Commit oneTBB source code 3b16143

Author: tbbdev

.bazelversion

@@ -1 +1 @@
-5.0.0
+6.0.0

BUILD.bazel

@@ -36,7 +36,7 @@ cc_library(
         "include/oneapi/tbb/detail/*.h",
     ]),
     copts = ["-w"] + select({
-        "@bazel_tools//platforms:windows": [""],
+        "@platforms//os:windows": [""],
         "//conditions:default": ["-mwaitpkg"],
     }),
     defines =
@@ -47,16 +47,16 @@ cc_library(
             ],
         }) +
         select({
-            "@bazel_tools//platforms:osx": ["_XOPEN_SOURCE"],
+            "@platforms//os:osx": ["_XOPEN_SOURCE"],
             "//conditions:default": [],
         }),
     includes = [
         "include",
     ],
     linkopts =
         select({
-            "@bazel_tools//platforms:windows": [],
-            "@bazel_tools//platforms:linux": [
+            "@platforms//os:windows": [],
+            "@platforms//os:linux": [
                 "-ldl",
                 "-pthread",
                 "-lrt",

Bazel.md

@@ -33,7 +33,7 @@ example
 
 _WORKSPACE.bazel_:
 ```python
-load("@bazel_tools//tools/build_defs/repo:git.bzl", "git_repository")
+load("@platforms//tools/build_defs/repo:git.bzl", "git_repository")
 
 git_repository(
     name = "oneTBB",

CMakeLists.txt

@@ -1,4 +1,4 @@
-# Copyright (c) 2020-2022 Intel Corporation
+# Copyright (c) 2020-2023 Intel Corporation
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -216,19 +216,17 @@ else()
     if (TBB_BUILD)
         add_subdirectory(src/tbb)
     endif()
-    if (NOT "${CMAKE_SYSTEM_PROCESSOR}" MATCHES "mips")
-        if (TBBMALLOC_BUILD)
-            add_subdirectory(src/tbbmalloc)
-            if(TBBMALLOC_PROXY_BUILD AND NOT "${MSVC_CXX_ARCHITECTURE_ID}" MATCHES "ARM64")
-                add_subdirectory(src/tbbmalloc_proxy)
-            endif()
-        endif()
-        if (APPLE OR NOT BUILD_SHARED_LIBS)
-            message(STATUS "TBBBind build targets are disabled due to unsupported environment")
-        else()
-            add_subdirectory(src/tbbbind)
+    if (TBBMALLOC_BUILD)
+        add_subdirectory(src/tbbmalloc)
+        if(TBBMALLOC_PROXY_BUILD AND NOT "${MSVC_CXX_ARCHITECTURE_ID}" MATCHES "ARM64")
+            add_subdirectory(src/tbbmalloc_proxy)
         endif()
     endif()
+    if (APPLE OR NOT BUILD_SHARED_LIBS)
+        message(STATUS "TBBBind build targets are disabled due to unsupported environment")
+    else()
+        add_subdirectory(src/tbbbind)
+    endif()
 
     # -------------------------------------------------------------------
     # Installation instructions
@@ -279,10 +277,27 @@ endif()
 
 if (ANDROID_PLATFORM)
     if ("${ANDROID_STL}" STREQUAL "c++_shared")
-        configure_file(
-        "${ANDROID_NDK}/sources/cxx-stl/llvm-libc++/libs/${ANDROID_ABI}/libc++_shared.so"
-        "${CMAKE_LIBRARY_OUTPUT_DIRECTORY}/libc++_shared.so"
-        COPYONLY)
+        if (${ANDROID_NDK_MAJOR} GREATER_EQUAL "25")
+            if(ANDROID_ABI STREQUAL "arm64-v8a")
+                set(ANDROID_TOOLCHAIN_NAME "aarch64-linux-android")
+            elseif(ANDROID_ABI STREQUAL "x86_64")
+                set(ANDROID_TOOLCHAIN_NAME "x86_64-linux-android")
+            elseif(ANDROID_ABI STREQUAL "armeabi-v7a")
+                set(ANDROID_TOOLCHAIN_NAME "arm-linux-androideabi")
+            elseif(ANDROID_ABI STREQUAL "x86")
+                set(ANDROID_TOOLCHAIN_NAME "i686-linux-android")
+            endif()
+
+            configure_file(
+            "${ANDROID_TOOLCHAIN_ROOT}/sysroot/usr/lib/${ANDROID_TOOLCHAIN_NAME}/libc++_shared.so"
+            "${CMAKE_LIBRARY_OUTPUT_DIRECTORY}/libc++_shared.so"
+            COPYONLY)
+        else()
+            configure_file(
+                "${ANDROID_NDK}/sources/cxx-stl/llvm-libc++/libs/${ANDROID_ABI}/libc++_shared.so"
+                "${CMAKE_LIBRARY_OUTPUT_DIRECTORY}/libc++_shared.so"
+                COPYONLY)
+        endif()
     endif()
     # This custom target may be implemented without separate CMake script, but it requires
     # ADB(Android Debug Bridge) executable file availability, so to incapsulate this requirement

INSTALL.md

@@ -77,6 +77,19 @@ cmake <options> ..
 cpack
 ```
 
