[CSSPGO][llvm-profgen] Change default cold threshold for context merging

[wenlei]

Summary

llvm-profgen uses profile summary based cold threshold to merge and trim cold context profile. This is to strike a good balance between profile size and performance.

We've been using 99.9% as the cutoff to save profile size without affecting performance. This change switch to use 99.9% instead of 99.9999% as default cold threshold cutoff for llvm-profgen.

Redundant switch csprof-cold-thres is also removed and tests cleaned up.

[wmi]

LGTM.

[wlei]

LGTM, thanks!

llvm/test/tools/llvm-profgen/cs-extbinary.test

 ; test for dwarf-based cs profile
-; RUN: llvm-profgen --format=extbinary --perfscript=%S/Inputs/recursion-compression-noprobe.perfscript --binary=%S/Inputs/recursion-compression-noprobe.perfbin --output=%t1 --csprof-cold-thres=0
+; RUN: llvm-profgen --format=extbinary --perfscript=%S/Inputs/recursion-compression-noprobe.perfscript --binary=%S/Inputs/recursion-compression-noprobe.perfbin --output=%t1 --profile-summary-cold-count=0
 ; RUN: llvm-profdata merge --sample --text --output=%t2 %t1
 ; RUN: FileCheck %S/recursion-compression-noprobe.test --input-file %t2
 ; RUN: llvm-profdata merge --sample --extbinary --output=%t3 %t2 && llvm-profdata merge --sample --text --output=%t4 %t3
 ; RUN: diff -b %t2 %t4
 
 
 ; test for probe-based cs profile
-; RUN: llvm-profgen --format=extbinary --perfscript=%S/Inputs/recursion-compression-pseudoprobe.perfscript --binary=%S/Inputs/recursion-compression-pseudoprobe.perfbin --output=%t5 --csprof-cold-thres=0
+; RUN: llvm-profgen --format=extbinary --perfscript=%S/Inputs/recursion-compression-pseudoprobe.perfscript --binary=%S/Inputs/recursion-compression-pseudoprobe.perfbin --output=%t5 --profile-summary-cold-count=0
 ; RUN: llvm-profdata merge --sample --text --output=%t6 %t5
 ; RUN: FileCheck %S/recursion-compression-pseudoprobe.test --input-file %t6
 ; RUN: llvm-profdata merge --sample --extbinary --output=%t7 %t6 && llvm-profdata merge --sample --text --output=%t8 %t7
 ; RUN: diff -b %t6 %t8

llvm/test/tools/llvm-profgen/fname-canonicalization.test

 ; Test unique linkage name decoding and canonicalization from dwarf debug info
-; RUN: llvm-profgen --perfscript=%S/Inputs/unique-linkage-name-dwarf.perfscript --binary=%S/Inputs/unique-linkage-name-dwarf.perfbin --output=%t --csprof-cold-thres=0
+; RUN: llvm-profgen --perfscript=%S/Inputs/unique-linkage-name-dwarf.perfscript --binary=%S/Inputs/unique-linkage-name-dwarf.perfbin --output=%t --profile-summary-cold-count=0
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK-DWARF-FNAME
 
 ; CHECK-DWARF-FNAME:[main:1 @ foo]:309:0
 ; CHECK-DWARF-FNAME: 2: 14
 ; CHECK-DWARF-FNAME: 3: 29 bar.__uniq.26267048767521081047744692097241227776:14
 ; CHECK-DWARF-FNAME:[main:1 @ foo:3 @ bar.__uniq.26267048767521081047744692097241227776]:84:0
 ; CHECK-DWARF-FNAME: 1: 14
 
 
 ; Test unique linkage name decoding and canonicalization from pseudo probe info
-; RUN: llvm-profgen --perfscript=%S/Inputs/unique-linkage-name-probe.perfscript --binary=%S/Inputs/unique-linkage-name-probe.perfbin --output=%t --csprof-cold-thres=0
+; RUN: llvm-profgen --perfscript=%S/Inputs/unique-linkage-name-probe.perfscript --binary=%S/Inputs/unique-linkage-name-probe.perfbin --output=%t --profile-summary-cold-count=0
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK-PROBE-FNAME
 
