Intel® oneAPI Base Toolkit Release Notes

ID 768214
Updated 10/25/2024
Version 2025.0.0
Public

author-image

By

Intel® oneAPI Base Toolkit supports direct programming and API programming, and delivers a unified language and libraries that offer full native code support across a range of hardware including Intel® and compatible processors, Intel® Processor Graphics Gen9, Gen11, Gen12, Intel® Iris® Xe MAX graphics, Intel® Data Center GPU Max Series, and Intel® Arria® 10 or Intel® Stratix® 10 SX FPGAs. It also contains analysis & debug tools for development and performance tuning.

System Requirements

Please see Intel oneAPI Base Toolkit System Requirements

Intel® oneAPI Base Toolkit Major Component Versions

Please visit Intel® oneAPI Toolkit and Component Versioning Schema for semantic versioning schema detail. 

The following table contains major versions of components in the latest oneAPI Base Toolkit 2025.0.0

Component Name Version
Intel® oneAPI DPC++ Compiler 2025.0.0
Intel® oneAPI DPC++ Library 2022.7.0
Intel® DPC++ Compatibility Tool 2025.0.0
Intel® oneAPI Math Kernel Library 2025.0.0
Intel® Distribution for GDB* 2025.0.0
Intel® VTune™ Profiler 2025.0.0
Intel® Advisor 2025.0.0
Intel® oneAPI Threading Building Blocks 2022.0.0
Intel® Integrated Performance Primitives 2022.0.0
Intel® Cryptography Primitives Library 2025.0.0
Intel® oneAPI Collective Communications Library 2021.14.0
Intel® oneAPI Data Analytics Library 2025.0.0
Intel® oneAPI Deep Neural Networks Library 2025.0.0

 

Note:  For Intel® AI Tools, please ensure you install the compatible version of the Intel® oneAPI Base Toolkit.

