https://github.com/fanju110 updated
https://github.com/llvm/llvm-project/pull/136098
>From 9494c9752400e4708dbc8b6a5ca4993ea9565e95 Mon Sep 17 00:00:00 2001
From: fanyikang <fanju...@163.com>
Date: Thu, 17 Apr 2025 15:17:07 +0800
Subject: [PATCH 1/2] Add support for IR PGO
(-fprofile-generate/-fprofile-use=<dir>/file)
This patch implements IR-based Profile-Guided Optimization support in Flang
through the following flags:
-fprofile-generate for instrumentation-based profile generation
-fprofile-use=<dir>/file for profile-guided optimization
Co-Authored-By: ict-ql <168183727+ict...@users.noreply.github.com>
---
clang/include/clang/Driver/Options.td | 4 +-
clang/lib/Driver/ToolChains/Flang.cpp | 8 +++
.../include/flang/Frontend/CodeGenOptions.def | 5 ++
flang/include/flang/Frontend/CodeGenOptions.h | 49 +++++++++++++++++
flang/lib/Frontend/CompilerInvocation.cpp | 12 +++++
flang/lib/Frontend/FrontendActions.cpp | 54 +++++++++++++++++++
flang/test/Driver/flang-f-opts.f90 | 5 ++
.../Inputs/gcc-flag-compatibility_IR.proftext | 19 +++++++
.../gcc-flag-compatibility_IR_entry.proftext | 14 +++++
flang/test/Profile/gcc-flag-compatibility.f90 | 39 ++++++++++++++
10 files changed, 207 insertions(+), 2 deletions(-)
create mode 100644 flang/test/Profile/Inputs/gcc-flag-compatibility_IR.proftext
create mode 100644
flang/test/Profile/Inputs/gcc-flag-compatibility_IR_entry.proftext
create mode 100644 flang/test/Profile/gcc-flag-compatibility.f90
diff --git a/clang/include/clang/Driver/Options.td
b/clang/include/clang/Driver/Options.td
index affc076a876ad..0b0dbc467c1e0 100644
--- a/clang/include/clang/Driver/Options.td
+++ b/clang/include/clang/Driver/Options.td
@@ -1756,7 +1756,7 @@ def fmcdc_max_test_vectors_EQ : Joined<["-"],
"fmcdc-max-test-vectors=">,
HelpText<"Maximum number of test vectors in MC/DC coverage">,
MarshallingInfoInt<CodeGenOpts<"MCDCMaxTVs">, "0x7FFFFFFE">;
def fprofile_generate : Flag<["-"], "fprofile-generate">,
- Group<f_Group>, Visibility<[ClangOption, CLOption]>,
+ Group<f_Group>, Visibility<[ClangOption, CLOption, FlangOption,
FC1Option]>,
HelpText<"Generate instrumented code to collect execution counts into
default.profraw (overridden by LLVM_PROFILE_FILE env var)">;
def fprofile_generate_EQ : Joined<["-"], "fprofile-generate=">,
Group<f_Group>, Visibility<[ClangOption, CLOption]>,
@@ -1773,7 +1773,7 @@ def fprofile_use : Flag<["-"], "fprofile-use">,
Group<f_Group>,
Visibility<[ClangOption, CLOption]>, Alias<fprofile_instr_use>;
def fprofile_use_EQ : Joined<["-"], "fprofile-use=">,
Group<f_Group>,
- Visibility<[ClangOption, CLOption]>,
+ Visibility<[ClangOption, CLOption, FlangOption, FC1Option]>,
MetaVarName<"<pathname>">,
HelpText<"Use instrumentation data for profile-guided optimization. If
pathname is a directory, it reads from <pathname>/default.profdata. Otherwise,
it reads from file <pathname>.">;
def fno_profile_instr_generate : Flag<["-"], "fno-profile-instr-generate">,
diff --git a/clang/lib/Driver/ToolChains/Flang.cpp
b/clang/lib/Driver/ToolChains/Flang.cpp
index a8b4688aed09c..fcdbe8a6aba5a 100644
--- a/clang/lib/Driver/ToolChains/Flang.cpp
+++ b/clang/lib/Driver/ToolChains/Flang.cpp
@@ -882,6 +882,14 @@ void Flang::ConstructJob(Compilation &C, const JobAction
&JA,
// TODO: Handle interactions between -w, -pedantic, -Wall, -WOption
Args.AddLastArg(CmdArgs, options::OPT_w);
+
+ if (Args.hasArg(options::OPT_fprofile_generate)){
+ CmdArgs.push_back("-fprofile-generate");
+ }
+ if (const Arg *A = Args.getLastArg(options::OPT_fprofile_use_EQ)) {
+ CmdArgs.push_back(Args.MakeArgString(std::string("-fprofile-use=") +
A->getValue()));
+ }
+
// Forward flags for OpenMP. We don't do this if the current action is an
// device offloading action other than OpenMP.
