Feature/merge upstream 20240417

.ci/monolithic-linux.sh

@@ -18,7 +18,7 @@ set -o pipefail
 
 MONOREPO_ROOT="${MONOREPO_ROOT:="$(git rev-parse --show-toplevel)"}"
 BUILD_DIR="${BUILD_DIR:=${MONOREPO_ROOT}/build}"
-rm -rf ${BUILD_DIR}
+rm -rf "${BUILD_DIR}"
 
 ccache --zero-stats
 
@@ -37,8 +37,8 @@ projects="${1}"
 targets="${2}"
 
 echo "--- cmake"
-pip install -q -r ${MONOREPO_ROOT}/mlir/python/requirements.txt
-cmake -S ${MONOREPO_ROOT}/llvm -B ${BUILD_DIR} \
+pip install -q -r "${MONOREPO_ROOT}"/mlir/python/requirements.txt
+cmake -S "${MONOREPO_ROOT}"/llvm -B "${BUILD_DIR}" \
       -D LLVM_ENABLE_PROJECTS="${projects}" \
       -G Ninja \
       -D CMAKE_BUILD_TYPE=Release \

.ci/monolithic-windows.sh

@@ -19,7 +19,7 @@ set -o pipefail
 MONOREPO_ROOT="${MONOREPO_ROOT:="$(git rev-parse --show-toplevel)"}"
 BUILD_DIR="${BUILD_DIR:=${MONOREPO_ROOT}/build}"
 
-rm -rf ${BUILD_DIR}
+rm -rf "${BUILD_DIR}"
 
 if [[ -n "${CLEAR_CACHE:-}" ]]; then
   echo "clearing sccache"
@@ -37,14 +37,14 @@ projects="${1}"
 targets="${2}"
 
 echo "--- cmake"
-pip install -q -r ${MONOREPO_ROOT}/mlir/python/requirements.txt
+pip install -q -r "${MONOREPO_ROOT}"/mlir/python/requirements.txt
 
 # The CMAKE_*_LINKER_FLAGS to disable the manifest come from research
 # on fixing a build reliability issue on the build server, please
 # see https://github.com/llvm/llvm-project/pull/82393 and
 # https://discourse.llvm.org/t/rfc-future-of-windows-pre-commit-ci/76840/40
 # for further information.
-cmake -S ${MONOREPO_ROOT}/llvm -B ${BUILD_DIR} \
+cmake -S "${MONOREPO_ROOT}"/llvm -B "${BUILD_DIR}" \
       -D LLVM_ENABLE_PROJECTS="${projects}" \
       -G Ninja \
       -D CMAKE_BUILD_TYPE=Release \

.github/CODEOWNERS

@@ -115,6 +115,10 @@ clang/test/AST/Interp/ @tbaederr
 /mlir/**/LLVMIR/**/BasicPtxBuilderInterface* @grypp
 /mlir/**/NVVM*/ @grypp
 
+# MLIR Python Bindings
+/mlir/test/python/ @makslevental @stellaraccident
+/mlir/python/ @makslevental @stellaraccident
+
 # BOLT
 /bolt/ @aaupov @maksfb @rafaelauler @ayermolo @dcci
 
@@ -125,3 +129,6 @@ clang/test/AST/Interp/ @tbaederr
 /llvm/**/TextAPI/ @cyndyishida
 /clang/**/InstallAPI/ @cyndyishida
 /clang/tools/clang-installapi/ @cyndyishida
+
+# ExtractAPI
+/clang/**/ExtractAPI @daniel-grumberg

.github/workflows/email-check.yaml

@@ -1,7 +1,7 @@
 name: "Check for private emails used in PRs"
 
 on:
-  pull_request_target:
+  pull_request:
     types:
       - opened
 
@@ -10,8 +10,6 @@ permissions:
 
 jobs:
   validate_email:
-    permissions:
-      pull-requests: write
     runs-on: ubuntu-latest
     if: github.repository == 'llvm/llvm-project'
     steps:
@@ -25,20 +23,24 @@ jobs:
         run: |
           git log -1
           echo "EMAIL=$(git show -s --format='%ae' HEAD~0)" >> $GITHUB_OUTPUT
+          # Create empty comment file
+          echo "[]" > comments
 
