agozillon created this revision.
Herald added subscribers: Moerafaat, zero9178, bzcheeseman, awarzynski,
sdasgup3, wenzhicui, wrengr, cota, teijeong, rdzhabarov, tatianashp, msifontes,
jurahul, Kayjukh, grosul1, Joonsoo, liufengdb, aartbik, mgester, arpith-jacob,
antiagainst, shauheen, rriddle, mehdi_amini, thopre, guansong, yaxunl.
Herald added a reviewer: sscalpone.
Herald added a reviewer: ftynse.
Herald added a reviewer: awarzynski.
Herald added projects: Flang, All.
agozillon requested review of this revision.
Herald added subscribers: cfe-commits, sstefan1, stephenneuendorffer,
nicolasvasilache, jdoerfert, MaskRay.
Herald added a reviewer: jdoerfert.
Herald added a reviewer: nicolasvasilache.
Herald added projects: clang, MLIR.
This patch adds the lowering for the RTLModuleFlagsAttr to LLVM-IR,
which lowers each individual arguent of the attribute to globals. AS well
as the application of it by flags in the frontend which have been activated
for flang fc1.
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D145264
Files:
clang/include/clang/Driver/Options.td
clang/lib/Driver/ToolChains/Flang.cpp
clang/lib/Driver/ToolChains/Flang.h
clang/test/Driver/flang/flang-omp.f90
flang/include/flang/Frontend/LangOptions.def
flang/lib/Frontend/CompilerInvocation.cpp
flang/lib/Frontend/FrontendActions.cpp
flang/test/Driver/driver-help.f90
flang/test/Lower/OpenMP/rtl-flags.f90
mlir/lib/Target/LLVMIR/Dialect/OpenMP/OpenMPToLLVMIRTranslation.cpp
Index: mlir/lib/Target/LLVMIR/Dialect/OpenMP/OpenMPToLLVMIRTranslation.cpp
===================================================================
--- mlir/lib/Target/LLVMIR/Dialect/OpenMP/OpenMPToLLVMIRTranslation.cpp
+++ mlir/lib/Target/LLVMIR/Dialect/OpenMP/OpenMPToLLVMIRTranslation.cpp
@@ -1351,6 +1351,40 @@
return success();
}
+/// Lowers the RTLModuleFlagsAttr which is applied to the module on the device
+/// pass when offloading, this attribute contains OpenMP RTL globals that can
+/// be passed as flags to the frontend, otherwise they are set to default
+LogicalResult
+convertRTLModuleFlagsAttr(Operation *op,
+ mlir::omp::RTLModuleFlagsAttr attribute,
+ LLVM::ModuleTranslation &moduleTranslation) {
+ llvm::OpenMPIRBuilder *ompBuilder = moduleTranslation.getOpenMPBuilder();
+
+ ompBuilder->createGlobalFlag(
+ attribute.getDebugKind() /*LangOpts().OpenMPTargetDebug*/,
+ "__omp_rtl_debug_kind");
+ ompBuilder->createGlobalFlag(
+ attribute
+ .getAssumeTeamsOversubscription() /*LangOpts().OpenMPTeamSubscription*/
+ ,
+ "__omp_rtl_assume_teams_oversubscription");
+ ompBuilder->createGlobalFlag(
+ attribute
+ .getAssumeThreadsOversubscription() /*LangOpts().OpenMPThreadSubscription*/
+ ,
+ "__omp_rtl_assume_threads_oversubscription");
+ ompBuilder->createGlobalFlag(
+ attribute.getAssumeNoThreadState() /*LangOpts().OpenMPNoThreadState*/,
+ "__omp_rtl_assume_no_thread_state");
+ ompBuilder->createGlobalFlag(
+ attribute
+ .getAssumeNoNestedParallelism() /*LangOpts().OpenMPNoNestedParallelism*/
+ ,
+ "__omp_rtl_assume_no_nested_parallelism");
+
+ return success();
+}
+
namespace {
/// Implementation of the dialect interface that converts operations belonging
@@ -1365,10 +1399,34 @@
LogicalResult
convertOperation(Operation *op, llvm::IRBuilderBase &builder,
LLVM::ModuleTranslation &moduleTranslation) const final;
+
+ LogicalResult
+ amendOperation(Operation *op, NamedAttribute attribute,
+ LLVM::ModuleTranslation &moduleTranslation) const final;
};
} // namespace
+/// Given an OpenMP MLIR attribute, create the corresponding LLVM-IR, runtime
+/// calls, or operation amendments
+LogicalResult OpenMPDialectLLVMIRTranslationInterface::amendOperation(
+ Operation *op, NamedAttribute attribute,
+ LLVM::ModuleTranslation &moduleTranslation) const {
+
+ return llvm::TypeSwitch<Attribute, LogicalResult>(attribute.getValue())
+ .Case([&](mlir::omp::RTLModuleFlagsAttr rtlAttr) {
+ return convertRTLModuleFlagsAttr(op, rtlAttr, moduleTranslation);
+ })
+ .Default([&](Attribute attr) {
+ // fall through for omp attributes that do not require lowering and/or
+ // have no concrete definition and thus no type to define a case on
+ // e.g. omp.is_device
+ return success();
+ });
+
+ return failure();
+}
+
/// Given an OpenMP MLIR operation, create the corresponding LLVM IR
/// (including OpenMP runtime calls).
