Expose -mllvm -accurate-sample-profile to clang.

Summary: With accurate sample profile, we can do more aggressive size optimization. For some size-critical application, this can reduce the text size by 20%

Reviewers: davidxl, rsmith

Reviewed By: davidxl, rsmith

Subscribers: mehdi_amini, eraman, sanjoy, cfe-commits

Differential Revision: https://reviews.llvm.org/D37091

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@311707 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/clang/Driver/Options.td b/include/clang/Driver/Options.td
index 6f40bb03e35ecf380dff41b536fb2092fbc6ebd6..2c58e27363c160416cb1d7d55290400b761a801a 100644 (file)
--- a/include/clang/Driver/Options.td
+++ b/include/clang/Driver/Options.td
@@ -637,12 +637,25 @@ def fno_profile_sample_use : Flag<["-"], "fno-profile-sample-use">, Group<f_Grou
 def fprofile_sample_use_EQ : Joined<["-"], "fprofile-sample-use=">,
     Group<f_Group>, Flags<[DriverOption, CC1Option]>,
     HelpText<"Enable sample-based profile guided optimizations">;
+def fprofile_sample_accurate : Flag<["-"], "fprofile-sample-accurate">,
+    Group<f_Group>, Flags<[DriverOption, CC1Option]>,
+    HelpText<"Specifies that the sample profile is accurate">,
+    DocBrief<[{Specifies that the sample profile is accurate. If the sample
+               profile is accurate, callsites without profile samples are marked
+               as cold. Otherwise, treat callsites without profile samples as if
+               we have no profile}]>;
+def fno_profile_sample_accurate : Flag<["-"], "fno-profile-sample-accurate">,
+  Group<f_Group>, Flags<[DriverOption]>;
 def fauto_profile : Flag<["-"], "fauto-profile">, Group<f_Group>,
     Alias<fprofile_sample_use>;
 def fno_auto_profile : Flag<["-"], "fno-auto-profile">, Group<f_Group>,
     Alias<fno_profile_sample_use>;
 def fauto_profile_EQ : Joined<["-"], "fauto-profile=">,
     Alias<fprofile_sample_use_EQ>;
+def fauto_profile_accurate : Flag<["-"], "fauto-profile-accurate">,
+    Group<f_Group>, Alias<fprofile_sample_accurate>;
+def fno_auto_profile_accurate : Flag<["-"], "fno-auto-profile-accurate">,
+    Group<f_Group>, Alias<fno_profile_sample_accurate>;
 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.">;

diff --git a/include/clang/Frontend/CodeGenOptions.def b/include/clang/Frontend/CodeGenOptions.def
index 6a866fe5072363d2c283bf126492573104850d78..c9040e7e40184c1dc85ddf94adef32d275a5fcca 100644 (file)
--- a/include/clang/Frontend/CodeGenOptions.def
+++ b/include/clang/Frontend/CodeGenOptions.def
@@ -183,6 +183,7 @@ CODEGENOPT(UnsafeFPMath      , 1, 0) ///< Allow unsafe floating point optzns.
 CODEGENOPT(UnwindTables      , 1, 0) ///< Emit unwind tables.
 CODEGENOPT(VectorizeLoop     , 1, 0) ///< Run loop vectorizer.
 CODEGENOPT(VectorizeSLP      , 1, 0) ///< Run SLP vectorizer.
+CODEGENOPT(ProfileSampleAccurate, 1, 0) ///< Sample profile is accurate.
 
   /// Attempt to use register sized accesses to bit-fields in structures, when
   /// possible.

diff --git a/lib/CodeGen/CodeGenFunction.cpp b/lib/CodeGen/CodeGenFunction.cpp
index 17295ae2be8d80ea53d7d83e8eb529ac6d3748f4..a9a1a53be20b1539150a6ebce5e2fd42cda9a5e5 100644 (file)
--- a/lib/CodeGen/CodeGenFunction.cpp
+++ b/lib/CodeGen/CodeGenFunction.cpp
@@ -838,6 +838,10 @@ void CodeGenFunction::StartFunction(GlobalDecl GD,
   Fn->addFnAttr("no-jump-tables",
                 llvm::toStringRef(CGM.getCodeGenOpts().NoUseJumpTables));
 
+  // Add profile-sample-accurate value.
+  if (CGM.getCodeGenOpts().ProfileSampleAccurate)
+    Fn->addFnAttr("profile-sample-accurate");
+
   if (getLangOpts().OpenCL) {
     // Add metadata for a kernel function.
     if (const FunctionDecl *FD = dyn_cast_or_null<FunctionDecl>(D))

diff --git a/lib/Driver/ToolChains/Clang.cpp b/lib/Driver/ToolChains/Clang.cpp
index 35dcf206abb8002d234c87d09b65bd3caa6544f6..fa768b70c53e576271f9b4a31bad11e5ccc885c1 100644 (file)
--- a/lib/Driver/ToolChains/Clang.cpp
+++ b/lib/Driver/ToolChains/Clang.cpp
@@ -2340,6 +2340,10 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
                     true))
     CmdArgs.push_back("-fno-jump-tables");
 
+  if (Args.hasFlag(options::OPT_fprofile_sample_accurate,
+                   options::OPT_fno_profile_sample_accurate, false))
+    CmdArgs.push_back("-fprofile-sample-accurate");
+
   if (!Args.hasFlag(options::OPT_fpreserve_as_comments,
                     options::OPT_fno_preserve_as_comments, true))
     CmdArgs.push_back("-fno-preserve-as-comments");

diff --git a/lib/Frontend/CompilerInvocation.cpp b/lib/Frontend/CompilerInvocation.cpp
index 24a08e84dc40377511e25d10315c9ac8a4603ed9..aea3af982859a70d9997b2042a43f404873fc3bf 100644 (file)
--- a/lib/Frontend/CompilerInvocation.cpp
+++ b/lib/Frontend/CompilerInvocation.cpp
@@ -652,6 +652,8 @@ static bool ParseCodeGenArgs(CodeGenOptions &Opts, ArgList &Args, InputKind IK,
 
   Opts.NoUseJumpTables = Args.hasArg(OPT_fno_jump_tables);
 
+  Opts.ProfileSampleAccurate = Args.hasArg(OPT_fprofile_sample_accurate);
+
   Opts.PrepareForLTO = Args.hasArg(OPT_flto, OPT_flto_EQ);
   Opts.EmitSummaryIndex = false;
   if (Arg *A = Args.getLastArg(OPT_flto_EQ)) {

diff --git a/test/CodeGen/profile-sample-accurate.c b/test/CodeGen/profile-sample-accurate.c
new file mode 100644 (file)
index 0000000..cf628d5
--- /dev/null
+++ b/test/CodeGen/profile-sample-accurate.c
@@ -0,0 +1,7 @@
+// Test to ensure -emit-llvm profile-sample-accurate is honored by clang.
+// RUN: %clang -S -emit-llvm %s -fprofile-sample-accurate -o - | FileCheck %s
+
+// CHECK: define void @foo()
+// CHECK: attributes {{.*}} "profile-sample-accurate"
+void foo() {
+}

diff --git a/test/Driver/clang_f_opts.c b/test/Driver/clang_f_opts.c
index c17cec6eba9bcd1269b164b8c30f57349702fc76..bb058a00cdf7b6effba2b802f789790487b016f0 100644 (file)
--- a/test/Driver/clang_f_opts.c
+++ b/test/Driver/clang_f_opts.c
@@ -53,6 +53,9 @@
 // CHECK-REROLL-LOOPS: "-freroll-loops"
 // CHECK-NO-REROLL-LOOPS-NOT: "-freroll-loops"
 
+// RUN: %clang -### -S -fprofile-sample-accurate %s 2>&1 | FileCheck -check-prefix=CHECK-PROFILE-SAMPLE-ACCURATE %s
+// CHECK-PROFILE-SAMPLE-ACCURATE: "-fprofile-sample-accurate"
+
 // RUN: %clang -### -S -fprofile-sample-use=%S/Inputs/file.prof %s 2>&1 | FileCheck -check-prefix=CHECK-SAMPLE-PROFILE %s
 // CHECK-SAMPLE-PROFILE: "-fprofile-sample-use={{.*}}/file.prof"
 

diff --git a/test/Integration/thinlto_profile_sample_accurate.c b/test/Integration/thinlto_profile_sample_accurate.c
new file mode 100644 (file)
index 0000000..d7966c2
--- /dev/null
+++ b/test/Integration/thinlto_profile_sample_accurate.c
@@ -0,0 +1,9 @@
+// Test to ensure -emit-llvm profile-sample-accurate is honored in ThinLTO.
+// RUN: %clang -O2 %s -flto=thin -fprofile-sample-accurate -c -o %t.o
+// RUN: llvm-lto -thinlto -o %t %t.o
+// RUN: %clang_cc1 -O2 -x ir %t.o -fthinlto-index=%t.thinlto.bc -emit-llvm -o - | FileCheck %s
+
+// CHECK: define void @foo()
+// CHECK: attributes {{.*}} "profile-sample-accurate"
+void foo() {
+}