From 411e81a4e391d9e8195e4b2a0a62bc60582e298a Mon Sep 17 00:00:00 2001 From: Alexey Bataev Date: Mon, 16 Dec 2019 11:16:46 -0500 Subject: [PATCH] [OPENMP50]Add if clause in target teams idistribute simd directive. According to OpenMP 5.0, if clause can be used in for simd directive. If condition in the if clause if false, the non-vectorized version of the loop must be executed. --- clang/lib/Sema/SemaOpenMP.cpp | 4 +- .../target_teams_distribute_simd_ast_print.cpp | 25 +- .../target_teams_distribute_simd_codegen.cpp | 275 +++++++++++++-------- .../target_teams_distribute_simd_if_messages.cpp | 14 +- 4 files changed, 204 insertions(+), 114 deletions(-) diff --git a/clang/lib/Sema/SemaOpenMP.cpp b/clang/lib/Sema/SemaOpenMP.cpp index 9033997..afe0f1a 100644 --- a/clang/lib/Sema/SemaOpenMP.cpp +++ b/clang/lib/Sema/SemaOpenMP.cpp @@ -4785,6 +4785,8 @@ StmtResult Sema::ActOnOpenMPExecutableDirective( Res = ActOnOpenMPTargetTeamsDistributeSimdDirective( ClausesWithImplicit, AStmt, StartLoc, EndLoc, VarsWithInheritedDSA); AllowedNameModifiers.push_back(OMPD_target); + if (LangOpts.OpenMP >= 50) + AllowedNameModifiers.push_back(OMPD_simd); break; case OMPD_declare_target: case OMPD_end_declare_target: @@ -10832,6 +10834,7 @@ static OpenMPDirectiveKind getOpenMPCaptureRegionForClause( CaptureRegion = OMPD_target; break; case OMPD_teams_distribute_simd: + case OMPD_target_teams_distribute_simd: if (OpenMPVersion >= 50 && (NameModifier == OMPD_unknown || NameModifier == OMPD_simd)) CaptureRegion = OMPD_teams; @@ -10844,7 +10847,6 @@ static OpenMPDirectiveKind getOpenMPCaptureRegionForClause( case OMPD_target: case OMPD_target_teams: case OMPD_target_teams_distribute: - case OMPD_target_teams_distribute_simd: case OMPD_distribute_parallel_for: case OMPD_task: case OMPD_taskloop: diff --git a/clang/test/OpenMP/target_teams_distribute_simd_ast_print.cpp b/clang/test/OpenMP/target_teams_distribute_simd_ast_print.cpp index ff47847..94a2f66 100644 --- a/clang/test/OpenMP/target_teams_distribute_simd_ast_print.cpp +++ b/clang/test/OpenMP/target_teams_distribute_simd_ast_print.cpp @@ -1,10 +1,16 @@ -// RUN: %clang_cc1 -verify -fopenmp -ast-print %s -Wno-openmp-mapping | FileCheck %s -// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -emit-pch -o %t %s -Wno-openmp-mapping -// RUN: %clang_cc1 -fopenmp -std=c++11 -include-pch %t -fsyntax-only -verify %s -ast-print -Wno-openmp-mapping | FileCheck %s +// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -ast-print %s -Wno-openmp-mapping | FileCheck %s --check-prefix=CHECK --check-prefix=OMP45 +// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -std=c++11 -emit-pch -o %t %s -Wno-openmp-mapping +// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -std=c++11 -include-pch %t -fsyntax-only -verify %s -ast-print -Wno-openmp-mapping | FileCheck %s --check-prefix=CHECK --check-prefix=OMP45 +// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=50 -DOMP5 -ast-print %s -Wno-openmp-mapping | FileCheck %s --check-prefix=CHECK --check-prefix=OMP50 +// RUN: %clang_cc1 -fopenmp -fopenmp-version=50 -DOMP5 -x c++ -std=c++11 -emit-pch -o %t %s -Wno-openmp-mapping +// RUN: %clang_cc1 -fopenmp -fopenmp-version=50 -DOMP5 -std=c++11 -include-pch %t -fsyntax-only -verify %s -ast-print -Wno-openmp-mapping | FileCheck %s --check-prefix=CHECK --check-prefix=OMP50 -// RUN: %clang_cc1 -verify -fopenmp-simd -ast-print %s -Wno-openmp-mapping | FileCheck %s -// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -emit-pch -o %t %s -Wno-openmp-mapping -// RUN: %clang_cc1 -fopenmp-simd -std=c++11 -include-pch %t -fsyntax-only -verify %s -ast-print -Wno-openmp-mapping | FileCheck %s +// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=45 -ast-print %s -Wno-openmp-mapping | FileCheck %s --check-prefix=CHECK --check-prefix=OMP45 +// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -std=c++11 -emit-pch -o %t %s -Wno-openmp-mapping +// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -std=c++11 -include-pch %t -fsyntax-only -verify %s -ast-print -Wno-openmp-mapping | FileCheck %s --check-prefix=CHECK --check-prefix=OMP45 +// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=50 -DOMP5 -ast-print %s -Wno-openmp-mapping | FileCheck %s --check-prefix=CHECK --check-prefix=OMP50 +// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=50 -DOMP5 -x c++ -std=c++11 -emit-pch -o %t %s -Wno-openmp-mapping +// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=50 -DOMP5 -std=c++11 -include-pch %t -fsyntax-only -verify %s -ast-print -Wno-openmp-mapping | FileCheck %s --check-prefix=CHECK --check-prefix=OMP50 // expected-no-diagnostics #ifndef HEADER @@ -191,10 +197,15 @@ int main (int argc, char **argv) { // CHECK: #pragma omp target teams distribute simd simdlen(clen - 1) // CHECK-NEXT: for (int k = 0; k < 10; ++k) // CHECK-NEXT: e += d + argc; +#ifdef OMP5 +#pragma omp target teams distribute simd safelen(clen-1) aligned(arr:N+6) if(simd:argc) +#else #pragma omp target teams distribute simd safelen(clen-1) aligned(arr:N+6) +#endif // OMP5 for (int k = 0; k < 10; ++k) e += d + argc + arr[k]; -// CHECK: #pragma omp target teams distribute simd safelen(clen - 1) aligned(arr: N + 6) +// OMP45: #pragma omp target teams distribute simd safelen(clen - 1) aligned(arr: N + 6) +// OMP50: #pragma omp target teams distribute simd safelen(clen - 1) aligned(arr: N + 6) if(simd: argc) // CHECK-NEXT: for (int k = 0; k < 10; ++k) // CHECK-NEXT: e += d + argc + arr[k]; return (0); diff --git a/clang/test/OpenMP/target_teams_distribute_simd_codegen.cpp b/clang/test/OpenMP/target_teams_distribute_simd_codegen.cpp index b170a69..14c3cd6 100644 --- a/clang/test/OpenMP/target_teams_distribute_simd_codegen.cpp +++ b/clang/test/OpenMP/target_teams_distribute_simd_codegen.cpp @@ -1,37 +1,65 @@ // Test host codegen. -// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CHECK --check-prefix CHECK-64 +// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -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 --check-prefix OMP45 // RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s -// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CHECK --check-prefix CHECK-64 -// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CHECK --check-prefix CHECK-32 +// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -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 --check-prefix OMP45 +// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -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 --check-prefix OMP45 // RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s -// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CHECK --check-prefix CHECK-32 - -// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY0 %s +// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -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 --check-prefix OMP45 +// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=50 -DOMP5 -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 --check-prefix OMP50 +// RUN: %clang_cc1 -fopenmp -fopenmp-version=50 -DOMP5 -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s +// RUN: %clang_cc1 -fopenmp -fopenmp-version=50 -DOMP5 -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 --check-prefix OMP50 +// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=50 -DOMP5 -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 --check-prefix OMP50 +// RUN: %clang_cc1 -fopenmp -fopenmp-version=50 -DOMP5 -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s +// RUN: %clang_cc1 -fopenmp -fopenmp-version=50 -DOMP5 -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 --check-prefix OMP50 + +// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s // RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s -// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY0 %s -// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY0 %s +// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s +// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s // RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s -// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY0 %s +// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s +// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=50 -DOMP5 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s +// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=50 -DOMP5 -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s +// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=50 -DOMP5 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s +// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=50 -DOMP5 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s +// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=50 -DOMP5 -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s +// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=50 -DOMP5 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s // SIMD-ONLY0-NOT: {{__kmpc|__tgt}} // Test target codegen - host bc file has to be created first. // RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm-bc %s -o %t-ppc-host.bc -// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix TCHECK --check-prefix TCHECK-64 +// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix TCHECK --check-prefix TCHECK-64 --check-prefix TOMP45 // RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t %s -// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix TCHECK --check-prefix TCHECK-64 +// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix TCHECK --check-prefix TCHECK-64 --check-prefix TOMP45 // RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm-bc %s -o %t-x86-host.bc -// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix TCHECK --check-prefix TCHECK-32 +// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix TCHECK --check-prefix TCHECK-32 --check-prefix TOMP45 // RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o %t %s -// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix TCHECK --check-prefix TCHECK-32 +// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix TCHECK --check-prefix TCHECK-32 --check-prefix TOMP45 +// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=50 -DOMP5 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm-bc %s -o %t-ppc-host.bc +// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=50 -DOMP5 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix TCHECK --check-prefix TCHECK-64 --check-prefix TOMP50 +// RUN: %clang_cc1 -fopenmp -fopenmp-version=50 -DOMP5 -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t %s +// RUN: %clang_cc1 -fopenmp -fopenmp-version=50 -DOMP5 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix TCHECK --check-prefix TCHECK-64 --check-prefix TOMP50 +// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=50 -DOMP5 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm-bc %s -o %t-x86-host.bc +// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=50 -DOMP5 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix TCHECK --check-prefix TCHECK-32 --check-prefix TOMP50 +// RUN: %clang_cc1 -fopenmp -fopenmp-version=50 -DOMP5 -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o %t %s +// RUN: %clang_cc1 -fopenmp -fopenmp-version=50 -DOMP5 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix TCHECK --check-prefix TCHECK-32 --check-prefix TOMP50 // RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm-bc %s -o %t-ppc-host.bc -// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY1 %s +// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck --check-prefix SIMD-ONLY1 %s // RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t %s -// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY1 %s +// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY1 %s // RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm-bc %s -o %t-x86-host.bc -// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY1 %s +// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck --check-prefix SIMD-ONLY1 %s // RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o %t %s -// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY1 %s +// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY1 %s +// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=50 -DOMP5 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm-bc %s -o %t-ppc-host.bc +// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=50 -DOMP5 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck --check-prefix SIMD-ONLY1 %s +// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=50 -DOMP5 -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t %s +// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=50 -DOMP5 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY1 %s +// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=50 -DOMP5 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm-bc %s -o %t-x86-host.bc +// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=50 -DOMP5 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck --check-prefix SIMD-ONLY1 %s +// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=50 -DOMP5 -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o %t %s +// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=50 -DOMP5 -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY1 %s // SIMD-ONLY1-NOT: {{__kmpc|__tgt}} // expected-no-diagnostics @@ -59,7 +87,8 @@ // CHECK-DAG: [[SIZET3:@.+]] = private unnamed_addr constant [2 x i64] [i64 4, i64 2] // CHECK-DAG: [[MAPT3:@.+]] = private unnamed_addr constant [2 x i64] [i64 800, i64 800] // CHECK-DAG: [[MAPT4:@.+]] = private unnamed_addr constant [9 x i64] [i64 800, i64 547, i64 800, i64 547, i64 547, i64 800, i64 800, i64 547, i64 547] -// CHECK-DAG: [[MAPT5:@.+]] = private unnamed_addr constant [6 x i64] [i64 32, i64 281474976711171, i64 800, i64 800, i64 800, i64 547] +// OMP45-DAG: [[MAPT5:@.+]] = private unnamed_addr constant [6 x i64] [i64 32, i64 281474976711171, i64 800, i64 800, i64 800, i64 547] +// OMP50-DAG: [[MAPT5:@.+]] = private unnamed_addr constant [7 x i64] [i64 32, i64 281474976711171, i64 800, i64 800, i64 800, i64 547, i64 800] // CHECK-DAG: [[SIZET6:@.+]] = private unnamed_addr constant [5 x i64] [i64 4, i64 4, i64 2, i64 1, i64 40] // CHECK-DAG: [[MAPT6:@.+]] = private unnamed_addr constant [5 x i64] [i64 800, i64 800, i64 800, i64 800, i64 547] // CHECK-DAG: [[SIZET7:@.+]] = private unnamed_addr constant [3 x i64] [i64 4, i64 2, i64 40] @@ -135,7 +164,11 @@ int foo(int n) { } // CHECK: call void [[HVT1:@.+]](i[[SZ]] {{[^,]+}}) +#ifdef OMP5 + #pragma omp target teams distribute simd if(target: 0) safelen(32) linear(a) if(simd: 1) +#else #pragma omp target teams distribute simd if(target: 0) safelen(32) linear(a) +#endif // OMP5 for (a = 0; a < 10; ++a) { a += 1; } @@ -254,48 +287,48 @@ int foo(int n) { // The names below are not necessarily consistent with the names used for the // addresses above as some are repeated. - // CHECK-DAG: store i[[SZ]] [[VLA0]], i[[SZ]]* [[CBPADDR0:%.