LogicalResult OpenMPDialectLLVMIRTranslationInterface::convertOperation(
Index: flang/test/Lower/OpenMP/rtl-flags.f90
===================================================================
--- /dev/null
+++ flang/test/Lower/OpenMP/rtl-flags.f90
@@ -0,0 +1,76 @@
+!RUN: %flang_fc1 -emit-fir -fopenmp -fopenmp-is-device %s -o - | FileCheck %s --check-prefix=DEFAULT-DEVICE-FIR
+!RUN: %flang_fc1 -emit-fir -fopenmp %s -o - | FileCheck %s --check-prefix=DEFAULT-HOST-FIR
+!RUN: %flang_fc1 -emit-llvm -fopenmp -fopenmp-is-device %s -o - | FileCheck %s --check-prefix=DEFAULT-DEVICE-LLVM
+!RUN: %flang_fc1 -emit-fir -fopenmp -fopenmp-target-debug -fopenmp-is-device %s -o - | FileCheck %s --check-prefix=DBG-DEVICE-FIR
+!RUN: %flang_fc1 -emit-llvm -fopenmp -fopenmp-target-debug -fopenmp-is-device %s -o - | FileCheck %s --check-prefix=DBG-DEVICE-LLVM
+!RUN: %flang_fc1 -emit-fir -fopenmp -fopenmp-target-debug=111 -fopenmp-is-device %s -o - | FileCheck %s --check-prefix=DBG-EQ-DEVICE-FIR
+!RUN: %flang_fc1 -emit-llvm -fopenmp -fopenmp-target-debug=111 -fopenmp-is-device %s -o - | FileCheck %s --check-prefix=DBG-EQ-DEVICE-LLVM
+!RUN: %flang_fc1 -emit-fir -fopenmp -fopenmp-assume-teams-oversubscription -fopenmp-is-device %s -o - | FileCheck %s --check-prefix=TEAMS-OSUB-DEVICE-FIR
+!RUN: %flang_fc1 -emit-llvm -fopenmp -fopenmp-assume-teams-oversubscription -fopenmp-is-device %s -o - | FileCheck %s --check-prefix=TEAMS-OSUB-DEVICE-LLVM
+!RUN: %flang_fc1 -emit-fir -fopenmp -fopenmp-assume-threads-oversubscription -fopenmp-is-device %s -o - | FileCheck %s --check-prefix=THREAD-OSUB-DEVICE-FIR
+!RUN: %flang_fc1 -emit-llvm -fopenmp -fopenmp-assume-threads-oversubscription -fopenmp-is-device %s -o - | FileCheck %s --check-prefix=THREAD-OSUB-DEVICE-LLVM
+!RUN: %flang_fc1 -emit-fir -fopenmp -fopenmp-assume-no-thread-state -fopenmp-is-device %s -o - | FileCheck %s --check-prefix=THREAD-STATE-DEVICE-FIR
+!RUN: %flang_fc1 -emit-llvm -fopenmp -fopenmp-assume-no-thread-state -fopenmp-is-device %s -o - | FileCheck %s --check-prefix=THREAD-STATE-DEVICE-LLVM
+!RUN: %flang_fc1 -emit-fir -fopenmp -fopenmp-assume-no-nested-parallelism -fopenmp-is-device %s -o - | FileCheck %s --check-prefix=NEST-PAR-DEVICE-FIR
+!RUN: %flang_fc1 -emit-llvm -fopenmp -fopenmp-assume-no-nested-parallelism -fopenmp-is-device %s -o - | FileCheck %s --check-prefix=NEST-PAR-DEVICE-LLVM
+!RUN: %flang_fc1 -emit-fir -fopenmp -fopenmp-target-debug -fopenmp-assume-teams-oversubscription -fopenmp-assume-no-nested-parallelism -fopenmp-assume-threads-oversubscription -fopenmp-assume-no-thread-state -fopenmp-is-device %s -o - | FileCheck %s --check-prefix=ALL-DEVICE-FIR
+!RUN: %flang_fc1 -emit-llvm -fopenmp -fopenmp-target-debug -fopenmp-assume-teams-oversubscription -fopenmp-assume-no-nested-parallelism -fopenmp-assume-threads-oversubscription -fopenmp-assume-no-thread-state -fopenmp-is-device %s -o - | FileCheck %s --check-prefix=ALL-DEVICE-LLVM