New in Intel® oneAPI Base Toolkit 2025.0

Toolkit Level Updates

  • Get the most from the latest hardware with new Intel developer tools support for Intel® Xeon® 6 Processors with Performance-Cores (P-Cores), formerly codenamed Granite Rapids and Intel® Core™ Ultra processors (Series 2), formerly codenamed Lunar Lake.
  • The Intel® oneAPI Base Toolkit (Base Kit) now offers two convenient subset bundles offering smaller downloads for specific developer use cases. Intel® C++ Essentials is for C++ developers is focused on compiling, debugging, and utilizing the most widely used Base Kit performance libraries for Intel CPUs and GPUs. Intel® Deep Learning Essentials provides advanced developers with the tools and libraries to develop, compile, test, and optimize deep learning frameworks and libraries, such as PyTorch and TensorFlow, for Intel CPUs and GPUs.
  • ISO C++ parallel STL code runs on CPU and offloads to GPU using Intel® oneAPI DPC++/C++ compiler.
  • Experience dynamic and flexible GPU programming with Intel® oneAPI DPC++/C++ Compiler's SYCL Bindless Textures support, utilizing textures at runtime without compile-time knowledge for improved performance and scalability in C++ with SYCL applications, alongside powerful new LLVM sanitizers to streamline development and ensure enhanced device code reliability.
  • Maximize your application's efficiency with Intel oneAPI DPC++/C++ Compiler's performance optimization features, tailored for the latest Intel platforms including Intel® Xeon® 6 Processors and Intel® Core™ Ultra processors (Series 2), to deliver peak performance and cutting-edge computing experiences.
  • Leverage enhanced OpenMP standards support and performance enhancements with the Intel® oneAPI DPC++/C++ Compiler, including OpenMP 5.x and 6.0 features for increased efficiency and flexibility, complemented by upgraded compiler opt-report capabilities for in-depth performance insights and optimization feedback.
  • GPU kernels run faster with Intel® oneAPI DPC++ Library (oneDPL) improved performance by up-to 4X for algorithms including reduce, scan and many other functions. 
  • Use oneDPL Range-based algorithms with over 20 new C++20 standard ranges and views to accelerate on multiarchitecture devices.
  • Intel® Math Kernel Library (oneMKL)SYCL Discrete Fourier Transform API is easier to use and to debug with key compilation messages added for type safety, reducing time to develop your application, especially when targeting Intel GPUs.
  • HPC workloads using oneMKL single precision 3D real in-place FFTs run faster on Intel® Data Center GPU Max Series.
  • Multi-threads apps run faster with Intel® oneAPI Threading Building Blocks (oneTBB) task_group, flow_graph and parallel_for_each improved scalibility
  • Get result faster using oneTBB flow graph to process overlapping messages on a shared graph, waiting for a specific message using the new try_put_and_wait experimental API
  • Intel® Integrated Performance Primitives (Intel IPP) now boasts CET-enabled protection, safeguarding your software against control-flow attacks and mitigates exploitation risks. Safeguard your software with cutting-edge, hardware-enforced security measures.
  • Use Intel® Cryptography Primitives Library to turbocharge RSA encryption (2K, 3K, 4K) with multi-buffer capabilities—achieving up to 4x the speed of OpenSSL.
  • Use Intel® Cryptography Primitives Library to dive into the future of hashing with our enhanced SM3 algorithm, now 5x faster thanks to the SM3_NI instructions
  • Intel® VTune™ Profiler now identifies GPU-bound bottlenecks, optimize rendering pipelines, and improve overall application responsiveness for media and content creation applications on Intel® Core™ Ultra 200V, codenamed Lunar Lake.
  • Intel® VTune™ Profiler now identifies and optimizes device-side inefficiencies for Direct X APIs.
  • Intel® Advisor introduces a more adaptable kernel matching mechanism, enabling developers to identify and analyze code regions relevant to their specific optimization goals. The integration with the XCG app streamlines the process of offloading computation to GPUs, enhancing performance on Intel's latest hardware.
  • Intel® oneAPI Deep Neural Network Library (oneDNN) dramatically boosts performance for Large Language Models and scaled dot-product subgraphs.
  • Intel® oneAPI Communications Library (oneCCL) now includes optimizations that enable workloads to scale and perform even better than before. Important enhancements have been made to key collectives, and even more optimizations are now available on single-node CPU configurations.  
  • Save time with Intel® DPC++ Compatibility Tool to easily migrate your CUDA code and CMake build script to SYCL as demonstrated by auto migration of more APIs used by popular AI, HPC and rendering apps.  The migrated code is easy to comprehend with SYCLcompat, easy to debug using CodePin, and runs performantly on Nvidia GPUs
  • Free your imaging apps from vendor lock-in using Intel® DPC++ Compatibility Tool to migrate bindless textures APIs to SYCL image extension
  • Intel® Distribution for GDB* adds support for Intel® Core™ Ultra processors (Series 2) on Windows* allowing developers to efficiently debug application code on these new CPUs and GPUs.
  • Intel® Distribution for GDB* rebases to GDB* 15 staying current and aligned with the latest enhancements supporting effective application debug.
  • Intel® Distribution for GDB* enhances the developer experience, both on the command line and when using Microsoft* Visual Studio and Visual Studio Code* by boosting the debugger performance and refining the user interface.

