merge main into amd-staging

Author: z1-cciauto

.ci/monolithic-linux.sh

@@ -102,51 +102,25 @@ if [[ "${runtimes}" != "" ]]; then
     exit 1
   fi
 
-  echo "--- ninja install-clang"
-
-  ninja -C ${BUILD_DIR} install-clang install-clang-resource-headers
-
-  RUNTIMES_BUILD_DIR="${MONOREPO_ROOT}/build-runtimes"
-  INSTALL_DIR="${BUILD_DIR}/install"
-  mkdir -p ${RUNTIMES_BUILD_DIR}
-
   echo "--- cmake runtimes C++26"
 
-  rm -rf "${RUNTIMES_BUILD_DIR}"
-  cmake -S "${MONOREPO_ROOT}/runtimes" -B "${RUNTIMES_BUILD_DIR}" -GNinja \
-      -D CMAKE_C_COMPILER="${INSTALL_DIR}/bin/clang" \
-      -D CMAKE_CXX_COMPILER="${INSTALL_DIR}/bin/clang++" \
-      -D LLVM_ENABLE_RUNTIMES="${runtimes}" \
-      -D LIBCXX_CXX_ABI=libcxxabi \
-      -D CMAKE_BUILD_TYPE=RelWithDebInfo \
-      -D CMAKE_INSTALL_PREFIX="${INSTALL_DIR}" \
-      -D LIBCXX_TEST_PARAMS="std=c++26" \
-      -D LIBCXXABI_TEST_PARAMS="std=c++26" \
-      -D LLVM_LIT_ARGS="${lit_args}"
+  cmake \
+    -D LIBCXX_TEST_PARAMS="std=c++26" \
+    -D LIBCXXABI_TEST_PARAMS="std=c++26" \
+    "${BUILD_DIR}"
 
   echo "--- ninja runtimes C++26"
 
-  ninja -vC "${RUNTIMES_BUILD_DIR}" ${runtime_targets}
+  ninja -C "${BUILD_DIR}" ${runtime_targets}
 
   echo "--- cmake runtimes clang modules"
 
-  # We don't need to do a clean build of runtimes, because LIBCXX_TEST_PARAMS
-  # and LIBCXXABI_TEST_PARAMS only affect lit configuration, which successfully
-  # propagates without a clean build. Other that those two variables, builds
-  # are supposed to be the same.
-
-  cmake -S "${MONOREPO_ROOT}/runtimes" -B "${RUNTIMES_BUILD_DIR}" -GNinja \
-      -D CMAKE_C_COMPILER="${INSTALL_DIR}/bin/clang" \
-      -D CMAKE_CXX_COMPILER="${INSTALL_DIR}/bin/clang++" \
-      -D LLVM_ENABLE_RUNTIMES="${runtimes}" \
-      -D LIBCXX_CXX_ABI=libcxxabi \
-      -D CMAKE_BUILD_TYPE=RelWithDebInfo \
-      -D CMAKE_INSTALL_PREFIX="${INSTALL_DIR}" \
-      -D LIBCXX_TEST_PARAMS="enable_modules=clang" \
-      -D LIBCXXABI_TEST_PARAMS="enable_modules=clang" \
-      -D LLVM_LIT_ARGS="${lit_args}"
+  cmake \
+    -D LIBCXX_TEST_PARAMS="enable_modules=clang" \
+    -D LIBCXXABI_TEST_PARAMS="enable_modules=clang" \
+    "${BUILD_DIR}"
 
   echo "--- ninja runtimes clang modules"
 