+
+!DEFAULT-DEVICE-FIR: module attributes {{{.*}}, omp.is_device = true, omp.rtlmoduleflags = #omp.rtlmoduleflags<>}
+!DEFAULT-HOST-FIR: module attributes {{{.*}}, omp.is_device = false}
+!DEFAULT-DEVICE-LLVM: @__omp_rtl_debug_kind = weak_odr hidden constant i32 0
+!DEFAULT-DEVICE-LLVM: @__omp_rtl_assume_teams_oversubscription = weak_odr hidden constant i32 0
+!DEFAULT-DEVICE-LLVM: @__omp_rtl_assume_threads_oversubscription = weak_odr hidden constant i32 0
+!DEFAULT-DEVICE-LLVM: @__omp_rtl_assume_no_thread_state = weak_odr hidden constant i32 0
+!DEFAULT-DEVICE-LLVM: @__omp_rtl_assume_no_nested_parallelism = weak_odr hidden constant i32 0
+
+!DBG-DEVICE-FIR: module attributes {{{.*}}, omp.is_device = true, omp.rtlmoduleflags = #omp.rtlmoduleflags<debug_kind = 1>}
+!DBG-DEVICE-LLVM: @__omp_rtl_debug_kind = weak_odr hidden constant i32 1
+!DBG-DEVICE-LLVM: @__omp_rtl_assume_teams_oversubscription = weak_odr hidden constant i32 0
+!DBG-DEVICE-LLVM: @__omp_rtl_assume_threads_oversubscription = weak_odr hidden constant i32 0
+!DBG-DEVICE-LLVM: @__omp_rtl_assume_no_thread_state = weak_odr hidden constant i32 0
+!DBG-DEVICE-LLVM: @__omp_rtl_assume_no_nested_parallelism = weak_odr hidden constant i32 0
+
+!DBG-EQ-DEVICE-FIR: module attributes {{{.*}}, omp.is_device = true, omp.rtlmoduleflags = #omp.rtlmoduleflags<debug_kind = 111>}
+!DBG-EQ-DEVICE-LLVM: @__omp_rtl_debug_kind = weak_odr hidden constant i32 111
+!DBG-EQ-DEVICE-LLVM: @__omp_rtl_assume_teams_oversubscription = weak_odr hidden constant i32 0
+!DBG-EQ-DEVICE-LLVM: @__omp_rtl_assume_threads_oversubscription = weak_odr hidden constant i32 0
+!DBG-EQ-DEVICE-LLVM: @__omp_rtl_assume_no_thread_state = weak_odr hidden constant i32 0
+!DBG-EQ-DEVICE-LLVM: @__omp_rtl_assume_no_nested_parallelism = weak_odr hidden constant i32 0
+
+!TEAMS-OSUB-DEVICE-FIR: module attributes {{{.*}}, omp.is_device = true, omp.rtlmoduleflags = #omp.rtlmoduleflags<assume_teams_oversubscription = true>}
+!TEAMS-OSUB-DEVICE-LLVM: @__omp_rtl_debug_kind = weak_odr hidden constant i32 0
+!TEAMS-OSUB-DEVICE-LLVM: @__omp_rtl_assume_teams_oversubscription = weak_odr hidden constant i32 1
+!TEAMS-OSUB-DEVICE-LLVM: @__omp_rtl_assume_threads_oversubscription = weak_odr hidden constant i32 0
+!TEAMS-OSUB-DEVICE-LLVM: @__omp_rtl_assume_no_thread_state = weak_odr hidden constant i32 0
+!TEAMS-OSUB-DEVICE-LLVM: @__omp_rtl_assume_no_nested_parallelism = weak_odr hidden constant i32 0
+
+!THREAD-OSUB-DEVICE-FIR: module attributes {{{.*}}, omp.is_device = true, omp.rtlmoduleflags = #omp.rtlmoduleflags<assume_threads_oversubscription = true>}
+!THREAD-OSUB-DEVICE-LLVM: @__omp_rtl_debug_kind = weak_odr hidden constant i32 0
+!THREAD-OSUB-DEVICE-LLVM: @__omp_rtl_assume_teams_oversubscription = weak_odr hidden constant i32 0