Intel® oneAPI DPC++ Compiler 2025.0.0

  • Unlock dynamic execution and flexible programming for Intel GPUs with the Intel® oneAPI DPC++/C++ Compiler's new SYCL Bindless Textures support, allowing developers to utilize textures at runtime without compile-time knowledge, and leverage texture objects for enhanced performance and scalability in C++ with SYCL applications.
  • Streamline your development process with the Intel® oneAPI DPC++/C++ Compiler's new LLVM sanitizers providing powerful tools to detect and troubleshoot device code issues with ease, ensuring cleaner and more reliable applications. 
  • Maximize your application's efficiency with Intel oneAPI DPC++/C++ Compiler's performance optimization features, tailored for the latest Intel platforms including Intel® Xeon® 6 Processors and Intel® Core™ Ultra processors (Series 2), to deliver peak performance and cutting-edge computing experiences.
  • The Intel® oneAPI DPC++/C++ Compiler enhances OpenMP standards conformance and performance optimizations for OpenMP 5.x and the new OpenMP 6.0 standards, featuring new interop properties, sync target no wait, free-agent threads/tasks, extended OMP_PLACES syntax, and advanced thread limit controls, all designed to boost application performance with unparalleled efficiency and flexibility.
  • Enhanced compiler insights with Intel® oneAPI DPC++/C++ Compiler's significant upgrades to the opt-report capabilities, now offering a more user-friendly optimization report that includes OpenMP offloading details, integrates with the open-source optimization remark framework, and adds optimization report functionality to the SYCL and OpenMP runtimes as well as AOT compilation paths for a more comprehensive understanding of application performance improvements.
  • Streamlined FPGA development with Intel® oneAPI DPC++/C++ Compiler's latest enhancements, featuring usability and performance improvements, flexible local buffer size configurations, seamless SPIR-V translation, and streamlined command options where -fintelfpga implies -qactypes and -fp-model=fast triggers aoc -vpfp-relaxed, simplifying the workflow for faster, more efficient FPGA application development

Intel® oneAPI DPC++ Library 2022.7.0

  • GPU kernels run faster with Intel® oneAPI DPC++ Library (oneDPL) improved performance by up-to 4X for algorithms including reduce, scan and many other functions. 
  • Use production released oneDPL Range-based algorithms with over 20 new C++20 standard ranges and views to accelerate on multiarchitecture devices
  • ISO C++ parallel STL code runs on CPU and offloads to GPU using Intel® oneAPI DPC++/C++ compiler

Intel® DPC++ Compatibility Tool 2025.0.0

  • Save time with Intel® DPC++ Compatibility Tool to easily migrate your CUDA code and CMake build script to SYCL as demonstrated by auto migration of more APIs used by popular AI, HPC and rendering apps.  The migrated code is easy to comprehend with SYCLcompat, easy to debug using CodePin, and runs performantly on Nvidia GPUs
  • Free your imaging apps from vendor lock-in using Intel® DPC++ Compatibility Tool to migrate bindless textures APIs to SYCL image extension

Intel® oneAPI Math Kernel Library 2025.0.0

  • Developers targeting Intel® Xeon® 6 Processors will benefit from the performance optimizations available on Intel(R) oneMKL 2025.0 across multiple domains as BLAS, LAPACK and FFT.
  • HPC workloads using single precision 3d real in-place FFT will get significant improvements to execute on Intel® Data Center GPU Max Series.
  • New distribution models and data types available for Random Number Generation (RNG) using SYCL device API. 
  • SYCL Discrete Fourier Transform API got easier to use and to debug with key compilation messages added for type safety, reducing time to develop your application, in special when targeting Intel GPUs.

  • Sparse domain on SYCL API now supports sparse matrices using Coordinate Format (COO). This format is widely used for fast sparse matrices construction and it can be easily converted to other popular formats such as Compressed Sparse Row (CSR) and Compressed Sparse Column) CSC.

Intel® Distribution for GDB* 2025.0.0

  • Intel® Distribution for GDB* adds support for Intel® Core™ Ultra processors (Series 2) on Windows* allowing developers to efficiently debug application code on these new CPUs and GPUs.
  • Intel® Distribution for GDB* rebases to GDB* 15 staying current and aligned with the latest enhancements supporting effective application debug.
  • Intel® Distribution for GDB* enhances the developer experience, both on the command line and when using Microsoft* Visual Studio and Visual Studio Code* by boosting the debugger performance and refining the user interface.