+## Installation from vcpkg
+
+You can download and install oneTBB using the [vcpkg](https://github.com/Microsoft/vcpkg) dependency manager:
+```sh
+  git clone https://github.com/Microsoft/vcpkg.git
+  cd vcpkg
+  ./bootstrap-vcpkg.sh #.\bootstrap-vcpkg.bat(for Windows)
+  ./vcpkg integrate install
+  ./vcpkg install tbb
+```
+
+The oneTBB port in vcpkg is kept up to date by Microsoft* team members and community contributors. If the version is out of date, create an issue or pull request on the [vcpkg repository](https://github.com/Microsoft/vcpkg).
+
 ## Example of Installation
 
 ### Single-configuration generators

README.md

@@ -20,6 +20,8 @@ Refer to oneTBB [examples](examples) and [samples](https://github.com/oneapi-src
 
 oneTBB is a part of [oneAPI](https://oneapi.io). The current branch implements version 1.1 of oneAPI Specification.
 
+> **_NOTE:_** Threading Building Blocks (TBB) is now called oneAPI Threading Building Blocks (oneTBB) to highlight that the tool is a part of the oneAPI ecosystem.
+
 ## Release Information
 Here are [Release Notes](RELEASE_NOTES.md) and [System Requirements](SYSTEM_REQUIREMENTS.md).
 

RELEASE_NOTES.md

@@ -18,36 +18,25 @@
 This document contains changes of oneTBB compared to the last release.
 
 ## Table of Contents <!-- omit in toc -->
-- [New Features](#new_features)
 - [Known Limitations](#known-limitations)
 - [Fixed Issues](#fixed-issues)
 - [Open-source Contributions Integrated](#open-source-contributions-integrated)
 
-## :white_check_mark: New Features
-- Improved support and use of the latest C++ standards for parallel_sort that allows using this algorithm with user-defined and standard library-defined objects with modern semantics.
-- The following features are now fully functional: task_arena extensions, collaborative_call_once, adaptive mutexes, heterogeneous overloads for concurrent_hash_map, and task_scheduler_handle.
-- Added support for Windows* Server 2022 and Python 3.10.
-
 ## :rotating_light: Known Limitations
+- A static assert causes compilation failures in oneTBB headers when compiling with Clang* 12.0.0 or newer if using the LLVM* standard library with -ffreestanding and C++11/14 compiler options.
 - An application using Parallel STL algorithms in libstdc++ versions 9 and 10 may fail to compile due to incompatible interface changes between earlier versions of Threading Building Blocks (TBB) and oneAPI Threading Building Blocks (oneTBB). Disable support for Parallel STL algorithms by defining PSTL_USE_PARALLEL_POLICIES (in libstdc++ 9) or _GLIBCXX_USE_TBB_PAR_BACKEND (in libstdc++ 10) macro to zero before inclusion of the first standard header file in each translation unit.
 - On Linux* OS, if oneAPI Threading Building Blocks (oneTBB) or Threading Building Blocks (TBB) are installed in a system folder like /usr/lib64, the application may fail to link due to the order in which the linker searches for libraries. Use the -L linker option to specify the correct location of oneTBB library. This issue does not affect the program execution.
 - The oneapi::tbb::info namespace interfaces might unexpectedly change the process affinity mask on Windows* OS systems (see https://github.com/open-mpi/hwloc/issues/366 for details) when using hwloc version lower than 2.5.
-- Using a hwloc version other than 1.11, 2.0, or 2.5 may cause an undefined behavior on Windows OS. See https://github.com/open-mpi/hwloc/issues/477 for details.
+- Using a hwloc version other than 1.11, 2.0, or 2.5 may cause an undefined behavior on Windows* OS. See https://github.com/open-mpi/hwloc/issues/477 for details.
 - The NUMA topology may be detected incorrectly on Windows OS machines where the number of NUMA node threads exceeds the size of 1 processor group.
 - On Windows OS on ARM64*, when compiling an application using oneTBB with the Microsoft* Compiler, the compiler issues a warning C4324 that a structure was padded due to the alignment specifier. Consider suppressing the warning by specifying /wd4324 to the compiler command line.
 - oneTBB does not support fork(), to work-around the issue, consider using task_scheduler_handle to join oneTBB worker threads before using fork().
 - C++ exception handling mechanism on Windows* OS on ARM64* might corrupt memory if an exception is thrown from any oneTBB parallel algorithm (see Windows* OS on ARM64* compiler issue: https://developercommunity.visualstudio.com/t/ARM64-incorrect-stack-unwinding-for-alig/1544293).
 