+!THREAD-OSUB-DEVICE-LLVM: @__omp_rtl_assume_threads_oversubscription = weak_odr hidden constant i32 1
+!THREAD-OSUB-DEVICE-LLVM: @__omp_rtl_assume_no_thread_state = weak_odr hidden constant i32 0
+!THREAD-OSUB-DEVICE-LLVM: @__omp_rtl_assume_no_nested_parallelism = weak_odr hidden constant i32 0
+
+!THREAD-STATE-DEVICE-FIR: module attributes {{{.*}}, omp.is_device = true, omp.rtlmoduleflags = #omp.rtlmoduleflags<assume_no_thread_state = true>}
+!THREAD-STATE-DEVICE-LLVM: @__omp_rtl_debug_kind = weak_odr hidden constant i32 0
+!THREAD-STATE-DEVICE-LLVM: @__omp_rtl_assume_teams_oversubscription = weak_odr hidden constant i32 0
+!THREAD-STATE-DEVICE-LLVM: @__omp_rtl_assume_threads_oversubscription = weak_odr hidden constant i32 0
+!THREAD-STATE-DEVICE-LLVM: @__omp_rtl_assume_no_thread_state = weak_odr hidden constant i32 1
+!THREAD-STATE-DEVICE-LLVM: @__omp_rtl_assume_no_nested_parallelism = weak_odr hidden constant i32 0
+
+!NEST-PAR-DEVICE-FIR: module attributes {{{.*}}, omp.is_device = true, omp.rtlmoduleflags = #omp.rtlmoduleflags<assume_no_nested_parallelism = true>}
+!NEST-PAR-DEVICE-LLVM: @__omp_rtl_debug_kind = weak_odr hidden constant i32 0
+!NEST-PAR-DEVICE-LLVM: @__omp_rtl_assume_teams_oversubscription = weak_odr hidden constant i32 0
+!NEST-PAR-DEVICE-LLVM: @__omp_rtl_assume_threads_oversubscription = weak_odr hidden constant i32 0
+!NEST-PAR-DEVICE-LLVM: @__omp_rtl_assume_no_thread_state = weak_odr hidden constant i32 0
+!NEST-PAR-DEVICE-LLVM: @__omp_rtl_assume_no_nested_parallelism = weak_odr hidden constant i32 1
+
+!ALL-DEVICE-FIR: module attributes {{{.*}}, omp.is_device = true, omp.rtlmoduleflags = #omp.rtlmoduleflags<debug_kind = 1, assume_teams_oversubscription = true, assume_threads_oversubscription = true, assume_no_thread_state = true, assume_no_nested_parallelism = true>}
+!ALL-DEVICE-LLVM: @__omp_rtl_debug_kind = weak_odr hidden constant i32 1
+!ALL-DEVICE-LLVM: @__omp_rtl_assume_teams_oversubscription = weak_odr hidden constant i32 1
+!ALL-DEVICE-LLVM: @__omp_rtl_assume_threads_oversubscription = weak_odr hidden constant i32 1
+!ALL-DEVICE-LLVM: @__omp_rtl_assume_no_thread_state = weak_odr hidden constant i32 1
+!ALL-DEVICE-LLVM: @__omp_rtl_assume_no_nested_parallelism = weak_odr hidden constant i32 1
+subroutine omp_subroutine()
+end subroutine omp_subroutine
Index: flang/test/Driver/driver-help.f90
===================================================================
--- flang/test/Driver/driver-help.f90
+++ flang/test/Driver/driver-help.f90
@@ -138,6 +138,7 @@
! HELP-FC1-NEXT: -fno-signed-zeros Allow optimizations that ignore the sign of floating point zeros
! HELP-FC1-NEXT: -fno-stack-arrays Allocate array temporaries on the heap (default)
! HELP-FC1-NEXT: -fopenacc Enable OpenACC
+! HELP-FC1-NEXT: -fopenmp-target-debug Enable debugging in the OpenMP offloading device RTL
! HELP-FC1-NEXT: -fopenmp Parse OpenMP pragmas and generate parallel code.
