Optimized Tools for Delivering High-Performance, Cross-Architecture Applications
Adalta è Unico Elite Reseller Italiano di Intel Software oneAPI Base Toolkit. Richiesta quotazione…
Heterogeneous Development Made Easier
The Intel oneAPI Base Toolkit is a core set of tools and libraries for building and deploying high-performance, data-centric applications across diverse architectures—CPUs, GPUs, and FPGAs. It features:
- Data Parallel C++ (DPC++) language that allows code reuse across hardware targets and custom tuning for individual accelerators
- Domain-specific libraries and the Intel® Distribution for Python*, enabling drop-in acceleration across relevant architectures
- Enhanced profiling, design, and debug tools
Priority Support is paid product support that covers all of the components included in the toolkit. It provides the following benefits for one year:
- Direct and private interaction with Intel’s support engineers, including the ability to submit confidential support requests
- Accelerated response time for technical questions and other product needs
- Priority assistance for escalated defects and feature requests
- Free download access to all new product updates and continued access to older versions of the product
- Access to a vast libraryof self-help documentation built from decades of experience with creating high-performance code
- Access to Intel public community forums supported by community technical experts and monitored by Intel engineers
On-site or online training and consultation by Intel technical consulting engineers may be added at an additional cost.
Nuove caratteristiche Intel oneAPI 2023
- The oneAPI 2023 tools empower developers to maximize the advanced capabilities of 4th Gen Intel® Xeon® Scalable Processors (formerly codenamed Sapphire Rapids) with Intel® Advanced Matrix Extensions (Intel® AMX), Quick assist Technology (QAT), Intel® AVX-512, bfloat16, and more as well as Intel® Data Center GPU Max Series (formerly codenamed Ponte Vecchio) with datatype flexibility, Intel® Xe Matrix Extensions (Intel® XMX), vector engine, XE Link, and other features.
- Improved support for SYCL: To aid code portability across architectures and new architecture adoption, improved SYCL support was added to the Intel® oneAPI DPC++/C++ Compiler. Intel® oneAPI DPC++ Library expands support of the C++ standard library in SYCL kernels with additional functions to simplify coding of common algorithms.
- Easier CUDA code migration: CUDA-to-SYCL code migration is enhanced to create single source code for multiarchitecture systems. The Intel® DPC++ Compatibility Tool (based on the open source SYCLomatic project) adds more than 100 new CUDA APIs migrating to the equivalent SYCL language and library functions including runtime, math, neural network domains.
- Improve accelerated computing support with more SYCL2020 and OpenMP 5.0, 5.1 features
- Improve SYCL CPU and GPU offload performance
- SYCL/DPC++ is on-par with OpenMP on CPU. E.g. Geomean of SYCL/DPC++ HCPBench 25 WLs is 106% of OpenMP
- SYCL/DPC++ HCPBench (25 WLs) shows better geomean performance on PVC over CUDA@A100, e.g. HCPBench@PVC is 138% of CUDA@A100, oneBench@PVC is 110% of CUDA@A100.
- oneDPL adds the ability to use OpenMP for thread-level parallelism. This allows developers who already use OpenMP on multicore CPUs to also use oneDPL high-level parallel algorithms in their codes without introducing extra dependencies and performance risks
- The Intel® DPC++ Compatibility Tool (based on the open source SYCLomatic project) adds more than 100 new CUDA APIs migrating to the equivalent SYCL language and library functions including runtime, math, and neural network domains.
- Intel® oneAPI Math Kernel Library increases CUDA library function API compatibility coverage for BLAS and FFT; for Sapphire Rapids, leverages Intel® XMX to optimize matrix multiply computations for TF32, FP16, BF16, and INT8 data types; and provides interfaces for SYCL and C/Fortran OpenMP offload programming.
- The Intel oneAPI Video Processing Library supports the industry’s only hardware AV1 codec in the Intel Data Center GPU Flex Series and Intel® Arc™ processors; expands OS support for RHEL9, CentOS, Stream 9, SLES15Sp4, and Rocky 9 Linux; and adds parallel encoding feature to sample_multi_transcode.
- Intel® Distribution for GDB* allows developers now to efficiently debug applications running on discrete GPUs using the L0 graphics drivers.
- Intel® Distribution for GDB* has been updated with more functional and stability improvements.
- To reduce the default download size of the Intel Base Toolkit, Intel Distribution for Python* is now available via separate download.
- Intel® VTune™ Profiler enables ability to identify MPI imbalance issues via its Application Performance Snapshot feature; and adds support for Sapphire Rapids, Ponte Vecchio, and 13th Gen Intel® Core™ processors.
Intel® Advisor adds automated roofline analysis for Intel Data Center GPU MAX Series to identify and prioritize memory, cache, or compute bottlenecks and understand their causes, and delivers actionable recommendations for optimizing data-transfer reuse costs of CPU-to-GPU offloading.
- Intel® oneAPI Threading Building Blocks improves support and use of the latest C++ standard for parallel_sort, offers an improved synchronization mechanism to reduce contention when multiple task_arena calls are used concurrently, and adds support for Microsoft Visual Studio 2022 and Windows Server 2022.
- The latest Intel® Integrated Performance Primitives release adds optimization for lossless compression method, zlib 1.2.13 in Intel® IPP Data compression. These new optimizations help improve the quality and speed of compression/decompression, in various data compression applications.
- Fixed errors in planar YCbCr to RGB conversion in Intel® IPP Image Processing Color Conversions functions
- Ongoing performance improvements and implementations of customer reported requests.
- Provides optimized performance for Intel® Data Center GPU Max Series utilizing oneCCL.
- Enables support for Allreduce, Allgather, Reduce, and Alltoall connectivity for GPUs on the same node
- There are no new features for oneDAL in the 2023.0 release.
- Deliver production quality optimizations for Sapphire Rapids, Ponte Vecchio, DG2, and ATS-M with support for S8/S8 weights and activations allowing greater input influence on the outcomes on Intel SPR hardware with AMX, and wider operators – BF32 on Saphire Rapids CPUs and TF32 Pone Vechio GPUs yield more accurate inferencing
- Limited support for FP64 operators on PVC GPUs for high precision model deployment
- Deliver Graph API support to simplify integration to frameworks and extend optimization capabilities
Cosa contiene Intel oneAPI
The following Intel oneAPI Toolkits are also available with paid product support.
Intel oneAPI Base & HPC Toolkit
Optimized tools for high-performance computing.
Intel oneAPI Base & IoT Toolkit
Enhanced tools for solutions that run at the network’s edge.
Intel oneAPI Base & Rendering Toolkit
Powerful libraries and tools for high-fidelity rendering and visualization applications.