 ## :hammer: Fixed Issues
-- Memory allocator crash on a system with an incomplete /proc/meminfo (GitHub* [#584](https://github.com/oneapi-src/oneTBB/issues/584)).
-- Incorrect blocking of task stealing (GitHub* #[478](https://github.com/oneapi-src/oneTBB/issues/478)).
-- Hang due to incorrect decrement of a limiter_node (GitHub* [#634](https://github.com/oneapi-src/oneTBB/issues/634)).
-- Memory corruption in some rare cases when passing big messages in a flow graph (GitHub* [#639](https://github.com/oneapi-src/oneTBB/issues/639)).
-- Possible deadlock in a throwable flow graph node with a lightweight policy. The lightweight policy is now ignored for functors that can throw exceptions (GitHub* [#420](https://github.com/oneapi-src/oneTBB/issues/420)).
-- Crash when obtaining a range from empty ordered and unordered containers (GitHub* [#641](https://github.com/oneapi-src/oneTBB/issues/641)).
-- Deadlock in a concurrent_vector resize() that could happen when the new size is less than the previous size (GitHub* [#733](https://github.com/oneapi-src/oneTBB/issues/733)).
+- Memory allocator crash when allocating ~1TB on 64-bit systems (GitHub* [#838](https://github.com/oneapi-src/oneTBB/issues/838)).
+- Fixed thread distribution over NUMA nodes on Windows* OS systems.
+- For oneapi::tbb::suspend, it is guaranteed that the user-specified callable object is executed by the calling thread.
 
 ## :octocat: Open-source Contributions Integrated
-- Improved aligned memory allocation. Contributed by Andrey Semashev (https://github.com/oneapi-src/oneTBB/pull/671).
-- Optimized usage of atomic_fence on IA-32 and Intel(R) 64 architectures. Contributed by Andrey Semashev (https://github.com/oneapi-src/oneTBB/pull/328).
-- Fixed incorrect definition of the assignment operator in containers. Contributed by Andrey Semashev (https://github.com/oneapi-src/oneTBB/issues/372).
+- Fix for full LTO* build, library and tests, on UNIX* OS systems. Contributed by Vladislav Shchapov (https://github.com/oneapi-src/oneTBB/pull/798).

SYSTEM_REQUIREMENTS.md

@@ -21,6 +21,7 @@ This document provides details about hardware, operating system, and software pr
 - [Supported Hardware](#supported-hardware)
 - [Software](#software)
   - [Supported Operating Systems](#supported-operating-systems)
+  - [Community-Supported Platforms](#community-supported-platforms)
   - [Supported Compilers](#supported-compilers)
 
 
@@ -54,6 +55,12 @@ This document provides details about hardware, operating system, and software pr
 - Systems with Android* operating systems
   - Android* 9
 
