llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT--> @llvm/pr-subscribers-bolt Author: Amir Ayupov (aaupov) <details> <summary>Changes</summary> Heatmap collects samples grouped by buckets. The size is configurable via `--block-size`, with 64 bytes as the default (X86 cache line size). Define section utilization as the number of buckets mapped to the section with non-zero samples divided by the total number of buckets covering the section. Note that for buckets that cross section boundaries, we will attribute the utilization to the first overlapping section. Test Plan: updated heatmap-preagg.test --- Full diff: https://github.com/llvm/llvm-project/pull/139193.diff 4 Files Affected: - (modified) bolt/include/bolt/Profile/Heatmap.h (+20-2) - (modified) bolt/lib/Profile/DataAggregator.cpp (+4-2) - (modified) bolt/lib/Profile/Heatmap.cpp (+46-21) - (modified) bolt/test/X86/heatmap-preagg.test (+11-9) ``````````diff diff --git a/bolt/include/bolt/Profile/Heatmap.h b/bolt/include/bolt/Profile/Heatmap.h index fc1e2cd30011e..c7b3d45fa5cc2 100644 --- a/bolt/include/bolt/Profile/Heatmap.h +++ b/bolt/include/bolt/Profile/Heatmap.h @@ -9,6 +9,7 @@ #ifndef BOLT_PROFILE_HEATMAP_H #define BOLT_PROFILE_HEATMAP_H +#include "llvm/ADT/StringMap.h" #include "llvm/ADT/StringRef.h" #include <cstdint> #include <map> @@ -45,6 +46,10 @@ class Heatmap { /// Map section names to their address range. const std::vector<SectionNameAndRange> TextSections; + uint64_t getNumBuckets(uint64_t Begin, uint64_t End) const { + return End / BucketSize + !!(End % BucketSize) - Begin / BucketSize; + }; + public: explicit Heatmap(uint64_t BucketSize = 4096, uint64_t MinAddress = 0, uint64_t MaxAddress = std::numeric_limits<uint64_t>::max(), @@ -77,9 +82,22 @@ class Heatmap { void printCDF(raw_ostream &OS) const; - void printSectionHotness(StringRef Filename) const; + /// Struct describing individual section hotness. + struct SectionStats { + uint64_t Samples{0}; + uint64_t Buckets{0}; + }; + + /// Mapping from section name to associated \p SectionStats. Special entries: + /// - [total] for total stats, + /// - [unmapped] for samples outside any section, if non-zero. + using SectionStatsMap = StringMap<SectionStats>; + + SectionStatsMap computeSectionStats() const; + + void printSectionHotness(const SectionStatsMap &, StringRef Filename) const; - void printSectionHotness(raw_ostream &OS) const; + void printSectionHotness(const SectionStatsMap &, raw_ostream &OS) const; size_t size() const { return Map.size(); } }; diff --git a/bolt/lib/Profile/DataAggregator.cpp b/bolt/lib/Profile/DataAggregator.cpp index a5ac87ee781b2..11850fab28bb8 100644 --- a/bolt/lib/Profile/DataAggregator.cpp +++ b/bolt/lib/Profile/DataAggregator.cpp @@ -1357,10 +1357,12 @@ std::error_code DataAggregator::printLBRHeatMap() { HM.printCDF(opts::OutputFilename); else HM.printCDF(opts::OutputFilename + ".csv"); + Heatmap::SectionStatsMap Stats = HM.computeSectionStats(); if (opts::OutputFilename == "-") - HM.printSectionHotness(opts::OutputFilename); + HM.printSectionHotness(Stats, opts::OutputFilename); else - HM.printSectionHotness(opts::OutputFilename + "-section-hotness.csv"); + HM.printSectionHotness(Stats, + opts::OutputFilename + "-section-hotness.csv"); return std::error_code(); } diff --git a/bolt/lib/Profile/Heatmap.cpp b/bolt/lib/Profile/Heatmap.cpp index c7821b3a1a15a..d3ff74f664046 100644 --- a/bolt/lib/Profile/Heatmap.cpp +++ b/bolt/lib/Profile/Heatmap.cpp @@ -284,23 +284,24 @@ void Heatmap::printCDF(raw_ostream &OS) const { Counts.clear(); } -void Heatmap::printSectionHotness(StringRef FileName) const { +void Heatmap::printSectionHotness(const Heatmap::SectionStatsMap &Stats, + StringRef FileName) const { std::error_code EC; raw_fd_ostream OS(FileName, EC, sys::fs::OpenFlags::OF_None); if (EC) { errs() << "error opening output file: " << EC.message() << '\n'; exit(1); } - printSectionHotness(OS); + printSectionHotness(Stats, OS); } -void Heatmap::printSectionHotness(raw_ostream &OS) const { +StringMap<Heatmap::SectionStats> Heatmap::computeSectionStats() const { uint64_t NumTotalCounts = 0; - StringMap<uint64_t> SectionHotness; + StringMap<SectionStats> Stat; unsigned TextSectionIndex = 0; if (TextSections.empty()) - return; + return Stat; uint64_t UnmappedHotness = 0; auto RecordUnmappedBucket = [&](uint64_t Address, uint64_t Frequency) { @@ -312,37 +313,61 @@ void Heatmap::printSectionHotness(raw_ostream &OS) const { UnmappedHotness += Frequency; }; - for (const std::pair<const uint64_t, uint64_t> &KV : Map) { - NumTotalCounts += KV.second; + for (const auto [Bucket, Count] : Map) { + NumTotalCounts += Count; // We map an address bucket to the first section (lowest address) // overlapping with that bucket. - auto Address = KV.first * BucketSize; + auto Address = Bucket * BucketSize; while (TextSectionIndex < TextSections.size() && Address >= TextSections[TextSectionIndex].EndAddress) TextSectionIndex++; if (TextSectionIndex >= TextSections.size() || Address + BucketSize < TextSections[TextSectionIndex].BeginAddress) { - RecordUnmappedBucket(Address, KV.second); + RecordUnmappedBucket(Address, Count); continue; } - SectionHotness[TextSections[TextSectionIndex].Name] += KV.second; + SectionStats &SecStats = Stat[TextSections[TextSectionIndex].Name]; + ++SecStats.Buckets; + SecStats.Samples += Count; } + Stat["[total]"] = SectionStats{NumTotalCounts, Map.size()}; + if (UnmappedHotness) + Stat["[unmapped]"] = SectionStats{UnmappedHotness, 0}; + + return Stat; +} +void Heatmap::printSectionHotness(const StringMap<SectionStats> &Stats, + raw_ostream &OS) const { + if (TextSections.empty()) + return; + + auto TotalIt = Stats.find("[total]"); + assert(TotalIt != Stats.end() && "Malformed SectionStatsMap"); + const uint64_t NumTotalCounts = TotalIt->second.Samples; assert(NumTotalCounts > 0 && "total number of heatmap buckets should be greater than 0"); - OS << "Section Name, Begin Address, End Address, Percentage Hotness\n"; - for (auto &TextSection : TextSections) { - OS << TextSection.Name << ", 0x" - << Twine::utohexstr(TextSection.BeginAddress) << ", 0x" - << Twine::utohexstr(TextSection.EndAddress) << ", " - << format("%.4f", - 100.0 * SectionHotness[TextSection.Name] / NumTotalCounts) - << "\n"; + OS << "Section Name, Begin Address, End Address, Percentage Hotness, " + << "Utilization Pct\n"; + for (const auto [Name, Begin, End] : TextSections) { + uint64_t Samples = 0; + uint64_t Buckets = 0; + auto SectionIt = Stats.find(Name); + if (SectionIt != Stats.end()) { + Samples = SectionIt->second.Samples; + Buckets = SectionIt->second.Buckets; + } + const float RelHotness = 100. * Samples / NumTotalCounts; + const float BucketUtilization = 100. * Buckets / getNumBuckets(Begin, End); + OS << formatv("{0}, {1:x}, {2:x}, {3:f4}, {4:f4}\n", Name, Begin, End, + RelHotness, BucketUtilization); } - if (UnmappedHotness > 0) - OS << "[unmapped], 0x0, 0x0, " - << format("%.4f", 100.0 * UnmappedHotness / NumTotalCounts) << "\n"; + auto UnmappedIt = Stats.find("[unmapped]"); + if (UnmappedIt == Stats.end()) + return; + const float UnmappedPct = 100. * UnmappedIt->second.Samples / NumTotalCounts; + OS << formatv("[unmapped], 0x0, 0x0, {0:f4}, 0\n", UnmappedPct); } } // namespace bolt } // namespace llvm diff --git a/bolt/test/X86/heatmap-preagg.test b/bolt/test/X86/heatmap-preagg.test index 00d4d521b1adf..660d37fd03cbe 100644 --- a/bolt/test/X86/heatmap-preagg.test +++ b/bolt/test/X86/heatmap-preagg.test @@ -17,17 +17,19 @@ RUN: FileCheck %s --check-prefix CHECK-SEC-HOT-BAT --input-file %t2-section-hotn CHECK-HEATMAP: PERF2BOLT: read 81 aggregated LBR entries CHECK-HEATMAP: HEATMAP: invalid traces: 1 -CHECK-SEC-HOT: .init, 0x401000, 0x40101b, 16.8545 -CHECK-SEC-HOT-NEXT: .plt, 0x401020, 0x4010b0, 4.7583 -CHECK-SEC-HOT-NEXT: .text, 0x4010b0, 0x401c25, 78.3872 -CHECK-SEC-HOT-NEXT: .fini, 0x401c28, 0x401c35, 0.0000 +CHECK-SEC-HOT: Section Name, Begin Address, End Address, Percentage Hotness, Utilization Pct +CHECK-SEC-HOT-NEXT: .init, 0x401000, 0x40101b, 16.8545, 100.0000 +CHECK-SEC-HOT-NEXT: .plt, 0x401020, 0x4010b0, 4.7583, 66.6667 +CHECK-SEC-HOT-NEXT: .text, 0x4010b0, 0x401c25, 78.3872, 85.1064 +CHECK-SEC-HOT-NEXT: .fini, 0x401c28, 0x401c35, 0.0000, 0.0000 CHECK-HEATMAP-BAT: PERF2BOLT: read 79 aggregated LBR entries CHECK-HEATMAP-BAT: HEATMAP: invalid traces: 2 -CHECK-SEC-HOT-BAT: .init, 0x401000, 0x40101b, 17.2888 -CHECK-SEC-HOT-BAT-NEXT: .plt, 0x401020, 0x4010b0, 5.6132 +CHECK-SEC-HOT-BAT: Section Name, Begin Address, End Address, Percentage Hotness, Utilization Pct +CHECK-SEC-HOT-BAT-NEXT: .init, 0x401000, 0x40101b, 17.2888, 100.0000 +CHECK-SEC-HOT-BAT-NEXT: .plt, 0x401020, 0x4010b0, 5.6132, 66.6667 CHECK-SEC-HOT-BAT-NEXT: .bolt.org.text, 0x4010b0, 0x401c25, 38.3385 -CHECK-SEC-HOT-BAT-NEXT: .fini, 0x401c28, 0x401c35, 0.0000 -CHECK-SEC-HOT-BAT-NEXT: .text, 0x800000, 0x8002cc, 38.7595 -CHECK-SEC-HOT-BAT-NEXT: .text.cold, 0x800300, 0x800415, 0.0000 +CHECK-SEC-HOT-BAT-NEXT: .fini, 0x401c28, 0x401c35, 0.0000, 0.0000 +CHECK-SEC-HOT-BAT-NEXT: .text, 0x800000, 0x8002cc, 38.7595, 91.6667 +CHECK-SEC-HOT-BAT-NEXT: .text.cold, 0x800300, 0x800415, 0.0000, 0.0000 `````````` </details> https://github.com/llvm/llvm-project/pull/139193 _______________________________________________ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
