Intel® oneAPI HPC Toolkit
Deliver Fast Applications That Scale across Clusters
Optimized Tools for High-Performance Computing
High-performance computing (HPC) is at the core of AI, machine learning, and deep learning applications. The Intel® oneAPI HPC Toolkit (HPC Kit) delivers what developers need to build, analyze, optimize, and scale HPC applications with the latest techniques in vectorization, multithreading, multi-node parallelization, and memory optimization.
This toolkit is an add-on to the Intel® oneAPI Base Toolkit, which is required for full functionality. It includes powerful data-centric libraries, advanced analysis tools, and Intel® Distribution for Python* for near-native code performance of core Python numerical, scientific, and machine learning packages.
"Intel's oneAPI toolkit has demonstrated powerful performance and good compatibility in GeoEast* software applications, and has provided us with important help in the further exploration of heterogeneous computing."
– BGP Inc.
Download the Toolkit
Deliver fast C++, Fortran, OpenMP*, and MPI applications that scale. Requires the Intel oneAPI Base Toolkit for full functionality.
Purchase with Priority Support
Submit questions, problems, and other technical support issues through direct and private interactions with Intel’s engineers.
Develop in the Cloud
Build and optimize oneAPI multiarchitecture applications using the latest optimized Intel® oneAPI and AI tools, and test your workloads across Intel® CPUs and GPUs. No hardware installations, software downloads, or configuration necessary. Free for 120 days with extensions possible.
Features
Simplify implementation of HPC applications on CPUs and accelerators with Intel’s industry-leading compiler technology and libraries.
Quickly gauge how your application is performing, how resource use impacts your code, and where it can be optimized to ensure faster cross-architecture performance.
Scale
Deploy applications and solutions across shared memory and distributed memory (such as clusters) computing systems using the included standards-driven MPI library and benchmarks, MPI analyzer and cluster tuning tools.
What's Included
Intel® oneAPI DPC++/C++ Compiler
Compile and optimize standard C++ and SYCL* code for CPU, GPU, and FPGA target architectures.
Intel® C++ Compiler Classic
Compile and optimize standard C++ for CPU architectures.
Intel® Fortran Compiler
Compile and optimize standard Fortran code for CPU and GPU architectures.
Intel® Fortran Compiler Classic
This standards-based Fortran compiler includes support for OpenMP that provides continuity with existing CPU-focused workflows.
Locate and debug threading, memory, and persistent memory errors early in the design cycle to avoid costly errors later.
Intel® MPI Library
Deliver flexible, efficient, scalable cluster messaging on CPU and GPU architectures and a variety of network fabrics.
Intel® Trace Analyzer and Collector
Understand MPI application behavior across its full runtime.
Get Started
Get Your System Ready
Check that you have the supported hardware and that your system meets the minimum requirements to install the HPC Kit.
Download the HPC Kit
After downloading, follow the Get Started Guide to configure your system and run your first sample.
Get Started Guide: Linux* | Windows* | macOS* | Containers
Next Steps
Access samples or run your own workloads with the help of tutorials and training.
Documentation & Code Samples
Documentation
Get Started Guides:
Linux | Windows | macOS | Containers
Code Samples
Learn how to access oneAPI code samples in a tool command line.
- Particle Diffusion
- Matrix Multiplication with CPUs and GPUs
- ISO3DFD Finite Difference Stencil Kernel - DPC++
- Mandelbrot
- ISO2DFD Finite Difference Stencil Kernel - DPC++
- 1d HeatTransfer Finite Difference Stencil Kernel - DPC++
macOS* Samples
Training
OpenMP* Offload Basics [self-paced]
Learn the fundamentals of using OpenMP offload directives to target GPUs, as well as using Intel® C, C++, and Fortran Compilers through hands-on practice in this guided learning path.
Essentials of DPC++ [self-paced]
Learn the basics of DPC++ for heterogeneous computing (CPU, GPU, FPGA, and AI accelerators) using live sample code on the Intel® Developer Cloud.
Intel® oneAPI Math Kernel Library (oneMKL) Essentials [self-paced]
Learn how to use oneMKL and its functions to create performant applications and speed up computations with low-level math routines.
Specifications
CPUs:
- Intel® Xeon® processor family
- Intel® Core™ processor family
- Other processors that are compatible with Intel® 64 architecture
GPUs:
- Intel® Processor Graphics Gen9 and above
- Xe Architecture
- NVIDIA* or AMD* GPUs using plug-ins from Codeplay*
Languages:
- C++ with SYCL
- Fortran
Note Requires Microsoft Visual Studio* on Windows
- Python
Operating systems:
- Windows
- Linux
- macOS†
†Not all HPC Kit components are available for macOS. The following components are included: Intel® C++ Compiler Classic and Intel® Fortran Compiler Classic.
Development environments:
- Compatible with compilers from Microsoft*, GCC*, Intel, and others that follow established language standards
- Windows: Microsoft Visual Studio
- Linux: Eclipse*
Distributed environments:
- MPI
OpenFabrics Interface* (OFI) framework implementation supporting the following:
- InfiniBand*
- iWARP, RDMA over Converged Ethernet (RoCE)
- Amazon Web Services Elastic Fabric Adapter (AWS EFA)*
- Cornelis Networks*
- Ethernet, IP over InfiniBand (IPoIB), IP over Intel OPA
For more information, see the system requirements.
Get Help
Your success is our success. Access these support resources when you need assistance.
For additional help, see our general oneAPI Support.
Stay in the Know with All Things CODE
Sign up to receive the latest trends, tutorials, tools, training, and more to
help you write better code optimized for CPUs, GPUs, FPGAs, and other
accelerators—stand-alone or in any combination.