-  ninja -vC "${RUNTIMES_BUILD_DIR}" ${runtime_targets}
+  ninja -C "${BUILD_DIR}" ${runtime_targets}
 fi

bolt/include/bolt/Profile/DataAggregator.h

@@ -78,6 +78,13 @@ class DataAggregator : public DataReader {
   static bool checkPerfDataMagic(StringRef FileName);
 
 private:
+  struct LBREntry {
+    uint64_t From;
+    uint64_t To;
+    bool Mispred;
+  };
+  friend raw_ostream &operator<<(raw_ostream &OS, const LBREntry &);
+
   struct PerfBranchSample {
     SmallVector<LBREntry, 32> LBR;
   };
@@ -476,7 +483,6 @@ class DataAggregator : public DataReader {
 
   /// Debugging dump methods
   void dump() const;
-  void dump(const LBREntry &LBR) const;
   void dump(const PerfBranchSample &Sample) const;
   void dump(const PerfMemSample &Sample) const;
 
@@ -504,6 +510,12 @@ class DataAggregator : public DataReader {
 
   friend class YAMLProfileWriter;
 };
+
+inline raw_ostream &operator<<(raw_ostream &OS,
+                               const DataAggregator::LBREntry &L) {
+  OS << formatv("{0:x} -> {1:x}/{2}", L.From, L.To, L.Mispred ? 'M' : 'P');
+  return OS;
+}
 } // namespace bolt
 } // namespace llvm
 

bolt/include/bolt/Profile/DataReader.h

@@ -32,18 +32,6 @@ namespace bolt {
 
 class BinaryFunction;
 
-struct LBREntry {
-  uint64_t From;
-  uint64_t To;
-  bool Mispred;
-};
-
-inline raw_ostream &operator<<(raw_ostream &OS, const LBREntry &LBR) {
-  OS << "0x" << Twine::utohexstr(LBR.From) << " -> 0x"
-     << Twine::utohexstr(LBR.To);
-  return OS;
-}
-
 struct Location {
   bool IsSymbol;
   StringRef Name;

bolt/lib/Profile/DataAggregator.cpp

@@ -580,8 +580,10 @@ void DataAggregator::processProfile(BinaryContext &BC) {
     }
   }
 
-  for (auto &FuncBranches : NamesToBranches)
+  for (auto &FuncBranches : NamesToBranches) {
     llvm::stable_sort(FuncBranches.second.Data);
+    llvm::stable_sort(FuncBranches.second.EntryData);
+  }
 
   for (auto &MemEvents : NamesToMemEvents)
     llvm::stable_sort(MemEvents.second.Data);
@@ -733,8 +735,10 @@ bool DataAggregator::doBranch(uint64_t From, uint64_t To, uint64_t Count,
   // corresponds to a return (if \p IsFrom) or a call continuation (otherwise).
   auto handleAddress = [&](uint64_t &Addr, bool IsFrom) {
     BinaryFunction *Func = getBinaryFunctionContainingAddress(Addr);
-    if (!Func)
+    if (!Func) {
+      Addr = 0;
       return std::pair{Func, false};
+    }
 
     Addr -= Func->getAddress();
 
@@ -972,7 +976,7 @@ bool DataAggregator::recordExit(BinaryFunction &BF, uint64_t From, bool Mispred,
   return true;
 }
 