 ; CHECK-PROBE-FNAME:[main:2 @ foo]:75:0
 ; CHECK-PROBE-FNAME: 2: 15
 ; CHECK-PROBE-FNAME: 3: 15
 ; CHECK-PROBE-FNAME: 4: 15
 ; CHECK-PROBE-FNAME: 6: 15
 ; CHECK-PROBE-FNAME: 8: 15 _ZL3barii.__uniq.26267048767521081047744692097241227776:15

llvm/test/tools/llvm-profgen/inline-cs-dangling-pseudoprobe.test

-; RUN: llvm-profgen --perfscript=%S/Inputs/inline-cs-dangling-pseudoprobe.perfscript --binary=%S/Inputs/inline-cs-pseudoprobe.perfbin --output=%t --show-unwinder-output --csprof-cold-thres=0 | FileCheck %s --check-prefix=CHECK-UNWINDER
+; RUN: llvm-profgen --perfscript=%S/Inputs/inline-cs-dangling-pseudoprobe.perfscript --binary=%S/Inputs/inline-cs-pseudoprobe.perfbin --output=%t --show-unwinder-output --profile-summary-cold-count=0 | FileCheck %s --check-prefix=CHECK-UNWINDER
 ; RUN: FileCheck %s --input-file %t
 
 ; CHECK:     [main:2 @ foo]:58:0
 ; CHECK-NEXT: 2: 15
 ; CHECK-NEXT: 3: 14
 ; CHECK-NEXT: 5: 14
 ; CHECK-NEXT: 6: 15
 ; CHECK-NEXT: !CFGChecksum: 138950591924

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

-; RUN: llvm-profgen --perfscript=%S/Inputs/inline-cs-noprobe.perfscript --binary=%S/Inputs/inline-cs-noprobe.perfbin --output=%t --show-unwinder-output --csprof-cold-thres=0 | FileCheck %s --check-prefix=CHECK-UNWINDER
+; RUN: llvm-profgen --perfscript=%S/Inputs/inline-cs-noprobe.perfscript --binary=%S/Inputs/inline-cs-noprobe.perfbin --output=%t --show-unwinder-output --profile-summary-cold-count=0 | FileCheck %s --check-prefix=CHECK-UNWINDER
 ; RUN: FileCheck %s --input-file %t
 
 ; CHECK:[main:1 @ foo]:309:0
 ; CHECK: 2.1: 14
 ; CHECK: 3: 15
 ; CHECK: 3.1: 14 bar:14
 ; CHECK: 3.2: 1
 ; CHECK:[main:1 @ foo:3.1 @ bar]:84:0

llvm/test/tools/llvm-profgen/inline-cs-pseudoprobe.test

-; RUN: llvm-profgen --perfscript=%S/Inputs/inline-cs-pseudoprobe.perfscript --binary=%S/Inputs/inline-cs-pseudoprobe.perfbin --output=%t --show-unwinder-output --csprof-cold-thres=0 | FileCheck %s --check-prefix=CHECK-UNWINDER
+; RUN: llvm-profgen --perfscript=%S/Inputs/inline-cs-pseudoprobe.perfscript --binary=%S/Inputs/inline-cs-pseudoprobe.perfbin --output=%t --show-unwinder-output --profile-summary-cold-count=0 | FileCheck %s --check-prefix=CHECK-UNWINDER
 ; RUN: FileCheck %s --input-file %t
 