Intel® VTune™ Profiler 2025.0.0

  • Adds support for Intel® Core™ Ultra 200V, codenamed Lunar Lake, Intel® Core™ Ultra 200 "Arrow Lake-S" series and 6th gen. Intel® Xeon® Scalable Processors, codenamed Granite Rapids.
  • Identify GPU-bound bottlenecks, optimize rendering pipelines, and improve overall application responsiveness for media and content creation applications on Intel® Core™ Ultra 200V, codenamed Lunar Lake.
  • Identify and optimize device-side inefficiencies for Direct X APIs.
  • Adds profiling support for Python 3.11. Improved productivity with the ability to focus Python profiling to only areas of interest and control performance data collection with ITT APIs.
  • The Platform Profiler capabilities in Intel® VTune™ Profiler has released its final version, available as stand-alone download. No further feature improvements or security fixes will be available after this final release. The capabilities are now transitioned to the EMON command line interface. For more information, see the Intel® VTune™ Profiler – Platform Profiler transition notice.

Intel® Advisor 2025.0.0

  • Intel Advisor 2025.0 expands its hardware support to include GNR, Intel's next-generation platform. Developers can now leverage Advisor's powerful analysis and optimization capabilities on the latest hardware.
  • Intel Advisor 2025.0 introduces a more adaptable kernel matching mechanism, enabling developers to identify and analyze code regions relevant to their specific optimization goals. The integration with the XCG app streamlines the process of offloading computation to GPUs, enhancing performance on Intel's latest hardware.

Intel® oneAPI Threading Building Blocks 2022.0.0

  • Multi-threads apps run faster with oneTBB task_group, flow_graph and parallel_for_each improved scalibility
  • Get result faster using oneTBB flow graph to process overlapping messages on a shared graph, waiting for a specific message using the new try_put_and_wait experimental API

Intel® Integrated Performance Primitives 2022.0.0

  • Security First: Intel IPP now boasts CET-enabled protection, safeguarding your software against control-flow attacks and mitigates exploitation risks. Safeguard your software with cutting-edge, hardware-enforced security measures.
  • Speed Up with Optimized Functions: ippiNormRel_L2_8u_C*MR now optimized for Intel's latest Granite & Sapphire Rapids platforms.
  • Thread-Safe Excellence:  Bug fixes on ippsWinKaiser_32f_I() increased its reliability in multi-threaded environments. 
  • Intel® Integrated Performance Primitives Cryptography (Intel® IPP Cryptography) is now Intel® Cryptography Primitives Library!
  • Experience the power of dispatching on SRF, turbocharging RSA encryption (2K, 3K, 4K) with multi-buffer capabilities—achieving up to 4x the speed of OpenSSL.
  • Dive into the future of hashing with our enhanced SM3 algorithm, now 5x faster thanks to the SM3_NI instruction.
  • Now built with the secure and powerful ICX compiler, our library is optimized for peak performance.

Intel® Cryptography Primitives Library 2025.0.0

  • Intel® Integrated Performance Primitives Cryptography (Intel® IPP Cryptography) is now Intel® Cryptography Primitives Library!
  • Experience the power of dispatching on SRF, turbocharging RSA encryption (2K, 3K, 4K) with multi-buffer capabilities—achieving up to 4x the speed of OpenSSL.
  • Dive into the future of hashing with our enhanced SM3 algorithm, now 5x faster thanks to the SM3_NI instruction.
  • Now built with the secure and powerful ICX compiler, our library is optimized for peak performance.

Intel® oneAPI Collective Communications Library 2021.14.0

Intel® oneAPI Communications Library 2021.14.0 brings further optimizations that allow workloads to scale and perform better. Some of the key features include:

  • Enhancements to oneCCL's Key-Value store that improves communication among ranks, allowing workloads to scale up to even larger number of nodes
  • Performance improvements to key collectives such as Allgather, Allreduce and Reduce-scatter
  • Even further optimizations for workloads on single-node CPU configurations
  • Other lower level optimizations that improve speed and resource utilization