+### Community-Supported Platforms
+- MinGW*
+- FreeBSD*
+- Microsoft* Windows* on ARM*/ARM64*
+- macOS* on ARM64*
+
 ### Supported Compilers
 - Intel* oneAPI DPC++/C++ Compiler
 - Intel* C++ Compiler 19.0 and 19.1 version

cmake/compilers/GNU.cmake

@@ -1,4 +1,4 @@
-# Copyright (c) 2020-2022 Intel Corporation
+# Copyright (c) 2020-2023 Intel Corporation
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -68,6 +68,9 @@ if (MINGW AND CMAKE_SYSTEM_PROCESSOR MATCHES "i.86")
     list (APPEND TBB_COMMON_COMPILE_FLAGS -msse2)
 endif ()
 
+# Gnu flags to prevent compiler from optimizing out security checks
+set(TBB_COMMON_COMPILE_FLAGS ${TBB_COMMON_COMPILE_FLAGS} -fno-strict-overflow -fno-delete-null-pointer-checks -fwrapv)
+
 # TBB malloc settings
 set(TBBMALLOC_LIB_COMPILE_FLAGS -fno-rtti -fno-exceptions)
 set(TBB_OPENMP_FLAG -fopenmp)

cmake/sanitize.cmake

@@ -1,4 +1,4 @@
-# Copyright (c) 2020-2021 Intel Corporation
+# Copyright (c) 2020-2022 Intel Corporation
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -39,4 +39,5 @@ set(TBB_TESTS_ENVIRONMENT ${TBB_TESTS_ENVIRONMENT}
     "LSAN_OPTIONS=suppressions=${CMAKE_CURRENT_SOURCE_DIR}/cmake/suppressions/lsan.suppressions")
 
 set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${TBB_SANITIZE_OPTION}")
+set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${TBB_SANITIZE_OPTION}")
 set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} ${TBB_SANITIZE_OPTION}")

doc/main/reference/reference.rst

@@ -47,7 +47,5 @@ The key properties of a preview feature are:
     scalable_memory_pools
     helpers_for_expressing_graphs
     concurrent_lru_cache_cls
-    constraints_extensions
-    info_namespace_extensions
     task_group_extensions
     custom_mutex_chmap

doc/main/tbb_userguide/Flow-Graph-exception-tips.rst

@@ -0,0 +1,17 @@
+.. _Flow_Graph_exception_tips:
+
+Flow Graph Tips for Exception Handling and Cancellation
+=======================================================
+
+
+The execution of a flow graph can be canceled directly or as a result of
+an exception that propagates beyond a node's body. You can then
+optionally reset the graph so that it can be re-executed.
+
+.. toctree::
+   :maxdepth: 4
+
+   ../tbb_userguide/catching_exceptions
+   ../tbb_userguide/cancel_a_graph
+   ../tbb_userguide/use_graph_reset
+   ../tbb_userguide/cancelling_nested_parallelism

doc/main/tbb_userguide/Flow-Graph-waiting-tips.rst

@@ -0,0 +1,11 @@
+.. _Flow_Graph_waiting_tips:
+
+Flow Graph Tips for Waiting for and Destroying a Flow Graph
+===========================================================
+
+.. toctree::
+   :maxdepth: 4
+
+   ../tbb_userguide/always_use_wait_for_all
+   ../tbb_userguide/avoid_dynamic_node_removal
+   ../tbb_userguide/destroy_graphs_outside_main_thread

doc/main/tbb_userguide/Guiding_Task_Scheduler_Execution.rst

@@ -61,8 +61,9 @@ assign a NUMA node identifier to the ``task_arena::constraints::numa_id`` field.
 
 The processors with `Intel® Hybrid Technology <https://www.intel.com/content/www/us/en/products/docs/processors/core/core-processors-with-hybrid-technology-brief.html>`_
 contain several core types, each is suited for different purposes.
-For example, some applications may improve their performance by preferring execution on the most performant cores.
-To set execution preference, assign specific core type identifier to the ``task_arena::constraints::core_type`` field.
+In most cases, systems with hybrid CPU architecture show reasonable performance without involving additional API calls.
+However, in some exceptional scenarios, performance may be tuned by setting the preferred core type.
+To set the preferred core type for the execution, assign a specific core type identifier to the ``task_arena::constraints::core_type`` field.
 
 The example shows how to set the most performant core type as preferable for work execution:
 

doc/main/tbb_userguide/Memory_Allocation.rst

@@ -68,4 +68,4 @@ redirect the standard routines to these functions.
 