if (Args.hasFlag(options::OPT_fopenmp, options::OPT_fopenmp_EQ,
diff --git a/flang/include/flang/Frontend/CodeGenOptions.def
b/flang/include/flang/Frontend/CodeGenOptions.def
index 57830bf51a1b3..4dec86cd8f51b 100644
--- a/flang/include/flang/Frontend/CodeGenOptions.def
+++ b/flang/include/flang/Frontend/CodeGenOptions.def
@@ -24,6 +24,11 @@ CODEGENOPT(OptimizationLevel, 2, 0) ///< The -O[0-3] option
specified.
CODEGENOPT(DebugPassManager, 1, 0) ///< Prints debug information for the new
///< pass manager.
+ENUM_CODEGENOPT(ProfileInstr, ProfileInstrKind, 2, ProfileNone)
+ENUM_CODEGENOPT(ProfileUse, ProfileInstrKind, 2, ProfileNone)
+/// Whether emit extra debug info for sample pgo profile collection.
+CODEGENOPT(DebugInfoForProfiling, 1, 0)
+CODEGENOPT(AtomicProfileUpdate , 1, 0) ///< Set -fprofile-update=atomic
CODEGENOPT(IsPIE, 1, 0) ///< PIE level is the same as PIC Level.
CODEGENOPT(PICLevel, 2, 0) ///< PIC level of the LLVM module.
CODEGENOPT(PrepareForFullLTO , 1, 0) ///< Set when -flto is enabled on the
diff --git a/flang/include/flang/Frontend/CodeGenOptions.h
b/flang/include/flang/Frontend/CodeGenOptions.h
index 2b4e823b3fef4..e052250f97e75 100644
--- a/flang/include/flang/Frontend/CodeGenOptions.h
+++ b/flang/include/flang/Frontend/CodeGenOptions.h
@@ -148,6 +148,55 @@ class CodeGenOptions : public CodeGenOptionsBase {
/// OpenMP is enabled.
using DoConcurrentMappingKind = flangomp::DoConcurrentMappingKind;
+ enum ProfileInstrKind {
+ ProfileNone, // Profile instrumentation is turned off.
+ ProfileClangInstr, // Clang instrumentation to generate execution counts
+ // to use with PGO.
+ ProfileIRInstr, // IR level PGO instrumentation in LLVM.
+ ProfileCSIRInstr, // IR level PGO context sensitive instrumentation in
LLVM.
+ };
+
+
+ /// Name of the profile file to use as output for -fprofile-instr-generate,
+ /// -fprofile-generate, and -fcs-profile-generate.
+ std::string InstrProfileOutput;
+
+ /// Name of the profile file to use as input for -fmemory-profile-use.
+ std::string MemoryProfileUsePath;
+
+ unsigned int DebugInfoForProfiling;
+
+ unsigned int AtomicProfileUpdate;
+
+ /// Name of the profile file to use as input for -fprofile-instr-use
+ std::string ProfileInstrumentUsePath;
+
+ /// Name of the profile remapping file to apply to the profile data
supplied
+ /// by -fprofile-sample-use or -fprofile-instr-use.
+ std::string ProfileRemappingFile;
+
+ /// Check if Clang profile instrumenation is on.
+ bool hasProfileClangInstr() const {
+ return getProfileInstr() == ProfileClangInstr;
+ }
+
+ /// Check if IR level profile instrumentation is on.
+ bool hasProfileIRInstr() const {
+ return getProfileInstr() == ProfileIRInstr;
+ }
+
+ /// Check if CS IR level profile instrumentation is on.
+ bool hasProfileCSIRInstr() const {
+ return getProfileInstr() == ProfileCSIRInstr;
+ }
+ /// Check if IR level profile use is on.
+ bool hasProfileIRUse() const {
+ return getProfileUse() == ProfileIRInstr ||
+ getProfileUse() == ProfileCSIRInstr;
+ }
+ /// Check if CSIR profile use is on.
