[llvm-profgen] Turn on cold profile trimming by default for non-CS profile

[wlei]

Summary

Turn on cold profile trimming by default for non-CS profile and use 10 as cold threshold which was well tuned number on our internal services.

[hoy]

lgtm, thx.

[wenlei]

lgtm with a nit.

llvm/tools/llvm-profgen/ProfileGenerator.cpp

392–394

If this functions takes ColdCntThreshold already, it'd be better to move the cold threshold setting out of it and pass in the final value.

[wlei]

As discussed offline, I will abandon this, user can specify the ProfileSummaryColdCount on their own side

llvm/test/tools/llvm-profgen/coroutine.test

-; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/coroutine.perfscript --binary=%S/Inputs/coroutine.perfbin --output=%t
+; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/coroutine.perfscript --binary=%S/Inputs/coroutine.perfbin --output=%t  --trim-cold-profile=0
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK
 
 ; Check that the head sample count for ticker is 0.
 ; CHECK: _Z6tickeri:67:0
 ; CHECK-NOT: _Z6tickeri.resume
 
 
 /*

llvm/test/tools/llvm-profgen/fs-discriminator.test

-; RUN: llvm-profgen --format=text --unsymbolized-profile=%S/Inputs/fs-discriminator.raw.prof --binary=%S/Inputs/fs-discriminator.perfbin --output=%t1
+; RUN: llvm-profgen --format=text --unsymbolized-profile=%S/Inputs/fs-discriminator.raw.prof --binary=%S/Inputs/fs-discriminator.perfbin --output=%t1  --trim-cold-profile=0
 ; RUN: FileCheck %s --input-file %t1 --check-prefix=CHECK
-; RUN: llvm-profgen --unsymbolized-profile=%S/Inputs/fs-discriminator.raw.prof --binary=%S/Inputs/fs-discriminator.perfbin --output=%t1
+; RUN: llvm-profgen --unsymbolized-profile=%S/Inputs/fs-discriminator.raw.prof --binary=%S/Inputs/fs-discriminator.perfbin --output=%t1  --trim-cold-profile=0
 ; RUN: llvm-profdata show --sample --show-sec-info-only %t1 | FileCheck %s --check-prefix=CHECK-SECTION
 
 ;CHECK-SECTION: ProfileSummarySection - Offset: [[#]], Size: [[#]], Flags: {fs-discriminator}
 
 ;CHECK: partition_pivot_last:88:1
 ;CHECK:  1: 4
 ;CHECK:  2: 4
 ;CHECK:  3: 4

llvm/test/tools/llvm-profgen/func-split.test

-; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/func-split.perfscript --binary=%S/Inputs/func-split.perfbin --output=%t
+; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/func-split.perfscript --binary=%S/Inputs/func-split.perfbin --output=%t  --trim-cold-profile=0
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK
-; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/func-split.perfscript --binary=%S/Inputs/func-split.perfbin --output=%t --ignore-stack-samples
+; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/func-split.perfscript --binary=%S/Inputs/func-split.perfbin --output=%t --ignore-stack-samples  --trim-cold-profile=0
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK-STRIP-CTX
 
 ;CHECK: [foo]:82:0
 ;CHECK:  2.1: 27
 ;CHECK:  3: 27
 ;CHECK:  3.1: 2 bar:2
 ;CHECK:  3.2: 26
 ;CHECK: [foo:3.1 @ bar]:2:0

