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

Summary:
SamplePGO binaries built with -gmlt to collect profile. The current -gmlt debug info is limited, and we need some additional info:

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

This patch adds these information to the -gmlt binary. 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, echristo, dblaikie

Reviewed By: echristo, dblaikie

Subscribers: aprantl, probinson, llvm-commits, mehdi_amini

Differential Revision: https://reviews.llvm.org/D25434

llvm-svn: 292457

7 files changed, 34 insertions, 10 deletions

diff --git a/llvm/include/llvm/Target/TargetOptions.h b/llvm/include/llvm/Target/TargetOptions.h
index f5134d99b03..f73afb4706e 100644
--- a/llvm/include/llvm/Target/TargetOptions.h
+++ b/llvm/include/llvm/Target/TargetOptions.h
@@ -108,7 +108,7 @@ namespace llvm {
           DisableIntegratedAS(false), CompressDebugSections(false),
           RelaxELFRelocations(false), FunctionSections(false),
           DataSections(false), UniqueSectionNames(true), TrapUnreachable(false),
-          EmulatedTLS(false), EnableIPRA(false),
+          EmulatedTLS(false), EnableIPRA(false), DebugInfoForProfiling(false),
           FloatABIType(FloatABI::Default),
           AllowFPOpFusion(FPOpFusion::Standard),
           ThreadModel(ThreadModel::POSIX),
@@ -225,6 +225,9 @@ namespace llvm {
     /// This flag enables InterProcedural Register Allocation (IPRA).
     unsigned EnableIPRA : 1;
 
+    /// This flag enables emitting extra debug info for sample profiling.
+    unsigned DebugInfoForProfiling : 1;
+
     /// FloatABIType - This setting is set by -float-abi=xxx option is specfied
     /// on the command line. This setting may either be Default, Soft, or Hard.
     /// Default selects the target's default behavior. Soft selects the ABI for
@@ -299,7 +302,8 @@ inline bool operator==(const TargetOptions &LHS,
     ARE_EQUAL(FPDenormalMode) &&
     ARE_EQUAL(ExceptionModel) &&
     ARE_EQUAL(MCOptions) &&
-    ARE_EQUAL(EnableIPRA);
+    ARE_EQUAL(EnableIPRA) &&
+    ARE_EQUAL(DebugInfoForProfiling);
 #undef ARE_EQUAL
 }
 
diff --git a/llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp b/llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp
index b465b98f368..8e2f4f2551a 100644
--- a/llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp
+++ b/llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp
@@ -1211,8 +1211,10 @@ void DwarfDebug::endFunction(const MachineFunction *MF) {
   TheCU.addRange(RangeSpan(Asm->getFunctionBegin(), Asm->getFunctionEnd()));
 
   // Under -gmlt, skip building the subprogram if there are no inlined
-  // subroutines inside it.
-  if (TheCU.getCUNode()->getEmissionKind() == DICompileUnit::LineTablesOnly &&
+  // subroutines inside it. But with -fdebug-info-for-profiling, the subprogram
+  // is still needed as we need its source location.
+  if (!Asm->TM.Options.DebugInfoForProfiling &&
+      TheCU.getCUNode()->getEmissionKind() == DICompileUnit::LineTablesOnly &&
       LScopes.getAbstractScopesList().empty() && !IsDarwin) {
     assert(InfoHolder.getScopeVariables().empty());
     assert(DbgValues.empty());
diff --git a/llvm/lib/CodeGen/AsmPrinter/DwarfUnit.cpp b/llvm/lib/CodeGen/AsmPrinter/DwarfUnit.cpp
index 2a866c071f5..4269bb672a9 100644
--- a/llvm/lib/CodeGen/AsmPrinter/DwarfUnit.cpp
+++ b/llvm/lib/CodeGen/AsmPrinter/DwarfUnit.cpp
@@ -1180,8 +1180,12 @@ bool DwarfUnit::applySubprogramDefinitionAttributes(const DISubprogram *SP,
 }
 
 void DwarfUnit::applySubprogramAttributes(const DISubprogram *SP, DIE &SPDie,
-                                          bool Minimal) {
-  if (!Minimal)
+                                          bool SkipSPAttributes) {
+  // If -fdebug-info-for-profiling is enabled, need to emit the subprogram
+  // and its source location.
+  bool SkipSPSourceLocation = SkipSPAttributes &&
+                              !Asm->TM.Options.DebugInfoForProfiling;
+  if (!SkipSPSourceLocation)
     if (applySubprogramDefinitionAttributes(SP, SPDie))
       return;
 
