[clang] [CGData] Clang Options (PR #90304)
via cfe-commits
cfe-commits at lists.llvm.org
Wed Sep 11 09:17:28 PDT 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-clang-driver
Author: Kyungwoo Lee (kyulee-com)
<details>
<summary>Changes</summary>
This adds new Clang flags to support codegen (CG) data:
- `-fcodegen-data-generate{=path}`: This flag passes `-codegen-data-generate` as a boolean to the LLVM backend, causing the raw CG data to be emitted into a custom section. Currently, for LLD MachO only, it also passes `--codegen-data-generate-path=<path>` so that the indexed CG data file can be automatically produced at link time. For linkers that do not yet support this feature, `llvm-cgdata` can be used manually to merge this CG data in object files.
- `-fcodegen-data-use{=path}`: This flag passes `-codegen-data-use-path=<path>` to the LLVM backend, enabling the use of specified CG data to optimistically outline functions.
- The default `<path>` is set to `default.cgdata` when not specified.
This depends on https://github.com/llvm/llvm-project/pull/90166.
This is a patch for https://discourse.llvm.org/t/rfc-enhanced-machine-outliner-part-2-thinlto-nolto/78753.
---
Full diff: https://github.com/llvm/llvm-project/pull/90304.diff
4 Files Affected:
- (modified) clang/include/clang/Driver/Options.td (+12)
- (modified) clang/lib/Driver/ToolChains/CommonArgs.cpp (+27)
- (modified) clang/lib/Driver/ToolChains/Darwin.cpp (+46)
- (added) clang/test/Driver/codegen-data.c (+42)
``````````diff
diff --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
index f78032255f036f..b400af5d99c654 100644
--- a/clang/include/clang/Driver/Options.td
+++ b/clang/include/clang/Driver/Options.td
@@ -1894,6 +1894,18 @@ def fprofile_selected_function_group :
Visibility<[ClangOption, CC1Option]>, MetaVarName<"<i>">,
HelpText<"Partition functions into N groups using -fprofile-function-groups and select only functions in group i to be instrumented. The valid range is 0 to N-1 inclusive">,
MarshallingInfoInt<CodeGenOpts<"ProfileSelectedFunctionGroup">>;
+def fcodegen_data_generate : Joined<["-"], "fcodegen-data-generate">,
+ Group<f_Group>, Visibility<[ClangOption, CC1Option]>,
+ HelpText<"Emit codegen data into object file. LLD for MachO (for now) merges them into default.cgdata">;
+def fcodegen_data_generate_EQ : Joined<["-"], "fcodegen-data-generate=">,
+ Group<f_Group>, Visibility<[ClangOption, CC1Option]>, MetaVarName<"<directory>">,
+ HelpText<"Emit codegen data into object file. LLD for MachO (for now) merges them into <directory>/default.cgdata">;
+def fcodegen_data_use : Joined<["-"], "fcodegen-data-use">,
+ Group<f_Group>, Visibility<[ClangOption, CC1Option]>,
+ HelpText<"Use codegen data read from default.cgdata to optimize the binary">;
+def fcodegen_data_use_EQ : Joined<["-"], "fcodegen-data-use=">,
+ Group<f_Group>, Visibility<[ClangOption, CC1Option]>, MetaVarName<"<directory>">,
+ HelpText<"Use codegen data read from <directory>/default.cgdata to optimize the binary">;
def fswift_async_fp_EQ : Joined<["-"], "fswift-async-fp=">,
Group<f_Group>,
Visibility<[ClangOption, CC1Option, CC1AsOption, CLOption]>,
diff --git a/clang/lib/Driver/ToolChains/CommonArgs.cpp b/clang/lib/Driver/ToolChains/CommonArgs.cpp
index 2ce6779f4b43e3..5fa502d64c0300 100644
--- a/clang/lib/Driver/ToolChains/CommonArgs.cpp
+++ b/clang/lib/Driver/ToolChains/CommonArgs.cpp
@@ -2753,6 +2753,33 @@ void tools::addMachineOutlinerArgs(const Driver &D,
addArg(Twine("-enable-machine-outliner=never"));
}
}
+
+ auto *CodeGenDataGenArg =
+ Args.getLastArg(options::OPT_fcodegen_data_generate,
+ options::OPT_fcodegen_data_generate_EQ);
+ auto *CodeGenDataUseArg = Args.getLastArg(options::OPT_fcodegen_data_use,
+ options::OPT_fcodegen_data_use_EQ);
+
+ // We only allow one of them to be specified.
