[llvm-profgen] Allow generating AutoFDO profile from CSSPGO binary

Add `-use-dwarf-correlation` switch to allow llvm-profgen to generate AutoFDO profile for binaries built with CSSPGO (pseudo-probe).

Differential Revision: https://reviews.llvm.org/D111776

diff --git a/llvm/test/tools/llvm-profgen/inline-force-dwarf.test b/llvm/test/tools/llvm-profgen/inline-force-dwarf.test
new file mode 100644 (file)
index 0000000..ddca6af
--- /dev/null
+++ b/llvm/test/tools/llvm-profgen/inline-force-dwarf.test
@@ -0,0 +1,38 @@
+; RUN: llvm-profgen --format=text --ignore-stack-samples --use-dwarf-correlation --perfscript=%S/Inputs/inline-cs-pseudoprobe.perfscript --binary=%S/Inputs/inline-cs-pseudoprobe.perfbin --output=%t --profile-summary-cold-count=0
+; RUN: FileCheck %s --input-file %t
+
+; CHECK:     main:295:0
+; CHECK-NEXT: 0: 0
+; CHECK-NEXT: 2: 0
+; CHECK-NEXT: 1: foo:295
+; CHECK-NEXT:  2: 14
+; CHECK-NEXT:  3: 15
+; CHECK-NEXT:  4: 0
+; CHECK-NEXT:  3: bar:84
+; CHECK-NEXT:   1: 14
+
+
+; clang -O3 -fexperimental-new-pass-manager -fuse-ld=lld -fpseudo-probe-for-profiling
+; -fno-omit-frame-pointer -mno-omit-leaf-frame-pointer -Xclang -mdisable-tail-calls
+; -g test.c  -o a.out
+
+#include <stdio.h>
+
+int bar(int x, int y) {
+  if (x % 3) {
+    return x - y;
+  }
+  return x + y;
+}
+
+void foo() {
+  int s, i = 0;
+  while (i++ < 4000 * 4000)
+    if (i % 91) s = bar(i, s); else s += 30;
+  printf("sum is %d\n", s);
+}
+
+int main() {
+  foo();
+  return 0;
+}

diff --git a/llvm/test/tools/llvm-profgen/inline-noprobe.test b/llvm/test/tools/llvm-profgen/inline-noprobe.test
index 691724e..7d8a876 100644 (file)
--- a/llvm/test/tools/llvm-profgen/inline-noprobe.test
+++ b/llvm/test/tools/llvm-profgen/inline-noprobe.test
@@ -1,7 +1,11 @@
 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/inline-noprobe.perfscript --binary=%S/Inputs/inline-noprobe.perfbin --output=%t --skip-symbolization
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK-RAW-PROFILE
+; RUN: llvm-profgen --format=text --use-dwarf-correlation --perfscript=%S/Inputs/inline-noprobe.perfscript --binary=%S/Inputs/inline-noprobe.perfbin --output=%t --skip-symbolization
+; RUN: FileCheck %s --input-file %t --check-prefix=CHECK-RAW-PROFILE
 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/inline-noprobe.perfscript --binary=%S/Inputs/inline-noprobe.perfbin --output=%t
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK
+; RUN: llvm-profgen --format=text --use-dwarf-correlation --perfscript=%S/Inputs/inline-noprobe.perfscript --binary=%S/Inputs/inline-noprobe.perfbin --output=%t
+; RUN: FileCheck %s --input-file %t --check-prefix=CHECK
 
 CHECK: main:669:0
 CHECK:  0: 0

diff --git a/llvm/tools/llvm-profgen/PerfReader.cpp b/llvm/tools/llvm-profgen/PerfReader.cpp
index 8fd2bfd..3ed6966 100644 (file)
--- a/llvm/tools/llvm-profgen/PerfReader.cpp
+++ b/llvm/tools/llvm-profgen/PerfReader.cpp
@@ -12,22 +12,22 @@
 
 #define DEBUG_TYPE "perf-reader"
 
