Improved Memory Operations

.github/workflows/prerelease.yml

@@ -20,7 +20,7 @@ permissions:
 jobs:
   versioning:
     name: Update Version
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-24
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -100,7 +100,7 @@ jobs:
 
         # Python
       - name: Set up Python ${{ env.PYTHON_VERSION }}
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v5.2.0
         with:
           python-version: ${{ env.PYTHON_VERSION }}
       - name: Build Python
@@ -184,7 +184,7 @@ jobs:
 
         # Python
       - name: Set up Python ${{ env.PYTHON_VERSION }}
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v5.2.0
         with:
           python-version: ${{ env.PYTHON_VERSION }}
       - name: Build Python
@@ -281,7 +281,7 @@ jobs:
 
   test_macos:
     name: MacOS
-    runs-on: macos-latest
+    runs-on: macos-13
 
     steps:
       - uses: actions/checkout@v4
@@ -316,14 +316,16 @@ jobs:
 
         # Python
       - name: Set up Python ${{ env.PYTHON_VERSION }}
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v5.2.0
         with:
           python-version: ${{ env.PYTHON_VERSION }}
       - name: Build Python
         run: |
           python -m pip install --upgrade pip
           pip install pytest pytest-repeat numpy pyarrow
           python -m pip install .
+        env:
+          MACOSX_DEPLOYMENT_TARGET: "11.0"
       - name: Test Python
         run: pytest scripts/test.py -s -x
 
@@ -346,7 +348,7 @@ jobs:
 
   test_windows:
     name: Windows
-    runs-on: windows-latest
+    runs-on: windows-2022
     steps:
       - uses: actions/checkout@v4
       - uses: ilammy/msvc-dev-cmd@v1
@@ -387,7 +389,7 @@ jobs:
 
         # Python
       - name: Set up Python ${{ env.PYTHON_VERSION }}
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v5.2.0
         with:
           python-version: ${{ env.PYTHON_VERSION }}
       - name: Build Python
@@ -400,7 +402,7 @@ jobs:
 
   test_alpine:
     name: Alpine Linux
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-24
     container:
       image: alpine:latest
       options: --privileged # If needed for certain Docker operations
@@ -449,18 +451,18 @@ jobs:
       ]
     strategy:
       matrix:
-        os: [ubuntu-latest, macos-latest, windows-latest]
+        os: [ubuntu-24, macos-13, windows-2022]
         python-version: ["36", "37", "38", "39", "310", "311", "312"]
     steps:
       - uses: actions/checkout@v4
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v5.2.0
         with:
           python-version: 3.x
 
         # We only need QEMU for Linux builds
       - name: Setup QEMU
-        if: matrix.os == 'ubuntu-latest'
+        if: matrix.os == 'ubuntu-24'
         uses: docker/setup-qemu-action@v3
       - name: Install cibuildwheel
         run: python -m pip install cibuildwheel

.github/workflows/release.yml

@@ -19,7 +19,7 @@ permissions:
 jobs:
   versioning:
     name: Update Version
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-24
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -49,7 +49,7 @@ jobs:
 
   rebase:
     name: Rebase Dev. Branch
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-24
     if: github.ref == 'refs/heads/main'
     needs: versioning
     steps:
@@ -78,26 +78,27 @@ jobs:
     needs: versioning
     strategy:
       matrix:
-        os: [ubuntu-latest, macos-latest, windows-latest]
+        os: [ubuntu-24, macos-13, windows-2022]
         python-version: ["36", "37", "38", "39", "310", "311", "312"]
     steps:
       - uses: actions/checkout@v4
         with:
           ref: "main"
 
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v5.2.0
         with:
           python-version: 3.x
       - name: Setup QEMU
-        if: matrix.os == 'ubuntu-latest' # We only need QEMU for Linux builds
+        if: matrix.os == 'ubuntu-24' # We only need QEMU for Linux builds
         uses: docker/setup-qemu-action@v3
       - name: Install cibuildwheel
         run: python -m pip install cibuildwheel
       - name: Build wheels
         run: cibuildwheel --output-dir wheelhouse
         env:
           CIBW_BUILD: cp${{ matrix.python-version }}-*
+          MACOSX_DEPLOYMENT_TARGET: "11.0"
       - name: Upload wheels
         uses: actions/upload-artifact@v4
         with:
@@ -152,7 +153,7 @@ jobs:
   # publish_javascript:
   #   name: Publish JavaScript
   #   needs: versioning
-  #   runs-on: ubuntu-latest
+  #   runs-on: ubuntu-24
   #   steps:
   #     - uses: actions/checkout@v4
   #       with:
@@ -297,7 +298,7 @@ jobs:
 
   create_macos_library:
     name: Create Library for MacOS ${{ matrix.arch }}
-    runs-on: macos-latest
+    runs-on: macos-13
     needs: versioning
     strategy:
       fail-fast: false

.gitignore

@@ -34,3 +34,7 @@ node_modules/
 leipzig1M.txt
 enwik9.txt
 xlsum.csv
+human_protein_1200row_800len.txt
+
+# StringZilla-specific log files
+/failed_sz_*