! HELP-FC1-NEXT: -fpass-plugin=<dsopath> Load pass plugin from a dynamic shared object file (only with new pass manager).
! HELP-FC1-NEXT: -freciprocal-math Allow division operations to be reassociated
Index: flang/lib/Frontend/FrontendActions.cpp
===================================================================
--- flang/lib/Frontend/FrontendActions.cpp
+++ flang/lib/Frontend/FrontendActions.cpp
@@ -177,6 +177,18 @@
// Fetch module from lb, so we can set
mlirModule = std::make_unique<mlir::ModuleOp>(lb.getModule());
+
+ if (ci.getInvocation().getFrontendOpts().features.IsEnabled(
+ Fortran::common::LanguageFeature::OpenMP)) {
+ if (ci.getInvocation().getLangOpts().OpenMPIsDevice)
+ mlir::omp::OpenMPDialect::setRTLFlags(
+ *mlirModule, ci.getInvocation().getLangOpts().OpenMPTargetDebug,
+ ci.getInvocation().getLangOpts().OpenMPTeamSubscription,
+ ci.getInvocation().getLangOpts().OpenMPThreadSubscription,
+ ci.getInvocation().getLangOpts().OpenMPNoThreadState,
+ ci.getInvocation().getLangOpts().OpenMPNoNestedParallelism);
+ }
+
setUpTargetMachine();
const llvm::DataLayout &dl = tm->createDataLayout();
setMLIRDataLayout(*mlirModule, dl);
Index: flang/lib/Frontend/CompilerInvocation.cpp
===================================================================
--- flang/lib/Frontend/CompilerInvocation.cpp
+++ flang/lib/Frontend/CompilerInvocation.cpp
@@ -670,6 +670,41 @@
if (args.hasArg(clang::driver::options::OPT_fopenmp)) {
res.getFrontendOpts().features.Enable(
Fortran::common::LanguageFeature::OpenMP);
+
+ if (args.hasArg(clang::driver::options::OPT_fopenmp_is_device)) {
+ if (args.hasFlag(
+ clang::driver::options::OPT_fopenmp_assume_teams_oversubscription,
+ clang::driver::options::
+ OPT_fno_openmp_assume_teams_oversubscription,
+ /*Default=*/false))
+ res.getLangOpts().OpenMPTeamSubscription = true;
+
+ if (args.hasArg(
+ clang::driver::options::OPT_fopenmp_assume_no_thread_state))
+ res.getLangOpts().OpenMPNoThreadState = 1;
+
+ if (args.hasArg(
+ clang::driver::options::OPT_fopenmp_assume_no_nested_parallelism))
+ res.getLangOpts().OpenMPNoNestedParallelism = 1;
+
+ if (args.hasFlag(clang::driver::options::
+ OPT_fopenmp_assume_threads_oversubscription,
+ clang::driver::options::
+ OPT_fno_openmp_assume_threads_oversubscription,
+ /*Default=*/false))
+ res.getLangOpts().OpenMPThreadSubscription = true;
+
+ if ((args.hasArg(clang::driver::options::OPT_fopenmp_target_debug) ||
+ args.hasArg(clang::driver::options::OPT_fopenmp_target_debug_EQ))) {
+ res.getLangOpts().OpenMPTargetDebug = getLastArgIntValue(
+ args, clang::driver::options::OPT_fopenmp_target_debug_EQ,
+ res.getLangOpts().OpenMPTargetDebug, diags);
+
+ if (!res.getLangOpts().OpenMPTargetDebug &&
+ args.hasArg(clang::driver::options::OPT_fopenmp_target_debug))
+ res.getLangOpts().OpenMPTargetDebug = 1;
+ }
+ }
}
// -pedantic
Index: flang/include/flang/Frontend/LangOptions.def
===================================================================
--- flang/include/flang/Frontend/LangOptions.def
+++ flang/include/flang/Frontend/LangOptions.def
@@ -34,6 +34,18 @@
LANGOPT(AssociativeMath, 1, false)
/// Allow division operations to be reassociated
LANGOPT(ReciprocalMath, 1, false)
+/// Enable debugging in the OpenMP offloading device RTL
+LANGOPT(OpenMPTargetDebug, 32, 0)
+/// Assume work-shared loops do not have more iterations than participating
+/// threads.
