https://github.com/anchuraj created https://github.com/llvm/llvm-project/pull/150860
Atomic Control Options are used to specify architectural characteristics to help lowering of atomic operations. The options used are: `-f[no-]atomic-remote-memory`, `-f[no-]atomic-fine-grained-memory`, `-f[no-]atomic-ignore-denormal-mode`. Legacy option `-m[no-]unsafe-fp-atomics` is aliased to `-f[no-]ignore-denormal-mode`. More details can be found in https://github.com/llvm/llvm-project/pull/102569. This PR implements the frontend support for these options with OpenMP atomic in flang. Backend changes are available in the draft PR: https://github.com/llvm/llvm-project/pull/143769 which will be raised after this merged. Original PR https://github.com/llvm/llvm-project/pull/143441 got reverted in https://github.com/llvm/llvm-project/pull/150504. `-triple amdgcn-amd-amdgpu` option is removed >From 05dbc02668f7b5c705a83da3f41aec4816a59c50 Mon Sep 17 00:00:00 2001 From: Anchu Rajendran <asudh...@amd.com> Date: Sun, 27 Jul 2025 19:15:30 -0500 Subject: [PATCH] [flang][MLIR][OpenMP][llvm]Atomic Control Support --- clang/include/clang/Driver/Options.td | 22 ++++---- flang/include/flang/Frontend/TargetOptions.h | 5 ++ .../Optimizer/Dialect/Support/FIRContext.h | 19 +++++++ flang/lib/Frontend/CompilerInvocation.cpp | 10 ++++ flang/lib/Lower/Bridge.cpp | 4 ++ flang/lib/Lower/OpenMP/Atomic.cpp | 9 +++- .../Optimizer/Dialect/Support/FIRContext.cpp | 51 +++++++++++++++++++ .../Lower/OpenMP/atomic-control-options.f90 | 37 ++++++++++++++ .../mlir/Dialect/OpenMP/OpenMPAttrDefs.td | 15 ++++++ mlir/include/mlir/Dialect/OpenMP/OpenMPOps.td | 8 +-- mlir/test/Dialect/OpenMP/ops.mlir | 10 +++- 11 files changed, 174 insertions(+), 16 deletions(-) create mode 100644 flang/test/Lower/OpenMP/atomic-control-options.f90 diff --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td index 916400efdb449..fa248381583cd 100644 --- a/clang/include/clang/Driver/Options.td +++ b/clang/include/clang/Driver/Options.td @@ -2320,21 +2320,21 @@ def fsymbol_partition_EQ : Joined<["-"], "fsymbol-partition=">, Group<f_Group>, defm atomic_remote_memory : BoolFOption<"atomic-remote-memory", LangOpts<"AtomicRemoteMemory">, DefaultFalse, - PosFlag<SetTrue, [], [ClangOption, CC1Option], "May have">, - NegFlag<SetFalse, [], [ClangOption], "Assume no">, - BothFlags<[], [ClangOption], " atomic operations on remote memory">>; + PosFlag<SetTrue, [], [ClangOption, CC1Option, FlangOption, FC1Option], "May have">, + NegFlag<SetFalse, [], [ClangOption, FlangOption], "Assume no">, + BothFlags<[], [ClangOption, FlangOption], " atomic operations on remote memory">>; defm atomic_fine_grained_memory : BoolFOption<"atomic-fine-grained-memory", LangOpts<"AtomicFineGrainedMemory">, DefaultFalse, - PosFlag<SetTrue, [], [ClangOption, CC1Option], "May have">, - NegFlag<SetFalse, [], [ClangOption], "Assume no">, - BothFlags<[], [ClangOption], " atomic operations on fine-grained memory">>; + PosFlag<SetTrue, [], [ClangOption, CC1Option, FlangOption, FC1Option], "May have">, + NegFlag<SetFalse, [], [ClangOption, FlangOption], "Assume no">, + BothFlags<[], [ClangOption, FlangOption], " atomic operations on fine-grained memory">>; defm atomic_ignore_denormal_mode : BoolFOption<"atomic-ignore-denormal-mode", LangOpts<"AtomicIgnoreDenormalMode">, DefaultFalse, - PosFlag<SetTrue, [], [ClangOption, CC1Option], "Allow">, - NegFlag<SetFalse, [], [ClangOption], "Disallow">, - BothFlags<[], [ClangOption], " atomic