Celebrating 5 years of Intel® oneAPI with their latest 2025.0 Release
News|by Gabrielle Alvear|3 December 2024
The latest 2025.0 release of Intel® oneAPI & AI Tools is now available, marking a significant milestone as we celebrate the 5-year anniversary of the oneAPI initiative.
This release further solidifies oneAPI's standing as a leading programming standard for data-centric heterogeneous computing.
Check out the latest Intel® oneAPI release and download the 2025.0 tools today and experience the future of computing.
Three Key Benefits of the latest 2025.0 Release
1. More Performance on Intel Platforms
- GenAI Performance: Achieve up to 3x higher performance on Intel® Xeon® 6 processors (P-cores) with oneDNN, Intel-optimised AI frameworks, and Intel® AMX1.
- HPCG Performance: Experience up to 2.5x better performance with MRDIMM2 and oneMKL.
- AI on PCs: Develop high-performance AI applications on PCs powered by Intel® Core™ Ultra processors (Series 2).
- Security and Encryption: Enhance security and encryption with the Intel® Cryptography Primitives Library.
2. More Access to Industry-Standard Tools
- Optimised Workflows: Benefit from built-in optimisations for AI frameworks and libraries, including native support for PyTorch 2.5 on Intel CPUs and GPUs.
- Performance Across Architectures: Achieve optimal performance across CPU, GPU, and AI accelerators with the latest LLMs—Llama 3.2, Qwen2, Phi-3.
- Streamlined Setup: Use our toolkit selector to install only what you need, simplifying your software setup.
3. More Hardware Choices
- Multi-Vendor Support: Enjoy increased support for multi-vendor, multi-architecture environments, including faster CUDA-to-SYCL migration of over 100 APIs used by popular AI, HPC, and rendering applications.
- Near-Native Performance: Achieve near-native performance on CPU and GPU for numeric compute with Intel’s Python distribution.
- GPU Kernel Speedup: Get 4x speedup of GPU kernels for algorithms with oneDPL3.
- Future Flexibility: Gain future system flexibility through cross-hardware AI-acceleration libraries, including Triton, JAX, and OpenXLA.
Speak with our experts to learn how you can deliver performant AI & HPC Code with Confidence
Join the global ecosystem of 6.8 million developers who leverage these tools to build, optimise, and deploy high-performance software that runs seamlessly on any vendor architecture. Fill in the form below to get started.
You can also visit the Intel® site to learn more about one API's 5th Anniversary.
Contact Grey Matter
If you have any questions or want some extra information, complete the form below and one of the team will be in touch ASAP. If you have a specific use case, please let us know and we'll help you find the right solution faster.
By submitting this form you are agreeing to our Privacy Policy and Website Terms of Use.