.vscode/launch.json

@@ -8,6 +8,7 @@
       "name": "Debug C++ Unit Tests",
       "type": "cppdbg",
       "request": "launch",
+      "preLaunchTask": "Build Test: Debug",
       "program": "${workspaceFolder}/build_debug/stringzilla_test_cpp20",
       "cwd": "${workspaceFolder}",
       "environment": [
@@ -18,16 +19,13 @@
       ],
       "stopAtEntry": false,
       "linux": {
-        "preLaunchTask": "Build with GCC: Debug",
         "MIMode": "gdb"
       },
       "osx": {
-        "preLaunchTask": "Build with LLVM: Debug",
         "MIMode": "lldb"
       },
       "windows": {
         "program": "${workspaceFolder}\\build_debug\\stringzilla_test_cpp20.exe",
-        "preLaunchTask": "Build with MSVC: Debug",
         "MIMode": "gdb",
         "miDebuggerPath": "C:\\MinGw\\bin\\gdb.exe"
       }
@@ -48,17 +46,15 @@
         }
       ],
       "stopAtEntry": false,
+      "preLaunchTask": "Build Benchmarks: Debug",
       "linux": {
-        "preLaunchTask": "Build with GCC: Debug",
         "MIMode": "gdb"
       },
       "osx": {
-        "preLaunchTask": "Build with LLVM: Debug",
         "MIMode": "lldb"
       },
       "windows": {
         "program": "${workspaceFolder}\\build_debug\\stringzilla_${fileBasenameNoExtension}.exe",
-        "preLaunchTask": "Build with MSVC: Debug",
         "MIMode": "gdb",
         "miDebuggerPath": "C:\\MinGw\\bin\\gdb.exe"
       }

.vscode/settings.json

@@ -257,7 +257,8 @@
     "xtr1common": "cpp",
     "xtree": "cpp",
     "xutility": "cpp",
-    "errno.h": "c"
+    "errno.h": "c",
+    "text_encoding": "cpp"
   },
   "python.pythonPath": "~/miniconda3/bin/python"
 }

.vscode/tasks.json

@@ -2,40 +2,58 @@
     "version": "2.0.0",
     "tasks": [
         {
-            "label": "Build with GCC: Debug",
-            "command": "./.github/workflows/build_tools.sh Debug GCC",
+            "label": "Build Test: Debug",
+            "command": "cmake -D CMAKE_BUILD_TYPE=Debug -D STRINGZILLA_BUILD_TEST=1 -B build_debug && cmake --build build_debug --config Debug --target stringzilla_test_cpp20",
+            "args": [],
             "type": "shell",
-            "problemMatcher": [
-                "$gcc"
-            ]
+            "osx": {
+                "environment": [
+                    {
+                        "name": "CXX",
+                        "value": "$(brew --prefix llvm)/bin/clang++"
+                    },
+                    {
+                        "name": "CC",
+                        "value": "$(brew --prefix llvm)/bin/clang"
+                    }
+                ]
+            }
         },
         {
-            "label": "Build with GCC: Release",
-            "command": "./.github/workflows/build_tools.sh Release GCC",
+            "label": "Build Benchmarks: Debug",
+            "command": "cmake -D CMAKE_BUILD_TYPE=Debug -D STRINGZILLA_BUILD_TEST=0 -D STRINGZILLA_BUILD_BENCHMARK=1 -B build_debug && cmake --build build_debug --config Debug",
+            "args": [],
             "type": "shell",
-            "problemMatcher": [
-                "$gcc"
-            ]
+            "osx": {
+                "environment": [
+                    {
+                        "name": "CXX",
+                        "value": "$(brew --prefix llvm)/bin/clang++"
+                    },
+                    {
+                        "name": "CC",
+                        "value": "$(brew --prefix llvm)/bin/clang"
+                    }
+                ]
+            }
         },
         {
-            "label": "Build with LLVM: Debug",
-            "command": "./.github/workflows/build_tools.sh Debug LLVM",
-            "type": "shell"
-        },
-        {
-            "label": "Build with LLVM: Release",
-            "command": "./.github/workflows/build_tools.sh Release LLVM",
-            "type": "shell"
-        },
-        {
-            "label": "Build with MSVC: Debug",
-            "command": "./.github/workflows/build_tools.sh Debug MSVC",
-            "type": "shell"
+            "label": "Build Benchmarks: Release",
+            "command": "cmake -D CMAKE_BUILD_TYPE=Release -D STRINGZILLA_BUILD_TEST=0 -D STRINGZILLA_BUILD_BENCHMARK=1 -B build_release && cmake --build build_release --config Release",
+            "args": [],
+            "type": "shell",
+            "osx": {
+                "environment": [
+                    {
+                        "name": "CXX",
+                        "value": "$(brew --prefix llvm)/bin/clang++"
+                    },
+                    {
+                        "name": "CC",
+                        "value": "$(brew --prefix llvm)/bin/clang"
+                    }
+                ]
+            }
         },
-        {
-            "label": "Build with MSVC: Release",
-            "command": "./.github/workflows/build_tools.sh Release MSVC",
-            "type": "shell"
-        }
     ]
 }

CMakeLists.txt

@@ -264,6 +264,7 @@ if(${STRINGZILLA_BUILD_BENCHMARK})
   define_launcher(stringzilla_bench_sort scripts/bench_sort.cpp 17 "${STRINGZILLA_TARGET_ARCH}")
   define_launcher(stringzilla_bench_token scripts/bench_token.cpp 17 "${STRINGZILLA_TARGET_ARCH}")
   define_launcher(stringzilla_bench_container scripts/bench_container.cpp 17 "${STRINGZILLA_TARGET_ARCH}")
+  define_launcher(stringzilla_bench_memory scripts/bench_memory.cpp 17 "${STRINGZILLA_TARGET_ARCH}")
 endif()
 
 if(${STRINGZILLA_BUILD_TEST})