+ bool hasProfileCSIRUse() const { return getProfileUse() == ProfileCSIRInstr;
}
+
// Define accessors/mutators for code generation options of enumeration type.
#define CODEGENOPT(Name, Bits, Default)
#define ENUM_CODEGENOPT(Name, Type, Bits, Default)
\
diff --git a/flang/lib/Frontend/CompilerInvocation.cpp
b/flang/lib/Frontend/CompilerInvocation.cpp
index 6f87a18d69c3d..f013fce2f3cfc 100644
--- a/flang/lib/Frontend/CompilerInvocation.cpp
+++ b/flang/lib/Frontend/CompilerInvocation.cpp
@@ -27,6 +27,7 @@
#include "clang/Driver/DriverDiagnostic.h"
#include "clang/Driver/OptionUtils.h"
#include "clang/Driver/Options.h"
+#include "clang/Driver/Driver.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/ADT/StringSwitch.h"
#include "llvm/Frontend/Debug/Options.h"
@@ -431,6 +432,17 @@ static void
parseCodeGenArgs(Fortran::frontend::CodeGenOptions &opts,
opts.IsPIE = 1;
}
+ if (args.hasArg(clang::driver::options::OPT_fprofile_generate)) {
+
opts.setProfileInstr(Fortran::frontend::CodeGenOptions::ProfileInstrKind::ProfileIRInstr);
+ opts.DebugInfoForProfiling =
args.hasArg(clang::driver::options::OPT_fdebug_info_for_profiling);
+ opts.AtomicProfileUpdate =
args.hasArg(clang::driver::options::OPT_fprofile_update_EQ);
+ }
+
+ if (auto A = args.getLastArg(clang::driver::options::OPT_fprofile_use_EQ)) {
+
opts.setProfileUse(Fortran::frontend::CodeGenOptions::ProfileInstrKind::ProfileIRInstr);
+ opts.ProfileInstrumentUsePath = A->getValue();
+ }
+
// -mcmodel option.
if (const llvm::opt::Arg *a =
args.getLastArg(clang::driver::options::OPT_mcmodel_EQ)) {
diff --git a/flang/lib/Frontend/FrontendActions.cpp
b/flang/lib/Frontend/FrontendActions.cpp
index c1f47b12abee2..68880bdeecf8d 100644
--- a/flang/lib/Frontend/FrontendActions.cpp
+++ b/flang/lib/Frontend/FrontendActions.cpp
@@ -63,11 +63,14 @@
#include "llvm/Support/Path.h"
#include "llvm/Support/SourceMgr.h"
#include "llvm/Support/ToolOutputFile.h"
+#include "llvm/Support/PGOOptions.h"
#include "llvm/Target/TargetMachine.h"
#include "llvm/TargetParser/RISCVISAInfo.h"
#include "llvm/TargetParser/RISCVTargetParser.h"
#include "llvm/Transforms/IPO/Internalize.h"
#include "llvm/Transforms/Utils/ModuleUtils.h"
+#include "llvm/Transforms/Instrumentation/InstrProfiling.h"
+#include "llvm/ProfileData/InstrProfCorrelator.h"
#include <memory>
#include <system_error>
@@ -130,6 +133,20 @@ static bool saveMLIRTempFile(const CompilerInvocation &ci,
// Custom BeginSourceFileAction
//===----------------------------------------------------------------------===//
+
+static llvm::cl::opt<llvm::PGOOptions::ColdFuncOpt> ClPGOColdFuncAttr(
+ "pgo-cold-func-opt", llvm::cl::init(llvm::PGOOptions::ColdFuncOpt::Default),
llvm::cl::Hidden,
+ llvm::cl::desc(
+ "Function attribute to apply to cold functions as determined by PGO"),
+ llvm::cl::values(clEnumValN(llvm::PGOOptions::ColdFuncOpt::Default,
"default",
+ "Default (no attribute)"),
+ clEnumValN(llvm::PGOOptions::ColdFuncOpt::OptSize, "optsize",
+ "Mark cold functions with optsize."),
+ clEnumValN(llvm::PGOOptions::ColdFuncOpt::MinSize, "minsize",
+ "Mark cold functions with minsize."),
+ clEnumValN(llvm::PGOOptions::ColdFuncOpt::OptNone, "optnone",
+ "Mark cold functions with optnone.")));
+
bool PrescanAction::beginSourceFileAction() { return runPrescan(); }
bool PrescanAndParseAction::beginSourceFileAction() {
@@ -892,6 +909,20 @@ static void
generateMachineCodeOrAssemblyImpl(clang::DiagnosticsEngine &diags,
delete tlii;
}
+
+// Default filename used for profile generation.
