloca of global_tid and bound_tid, and prev lb and ub vars
// CHECK: {{.+}} = alloca i{{[0-9]+}}*,
// CHECK: {{.+}} = alloca i{{[0-9]+}}*,
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: [[VEC_ADDR1:%.+]] = alloca [2 x i{{[0-9]+}}]*,
// CHECK: [[T_VAR_ADDR1:%.+]] = alloca i{{[0-9]+}}*,
// CHECK: [[S_ARR_ADDR1:%.+]] = alloca [2 x [[S_INT_TY]]]*,
// CHECK: [[VAR_ADDR1:%.+]] = alloca [[S_INT_TY]]*,
// skip loop variables
// CHECK: {{.+}} = alloca i{{[0-9]+}},
// CHECK: {{.+}} = alloca i{{[0-9]+}},
// CHECK: {{.+}} = alloca i{{[0-9]+}},
// CHECK: {{.+}} = alloca i{{[0-9]+}},
// CHECK: [[OMP_IS_LAST1:%.+]] = alloca i{{[0-9]+}},
// CHECK: [[T_VAR_PRIV1:%.+]] = alloca i{{[0-9]+}},
// CHECK: [[VEC_PRIV1:%.+]] = alloca [2 x i{{[0-9]+}}],
// CHECK: [[S_ARR_PRIV1:%.+]] = alloca [2 x [[S_INT_TY]]],
// CHECK: [[VAR_PRIV1:%.+]] = alloca [[S_INT_TY]],
// CHECK: [[TMP_PRIV1:%.+]] = alloca [[S_INT_TY]]*,
// skip init of bound and global tid
// CHECK: store i{{[0-9]+}}* {{.*}},
// CHECK: store i{{[0-9]+}}* {{.*}},
// copy from parameters to local address variables
// CHECK: store [2 x i{{[0-9]+}}]* [[VEC_IN1]], [2 x i{{[0-9]+}}]** [[VEC_ADDR1]],
// CHECK: store i{{[0-9]+}}* [[T_VAR_IN1]], i{{[0-9]+}}** [[T_VAR_ADDR1]],
// CHECK: store [2 x [[S_INT_TY]]]* [[S_ARR_IN1]], [2 x [[S_INT_TY]]]** [[S_ARR_ADDR1]],
// CHECK: store [[S_INT_TY]]* [[VAR_IN1]], [[S_INT_TY]]** [[VAR_ADDR1]],
// load content of local address variables
// CHECK: [[VEC_ADDR_REF1:%.+]] = load [2 x i{{[0-9]+}}]*, [2 x i{{[0-9]+}}]** [[VEC_ADDR1]],
// CHECK: [[T_VAR_ADDR_REF1:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[T_VAR_ADDR1]],
// CHECK: [[S_ARR_ADDR_REF1:%.+]] = load [2 x [[S_INT_TY]]]*, [2 x [[S_INT_TY]]]** [[S_ARR_ADDR1]],
// CHECK-DAG: store i{{[0-9]+}} 0, i{{[0-9]+}}* [[OMP_IS_LAST1]],
// CHECK: [[VAR_ADDR1_REF:%.+]] = load [[S_INT_TY]]*, [[S_INT_TY]]** [[VAR_ADDR1]],
// CHECK-DAG: store [[S_INT_TY]]* [[VAR_PRIV1]], [[S_INT_TY]]** [[TMP_PRIV1]],
// CHECK: call void @__kmpc_for_static_init_4(
// assignment: vec[i] = t_var;
// CHECK: [[IV_VAL1:%.+]] =
// CHECK: [[T_VAR_PRIV_VAL1:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[T_VAR_PRIV1]],
// CHECK: [[VEC_PTR1:%.+]] = getelementptr inbounds [2 x i{{[0-9]+}}], [2 x i{{[0-9]+}}]* [[VEC_PRIV1]], i{{[0-9]+}} 0, i{{[0-9]+}} {{.+}}
// CHECK: store i{{[0-9]+}} [[T_VAR_PRIV_VAL1]], i{{[0-9]+}}* [[VEC_PTR1]],
// assignment: s_arr[i] = var;
// CHECK-DAG: [[S_ARR_PTR1:%.+]] = getelementptr inbounds [2 x [[S_INT_TY]]], [2 x [[S_INT_TY]]]* [[S_ARR_PRIV1]],
// CHECK-DAG: [[TMP_VAL1:%.+]] = load [[S_INT_TY]]*, [[S_INT_TY]]** [[TMP_PRIV1]],
// CHECK-DAG: [[S_ARR_PTR_BCAST1:%.+]] = bitcast [[S_INT_TY]]* [[S_ARR_PTR1]] to i8*
// CHECK-DAG: [[TMP_VAL_BCAST1:%.+]] = bitcast [[S_INT_TY]]* [[TMP_VAL1]] to i8*
// CHECK-DAG: call void @llvm.memcpy.{{.+}}(i8* [[S_ARR_PTR_BCAST1]], i8* [[TMP_VAL_BCAST1]],
// CHECK: call void @__kmpc_for_static_fini(
// lastprivates
// CHECK: [[OMP_IS_LAST_VAL:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[OMP_IS_LAST1]],
// CHECK: [[IS_LAST_IT:%.+]] = icmp ne i{{[0-9]+}} [[OMP_IS_LAST_VAL]], 0
// CHECK: br i1 [[IS_LAST_IT]], label %[[OMP_LASTPRIV_BLOCK:.+]], label %[[OMP_LASTPRIV_DONE:.+]]
// CHECK: [[OMP_LASTPRIV_BLOCK]]:
// CHECK: [[T_VAR_VAL:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[T_VAR_PRIV1]],
// CHECK: store i{{[0-9]+}} [[T_VAR_VAL]], i{{[0-9]+}}* [[T_VAR_ADDR_REF1]],
// CHECK: [[BCAST_VEC_ADDR_REF:%.+]] = bitcast [2 x i{{[0-9]+}}]* [[VEC_ADDR_REF1]] to i8*
// CHECK: [[BCAST_VEC_PRIV:%.+]] = bitcast [2 x i{{[0-9]+}}]* [[VEC_PRIV1]] to i8*
// CHECK: call void @llvm.memcpy.{{.+}}(i8* [[BCAST_VEC_ADDR_REF]], i8* [[BCAST_VEC_PRIV]],
// CHECK: [[S_ARR_BEGIN:%.+]] = getelementptr inbounds [2 x [[S_INT_TY]]], [2 x [[S_INT_TY]]]* [[S_ARR_ADDR_REF]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
// CHECK: [[S_ARR_PRIV_BCAST:%.+]] = bitcast [2 x [[S_INT_TY]]]* [[S_ARR_PRIV1]] to [[S_INT_TY]]*
// CHECK: [[S_ARR_BEGIN_GEP:%.+]] = getelementptr [[S_INT_TY]], [[S_INT_TY]]* [[S_ARR_BEGIN]], i{{[0-9]+}} 2
// CHECK: [[S_ARR_IS_EMPTY:%.+]] = icmp eq [[S_INT_TY]]* [[S_ARR_BEGIN]], [[S_ARR_BEGIN_GEP]]
// CHECK: br i1 [[S_ARR_IS_EMPTY]], label %[[S_ARR_COPY_DONE:.+]], label %[[S_ARR_COPY_BLOCK:.+]]
// CHECK: [[S_ARR_COPY_BLOCK]]:
// CHECK: [[S_ARR_SRC_EL:%.+]] = phi [[S_INT_TY]]*{{.+}}
// CHECK: [[S_ARR_DST_EL:%.+]] = phi [[S_INT_TY]]*{{.+}}
// CHECK: [[S_ARR_DST_BCAST:%.+]] = bitcast [[S_INT_TY]]* [[S_ARR_DST_EL]] to i8*
// CHECK: [[S_ARR_SRC_BCAST:%.+]] = bitcast [[S_INT_TY]]* [[S_ARR_SRC_EL]] to i8*
// CHECK: call void @llvm.memcpy.{{.+}}(i8* [[S_ARR_DST_BCAST]], i8* [[S_ARR_SRC_BCAST]]{{.+}})
// CHECK: [[S_ARR_DST_NEXT:%.+]] = getelementptr [[S_INT_TY]], [[S_INT_TY]]* [[S_ARR_DST_EL]], i{{[0-9]+}} 1
// CHECK: [[S_ARR_SRC_NEXT:%.+]] = getelementptr{{.+}}
// CHECK: [[CPY_IS_FINISHED:%.+]] = icmp eq [[S_INT_TY]]* [[S_ARR_DST_NEXT]], [[S_ARR_BEGIN_GEP]]
// CHECK: br i1 [[CPY_IS_FINISHED]], label %[[S_ARR_COPY_DONE]], label %[[S_ARR_COPY_BLOCK]]
// CHECK: [[S_ARR_COPY_DONE]]:
// CHECK: [[TMP_VAL1:%.+]] = load [[S_INT_TY]]*, [[S_INT_TY]]** [[TMP_PRIV1]],
// CHECK: [[VAR_ADDR_REF_BCAST:%.+]] = bitcast [[S_INT_TY]]* [[VAR_ADDR1_REF]] to i8*
// CHECK: [[TMP_VAL1_BCAST:%.+]] = bitcast [[S_INT_TY]]* [[TMP_VAL1]] to i8*
// CHECK: call void @llvm.memcpy.{{.+}}(i8* [[VAR_ADDR_REF_BCAST]], i8* [[TMP_VAL1_BCAST]],{{.+}})
// CHECK: ret void
#endif

120
clang/test/OpenMP/teams_distribute_parallel_for_num_threads_codegen.cpp Normal file
View File

@ -0,0 +1,120 @@
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple %itanium_abi_triple -emit-llvm %s -fexceptions -fcxx-exceptions -o - | FileCheck %s
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple %itanium_abi_triple -fexceptions -fcxx-exceptions -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple %itanium_abi_triple -fexceptions -fcxx-exceptions -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
typedef __INTPTR_TYPE__ intptr_t;
// CHECK-DAG: [[IDENT_T_TY:%.+]] = type { i32, i32, i32, i32, i8* }
// CHECK-DAG: [[S_TY:%.+]] = type { [[INTPTR_T_TY:i[0-9]+]], [[INTPTR_T_TY]], [[INTPTR_T_TY]] }
// CHECK-DAG: [[STR:@.+]] = private unnamed_addr constant [23 x i8] c";unknown;unknown;0;0;;\00"
// CHECK-DAG: [[DEF_LOC_2:@.+]] = private unnamed_addr constant [[IDENT_T_TY]] { i32 0, i32 2, i32 0, i32 0, i8* getelementptr inbounds ([23 x i8], [23 x i8]* [[STR]], i32 0, i32 0) }
void foo();
struct S {
intptr_t a, b, c;
S(intptr_t a) : a(a) {}
operator char() { return a; }
~S() {}
};
template <typename T, int C>
int tmain() {
#pragma omp target
#pragma omp teams distribute parallel for num_threads(C)
for (int i = 0; i < 100; i++)
foo();
#pragma omp target
#pragma omp teams distribute parallel for num_threads(T(23))
for (int i = 0; i < 100; i++)
foo();
return 0;
}
int main() {
S s(0);
char a = s;