-ErrorOr<LBREntry> DataAggregator::parseLBREntry() {
+ErrorOr<DataAggregator::LBREntry> DataAggregator::parseLBREntry() {
   LBREntry Res;
   ErrorOr<StringRef> FromStrRes = parseString('/');
   if (std::error_code EC = FromStrRes.getError())
@@ -1430,54 +1434,16 @@ void DataAggregator::parseLBRSample(const PerfBranchSample &Sample,
       const uint64_t TraceTo = NextLBR->From;
       const BinaryFunction *TraceBF =
           getBinaryFunctionContainingAddress(TraceFrom);
-      if (opts::HeatmapMode == opts::HeatmapModeKind::HM_Exclusive) {
-        FTInfo &Info = FallthroughLBRs[Trace(TraceFrom, TraceTo)];
+      FTInfo &Info = FallthroughLBRs[Trace(TraceFrom, TraceTo)];
+      if (TraceBF && TraceBF->containsAddress(LBR.From))
         ++Info.InternCount;
-      } else if (TraceBF && TraceBF->containsAddress(TraceTo)) {
-        FTInfo &Info = FallthroughLBRs[Trace(TraceFrom, TraceTo)];
-        if (TraceBF->containsAddress(LBR.From))
-          ++Info.InternCount;
-        else
-          ++Info.ExternCount;
-      } else {
-        const BinaryFunction *ToFunc =
-            getBinaryFunctionContainingAddress(TraceTo);
-        if (TraceBF && ToFunc) {
-          LLVM_DEBUG({
-            dbgs() << "Invalid trace starting in " << TraceBF->getPrintName()
-                   << formatv(" @ {0:x}", TraceFrom - TraceBF->getAddress())
-                   << formatv(" and ending @ {0:x}\n", TraceTo);
-          });
-          ++NumInvalidTraces;
-        } else {
-          LLVM_DEBUG({
-            dbgs() << "Out of range trace starting in "
-                   << (TraceBF ? TraceBF->getPrintName() : "None")
-                   << formatv(" @ {0:x}",
-                              TraceFrom - (TraceBF ? TraceBF->getAddress() : 0))
-                   << " and ending in "
-                   << (ToFunc ? ToFunc->getPrintName() : "None")
-                   << formatv(" @ {0:x}\n",
-                              TraceTo - (ToFunc ? ToFunc->getAddress() : 0));
-          });
-          ++NumLongRangeTraces;
-        }
-      }
+      else
+        ++Info.ExternCount;
       ++NumTraces;
     }
     NextLBR = &LBR;
 
-    // Record branches outside binary functions for heatmap.
-    if (opts::HeatmapMode == opts::HeatmapModeKind::HM_Exclusive) {
-      TakenBranchInfo &Info = BranchLBRs[Trace(LBR.From, LBR.To)];
-      ++Info.TakenCount;
-      continue;
-    }
-    uint64_t From = getBinaryFunctionContainingAddress(LBR.From) ? LBR.From : 0;
-    uint64_t To = getBinaryFunctionContainingAddress(LBR.To) ? LBR.To : 0;
-    if (!From && !To)
-      continue;
-    TakenBranchInfo &Info = BranchLBRs[Trace(From, To)];
+    TakenBranchInfo &Info = BranchLBRs[Trace(LBR.From, LBR.To)];
     ++Info.TakenCount;
     Info.MispredCount += LBR.Mispred;
   }
@@ -2398,16 +2364,10 @@ std::error_code DataAggregator::writeBATYAML(BinaryContext &BC,
 
 void DataAggregator::dump() const { DataReader::dump(); }
 
-void DataAggregator::dump(const LBREntry &LBR) const {
-  Diag << "From: " << Twine::utohexstr(LBR.From)
-       << " To: " << Twine::utohexstr(LBR.To) << " Mispred? " << LBR.Mispred
-       << "\n";
-}
-
 void DataAggregator::dump(const PerfBranchSample &Sample) const {
   Diag << "Sample LBR entries: " << Sample.LBR.size() << "\n";
   for (const LBREntry &LBR : Sample.LBR)
-    dump(LBR);
+    Diag << LBR << '\n';
 }
 
 void DataAggregator::dump(const PerfMemSample &Sample) const {

bolt/test/X86/pre-aggregated-perf.test

@@ -36,26 +36,26 @@ RUN: llvm-bolt %t.exe -p %p/Inputs/pre-aggregated.txt --pa -o %t.null | FileChec
 
 CHECK: BOLT-INFO: 4 out of 7 functions in the binary (57.1%) have non-empty execution profile
 
-RUN: cat %t | sort | FileCheck %s -check-prefix=PERF2BOLT
-RUN: cat %t.new | FileCheck %s -check-prefix=NEWFORMAT
+RUN: FileCheck %s -check-prefix=PERF2BOLT --input-file %t
+RUN: FileCheck %s -check-prefix=NEWFORMAT --input-file %t.new
 
