Add -fdebug-info-for-profiling to emit more debug info for sample pgo profile collection

Summary:
SamplePGO uses profile with debug info to collect profile. Unlike the traditional debugging purpose, sample pgo needs more accurate debug info to represent the profile. We add -femit-accurate-debug-info for this purpose. It can be combined with all debugging modes (-g, -gmlt, etc). It makes sure that the following pieces of info is always emitted:

* start line of all subprograms
* linkage name of all subprograms
* standalone subprograms (functions that has neither inlined nor been inlined)

The impact on speccpu2006 binary size (size increase comparing with -g0 binary, also includes data for -g binary, which does not change with this patch):

               -gmlt(orig) -gmlt(patched) -g
433.milc       4.68%       5.40%          19.73%
444.namd       8.45%       8.93%          45.99%
447.dealII     97.43%      115.21%        374.89%
450.soplex     27.75%      31.88%         126.04%
453.povray     21.81%      26.16%         92.03%
470.lbm        0.60%       0.67%          1.96%
482.sphinx3    5.77%       6.47%          26.17%
400.perlbench  17.81%      19.43%         73.08%
401.bzip2      3.73%       3.92%          12.18%
403.gcc        31.75%      34.48%         122.75%
429.mcf        0.78%       0.88%          3.89%
445.gobmk      6.08%       7.92%          42.27%
456.hmmer      10.36%      11.25%         35.23%
458.sjeng      5.08%       5.42%          14.36%
462.libquantum 1.71%       1.96%          6.36%
464.h264ref    15.61%      16.56%         43.92%
471.omnetpp    11.93%      15.84%         60.09%
473.astar      3.11%       3.69%          14.18%
483.xalancbmk  56.29%      81.63%         353.22%
geomean        15.60%      18.30%         57.81%

Debug info size change for -gmlt binary with this patch:

433.milc       13.46%
444.namd       5.35%
447.dealII     18.21%
450.soplex     14.68%
453.povray     19.65%
470.lbm        6.03%
482.sphinx3    11.21%
400.perlbench  8.91%
401.bzip2      4.41%
403.gcc        8.56%
429.mcf        8.24%
445.gobmk      29.47%
456.hmmer      8.19%
458.sjeng      6.05%
462.libquantum 11.23%
464.h264ref    5.93%
471.omnetpp    31.89%
473.astar      16.20%
483.xalancbmk  44.62%
geomean        16.83%

Reviewers: davidxl, andreadb, rob.lougher, dblaikie, echristo

Reviewed By: dblaikie, echristo

Subscribers: hfinkel, rob.lougher, andreadb, gbedwell, cfe-commits, probinson, llvm-commits, mehdi_amini

Differential Revision: https://reviews.llvm.org/D25435

llvm-svn: 292458

7 files changed, 23 insertions, 1 deletions

diff --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
index ecc34af44ef..af9e4a77ea2 100644
--- a/clang/include/clang/Driver/Options.td
+++ b/clang/include/clang/Driver/Options.td
@@ -516,6 +516,12 @@ def fprofile_sample_use_EQ : Joined<["-"], "fprofile-sample-use=">,
     HelpText<"Enable sample-based profile guided optimizations">;
 def fauto_profile_EQ : Joined<["-"], "fauto-profile=">,
     Alias<fprofile_sample_use_EQ>;
+def fdebug_info_for_profiling : Flag<["-"], "fdebug-info-for-profiling">, Group<f_Group>,
+    Flags<[CC1Option]>,
+    HelpText<"Emit extra debug info to make sample profile more accurate.">;
+def fno_debug_info_for_profiling : Flag<["-"], "fno-debug-info-for-profiling">, Group<f_Group>,
+    Flags<[DriverOption]>,
+    HelpText<"Do not emit extra debug info for sample profiler.">;
 def fprofile_instr_generate : Flag<["-"], "fprofile-instr-generate">,
     Group<f_Group>, Flags<[CoreOption]>,
     HelpText<"Generate instrumented code to collect execution counts into default.profraw file (overridden by '=' form of option or LLVM_PROFILE_FILE env var)">;
diff --git a/clang/include/clang/Frontend/CodeGenOptions.def b/clang/include/clang/Frontend/CodeGenOptions.def
index d4b2049d61f..0685b6613f3 100644
--- a/clang/include/clang/Frontend/CodeGenOptions.def
+++ b/clang/include/clang/Frontend/CodeGenOptions.def
@@ -258,6 +258,9 @@ CODEGENOPT(PIECopyRelocations, 1, 0)
 /// paths that reach the end of a function without executing a required return.
 CODEGENOPT(StrictReturn, 1, 1)
 