// CHECK: call i{{[0-9]+}} @__tgt_target(
// CHECK: call void [[OFFLOADING_FUN_0:@.+]](
// CHECK: call i{{[0-9]+}} @__tgt_target(
// CHECK: call void [[OFFLOADING_FUN_1:@.+]](
// CHECK: invoke{{.+}} [[TMAIN_5:@.+]]()
// CHECK: invoke{{.+}} [[TMAIN_1:@.+]]()
#pragma omp target
// CHECK: define internal void [[OFFLOADING_FUN_0]](
// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_teams({{.+}}, i32 0, {{.+}}* [[OMP_TEAMS_OUTLINED_0:@.+]] to {{.+}})
#pragma omp teams distribute parallel for num_threads(2)
for (int i = 0; i < 100; i++) {
// CHECK: define{{.+}} void [[OMP_TEAMS_OUTLINED_0]](
// CHECK: call {{.*}}void @__kmpc_push_num_threads([[IDENT_T_TY]]* [[DEF_LOC_2]], i32 {{.+}}, i32 2)
// CHECK: call {{.*}}void {{.*}} @__kmpc_fork_call(
foo();
}
#pragma omp target
// CHECK: define internal void [[OFFLOADING_FUN_1]](
// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_teams({{.+}}, i32 1, {{.+}}* [[OMP_TEAMS_OUTLINED_1:@.+]] to {{.+}})
#pragma omp teams distribute parallel for num_threads(a)
for (int i = 0; i < 100; i++) {
// CHECK: define{{.+}} void [[OMP_TEAMS_OUTLINED_1]](
// CHECK-DAG: [[A_ADDR:%.+]] = alloca i8*,
// CHECK-DAG: [[A_REF:%.+]] = load i8*, i8** [[A_ADDR]],
// CHECK-DAG: [[A_VAL:%.+]] = load i8, i8* [[A_REF]],
// CHECK-DAG: [[A_EXT:%.+]] = sext i8 [[A_VAL]] to {{.+}}
// CHECK: call {{.*}}void @__kmpc_push_num_threads([[IDENT_T_TY]]* [[DEF_LOC_2]], i32 {{.+}}, i32 [[A_EXT]])
// CHECK: call {{.*}}void {{.*}} @__kmpc_fork_call(
foo();
}
return a + tmain<char, 5>() + tmain<S, 1>();
}
// tmain 5
// CHECK-DAG: define {{.*}}i{{[0-9]+}} [[TMAIN_5]]()
// CHECK: call i{{[0-9]+}} @__tgt_target(
// CHECK: call void [[T_OFFLOADING_FUN_0:@.+]](
// CHECK: call i{{[0-9]+}} @__tgt_target(
// CHECK: call void [[T_OFFLOADING_FUN_1:@.+]](
// tmain 1
// CHECK-DAG: define {{.*}}i{{[0-9]+}} [[TMAIN_1]]()
// CHECK: call i{{[0-9]+}} @__tgt_target(
// CHECK: call void [[T_OFFLOADING_FUN_2:@.+]](
// CHECK: call i{{[0-9]+}} @__tgt_target(
// CHECK: call void [[T_OFFLOADING_FUN_3:@.+]](
// CHECK: define internal void [[T_OFFLOADING_FUN_0]](
// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_teams({{.+}}, i32 0, {{.+}}* [[T_OMP_TEAMS_OUTLINED_0:@.+]] to {{.+}})
// CHECK: define{{.+}} void [[T_OMP_TEAMS_OUTLINED_0]](
// CHECK: call {{.*}}void @__kmpc_push_num_threads([[IDENT_T_TY]]* [[DEF_LOC_2]], i32 {{.+}}, i32 5)
// CHECK: call {{.*}}void {{.*}} @__kmpc_fork_call(
// CHECK: define internal void [[T_OFFLOADING_FUN_1]](
// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_teams({{.+}}, i32 0, {{.+}}* [[T_OMP_TEAMS_OUTLINED_1:@.+]] to {{.+}})
// CHECK: define{{.+}} void [[T_OMP_TEAMS_OUTLINED_1]](
// CHECK: call {{.*}}void @__kmpc_push_num_threads([[IDENT_T_TY]]* [[DEF_LOC_2]], i32 {{.+}}, i32 23)
// CHECK: call {{.*}}void {{.*}} @__kmpc_fork_call(
// CHECK: define internal void [[T_OFFLOADING_FUN_2]](
// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_teams({{.+}}, i32 0, {{.+}}* [[T_OMP_TEAMS_OUTLINED_2:@.+]] to {{.+}})
// CHECK: define{{.+}} void [[T_OMP_TEAMS_OUTLINED_2]](
// CHECK: call {{.*}}void @__kmpc_push_num_threads([[IDENT_T_TY]]* [[DEF_LOC_2]], i32 {{.+}}, i32 1)
// CHECK: call {{.*}}void {{.*}} @__kmpc_fork_call(
// CHECK: define internal void [[T_OFFLOADING_FUN_3]](
// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_teams({{.+}}, i32 {{.+}}, {{.+}}* [[T_OMP_TEAMS_OUTLINED_3:@.+]] to {{.+}})
// CHECK: define{{.+}} void [[T_OMP_TEAMS_OUTLINED_3]]({{.+}}, {{.+}}, {{.+}} [[NUM_TH_CPT_IN:%.+]])
// CHECK: [[NUM_TH_CPT:%.+]] = alloca i8*,
// CHECK: store {{.+}} [[NUM_TH_CPT_IN]], {{.+}} [[NUM_TH_CPT]],
// CHECK: [[NUM_TH_REF:%.+]] = load{{.+}}, {{.+}} [[NUM_TH_CPT]],
// CHECK-DAG: [[NUM_TH_VAL:%.+]] = load {{.+}}, {{.+}} [[NUM_TH_REF]],
// CHECK-DAG: [[NUM_TH_SEXT:%.+]] = sext i8 [[NUM_TH_VAL]] to {{.+}}
// CHECK: call {{.*}}void @__kmpc_push_num_threads([[IDENT_T_TY]]* [[DEF_LOC_2]], i32 {{.+}}, i32 [[NUM_TH_SEXT]])
// CHECK: call {{.*}}void {{.*}} @__kmpc_fork_call(
#endif

329
clang/test/OpenMP/teams_distribute_parallel_for_private_codegen.cpp Normal file
View File

@ -0,0 +1,329 @@
// RUN: %clang_cc1 -DCHECK -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
// RUN: %clang_cc1 -DCHECK -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCHECK -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
// RUN: %clang_cc1 -DCHECK -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
// RUN: %clang_cc1 -DCHECK -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCHECK -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
// RUN: %clang_cc1 -DLAMBDA -verify -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix LAMBDA --check-prefix LAMBDA-64
// RUN: %clang_cc1 -DLAMBDA -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DLAMBDA -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix LAMBDA --check-prefix LAMBDA-64
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
struct St {
int a, b;
St() : a(0), b(0) {}
St(const St &st) : a(st.a + st.b), b(0) {}
~St() {}
};
volatile int g = 1212;
volatile int &g1 = g;
template <class T>
struct S {
T f;
S(T a) : f(a + g) {}
S() : f(g) {}
S(const S &s, St t = St()) : f(s.f + t.a) {}
operator T() { return T(); }
~S() {}
};
// CHECK-DAG: [[S_FLOAT_TY:%.+]] = type { float }
// CHECK-DAG: [[S_INT_TY:%.+]] = type { i{{[0-9]+}} }
template <typename T>
T tmain() {
S<T> test;
T t_var = T();
T vec[] = {1, 2};
S<T> s_arr[] = {1, 2};
S<T> &var = test;
#pragma omp target
#pragma omp teams distribute parallel for private(t_var, vec, s_arr, var)
for (int i = 0; i < 2; ++i) {
vec[i] = t_var;
s_arr[i] = var;
}
return T();
}
// CHECK-DAG: [[TEST:@.+]] = global [[S_FLOAT_TY]] zeroinitializer,
S<float> test;
// CHECK-DAG: [[T_VAR:@.+]] = global i{{[0-9]+}} 333,
int t_var = 333;
// CHECK-DAG: [[VEC:@.+]] = global [2 x i{{[0-9]+}}] [i{{[0-9]+}} 1, i{{[0-9]+}} 2],
int vec[] = {1, 2};
// CHECK-DAG: [[S_ARR:@.+]] = global [2 x [[S_FLOAT_TY]]] zeroinitializer,
S<float> s_arr[] = {1, 2};
// CHECK-DAG: [[VAR:@.+]] = global [[S_FLOAT_TY]] zeroinitializer,
S<float> var(3);
// CHECK-DAG: [[SIVAR:@.+]] = internal global i{{[0-9]+}} 0,
int main() {
static int sivar;
#ifdef LAMBDA
// LAMBDA: [[G:@.+]] = global i{{[0-9]+}} 1212,
// LAMBDA-LABEL: @main
// LAMBDA: call void [[OUTER_LAMBDA:@.+]](
[&]() {
// LAMBDA: define{{.*}} internal{{.*}} void [[OUTER_LAMBDA]](
// LAMBDA: call i32 @__tgt_target(i32 -1, i8* @{{[^,]+}}, i32 3, i8** %{{[^,]+}}, i8** %{{[^,]+}}, i{{64|32}}* {{.+}}@{{[^,]+}}, i32 0, i32 0), i32* {{.+}}@{{[^,]+}}, i32 0, i32 0))
// LAMBDA: call void @[[LOFFL1:.+]](
// LAMBDA: ret
#pragma omp target
#pragma omp teams distribute parallel for private(g, g1, sivar)
for (int i = 0; i < 2; ++i) {
// LAMBDA: define{{.*}} internal{{.*}} void @[[LOFFL1]](i{{64|32}} {{%.+}}, i{{64|32}} {{%.+}})
// LAMBDA: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 0, {{.+}} @[[LOUTL1:.+]] to {{.+}})