       - name: Validate author email
         if: ${{ endsWith(steps.author.outputs.EMAIL, 'noreply.github.com')  }}
-        uses: actions/github-script@v7
         env:
-          EMAIL: ${{ steps.author.outputs.EMAIL }}
+          COMMENT: >-
+            ⚠️ We detected that you are using a GitHub private e-mail address to contribute to the repo.<br/>
+            Please turn off [Keep my email addresses private](https://github.com/settings/emails) setting in your account.<br/>
+            See [LLVM Discourse](https://discourse.llvm.org/t/hidden-emails-on-github-should-we-do-something-about-it) for more information.
+        run: |
+          cat << EOF > comments
+          [{"body" : "$COMMENT"}]
+          EOF
+
+      - uses: actions/upload-artifact@26f96dfa697d77e81fd5907df203aa23a56210a8 #v4.3.0
+        if: always()
         with:
-          script: |
-            const { EMAIL } = process.env
-            await github.rest.issues.createComment({
-              issue_number: context.issue.number,
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              body: `⚠️ We detected that you are using a GitHub private e-mail address to contribute to the repo.
-              Please turn off [Keep my email addresses private](https://github.com/settings/emails) setting in your account.
-              See [LLVM Discourse](https://discourse.llvm.org/t/hidden-emails-on-github-should-we-do-something-about-it) for more information.
-            `})
+          name: workflow-args
+          path: |
+            comments

.github/workflows/issue-write.yml

@@ -2,7 +2,9 @@ name: Comment on an issue
 
 on:
   workflow_run:
-    workflows: ["Check code formatting"]
+    workflows:
+      - "Check code formatting"
+      - "Check for private emails used in PRs"
     types:
       - completed
 
@@ -31,7 +33,7 @@ jobs:
           script: |
             var fs = require('fs');
             const comments = JSON.parse(fs.readFileSync('./comments'));
-            if (!comments) {
+            if (!comments || comments.length == 0) {
               return;
             }
 
@@ -77,6 +79,15 @@ jobs:
             }
             const gql_result = await github.graphql(gql_query, gql_variables);
             console.log(gql_result);
+            // If the branch for the PR was deleted before this job has a chance
+            // to run, then the ref will be null.  This can happen if someone:
+            // 1. Rebase the PR, which triggers some workflow.
+            // 2. Immediately merges the PR and deletes the branch.
+            // 3. The workflow finishes and triggers this job.
+            if (!gql_result.repository.ref) {
+              console.log("Ref has been deleted");
+              return;
+            }
             console.log(gql_result.repository.ref.associatedPullRequests.nodes);
 
             var pr_number = 0;

.github/workflows/libcxx-build-and-test.yaml

@@ -38,11 +38,11 @@ env:
   # LLVM POST-BRANCH bump version
   # LLVM POST-BRANCH add compiler test for ToT - 1, e.g. "Clang 17"
   # LLVM RELEASE bump remove compiler ToT - 3, e.g. "Clang 15"
-  LLVM_HEAD_VERSION: "18"   # Used compiler, update POST-BRANCH.
-  LLVM_PREVIOUS_VERSION: "17"
-  LLVM_OLDEST_VERSION: "16"
+  LLVM_HEAD_VERSION: "19"   # Used compiler, update POST-BRANCH.
+  LLVM_PREVIOUS_VERSION: "18"
+  LLVM_OLDEST_VERSION: "17"
   GCC_STABLE_VERSION: "13"
-  LLVM_SYMBOLIZER_PATH: "/usr/bin/llvm-symbolizer-18"
+  LLVM_SYMBOLIZER_PATH: "/usr/bin/llvm-symbolizer-19"
   CLANG_CRASH_DIAGNOSTICS_DIR: "crash_diagnostics"
 