llvm/test/tools/llvm-profgen/inline-noprobe.test

 ; 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 --unsymbolized-profile=%t --binary=%S/Inputs/inline-noprobe.perfbin --output=%t1
+; RUN: llvm-profgen --format=text --unsymbolized-profile=%t --binary=%S/Inputs/inline-noprobe.perfbin --output=%t1  --trim-cold-profile=0
 ; RUN: FileCheck %s --input-file %t1 --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: llvm-profgen --format=text --use-dwarf-correlation --perfscript=%S/Inputs/inline-noprobe.perfscript --binary=%S/Inputs/inline-noprobe.perfbin --output=%t  --trim-cold-profile=0
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK
 ; RUN: echo -e "0\n0" > %t
-; RUN: llvm-profgen --format=text --unsymbolized-profile=%t --binary=%S/Inputs/inline-noprobe.perfbin --output=%t1 --fill-zero-for-all-funcs
+; RUN: llvm-profgen --format=text --unsymbolized-profile=%t --binary=%S/Inputs/inline-noprobe.perfbin --output=%t1 --fill-zero-for-all-funcs  --trim-cold-profile=0
 ; RUN: FileCheck %s --input-file %t1 --check-prefix=CHECK-ALL-ZERO
-; RUN: llvm-profgen --format=text --unsymbolized-profile=%S/Inputs/out-of-bounds.raw.prof --binary=%S/Inputs/inline-noprobe.perfbin --output=%t1
+; RUN: llvm-profgen --format=text --unsymbolized-profile=%S/Inputs/out-of-bounds.raw.prof --binary=%S/Inputs/inline-noprobe.perfbin --output=%t1  --trim-cold-profile=0
 ; RUN: FileCheck %s --input-file %t1 --check-prefix=CHECK-OB
 
 CHECK: main:188:0
 CHECK:  0: 0
 CHECK:  2: 0
 CHECK:  1: foo:188
 CHECK:   2.1: 42
 CHECK:   3: 62

llvm/test/tools/llvm-profgen/inline-noprobe2.test

 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/artificial-branch.perfscript --binary=%S/Inputs/inline-noprobe2.perfbin --output=%t  --skip-symbolization --use-offset=0
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK-ARTIFICIAL-BRANCH
 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/inline-noprobe2.perfscript --binary=%S/Inputs/inline-noprobe2.perfbin --output=%t  --skip-symbolization --use-offset=0
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK-RAW-PROFILE
-; RUN: llvm-profgen --format=text --unsymbolized-profile=%t --binary=%S/Inputs/inline-noprobe2.perfbin --output=%t1 --use-offset=0
+; RUN: llvm-profgen --format=text --unsymbolized-profile=%t --binary=%S/Inputs/inline-noprobe2.perfbin --output=%t1 --use-offset=0  --trim-cold-profile=0
 ; RUN: FileCheck %s --input-file %t1 --check-prefix=CHECK
 
-; RUN: llvm-profgen --format=extbinary --perfscript=%S/Inputs/inline-noprobe2.perfscript --binary=%S/Inputs/inline-noprobe2.perfbin --output=%t --populate-profile-symbol-list=1
+; RUN: llvm-profgen --format=extbinary --perfscript=%S/Inputs/inline-noprobe2.perfscript --binary=%S/Inputs/inline-noprobe2.perfbin --output=%t --populate-profile-symbol-list=1  --trim-cold-profile=0
 ; RUN: llvm-profdata show -show-prof-sym-list -sample %t | FileCheck %s --check-prefix=CHECK-SYM-LIST
 
 ; CHECK-ARTIFICIAL-BRANCH: 3
 ; CHECK-ARTIFICIAL-BRANCH: 400540-400540:1
 ; CHECK-ARTIFICIAL-BRANCH: 400870-400870:2
 ; CHECK-ARTIFICIAL-BRANCH: 400875-4008bf:1
 ; CHECK-ARTIFICIAL-BRANCH: 2
 ; CHECK-ARTIFICIAL-BRANCH: 400870->400540:2

llvm/test/tools/llvm-profgen/noinline-noprobe.test

 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/noprobe.perfscript --binary=%S/Inputs/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/noprobe.mmap.perfscript --binary=%S/Inputs/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/noprobe.aggperfscript --binary=%S/Inputs/noprobe.perfbin --output=%t --skip-symbolization
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK-RAW-PROFILE-AGG
-; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/noprobe.perfscript --binary=%S/Inputs/noprobe.perfbin --output=%t
+; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/noprobe.perfscript --binary=%S/Inputs/noprobe.perfbin --output=%t --trim-cold-profile=0
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK
 