// LAMBDA: ret void
// LAMBDA: define internal void @[[LOUTL1]]({{.+}})
// Skip global, bound tid and loop vars
// LAMBDA: {{.+}} = alloca i32*,
// LAMBDA: {{.+}} = alloca i32*,
// LAMBDA: alloca i32,
// LAMBDA: alloca i32,
// LAMBDA: alloca i32,
// LAMBDA: alloca i32,
// LAMBDA: alloca i32,
// LAMBDA: [[G_PRIV:%.+]] = alloca i{{[0-9]+}},
// LAMBDA: [[G1_PRIV:%.+]] = alloca i{{[0-9]+}}
// LAMBDA: [[TMP:%.+]] = alloca i{{[0-9]+}}*,
// LAMBDA: [[SIVAR_PRIV:%.+]] = alloca i{{[0-9]+}},
// LAMBDA: store{{.+}} [[G1_PRIV]], {{.+}} [[TMP]],
g = 1;
g1 = 1;
sivar = 2;
// LAMBDA: call void @__kmpc_for_static_init_4(
// LAMBDA: call void {{.+}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[LPAR_OUTL:.+]] to
// LAMBDA: call void @__kmpc_for_static_fini(
// LAMBDA: ret void
// LAMBDA: define internal void @[[LPAR_OUTL]]({{.+}})
// Skip global, bound tid and loop vars
// LAMBDA: {{.+}} = alloca i32*,
// LAMBDA: {{.+}} = alloca i32*,
// LAMBDA: alloca i{{[0-9]+}},
// LAMBDA: alloca i{{[0-9]+}},
// LAMBDA: alloca i32,
// LAMBDA: alloca i32,
// LAMBDA: alloca i32,
// LAMBDA: alloca i32,
// LAMBDA: alloca i32,
// LAMBDA: [[G_PRIV:%.+]] = alloca i{{[0-9]+}},
// LAMBDA: [[G1_PRIV:%.+]] = alloca i{{[0-9]+}}
// LAMBDA: [[TMP:%.+]] = alloca i{{[0-9]+}}*,
// LAMBDA: [[SIVAR_PRIV:%.+]] = alloca i{{[0-9]+}},
// LAMBDA: store{{.+}} [[G1_PRIV]], {{.+}} [[TMP]],
// LAMBDA-DAG: store{{.+}} 1, {{.+}} [[G_PRIV]],
// LAMBDA-DAG: store{{.+}} 2, {{.+}} [[SIVAR_PRIV]],
// LAMBDA-DAG: [[G1_REF:%.+]] = load{{.+}}, {{.+}} [[TMP]],
// LAMBDA-DAG: store{{.+}} 1, {{.+}} [[G1_REF]],
// LAMBDA: call void [[INNER_LAMBDA:@.+]](
// LAMBDA: call void @__kmpc_for_static_fini(
// LAMBDA: ret void
[&]() {
// LAMBDA: define {{.+}} void [[INNER_LAMBDA]](%{{.+}}* [[ARG_PTR:%.+]])
// LAMBDA: store %{{.+}}* [[ARG_PTR]], %{{.+}}** [[ARG_PTR_REF:%.+]],
g = 2;
g1 = 2;
sivar = 4;
// LAMBDA: [[ARG_PTR:%.+]] = load %{{.+}}*, %{{.+}}** [[ARG_PTR_REF]]
// LAMBDA: [[G_PTR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG_PTR]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
// LAMBDA: [[G_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[G_PTR_REF]]
// LAMBDA: store i{{[0-9]+}} 2, i{{[0-9]+}}* [[G_REF]]
// LAMBDA: [[G1_PTR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG_PTR]], i{{[0-9]+}} 0, i{{[0-9]+}} 1
// LAMBDA: [[G1_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[G1_PTR_REF]]
// LAMBDA: store i{{[0-9]+}} 2, i{{[0-9]+}}* [[G1_REF]]
// LAMBDA: [[SIVAR_PTR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG_PTR]], i{{[0-9]+}} 0, i{{[0-9]+}} 2
// LAMBDA: [[SIVAR_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[SIVAR_PTR_REF]]
// LAMBDA: store i{{[0-9]+}} 4, i{{[0-9]+}}* [[SIVAR_REF]]
}();
}
}();
return 0;
#else
#pragma omp target
#pragma omp teams distribute parallel for private(t_var, vec, s_arr, var, sivar)
for (int i = 0; i < 2; ++i) {
vec[i] = t_var;
s_arr[i] = var;
sivar += i;
}
return tmain<int>();
#endif
}
// CHECK: define {{.*}}i{{[0-9]+}} @main()
// CHECK: call i32 @__tgt_target(i32 -1, i8* @{{[^,]+}}, i32 5, i8** %{{[^,]+}}, i8** %{{[^,]+}}, i{{64|32}}* {{.+}}@{{[^,]+}}, i32 0, i32 0), i32* {{.+}}@{{[^,]+}}, i32 0, i32 0))
// CHECK: call void @[[OFFL1:.+]](i{{64|32}} %{{.+}})
// CHECK: {{%.+}} = call{{.*}} i32 @[[TMAIN_INT:.+]]()
// CHECK: ret
// CHECK: define{{.*}} void @[[OFFL1]]({{.+}})
// CHECK: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 0, {{.+}} @[[OUTL1:.+]] to {{.+}})
// CHECK: ret void
// CHECK: define internal void @[[OUTL1]]({{.+}})
// Skip global, bound tid and loop vars
// CHECK: {{.+}} = alloca i32*,
// CHECK: {{.+}} = alloca i32*,
// CHECK: {{.+}} = alloca i32,
// CHECK: {{.+}} = alloca i32,
// CHECK: {{.+}} = alloca i32,
// CHECK: {{.+}} = alloca i32,
// CHECK: {{.+}} = alloca i32,
// CHECK-DAG: [[T_VAR_PRIV:%.+]] = alloca i{{[0-9]+}},
// CHECK-DAG: [[VEC_PRIV:%.+]] = alloca [2 x i{{[0-9]+}}],
// CHECK-DAG: [[S_ARR_PRIV:%.+]] = alloca [2 x [[S_FLOAT_TY]]],
// CHECK-DAG: [[VAR_PRIV:%.+]] = alloca [[S_FLOAT_TY]],
// CHECK-DAG: [[SIVAR_PRIV:%.+]] = alloca i{{[0-9]+}},
// CHECK: alloca i32,
// private(s_arr)
// CHECK-DAG: [[S_ARR_PRIV_BGN:%.+]] = getelementptr{{.*}} [2 x [[S_FLOAT_TY]]], [2 x [[S_FLOAT_TY]]]* [[S_ARR_PRIV]],
// CHECK-DAG: [[S_ARR_PTR_ALLOC:%.+]] = phi{{.+}} [ [[S_ARR_PRIV_BGN]], {{.+}} ], [ [[S_ARR_NEXT:%.+]], {{.+}} ]
// CHECK-DAG: call void @{{.+}}({{.+}} [[S_ARR_PTR_ALLOC]])
// CHECK-DAG: [[S_ARR_NEXT]] = getelementptr {{.+}} [[S_ARR_PTR_ALLOC]],
// private(var)
// CHECK-DAG: call void @{{.+}}({{.+}} [[VAR_PRIV]])
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void {{.+}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTL1:.+]] to
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
// CHECK: define internal void @[[PAR_OUTL1]]({{.+}})
// Skip global, bound tid and loop vars
// CHECK: {{.+}} = alloca i32*,
// CHECK: {{.+}} = alloca i32*,
// CHECK: {{.+}} = alloca i{{[0-9]+}},
// CHECK: {{.+}} = alloca i{{[0-9]+}},
// CHECK: {{.+}} = alloca i32,
// CHECK: {{.+}} = alloca i32,
// CHECK: {{.+}} = alloca i32,
// CHECK: {{.+}} = alloca i32,
// CHECK: {{.+}} = alloca i32,
// CHECK-DAG: [[T_VAR_PRIV:%.+]] = alloca i{{[0-9]+}},
// CHECK-DAG: [[VEC_PRIV:%.+]] = alloca [2 x i{{[0-9]+}}],
// CHECK-DAG: [[S_ARR_PRIV:%.+]] = alloca [2 x [[S_FLOAT_TY]]],
// CHECK-DAG: [[VAR_PRIV:%.+]] = alloca [[S_FLOAT_TY]],
// CHECK-DAG: [[SIVAR_PRIV:%.+]] = alloca i{{[0-9]+}},
// CHECK: alloca i32,
// private(s_arr)
// CHECK-DAG: [[S_ARR_PRIV_BGN:%.+]] = getelementptr{{.*}} [2 x [[S_FLOAT_TY]]], [2 x [[S_FLOAT_TY]]]* [[S_ARR_PRIV]],
// CHECK-DAG: [[S_ARR_PTR_ALLOC:%.+]] = phi{{.+}} [ [[S_ARR_PRIV_BGN]], {{.+}} ], [ [[S_ARR_NEXT:%.+]], {{.+}} ]
// CHECK-DAG: call void @{{.+}}({{.+}} [[S_ARR_PTR_ALLOC]])
// CHECK-DAG: [[S_ARR_NEXT]] = getelementptr {{.+}} [[S_ARR_PTR_ALLOC]],
// private(var)
// CHECK-DAG: call void @{{.+}}({{.+}} [[VAR_PRIV]])
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK-DAG: {{.+}} = {{.+}} [[T_VAR_PRIV]]
// CHECK-DAG: {{.+}} = {{.+}} [[VEC_PRIV]]
// CHECK-DAG: {{.+}} = {{.+}} [[S_ARR_PRIV]]
// CHECK-DAG: {{.+}} = {{.+}} [[VAR_PRIV]]
// CHECK-DAG: {{.+}} = {{.+}} [[SIVAR_PRIV]]
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
// CHECK: define{{.*}} i{{[0-9]+}} @[[TMAIN_INT]]()
// CHECK: call i32 @__tgt_target(i32 -1, i8* @{{[^,]+}}, i32 0,
// CHECK: call void @[[TOFFL1:.+]]()
// CHECK: ret
// CHECK: define {{.*}}void @[[TOFFL1]]()
// CHECK: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 0, {{.+}} @[[TOUTL1:.+]] to {{.+}})
// CHECK: ret void
// CHECK: define internal void @[[TOUTL1]]({{.+}})
// Skip global, bound tid and loop vars
// CHECK: {{.+}} = alloca i32*,
// CHECK: {{.+}} = alloca i32*,
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: [[T_VAR_PRIV:%.+]] = alloca i{{[0-9]+}},
// CHECK: [[VEC_PRIV:%.+]] = alloca [2 x i{{[0-9]+}}],
