https://github.com/nicebert updated https://github.com/llvm/llvm-project/pull/178914
>From bf77711c128a74e835cf96287c7fa6974bd9baed Mon Sep 17 00:00:00 2001 From: Nicole Aschenbrenner <[email protected]> Date: Tue, 27 Jan 2026 09:54:06 -0600 Subject: [PATCH] [clang][OpenMP] Add -fopenmp-target-fast convenience flag Add meta-flag that implies multiple GPU runtime assumptions: - -fopenmp-assume-no-thread-state - -fopenmp-assume-no-nested-parallelism The flag is automatically enabled by -Ofast and can be explicitly disabled with -fno-openmp-target-fast. Individual implied flags can be selectively overridden while keeping others enabled. Testing: Added Driver/openmp-target-fast-flag.c to verify flag handling and implication logic. --- clang/include/clang/Options/Options.td | 11 ++++++ clang/lib/Driver/ToolChains/Clang.cpp | 42 ++++++++++++++++++++- clang/test/Driver/openmp-target-fast-flag.c | 39 +++++++++++++++++++ 3 files changed, 90 insertions(+), 2 deletions(-) create mode 100644 clang/test/Driver/openmp-target-fast-flag.c diff --git a/clang/include/clang/Options/Options.td b/clang/include/clang/Options/Options.td index 421208a812bbc..8ae1e9767b910 100644 --- a/clang/include/clang/Options/Options.td +++ b/clang/include/clang/Options/Options.td @@ -3986,9 +3986,13 @@ def fno_openmp_assume_threads_oversubscription : Flag<["-"], "fno-openmp-assume- def fopenmp_assume_no_thread_state : Flag<["-"], "fopenmp-assume-no-thread-state">, HelpText<"Assert no thread in a parallel region modifies an ICV">, MarshallingInfoFlag<LangOpts<"OpenMPNoThreadState">>; +def fno_openmp_assume_no_thread_state : Flag<["-"], "fno-openmp-assume-no-thread-state">, + HelpText<"Assert that a thread in a parallel region may modify an ICV">; def fopenmp_assume_no_nested_parallelism : Flag<["-"], "fopenmp-assume-no-nested-parallelism">, HelpText<"Assert no nested parallel regions in the GPU">, MarshallingInfoFlag<LangOpts<"OpenMPNoNestedParallelism">>; +def fno_openmp_assume_no_nested_parallelism : Flag<["-"], "fno-openmp-assume-no-nested-parallelism">, + HelpText<"Assert that a nested parallel region may be used in the GPU">; } // let Group = f_Group } // let Visibility = [ClangOption, CC1Option, FC1Option] @@ -4012,6 +4016,13 @@ def fopenmp_target_new_runtime : Flag<["-"], "fopenmp-target-new-runtime">, Group<f_Group>, Flags<[HelpHidden]>, Visibility<[ClangOption, CC1Option]>; def fno_openmp_target_new_runtime : Flag<["-"], "fno-openmp-target-new-runtime">, Group<f_Group>, Flags<[HelpHidden]>, Visibility<[ClangOption, CC1Option]>; +def fopenmp_target_fast : Flag<["-"], "fopenmp-target-fast">, + Group<f_Group>, Flags<[NoArgumentUnused, HelpHidden]>, + Visibility<[ClangOption, CC1Option]>, + HelpText<"Assert common GPU usage patterns to enable OpenMP runtime optimizations">; +def fno_openmp_target_fast : Flag<["-"], "fno-openmp-target-fast">, + Group<f_Group>, Flags<[NoArgumentUnused, HelpHidden]>, + Visibility<[ClangOption, CC1Option]>; defm openmp_optimistic_collapse : BoolFOption<"openmp-optimistic-collapse", LangOpts<"OpenMPOptimisticCollapse">, DefaultFalse, PosFlag<SetTrue, [], [ClangOption, CC1Option]>, diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp index 0293b04217673..33ec50b148cf9 100644 --- a/clang/lib/Driver/ToolChains/Clang.cpp +++ b/clang/lib/Driver/ToolChains/Clang.cpp @@ -6675,6 +6675,11 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA, options::OPT_fno_offload_via_llvm, false) && (JA.isDeviceOffloading(Action::OFK_None) || JA.isDeviceOffloading(Action::OFK_OpenMP))) { + + // Determine if target-fast optimizations should be enabled + bool TargetFastUsed = + Args.hasFlag(options::OPT_fopenmp_target_fast, + options::OPT_fno_openmp_target_fast, OFastEnabled); switch (D.getOpenMPRuntime(Args)) { case Driver::OMPRT_OMP: case Driver::OMPRT_IOMP5: @@ -6725,10 +6730,43 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA, 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)) + + // Handle -fopenmp-target-fast + if (Arg *A = Args.getLastArg(options::OPT_fopenmp_target_fast, + options::OPT_fno_openmp_target_fast)) { + if (A->getOption().matches(options::OPT_fopenmp_target_fast)) + CmdArgs.push_back("-fopenmp-target-fast"); + else + CmdArgs.push_back("-fno-openmp-target-fast"); + } else if (OFastEnabled) { + CmdArgs.push_back("-fopenmp-target-fast"); + } + + // Handle -fopenmp-assume-no-thread-state (implied by target-fast) + if (Arg *A = + Args.getLastArg(options::OPT_fopenmp_assume_no_thread_state, + options::OPT_fno_openmp_assume_no_thread_state)) { + if (A->getOption().matches(options::OPT_fopenmp_assume_no_thread_state)) + CmdArgs.push_back("-fopenmp-assume-no-thread-state"); + else + CmdArgs.push_back("-fno-openmp-assume-no-thread-state"); + } else if (TargetFastUsed) { CmdArgs.push_back("-fopenmp-assume-no-thread-state"); - if (Args.hasArg(options::OPT_fopenmp_assume_no_nested_parallelism)) + } + + // Handle -fopenmp-assume-no-nested-parallelism (implied by target-fast) + if (Arg *A = Args.getLastArg( + options::OPT_fopenmp_assume_no_nested_parallelism, + options::OPT_fno_openmp_assume_no_nested_parallelism)) { + if (A->getOption().matches( + options::OPT_fopenmp_assume_no_nested_parallelism)) + CmdArgs.push_back("-fopenmp-assume-no-nested-parallelism"); + else + CmdArgs.push_back("-fno-openmp-assume-no-nested-parallelism"); + } else if (TargetFastUsed) { CmdArgs.push_back("-fopenmp-assume-no-nested-parallelism"); + } + if (Args.hasArg(options::OPT_fopenmp_offload_mandatory)) CmdArgs.push_back("-fopenmp-offload-mandatory"); if (Args.hasArg(options::OPT_fopenmp_force_usm)) diff --git a/clang/test/Driver/openmp-target-fast-flag.c b/clang/test/Driver/openmp-target-fast-flag.c new file mode 100644 index 0000000000000..9ad849bf21ead --- /dev/null +++ b/clang/test/Driver/openmp-target-fast-flag.c @@ -0,0 +1,39 @@ +// REQUIRES: x86-registered-target, amdgpu-registered-target + +// RUN: %clang -### -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx90a -nogpulib %s -O0 2>&1 \ +// RUN: | FileCheck -check-prefixes=DefaultTFast,DefaultTState,DefaultNoNestParallel %s + +// RUN: %clang -### -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx90a -nogpulib -O0 -fopenmp-target-fast %s 2>&1 \ +// RUN: | FileCheck -check-prefixes=TFast,TState,NestParallel %s + +// RUN: %clang -### -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx90a -nogpulib -O3 %s 2>&1 \ +// RUN: | FileCheck -check-prefixes=O3,DefaultTFast,DefaultTState,DefaultNoNestParallel %s + +// RUN: %clang -### -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx90a -nogpulib -O3 -fno-openmp-target-fast %s 2>&1 \ +// RUN: | FileCheck -check-prefixes=O3,NoTFast,DefaultTState,DefaultNoNestParallel %s + +// RUN: %clang -### -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx90a -nogpulib -Ofast %s 2>&1 \ +// RUN: | FileCheck -check-prefixes=OFast,TFast,TState,NestParallel %s + +// RUN: %clang -### -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx90a -nogpulib -Ofast -fno-openmp-target-fast %s 2>&1 \ +// RUN: | FileCheck -check-prefixes=OFast,NoTFast,DefaultTState,DefaultNoNestParallel %s + +// RUN: %clang -### -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx90a -nogpulib -O0 -fno-openmp-target-fast -fopenmp-target-fast %s 2>&1 \ +// RUN: | FileCheck -check-prefixes=TFast,TState,NestParallel %s + +// O3: -O3 +// OFast: -Ofast + +// TFast: "-fopenmp-target-fast" +// TFast-NOT: "-fno-openmp-target-fast" +// NoTFast: "-fno-openmp-target-fast" +// NoTFast-NOT: "-fopenmp-target-fast" +// DefaultTFast-NOT: {{"-f(no-)?openmp-target-fast"}} + +// TState: "-fopenmp-assume-no-thread-state" +// TState-NOT: "-fno-openmp-assume-no-thread-state" +// DefaultTState-NOT: {{"-f(no-)?openmp-assume-no-thread-state"}} + +// NestParallel: "-fopenmp-assume-no-nested-parallelism" +// NestParallel-NOT: "-fno-openmp-assume-no-nested-parallelism" +// DefaultNoNestParallel-NOT: {{"-f(-no-)?openmp-assume-no-nested-parallelism"}} _______________________________________________ cfe-commits mailing list [email protected] https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