operations to ignore denormal mode">>; + PosFlag<SetTrue, [], [ClangOption, CC1Option, FlangOption, FC1Option], "Allow">, + NegFlag<SetFalse, [], [ClangOption, FlangOption], "Disallow">, + BothFlags<[], [ClangOption, FlangOption], " atomic operations to ignore denormal mode">>; defm memory_profile : OptInCC1FFlag<"memory-profile", "Enable", "Disable", " heap memory profiling">; def fmemory_profile_EQ : Joined<["-"], "fmemory-profile=">, @@ -5360,9 +5360,9 @@ defm amdgpu_precise_memory_op " precise memory mode (AMDGPU only)">; def munsafe_fp_atomics : Flag<["-"], "munsafe-fp-atomics">, - Visibility<[ClangOption, CC1Option]>, Alias<fatomic_ignore_denormal_mode>; + Visibility<[ClangOption, CC1Option, FlangOption, FC1Option]>, Alias<fatomic_ignore_denormal_mode>; def mno_unsafe_fp_atomics : Flag<["-"], "mno-unsafe-fp-atomics">, - Visibility<[ClangOption]>, Alias<fno_atomic_ignore_denormal_mode>; + Visibility<[ClangOption, FlangOption]>, Alias<fno_atomic_ignore_denormal_mode>; def faltivec : Flag<["-"], "faltivec">, Group<f_Group>; def fno_altivec : Flag<["-"], "fno-altivec">, Group<f_Group>; diff --git a/flang/include/flang/Frontend/TargetOptions.h b/flang/include/flang/Frontend/TargetOptions.h index 002d8d158abd4..f6e5634d5a995 100644 --- a/flang/include/flang/Frontend/TargetOptions.h +++ b/flang/include/flang/Frontend/TargetOptions.h @@ -53,6 +53,11 @@ class TargetOptions { /// Print verbose assembly bool asmVerbose = false; + + /// Atomic control options + bool atomicIgnoreDenormalMode = false; + bool atomicRemoteMemory = false; + bool atomicFineGrainedMemory = false; }; } // end namespace Fortran::frontend diff --git a/flang/include/flang/Optimizer/Dialect/Support/FIRContext.h b/flang/include/flang/Optimizer/Dialect/Support/FIRContext.h index 2df14f83c11e1..c0c0b744206cd 100644 --- a/flang/include/flang/Optimizer/Dialect/Support/FIRContext.h +++ b/flang/include/flang/Optimizer/Dialect/Support/FIRContext.h @@ -58,6 +58,25 @@ void setTargetCPU(mlir::ModuleOp mod, llvm::StringRef cpu); /// Get the target CPU string from the Module or return a null reference. llvm::StringRef getTargetCPU(mlir::ModuleOp mod); +/// Sets whether Denormal Mode can be ignored or not for lowering of floating +/// point atomic operations. +void setAtomicIgnoreDenormalMode(mlir::ModuleOp mod, bool value); +/// Gets whether Denormal Mode can be ignored or not for lowering of floating +/// point atomic operations. +bool getAtomicIgnoreDenormalMode(mlir::ModuleOp mod); +/// Sets whether fine grained memory can be used or not for lowering of atomic +/// operations. +void setAtomicFineGrainedMemory(mlir::ModuleOp mod, bool value); +/// Gets whether fine grained memory can be used or not for lowering of atomic +/// operations. +bool getAtomicFineGrainedMemory(mlir::ModuleOp mod); +/// Sets whether remote memory can be used or not for lowering of atomic +/// operations. +void setAtomicRemoteMemory(mlir::ModuleOp mod, bool value); +/// Gets whether remote memory can be used or not for lowering of atomic +/// operations. +bool getAtomicRemoteMemory(mlir::ModuleOp mod); + /// Set the tune CPU for the module. `cpu` must not be deallocated while /// module `mod` is still live. void setTuneCPU(mlir::ModuleOp mod, llvm::StringRef cpu); diff --git a/flang/lib/Frontend/CompilerInvocation.cpp b/flang/lib/Frontend/CompilerInvocation.cpp index f55d866435997..111c5aa48726f 100644 --- a/flang/lib/Frontend/CompilerInvocation.cpp +++ b/flang/lib/Frontend/CompilerInvocation.cpp @@ -512,6 +512,16 @@ static void parseTargetArgs(TargetOptions &opts, llvm::opt::ArgList &args) { args.getLastArg(clang::driver::options::OPT_triple)) opts.triple = a->getValue(); + opts.atomicIgnoreDenormalMode = args.hasFlag( + clang::driver::options::OPT_fatomic_ignore_denormal_mode, + clang::driver::options::OPT_fno_atomic_ignore_denormal_mode, false); + opts.atomicFineGrainedMemory = args.hasFlag( + clang::driver::options::OPT_fatomic_fine_grained_memory, + clang::driver::options::OPT_fno_atomic_fine_grained_memory, false); + opts.atomicRemoteMemory = + args.hasFlag(clang::driver::options::OPT_fatomic_remote_memory, + clang::driver::options::OPT_fno_atomic_remote_memory, false); + if (const llvm::opt::Arg *a = args.getLastArg(clang::driver::options::OPT_target_cpu)) opts.cpu = a->getValue(); diff --git a/flang/lib/Lower/Bridge.cpp b/flang/lib/Lower/Bridge.cpp index 92aae792248c5..ac3669c907fbc 100644 --- a/flang/lib/Lower/Bridge.cpp +++ b/flang/lib/Lower/Bridge.cpp @@ -6733,6 +6733,10 @@ Fortran::lower::LoweringBridge::LoweringBridge( fir::setKindMapping(*module, kindMap); fir::setTargetCPU(*module, targetMachine.getTargetCPU()); fir::setTuneCPU(*module, targetOpts.cpuToTuneFor); + fir::setAtomicIgnoreDenormalMode(*module, + targetOpts.atomicIgnoreDenormalMode); + fir::setAtomicFineGrainedMemory(*module, targetOpts.atomicFineGrainedMemory); + fir::setAtomicRemoteMemory(*module, targetOpts.atomicRemoteMemory); fir::setTargetFeatures(*module, targetMachine.getTargetFeatureString()); fir::support::setMLIRDataLayout(*module, targetMachine.createDataLayout()); fir::setIdent(*module, Fortran::common::getFlangFullVersion()); diff --git a/flang/lib/Lower/OpenMP/Atomic.cpp b/flang/lib/Lower/OpenMP/Atomic.cpp index 9a233d2d8cb08..d4f83f57bd5d4 100644 --- a/flang/lib/Lower/OpenMP/Atomic.cpp +++ b/flang/lib/Lower/OpenMP/Atomic.cpp @@ -635,9 +635,16 @@ genAtomicUpdate(lower::AbstractConverter &converter, } } + mlir::ModuleOp module = builder.getModule(); + mlir::omp::AtomicControlAttr atomicControlAttr = + mlir::omp::AtomicControlAttr::get( + builder.getContext(), fir::getAtomicIgnoreDenormalMode(module), + fir::getAtomicFineGrainedMemory(module), + fir::getAtomicRemoteMemory(module)); builder.restoreInsertionPoint(atomicAt); auto updateOp = mlir::omp::AtomicUpdateOp::create( - builder, loc, atomAddr, hint, makeMemOrderAttr(converter, memOrder)); + builder, loc, atomAddr, atomicControlAttr, hint, + makeMemOrderAttr(converter, memOrder)); mlir::Region ®ion = updateOp->getRegion(0); mlir::Block *block = builder.createBlock(®ion, {}, {atomType}, {loc}); diff --git a/flang/lib/Optimizer/Dialect/Support/FIRContext.cpp b/flang/lib/Optimizer/Dialect/Support/FIRContext.cpp index 01c0be66d1ecc..c2e0afe122b4e 100644 --- a/flang/lib/Optimizer/Dialect/Support/FIRContext.cpp +++ b/flang/lib/Optimizer/Dialect/Support/FIRContext.cpp @@ -88,6 +88,57 @@ void fir::setTuneCPU(mlir::ModuleOp mod, llvm::StringRef cpu) { mod->setAttr(tuneCpuName, mlir::StringAttr::get(ctx, cpu)); } +static constexpr const char *atomicIgnoreDenormalModeName = + "fir.atomic_ignore_denormal_mode"; + +void fir::setAtomicIgnoreDenormalMode(mlir::ModuleOp mod, bool value) { + if (value) { + auto *ctx = mod.getContext(); + mod->setAttr(atomicIgnoreDenormalModeName, mlir::UnitAttr::get(ctx)); + } else { + if (mod->hasAttr(atomicIgnoreDenormalModeName)) + mod->removeAttr(atomicIgnoreDenormalModeName); + } +} + +bool