// CHECK: [[S_ARR_PRIV:%.+]] = alloca [2 x [[S_INT_TY]]],
// CHECK: [[VAR_PRIV:%.+]] = alloca [[S_INT_TY]],
// CHECK: [[TMP:%.+]] = alloca [[S_INT_TY]]*,
// CHECK: alloca i32,
// private(s_arr)
// CHECK-DAG: [[S_ARR_PRIV_BGN:%.+]] = getelementptr{{.*}} [2 x [[S_INT_TY]]], [2 x [[S_INT_TY]]]* [[S_ARR_PRIV]],
// CHECK-DAG: [[S_ARR_PTR_ALLOC:%.+]] = phi{{.+}} [ [[S_ARR_PRIV_BGN]], {{.+}} ], [ [[S_ARR_NEXT:%.+]], {{.+}} ]
// CHECK-DAG: call void @{{.+}}({{.+}} [[S_ARR_PTR_ALLOC]])
// CHECK-DAG: [[S_ARR_NEXT]] = getelementptr {{.+}} [[S_ARR_PTR_ALLOC]],
// CHECK-DAG: [[S_ARR_PRIV_BGN:%.+]] = getelementptr{{.*}} [2 x [[S_INT_TY]]], [2 x [[S_INT_TY]]]* [[S_ARR_PRIV]],
// CHECK-DAG: [[S_ARR_PTR_ALLOC:%.+]] = phi{{.+}} [ [[S_ARR_PRIV_BGN]], {{.+}} ], [ [[S_ARR_NEXT:%.+]], {{.+}} ]
// CHECK-DAG: call void @{{.+}}({{.+}} [[S_ARR_PTR_ALLOC]])
// CHECK-DAG: [[S_ARR_NEXT]] = getelementptr {{.+}} [[S_ARR_PTR_ALLOC]],
// private(var)
// CHECK-DAG: call void @{{.+}}({{.+}} [[VAR_PRIV]])
// CHECK-DAG: store{{.+}} [[VAR_PRIV]], {{.+}} [[TMP]]
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void {{.+}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[TPAR_OUTL1:.+]] to
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
// CHECK: define internal void @[[TPAR_OUTL1]]({{.+}})
// Skip global, bound tid and loop vars
// CHECK: {{.+}} = alloca i32*,
// CHECK: {{.+}} = alloca i32*,
// prev lb and ub
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// iter variables
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: [[T_VAR_PRIV:%.+]] = alloca i{{[0-9]+}},
// CHECK: [[VEC_PRIV:%.+]] = alloca [2 x i{{[0-9]+}}],
// CHECK: [[S_ARR_PRIV:%.+]] = alloca [2 x [[S_INT_TY]]],
// CHECK: [[VAR_PRIV:%.+]] = alloca [[S_INT_TY]],
// CHECK: [[TMP:%.+]] = alloca [[S_INT_TY]]*,
// CHECK: alloca i32,
// private(s_arr)
// CHECK-DAG: [[S_ARR_PRIV_BGN:%.+]] = getelementptr{{.*}} [2 x [[S_INT_TY]]], [2 x [[S_INT_TY]]]* [[S_ARR_PRIV]],
// CHECK-DAG: [[S_ARR_PTR_ALLOC:%.+]] = phi{{.+}} [ [[S_ARR_PRIV_BGN]], {{.+}} ], [ [[S_ARR_NEXT:%.+]], {{.+}} ]
// CHECK-DAG: call void @{{.+}}({{.+}} [[S_ARR_PTR_ALLOC]])
// CHECK-DAG: [[S_ARR_NEXT]] = getelementptr {{.+}} [[S_ARR_PTR_ALLOC]],
// CHECK-DAG: [[S_ARR_PRIV_BGN:%.+]] = getelementptr{{.*}} [2 x [[S_INT_TY]]], [2 x [[S_INT_TY]]]* [[S_ARR_PRIV]],
// CHECK-DAG: [[S_ARR_PTR_ALLOC:%.+]] = phi{{.+}} [ [[S_ARR_PRIV_BGN]], {{.+}} ], [ [[S_ARR_NEXT:%.+]], {{.+}} ]
// CHECK-DAG: call void @{{.+}}({{.+}} [[S_ARR_PTR_ALLOC]])
// CHECK-DAG: [[S_ARR_NEXT]] = getelementptr {{.+}} [[S_ARR_PTR_ALLOC]],
// private(var)
// CHECK-DAG: call void @{{.+}}({{.+}} [[VAR_PRIV]])
// CHECK-DAG: store{{.+}} [[VAR_PRIV]], {{.+}} [[TMP]]
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK-DAG: {{.+}} = {{.+}} [[T_VAR_PRIV]]
// CHECK-DAG: {{.+}} = {{.+}} [[VEC_PRIV]]
// CHECK-DAG: {{.+}} = {{.+}} [[S_ARR_PRIV]]
// CHECK-DAG: {{.+}} = {{.+}} [[TMP]]
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: ret void
#endif

90
clang/test/OpenMP/teams_distribute_parallel_for_proc_bind_codegen.cpp Normal file
View File

@ -0,0 +1,90 @@
// add -fopenmp-targets
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
typedef __INTPTR_TYPE__ intptr_t;
// CHECK-DAG: [[IDENT_T_TY:%.+]] = type { i32, i32, i32, i32, i8* }
// CHECK-DAG: [[STR:@.+]] = private unnamed_addr constant [23 x i8] c";unknown;unknown;0;0;;\00"
// CHECK-DAG: [[DEF_LOC_2:@.+]] = private unnamed_addr constant [[IDENT_T_TY]] { i32 0, i32 2, i32 0, i32 0, i8* getelementptr inbounds ([23 x i8], [23 x i8]* [[STR]], i32 0, i32 0) }
void foo();
struct S {
intptr_t a, b, c;
S(intptr_t a) : a(a) {}
operator char() { return a; }
~S() {}
};
template <typename T>
T tmain() {
#pragma omp target
#pragma omp teams distribute parallel for proc_bind(master)
for(int i = 0; i < 1000; i++) {}
return T();
}
int main() {
// CHECK-LABEL: @main
#pragma omp target
#pragma omp teams distribute parallel for proc_bind(spread)
for(int i = 0; i < 1000; i++) {}
#pragma omp target
#pragma omp teams distribute parallel for proc_bind(close)
for(int i = 0; i < 1000; i++) {}
return tmain<int>();
}
// CHECK: call {{.*}}@__tgt_target({{.+}})
// CHECK: call void [[OFFL1:@.+]]()
// CHECK: call {{.*}}@__tgt_target({{.+}})
// CHECK: call void [[OFFL2:@.+]]()
// CHECK: [[CALL_RET:%.+]] = call{{.+}} i32 [[TMAIN:@.+]]()
// CHECK: ret i32 [[CALL_RET]]
// CHECK: define{{.+}} void [[OFFL1]](
// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_teams({{.+}}, {{.+}}, {{.+}}* [[OMP_OUTLINED_1:@.+]] to {{.+}})
// CHECK: define{{.+}} [[OMP_OUTLINED_1]](i32* {{.+}} [[GTID_IN:%.+]],
// CHECK: [[GTID_ADDR:%.+]] = alloca i32*,
// CHECK: store i32* [[GTID_IN]], i32** [[GTID_ADDR]],
// CHECK: [[GTID_REF:%.+]] = load i32*, i32** [[GTID_ADDR]],
// CHECK: [[GTID_VAL:%.+]] = load i32, i32* [[GTID_REF]],
// CHECK: call {{.*}}void @__kmpc_push_proc_bind([[IDENT_T_TY]]* [[DEF_LOC_2]], i32 [[GTID_VAL]], i32 4)
// CHECK: call {{.*}}void (%ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(
// CHECK: ret void
// CHECK: define{{.+}} [[OFFL2]]()
// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_teams({{.+}}, {{.+}}, {{.+}}* [[OMP_OUTLINED_1:@.+]] to {{.+}})
// CHECK: define{{.+}} [[OMP_OUTLINED_1]](i32* {{.+}} [[GTID_IN:%.+]],
// CHECK: [[GTID_ADDR:%.+]] = alloca i32*,
// CHECK: store i32* [[GTID_IN]], i32** [[GTID_ADDR]],
// CHECK: [[GTID_REF:%.+]] = load i32*, i32** [[GTID_ADDR]],
// CHECK: [[GTID_VAL:%.+]] = load i32, i32* [[GTID_REF]],
// CHECK: call {{.*}}void @__kmpc_push_proc_bind([[IDENT_T_TY]]* [[DEF_LOC_2]], i32 [[GTID_VAL]], i32 3)
// CHECK: call {{.*}}void (%ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(
// CHECK: ret void
// CHECK: define{{.+}} [[TMAIN]]()
// CHECK: call {{.*}}@__tgt_target({{.+}})
// CHECK: call void [[OFFL3:@.+]]()
// CHECK: define{{.+}} [[OFFL3]]()
// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_teams({{.+}}, {{.+}}, {{.+}}* [[OMP_OUTLINED_3:@.+]] to {{.+}})
// CHECK: define{{.+}} [[OMP_OUTLINED_3]](i32* {{.+}} [[GTID_IN:%.+]],
// CHECK: [[GTID_ADDR:%.+]] = alloca i32*,
// CHECK: store i32* [[GTID_IN]], i32** [[GTID_ADDR]],
// CHECK: [[GTID_REF:%.+]] = load i32*, i32** [[GTID_ADDR]],
// CHECK: [[GTID_VAL:%.+]] = load i32, i32* [[GTID_REF]],
// CHECK: call {{.*}}void @__kmpc_push_proc_bind([[IDENT_T_TY]]* [[DEF_LOC_2]], i32 [[GTID_VAL]], i32 2)
// CHECK: call {{.*}}void (%ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(
// CHECK: ret void
#endif

342
clang/test/OpenMP/teams_distribute_parallel_for_reduction_codegen.cpp Normal file
View File

@ -0,0 +1,342 @@
// RUN: %clang_cc1 -DCHECK -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
// RUN: %clang_cc1 -DCHECK -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCHECK -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
// RUN: %clang_cc1 -DCHECK -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