+]], - // CHECK-DAG: store i[[SZ]] [[VLA0]], i[[SZ]]* [[CPADDR0:%.+]], + // CHECK-DAG: store i[[SZ]] [[A_CVAL]], i[[SZ]]* [[CBPADDR0:%.+]], + // CHECK-DAG: store i[[SZ]] [[A_CVAL]], i[[SZ]]* [[CPADDR0:%.+]], // CHECK-DAG: [[CBPADDR0]] = bitcast i8** {{%[^,]+}} to i[[SZ]]* // CHECK-DAG: [[CPADDR0]] = bitcast i8** {{%[^,]+}} to i[[SZ]]* - // CHECK-DAG: store i64 {{4|8}}, i64* {{%[^,]+}} + // CHECK-DAG: store i64 4, i64* {{%[^,]+}} - // CHECK-DAG: store i[[SZ]] [[VLA1]], i[[SZ]]* [[CBPADDR1:%.+]], - // CHECK-DAG: store i[[SZ]] [[VLA1]], i[[SZ]]* [[CPADDR1:%.+]], - // CHECK-DAG: [[CBPADDR1]] = bitcast i8** {{%[^,]+}} to i[[SZ]]* - // CHECK-DAG: [[CPADDR1]] = bitcast i8** {{%[^,]+}} to i[[SZ]]* - // CHECK-DAG: store i64 {{4|8}}, i64* {{%[^,]+}} + // CHECK-DAG: store [10 x float]* %{{.+}}, [10 x float]** [[CBPADDR1:%.+]], + // CHECK-DAG: store [10 x float]* %{{.+}}, [10 x float]** [[CPADDR1:%.+]], + // CHECK-DAG: [[CBPADDR1]] = bitcast i8** {{%[^,]+}} to [10 x float]** + // CHECK-DAG: [[CPADDR1]] = bitcast i8** {{%[^,]+}} to [10 x float]** + // CHECK-DAG: store i64 40, i64* {{%[^,]+}} - // CHECK-DAG: store i[[SZ]] 5, i[[SZ]]* [[CBPADDR2:%.+]], - // CHECK-DAG: store i[[SZ]] 5, i[[SZ]]* [[CPADDR2:%.+]], + // CHECK-DAG: store i[[SZ]] [[VLA0]], i[[SZ]]* [[CBPADDR2:%.+]], + // CHECK-DAG: store i[[SZ]] [[VLA0]], i[[SZ]]* [[CPADDR2:%.+]], // CHECK-DAG: [[CBPADDR2]] = bitcast i8** {{%[^,]+}} to i[[SZ]]* // CHECK-DAG: [[CPADDR2]] = bitcast i8** {{%[^,]+}} to i[[SZ]]* // CHECK-DAG: store i64 {{4|8}}, i64* {{%[^,]+}} - // CHECK-DAG: store i[[SZ]] [[A_CVAL]], i[[SZ]]* [[CBPADDR3:%.+]], - // CHECK-DAG: store i[[SZ]] [[A_CVAL]], i[[SZ]]* [[CPADDR3:%.+]], - // CHECK-DAG: [[CBPADDR3]] = bitcast i8** {{%[^,]+}} to i[[SZ]]* - // CHECK-DAG: [[CPADDR3]] = bitcast i8** {{%[^,]+}} to i[[SZ]]* - // CHECK-DAG: store i64 4, i64* {{%[^,]+}} - - // CHECK-DAG: store [10 x float]* %{{.+}}, [10 x float]** [[CBPADDR4:%.+]], - // CHECK-DAG: store [10 x float]* %{{.+}}, [10 x float]** [[CPADDR4:%.+]], - // CHECK-DAG: [[CBPADDR4]] = bitcast i8** {{%[^,]+}} to [10 x float]** - // CHECK-DAG: [[CPADDR4]] = bitcast i8** {{%[^,]+}} to [10 x float]** - // CHECK-DAG: store i64 40, i64* {{%[^,]+}} - - // CHECK-DAG: store float* %{{.+}}, float** [[CBPADDR5:%.+]], - // CHECK-DAG: store float* %{{.+}}, float** [[CPADDR5:%.+]], - // CHECK-DAG: [[CBPADDR5]] = bitcast i8** {{%[^,]+}} to float** - // CHECK-DAG: [[CPADDR5]] = bitcast i8** {{%[^,]+}} to float** + // CHECK-DAG: store float* %{{.+}}, float** [[CBPADDR3:%.+]], + // CHECK-DAG: store float* %{{.+}}, float** [[CPADDR3:%.+]], + // CHECK-DAG: [[CBPADDR3]] = bitcast i8** {{%[^,]+}} to float** + // CHECK-DAG: [[CPADDR3]] = bitcast i8** {{%[^,]+}} to float** // CHECK-DAG: store i64 [[BNSIZE]], i64* {{%[^,]+}} - // CHECK-DAG: store [5 x [10 x double]]* %{{.+}}, [5 x [10 x double]]** [[CBPADDR6:%.+]], - // CHECK-DAG: store [5 x [10 x double]]* %{{.+}}, [5 x [10 x double]]** [[CPADDR6:%.+]], - // CHECK-DAG: [[CBPADDR6]] = bitcast i8** {{%[^,]+}} to [5 x [10 x double]]** - // CHECK-DAG: [[CPADDR6]] = bitcast i8** {{%[^,]+}} to [5 x [10 x double]]** + // CHECK-DAG: store [5 x [10 x double]]* %{{.+}}, [5 x [10 x double]]** [[CBPADDR4:%.+]], + // CHECK-DAG: store [5 x [10 x double]]* %{{.+}}, [5 x [10 x double]]** [[CPADDR4:%.+]], + // CHECK-DAG: [[CBPADDR4]] = bitcast i8** {{%[^,]+}} to [5 x [10 x double]]** + // CHECK-DAG: [[CPADDR4]] = bitcast i8** {{%[^,]+}} to [5 x [10 x double]]** // CHECK-DAG: store i64 400, i64* {{%[^,]+}} + // CHECK-DAG: store i[[SZ]] 5, i[[SZ]]* [[CBPADDR5:%.+]], + // CHECK-DAG: store i[[SZ]] 5, i[[SZ]]* [[CPADDR5:%.+]], + // CHECK-DAG: [[CBPADDR5]] = bitcast i8** {{%[^,]+}} to i[[SZ]]* + // CHECK-DAG: [[CPADDR5]] = bitcast i8** {{%[^,]+}} to i[[SZ]]* + // CHECK-DAG: store i64 {{4|8}}, i64* {{%[^,]+}} + + // CHECK-DAG: store i[[SZ]] [[VLA1]], i[[SZ]]* [[CBPADDR6:%.+]], + // CHECK-DAG: store i[[SZ]] [[VLA1]], i[[SZ]]* [[CPADDR6:%.+]], + // CHECK-DAG: [[CBPADDR6]] = bitcast i8** {{%[^,]+}} to i[[SZ]]* + // CHECK-DAG: [[CPADDR6]] = bitcast i8** {{%[^,]+}} to i[[SZ]]* + // CHECK-DAG: store i64 {{4|8}}, i64* {{%[^,]+}} + // CHECK-DAG: store double* %{{.+}}, double** [[CBPADDR7:%.+]], // CHECK-DAG: store double* %{{.+}}, double** [[CPADDR7:%.+]], // CHECK-DAG: [[CBPADDR7]] = bitcast i8** {{%[^,]+}} to double** @@ -507,7 +540,7 @@ struct S1 { int b = n+1; short int c[2][n]; - #pragma omp target teams distribute simd if(target: n>60) + #pragma omp target teams distribute simd if(n>60) for (int i = 0; i < 10; ++i) { this->a = (double)b + 1.5; c[1][1] = ++a; @@ -549,7 +582,9 @@ int bar(int n){ // CHECK-32: store i32 %{{.+}}, i32* [[B_ADDR:%.+]], // CHECK-32: [[B_CVAL:%.+]] = load i[[SZ]], i[[SZ]]* [[B_ADDR]], -// CHECK: [[IF:%.+]] = icmp sgt i32 {{[^,]+}}, 60 +// OMP45: [[IF:%.+]] = icmp sgt i32 {{[^,]+}}, 60 +// OMP50: store i8 +// OMP50: [[IF:%.