 CHECK: bar:77:21
 CHECK:  0: 20
 CHECK:  1: 20
 CHECK:  2: 13
 CHECK:  4: 6
 CHECK:  5: 18

llvm/test/tools/llvm-profgen/profile-density.test

-; RUN: llvm-profgen --format=text --unsymbolized-profile=%S/Inputs/profile-density.raw.prof --binary=%S/Inputs/inline-noprobe2.perfbin --output=%t1 --use-offset=0 --show-density -hot-function-density-threshold=1 &> %t2
+; RUN: llvm-profgen --format=text --unsymbolized-profile=%S/Inputs/profile-density.raw.prof --binary=%S/Inputs/inline-noprobe2.perfbin --output=%t1 --use-offset=0 --show-density -hot-function-density-threshold=1  --trim-cold-profile=0 &> %t2
 ; RUN: FileCheck %s --input-file %t2 --check-prefix=CHECK-DENSITY
 
-; RUN: llvm-profgen --format=text --unsymbolized-profile=%S/Inputs/profile-density-cs.raw.prof --binary=%S/Inputs/inline-noprobe2.perfbin --output=%t3 --show-density -hot-function-density-threshold=1 &> %t4
+; RUN: llvm-profgen --format=text --unsymbolized-profile=%S/Inputs/profile-density-cs.raw.prof --binary=%S/Inputs/inline-noprobe2.perfbin --output=%t3 --show-density -hot-function-density-threshold=1  --trim-cold-profile=0 &> %t4
 ; RUN: FileCheck %s --input-file %t4 --check-prefix=CHECK-DENSITY-CS
 
 ;CHECK-DENSITY: AutoFDO is estimated to optimize better with 4.9x more samples. Please consider increasing sampling rate or profiling for longer duration to get more samples.
 ;CHECK-DENSITY: Minimum profile density for hot functions with top 99.00% total samples: 0.2
 
 ;CHECK-DENSITY-CS: Minimum profile density for hot functions with top 99.00% total samples: 31.4
 
 ; original code:

llvm/tools/llvm-profgen/ProfileGenerator.cpp

static cl::opt<double> HotFunctionDensityThreshold(
     llvm::cl::desc(
         "specify density threshold for hot functions (default: 1000)"),
     llvm::cl::Optional);
 static cl::opt<bool> ShowDensity("show-density", llvm::cl::init(false),
                                  llvm::cl::desc("show profile density details"),
                                  llvm::cl::Optional);
 
 extern cl::opt<int> ProfileSummaryCutoffHot;
+extern cl::opt<int> ProfileSummaryCutoffCold;
+extern cl::opt<int> ProfileSummaryColdCount;
 
 using namespace llvm;
 using namespace sampleprof;
 
 namespace llvm {
 namespace sampleprof {
 
 // Initialize the MaxCompressionSize to -1 which means no size limit

 void ProfileGenerator::postProcessProfiles() {
   computeSummaryAndThreshold();
   trimColdProfiles(ProfileMap, ColdCountThreshold);
   calculateAndShowDensity(ProfileMap);
 }
 
 void ProfileGenerator::trimColdProfiles(const SampleProfileMap &Profiles,
                                         uint64_t ColdCntThreshold) {
-  if (!TrimColdProfile)
+  if (TrimColdProfile.getNumOccurrences() && !TrimColdProfile)
     return;
 
+  if (!ProfileSummaryCutoffCold.getNumOccurrences() &&
+      !ProfileSummaryColdCount.getNumOccurrences())
+    ColdCntThreshold = 10;
+
   // Move cold profiles into a tmp container.
   std::vector<SampleContext> ColdProfiles;
   for (const auto &I : ProfileMap) {
     if (I.second.getTotalSamples() < ColdCntThreshold)
       ColdProfiles.emplace_back(I.first);
   }
 
   // Remove the cold profile from ProfileMap.