// RUN: %clang_cc1 -DCHECK -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCHECK -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
// RUN: %clang_cc1 -DLAMBDA -verify -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix LAMBDA --check-prefix LAMBDA-64
// RUN: %clang_cc1 -DLAMBDA -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DLAMBDA -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix LAMBDA --check-prefix LAMBDA-64
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
template <typename T>
T tmain() {
T t_var = T();
T vec[] = {1, 2};
#pragma omp target
#pragma omp teams distribute parallel for reduction(+: t_var)
for (int i = 0; i < 2; ++i) {
t_var += (T) i;
}
return T();
}
int main() {
static int sivar;
#ifdef LAMBDA
// LAMBDA: [[RED_VAR:@.+]] = common global [8 x {{.+}}] zeroinitializer
// LAMBDA-LABEL: @main
// LAMBDA: call void [[OUTER_LAMBDA:@.+]](
[&]() {
// LAMBDA: define{{.*}} internal{{.*}} void [[OUTER_LAMBDA]](
// LAMBDA: call i32 @__tgt_target(i32 -1, i8* @{{[^,]+}}, i32 1, i8** %{{[^,]+}}, i8** %{{[^,]+}}, i{{64|32}}* {{.+}}@{{[^,]+}}, i32 0, i32 0), i32* {{.+}}@{{[^,]+}}, i32 0, i32 0))
// LAMBDA: call void @[[LOFFL1:.+]](
// LAMBDA: ret
#pragma omp target
#pragma omp teams distribute parallel for reduction(+: sivar)
for (int i = 0; i < 2; ++i) {
// LAMBDA: define{{.*}} internal{{.*}} void @[[LOFFL1]](i{{64|32}} [[SIVAR_ARG:%.+]])
// LAMBDA: [[SIVAR_ADDR:%.+]] = alloca i{{.+}},
// LAMBDA: store{{.+}} [[SIVAR_ARG]], {{.+}} [[SIVAR_ADDR]],
// LAMBDA: [[SIVAR_CONV:%.+]] = bitcast{{.+}} [[SIVAR_ADDR]] to
// LAMBDA: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 1, {{.+}} @[[LOUTL1:.+]] to {{.+}}, {{.+}} [[SIVAR_CONV]])
// LAMBDA: ret void
// LAMBDA: define internal void @[[LOUTL1]]({{.+}}, {{.+}}, {{.+}} [[SIVAR_ARG:%.+]])
// Skip global and bound tid vars
// LAMBDA: {{.+}} = alloca i32*,
// LAMBDA: {{.+}} = alloca i32*,
// LAMBDA: [[SIVAR_ADDR:%.+]] = alloca i{{.+}}*,
// LAMBDA: [[SIVAR_PRIV:%.+]] = alloca i{{.+}},
// LAMBDA: [[RED_LIST:%.+]] = alloca [1 x {{.+}}],
// LAMBDA: store{{.+}} [[SIVAR_ARG]], {{.+}} [[SIVAR_ADDR]],
// LAMBDA: [[SIVAR_REF:%.+]] = load{{.+}}, {{.+}} [[SIVAR_ADDR]]
// LAMBDA: store{{.+}} 0, {{.+}} [[SIVAR_PRIV]],
// LAMBDA: call void @__kmpc_for_static_init_4(
// LAMBDA: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[LPAR_OUTL:.+]] to
// LAMBDA: call void @__kmpc_for_static_fini(
// LAMBDA: [[RED_LIST_GEP:%.+]] = getelementptr{{.+}} [[RED_LIST]],
// LAMBDA: [[SIVAR_PRIV_CAST:%.+]] = bitcast{{.+}} [[SIVAR_PRIV]] to
// LAMBDA: store{{.+}} [[SIVAR_PRIV_CAST]], {{.+}} [[RED_LIST_GEP]],
// LAMBDA: [[RED_LIST_BCAST:%.+]] = bitcast{{.+}} [[RED_LIST]] to
// LAMBDA: [[K_RED_RET:%.+]] = call{{.+}} @__kmpc_reduce_nowait({{.+}}, {{.+}}, {{.+}}, {{.+}}, {{.+}} [[RED_LIST_BCAST]], {{.+}} [[RED_FUN:@.+]], {{.+}} [[RED_VAR]])
// LAMBDA: switch{{.+}} [[K_RED_RET]], label{{.+}} [
// LAMBDA: {{.+}}, label %[[CASE1:.+]]
// LAMBDA: {{.+}}, label %[[CASE2:.+]]
// LAMBDA: ]
// LAMBDA: [[CASE1]]:
// LAMBDA-DAG: [[SIVAR_VAL:%.+]] = load{{.+}}, {{.+}} [[SIVAR_REF]],
// LAMBDA-DAG: [[SIVAR_PRIV_VAL:%.+]] = load{{.+}}, {{.+}} [[SIVAR_PRIV]],
// LAMBDA-DAG: [[SIVAR_INC:%.+]] = add{{.+}} [[SIVAR_VAL]], [[SIVAR_PRIV_VAL]]
// LAMBDA: store{{.+}} [[SIVAR_INC]], {{.+}} [[SIVAR_REF]],
// LAMBDA: call void @__kmpc_end_reduce_nowait({{.+}}, {{.+}}, {{.+}} [[RED_VAR]])
// LAMBDA: br
// LAMBDA: [[CASE2]]:
// LAMBDA-DAG: [[SIVAR_PRIV_VAL:%.+]] = load{{.+}}, {{.+}} [[SIVAR_PRIV]],
// LAMBDA-DAG: [[ATOMIC_RES:%.+]] = atomicrmw add{{.+}} [[SIVAR_REF]], {{.+}} [[SIVAR_PRIV_VAL]]
// LAMBDA: br
// LAMBDA: define internal void @[[LPAR_OUTL]]({{.+}}, {{.+}}, {{.+}}, {{.+}}, {{.+}} [[SIVAR_ARG:%.+]])
// Skip global and bound tid vars, and prev lb and ub vars
// LAMBDA: {{.+}} = alloca i32*,
// LAMBDA: {{.+}} = alloca i32*,
// LAMBDA: alloca i{{[0-9]+}},
// LAMBDA: alloca i{{[0-9]+}},
// LAMBDA: [[SIVAR_ADDR:%.+]] = alloca i{{.+}}*,
// skip loop vars
// LAMBDA: alloca i32,
// LAMBDA: alloca i32,
// LAMBDA: alloca i32,
// LAMBDA: alloca i32,
// LAMBDA: alloca i32,
// LAMBDA: [[SIVAR_PRIV:%.+]] = alloca i{{.+}},
// LAMBDA: [[RED_LIST:%.+]] = alloca [1 x {{.+}}],
// LAMBDA: store{{.+}} [[SIVAR_ARG]], {{.+}} [[SIVAR_ADDR]],
// LAMBDA: [[SIVAR_REF:%.+]] = load{{.+}}, {{.+}} [[SIVAR_ADDR]]
// LAMBDA: store{{.+}} 0, {{.+}} [[SIVAR_PRIV]],
// LAMBDA: call void @__kmpc_for_static_init_4(
// LAMBDA: store{{.+}}, {{.+}} [[SIVAR_PRIV]],
// LAMBDA: call void [[INNER_LAMBDA:@.+]](
// LAMBDA: call void @__kmpc_for_static_fini(
// LAMBDA: [[RED_LIST_GEP:%.+]] = getelementptr{{.+}} [[RED_LIST]],
// LAMBDA: [[SIVAR_PRIV_CAST:%.+]] = bitcast{{.+}} [[SIVAR_PRIV]] to
// LAMBDA: store{{.+}} [[SIVAR_PRIV_CAST]], {{.+}} [[RED_LIST_GEP]],
// LAMBDA: [[RED_LIST_BCAST:%.+]] = bitcast{{.+}} [[RED_LIST]] to
// LAMBDA: [[K_RED_RET:%.+]] = call{{.+}} @__kmpc_reduce_nowait({{.+}}, {{.+}}, {{.+}}, {{.+}}, {{.+}} [[RED_LIST_BCAST]], {{.+}} [[RED_FUN:@.+]], {{.+}} [[RED_VAR]])
// LAMBDA: switch{{.+}} [[K_RED_RET]], label{{.+}} [
// LAMBDA: {{.+}}, label %[[CASE1:.+]]
// LAMBDA: {{.+}}, label %[[CASE2:.+]]
// LAMBDA: ]
// LAMBDA: [[CASE1]]:
// LAMBDA-DAG: [[SIVAR_VAL:%.+]] = load{{.+}}, {{.+}} [[SIVAR_REF]],
// LAMBDA-DAG: [[SIVAR_PRIV_VAL:%.+]] = load{{.+}}, {{.+}} [[SIVAR_PRIV]],
// LAMBDA-DAG: [[SIVAR_INC:%.+]] = add{{.+}} [[SIVAR_VAL]], [[SIVAR_PRIV_VAL]]
// LAMBDA: store{{.+}} [[SIVAR_INC]], {{.+}} [[SIVAR_REF]],
// LAMBDA: call void @__kmpc_end_reduce_nowait({{.+}}, {{.+}}, {{.+}} [[RED_VAR]])
// LAMBDA: br
// LAMBDA: [[CASE2]]:
// LAMBDA-DAG: [[SIVAR_PRIV_VAL:%.+]] = load{{.+}}, {{.+}} [[SIVAR_PRIV]],
// LAMBDA-DAG: [[ATOMIC_RES:%.+]] = atomicrmw add{{.+}} [[SIVAR_REF]], {{.+}} [[SIVAR_PRIV_VAL]]
// LAMBDA: br
sivar += i;
[&]() {
// LAMBDA: define {{.+}} void [[INNER_LAMBDA]](%{{.+}}* [[ARG_PTR:%.+]])
// LAMBDA: store %{{.+}}* [[ARG_PTR]], %{{.+}}** [[ARG_PTR_REF:%.+]],
sivar += 4;
// LAMBDA: [[ARG_PTR:%.+]] = load %{{.+}}*, %{{.+}}** [[ARG_PTR_REF]]
// LAMBDA: [[SIVAR_PTR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG_PTR]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
// LAMBDA: [[SIVAR_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[SIVAR_PTR_REF]]
// LAMBDA: [[SIVAR_VAL:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[SIVAR_REF]]
// LAMBDA: [[SIVAR_INC:%.+]] = add{{.+}} [[SIVAR_VAL]], 4
// LAMBDA: store i{{[0-9]+}} [[SIVAR_INC]], i{{[0-9]+}}* [[SIVAR_REF]]
}();
}
}();
return 0;
#else
#pragma omp target
#pragma omp teams distribute parallel for reduction(+: sivar)
for (int i = 0; i < 2; ++i) {
sivar += i;
}
return tmain<int>();
#endif
}
// CHECK: [[RED_VAR:@.+]] = common global [8 x {{.+}}] zeroinitializer
// CHECK: define {{.*}}i{{[0-9]+}} @main()
// CHECK: call i32 @__tgt_target(i32 -1, i8* @{{[^,]+}}, i32 1, i8** %{{[^,]+}}, i8** %{{[^,]+}}, i{{64|32}}* {{.+}}@{{[^,]+}}, i32 0, i32 0), i32* {{.+}}@{{[^,]+}}, i32 0, i32 0))