 ## Test --profile-format option with perf2bolt
 RUN: perf2bolt %t.exe -o %t.fdata --pa -p %p/Inputs/pre-aggregated.txt \
 RUN:   --profile-format=fdata
-RUN: cat %t.fdata | sort | FileCheck %s -check-prefix=PERF2BOLT
+RUN: FileCheck %s -check-prefix=PERF2BOLT --input-file %t.fdata
 
 RUN: perf2bolt %t.exe -o %t.yaml --pa -p %p/Inputs/pre-aggregated.txt \
 RUN:   --profile-format=yaml --profile-use-dfs
-RUN: cat %t.yaml | FileCheck %s -check-prefix=NEWFORMAT
+RUN: FileCheck %s -check-prefix=NEWFORMAT --input-file %t.yaml
 
 ## Test --profile-format option with llvm-bolt --aggregate-only
 RUN: llvm-bolt %t.exe -o %t.bolt.fdata --pa -p %p/Inputs/pre-aggregated.txt \
 RUN:   --aggregate-only --profile-format=fdata
-RUN: cat %t.bolt.fdata | sort | FileCheck %s -check-prefix=PERF2BOLT
+RUN: FileCheck %s -check-prefix=PERF2BOLT --input-file %t.bolt.fdata
 
 RUN: llvm-bolt %t.exe -o %t.bolt.yaml --pa -p %p/Inputs/pre-aggregated.txt \
 RUN:   --aggregate-only --profile-format=yaml --profile-use-dfs
-RUN: cat %t.bolt.yaml | FileCheck %s -check-prefix=NEWFORMAT
+RUN: FileCheck %s -check-prefix=NEWFORMAT --input-file %t.bolt.yaml
 
 ## Test pre-aggregated basic profile
 RUN: perf2bolt %t.exe -o %t --pa -p %p/Inputs/pre-aggregated-basic.txt -o %t.ba \
@@ -67,16 +67,17 @@ BASIC-ERROR: BOLT-INFO: 0 out of 7 functions in the binary (0.0%) have non-empty
 BASIC-SUCCESS: BOLT-INFO: 4 out of 7 functions in the binary (57.1%) have non-empty execution profile
 CHECK-BASIC-NL: no_lbr cycles
 
-PERF2BOLT: 0 [unknown] 7f36d18d60c0 1 main 53c 0 2
-PERF2BOLT: 1 main 451 1 SolveCubic 0 0 2
-PERF2BOLT: 1 main 490 0 [unknown] 4005f0 0 1
-PERF2BOLT: 1 main 537 0 [unknown] 400610 0 1
-PERF2BOLT: 1 usqrt 30 1 usqrt 32 0 22
-PERF2BOLT: 1 usqrt 30 1 usqrt 39 4 33
-PERF2BOLT: 1 usqrt 35 1 usqrt 39 0 22
-PERF2BOLT: 1 usqrt 3d 1 usqrt 10 0 58
-PERF2BOLT: 1 usqrt 3d 1 usqrt 3f 0 22
-PERF2BOLT: 1 usqrt a 1 usqrt 10 0 22
+PERF2BOLT: 1 frame_dummy/1 1e 1 frame_dummy/1 0 0 1
+PERF2BOLT-NEXT: 1 main 451 1 SolveCubic 0 0 2
+PERF2BOLT-NEXT: 1 main 490 0 [unknown] 0 0 1
+PERF2BOLT-NEXT: 1 main 537 0 [unknown] 0 0 1
+PERF2BOLT-NEXT: 0 [unknown] 0 1 main 53c 0 2
+PERF2BOLT-NEXT: 1 usqrt a 1 usqrt 10 0 22
+PERF2BOLT-NEXT: 1 usqrt 30 1 usqrt 32 0 22
+PERF2BOLT-NEXT: 1 usqrt 30 1 usqrt 39 4 33
+PERF2BOLT-NEXT: 1 usqrt 35 1 usqrt 39 0 22
+PERF2BOLT-NEXT: 1 usqrt 3d 1 usqrt 10 0 58
+PERF2BOLT-NEXT: 1 usqrt 3d 1 usqrt 3f 0 22
 