+]] = trunc i8 %{{.+}} to i1 // CHECK: br i1 [[IF]], label %[[TRY:[^,]+]], label %[[FAIL:[^,]+]] // CHECK: [[TRY]] // We capture 2 VLA sizes in this target region @@ -558,42 +593,67 @@ int bar(int n){ // CHECK-32: [[CSZSIZE:%.+]] = mul nuw i32 [[CELEMSIZE2]], 2 // CHECK-32: [[CSIZE:%.+]] = sext i32 [[CSZSIZE]] to i64 -// CHECK-DAG: [[RET:%.+]] = call i32 @__tgt_target_teams(i64 -1, i8* @{{[^,]+}}, i32 6, i8** [[BPR:%[^,]+]], i8** [[PR:%[^,]+]], i64* [[SR:%[^,]+]], i64* getelementptr inbounds ([6 x i64], [6 x i64]* [[MAPT5]], i32 0, i32 0), i32 0, i32 1) -// CHECK-DAG: [[BPR]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[BP:%.+]], i32 0, i32 0 -// CHECK-DAG: [[PR]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[P:%.+]], i32 0, i32 0 -// CHECK-DAG: [[SR]] = getelementptr inbounds [6 x i64], [6 x i64]* [[S:%.+]], i32 0, i32 0 -// CHECK-DAG: [[SADDR0:%.+]] = getelementptr inbounds [6 x i64], [6 x i64]* [[S]], i32 [[IDX0:[0-9]+]] -// CHECK-DAG: [[BPADDR0:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[BP]], i32 [[IDX0]] -// CHECK-DAG: [[PADDR0:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[P]], i32 [[IDX0]] -// CHECK-DAG: [[SADDR1:%.+]] = getelementptr inbounds [6 x i64], [6 x i64]* [[S]], i32 [[IDX1:[0-9]+]] -// CHECK-DAG: [[BPADDR1:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[BP]], i32 [[IDX1]] -// CHECK-DAG: [[PADDR1:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[P]], i32 [[IDX1]] -// CHECK-DAG: [[SADDR2:%.+]] = getelementptr inbounds [6 x i64], [6 x i64]* [[S]], i32 [[IDX2:[0-9]+]] -// CHECK-DAG: [[BPADDR2:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[BP]], i32 [[IDX2]] -// CHECK-DAG: [[PADDR2:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[P]], i32 [[IDX2]] -// CHECK-DAG: [[SADDR3:%.+]] = getelementptr inbounds [6 x i64], [6 x i64]* [[S]], i32 [[IDX3:[0-9]+]] -// CHECK-DAG: [[BPADDR3:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[BP]], i32 [[IDX3]] -// CHECK-DAG: [[PADDR3:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[P]], i32 [[IDX3]] -// CHECK-DAG: [[SADDR4:%.+]] = getelementptr inbounds [6 x i64], [6 x i64]* [[S]], i32 [[IDX3:[0-9]+]] -// CHECK-DAG: [[BPADDR4:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[BP]], i32 [[IDX3]] -// CHECK-DAG: [[PADDR4:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[P]], i32 [[IDX3]] -// CHECK-DAG: [[SADDR5:%.+]] = getelementptr inbounds [6 x i64], [6 x i64]* [[S]], i32 [[IDX3:[0-9]+]] -// CHECK-DAG: [[BPADDR5:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[BP]], i32 [[IDX3]] -// CHECK-DAG: [[PADDR5:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[P]], i32 [[IDX3]] +// OMP45-DAG: [[RET:%.+]] = call i32 @__tgt_target_teams(i64 -1, i8* @{{[^,]+}}, i32 6, i8** [[BPR:%[^,]+]], i8** [[PR:%[^,]+]], i64* [[SR:%[^,]+]], i64* getelementptr inbounds ([6 x i64], [6 x i64]* [[MAPT5]], i32 0, i32 0), i32 0, i32 1) +// OMP45-DAG: [[BPR]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[BP:%.+]], i32 0, i32 0 +// OMP45-DAG: [[PR]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[P:%.+]], i32 0, i32 0 +// OMP45-DAG: [[SR]] = getelementptr inbounds [6 x i64], [6 x i64]* [[S:%.+]], i32 0, i32 0 +// OMP45-DAG: [[SADDR0:%.+]] = getelementptr inbounds [6 x i64], [6 x i64]* [[S]], i32 [[IDX0:[0-9]+]] +// OMP45-DAG: [[BPADDR0:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[BP]], i32 [[IDX0]] +// OMP45-DAG: [[PADDR0:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[P]], i32 [[IDX0]] +// OMP45-DAG: [[SADDR1:%.+]] = getelementptr inbounds [6 x i64], [6 x i64]* [[S]], i32 [[IDX1:[0-9]+]] +// OMP45-DAG: [[BPADDR1:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[BP]], i32 [[IDX1]] +// OMP45-DAG: [[PADDR1:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[P]], i32 [[IDX1]] +// OMP45-DAG: [[SADDR2:%.+]] = getelementptr inbounds [6 x i64], [6 x i64]* [[S]], i32 [[IDX2:[0-9]+]] +// OMP45-DAG: [[BPADDR2:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[BP]], i32 [[IDX2]] +// OMP45-DAG: [[PADDR2:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[P]], i32 [[IDX2]] +// OMP45-DAG: [[SADDR3:%.+]] = getelementptr inbounds [6 x i64], [6 x i64]* [[S]], i32 [[IDX3:[0-9]+]] +// OMP45-DAG: [[BPADDR3:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[BP]], i32 [[IDX3]] +// OMP45-DAG: [[PADDR3:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[P]], i32 [[IDX3]] +// OMP45-DAG: [[SADDR4:%.+]] = getelementptr inbounds [6 x i64], [6 x i64]* [[S]], i32 [[IDX4:[0-9]+]] +// OMP45-DAG: [[BPADDR4:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[BP]], i32 [[IDX4]] +// OMP45-DAG: [[PADDR4:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[P]], i32 [[IDX4]] +// OMP45-DAG: [[SADDR5:%.+]] = getelementptr inbounds [6 x i64], [6 x i64]* [[S]], i32 [[IDX5:[0-9]+]] +// OMP45-DAG: [[BPADDR5:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[BP]], i32 [[IDX5]] +// OMP45-DAG: [[PADDR5:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[P]], i32 [[IDX5]] +// OMP50-DAG: [[RET:%.