// CHECK: call void @[[OFFL1:.+]](i{{64|32}} %{{.+}})
// CHECK: {{%.+}} = call{{.*}} i32 @[[TMAIN_INT:.+]]()
// CHECK: ret
// CHECK: define{{.*}} void @[[OFFL1]](i{{64|32}} [[SIVAR_ARG:%.+]])
// CHECK: [[SIVAR_ADDR:%.+]] = alloca i{{.+}},
// CHECK: store{{.+}} [[SIVAR_ARG]], {{.+}} [[SIVAR_ADDR]],
// CHECK-64: [[SIVAR_CONV:%.+]] = bitcast{{.+}} [[SIVAR_ADDR]] to
// CHECK-64: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 1, {{.+}} @[[OUTL1:.+]] to {{.+}}, {{.+}} [[SIVAR_CONV]])
// CHECK-32: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 1, {{.+}} @[[OUTL1:.+]] to {{.+}}, {{.+}} [[SIVAR_ADDR]])
// CHECK: ret void
// CHECK: define internal void @[[OUTL1]]({{.+}}, {{.+}}, {{.+}} [[SIVAR_ARG:%.+]])
// Skip global and bound tid vars
// CHECK: {{.+}} = alloca i32*,
// CHECK: {{.+}} = alloca i32*,
// CHECK: [[SIVAR_ADDR:%.+]] = alloca i{{.+}}*,
// CHECK: [[SIVAR_PRIV:%.+]] = alloca i{{.+}},
// CHECK: [[RED_LIST:%.+]] = alloca [1 x {{.+}}],
// CHECK: store{{.+}} [[SIVAR_ARG]], {{.+}} [[SIVAR_ADDR]],
// CHECK: [[SIVAR_REF:%.+]] = load{{.+}}, {{.+}} [[SIVAR_ADDR]]
// CHECK: store{{.+}} 0, {{.+}} [[SIVAR_PRIV]],
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTL:.+]] to
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: [[RED_LIST_GEP:%.+]] = getelementptr{{.+}} [[RED_LIST]],
// CHECK: [[SIVAR_PRIV_CAST:%.+]] = bitcast{{.+}} [[SIVAR_PRIV]] to
// CHECK: store{{.+}} [[SIVAR_PRIV_CAST]], {{.+}} [[RED_LIST_GEP]],
// CHECK: [[RED_LIST_BCAST:%.+]] = bitcast{{.+}} [[RED_LIST]] to
// CHECK: [[K_RED_RET:%.+]] = call{{.+}} @__kmpc_reduce_nowait({{.+}}, {{.+}}, {{.+}}, {{.+}}, {{.+}} [[RED_LIST_BCAST]], {{.+}} [[RED_FUN:@.+]], {{.+}} [[RED_VAR]])
// CHECK: switch{{.+}} [[K_RED_RET]], label{{.+}} [
// CHECK: {{.+}}, label %[[CASE1:.+]]
// CHECK: {{.+}}, label %[[CASE2:.+]]
// CHECK: ]
// CHECK: [[CASE1]]:
// CHECK-DAG: [[SIVAR_VAL:%.+]] = load{{.+}}, {{.+}} [[SIVAR_REF]],
// CHECK-DAG: [[SIVAR_PRIV_VAL:%.+]] = load{{.+}}, {{.+}} [[SIVAR_PRIV]],
// CHECK-DAG: [[SIVAR_INC:%.+]] = add{{.+}} [[SIVAR_VAL]], [[SIVAR_PRIV_VAL]]
// CHECK: store{{.+}} [[SIVAR_INC]], {{.+}} [[SIVAR_REF]],
// CHECK: call void @__kmpc_end_reduce_nowait({{.+}}, {{.+}}, {{.+}} [[RED_VAR]])
// CHECK: br
// CHECK: [[CASE2]]:
// CHECK-DAG: [[SIVAR_PRIV_VAL:%.+]] = load{{.+}}, {{.+}} [[SIVAR_PRIV]],
// CHECK-DAG: [[ATOMIC_RES:%.+]] = atomicrmw add{{.+}} [[SIVAR_REF]], {{.+}} [[SIVAR_PRIV_VAL]]
// CHECK: br
// CHECK: define internal void @[[PAR_OUTL]]({{.+}}, {{.+}}, {{.+}}, {{.+}}, {{.+}} [[SIVAR_ARG:%.+]])
// Skip global and bound tid vars, and prev lb and ub
// CHECK: {{.+}} = alloca i32*,
// CHECK: {{.+}} = alloca i32*,
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: [[SIVAR_ADDR:%.+]] = alloca i{{.+}}*,
// skip loop vars
// CHECK: alloca i32,
// CHECK: alloca i32,
// CHECK: alloca i32,
// CHECK: alloca i32,
// CHECK: alloca i32,
// CHECK: [[SIVAR_PRIV:%.+]] = alloca i{{.+}},
// CHECK: [[RED_LIST:%.+]] = alloca [1 x {{.+}}],
// CHECK: store{{.+}} [[SIVAR_ARG]], {{.+}} [[SIVAR_ADDR]],
// CHECK: [[SIVAR_REF:%.+]] = load{{.+}}, {{.+}} [[SIVAR_ADDR]]
// CHECK: store{{.+}} 0, {{.+}} [[SIVAR_PRIV]],
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: store{{.+}}, {{.+}} [[SIVAR_PRIV]],
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: [[RED_LIST_GEP:%.+]] = getelementptr{{.+}} [[RED_LIST]],
// CHECK: [[SIVAR_PRIV_CAST:%.+]] = bitcast{{.+}} [[SIVAR_PRIV]] to
// CHECK: store{{.+}} [[SIVAR_PRIV_CAST]], {{.+}} [[RED_LIST_GEP]],
// CHECK: [[RED_LIST_BCAST:%.+]] = bitcast{{.+}} [[RED_LIST]] to
// CHECK: [[K_RED_RET:%.+]] = call{{.+}} @__kmpc_reduce_nowait({{.+}}, {{.+}}, {{.+}}, {{.+}}, {{.+}} [[RED_LIST_BCAST]], {{.+}} [[RED_FUN:@.+]], {{.+}} [[RED_VAR]])
// CHECK: switch{{.+}} [[K_RED_RET]], label{{.+}} [
// CHECK: {{.+}}, label %[[CASE1:.+]]
// CHECK: {{.+}}, label %[[CASE2:.+]]
// CHECK: ]
// CHECK: [[CASE1]]:
// CHECK-DAG: [[SIVAR_VAL:%.+]] = load{{.+}}, {{.+}} [[SIVAR_REF]],
// CHECK-DAG: [[SIVAR_PRIV_VAL:%.+]] = load{{.+}}, {{.+}} [[SIVAR_PRIV]],
// CHECK-DAG: [[SIVAR_INC:%.+]] = add{{.+}} [[SIVAR_VAL]], [[SIVAR_PRIV_VAL]]
// CHECK: store{{.+}} [[SIVAR_INC]], {{.+}} [[SIVAR_REF]],
// CHECK: call void @__kmpc_end_reduce_nowait({{.+}}, {{.+}}, {{.+}} [[RED_VAR]])
// CHECK: br
// CHECK: [[CASE2]]:
// CHECK-DAG: [[SIVAR_PRIV_VAL:%.+]] = load{{.+}}, {{.+}} [[SIVAR_PRIV]],
// CHECK-DAG: [[ATOMIC_RES:%.+]] = atomicrmw add{{.+}} [[SIVAR_REF]], {{.+}} [[SIVAR_PRIV_VAL]]
// CHECK: br
// CHECK: define{{.*}} i{{[0-9]+}} @[[TMAIN_INT]]()
// CHECK: call i32 @__tgt_target(i32 -1, i8* @{{[^,]+}}, i32 1,
// CHECK: call void @[[TOFFL1:.+]]({{.+}})
// CHECK: ret
// CHECK: define{{.*}} void @[[TOFFL1]](i{{64|32}} [[TVAR_ARG:%.+]])
// CHECK: [[TVAR_ADDR:%.+]] = alloca i{{.+}},
// CHECK: store{{.+}} [[TVAR_ARG]], {{.+}} [[TVAR_ADDR]],
// CHECK-64: [[TVAR_CONV:%.+]] = bitcast{{.+}} [[TVAR_ADDR]] to
// CHECK-64: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 1, {{.+}} @[[TOUTL1:.+]] to {{.+}}, {{.+}} [[TVAR_CONV]])
// CHECK-32: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 1, {{.+}} @[[TOUTL1:.+]] to {{.+}}, {{.+}} [[TVAR_ADDR]])
// CHECK: ret void
// CHECK: define internal void @[[TOUTL1]]({{.+}}, {{.+}}, {{.+}} [[TVAR_ARG:%.+]])
// Skip global and bound tid vars
// CHECK: {{.+}} = alloca i32*,
// CHECK: {{.+}} = alloca i32*,
// CHECK: [[TVAR_ADDR:%.+]] = alloca i{{.+}}*,
// CHECK: [[TVAR_PRIV:%.+]] = alloca i{{.+}},
// CHECK: [[RED_LIST:%.+]] = alloca [1 x {{.+}}],
// CHECK: store{{.+}} [[TVAR_ARG]], {{.+}} [[TVAR_ADDR]],
// CHECK: [[TVAR_REF:%.+]] = load{{.+}}, {{.+}} [[TVAR_ADDR]]
// CHECK: store{{.+}} 0, {{.+}} [[TVAR_PRIV]],
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[TPAR_OUTL:.+]] to
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: [[RED_LIST_GEP:%.+]] = getelementptr{{.+}} [[RED_LIST]],
// CHECK: [[TVAR_PRIV_CAST:%.+]] = bitcast{{.+}} [[TVAR_PRIV]] to
// CHECK: store{{.+}} [[TVAR_PRIV_CAST]], {{.+}} [[RED_LIST_GEP]],
// CHECK: [[RED_LIST_BCAST:%.+]] = bitcast{{.+}} [[RED_LIST]] to
// CHECK: [[K_RED_RET:%.+]] = call{{.+}} @__kmpc_reduce_nowait({{.+}}, {{.+}}, {{.+}}, {{.+}}, {{.+}} [[RED_LIST_BCAST]], {{.+}} [[RED_FUN:@.+]], {{.+}} [[RED_VAR]])
// CHECK: switch{{.+}} [[K_RED_RET]], label{{.+}} [
// CHECK: {{.+}}, label %[[CASE1:.+]]
// CHECK: {{.+}}, label %[[CASE2:.+]]
// CHECK: ]
// CHECK: [[CASE1]]:
// CHECK-DAG: [[TVAR_VAL:%.+]] = load{{.+}}, {{.+}} [[TVAR_REF]],
// CHECK-DAG: [[TVAR_PRIV_VAL:%.+]] = load{{.+}}, {{.+}} [[TVAR_PRIV]],
// CHECK-DAG: [[TVAR_INC:%.+]] = add{{.+}} [[TVAR_VAL]], [[TVAR_PRIV_VAL]]
// CHECK: store{{.+}} [[TVAR_INC]], {{.+}} [[TVAR_REF]],
// CHECK: call void @__kmpc_end_reduce_nowait({{.+}}, {{.+}}, {{.+}} [[RED_VAR]])
// CHECK: br
// CHECK: [[CASE2]]:
// CHECK-DAG: [[TVAR_PRIV_VAL:%.+]] = load{{.+}}, {{.+}} [[TVAR_PRIV]],