fir::getAtomicIgnoreDenormalMode(mlir::ModuleOp mod) { + return mod->hasAttr(atomicIgnoreDenormalModeName); +} + +static constexpr const char *atomicFineGrainedMemoryName = + "fir.atomic_fine_grained_memory"; + +void fir::setAtomicFineGrainedMemory(mlir::ModuleOp mod, bool value) { + if (value) { + auto *ctx = mod.getContext(); + mod->setAttr(atomicFineGrainedMemoryName, mlir::UnitAttr::get(ctx)); + } else { + if (mod->hasAttr(atomicFineGrainedMemoryName)) + mod->removeAttr(atomicFineGrainedMemoryName); + } +} + +bool fir::getAtomicFineGrainedMemory(mlir::ModuleOp mod) { + return mod->hasAttr(atomicFineGrainedMemoryName); +} + +static constexpr const char *atomicRemoteMemoryName = + "fir.atomic_remote_memory"; + +void fir::setAtomicRemoteMemory(mlir::ModuleOp mod, bool value) { + if (value) { + auto *ctx = mod.getContext(); + mod->setAttr(atomicRemoteMemoryName, mlir::UnitAttr::get(ctx)); + } else { + if (mod->hasAttr(atomicRemoteMemoryName)) + mod->removeAttr(atomicRemoteMemoryName); + } +} + +bool fir::getAtomicRemoteMemory(mlir::ModuleOp mod) { + return mod->hasAttr(atomicRemoteMemoryName); +} + llvm::StringRef fir::getTuneCPU(mlir::ModuleOp mod) { if (auto attr = mod->getAttrOfType<mlir::StringAttr>(tuneCpuName)) return attr.getValue(); diff --git a/flang/test/Lower/OpenMP/atomic-control-options.f90 b/flang/test/Lower/OpenMP/atomic-control-options.f90 new file mode 100644 index 0000000000000..407f83b856eec --- /dev/null +++ b/flang/test/Lower/OpenMP/atomic-control-options.f90 @@ -0,0 +1,37 @@ +! RUN: %flang_fc1 -emit-hlfir -fopenmp -fopenmp-is-device -munsafe-fp-atomics %s -o - | FileCheck -check-prefix=UNSAFE-FP-ATOMICS %s +! RUN: %flang_fc1 -emit-hlfir -fopenmp -fopenmp-is-device -fatomic-ignore-denormal-mode %s -o - | FileCheck -check-prefix=IGNORE-DENORMAL %s +! RUN: %flang_fc1 -emit-hlfir -fopenmp -fopenmp-is-device -fatomic-fine-grained-memory %s -o - | FileCheck -check-prefix=FINE-GRAINED-MEMORY %s +! RUN: %flang_fc1 -emit-hlfir -fopenmp -fopenmp-is-device -fatomic-remote-memory %s -o - | FileCheck -check-prefix=REMOTE-MEMORY %s +program test + implicit none + integer :: A, B, threads + threads = 128 + A = 0 + B = 0 + !UNSAFE-FP-ATOMICS: omp.atomic.update %{{.*}} : !fir.ref<i32> { + !UNSAFE-FP-ATOMICS: } {atomic_control = #omp.atomic_control<ignore_denormal_mode = true>} + !IGNORE-DENORMAL: omp.atomic.update %{{.*}} : !fir.ref<i32> { + !IGNORE-DENORMAL: } {atomic_control = #omp.atomic_control<ignore_denormal_mode = true>} + !FINE-GRAINED-MEMORY: omp.atomic.update %{{.*}} : !fir.ref<i32> { + !FINE-GRAINED-MEMORY: } {atomic_control = #omp.atomic_control<fine_grained_memory = true>} + !REMOTE-MEMORY: omp.atomic.update %{{.*}} : !fir.ref<i32> { + !REMOTE-MEMORY: } {atomic_control = #omp.atomic_control<remote_memory = true>} + !$omp target parallel num_threads(threads) + !$omp atomic + A = A + 1 + !$omp end target parallel + !UNSAFE-FP-ATOMICS: omp.atomic.update %{{.*}} : !fir.ref<i32> { + !UNSAFE-FP-ATOMICS: } {atomic_control = #omp.atomic_control<ignore_denormal_mode = true>} + !IGNORE-DENORMAL: omp.atomic.update %{{.*}} : !fir.ref<i32> { + !IGNORE-DENORMAL: } {atomic_control = #omp.atomic_control<ignore_denormal_mode = true>} + !FINE-GRAINED-MEMORY: omp.atomic.update %{{.*}} : !fir.ref<i32> { + !FINE-GRAINED-MEMORY: } {atomic_control = #omp.atomic_control<fine_grained_memory = true>} + !REMOTE-MEMORY: omp.atomic.update %{{.*}} : !fir.ref<i32> { + !REMOTE-MEMORY: } {atomic_control = #omp.atomic_control<remote_memory = true>} + !