+namespace llvm {
+ extern llvm::cl::opt<bool> DebugInfoCorrelate;
+ extern llvm::cl::opt<InstrProfCorrelator::ProfCorrelatorKind>
ProfileCorrelate;
+
+
+std::string getDefaultProfileGenName() {
+ return DebugInfoCorrelate || ProfileCorrelate !=
llvm::InstrProfCorrelator::NONE
+ ? "default_%m.proflite"
+ : "default_%m.profraw";
+}
+}
+
void CodeGenAction::runOptimizationPipeline(llvm::raw_pwrite_stream &os) {
CompilerInstance &ci = getInstance();
const CodeGenOptions &opts = ci.getInvocation().getCodeGenOpts();
@@ -909,6 +940,29 @@ void
CodeGenAction::runOptimizationPipeline(llvm::raw_pwrite_stream &os) {
llvm::PassInstrumentationCallbacks pic;
llvm::PipelineTuningOptions pto;
std::optional<llvm::PGOOptions> pgoOpt;
+
+ if (opts.hasProfileIRInstr()){
+ // // -fprofile-generate.
+ pgoOpt = llvm::PGOOptions(
+ opts.InstrProfileOutput.empty() ? llvm::getDefaultProfileGenName()
+ : opts.InstrProfileOutput,
+ "", "", opts.MemoryProfileUsePath, nullptr, llvm::PGOOptions::IRInstr,
+ llvm::PGOOptions::NoCSAction, ClPGOColdFuncAttr,
+ opts.DebugInfoForProfiling,
+ /*PseudoProbeForProfiling=*/false, opts.AtomicProfileUpdate);
+ }
+ else if (opts.hasProfileIRUse()) {
+ llvm::IntrusiveRefCntPtr<llvm::vfs::FileSystem> VFS =
llvm::vfs::getRealFileSystem();
+ // -fprofile-use.
+ auto CSAction = opts.hasProfileCSIRUse() ? llvm::PGOOptions::CSIRUse
+ :
llvm::PGOOptions::NoCSAction;
+ pgoOpt = llvm::PGOOptions(opts.ProfileInstrumentUsePath, "",
+ opts.ProfileRemappingFile,
+ opts.MemoryProfileUsePath, VFS,
+ llvm::PGOOptions::IRUse, CSAction, ClPGOColdFuncAttr,
+ opts.DebugInfoForProfiling);
+ }
+
llvm::StandardInstrumentations si(llvmModule->getContext(),
opts.DebugPassManager);
si.registerCallbacks(pic, &mam);
diff --git a/flang/test/Driver/flang-f-opts.f90
b/flang/test/Driver/flang-f-opts.f90
index 4493a519e2010..b972b9b7b2a59 100644
--- a/flang/test/Driver/flang-f-opts.f90
+++ b/flang/test/Driver/flang-f-opts.f90
@@ -8,3 +8,8 @@
! CHECK-LABEL: "-fc1"
! CHECK: -ffp-contract=off
! CHECK: -O3
+
+! RUN: %flang -### -S -fprofile-generate %s 2>&1 | FileCheck
-check-prefix=CHECK-PROFILE-GENERATE-LLVM %s
+! CHECK-PROFILE-GENERATE-LLVM: "-fprofile-generate"
+! RUN: %flang -### -S -fprofile-use=%S %s 2>&1 | FileCheck
-check-prefix=CHECK-PROFILE-USE-DIR %s
+! CHECK-PROFILE-USE-DIR: "-fprofile-use={{.*}}"
diff --git a/flang/test/Profile/Inputs/gcc-flag-compatibility_IR.proftext
b/flang/test/Profile/Inputs/gcc-flag-compatibility_IR.proftext
new file mode 100644
index 0000000000000..6a6df8b1d4d5b
--- /dev/null
+++ b/flang/test/Profile/Inputs/gcc-flag-compatibility_IR.proftext
@@ -0,0 +1,19 @@
+# IR level Instrumentation Flag
+:ir
+_QQmain
+# Func Hash:
+146835646621254984
+# Num Counters:
+2
+# Counter Values:
+100
+1
+
+main
+# Func Hash:
+742261418966908927
+# Num Counters:
+1
+# Counter Values:
+1
+
diff --git a/flang/test/Profile/Inputs/gcc-flag-compatibility_IR_entry.proftext
b/flang/test/Profile/Inputs/gcc-flag-compatibility_IR_entry.proftext
new file mode 100644
index 0000000000000..9a46140286673
--- /dev/null
+++ b/flang/test/Profile/Inputs/gcc-flag-compatibility_IR_entry.proftext
@@ -0,0 +1,14 @@
+# IR level Instrumentation Flag
+:ir
+:entry_first
+_QQmain
+# Func Hash:
+146835646621254984
+# Num Counters:
+2
+# Counter Values:
+100
+1
+
+
+
diff --git a/flang/test/Profile/gcc-flag-compatibility.f90
b/flang/test/Profile/gcc-flag-compatibility.f90
new file mode 100644
index 0000000000000..0124bc79b87ef
--- /dev/null
+++ b/flang/test/Profile/gcc-flag-compatibility.f90
@@ -0,0 +1,39 @@
+! Tests for -fprofile-generate and -fprofile-use flag compatibility. These two
+! flags behave similarly to their GCC counterparts:
+!