// CHECK-DAG: [[ATOMIC_RES:%.+]] = atomicrmw add{{.+}} [[TVAR_REF]], {{.+}} [[TVAR_PRIV_VAL]]
// CHECK: br
// CHECK: define internal void @[[TPAR_OUTL]]({{.+}}, {{.+}}, {{.+}}, {{.+}}, {{.+}} [[TVAR_ARG:%.+]])
// Skip global and bound tid vars, and prev lb and ub vars
// CHECK: {{.+}} = alloca i32*,
// CHECK: {{.+}} = alloca i32*,
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: [[TVAR_ADDR:%.+]] = alloca i{{.+}}*,
// skip loop vars
// CHECK: alloca i32,
// CHECK: alloca i32,
// CHECK: alloca i32,
// CHECK: alloca i32,
// CHECK: alloca i32,
// CHECK: [[TVAR_PRIV:%.+]] = alloca i{{.+}},
// CHECK: [[RED_LIST:%.+]] = alloca [1 x {{.+}}],
// CHECK: store{{.+}} [[TVAR_ARG]], {{.+}} [[TVAR_ADDR]],
// CHECK: [[TVAR_REF:%.+]] = load{{.+}}, {{.+}} [[TVAR_ADDR]]
// CHECK: store{{.+}} 0, {{.+}} [[TVAR_PRIV]],
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: store{{.+}}, {{.+}} [[TVAR_PRIV]],
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: [[RED_LIST_GEP:%.+]] = getelementptr{{.+}} [[RED_LIST]],
// CHECK: [[TVAR_PRIV_CAST:%.+]] = bitcast{{.+}} [[TVAR_PRIV]] to
// CHECK: store{{.+}} [[TVAR_PRIV_CAST]], {{.+}} [[RED_LIST_GEP]],
// CHECK: [[RED_LIST_BCAST:%.+]] = bitcast{{.+}} [[RED_LIST]] to
// CHECK: [[K_RED_RET:%.+]] = call{{.+}} @__kmpc_reduce_nowait({{.+}}, {{.+}}, {{.+}}, {{.+}}, {{.+}} [[RED_LIST_BCAST]], {{.+}} [[RED_FUN:@.+]], {{.+}} [[RED_VAR]])
// CHECK: switch{{.+}} [[K_RED_RET]], label{{.+}} [
// CHECK: {{.+}}, label %[[CASE1:.+]]
// CHECK: {{.+}}, label %[[CASE2:.+]]
// CHECK: ]
// CHECK: [[CASE1]]:
// CHECK-DAG: [[TVAR_VAL:%.+]] = load{{.+}}, {{.+}} [[TVAR_REF]],
// CHECK-DAG: [[TVAR_PRIV_VAL:%.+]] = load{{.+}}, {{.+}} [[TVAR_PRIV]],
// CHECK-DAG: [[TVAR_INC:%.+]] = add{{.+}} [[TVAR_VAL]], [[TVAR_PRIV_VAL]]
// CHECK: store{{.+}} [[TVAR_INC]], {{.+}} [[TVAR_REF]],
// CHECK: call void @__kmpc_end_reduce_nowait({{.+}}, {{.+}}, {{.+}} [[RED_VAR]])
// CHECK: br
// CHECK: [[CASE2]]:
// CHECK-DAG: [[TVAR_PRIV_VAL:%.+]] = load{{.+}}, {{.+}} [[TVAR_PRIV]],
// CHECK-DAG: [[ATOMIC_RES:%.+]] = atomicrmw add{{.+}} [[TVAR_REF]], {{.+}} [[TVAR_PRIV_VAL]]
// CHECK: br
#endif

398
clang/test/OpenMP/teams_distribute_parallel_for_schedule_codegen.cpp Normal file
View File

@ -0,0 +1,398 @@
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
// Test host codegen.
// RUN: %clang_cc1 -DCK1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CK1 --check-prefix CK1-64
// RUN: %clang_cc1 -DCK1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCK1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CK1 --check-prefix CK1-64
// RUN: %clang_cc1 -DCK1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CK1 --check-prefix CK1-32
// RUN: %clang_cc1 -DCK1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCK1 -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CK1 --check-prefix CK1-32
#ifdef CK1
template <typename T, int X, long long Y>
struct SS{
T a[X];
float b;
// CK1: define {{.*}}i32 @{{.+}}foo{{.+}}(
int foo(void) {
// CK1: call i32 @__tgt_target(
// CK1: call void @[[OFFL1:.+]](
#pragma omp target
#pragma omp teams distribute parallel for
for(int i = 0; i < X; i++) {
a[i] = (T)0;
}
// CK1: call i32 @__tgt_target(
// CK1: call void @[[OFFL2:.+]](
#pragma omp target
#pragma omp teams distribute parallel for schedule(static)
for(int i = 0; i < X; i++) {
a[i] = (T)0;
}
// CK1: call i32 @__tgt_target(
// CK1: call void @[[OFFL3:.+]](
#pragma omp target
#pragma omp teams distribute parallel for schedule(static, X/2)
for(int i = 0; i < X; i++) {
a[i] = (T)0;
}
// CK1: call i32 @__tgt_target(
// CK1: call void @[[OFFL4:.+]](
#pragma omp target
#pragma omp teams distribute parallel for schedule(dynamic)
for(int i = 0; i < X; i++) {
a[i] = (T)0;
}
// CK1: call i32 @__tgt_target(
// CK1: call void @[[OFFL5:.+]](
#pragma omp target
#pragma omp teams distribute parallel for schedule(dynamic, X/2)
for(int i = 0; i < X; i++) {
a[i] = (T)0;
}
// CK1: define internal void @[[OFFL1]](
// CK1: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 1, {{.+}} @[[OUTL1:.+]] to {{.+}},
// CK1: ret void
// CK1: define internal void @[[OUTL1]]({{.+}})
// CK1: call void @__kmpc_for_static_init_4(
// CK1: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTL1:.+]] to
// CK1: call void @__kmpc_for_static_fini(
// CK1: ret void
// CK1: define internal void @[[PAR_OUTL1]]({{.+}})
// CK1: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, i32 34,
// CK1: call void @__kmpc_for_static_fini(
// CK1: ret void
// CK1: define internal void @[[OFFL2]](
// CK1: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 1, {{.+}} @[[OUTL2:.+]] to {{.+}},
// CK1: ret void
// CK1: define internal void @[[OUTL2]]({{.+}})
// CK1: call void @__kmpc_for_static_init_4(
// CK1: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTL2:.+]] to
// CK1: call void @__kmpc_for_static_fini(
// CK1: ret void
// CK1: define internal void @[[PAR_OUTL2]]({{.+}})
// CK1: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, i32 34,
// CK1: call void @__kmpc_for_static_fini(
// CK1: ret void
// CK1: define internal void @[[OFFL3]](
// CK1: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 1, {{.+}} @[[OUTL3:.+]] to {{.+}},
// CK1: ret void
// CK1: define internal void @[[OUTL3]]({{.+}})
// CK1: call void @__kmpc_for_static_init_4(
// CK1: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTL3:.+]] to
// CK1: call void @__kmpc_for_static_fini(
// CK1: ret void
// CK1: define internal void @[[PAR_OUTL3]]({{.+}})
// CK1: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, i32 33,
// CK1: call void @__kmpc_for_static_fini(
// CK1: ret void
// CK1: define internal void @[[OFFL4]](
// CK1: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 1, {{.+}} @[[OUTL4:.+]] to {{.+}},
// CK1: ret void
// CK1: define internal void @[[OUTL4]]({{.+}})
// CK1: call void @__kmpc_for_static_init_4(
// CK1: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTL4:.+]] to
// CK1: call void @__kmpc_for_static_fini(
// CK1: ret void
// CK1: define internal void @[[PAR_OUTL4]]({{.+}})
// CK1: call void @__kmpc_dispatch_init_4({{.+}}, {{.+}}, i32 35,
// CK1: call {{.+}} @__kmpc_dispatch_next_4(
// CK1: ret void
// CK1: define internal void @[[OFFL5]](
// CK1: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 1, {{.+}} @[[OUTL5:.+]] to {{.+}},
// CK1: ret void
// CK1: define internal void @[[OUTL5]]({{.+}})
// CK1: call void @__kmpc_for_static_init_4(
// CK1: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTL5:.+]] to
// CK1: call void @__kmpc_for_static_fini(
// CK1: ret void
// CK1: define internal void @[[PAR_OUTL5]]({{.+}})
// CK1: call void @__kmpc_dispatch_init_4({{.+}}, {{.+}}, i32 35,
// CK1: call {{.+}} @__kmpc_dispatch_next_4(
// CK1: ret void
return a[0];
}
};
int teams_template_struct(void) {
SS<int, 123, 456> V;
return V.foo();
}
#endif // CK1
// Test host codegen.
