https://github.com/tblah created https://github.com/llvm/llvm-project/pull/73111
Enable by default when optimizing for speed. For simplicity, only forward the flag to the frontend driver when it contradicts what is implied by the optimization level. Since https://github.com/llvm/llvm-project/pull/72903 there are now no known performance regressions. Original PR was https://github.com/llvm/llvm-project/pull/68597 >From 6000017d6d23b2f861cd6dceb82f54a2685059b6 Mon Sep 17 00:00:00 2001 From: Tom Eccles <tom.ecc...@arm.com> Date: Thu, 14 Sep 2023 09:09:29 +0000 Subject: [PATCH] [flang] Enable alias tags pass by default Enable by default when optimizing for speed. For simplicity, only forward the flag to the frontend driver when it contradicts what is implied by the optimization level. --- clang/lib/Driver/ToolChains/Flang.cpp | 20 ++++++++++++++++++++ flang/include/flang/Tools/CLOptions.inc | 8 ++++---- flang/lib/Frontend/CompilerInvocation.cpp | 22 ++++++++++++++++++---- flang/test/Driver/falias-analysis.f90 | 4 ++++ flang/test/Driver/mlir-pass-pipeline.f90 | 2 ++ flang/test/Driver/optimization-remark.f90 | 22 +++++++++------------- flang/test/Fir/basic-program.fir | 4 ++++ flang/tools/tco/tco.cpp | 1 + 8 files changed, 62 insertions(+), 21 deletions(-) diff --git a/clang/lib/Driver/ToolChains/Flang.cpp b/clang/lib/Driver/ToolChains/Flang.cpp index 8bdd920c3dcbb796..9382433b94dadfd4 100644 --- a/clang/lib/Driver/ToolChains/Flang.cpp +++ b/clang/lib/Driver/ToolChains/Flang.cpp @@ -142,6 +142,26 @@ void Flang::addCodegenOptions(const ArgList &Args, if (shouldLoopVersion(Args)) CmdArgs.push_back("-fversion-loops-for-stride"); + Arg *aliasAnalysis = Args.getLastArg(options::OPT_falias_analysis, + options::OPT_fno_alias_analysis); + Arg *optLevel = + Args.getLastArg(options::OPT_Ofast, options::OPT_O, options::OPT_O4); + if (aliasAnalysis) { + bool falias_analysis = + aliasAnalysis->getOption().matches(options::OPT_falias_analysis); + // only pass on the argument if it does not match that implied by the + // optimization level + if (optLevel) { + if (!falias_analysis) { + CmdArgs.push_back("-fno-alias-analysis"); + } + } else { + if (falias_analysis) + // requested alias analysis but no optimization enabled + CmdArgs.push_back("-falias-analysis"); + } + } + Args.addAllArgs(CmdArgs, {options::OPT_flang_experimental_hlfir, options::OPT_flang_deprecated_no_hlfir, options::OPT_flang_experimental_polymorphism, diff --git a/flang/include/flang/Tools/CLOptions.inc b/flang/include/flang/Tools/CLOptions.inc index c452c023b4a80ce1..5a17385fb3dae87a 100644 --- a/flang/include/flang/Tools/CLOptions.inc +++ b/flang/include/flang/Tools/CLOptions.inc @@ -157,11 +157,11 @@ inline void addDebugFoundationPass(mlir::PassManager &pm) { [&]() { return fir::createAddDebugFoundationPass(); }); } -inline void addFIRToLLVMPass( - mlir::PassManager &pm, llvm::OptimizationLevel optLevel = defaultOptLevel) { +inline void addFIRToLLVMPass(mlir::PassManager &pm, + llvm::OptimizationLevel optLevel = defaultOptLevel, bool applyTbaa = true) { fir::FIRToLLVMPassOptions options; options.ignoreMissingTypeDescriptors = ignoreMissingTypeDescriptors; - options.applyTBAA = optLevel.isOptimizingForSpeed(); + options.applyTBAA = applyTbaa; options.forceUnifiedTBAATree = useOldAliasTags; addPassConditionally(pm, disableFirToLlvmIr, [&]() { return fir::createFIRToLLVMPass(options); }); @@ -311,7 +311,7 @@ inline void createDefaultFIRCodeGenPassPipeline( if (config.VScaleMin != 0) pm.addPass(fir::createVScaleAttrPass({config.VScaleMin, config.VScaleMax})); - fir::addFIRToLLVMPass(pm, config.OptLevel); + fir::addFIRToLLVMPass(pm, config.OptLevel, config.AliasAnalysis); } /// Create a pass pipeline for lowering from MLIR to LLVM IR diff --git a/flang/lib/Frontend/CompilerInvocation.cpp b/flang/lib/Frontend/CompilerInvocation.cpp index cb4f2d6a6225205b..cfb1dd91ead30564 100644 --- a/flang/lib/Frontend/CompilerInvocation.cpp +++ b/flang/lib/Frontend/CompilerInvocation.cpp @@ -242,10 +242,24 @@ static void parseCodeGenArgs(Fortran::frontend::CodeGenOptions &opts, clang::driver::options::OPT_fno_loop_versioning, false)) opts.LoopVersioning = 1; - opts.AliasAnalysis = - args.hasFlag(clang::driver::options::OPT_falias_analysis, - clang::driver::options::OPT_fno_alias_analysis, - /*default=*/false); + bool aliasAnalysis = false; + bool noAliasAnalysis = false; + if (auto *arg = + args.getLastArg(clang::driver::options::OPT_falias_analysis, + clang::driver::options::OPT_fno_alias_analysis)) { + if (arg->getOption().matches(clang::driver::options::OPT_falias_analysis)) + aliasAnalysis = true; + else + noAliasAnalysis = true; + } + opts.AliasAnalysis = 0; + if (opts.OptimizationLevel > 0) { + if (!noAliasAnalysis) + opts.AliasAnalysis = 1; + } else { + if (aliasAnalysis) + opts.AliasAnalysis = 1; + } for (auto *a : args.filtered(clang::driver::options::OPT_fpass_plugin_EQ)) opts.LLVMPassPlugins.push_back(a->getValue()); diff --git a/flang/test/Driver/falias-analysis.f90 b/flang/test/Driver/falias-analysis.f90 index f2c5dbde6d2c878c..1c74276974d47204 100644 --- a/flang/test/Driver/falias-analysis.f90 +++ b/flang/test/Driver/falias-analysis.f90 @@ -4,10 +4,14 @@ ! RUN: %flang -c -emit-llvm -falias-analysis %s -o - | llvm-dis | FileCheck %s --check-prefix=CHECK-AA --check-prefix=CHECK-ALL ! RUN: %flang -c -emit-llvm -falias-analysis -fno-alias-analysis %s -o - | llvm-dis | FileCheck %s --check-prefix=CHECK-NOAA --check-prefix=CHECK-ALL ! RUN: %flang -c -emit-llvm %s -o - | llvm-dis | FileCheck %s --check-prefix=CHECK-NOAA --check-prefix=CHECK-ALL +! RUN: %flang -c -emit-llvm -Ofast %s -o - | llvm-dis | FileCheck %s --check-prefix=CHECK-AA --check-prefix=CHECK-ALL +! RUN: %flang -c -emit-llvm -Ofast -fno-alias-analysis %s -o - | llvm-dis | FileCheck %s --check-prefix=CHECK-NOAA --check-prefix=CHECK-ALL ! RUN: %flang -fc1 -emit-llvm -falias-analysis %s -o - | FileCheck %s --check-prefix=CHECK-AA --check-prefix=CHECK-ALL ! RUN: %flang -fc1 -emit-llvm -falias-analysis -fno-alias-analysis %s -o - | FileCheck %s --check-prefix=CHECK-NOAA --check-prefix=CHECK-ALL ! RUN: %flang -fc1 -emit-llvm %s -o - | FileCheck %s --check-prefix=CHECK-NOAA --check-prefix=CHECK-ALL +! RUN: %flang -fc1 -emit-llvm -O3 %s -o - | FileCheck %s --check-prefix=CHECK-AA --check-prefix=CHECK-ALL +! RUN: %flang -fc1 -emit-llvm -O3 -fno-alias-analysis %s -o - | FileCheck %s --check-prefix=CHECK-NOAA --check-prefix=CHECK-ALL subroutine simple(a) integer, intent(inout) :: a(:) diff --git a/flang/test/Driver/mlir-pass-pipeline.f90 b/flang/test/Driver/mlir-pass-pipeline.f90 index 7f92ec25bef98ec7..3d8c42f123e2eb06 100644 --- a/flang/test/Driver/mlir-pass-pipeline.f90 +++ b/flang/test/Driver/mlir-pass-pipeline.f90 @@ -51,6 +51,8 @@ ! ALL-NEXT: 'func.func' Pipeline ! ALL-NEXT: PolymorphicOpConversion +! O2-NEXT: AddAliasTags +! O2-NEXT: 'func.func' Pipeline ! ALL-NEXT: CFGConversion ! ALL-NEXT: SCFToControlFlow diff --git a/flang/test/Driver/optimization-remark.f90 b/flang/test/Driver/optimization-remark.f90 index 13fc24346eac68b8..20ff9eb59a6702d6 100644 --- a/flang/test/Driver/optimization-remark.f90 +++ b/flang/test/Driver/optimization-remark.f90 @@ -41,28 +41,24 @@ ! Once we start filtering, this is reduced to 1 one of the loop passes. ! PASS-REGEX-LOOP-ONLY-NOT: optimization-remark.f90:77:7: remark: hoisting load [-Rpass=licm] -! PASS-REGEX-LOOP-ONLY: optimization-remark.f90:83:5: remark: Loop deleted because it is invariant [-Rpass=loop-delete] +! PASS-REGEX-LOOP-ONLY: optimization-remark.f90:79:5: remark: Loop deleted because it is invariant [-Rpass=loop-delete] ! MISSED-REGEX-LOOP-ONLY-NOT: optimization-remark.f90:77:7: remark: failed to hoist load with loop-invariant address because load is conditionally executed [-Rpass-missed=licm] -! MISSED-REGEX-LOOP-ONLY: optimization-remark.f90:76:4: remark: loop not vectorized [-Rpass-missed=loop-vectorize] +! MISSED-REGEX-LOOP-ONLY: optimization-remark.f90:72:4: remark: loop not vectorized [-Rpass-missed=loop-vectorize] -! ANALYSIS-REGEX-LOOP-ONLY: optimization-remark.f90:79:7: remark: loop not vectorized: unsafe dependent memory operations in loop. Use #pragma clang loop distribute(enable) to allow loop distribution to attempt to isolate the offending operations into a separate loop -! ANALYSIS-REGEX-LOOP-ONLY: Unknown data dependence. Memory location is the same as accessed at optimization-remark.f90:78:7 [-Rpass-analysis=loop-vectorize] +! ANALYSIS-REGEX-LOOP-ONLY: optimization-remark.f90:73:7: remark: loop not vectorized: cannot identify array bounds [-Rpass-analysis=loop-vectorize] ! ANALYSIS-REGEX-LOOP-ONLY-NOT: remark: {{.*}}: IR instruction count changed from {{[0-9]+}} to {{[0-9]+}}; Delta: {{-?[0-9]+}} [-Rpass-analysis=size-info] -! PASS: optimization-remark.f90:77:7: remark: hoisting load [-Rpass=licm] -! PASS: optimization-remark.f90:83:5: remark: Loop deleted because it is invariant [-Rpass=loop-delete] +! PASS: optimization-remark.f90:79:5: remark: Loop deleted because it is invariant [-Rpass=loop-delete] -! MISSED: optimization-remark.f90:77:7: remark: failed to hoist load with loop-invariant address because load is conditionally executed [-Rpass-missed=licm] -! MISSED: optimization-remark.f90:76:4: remark: loop not vectorized [-Rpass-missed=loop-vectorize] -! MISSED-NOT: optimization-remark.f90:79:7: remark: loop not vectorized: unsafe dependent memory operations in loop. Use #pragma clang loop distribute(enable) to allow loop distribution to attempt to isolate the offending operations into a separate loop +! MISSED: optimization-remark.f90:73:7: remark: failed to move load with loop-invariant address because the loop may invalidate its value [-Rpass-missed=licm] +! MISSED: optimization-remark.f90:72:4: remark: loop not vectorized [-Rpass-missed=loop-vectorize] +! MISSED-NOT: optimization-remark.f90:75:7: remark: loop not vectorized: unsafe dependent memory operations in loop. Use #pragma clang loop distribute(enable) to allow loop distribution to attempt to isolate the offending operations into a separate loop ! MISSED-NOT: Unknown data dependence. Memory location is the same as accessed at optimization-remark.f90:78:7 [-Rpass-analysis=loop-vectorize] -! ANALYSIS: optimization-remark.f90:79:7: remark: loop not vectorized: unsafe dependent memory operations in loop. Use #pragma clang loop distribute(enable) to allow loop distribution to attempt to isolate the offending operations into a separate loop -! ANALYSIS: Unknown data dependence. Memory location is the same as accessed at optimization-remark.f90:78:7 [-Rpass-analysis=loop-vectorize] -! ANALYSIS: remark: {{.*}}: IR instruction count changed from {{[0-9]+}} to {{[0-9]+}}; Delta: {{-?[0-9]+}} [-Rpass-analysis=size-info] -! ANALYSIS-NOT: optimization-remark.f90:77:7: remark: failed to hoist load with loop-invariant address because load is conditionally executed [-Rpass-missed=licm] +! ANALYSIS: optimization-remark.f90:74:7: remark: loop not vectorized: unsafe dependent memory operations in loop. +! ANALYSIS: remark: {{.*}} instructions in function [-Rpass-analysis=asm-printer] subroutine swap_real(a1, a2) implicit none diff --git a/flang/test/Fir/basic-program.fir b/flang/test/Fir/basic-program.fir index 0e82f7dfdedb447d..d8a9e74c318ce186 100644 --- a/flang/test/Fir/basic-program.fir +++ b/flang/test/Fir/basic-program.fir @@ -57,6 +57,10 @@ func.func @_QQmain() { // PASSES-NEXT: 'func.func' Pipeline // PASSES-NEXT: PolymorphicOpConversion + +// PASSES-NEXT: AddAliasTags + +// PASSES-NEXT: 'func.func' Pipeline // PASSES-NEXT: CFGConversion // PASSES-NEXT: SCFToControlFlow diff --git a/flang/tools/tco/tco.cpp b/flang/tools/tco/tco.cpp index 31d6bac142dc421b..a649535a39b74b31 100644 --- a/flang/tools/tco/tco.cpp +++ b/flang/tools/tco/tco.cpp @@ -120,6 +120,7 @@ compileFIR(const mlir::PassPipelineCLParser &passPipeline) { return mlir::failure(); } else { MLIRToLLVMPassPipelineConfig config(llvm::OptimizationLevel::O2); + config.AliasAnalysis = true; // enabled when optimizing for speed if (codeGenLLVM) { // Run only CodeGen passes. fir::createDefaultFIRCodeGenPassPipeline(pm, config); _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