@@ -1189,12 +1193,13 @@ void DwarfUnit::applySubprogramAttributes(const DISubprogram *SP, DIE &SPDie,
   if (!SP->getName().empty())
     addString(SPDie, dwarf::DW_AT_name, SP->getName());
 
+  if (!SkipSPSourceLocation)
+    addSourceLine(SPDie, SP);
+
   // Skip the rest of the attributes under -gmlt to save space.
-  if (Minimal)
+  if (SkipSPAttributes)
     return;
 
-  addSourceLine(SPDie, SP);
-
   // Add the prototype if we have a prototype and we have a C like
   // language.
   uint16_t Language = getLanguage();
diff --git a/llvm/lib/CodeGen/AsmPrinter/DwarfUnit.h b/llvm/lib/CodeGen/AsmPrinter/DwarfUnit.h
index 8654d6f0caf..a4646eca7a6 100644
--- a/llvm/lib/CodeGen/AsmPrinter/DwarfUnit.h
+++ b/llvm/lib/CodeGen/AsmPrinter/DwarfUnit.h
@@ -256,7 +256,7 @@ public:
   DIE *getOrCreateSubprogramDIE(const DISubprogram *SP, bool Minimal = false);
 
   void applySubprogramAttributes(const DISubprogram *SP, DIE &SPDie,
-                                 bool Minimal = false);
+                                 bool SkipSPAttributes = false);
 
   /// Find existing DIE or create new DIE for the given type.
   DIE *getOrCreateTypeDIE(const MDNode *N);
diff --git a/llvm/lib/Target/TargetMachine.cpp b/llvm/lib/Target/TargetMachine.cpp
index f2c30a583e1..2b3f282f363 100644
--- a/llvm/lib/Target/TargetMachine.cpp
+++ b/llvm/lib/Target/TargetMachine.cpp
@@ -35,6 +35,10 @@ cl::opt<bool> EnableIPRA("enable-ipra", cl::init(false), cl::Hidden,
                          cl::desc("Enable interprocedural register allocation "
                                   "to reduce load/store at procedure calls."));
 
+cl::opt<bool> DebugInfoForProfiling(
+    "debug-info-for-profiling", cl::init(false), cl::Hidden,
+    cl::desc("Emit extra debug info to make sample profile more accurate."));
+
 //---------------------------------------------------------------------------
 // TargetMachine Class
 //
@@ -47,6 +51,8 @@ TargetMachine::TargetMachine(const Target &T, StringRef DataLayoutString,
       RequireStructuredCFG(false), DefaultOptions(Options), Options(Options) {
   if (EnableIPRA.getNumOccurrences())
     this->Options.EnableIPRA = EnableIPRA;
+  if (DebugInfoForProfiling.getNumOccurrences())
+    this->Options.DebugInfoForProfiling = DebugInfoForProfiling;
 }
 
 TargetMachine::~TargetMachine() {
diff --git a/llvm/test/DebugInfo/Generic/gmlt.test b/llvm/test/DebugInfo/Generic/gmlt.test
index e36a3bdea35..d098d1e9125 100644
--- a/llvm/test/DebugInfo/Generic/gmlt.test
+++ b/llvm/test/DebugInfo/Generic/gmlt.test
@@ -1,5 +1,6 @@
 ; REQUIRES: object-emission
 ; RUN: %llc_dwarf -O0 -filetype=obj < %S/../Inputs/gmlt.ll | llvm-dwarfdump - | FileCheck %S/../Inputs/gmlt.ll
+; RUN: %llc_dwarf -O0 -filetype=obj -debug-info-for-profiling < %S/../Inputs/gmlt.ll | llvm-dwarfdump - | FileCheck %S/../Inputs/gmlt.ll --check-prefixes=PROFILING
 
 ; There's a darwin specific test in X86/gmlt, so it's okay to XFAIL this here.
 ; XFAIL: darwin
diff --git a/llvm/test/DebugInfo/Inputs/gmlt.ll b/llvm/test/DebugInfo/Inputs/gmlt.ll
index dc02e77909f..b6df50109ff 100644
--- a/llvm/test/DebugInfo/Inputs/gmlt.ll
+++ b/llvm/test/DebugInfo/Inputs/gmlt.ll
@@ -76,6 +76,12 @@
 ; CHECK-NOT: {{DW_TAG|DW_AT}}
 ; CHECK: NULL
 
+; PROFILING: DW_TAG_subprogram
+; PROFILING: DW_AT_name {{.*}} "f1"
+; With -debug-info-for-profiling, we need to emit decl_file a-nd decl_line
+; of the subprogram.
+; PROFILING: DW_AT_decl_file
+; PROFILING: DW_AT_decl_line
 
 ; CHECK: .debug_ranges contents: