[SampleFDO] Treat names in profile as not cold only when profile symbol list is available

[wmi]

Summary

In rL372232, we treated names showing up in profile as not cold when profile-sample-accurate is enabled. This caused 70k size regression in Chrome/Android. The patch put a guard and only enable the change when profile symbol list is available, i.e., keep the old behavior when profile symbol list is not available.

[davidxl]

lgtm

llvm/trunk/lib/Transforms/IPO/SampleProfile.cpp

bool SampleProfileLoader::runOnFunction(Function &F, ModuleAnalysisManager *AM) {
   // this will be overwritten in emitAnnotations.
   uint64_t initialEntryCount = -1;
 
   ProfSampleAccEnabled =
       ProfileSampleAccurate || F.hasFnAttribute("profile-sample-accurate");
   if (ProfSampleAccEnabled) {
     // PSL -- profile symbol list include all the symbols in sampled binary.
     // It is used to prevent new functions to be treated as cold.
-    // If ProfileSampleAccurate is true or F has profile-sample-accurate
-    // attribute, and if there is no profile symbol list read in, initialize
-    // all the function entry counts to 0; if there is profile symbol list, only
-    // initialize the entry count to 0 when current function is in the list.
-    if (!PSL || PSL->contains(F.getName()))
+    if (PSL) {
+      // Profile symbol list is available, initialize the entry count to 0
+      // only for functions in the list.
+      if (PSL->contains(F.getName()))
         initialEntryCount = 0;
 
       // When ProfileSampleAccurate is true, function without sample will be
       // regarded as cold. To minimize the potential negative performance
       // impact it could have, we want to be a little conservative here
       // saying if a function shows up in the profile, no matter as outline
       // function, inline instance or call targets, treat the function as not
       // being cold. This will handle the cases such as most callsites of a
       // function are inlined in sampled binary but not inlined in current
       // build (because of source code drift, imprecise debug information, or
-    // the callsites are all cold individually but not cold accumulatively...),
-    // so the outline function showing up as cold in sampled binary will
-    // actually not be cold after current build.
+      // the callsites are all cold individually but not cold
+      // accumulatively...), so the outline function showing up as cold in
+      // sampled binary will actually not be cold after current build.
       StringRef CanonName = FunctionSamples::getCanonicalFnName(F);
       if (NamesInProfile.count(CanonName))
         initialEntryCount = -1;
+    } else {
+      // If there is no profile symbol list available, initialize all the
+      // function entry counts to 0. It means all the functions without
+      // profile will be regarded as cold.
+      initialEntryCount = 0;
+    }
   }
 
   F.setEntryCount(ProfileCount(initialEntryCount, Function::PCT_Real));
   std::unique_ptr<OptimizationRemarkEmitter> OwnedORE;
   if (AM) {
     auto &FAM =
         AM->getResult<FunctionAnalysisManagerModuleProxy>(*F.getParent())
             .getManager();

llvm/trunk/test/Transforms/SampleProfile/profile-sample-accurate.ll

 ; RUN: opt < %s -sample-profile -sample-profile-file=%S/Inputs/profsampleacc.extbinary.afdo -profile-summary-cutoff-hot=600000 -profile-sample-accurate -S | FileCheck %s
 ; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/profsampleacc.extbinary.afdo -profile-summary-cutoff-hot=600000 -profile-sample-accurate -S | FileCheck %s
-; With the hot cutoff being set to 600000, the inline instance of _Z3sumii
-; in main is neither hot nor cold. Check it will still be inlined when
-; profile-sample-accurate is enabled, and check _Z3sumii's function entry
-; count won't be initialized to 0 because it shows up in the profile as
-; inline instance.
-
+; RUN: llvm-profdata merge -sample -extbinary -prof-sym-list=%S/Inputs/profile-symbol-list.text %S/Inputs/profsampleacc.extbinary.afdo -o %t.symlist.afdo
+; RUN: opt < %s -sample-profile -sample-profile-file=%t.symlist.afdo -profile-summary-cutoff-hot=600000 -profile-sample-accurate -S | FileCheck %s --check-prefix=PROFSYMLIST
+; RUN: opt < %s -passes=sample-profile -sample-profile-file=%t.symlist.afdo -profile-summary-cutoff-hot=600000 -profile-sample-accurate -S | FileCheck %s --check-prefix=PROFSYMLIST
+;
 ; Original C++ test case
 ;
 ; #include <stdio.h>
 ;
 ; int sum(int x, int y) {
 ;   return x + y;
 ; }
 ;
 ; int main() {
 ;   int s, i = 0;
 ;   while (i++ < 20000 * 20000)
 ;     if (i != 100) s = sum(i, s); else s = 30;
 ;   printf("sum is %d\n", s);
 ;   return 0;
 ; }
 ;
 @.str = private unnamed_addr constant [11 x i8] c"sum is %d\0A\00", align 1
 