+]] = call i32 @__tgt_target_teams(i64 -1, i8* @{{[^,]+}}, i32 7, i8** [[BPR:%[^,]+]], i8** [[PR:%[^,]+]], i64* [[SR:%[^,]+]], i64* getelementptr inbounds ([7 x i64], [7 x i64]* [[MAPT5]], i32 0, i32 0), i32 0, i32 1) +// OMP50-DAG: [[BPR]] = getelementptr inbounds [7 x i8*], [7 x i8*]* [[BP:%.+]], i32 0, i32 0 +// OMP50-DAG: [[PR]] = getelementptr inbounds [7 x i8*], [7 x i8*]* [[P:%.+]], i32 0, i32 0 +// OMP50-DAG: [[SR]] = getelementptr inbounds [7 x i64], [7 x i64]* [[S:%.+]], i32 0, i32 0 +// OMP50-DAG: [[SADDR0:%.+]] = getelementptr inbounds [7 x i64], [7 x i64]* [[S]], i32 [[IDX0:[0-9]+]] +// OMP50-DAG: [[BPADDR0:%.+]] = getelementptr inbounds [7 x i8*], [7 x i8*]* [[BP]], i32 [[IDX0]] +// OMP50-DAG: [[PADDR0:%.+]] = getelementptr inbounds [7 x i8*], [7 x i8*]* [[P]], i32 [[IDX0]] +// OMP50-DAG: [[SADDR1:%.+]] = getelementptr inbounds [7 x i64], [7 x i64]* [[S]], i32 [[IDX1:[0-9]+]] +// OMP50-DAG: [[BPADDR1:%.+]] = getelementptr inbounds [7 x i8*], [7 x i8*]* [[BP]], i32 [[IDX1]] +// OMP50-DAG: [[PADDR1:%.+]] = getelementptr inbounds [7 x i8*], [7 x i8*]* [[P]], i32 [[IDX1]] +// OMP50-DAG: [[SADDR2:%.+]] = getelementptr inbounds [7 x i64], [7 x i64]* [[S]], i32 [[IDX2:[0-9]+]] +// OMP50-DAG: [[BPADDR2:%.+]] = getelementptr inbounds [7 x i8*], [7 x i8*]* [[BP]], i32 [[IDX2]] +// OMP50-DAG: [[PADDR2:%.+]] = getelementptr inbounds [7 x i8*], [7 x i8*]* [[P]], i32 [[IDX2]] +// OMP50-DAG: [[SADDR3:%.+]] = getelementptr inbounds [7 x i64], [7 x i64]* [[S]], i32 [[IDX3:[0-9]+]] +// OMP50-DAG: [[BPADDR3:%.+]] = getelementptr inbounds [7 x i8*], [7 x i8*]* [[BP]], i32 [[IDX3]] +// OMP50-DAG: [[PADDR3:%.+]] = getelementptr inbounds [7 x i8*], [7 x i8*]* [[P]], i32 [[IDX3]] +// OMP50-DAG: [[SADDR4:%.+]] = getelementptr inbounds [7 x i64], [7 x i64]* [[S]], i32 [[IDX4:[0-9]+]] +// OMP50-DAG: [[BPADDR4:%.+]] = getelementptr inbounds [7 x i8*], [7 x i8*]* [[BP]], i32 [[IDX4]] +// OMP50-DAG: [[PADDR4:%.+]] = getelementptr inbounds [7 x i8*], [7 x i8*]* [[P]], i32 [[IDX4]] +// OMP50-DAG: [[SADDR5:%.+]] = getelementptr inbounds [7 x i64], [7 x i64]* [[S]], i32 [[IDX5:[0-9]+]] +// OMP50-DAG: [[BPADDR5:%.+]] = getelementptr inbounds [7 x i8*], [7 x i8*]* [[BP]], i32 [[IDX5]] +// OMP50-DAG: [[PADDR5:%.+]] = getelementptr inbounds [7 x i8*], [7 x i8*]* [[P]], i32 [[IDX5]] +// OMP50-DAG: [[SADDR6:%.+]] = getelementptr inbounds [7 x i64], [7 x i64]* [[S]], i32 [[IDX6:[0-9]+]] +// OMP50-DAG: [[BPADDR6:%.+]] = getelementptr inbounds [7 x i8*], [7 x i8*]* [[BP]], i32 [[IDX6]] +// OMP50-DAG: [[PADDR6:%.+]] = getelementptr inbounds [7 x i8*], [7 x i8*]* [[P]], i32 [[IDX6]] // The names below are not necessarily consistent with the names used for the // addresses above as some are repeated. -// CHECK-DAG: store i[[SZ]] [[VLA0]], i[[SZ]]* [[CBPADDR0:%.+]], -// CHECK-DAG: store i[[SZ]] [[VLA0]], i[[SZ]]* [[CPADDR0:%.+]], -// CHECK-DAG: [[CBPADDR0]] = bitcast i8** {{%[^,]+}} to i[[SZ]]* -// CHECK-DAG: [[CPADDR0]] = bitcast i8** {{%[^,]+}} to i[[SZ]]* -// CHECK-DAG: store i64 {{4|8}}, i64* {{%[^,]+}} - -// CHECK-DAG: store i[[SZ]] 2, i[[SZ]]* [[CBPADDR1:%.+]], -// CHECK-DAG: store i[[SZ]] 2, i[[SZ]]* [[CPADDR1:%.+]], -// CHECK-DAG: [[CBPADDR1]] = bitcast i8** {{%[^,]+}} to i[[SZ]]* -// CHECK-DAG: [[CPADDR1]] = bitcast i8** {{%[^,]+}} to i[[SZ]]* -// CHECK-DAG: store i64 {{4|8}}, i64* {{%[^,]+}} +// CHECK-DAG: store [[S1]]* %{{.+}}, [[S1]]** [[CBPADDR0:%.+]], +// CHECK-DAG: store double* %{{.+}}, double** [[CPADDR0:%.+]], +// CHECK-DAG: [[CBPADDR0]] = bitcast i8** {{%[^,]+}} to [[S1]]** +// CHECK-DAG: [[CPADDR0]] = bitcast i8** {{%[^,]+}} to double** +// CHECK-DAG: store i64 %{{.+}}, i64* {{%[^,]+}} + +// CHECK-DAG: store [[S1]]* %{{.+}}, [[S1]]** [[CBPADDR1:%.+]], +// CHECK-DAG: store double* %{{.+}}, double** [[CPADDR1:%.+]], +// CHECK-DAG: [[CBPADDR1]] = bitcast i8** {{%[^,]+}} to [[S1]]** +// CHECK-DAG: [[CPADDR1]] = bitcast i8** {{%[^,]+}} to double** +// CHECK-DAG: store i64 {{8|4}}, i64* {{%[^,]+}} // CHECK-DAG: store i[[SZ]] [[B_CVAL]], i[[SZ]]* [[CBPADDR2:%.+]], // CHECK-DAG: store i[[SZ]] [[B_CVAL]], i[[SZ]]* [[CPADDR2:%.+]], @@ -601,17 +661,17 @@ int bar(int n){ // CHECK-DAG: [[CPADDR2]] = bitcast i8** {{%[^,]+}} to i[[SZ]]* // CHECK-DAG: store i64 4, i64* {{%[^,]+}} -// CHECK-DAG: store [[S1]]* %{{.+}}, [[S1]]** [[CBPADDR3:%.+]], -// CHECK-DAG: store double* %{{.+}}, double** [[CPADDR3:%.+]], -// CHECK-DAG: [[CBPADDR3]] = bitcast i8** {{%[^,]+}} to [[S1]]** -// CHECK-DAG: [[CPADDR3]] = bitcast i8** {{%[^,]+}} to double** -// CHECK-DAG: store i64 8, i64* {{%[^,]+}} +// CHECK-DAG: store i[[SZ]] 2, i[[SZ]]* [[CBPADDR3:%.+]], +// CHECK-DAG: store i[[SZ]] 2, i[[SZ]]* [[CPADDR3:%.+]], +// CHECK-DAG: [[CBPADDR3]] = bitcast i8** {{%[^,]+}} to i[[SZ]]* +// CHECK-DAG: [[CPADDR3]] = bitcast i8** {{%[^,]+}} to i[[SZ]]* +// CHECK-DAG: store i64 {{4|8}}, i64* {{%[^,]+}} -// CHECK-DAG: store [[S1]]* %{{.+}}, [[S1]]** [[CBPADDR4:%.+]], -// CHECK-DAG: store double* %{{.