+ if (CodeGenDataGenArg && CodeGenDataUseArg)
+ D.Diag(diag::err_drv_argument_not_allowed_with)
+ << CodeGenDataGenArg->getAsString(Args)
+ << CodeGenDataUseArg->getAsString(Args);
+
+ // For codegen data gen, the output file is passed to the linker
+ // while a boolean flag is passed to the LLVM backend.
+ if (CodeGenDataGenArg)
+ addArg(Twine("-codegen-data-generate"));
+
+ // For codegen data use, the input file is passed to the LLVM backend.
+ if (CodeGenDataUseArg) {
+ SmallString<128> Path(CodeGenDataUseArg->getNumValues() == 0
+ ? ""
+ : CodeGenDataUseArg->getValue());
+ if (Path.empty() || llvm::sys::fs::is_directory(Path))
+ llvm::sys::path::append(Path, "default.cgdata");
+ addArg(Twine("-codegen-data-use-path=" + Path.str()));
+ }
}
void tools::addOpenMPDeviceRTL(const Driver &D,
diff --git a/clang/lib/Driver/ToolChains/Darwin.cpp b/clang/lib/Driver/ToolChains/Darwin.cpp
index 5e7f9290e2009d..9e72e280109640 100644
--- a/clang/lib/Driver/ToolChains/Darwin.cpp
+++ b/clang/lib/Driver/ToolChains/Darwin.cpp
@@ -476,6 +476,19 @@ void darwin::Linker::AddLinkArgs(Compilation &C, const ArgList &Args,
llvm::sys::path::append(Path, "default.profdata");
CmdArgs.push_back(Args.MakeArgString(Twine("--cs-profile-path=") + Path));
}
+
+ auto *CodeGenDataGenArg =
+ Args.getLastArg(options::OPT_fcodegen_data_generate,
+ options::OPT_fcodegen_data_generate_EQ);
+ if (CodeGenDataGenArg) {
+ SmallString<128> Path(CodeGenDataGenArg->getNumValues() == 0
+ ? ""
+ : CodeGenDataGenArg->getValue());
+ if (Path.empty() || llvm::sys::fs::is_directory(Path))
+ llvm::sys::path::append(Path, "default.cgdata");
+ CmdArgs.push_back(
+ Args.MakeArgString(Twine("--codegen-data-generate-path=") + Path));
+ }
}
}
@@ -633,6 +646,39 @@ void darwin::Linker::ConstructJob(Compilation &C, const JobAction &JA,
CmdArgs.push_back("-mllvm");
CmdArgs.push_back("-enable-linkonceodr-outlining");
+ // Propagate codegen data flags to the linker for the LLVM backend.
+ auto *CodeGenDataGenArg =
+ Args.getLastArg(options::OPT_fcodegen_data_generate,
+ options::OPT_fcodegen_data_generate_EQ);
+ auto *CodeGenDataUseArg = Args.getLastArg(options::OPT_fcodegen_data_use,
+ options::OPT_fcodegen_data_use_EQ);
+
+ // We only allow one of them to be specified.
+ const Driver &D = getToolChain().getDriver();
+ if (CodeGenDataGenArg && CodeGenDataUseArg)
+ D.Diag(diag::err_drv_argument_not_allowed_with)
+ << CodeGenDataGenArg->getAsString(Args)
+ << CodeGenDataUseArg->getAsString(Args);
+
+ // For codegen data gen, the output file is passed to the linker
+ // while a boolean flag is passed to the LLVM backend.
+ if (CodeGenDataGenArg) {
+ CmdArgs.push_back("-mllvm");
+ CmdArgs.push_back("-codegen-data-generate");
+ }
+
+ // For codegen data use, the input file is passed to the LLVM backend.
+ if (CodeGenDataUseArg) {
+ SmallString<128> Path(CodeGenDataUseArg->getNumValues() == 0
+ ? ""
+ : CodeGenDataUseArg->getValue());
+ if (Path.empty() || llvm::sys::fs::is_directory(Path))
+ llvm::sys::path::append(Path, "default.cgdata");
+ CmdArgs.push_back("-mllvm");
+ CmdArgs.push_back(
+ Args.MakeArgString("-codegen-data-use-path=" + Path.str()));
+ }
+
// Setup statistics file output.
SmallString<128> StatsFile =
getStatsFileName(Args, Output, Inputs[0], getToolChain().getDriver());
diff --git a/clang/test/Driver/codegen-data.c b/clang/test/Driver/codegen-data.c
new file mode 100644
index 00000000000000..a72850afc59736
--- /dev/null
+++ b/clang/test/Driver/codegen-data.c
@@ -0,0 +1,42 @@
+// Verify only one of codegen-data flag is passed.