+LANGOPT(OpenMPThreadSubscription, 1, 0)
+/// Assume distributed loops do not have more iterations than participating
+/// teams.
+LANGOPT(OpenMPTeamSubscription, 1, 0)
+/// Assume that no thread in a parallel region will modify an ICV.
+LANGOPT(OpenMPNoThreadState, 1, 0)
+/// Assume that no thread in a parallel region will encounter a parallel region
+LANGOPT(OpenMPNoNestedParallelism, 1, 0)
#undef LANGOPT
#undef ENUM_LANGOPT
Index: clang/test/Driver/flang/flang-omp.f90
===================================================================
--- /dev/null
+++ clang/test/Driver/flang/flang-omp.f90
@@ -0,0 +1,29 @@
+! Check that flang -fc1 is invoked when in --driver-mode=flang
+! and the relevant openmp and openmp offload flags are utilised
+! and passed down correctly
+
+! Test -fopenmp with offload for RTL Flag Options
+! RUN: %clang --driver-mode=flang -### -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -fopenmp-assume-threads-oversubscription %s 2>&1 | FileCheck --check-prefixes=CHECK-THREADS-OVS %s
+! CHECK-THREADS-OVS: "{{[^"]*}}flang-new" "-fc1" {{.*}} "-fopenmp" {{.*}} "-fopenmp-is-device" "-fopenmp-assume-threads-oversubscription" {{.*}}.f90"
+
+! RUN: %clang --driver-mode=flang -### -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -fopenmp-assume-teams-oversubscription %s 2>&1 | FileCheck --check-prefixes=CHECK-TEAMS-OVS %s
+! CHECK-TEAMS-OVS: "{{[^"]*}}flang-new" "-fc1" {{.*}} "-fopenmp" {{.*}} "-fopenmp-is-device" "-fopenmp-assume-teams-oversubscription" {{.*}}.f90"
+
+! RUN: %clang --driver-mode=flang -### -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -fopenmp-assume-no-nested-parallelism %s 2>&1 | FileCheck --check-prefixes=CHECK-NEST-PAR %s
+! CHECK-NEST-PAR: "{{[^"]*}}flang-new" "-fc1" {{.*}} "-fopenmp" {{.*}} "-fopenmp-is-device" "-fopenmp-assume-no-nested-parallelism" {{.*}}.f90"
+
+! RUN: %clang --driver-mode=flang -### -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -fopenmp-assume-no-thread-state %s 2>&1 | FileCheck --check-prefixes=CHECK-THREAD-STATE %s
+! CHECK-THREAD-STATE: "{{[^"]*}}flang-new" "-fc1" {{.*}} "-fopenmp" {{.*}} "-fopenmp-is-device" "-fopenmp-assume-no-thread-state" {{.*}}.f90"
+
+! RUN: %clang --driver-mode=flang -### -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -fopenmp-target-debug %s 2>&1 | FileCheck --check-prefixes=CHECK-TARGET-DEBUG %s
+! CHECK-TARGET-DEBUG: "{{[^"]*}}flang-new" "-fc1" {{.*}} "-fopenmp" {{.*}} "-fopenmp-is-device" "-fopenmp-target-debug" {{.*}}.f90"
+
+! RUN: %clang --driver-mode=flang -### -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -fopenmp-target-debug=111 %s 2>&1 | FileCheck --check-prefixes=CHECK-TARGET-DEBUG-EQ %s
+! CHECK-TARGET-DEBUG-EQ: "{{[^"]*}}flang-new" "-fc1" {{.*}} "-fopenmp" {{.*}} "-fopenmp-is-device" "-fopenmp-target-debug=111" {{.*}}.f90"
+
+! RUN: %clang --driver-mode=flang -### -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -fopenmp-target-debug -fopenmp-assume-threads-oversubscription \