 NEWFORMAT:  - name:            'frame_dummy/1'
 NEWFORMAT:    fid:             3

clang-tools-extra/clang-tidy/abseil/AbseilTidyModule.cpp

@@ -59,14 +59,12 @@ class AbseilModule : public ClangTidyModule {
     CheckFactories.registerCheck<NoNamespaceCheck>("abseil-no-namespace");
     CheckFactories.registerCheck<RedundantStrcatCallsCheck>(
         "abseil-redundant-strcat-calls");
-    CheckFactories.registerCheck<StrCatAppendCheck>(
-        "abseil-str-cat-append");
+    CheckFactories.registerCheck<StrCatAppendCheck>("abseil-str-cat-append");
     CheckFactories.registerCheck<StringFindStartswithCheck>(
         "abseil-string-find-startswith");
     CheckFactories.registerCheck<StringFindStrContainsCheck>(
         "abseil-string-find-str-contains");
-    CheckFactories.registerCheck<TimeComparisonCheck>(
-        "abseil-time-comparison");
+    CheckFactories.registerCheck<TimeComparisonCheck>("abseil-time-comparison");
     CheckFactories.registerCheck<TimeSubtractionCheck>(
         "abseil-time-subtraction");
     CheckFactories.registerCheck<UpgradeDurationConversionsCheck>(

clang-tools-extra/clang-tidy/abseil/DurationDivisionCheck.h

@@ -15,7 +15,7 @@ namespace clang::tidy::abseil {
 
 // Find potential incorrect uses of integer division of absl::Duration objects.
 //
-// For the user-facing documentation see: 
+// For the user-facing documentation see:
 // http://clang.llvm.org/extra/clang-tidy/checks/abseil/duration-division.html
 
 class DurationDivisionCheck : public ClangTidyCheck {

clang-tools-extra/clang-tidy/abseil/NoInternalDependenciesCheck.cpp

@@ -27,7 +27,8 @@ void NoInternalDependenciesCheck::registerMatchers(MatchFinder *Finder) {
       this);
 }
 
-void NoInternalDependenciesCheck::check(const MatchFinder::MatchResult &Result) {
+void NoInternalDependenciesCheck::check(
+    const MatchFinder::MatchResult &Result) {
   const auto *InternalDependency =
       Result.Nodes.getNodeAs<NestedNameSpecifierLoc>("InternalDep");
 

clang-tools-extra/clang-tidy/abseil/NoInternalDependenciesCheck.h

@@ -1,4 +1,4 @@
-//===--- NoInternalDependenciesCheck.h - clang-tidy----------------------*- C++ -*-===//
+//===--- NoInternalDependenciesCheck.h - clang-tidy--------------*- C++ -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.

clang-tools-extra/clang-tidy/abseil/NoNamespaceCheck.cpp

@@ -15,10 +15,9 @@ using namespace clang::ast_matchers;
 namespace clang::tidy::abseil {
 
 void NoNamespaceCheck::registerMatchers(MatchFinder *Finder) {
-  Finder->addMatcher(
-      namespaceDecl(hasName("::absl"), unless(isInAbseilFile()))
-          .bind("abslNamespace"),
-      this);
+  Finder->addMatcher(namespaceDecl(hasName("::absl"), unless(isInAbseilFile()))
+                         .bind("abslNamespace"),
+                     this);
 }
 
 void NoNamespaceCheck::check(const MatchFinder::MatchResult &Result) {