 ; CHECK:     [main:2 @ foo]:74:0
 ; CHECK-NEXT: 2: 15
 ; CHECK-NEXT: 3: 15
 ; CHECK-NEXT: 4: 14
 ; CHECK-NEXT: 5: 1
 ; CHECK-NEXT: 6: 15

llvm/test/tools/llvm-profgen/merge-cold-profile.test

 ; Used the data from recursion-compression.test, refer it for the unmerged output
-; RUN: llvm-profgen --perfscript=%S/Inputs/recursion-compression-pseudoprobe.perfscript --binary=%S/Inputs/recursion-compression-pseudoprobe.perfbin --output=%t1 --compress-recursion=-1 --csprof-cold-thres=8
+; RUN: llvm-profgen --perfscript=%S/Inputs/recursion-compression-pseudoprobe.perfscript --binary=%S/Inputs/recursion-compression-pseudoprobe.perfbin --output=%t1 --compress-recursion=-1 --profile-summary-cold-count=8
 ; RUN: FileCheck %s --input-file %t1
 
 ; Test --csprof-trim-cold-context=0
-; RUN: llvm-profgen --perfscript=%S/Inputs/recursion-compression-pseudoprobe.perfscript --binary=%S/Inputs/recursion-compression-pseudoprobe.perfbin --output=%t2 --compress-recursion=-1 --csprof-cold-thres=100 --csprof-trim-cold-context=0
+; RUN: llvm-profgen --perfscript=%S/Inputs/recursion-compression-pseudoprobe.perfscript --binary=%S/Inputs/recursion-compression-pseudoprobe.perfbin --output=%t2 --compress-recursion=-1 --profile-summary-cold-count=100 --csprof-trim-cold-context=0
 ; RUN: FileCheck %s --input-file %t2 --check-prefix=CHECK-KEEP-COLD
 
 ; Test --csprof-merge-cold-context=0
-; RUN: llvm-profgen --perfscript=%S/Inputs/recursion-compression-pseudoprobe.perfscript --binary=%S/Inputs/recursion-compression-pseudoprobe.perfbin --output=%t3 --compress-recursion=-1 --csprof-cold-thres=10 --csprof-merge-cold-context=0
+; RUN: llvm-profgen --perfscript=%S/Inputs/recursion-compression-pseudoprobe.perfscript --binary=%S/Inputs/recursion-compression-pseudoprobe.perfbin --output=%t3 --compress-recursion=-1 --profile-summary-cold-count=10 --csprof-merge-cold-context=0
 ; RUN: FileCheck %s --input-file %t3 --check-prefix=CHECK-UNMERGED
 
 ; CHECK:     [fa]:14:4
 ; CHECK-NEXT: 1: 4
 ; CHECK-NEXT: 2: 18446744073709551615
 ; CHECK-NEXT: 3: 4
 ; CHECK-NEXT: 4: 2
 ; CHECK-NEXT: 5: 1

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

-; RUN: llvm-profgen --perfscript=%S/Inputs/noinline-cs-noprobe.perfscript --binary=%S/Inputs/noinline-cs-noprobe.perfbin --output=%t --show-unwinder-output --csprof-cold-thres=0 | FileCheck %s --check-prefix=CHECK-UNWINDER
+; RUN: llvm-profgen --perfscript=%S/Inputs/noinline-cs-noprobe.perfscript --binary=%S/Inputs/noinline-cs-noprobe.perfbin --output=%t --show-unwinder-output --profile-summary-cold-count=0 | FileCheck %s --check-prefix=CHECK-UNWINDER
 ; RUN: FileCheck %s --input-file %t
 
 ; CHECK:[main:1 @ foo]:54:0
 ; CHECK: 2: 3
 ; CHECK: 3: 3 bar:3
 ; CHECK:[main:1 @ foo:3 @ bar]:50:3
 ; CHECK: 0: 3
 ; CHECK: 1: 3

llvm/test/tools/llvm-profgen/noinline-cs-pseudoprobe.test

-; RUN: llvm-profgen --perfscript=%S/Inputs/noinline-cs-pseudoprobe.perfscript --binary=%S/Inputs/noinline-cs-pseudoprobe.perfbin --output=%t --show-unwinder-output --csprof-cold-thres=0 | FileCheck %s --check-prefix=CHECK-UNWINDER
+; RUN: llvm-profgen --perfscript=%S/Inputs/noinline-cs-pseudoprobe.perfscript --binary=%S/Inputs/noinline-cs-pseudoprobe.perfbin --output=%t --show-unwinder-output --profile-summary-cold-count=0 | FileCheck %s --check-prefix=CHECK-UNWINDER
 ; RUN: FileCheck %s --input-file %t
 
