Intel oneAPI 2024 helps accelerate HPC, AI and rendering applications
Intel oneAPI Toolkit 2024 has been released! The new version includes new features and enhancements that accelerate HPC, AI and also rendering applications on various platforms, including Intel CPUs, GPUs and AI accelerators. The tools are based on oneAPI, an open and unified programming model that supports C++, OpenMP, SYCL, Fortran MPI and Python. Developers can access the tools from Intel or via popular repositories and containers, and they can also use the Intel Developer Cloud to evaluate the latest Intel hardware and software.
What challenges are developers and ISVs facing?
Many data-centric workloads run best when deployed across a mix of architectures (CPU, GPU, FPGA, AI and other accelerators). However, different architectures typically require unique languages, tools and libraries, adding complexity for developers and limiting code reuse. This makes it difficult to take advantage of multiarchitecture systems and new architectures, optimize application performance, and maintain code efficiently and cost-effectively.
Intel® Software Development Tools help developers build and optimise high-performance applications efficiently through a complete set of advanced compilers, libraries, optimised frameworks, and analysis, debug and porting tools. Built on a legacy with decades of expertise, the tools support:
Familiar languages⎯C, C++, SYCL, Fortran and Python, plus standards including MPI and OpenMP, providing full continuity with existing code.
Intel CPUs, GPUs and FPGAs⎯Enabling unique hardware features such as those for performance, high-bandwidth memory, AI and rendering.
Highlights of the 2024 Intel oneAPI tools release
Intel DPC++/C++ Compiler improves productivity and code offload with a near complete SYCL 2020 implementation, an easier way to adapt C++ code using virtual functions to run with SYCL device offload, and improved error messaging and handling for SYCL and OpenMP code.
Intel Fortran Compiler provides initial Fortran 2023 standards support and adds popular LLVM sanitisers to catch various errors and bugs on CPU.
Intel oneAPI Math Kernel Library integrates vector math optimizations into RNGs for HPC simulations, statistical sampling, and more on X86 CPUs and Intel GPUs. It also delivers high-performance benchmarks optimized for Intel Xeon CPU Max Series and Intel Data Center GPU Max Series.
Intel oneAPI Data Analytics Library optimises big data analysis with integration into Microsoft’s open source ML.Net framework to build and ship machine learning models.
Intel oneAPI Deep Neural Network Library streamlines storage efficiency and optimises performance on Intel Xeon processors. It also enhances compatibility with graph compiler capabilities and advances code generation through the Compiler Xbyak backend and accelerated sparse_tensor_dense_matmul() performance on Intel Xeon processors with TensorFlow 2.5.
Intel oneAPI Threading Building Blocks (oneTBB) can be compiled on WebAssembly (Wasm) using Emscripten, facilitating the library’s use by applications running on a web browser.
Intel MPI Library simplifies large MPI message passing and provides more granular process grouping by using MPI Sessions. It also improves MPI application performance on systems with nodes that include the data genter GPU Max Series through efficient message passing and collective operations infrastructure. It enables Fortran codes to use larger data sets through seamless support of 8-byte integers with native support of ILP64. It also supports systems with software management stacks based on the PMIx standard.
Intel oneAPI Collective Communications Library boosts performance for distributed AI workloads through better utilisation of hardware resources.
Intel Integrated Performance Primitives helps users securely transmit data faster with Intel AVX-2 and Intel AVX-512 optimisations for the AES-GCM and RSA algorithms. It also provides fast performance for the image and signal processing domains with Intel AVX-512 optimisations for various functions.
Buy Intel oneAPI 2024 with Priority Support
Alfasoft is an Intel Software Elite Reseller. We offer exclusive pricing for the Intel tools with Priority Support.