+}}, double** [[CPADDR4:%.+]], -// CHECK-DAG: [[CBPADDR4]] = bitcast i8** {{%[^,]+}} to [[S1]]** -// CHECK-DAG: [[CPADDR4]] = bitcast i8** {{%[^,]+}} to double** -// CHECK-DAG: store i64 8, i64* {{%[^,]+}} +// CHECK-DAG: store i[[SZ]] [[VLA0]], i[[SZ]]* [[CBPADDR4:%.+]], +// CHECK-DAG: store i[[SZ]] [[VLA0]], i[[SZ]]* [[CPADDR4:%.+]], +// CHECK-DAG: [[CBPADDR4]] = bitcast i8** {{%[^,]+}} to i[[SZ]]* +// CHECK-DAG: [[CPADDR4]] = bitcast i8** {{%[^,]+}} to i[[SZ]]* +// CHECK-DAG: store i64 {{4|8}}, i64* {{%[^,]+}} // CHECK-DAG: store i16* %{{.+}}, i16** [[CBPADDR5:%.+]], // CHECK-DAG: store i16* %{{.+}}, i16** [[CPADDR5:%.+]], @@ -619,11 +679,18 @@ int bar(int n){ // CHECK-DAG: [[CPADDR5]] = bitcast i8** {{%[^,]+}} to i16** // CHECK-DAG: store i64 [[CSIZE]], i64* {{%[^,]+}} +// OMP50-DAG: store i[[SZ]] [[IF_C:%.+]], i[[SZ]]* [[CBPADDR6:%.+]], +// OMP50-DAG: store i[[SZ]] [[IF_C]], i[[SZ]]* [[CPADDR6:%.+]], +// OMP50-DAG: [[CBPADDR6]] = bitcast i8** {{%[^,]+}} to i[[SZ]]* +// OMP50-DAG: [[CPADDR6]] = bitcast i8** {{%[^,]+}} to i[[SZ]]* +// OMP50-DAG: store i64 1, i64* {{%[^,]+}} + // CHECK-NEXT: [[ERROR:%.+]] = icmp ne i32 [[RET]], 0 // CHECK-NEXT: br i1 [[ERROR]], label %[[FAIL:[^,]+]], label %[[END:[^,]+]] // CHECK: [[FAIL]] -// CHECK: call void [[HVT7:@.+]]({{[^,]+}}, {{[^,]+}}, {{[^,]+}}, {{[^,]+}}, {{[^,]+}}) +// OMP45: call void [[HVT7:@.+]]({{[^,]+}}, {{[^,]+}}, {{[^,]+}}, {{[^,]+}}, {{[^,]+}}) +// OMP50: call void [[HVT7:@.+]]({{[^,]+}}, {{[^,]+}}, {{[^,]+}}, {{[^,]+}}, {{[^,]+}}, {{[^,]+}}) // CHECK-NEXT: br label %[[END]] // CHECK: [[END]] @@ -710,10 +777,10 @@ int bar(int n){ // CHECK-DAG: [[BPADDR2:%.+]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[BP]], i32 0, i32 2 // CHECK-DAG: [[PADDR2:%.+]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[P]], i32 0, i32 2 -// CHECK-DAG: store i[[SZ]] [[VAL2:%.+]], i[[SZ]]* [[CBPADDR2:%.+]], -// CHECK-DAG: store i[[SZ]] [[VAL2]], i[[SZ]]* [[CPADDR2:%.+]], -// CHECK-DAG: [[CBPADDR2]] = bitcast i8** {{%[^,]+}} to i[[SZ]]* -// CHECK-DAG: [[CPADDR2]] = bitcast i8** {{%[^,]+}} to i[[SZ]]* +// CHECK-DAG: store [10 x i32]* [[VAL2:%.+]], [10 x i32]** [[CBPADDR2:%.+]], +// CHECK-DAG: store [10 x i32]* [[VAL2]], [10 x i32]** [[CPADDR2:%.+]], +// CHECK-DAG: [[CBPADDR2]] = bitcast i8** {{%[^,]+}} to [10 x i32]** +// CHECK-DAG: [[CPADDR2]] = bitcast i8** {{%[^,]+}} to [10 x i32]** // CHECK: [[ERROR:%.+]] = icmp ne i32 [[RET]], 0 // CHECK-NEXT: br i1 [[ERROR]], label %[[FAIL:.+]], label %[[END:[^,]+]] @@ -739,7 +806,9 @@ int bar(int n){ // CHECK: [[LOCAL_VLA1:%.+]] = alloca i[[SZ]] // CHECK: [[LOCAL_VLA2:%.+]] = alloca i[[SZ]] // CHECK: [[LOCAL_C:%.+]] = alloca i16* +// OMP50: alloca i[[SZ]] // CHECK: [[LOCAL_B_CASTED:%.+]] = alloca i[[SZ]] +// OMP50: [[IF_CASTED:%.+]] = alloca i[[SZ]] // CHECK-DAG: store [[S1]]* [[ARG_THIS:%.+]], [[S1]]** [[LOCAL_THIS]] // CHECK-DAG: store i[[SZ]] [[ARG_B:%.+]], i[[SZ]]* [[LOCAL_B]] // CHECK-DAG: store i[[SZ]] [[ARG_VLA1:%.+]], i[[SZ]]* [[LOCAL_VLA1]] @@ -758,11 +827,14 @@ int bar(int n){ // CHECK-32-DAG:[[LOCAL_BV:%.+]] = load i32, i32* [[LOCAL_B]] // CHECK-32-DAG:store i32 [[LOCAL_BV]], i32* [[LOCAL_B_CASTED]], align // CHECK-DAG: [[REF_B:%.+]] = load i[[SZ]], i[[SZ]]* [[LOCAL_B_CASTED]], +// OMP50-DAG: [[IF_CAST:%.+]] = load i[[SZ]], i[[SZ]]* [[IF_CASTED]], -// CHECK: call {{.*}}void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_teams(%struct.ident_t* [[DEF_LOC]], i32 5, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, [[S1]]*, i[[SZ]], i[[SZ]], i[[SZ]], i16*)* [[OMP_OUTLINED5:@.+]] to void (i32*, i32*, ...)*), [[S1]]* [[REF_THIS]], i[[SZ]] [[REF_B]], i[[SZ]] [[VAL_VLA1]], i[[SZ]] [[VAL_VLA2]], i16* [[REF_C]]) +// OMP45: call {{.*}}void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_teams(%struct.ident_t* [[DEF_LOC]], i32 5, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, [[S1]]*, i[[SZ]], i[[SZ]], i[[SZ]], i16*)* [[OMP_OUTLINED5:@.+]] to void (i32*, i32*, ...)*), [[S1]]* [[REF_THIS]], i[[SZ]] [[REF_B]], i[[SZ]] [[VAL_VLA1]], i[[SZ]] [[VAL_VLA2]], i16* [[REF_C]]) +// OMP50: call {{.*}}void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_teams(%struct.ident_t* [[DEF_LOC]], i32 6, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, [[S1]]*, i[[SZ]], i[[SZ]], i[[SZ]], i16*, i[[SZ]])* [[OMP_OUTLINED5:@.+]] to void (i32*, i32*, ...)*), [[S1]]* [[REF_THIS]], i[[SZ]] [[REF_B]], i[[SZ]] [[VAL_VLA1]], i[[SZ]] [[VAL_VLA2]], i16* [[REF_C]], i[[SZ]] [[IF_CAST]]) // // -// CHECK: define internal {{.*}}void [[OMP_OUTLINED5]](i32* noalias %.global_tid., i32* noalias %.bound_tid., [[S1]]* %{{.+}}, i[[SZ]] %{{.+}}, i[[SZ]] %{{.+}}, i[[SZ]] %{{.+}}, i16* {{.+}}) +// OMP45: define internal {{.*}}void [[OMP_OUTLINED5]](i32* noalias %.global_tid., i32* noalias %.bound_tid., [[S1]]* %{{.+}}, i[[SZ]] %{{.+}}, i[[SZ]] %{{.+}}, i[[SZ]] %{{.+}}, i16* {{.+}}) +// OMP50: define internal {{.*}}void [[OMP_OUTLINED5]](i32* noalias %.global_tid., i32* noalias %.bound_tid., [[S1]]* %{{.