Intel® oneAPI Data Analytics Library 2025.0.0

  • Intel® oneAPI Data Analytics Library 2025.0.0 enabled calculation of SHAP values for binary classification models required for explainability RF algorithms
  • Intel® oneAPI Data Analytics Library 2025.0.0 enabled performance improvements for Decision Forest

Intel® oneAPI Deep Neural Networks Library 2025.0.0

Intel® oneAPI Deep Neural Network Library (oneDNN) 2025.0 introduces:

  • Accelerated AI workloads: Experience significantly faster performance for Large Language Models and scaled dot product subgraphs.
  • Optimized for Intel hardware: Benefit from oneDNN's tailored optimizations for Intel CPUs and GPUs, ensuring maximum efficiency and performance.
  • Enhanced productivity: Save time and resources by leveraging oneDNN's cutting-edge acceleration technology for hardware to accelerate your AI development and deployment.

Deprecation Notices

  • None

Installation Instructions

Please visit Installation Guide for Intel oneAPI Toolkits

How to Start Using the Tools

Please reference:

Known Issues, Limitations and Workarounds

  1. Known Issue: When using Intel® oneAPI DPC++/C++ Compiler on a Linux machine, users may run into an issue if the highest version of GNU gcc detected doesn't have the equivalent g++ package installed. More details on the error and workarounds can be found here.
  2. Known Issue: For latest supported Eclipse IDE eclipse-cpp-2024-06-R, sample browser plugin is unable to integrate during basekit installation due to missing 'osgi.bundle; org.apache.commons.io 0.0.0' bundle. Workaround is to skip the integration of eclipse during installation and later provide the plugin location manually. 
  3. Limitations

    1. The 2025.0 and onwards release of Intel oneAPI development tools no longer support the creation of 32bit applications. Only 64bit applications are supported. As a result, the 2025.0 oneAPI environment setup scripts (setvars, oneapi-vars and modulefiles) included with the Intel oneAPI toolkits only support initialization of 64-bit development environments.

      If you are developing 32-bit libraries and applications using older versions (2024.x and earlier) of the Intel oneAPI Toolkits you will have to manually configure your 32-bit development environment. For example, if you are using the 2023.0.0 version of the icc compiler with the 2023.0.0 version of the mkl library, you can configure that environment manually by sourcing the $ONEAPI_ROOT/compiler/2023.0.0/env/vars.sh and $ONEAPI_ROOT/mkl/2023.0.0/env/vars.sh scripts with the ia32 parameter. 

      If you are using the new "unified" directory layout introduced with the 2024.x oneAPI toolkits release, the oneapi-vars script can still be used to configure a 32-bit development environment, for 2024.x releases, only, by passing ia32 as an argument to the oneapi-vars script. This is because each oneapi-vars script is unique in the unified directory layout. This only works with the 2024.x toolkit releases.

      Similarly, each oneAPI toolkit release includes a unique set of modulefiles. Which means user can configure a 32-bit development environment using modulefiles, but only when referencing pre-2025.0 toolkits.

    2. Running any GPU code on a Virtual Machine is not supported at this time.

    3. If you have chosen to download the Get Started Guide to use offline, viewing it in Chrome may cause the text to disappear when the browser window is resized. To fix this problem, resize your browser window again, or use a different browser.

Release Notes for All Tools included in Intel® oneAPI Base Toolkit

Previous oneAPI Releases

Notices and Disclaimers

Intel technologies may require enabled hardware, software or service activation.

No product or component can be absolutely secure.

Your costs and results may vary.

© Intel Corporation. Intel, the Intel logo, and other Intel marks are trademarks of Intel Corporation or its subsidiaries. Other names and brands may be claimed as the property of others.

No license (express or implied, by estoppel or otherwise) to any intellectual property rights is granted by this document.

The products described may contain design defects or errors known as errata which may cause the product to deviate from published specifications. Current characterized errata are available on request.

Intel disclaims all express and implied warranties, including without limitation, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement, as well as any warranty arising from course of performance, course of dealing, or usage in trade.

Product and Performance Information

1

Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex.