The one API 2022 toolkits were released today by Intel. Cross-architecture features have been enhanced in new toolkits, giving developers more utility and architectural options to speed up computing. “The one API software engineering team’s breadth of over 900 technical improvements to accelerate development time and performance for critical application workloads across Intel’s client and server CPUs and GPUs has impressed me.
The comprehensive set of one API technologies adheres to industry best practices and includes deep technical innovations that enable application developers to achieve the best possible run-time performance from the cloud to the edge. To improve programmer productivity on Intel platforms, our one API 2022 release includes multi-language support and cross-architecture performance acceleration “Intel’s chief technology officer, senior vice president, and general manager of the Software and Advanced Technology Group, Greg Lavender, said.
The world’s first unified compiler for C++, SYCL, and Fortran, data-parallel Python for CPUs and GPUs, comprehensive accelerator performance modeling and tuning, and performance acceleration for AI and ray-tracing visualization workloads are just a few of the new features. When developing cross-architecture applications, the one API cross-architecture programming model provides developers with tools aimed at increasing code productivity and velocity.
According to an Evans Data poll, 40% of developers are aiming towards heterogeneous systems, which include several processors, processor cores, and co-processors. With cross-architecture computing pushing ahead with one API over heterogeneous fabrics of CPUs, GPUs, FPGAs, and other accelerators—all of which require software to connect these pieces into a comprehensive solution—the pace of innovation is further increasing. Without the economic and technical constraints of proprietary programming models, developers can choose the finest hardware for a specific solution with one API.
Compilers, libraries, pre-optimized frameworks, analyzers, and debuggers are all part of the Intel one API toolkits for 2022, which deliver performance and productivity. Over the last year, more than 900 new and improved features have been added to the foundational and domain-specific toolkits, strengthening each tool. They can now be downloaded or used for free in the Intel DevCloud. Among the highlights are:
Cross-architecture programming
- Using a shared LLVM backend, Intel produced the world’s first unified compiler that implements C++, SYCL, and Fortran for CPUs and GPUs.
- Python, today’s most popular programming language, gets accelerated computing on CPUs and GPUs.
- The Intel DPC++ Compatibility Tool has been updated to transition 90 to 95 per cent of CUDA code to SYCL/DPC++ automatically.
Performance on the latest hardware
- Hardware assistance – Intel one API Toolkits are optimized to enable advanced features of the latest and upcoming new hardware, such as 12th Generation Intel Core processors with AVX-VNNI, Next Generation Intel Xeon Scalable processors codenamed Sapphire Rapids with Intel Advanced Matrix Extension (Intel AMX), and upcoming Xe client and data center GPUs.
AI performance optimizations
- The latest Intel Optimization for TensorFlow and Intel Optimization for PyTorch boosts deep learning framework performance by up to ten times over previous versions.
- On Intel CPUs, the new Intel Extension for Scikit-learn accelerates machine learning algorithms by more than 100 times over the open-source version.
- Intel Neural Compressor was introduced to improve inference performance across multiple deep learning frameworks using post-training optimization techniques.
Advanced tools for development productivity
- Expert performance analysis for CPUs and accelerators – The flame graph display in Intel VTune Profiler aids in the visualisation of performance hot spots. Before making code modifications, developers can use Intel Advisor’s accelerator performance modelling to assess the performance benefits of offloading to a GPU.
- Advanced ray tracing – New capabilities such as cone telemetry, auxiliary feature denoising, and FP16 support improve overall rendering performance by providing more robust forms and reducing rendering times. Support for forthcoming Intel Xe GPUs, as well as real-time denoising, boost industry-leading, final frame, production-quality rendering even further.
- Deeper Microsoft Visual Studio Code integration, support for Microsoft Visual Studio 2022, and Microsoft WSL2 for Linux development on Windows have all been added to the development environment.
also read:
Apple to launch its 27-inch iMac Pro with a mini-LED display