 ; CHECK:     [main:2 @ foo]:75:0
 ; CHECK-NEXT: 2: 15
 ; CHECK-NEXT: 3: 15
 ; CHECK-NEXT: 4: 15
 ; CHECK-NEXT: 6: 15
 ; CHECK-NEXT: 8: 15 bar:15

llvm/test/tools/llvm-profgen/recursion-compression-noprobe.test

 ; Firstly test uncompression(--compress-recursion=0)
-; RUN: llvm-profgen --perfscript=%S/Inputs/recursion-compression-noprobe.perfscript --binary=%S/Inputs/recursion-compression-noprobe.perfbin --output=%t --compress-recursion=0 --csprof-cold-thres=0
+; RUN: llvm-profgen --perfscript=%S/Inputs/recursion-compression-noprobe.perfscript --binary=%S/Inputs/recursion-compression-noprobe.perfbin --output=%t --compress-recursion=0 --profile-summary-cold-count=0
 ; RUN: FileCheck %s --input-file %t -check-prefix=CHECK-UNCOMPRESS
-; RUN: llvm-profgen --perfscript=%S/Inputs/recursion-compression-noprobe.perfscript --binary=%S/Inputs/recursion-compression-noprobe.perfbin --output=%t --csprof-cold-thres=0
+; RUN: llvm-profgen --perfscript=%S/Inputs/recursion-compression-noprobe.perfscript --binary=%S/Inputs/recursion-compression-noprobe.perfbin --output=%t --profile-summary-cold-count=0
 ; RUN: FileCheck %s --input-file %t
 
 ; CHECK-UNCOMPRESS:[main:1 @ foo:3 @ fa:2 @ fb]:48:0
 ; CHECK-UNCOMPRESS: 1: 11
 ; CHECK-UNCOMPRESS: 2: 1 fa:1
 ; CHECK-UNCOMPRESS:[main:1 @ foo:3 @ fa]:24:0
 ; CHECK-UNCOMPRESS: 1: 1
 ; CHECK-UNCOMPRESS: 2: 13 fb:11

llvm/test/tools/llvm-profgen/recursion-compression-pseudoprobe.test

 ; Firstly test uncompression(--compress-recursion=0)
-; RUN: llvm-profgen --perfscript=%S/Inputs/recursion-compression-pseudoprobe.perfscript --binary=%S/Inputs/recursion-compression-pseudoprobe.perfbin --output=%t --compress-recursion=0 --csprof-cold-thres=0
+; RUN: llvm-profgen --perfscript=%S/Inputs/recursion-compression-pseudoprobe.perfscript --binary=%S/Inputs/recursion-compression-pseudoprobe.perfbin --output=%t --compress-recursion=0 --profile-summary-cold-count=0
 ; RUN: FileCheck %s --input-file %t -check-prefix=CHECK-UNCOMPRESS
-; RUN: llvm-profgen --perfscript=%S/Inputs/recursion-compression-pseudoprobe.perfscript --binary=%S/Inputs/recursion-compression-pseudoprobe.perfbin --output=%t --show-unwinder-output --csprof-cold-thres=0 | FileCheck %s --check-prefix=CHECK-UNWINDER
+; RUN: llvm-profgen --perfscript=%S/Inputs/recursion-compression-pseudoprobe.perfscript --binary=%S/Inputs/recursion-compression-pseudoprobe.perfbin --output=%t --show-unwinder-output --profile-summary-cold-count=0 | FileCheck %s --check-prefix=CHECK-UNWINDER
 ; RUN: FileCheck %s --input-file %t
 