+! RUN: -fopenmp-assume-teams-oversubscription -fopenmp-assume-no-nested-parallelism -fopenmp-assume-no-thread-state \
+! RUN: %s 2>&1 | FileCheck --check-prefixes=CHECK-RTL-ALL %s
+! CHECK-RTL-ALL: "{{[^"]*}}flang-new" "-fc1" {{.*}} "-fopenmp" {{.*}} "-fopenmp-is-device" "-fopenmp-target-debug" "-fopenmp-assume-teams-oversubscription"
+! CHECK-RTL-ALL: "-fopenmp-assume-threads-oversubscription" "-fopenmp-assume-no-thread-state" "-fopenmp-assume-no-nested-parallelism"
+! CHECK-RTL-ALL: {{.*}}.f90"
\ No newline at end of file
Index: clang/lib/Driver/ToolChains/Flang.h
===================================================================
--- clang/lib/Driver/ToolChains/Flang.h
+++ clang/lib/Driver/ToolChains/Flang.h
@@ -56,6 +56,14 @@
void addTargetOptions(const llvm::opt::ArgList &Args,
llvm::opt::ArgStringList &CmdArgs) const;
+ /// Extract offload options from the driver arguments and add them to
+ /// the command arguments.
+ ///
+ /// \param [in] JA The job action
+ /// \param [out] CmdArgs The list of output command arguments
+ void addOffloadOptions(const JobAction &JA, const llvm::opt::ArgList &Args,
+ llvm::opt::ArgStringList &CmdArgs) const;
+
/// Extract other compilation options from the driver arguments and add them
/// to the command arguments.
///
Index: clang/lib/Driver/ToolChains/Flang.cpp
===================================================================
--- clang/lib/Driver/ToolChains/Flang.cpp
+++ clang/lib/Driver/ToolChains/Flang.cpp
@@ -114,6 +114,34 @@
// TODO: Add target specific flags, ABI, mtune option etc.
}
+void Flang::addOffloadOptions(const JobAction &JA, const ArgList &Args,
+ ArgStringList &CmdArgs) const {
+ bool IsOpenMPDevice = JA.isDeviceOffloading(Action::OFK_OpenMP);
+
+ if (IsOpenMPDevice) {
+ // When in OpenMP offloading mode, enable debugging on the device.
+ Args.AddAllArgs(CmdArgs, options::OPT_fopenmp_target_debug_EQ);
+ if (Args.hasFlag(options::OPT_fopenmp_target_debug,
+ options::OPT_fno_openmp_target_debug, /*Default=*/false))
+ CmdArgs.push_back("-fopenmp-target-debug");
+
+ // When in OpenMP offloading mode, forward assumptions information about
+ // thread and team counts in the device.
+ if (Args.hasFlag(options::OPT_fopenmp_assume_teams_oversubscription,
+ options::OPT_fno_openmp_assume_teams_oversubscription,
+ /*Default=*/false))
+ CmdArgs.push_back("-fopenmp-assume-teams-oversubscription");
+ if (Args.hasFlag(options::OPT_fopenmp_assume_threads_oversubscription,
+ options::OPT_fno_openmp_assume_threads_oversubscription,
+ /*Default=*/false))
+ CmdArgs.push_back("-fopenmp-assume-threads-oversubscription");
+ if (Args.hasArg(options::OPT_fopenmp_assume_no_thread_state))
+ CmdArgs.push_back("-fopenmp-assume-no-thread-state");
+ if (Args.hasArg(options::OPT_fopenmp_assume_no_nested_parallelism))
+ CmdArgs.push_back("-fopenmp-assume-no-nested-parallelism");
+ }
+}
+
static void addFloatingPointOptions(const Driver &D, const ArgList &Args,
ArgStringList &CmdArgs) {
StringRef FPContract;
@@ -311,6 +339,9 @@
// Add target args, features, etc.