 
@@ -59,8 +59,8 @@ jobs:
           'generic-cxx26',
           'generic-modules'
         ]
-        cc: [  'clang-18' ]
-        cxx: [ 'clang++-18' ]
+        cc: [  'clang-19' ]
+        cxx: [ 'clang++-19' ]
         clang_tidy: [ 'ON' ]
         include:
           - config: 'generic-gcc'
@@ -100,22 +100,22 @@ jobs:
           'generic-cxx20',
           'generic-cxx23'
         ]
-        cc: [ 'clang-18' ]
-        cxx: [ 'clang++-18' ]
+        cc: [ 'clang-19' ]
+        cxx: [ 'clang++-19' ]
         clang_tidy: [ 'ON' ]
         include:
           - config: 'generic-gcc-cxx11'
             cc: 'gcc-13'
             cxx: 'g++-13'
             clang_tidy: 'OFF'
-          - config: 'generic-cxx23'
-            cc: 'clang-16'
-            cxx: 'clang++-16'
-            clang_tidy: 'OFF'
           - config: 'generic-cxx23'
             cc: 'clang-17'
             cxx: 'clang++-17'
             clang_tidy: 'OFF'
+          - config: 'generic-cxx26'
+            cc: 'clang-18'
+            cxx: 'clang++-18'
+            clang_tidy: 'ON'
     steps:
       - uses: actions/checkout@v4
       - name: ${{ matrix.config }}
@@ -186,8 +186,8 @@ jobs:
       - name: ${{ matrix.config }}
         run: libcxx/utils/ci/run-buildbot ${{ matrix.config }}
         env:
-          CC: clang-18
-          CXX: clang++-18
+          CC: clang-19
+          CXX: clang++-19
           ENABLE_CLANG_TIDY: "OFF"
       - uses: actions/upload-artifact@26f96dfa697d77e81fd5907df203aa23a56210a8 # v4.3.0
         if: always()

.github/workflows/pr-code-format.yml

@@ -1,4 +1,8 @@
 name: "Check code formatting"
+
+permissions:
+  contents: read
+
 on:
   pull_request:
     branches:
@@ -33,7 +37,7 @@ jobs:
       - name: Fetch code formatting utils
         uses: actions/[email protected]
         with:
-          reository: ${{ github.repository }}
+          repository: ${{ github.repository }}
           ref: ${{ github.base_ref }}
           sparse-checkout: |
             llvm/utils/git/requirements_formatting.txt
@@ -73,7 +77,9 @@ jobs:
         # to take advantage of the new --diff_from_common_commit option
         # explicitly in code-format-helper.py and not have to diff starting at
         # the merge base.
+        # Create an empty comments file so the pr-write job doesn't fail.
         run: |
+          echo "[]" > comments &&
           python ./code-format-tools/llvm/utils/git/code-format-helper.py \
             --write-comment-to-file \
             --token ${{ secrets.GITHUB_TOKEN }} \

.github/workflows/release-lit.yml

@@ -58,7 +58,7 @@ jobs:
           cd llvm/utils/lit
           # Remove 'dev' suffix from lit version.
           sed -i 's/ + "dev"//g' lit/__init__.py
-          python3 setup.py sdist
+          python3 setup.py sdist bdist_wheel
 
       - name: Upload lit to test.pypi.org
         uses: pypa/gh-action-pypi-publish@release/v1

bolt/docs/BAT.md

@@ -42,21 +42,21 @@ and [BoltAddressTranslation.cpp](/bolt/lib/Profile/BoltAddressTranslation.cpp).
 ### Layout
 The general layout is as follows:
 ```
-Hot functions table header
-|------------------|
-|  Function entry  |
-| |--------------| |
-| | OutOff InOff | |
-| |--------------| |
-~~~~~~~~~~~~~~~~~~~~
+Hot functions table
+Cold functions table
 
-Cold functions table header
+Functions table:
 |------------------|
 |  Function entry  |
-| |--------------| |
-| | OutOff InOff | |
-| |--------------| |
-~~~~~~~~~~~~~~~~~~~~
+|                  |
+|     Address      |
+|   translation    |
+|      table       |
+|                  |
+| Secondary entry  |
+|      points      |
+|------------------|
+
 ```
 
 ### Functions table
@@ -74,19 +74,21 @@ internal offsets, and between hot and cold fragments, to better spread deltas
 and save space.
 