$omp target parallel num_threads(threads) + !$omp atomic capture + A = A + B + B = A + !$omp end atomic + !$omp end target parallel +end program test diff --git a/mlir/include/mlir/Dialect/OpenMP/OpenMPAttrDefs.td b/mlir/include/mlir/Dialect/OpenMP/OpenMPAttrDefs.td index 704d0b2220e8a..72ce4c6a21cb3 100644 --- a/mlir/include/mlir/Dialect/OpenMP/OpenMPAttrDefs.td +++ b/mlir/include/mlir/Dialect/OpenMP/OpenMPAttrDefs.td @@ -22,6 +22,21 @@ class OpenMP_Attr<string name, string attrMnemonic, list<Trait> traits = [], let mnemonic = attrMnemonic; } +//===----------------------------------------------------------------------===// +// AtomicControlAttr +//===----------------------------------------------------------------------===// + +// Atomic control attributes hold information about architectural +// characteristics which are required for lowering atomic operations. +def AtomicControlAttr : OpenMP_Attr<"AtomicControl", "atomic_control"> { + let parameters = + (ins DefaultValuedParameter<"bool", "false">:$ignore_denormal_mode, + DefaultValuedParameter<"bool", "false">:$fine_grained_memory, + DefaultValuedParameter<"bool", "false">:$remote_memory); + + let assemblyFormat = "`<` struct(params) `>`"; +} + //===----------------------------------------------------------------------===// // DeclareTargetAttr //===----------------------------------------------------------------------===// diff --git a/mlir/include/mlir/Dialect/OpenMP/OpenMPOps.td b/mlir/include/mlir/Dialect/OpenMP/OpenMPOps.td index 8cf18b43450ab..be114ea4fb631 100644 --- a/mlir/include/mlir/Dialect/OpenMP/OpenMPOps.td +++ b/mlir/include/mlir/Dialect/OpenMP/OpenMPOps.td @@ -1750,9 +1750,11 @@ def AtomicUpdateOp : OpenMP_Op<"atomic.update", traits = [ operations. }] # clausesDescription; - let arguments = !con((ins Arg<OpenMP_PointerLikeType, - "Address of variable to be updated", - [MemRead, MemWrite]>:$x), clausesArgs); + let arguments = !con( + (ins Arg<OpenMP_PointerLikeType, + "Address of variable to be updated", [MemRead, MemWrite]>:$x, + OptionalAttr<AtomicControlAttr>:$atomic_control), + clausesArgs); // Override region definition. let regions = (region SizedRegion<1>:$region); diff --git a/mlir/test/Dialect/OpenMP/ops.mlir b/mlir/test/Dialect/OpenMP/ops.mlir index 4c50ed3230976..8c846cde1a3ca 100644 --- a/mlir/test/Dialect/OpenMP/ops.mlir +++ b/mlir/test/Dialect/OpenMP/ops.mlir @@ -1406,7 +1406,7 @@ func.func @omp_atomic_update(%x : memref<i32>, %expr : i32, %xBool : memref<i1>, // CHECK-NEXT: (%[[XVAL:.*]]: i1): // CHECK-NEXT: %[[NEWVAL:.*]] = llvm.icmp "eq" %[[XVAL]], %[[EXPRBOOL]] : i1 // CHECK-NEXT: omp.yield(%[[NEWVAL]] : i1) - // } + // CHECK-NEXT: } omp.atomic.update %xBool : memref<i1> { ^bb0(%xval: i1): %newval = llvm.icmp "eq" %xval, %exprBool : i1 @@ -1562,6 +1562,14 @@ func.func @omp_atomic_update(%x : memref<i32>, %expr : i32, %xBool : memref<i1>, omp.yield(%newval : i32) } + // CHECK: omp.atomic.update %[[X]] : memref<i32> { + // CHECK-NEXT: (%[[XVAL:.*]]: i32): + // CHECK-NEXT: omp.yield(%{{.+}} : i32) + // CHECK-NEXT: } {atomic_control = #omp.atomic_control<ignore_denormal_mode = true, fine_grained_memory = true, remote_memory = true>} + omp.atomic.update %x : memref<i32> { + ^bb0(%xval:i32): + omp.yield(%const:i32) + } {atomic_control = #omp.atomic_control<ignore_denormal_mode = true, fine_grained_memory = true, remote_memory = true>} return } _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