    ../tbb_userguide/Which_Dynamic_Libraries_to_Use
    ../tbb_userguide/Allocator_Configuration
-   ../tbb_userguide/Automically_Replacing_malloc
+   ../tbb_userguide/automatically-replacing-malloc

doc/main/tbb_userguide/Migration_Guide/Task_API.rst

@@ -361,7 +361,7 @@ is not guaranteed to be executed next by the current thread.
         
         tbb::task_spawn(child);
         
-        root.wait_for_all();;
+        root.wait_for_all();
     }
 
 In oneTBB, this can be done using ``oneapi::tbb::task_group``. 

doc/main/tbb_userguide/Working_on_the_Assembly_Line_pipeline.rst

@@ -115,13 +115,13 @@ the overhead of copying a ``TextSlice``.
        oneapi::tbb::parallel_pipeline(
            ntoken,
            oneapi::tbb::make_filter<void,TextSlice*>(
-               oneapi::tbb::filter::serial_in_order, MyInputFunc(input_file) )
+               oneapi::tbb::filter_mode::serial_in_order, MyInputFunc(input_file) )
        &
            oneapi::tbb::make_filter<TextSlice*,TextSlice*>(
-               oneapi::tbb::filter::parallel, MyTransformFunc() )
+               oneapi::tbb::filter_mode::parallel, MyTransformFunc() )
        &
            oneapi::tbb::make_filter<TextSlice*,void>(
-               oneapi::tbb::filter::serial_in_order, MyOutputFunc(output_file) ) );
+               oneapi::tbb::filter_mode::serial_in_order, MyOutputFunc(output_file) ) );
    } 
 
 
@@ -172,13 +172,13 @@ equivalent version of the previous example that does this follows:
 
 
    void RunPipeline( int ntoken, FILE* input_file, FILE* output_file ) {
-       oneapi::tbb::filter<void,TextSlice*> f1( oneapi::tbb::filter::serial_in_order, 
+       oneapi::tbb::filter_mode<void,TextSlice*> f1( oneapi::tbb::filter_mode::serial_in_order, 
                                           MyInputFunc(input_file) );
-       oneapi::tbb::filter<TextSlice*,TextSlice*> f2(oneapi::tbb::filter::parallel, 
+       oneapi::tbb::filter_mode<TextSlice*,TextSlice*> f2(oneapi::tbb::filter_mode::parallel, 
                                                MyTransformFunc() );
-       oneapi::tbb::filter<TextSlice*,void> f3(oneapi::tbb::filter::serial_in_order, 
+       oneapi::tbb::filter_mode<TextSlice*,void> f3(oneapi::tbb::filter_mode::serial_in_order, 
                                          MyOutputFunc(output_file) );
-       oneapi::tbb::filter<void,void> f = f1 & f2 & f3;
+       oneapi::tbb::filter_mode<void,void> f = f1 & f2 & f3;
        oneapi::tbb::parallel_pipeline(ntoken,f);
    }
 

doc/main/tbb_userguide/automatically-replacing-malloc.rst

@@ -0,0 +1,22 @@
+.. _automatically-replacing-malloc:
+
+Automatically Replacing ``malloc`` and Other C/C++ Functions for Dynamic Memory Allocation
+==========================================================================================
+
+
+On Windows*, Linux\* operating systems, it is possible to automatically
+replace all calls to standard functions for dynamic memory allocation
+(such as ``malloc``) with the |full_name| scalable equivalents.
+Doing so can sometimes improve application performance.
+
+
+Replacements are provided by the proxy library (the library names can be
+found in platform-specific sections below). A proxy library and a
+scalable memory allocator library should be taken from the same release
+of oneTBB, otherwise the libraries may be mutually incompatible.
+
+.. toctree::
+   :maxdepth: 4
+
+   ../tbb_userguide/Windows_C_Dynamic_Memory_Interface_Replacement
+   ../tbb_userguide/Linux_C_Dynamic_Memory_Interface_Replacement

doc/main/tbb_userguide/snippets/flow_graph_examples.cpp

@@ -17,10 +17,6 @@
 /* Flow Graph Code Example for the Userguide.
 */
 
-//! Enable extended task_arena constraints feature for supporting Intel Hybrid Technology
-//! and Intel Hyper-Threading Technology.
-#define TBB_PREVIEW_TASK_ARENA_CONSTRAINTS_EXTENSION 1
-
 #include <oneapi/tbb/flow_graph.h>
 #include <vector>