-; CHECK: define i32 @_Z3sumii{{.*}}!prof ![[UNKNOWN_ID:[0-9]+]]
+; Check _Z3sumii's function entry count will be intialized to 0 if no profile
+; symbol list is available.
+; If symbol list is available, _Z3sumii's function entry count will be
+; initialized to -1 if it shows up in the profile.
+;
+; CHECK: define i32 @_Z3sumii{{.*}}!prof ![[ZERO_ID:[0-9]+]]
+; PROFSYMLIST: define i32 @_Z3sumii{{.*}}!prof ![[UNKNOWN_ID:[0-9]+]]
 ; Function Attrs: nounwind uwtable
 define i32 @_Z3sumii(i32 %x, i32 %y) !dbg !4 {
 entry:
   %x.addr = alloca i32, align 4
   %y.addr = alloca i32, align 4
   store i32 %x, i32* %x.addr, align 4
   store i32 %y, i32* %y.addr, align 4
   %0 = load i32, i32* %x.addr, align 4, !dbg !11
while.cond:                                       ; preds = %if.end, %entry
   %cmp = icmp slt i32 %0, 400000000, !dbg !14
   br i1 %cmp, label %while.body, label %while.end, !dbg !14
 
 while.body:                                       ; preds = %while.cond
   %1 = load i32, i32* %i, align 4, !dbg !16
   %cmp1 = icmp ne i32 %1, 100, !dbg !16
   br i1 %cmp1, label %if.then, label %if.else, !dbg !16
 
-; Check _Z3sumii is inlined at this callsite.
+; With the hot cutoff being set to 600000, the inline instance of _Z3sumii
+; in main is neither hot nor cold. Check it will still be inlined when
+; profile-sample-accurate is enabled.
 ; CHECK: if.then:
 ; CHECK-NOT: call i32 @_Z3sumii
 ; CHECK: if.else:
+; PROFSYMLIST: if.then:
+; PROFSYMLIST-NOT: call i32 @_Z3sumii
+; PROFSYMLIST: if.else:
 if.then:                                          ; preds = %while.body
   %2 = load i32, i32* %i, align 4, !dbg !18
   %3 = load i32, i32* %s, align 4, !dbg !18
   %call = call i32 @_Z3sumii(i32 %2, i32 %3), !dbg !18
   store i32 %call, i32* %s, align 4, !dbg !18
   br label %if.end, !dbg !18
 
 if.else:                                          ; preds = %while.body

 }
 
 declare i32 @printf(i8*, ...) #2
 
 !llvm.dbg.cu = !{!0}
 !llvm.module.flags = !{!8, !9}
 !llvm.ident = !{!10}
 
-; CHECK: ![[UNKNOWN_ID]] = !{!"function_entry_count", i64 -1}
+; CHECK: ![[ZERO_ID]] = !{!"function_entry_count", i64 0}
+; PROFSYMLIST: ![[UNKNOWN_ID]] = !{!"function_entry_count", i64 -1}
 !0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, producer: "clang version 3.5 ", isOptimized: false, emissionKind: NoDebug, file: !1, enums: !2, retainedTypes: !2, globals: !2, imports: !2)
 !1 = !DIFile(filename: "calls.cc", directory: ".")
 !2 = !{}
 !4 = distinct !DISubprogram(name: "sum", line: 3, isLocal: false, isDefinition: true, virtualIndex: 6, flags: DIFlagPrototyped, isOptimized: false, unit: !0, scopeLine: 3, file: !1, scope: !5, type: !6, retainedNodes: !2)
 !5 = !DIFile(filename: "calls.cc", directory: ".")
 !6 = !DISubroutineType(types: !2)
 !7 = distinct !DISubprogram(name: "main", line: 7, isLocal: false, isDefinition: true, virtualIndex: 6, flags: DIFlagPrototyped, isOptimized: false, unit: !0, scopeLine: 7, file: !1, scope: !5, type: !6, retainedNodes: !2)
 !8 = !{i32 2, !"Dwarf Version", i32 4}