+! -fprofile-generate Generates the profile file ./default.profraw
+! -fprofile-use=<dir>/file Uses the profile file <dir>/file
+
+! On AIX, -flto used to be required with -fprofile-generate.
gcc-flag-compatibility-aix.c is used to do the testing on AIX with -flto
+! RUN: %flang %s -c -S -o - -emit-llvm -fprofile-generate | FileCheck
-check-prefix=PROFILE-GEN %s
+! PROFILE-GEN: @__profc_{{_?}}main = {{(private|internal)}} global [1 x i64]
zeroinitializer, section
+! PROFILE-GEN: @__profd_{{_?}}main =
+
+
+
+! Check that -fprofile-use=some/path/file.prof reads some/path/file.prof
+! This uses LLVM IR format profile.
+! RUN: rm -rf %t.dir
+! RUN: mkdir -p %t.dir/some/path
+! RUN: llvm-profdata merge %S/Inputs/gcc-flag-compatibility_IR.proftext -o
%t.dir/some/path/file.prof
+! RUN: %flang %s -o - -emit-llvm -S -fprofile-use=%t.dir/some/path/file.prof |
FileCheck -check-prefix=PROFILE-USE-IR1 %s
+!
+
+
+
+! RUN: llvm-profdata merge %S/Inputs/gcc-flag-compatibility_IR_entry.proftext
-o %t.dir/some/path/file.prof
+! RUN: %flang %s -o - -emit-llvm -S -fprofile-use=%t.dir/some/path/file.prof |
FileCheck -check-prefix=PROFILE-USE-IR2 %s
+! PROFILE-USE-IR1: = !{!"branch_weights", i32 100, i32 1}
+! PROFILE-USE-IR2: = !{!"branch_weights", i32 1, i32 100}
+
+
+program main
+ implicit none
+ integer :: i
+ integer :: X = 0
+
+ do i = 0, 99
+ X = X + i
+ end do
+
+end program main
>From b897c7aa1e21dfe46b4acf709f3ea38d9021c164 Mon Sep 17 00:00:00 2001
From: FYK <fanyik...@bosc.ac.cn>
Date: Wed, 23 Apr 2025 09:56:14 +0800
Subject: [PATCH 2/2] Update flang/lib/Frontend/FrontendActions.cpp
Remove redundant comment symbols
Co-authored-by: Tom Eccles <t...@freedommail.info>
---
flang/lib/Frontend/FrontendActions.cpp | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/flang/lib/Frontend/FrontendActions.cpp
b/flang/lib/Frontend/FrontendActions.cpp
index 68880bdeecf8d..cd13a6aca92cd 100644
--- a/flang/lib/Frontend/FrontendActions.cpp
+++ b/flang/lib/Frontend/FrontendActions.cpp
@@ -942,7 +942,7 @@ void
CodeGenAction::runOptimizationPipeline(llvm::raw_pwrite_stream &os) {
std::optional<llvm::PGOOptions> pgoOpt;
if (opts.hasProfileIRInstr()){
- // // -fprofile-generate.
+ // -fprofile-generate.
pgoOpt = llvm::PGOOptions(
opts.InstrProfileOutput.empty() ? llvm::getDefaultProfileGenName()
: opts.InstrProfileOutput,
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