addTargetOptions(Args, CmdArgs);
+ // Offloading related options
+ addOffloadOptions(JA, Args, CmdArgs);
+
// Add other compile options
addOtherOptions(Args, CmdArgs);
Index: clang/include/clang/Driver/Options.td
===================================================================
--- clang/include/clang/Driver/Options.td
+++ clang/include/clang/Driver/Options.td
@@ -2676,24 +2676,24 @@
Flags<[CC1Option, NoArgumentUnused, HelpHidden]>;
def fopenmp_cuda_teams_reduction_recs_num_EQ : Joined<["-"], "fopenmp-cuda-teams-reduction-recs-num=">, Group<f_Group>,
Flags<[CC1Option, NoArgumentUnused, HelpHidden]>;
-def fopenmp_target_debug : Flag<["-"], "fopenmp-target-debug">, Group<f_Group>, Flags<[CC1Option, NoArgumentUnused]>,
+def fopenmp_target_debug : Flag<["-"], "fopenmp-target-debug">, Group<f_Group>, Flags<[CC1Option, FC1Option, NoArgumentUnused]>,
HelpText<"Enable debugging in the OpenMP offloading device RTL">;
-def fno_openmp_target_debug : Flag<["-"], "fno-openmp-target-debug">, Group<f_Group>, Flags<[NoArgumentUnused]>;
-def fopenmp_target_debug_EQ : Joined<["-"], "fopenmp-target-debug=">, Group<f_Group>, Flags<[CC1Option, NoArgumentUnused, HelpHidden]>;
+def fno_openmp_target_debug : Flag<["-"], "fno-openmp-target-debug">, Group<f_Group>, Flags<[NoArgumentUnused, FC1Option]>;
+def fopenmp_target_debug_EQ : Joined<["-"], "fopenmp-target-debug=">, Group<f_Group>, Flags<[CC1Option, FC1Option, NoArgumentUnused, HelpHidden]>;
def fopenmp_assume_teams_oversubscription : Flag<["-"], "fopenmp-assume-teams-oversubscription">,
- Group<f_Group>, Flags<[CC1Option, NoArgumentUnused, HelpHidden]>;
+ Group<f_Group>, Flags<[CC1Option, FC1Option, NoArgumentUnused, HelpHidden]>;
def fopenmp_assume_threads_oversubscription : Flag<["-"], "fopenmp-assume-threads-oversubscription">,
- Group<f_Group>, Flags<[CC1Option, NoArgumentUnused, HelpHidden]>;
+ Group<f_Group>, Flags<[CC1Option, FC1Option, NoArgumentUnused, HelpHidden]>;
def fno_openmp_assume_teams_oversubscription : Flag<["-"], "fno-openmp-assume-teams-oversubscription">,
- Group<f_Group>, Flags<[CC1Option, NoArgumentUnused, HelpHidden]>;
+ Group<f_Group>, Flags<[CC1Option, FC1Option, NoArgumentUnused, HelpHidden]>;
def fno_openmp_assume_threads_oversubscription : Flag<["-"], "fno-openmp-assume-threads-oversubscription">,
- Group<f_Group>, Flags<[CC1Option, NoArgumentUnused, HelpHidden]>;
+ Group<f_Group>, Flags<[CC1Option, FC1Option, NoArgumentUnused, HelpHidden]>;
def fopenmp_assume_no_thread_state : Flag<["-"], "fopenmp-assume-no-thread-state">, Group<f_Group>,
- Flags<[CC1Option, NoArgumentUnused, HelpHidden]>,
+ Flags<[CC1Option, FC1Option, NoArgumentUnused, HelpHidden]>,
HelpText<"Assert no thread in a parallel region modifies an ICV">,
MarshallingInfoFlag<LangOpts<"OpenMPNoThreadState">>;
def fopenmp_assume_no_nested_parallelism : Flag<["-"], "fopenmp-assume-no-nested-parallelism">, Group<f_Group>,
- Flags<[CC1Option, NoArgumentUnused, HelpHidden]>,
+ Flags<[CC1Option, FC1Option, NoArgumentUnused, HelpHidden]>,
HelpText<"Assert no nested parallel regions in the GPU">,
MarshallingInfoFlag<LangOpts<"OpenMPNoNestedParallelism">>;
def fopenmp_offload_mandatory : Flag<["-"], "fopenmp-offload-mandatory">, Group<f_Group>,
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