 Hot indices are delta encoded, implicitly starting at zero.
-| Entry  | Encoding | Description |
-| ------ | ------| ----------- |
-| `Address` | Continuous, Delta, ULEB128 | Function address in the output binary |
-| `HotIndex` | Delta, ULEB128 | Cold functions only: index of corresponding hot function in hot functions table |
-| `FuncHash` | 8b | Hot functions only: function hash for input function |
-| `NumBlocks` | ULEB128 | Hot functions only: number of basic blocks in the original function |
-| `NumEntries` | ULEB128 | Number of address translation entries for a function |
-| `EqualElems` | ULEB128 | Hot functions only: number of equal offsets in the beginning of a function |
-| `BranchEntries` | Bitmask, `alignTo(EqualElems, 8)` bits | Hot functions only: if `EqualElems` is non-zero, bitmask denoting entries with `BRANCHENTRY` bit |
-
-Function header is followed by `EqualElems` offsets (hot functions only) and
-`NumEntries-EqualElems` (`NumEntries` for cold functions) pairs of offsets for
-current function.
+| Entry  | Encoding | Description | Hot/Cold |
+| ------ | ------| ----------- | ------ |
+| `Address` | Continuous, Delta, ULEB128 | Function address in the output binary | Both |
+| `HotIndex` | Delta, ULEB128 | Index of corresponding hot function in hot functions table | Cold |
+| `FuncHash` | 8b | Function hash for input function | Hot |
+| `NumBlocks` | ULEB128 | Number of basic blocks in the original function | Hot |
+| `NumSecEntryPoints` | ULEB128 | Number of secondary entry points in the original function | Hot |
+| `ColdInputSkew` | ULEB128 | Skew to apply to all input offsets | Cold |
+| `NumEntries` | ULEB128 | Number of address translation entries for a function | Both |
+| `EqualElems` | ULEB128 | Number of equal offsets in the beginning of a function | Both |
+| `BranchEntries` | Bitmask, `alignTo(EqualElems, 8)` bits | If `EqualElems` is non-zero, bitmask denoting entries with `BRANCHENTRY` bit | Both |
+
+Function header is followed by *Address Translation Table* with `NumEntries`
+total entries, and *Secondary Entry Points* table with `NumSecEntryPoints`
+entries (hot functions only).
 
 ### Address translation table
 Delta encoding means that only the difference with the previous corresponding
@@ -98,8 +100,18 @@ entry is encoded. Input offsets implicitly start at zero.
 | `BBHash` | Optional, 8b | Basic block hash in input binary | BB |
 | `BBIdx`  | Optional, Delta, ULEB128 | Basic block index in input binary | BB |
 
+The table omits the first `EqualElems` input offsets where the input offset
+equals output offset.
+
 `BRANCHENTRY` bit denotes whether a given offset pair is a control flow source
 (branch or call instruction). If not set, it signifies a control flow target
 (basic block offset).
 `InputAddr` is omitted for equal offsets in input and output function. In this
 case, `BRANCHENTRY` bits are encoded separately in a `BranchEntries` bitvector.
+
+### Secondary Entry Points table
+The table is emitted for hot fragments only. It contains `NumSecEntryPoints`
+offsets denoting secondary entry points, delta encoded, implicitly starting at zero.
+| Entry | Encoding | Description |
+| ----- | -------- | ----------- |
+| `SecEntryPoint` | Delta, ULEB128 | Secondary entry point offset |

bolt/include/bolt/Core/AddressMap.h

@@ -14,7 +14,6 @@
 #ifndef BOLT_CORE_ADDRESS_MAP_H
 #define BOLT_CORE_ADDRESS_MAP_H
 
-#include "llvm/ADT/StringRef.h"
 #include "llvm/MC/MCSymbol.h"
 
 #include <optional>

bolt/include/bolt/Core/BinaryContext.h

@@ -265,7 +265,8 @@ class BinaryContext {
 
 public:
   static Expected<std::unique_ptr<BinaryContext>>
-  createBinaryContext(const ObjectFile *File, bool IsPIC,
+  createBinaryContext(Triple TheTriple, StringRef InputFileName,
+                      SubtargetFeatures *Features, bool IsPIC,
                       std::unique_ptr<DWARFContext> DwCtx,
                       JournalingStreams Logger);
 

bolt/include/bolt/Core/BinaryData.h

@@ -18,7 +18,6 @@
 #include "llvm/ADT/Twine.h"
 #include "llvm/MC/MCSymbol.h"
 #include "llvm/Support/raw_ostream.h"
-#include <algorithm>
 #include <string>
 #include <vector>
 
@@ -108,7 +107,6 @@ class BinaryData {
   std::vector<MCSymbol *> &getSymbols() { return Symbols; }
 
   bool hasName(StringRef Name) const;
-  bool hasNameRegex(StringRef Name) const;
   bool nameStartsWith(StringRef Prefix) const;
 
   bool hasSymbol(const MCSymbol *Symbol) const {

bolt/include/bolt/Core/BinaryDomTree.h

@@ -16,7 +16,6 @@
 
 #include "bolt/Core/BinaryBasicBlock.h"
 #include "llvm/IR/Dominators.h"
-#include "llvm/Support/GenericDomTreeConstruction.h"
 
 namespace llvm {
 namespace bolt {