+// RUN: not %clang -### -S --target=aarch64-linux-gnu -fcodegen-data-generate -fcodegen-data-use %s 2>&1 | FileCheck %s --check-prefix=CONFLICT
+// RUN: not %clang -### -S --target=arm64-apple-darwin -fcodegen-data-generate -fcodegen-data-use %s 2>&1 | FileCheck %s --check-prefix=CONFLICT
+// CONFLICT: error: invalid argument '-fcodegen-data-generate' not allowed with '-fcodegen-data-use'
+
+// Verify the codegen-data-generate (boolean) flag is passed to LLVM
+// RUN: %clang -### -S --target=aarch64-linux-gnu -fcodegen-data-generate %s 2>&1| FileCheck %s --check-prefix=GENERATE
+// RUN: %clang -### -S --target=arm64-apple-darwin -fcodegen-data-generate %s 2>&1| FileCheck %s --check-prefix=GENERATE
+// GENERATE: "-mllvm" "-codegen-data-generate"
+
+// Verify the codegen-data-use-path flag (with a default value) is passed to LLVM.
+// RUN: %clang -### -S --target=aarch64-linux-gnu -fcodegen-data-use %s 2>&1| FileCheck %s --check-prefix=USE
+// RUN: %clang -### -S --target=arm64-apple-darwin -fcodegen-data-use %s 2>&1| FileCheck %s --check-prefix=USE
+// RUN: mkdir -p %t.d/some/dir
+// RUN: %clang -### -S --target=aarch64-linux-gnu -fcodegen-data-use=%t.d/some/dir %s 2>&1 | FileCheck %s --check-prefix=USE-DIR
+// RUN: %clang -### -S --target=arm64-apple-darwin -fcodegen-data-use=%t.d/some/dir %s 2>&1 | FileCheck %s --check-prefix=USE-DIR
+// RUN: %clang -### -S --target=aarch64-linux-gnu -fcodegen-data-use=file %s 2>&1 | FileCheck %s --check-prefix=USE-FILE
+// RUN: %clang -### -S --target=arm64-apple-darwin -fcodegen-data-use=file %s 2>&1 | FileCheck %s --check-prefix=USE-FILE
+// USE: "-mllvm" "-codegen-data-use-path=default.cgdata"
+// USE-DIR: "-mllvm" "-codegen-data-use-path={{.*}}.d/some/dir{{/|\\\\}}default.cgdata"
+// USE-FILE: "-mllvm" "-codegen-data-use-path=file"
+
+// Verify the codegen-data-generate (boolean) flag with a LTO.
+// RUN: %clang -### -flto --target=aarch64-linux-gnu -fcodegen-data-generate %s 2>&1 | FileCheck %s --check-prefix=GENERATE-LTO
+// GENERATE-LTO: {{ld(.exe)?"}}
+// GENERATE-LTO-SAME: "-plugin-opt=-codegen-data-generate"
+// RUN: %clang -### -flto --target=arm64-apple-darwin -fcodegen-data-generate %s 2>&1 | FileCheck %s --check-prefix=GENERATE-LTO-DARWIN
+// GENERATE-LTO-DARWIN: {{ld(.exe)?"}}
+// GENERATE-LTO-DARWIN-SAME: "-mllvm" "-codegen-data-generate"
+
+// Verify the codegen-data-use-path flag with a LTO is passed to LLVM.
+// RUN: %clang -### -flto=thin --target=aarch64-linux-gnu -fcodegen-data-use %s 2>&1 | FileCheck %s --check-prefix=USE-LTO
+// USE-LTO: {{ld(.exe)?"}}
+// USE-LTO-SAME: "-plugin-opt=-codegen-data-use-path=default.cgdata"
+// RUN: %clang -### -flto=thin --target=arm64-apple-darwin -fcodegen-data-use %s 2>&1 | FileCheck %s --check-prefix=USE-LTO-DARWIN
+// USE-LTO-DARWIN: {{ld(.exe)?"}}
+// USE-LTO-DARWIN-SAME: "-mllvm" "-codegen-data-use-path=default.cgdata"
+
+// For now, LLD MachO supports for generating the codegen data at link time.
+// RUN: %clang -### -fuse-ld=lld -B%S/Inputs/lld --target=arm64-apple-darwin -fcodegen-data-generate %s 2>&1 | FileCheck %s --check-prefix=GENERATE-LLD-DARWIN
+// GENERATE-LLD-DARWIN: {{ld(.exe)?"}}
+// GENERATE-LLD-DARWIN-SAME: "--codegen-data-generate-path=default.cgdata"
``````````
</details>
https://github.com/llvm/llvm-project/pull/90304
More information about the cfe-commits
mailing list