// RUN: %clang_cc1 -DCK2 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CK2 --check-prefix CK2-64
// RUN: %clang_cc1 -DCK2 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCK2 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CK2 --check-prefix CK2-64
// RUN: %clang_cc1 -DCK2 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CK2 --check-prefix CK2-32
// RUN: %clang_cc1 -DCK2 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -DCK2 -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CK2 --check-prefix CK2-32
#ifdef CK2
template <typename T, int n>
int tmain(T argc) {
T a[n];
int m = 10;
#pragma omp target
#pragma omp teams distribute parallel for
for(int i = 0; i < n; i++) {
a[i] = (T)0;
}
#pragma omp target
#pragma omp teams distribute parallel for schedule(static)
for(int i = 0; i < n; i++) {
a[i] = (T)0;
}
#pragma omp target
#pragma omp teams distribute parallel for schedule(static, m)
for(int i = 0; i < n; i++) {
a[i] = (T)0;
}
#pragma omp target
#pragma omp teams distribute parallel for schedule(dynamic)
for(int i = 0; i < n; i++) {
a[i] = (T)0;
}
#pragma omp target
#pragma omp teams distribute parallel for schedule(dynamic, m)
for(int i = 0; i < n; i++) {
a[i] = (T)0;
}
return 0;
}
int main (int argc, char **argv) {
int n = 100;
int a[n];
int m = 10;
#pragma omp target
#pragma omp teams distribute parallel for
for(int i = 0; i < n; i++) {
a[i] = 0;
}
#pragma omp target
#pragma omp teams distribute parallel for dist_schedule(static)
for(int i = 0; i < n; i++) {
a[i] = 0;
}
#pragma omp target
#pragma omp teams distribute parallel for dist_schedule(static, m)
for(int i = 0; i < n; i++) {
a[i] = 0;
}
#pragma omp target
#pragma omp teams distribute parallel for schedule(dynamic)
for(int i = 0; i < n; i++) {
a[i] = 0;
}
#pragma omp target
#pragma omp teams distribute parallel for schedule(dynamic, m)
for(int i = 0; i < n; i++) {
a[i] = 0;
}
return tmain<int, 10>(argc);
}
// CK2: define {{.*}}i32 @{{[^,]+}}(i{{.+}}{{.+}} %[[ARGC:.+]], {{.+}})
// CK2: call i32 @__tgt_target(
// CK2: call void @[[OFFL1:.+]]({{.+}})
// CK2: call i32 @__tgt_target(
// CK2: call void @[[OFFL2:.+]]({{.+}})
// CK2: call i32 @__tgt_target(
// CK2: call void @[[OFFL3:.+]]({{.+}})
// CK2: call i32 @__tgt_target(
// CK2: call void @[[OFFL4:.+]]({{.+}})
// CK2: call i32 @__tgt_target(
// CK2: call void @[[OFFL5:.+]]({{.+}})
// CK2: {{%.+}} = call{{.*}} i32 @[[TMAIN:.+]]({{.+}})
// CK2: ret
// CK2: define {{.*}}void @[[OFFL1]]({{.+}})
// CK2: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 3, {{.+}} @[[OUTL1:.+]] to {{.+}},
// CK2: ret void
// CK2: define internal void @[[OUTL1]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4(
// CK2: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTL1:.+]] to
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define internal void @[[PAR_OUTL1]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, i32 34,
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define {{.*}}void @[[OFFL2]]({{.+}})
// CK2: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 3, {{.+}} @[[OUTL2:.+]] to {{.+}},
// CK2: ret void
// CK2: define internal void @[[OUTL2]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4(
// CK2: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTL2:.+]] to
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define internal void @[[PAR_OUTL2]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, i32 34,
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define {{.*}}void @[[OFFL3]]({{.+}})
// CK2: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 4, {{.+}} @[[OUTL3:.+]] to {{.+}},
// CK2: ret void
// CK2: define internal void @[[OUTL3]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4(
// CK2: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTL3:.+]] to
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define internal void @[[PAR_OUTL3]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, i32 34
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define {{.*}}void @[[OFFL4]]({{.+}})
// CK2: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 {{.+}}, {{.+}} @[[OUTL4:.+]] to {{.+}},
// CK2: ret void
// CK2: define internal void @[[OUTL4]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4(
// CK2: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTL4:.+]] to
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define internal void @[[PAR_OUTL4]]({{.+}})
// CK2: call void @__kmpc_dispatch_init_4({{.+}}, {{.+}}, i32 35,
// CK2: call {{.+}} @__kmpc_dispatch_next_4(
// CK2: ret void
// CK2: define {{.*}}void @[[OFFL5]]({{.+}})
// CK2: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 {{.+}}, {{.+}} @[[OUTL5:.+]] to {{.+}},
// CK2: ret void
// CK2: define internal void @[[OUTL5]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4(
// CK2: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTL5:.+]] to
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define internal void @[[PAR_OUTL5]]({{.+}})
// CK2: call void @__kmpc_dispatch_init_4({{.+}}, {{.+}}, i32 35,
// CK2: call {{.+}} @__kmpc_dispatch_next_4(
// CK2: ret void
// CK2: define {{.*}}i32 @[[TMAIN]]({{.+}})
// CK2: call i32 @__tgt_target(
// CK2: call void @[[OFFLT1:.+]]({{.+}})
// CK2: call i32 @__tgt_target(
// CK2: call void @[[OFFLT2:.+]]({{.+}})
// CK2: call i32 @__tgt_target(
// CK2: call void @[[OFFLT3:.+]]({{.+}})
// CK2: call i32 @__tgt_target(
// CK2: call void @[[OFFLT4:.+]]({{.+}})
// CK2: call i32 @__tgt_target(
// CK2: call void @[[OFFLT5:.+]]({{.+}})
// CK2: ret
// CK2-NEXT: }
// CK2: define {{.*}}void @[[OFFLT1]]({{.+}})
// CK2: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 1, {{.+}} @[[OUTLT1:.+]] to {{.+}},
// CK2: ret void
// CK2: define internal void @[[OUTLT1]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4(
// CK2: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTLT1:.+]] to
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define internal void @[[PAR_OUTLT1]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, i32 34,
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define {{.*}}void @[[OFFLT2]]({{.+}})
// CK2: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 1, {{.+}} @[[OUTLT2:.+]] to {{.+}},
// CK2: ret void
// CK2: define internal void @[[OUTLT2]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4(
// CK2: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTLT2:.+]] to
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define internal void @[[PAR_OUTLT2]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, i32 34,
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define {{.*}}void @[[OFFLT3]]({{.+}})
// CK2: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 {{.+}}, {{.+}} @[[OUTLT3:.+]] to {{.+}},
// CK2: ret void
// CK2: define internal void @[[OUTLT3]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4(
// CK2: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTLT3:.+]] to
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define internal void @[[PAR_OUTLT3]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, i32 33,
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define {{.*}}void @[[OFFLT4]]({{.+}})
// CK2: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 {{.+}}, {{.+}} @[[OUTLT4:.+]] to {{.+}},
// CK2: ret void
// CK2: define internal void @[[OUTLT4]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4(
// CK2: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTLT4:.+]] to
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define internal void @[[PAR_OUTLT4]]({{.+}})
// CK2: call void @__kmpc_dispatch_init_4({{.+}}, {{.+}}, i32 35,
// CK2: call {{.+}} @__kmpc_dispatch_next_4(
// CK2: ret void
// CK2: define {{.*}}void @[[OFFLT5]]({{.+}})
// CK2: call void {{.+}} @__kmpc_fork_teams({{.+}}, i32 {{.+}}, {{.+}} @[[OUTLT5:.+]] to {{.+}},
// CK2: ret void
// CK2: define internal void @[[OUTLT5]]({{.+}})
// CK2: call void @__kmpc_for_static_init_4(
// CK2: call void {{.*}} @__kmpc_fork_call({{.+}}, {{.+}}, {{.+}} @[[PAR_OUTLT5:.+]] to
// CK2: call void @__kmpc_for_static_fini(
// CK2: ret void
// CK2: define internal void @[[PAR_OUTLT5]]({{.+}})
// CK2: call void @__kmpc_dispatch_init_4({{.+}}, {{.+}}, i32 35,
// CK2: call {{.+}} @__kmpc_dispatch_next_4(
// CK2: ret void
#endif // CK2
#endif // #ifndef HEADER