+/// Whether emit extra debug info for sample pgo profile collection.
+CODEGENOPT(DebugInfoForProfiling, 1, 0)
+
 #undef CODEGENOPT
 #undef ENUM_CODEGENOPT
 #undef VALUE_CODEGENOPT
diff --git a/clang/lib/CodeGen/BackendUtil.cpp b/clang/lib/CodeGen/BackendUtil.cpp
index 765c403fd15..bac1e89820a 100644
--- a/clang/lib/CodeGen/BackendUtil.cpp
+++ b/clang/lib/CodeGen/BackendUtil.cpp
@@ -573,6 +573,7 @@ void EmitAssemblyHelper::CreateTargetMachine(bool MustCreateTM) {
   Options.DisableIntegratedAS = CodeGenOpts.DisableIntegratedAS;
   Options.CompressDebugSections = CodeGenOpts.CompressDebugSections;
   Options.RelaxELFRelocations = CodeGenOpts.RelaxELFRelocations;
+  Options.DebugInfoForProfiling = CodeGenOpts.DebugInfoForProfiling;
 
   // Set EABI version.
   Options.EABIVersion = llvm::StringSwitch<llvm::EABI>(TargetOpts.EABIVersion)
diff --git a/clang/lib/CodeGen/CGDebugInfo.cpp b/clang/lib/CodeGen/CGDebugInfo.cpp
index 12a68036b09..c3dd53f12e2 100644
--- a/clang/lib/CodeGen/CGDebugInfo.cpp
+++ b/clang/lib/CodeGen/CGDebugInfo.cpp
@@ -2774,9 +2774,10 @@ void CGDebugInfo::collectFunctionDeclProps(GlobalDecl GD, llvm::DIFile *Unit,
   }
   // No need to replicate the linkage name if it isn't different from the
   // subprogram name, no need to have it at all unless coverage is enabled or
-  // debug is set to more than just line tables.
+  // debug is set to more than just line tables or extra debug info is needed.
   if (LinkageName == Name || (!CGM.getCodeGenOpts().EmitGcovArcs &&
                               !CGM.getCodeGenOpts().EmitGcovNotes &&
+                              !CGM.getCodeGenOpts().DebugInfoForProfiling &&
                               DebugKind <= codegenoptions::DebugLineTablesOnly))
     LinkageName = StringRef();
 
diff --git a/clang/lib/Driver/Tools.cpp b/clang/lib/Driver/Tools.cpp
index e7c6f22c95d..cb11f5d6f59 100644
--- a/clang/lib/Driver/Tools.cpp
+++ b/clang/lib/Driver/Tools.cpp
@@ -5615,6 +5615,10 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
       A->render(Args, CmdArgs);
   }
 
+  if (Args.hasFlag(options::OPT_fdebug_info_for_profiling,
+                   options::OPT_fno_debug_info_for_profiling, false))
+    CmdArgs.push_back("-fdebug-info-for-profiling");
+
   // -fbuiltin is default unless -mkernel is used.
   bool UseBuiltins =
       Args.hasFlag(options::OPT_fbuiltin, options::OPT_fno_builtin,
diff --git a/clang/lib/Frontend/CompilerInvocation.cpp b/clang/lib/Frontend/CompilerInvocation.cpp
index 8256edd988e..7576d6d4e5e 100644
--- a/clang/lib/Frontend/CompilerInvocation.cpp
+++ b/clang/lib/Frontend/CompilerInvocation.cpp
@@ -544,6 +544,8 @@ static bool ParseCodeGenArgs(CodeGenOptions &Opts, ArgList &Args, InputKind IK,
   Opts.DisableIntegratedAS = Args.hasArg(OPT_fno_integrated_as);
   Opts.Autolink = !Args.hasArg(OPT_fno_autolink);
   Opts.SampleProfileFile = Args.getLastArgValue(OPT_fprofile_sample_use_EQ);
+  Opts.DebugInfoForProfiling = Args.hasFlag(
+      OPT_fdebug_info_for_profiling, OPT_fno_debug_info_for_profiling, false);
 
   setPGOInstrumentor(Opts, Args, Diags);
   Opts.InstrProfileOutput =
diff --git a/clang/test/Driver/clang_f_opts.c b/clang/test/Driver/clang_f_opts.c
index 210e16935d8..0261d93c49b 100644
--- a/clang/test/Driver/clang_f_opts.c
+++ b/clang/test/Driver/clang_f_opts.c
@@ -482,3 +482,8 @@
 // RUN: %clang -### -S -fno-strict-return %s 2>&1 | FileCheck -check-prefix=CHECK-NO-STRICT-RETURN %s
 // CHECK-STRICT-RETURN-NOT: "-fno-strict-return"
 // CHECK-NO-STRICT-RETURN: "-fno-strict-return"
+
+// RUN: %clang -### -S -fno-debug-info-for-profiling -fdebug-info-for-profiling %s 2>&1 | FileCheck -check-prefix=CHECK-PROFILE-DEBUG %s
+// RUN: %clang -### -S -fdebug-info-for-profiling -fno-debug-info-for-profiling %s 2>&1 | FileCheck -check-prefix=CHECK-NO-PROFILE-DEBUG %s
+// CHECK-PROFILE-DEBUG: -fdebug-info-for-profiling
+// CHECK-NO-PROFILE-DEBUG-NOT: -fdebug-info-for-profiling