-static cl::opt<bool> ShowMmapEvents("show-mmap-events", cl::ReallyHidden,
-                                    cl::init(false), cl::ZeroOrMore,
-                                    cl::desc("Print binary load events."));
-
-cl::opt<bool> SkipSymbolization("skip-symbolization", cl::ReallyHidden,
-                                cl::init(false), cl::ZeroOrMore,
+cl::opt<bool> SkipSymbolization("skip-symbolization", cl::init(false),
+                                cl::ZeroOrMore,
                                 cl::desc("Dump the unsymbolized profile to the "
                                          "output file. It will show unwinder "
                                          "output for CS profile generation."));
-cl::opt<bool> UseOffset("use-offset", cl::ReallyHidden, cl::init(true),
-                        cl::ZeroOrMore,
-                        cl::desc("Work with `--skip-symbolization` to dump the "
-                                 "offset instead of virtual address."));
-cl::opt<bool>
-    IgnoreStackSamples("ignore-stack-samples", cl::ReallyHidden,
-                       cl::init(false), cl::ZeroOrMore,
+
+static cl::opt<bool> ShowMmapEvents("show-mmap-events", cl::init(false),
+                                    cl::ZeroOrMore,
+                                    cl::desc("Print binary load events."));
+
+static cl::opt<bool>
+    UseOffset("use-offset", cl::init(true), cl::ZeroOrMore,
+              cl::desc("Work with `--skip-symbolization` to dump the "
+                       "offset instead of virtual address."));
+static cl::opt<bool>
+    IgnoreStackSamples("ignore-stack-samples", cl::init(false), cl::ZeroOrMore,
                        cl::desc("Ignore call stack samples for hybrid samples "
                                 "and produce context-insensitive profile."));
 

diff --git a/llvm/tools/llvm-profgen/ProfiledBinary.cpp b/llvm/tools/llvm-profgen/ProfiledBinary.cpp
index 31a8ba1..bbc26d1 100644 (file)
--- a/llvm/tools/llvm-profgen/ProfiledBinary.cpp
+++ b/llvm/tools/llvm-profgen/ProfiledBinary.cpp
@@ -22,22 +22,27 @@
 using namespace llvm;
 using namespace sampleprof;
 
-cl::opt<bool> ShowDisassemblyOnly("show-disassembly-only", cl::ReallyHidden,
-                                  cl::init(false), cl::ZeroOrMore,
+cl::opt<bool> ShowDisassemblyOnly("show-disassembly-only", cl::init(false),
+                                  cl::ZeroOrMore,
                                   cl::desc("Print disassembled code."));
 
-cl::opt<bool> ShowSourceLocations("show-source-locations", cl::ReallyHidden,
-                                  cl::init(false), cl::ZeroOrMore,
+cl::opt<bool> ShowSourceLocations("show-source-locations", cl::init(false),
+                                  cl::ZeroOrMore,
                                   cl::desc("Print source locations."));
 
-cl::opt<bool> ShowCanonicalFnName("show-canonical-fname", cl::ReallyHidden,
-                                  cl::init(false), cl::ZeroOrMore,
-                                  cl::desc("Print canonical function name."));
+static cl::opt<bool>
+    ShowCanonicalFnName("show-canonical-fname", cl::init(false), cl::ZeroOrMore,
+                        cl::desc("Print canonical function name."));
 
-cl::opt<bool> ShowPseudoProbe(
-    "show-pseudo-probe", cl::ReallyHidden, cl::init(false), cl::ZeroOrMore,
+static cl::opt<bool> ShowPseudoProbe(
+    "show-pseudo-probe", cl::init(false), cl::ZeroOrMore,
     cl::desc("Print pseudo probe section and disassembled info."));
 
+static cl::opt<bool> UseDwarfCorrelation(
+    "use-dwarf-correlation", cl::init(false), cl::ZeroOrMore,
+    cl::desc("Use dwarf for profile correlation even when binary contains "
+             "pseudo probe."));
+
 static cl::list<std::string> DisassembleFunctions(
     "disassemble-functions", cl::CommaSeparated,
     cl::desc("List of functions to print disassembly for. Accept demangled "
@@ -271,6 +276,9 @@ void ProfiledBinary::setPreferredTextSegmentAddresses(const ELFObjectFileBase *O
 }
 
 void ProfiledBinary::decodePseudoProbe(const ELFObjectFileBase *Obj) {
+  if (UseDwarfCorrelation)
+    return;
+
   StringRef FileName = Obj->getFileName();
   for (section_iterator SI = Obj->section_begin(), SE = Obj->section_end();
        SI != SE; ++SI) {