+}}, i[[SZ]] %{{.+}}, i[[SZ]] %{{.+}}, i[[SZ]] %{{.+}}, i16* {{.+}}, i[[SZ]] %{{.+}}) // To reduce complexity, we're only going as far as validating the signature of the outlined parallel function. @@ -843,8 +915,11 @@ int bar(int n){ // CHECK: define internal {{.*}}void [[OMP_OUTLINED7]](i32* noalias %.global_tid., i32* noalias %.bound_tid., i[[SZ]] %{{.+}}, i[[SZ]] %{{.+}}, [10 x i32]* {{.+}}) // To reduce complexity, we're only going as far as validating the signature of the outlined parallel function. +// OMP45-NOT: !{!"llvm.loop.vectorize.enable", i1 false} // CHECK-DAG: !{!"llvm.loop.vectorize.width", i32 16} // CHECK-DAG: !{!"llvm.loop.vectorize.enable", i1 true} // CHECK-DAG: !{!"llvm.loop.vectorize.width", i32 32} +// OMP45-NOT: !{!"llvm.loop.vectorize.enable", i1 false} +// OMP50-DAG: !{!"llvm.loop.vectorize.enable", i1 false} #endif diff --git a/clang/test/OpenMP/target_teams_distribute_simd_if_messages.cpp b/clang/test/OpenMP/target_teams_distribute_simd_if_messages.cpp index 53af6e7..0cb51d3 100644 --- a/clang/test/OpenMP/target_teams_distribute_simd_if_messages.cpp +++ b/clang/test/OpenMP/target_teams_distribute_simd_if_messages.cpp @@ -1,6 +1,8 @@ -// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -ferror-limit 100 %s -Wuninitialized +// RUN: %clang_cc1 -verify=expected,omp45 -fopenmp -fopenmp-version=45 -ferror-limit 100 %s -Wuninitialized +// RUN: %clang_cc1 -verify=expected,omp50 -fopenmp -fopenmp-version=50 -ferror-limit 100 %s -Wuninitialized -// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=45 -ferror-limit 100 %s -Wuninitialized +// RUN: %clang_cc1 -verify=expected,omp45 -fopenmp-simd -fopenmp-version=45 -ferror-limit 100 %s -Wuninitialized +// RUN: %clang_cc1 -verify=expected,omp50 -fopenmp-simd -fopenmp-version=50 -ferror-limit 100 %s -Wuninitialized void foo() { } @@ -51,11 +53,11 @@ int tmain(T argc, S **argv) { for (i = 0; i < argc; ++i) foo(); #pragma omp target teams distribute simd if(target: argc) for (i = 0; i < argc; ++i) foo(); -#pragma omp target teams distribute simd if(target : argc) if (distribute:argc) // expected-error {{directive name modifier 'distribute' is not allowed for '#pragma omp target teams distribute simd'}} +#pragma omp target teams distribute simd if(target : argc) if (simd:argc) // omp45-error {{directive name modifier 'simd' is not allowed for '#pragma omp target teams distribute simd'}} for (i = 0; i < argc; ++i) foo(); #pragma omp target teams distribute simd if(target: argc) if (target:argc) // expected-error {{directive '#pragma omp target teams distribute simd' cannot contain more than one 'if' clause with 'target' name modifier}} for (i = 0; i < argc; ++i) foo(); -#pragma omp target teams distribute simd if(target: argc) if (argc) // expected-note {{previous clause with directive name modifier specified here}} expected-error {{no more 'if' clause is allowed}} +#pragma omp target teams distribute simd if(target: argc) if (argc) // expected-note {{previous clause with directive name modifier specified here}} omp45-error {{no more 'if' clause is allowed}} omp50-error {{expected 'simd' directive name modifier}} for (i = 0; i < argc; ++i) foo(); #pragma omp target teams distribute simd if(distribute : argc) // expected-error {{directive name modifier 'distribute' is not allowed for '#pragma omp target teams distribute simd'}} for (i = 0; i < argc; ++i) foo(); @@ -97,11 +99,11 @@ int main(int argc, char **argv) { for (i = 0; i < argc; ++i) foo(); #pragma omp target teams distribute simd if(target: z/argc) for (i = 0; i < argc; ++i) foo(); -#pragma omp target teams distribute simd if(target : argc) if (distribute:argc) // expected-error {{directive name modifier 'distribute' is not allowed for '#pragma omp target teams distribute simd'}} +#pragma omp target teams distribute simd if(target : argc) if (simd:argc) // omp45-error {{directive name modifier 'simd' is not allowed for '#pragma omp target teams distribute simd'}} for (i = 0; i < argc; ++i) foo(); #pragma omp target teams distribute simd if(target: argc) if (target:argc) // expected-error {{directive '#pragma omp target teams distribute simd' cannot contain more than one 'if' clause with 'target' name modifier}} for (i = 0; i < argc; ++i) foo(); -#pragma omp target teams distribute simd if(target: argc) if (argc) // expected-note {{previous clause with directive name modifier specified here}} expected-error {{no more 'if' clause is allowed}} +#pragma omp target teams distribute simd if(target: argc) if (argc) // expected-note {{previous clause with directive name modifier specified here}} omp45-error {{no more 'if' clause is allowed}} omp50-error {{expected 'simd' directive name modifier}} for (i = 0; i < argc; ++i) foo(); #pragma omp target teams distribute simd if(distribute : argc) // expected-error {{directive name modifier 'distribute' is not allowed for '#pragma omp target teams distribute simd'}} for (i = 0; i < argc; ++i) foo(); -- 2.7.4