 ; CHECK-UNCOMPRESS: [main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:6 @ fa:8 @ fa:7 @ fb:6 @ fa]:4:1
 ; CHECK-UNCOMPRESS:  1: 1
 ; CHECK-UNCOMPRESS:  3: 1
 ; CHECK-UNCOMPRESS:  4: 1
 ; CHECK-UNCOMPRESS:  7: 1 fb:1
 ; CHECK-UNCOMPRESS:  !CFGChecksum: 120515930909

llvm/tools/llvm-profgen/ProfileGenerator.cpp

 
 static cl::opt<int32_t, true> RecursionCompression(
     "compress-recursion",
     cl::desc("Compressing recursion by deduplicating adjacent frame "
              "sequences up to the specified size. -1 means no size limit."),
     cl::Hidden,
     cl::location(llvm::sampleprof::CSProfileGenerator::MaxCompressionSize));
 
-static cl::opt<uint64_t> CSProfColdThreshold(
-    "csprof-cold-thres", cl::init(100), cl::ZeroOrMore,
-    cl::desc("Specify the total samples threshold for a context profile to "
-             "be considered cold, any cold profiles will be merged into "
-             "context-less base profiles"));
-
 static cl::opt<bool> CSProfMergeColdContext(
     "csprof-merge-cold-context", cl::init(true), cl::ZeroOrMore,
-    cl::desc("This works together with --csprof-cold-thres. If the total count "
-             "of context profile is smaller than the threshold, it will be "
-             "merged into context-less base profile."));
+    cl::desc("If the total count of context profile is smaller than "
+             "the threshold, it will be merged into context-less base "
+             "profile."));
 
 static cl::opt<bool> CSProfTrimColdContext(
     "csprof-trim-cold-context", cl::init(true), cl::ZeroOrMore,
-    cl::desc("This works together with --csprof-cold-thres. If the total count "
-             "of the profile after all merge is done is still smaller than "
-             "threshold, it will be trimmed."));
+    cl::desc("If the total count of the profile after all merge is done "
+             "is still smaller than threshold, it will be trimmed."));
+
+extern cl::opt<int> ProfileSummaryCutoffCold;
 
 using namespace llvm;
 using namespace sampleprof;
 
 namespace llvm {
 namespace sampleprof {
 
 // Initialize the MaxCompressionSize to -1 which means no size limit
void CSProfileGenerator::postProcessProfiles() {
 
   // Trim and merge cold context profile using cold threshold above;
   SampleContextTrimmer(ProfileMap)
       .trimAndMergeColdContextProfiles(
           ColdCountThreshold, CSProfTrimColdContext, CSProfMergeColdContext);
 }
 
 void CSProfileGenerator::computeSummaryAndThreshold() {
+  // Update the default value of cold cutoff for llvm-profgen.
+  // Do it here because we don't want to change the global default,
+  // which would lead CS profile size too large.
+  if (!ProfileSummaryCutoffCold.getNumOccurrences())
+    ProfileSummaryCutoffCold = 999000;
+
   SampleProfileSummaryBuilder Builder(ProfileSummaryBuilder::DefaultCutoffs);
   auto Summary = Builder.computeSummaryForProfiles(ProfileMap);
   HotCountThreshold = ProfileSummaryBuilder::getHotCountThreshold(
       (Summary->getDetailedSummary()));
   ColdCountThreshold = ProfileSummaryBuilder::getColdCountThreshold(
       (Summary->getDetailedSummary()));
-
-  // Use threshold calculated from profile summary unless specified.
-  if (CSProfColdThreshold.getNumOccurrences()) {
-    ColdCountThreshold = CSProfColdThreshold;
-  }
 }
 
 void CSProfileGenerator::write(std::unique_ptr<SampleProfileWriter> Writer,
                                StringMap<FunctionSamples> &ProfileMap) {
   if (std::error_code EC = Writer->write(ProfileMap))
     exitWithError(std::move(EC));
 }