HPC Development

Build cross-architecture HPC, AI, and scientific visualization applications efficiently.

The HPC Software Journey to Exascale

HPC is driving significant modern-day discoveries using traditional HPC methods and newer AI augmented solutions. These discoveries are at the core of breakthroughs in science, engineering, finance, and medicine—from crash simulation to weather forecasting to molecular modeling.

HPC Software Portfolio

Intel’s end-to-end, flexible HPC solutions deliver world-class compute, acceleration, and software innovation built around performance, openness, and scale.

Cross-architecture Performance

Powerful hardware (CPU, GPU, and FPGA) capabilities and oneAPI software to simplify development and boost performance enable portability across HPC nodes, data-center servers, high-powered workstations, and cloud.

Open Development

Through open development, the ecosystem innovates faster. Intel’s open source technology contributions and oneAPI open, cross-architecture programming provides choices without proprietary lock-in.

Ecosystem Leadership

Collaborations with universities and research organizations, industry groups, standards bodies, and HPC communities continuously innovate and scale new HPC technologies.

Intel's Cross-architecture Development Tools for oneAPI

Developers, researchers, and data scientists can confidently develop performant code quickly and correctly with these tools. Scale compute-intensive workloads that exploit cutting-edge features of HPC clusters, CPUs, GPUs, and FPGAs powered by Intel. oneAPI supports HPC standards including C/C++, Fortran, Python*, OpenMP*, SYCL*, and MPI for integration with existing code.

Build, analyze, optimize, and scale fast HPC applications using vectorization, multithreading, multi-node parallelization, and memory optimization techniques. Deploy across shared- and distributed-memory computing systems using foundational tools (compilers and libraries), Intel® MPI Library, and cluster tuning and health-check tools.

Download the Intel® oneAPI Base Toolkit

Download Intel® oneAPI HPC Toolkit

AI Tools—Powered by oneAPI

Accelerate end-to-end data science and machine learning pipelines. Achieve drop-in acceleration with optimized Python libraries and deep learning frameworks.

Learn More |Download

    Intel® Rendering Toolkit

    Create high-fidelity, interactive, photorealistic rendering and visualization applications for data and scientific visualization, design, and studio content creation.

    Learn More |Download

      Intel® Distribution of OpenVINO™ Toolkit—Powered by oneAPI

      Build high-performance AI and deep learning applications and simplify inference deployment.

      Learn More |Download

        HPC Use Cases

        Intel Tools Help Prepare Code for Aurora

        The Aurora Supercomputer from Argonne National Laboratory (built on Intel® architecture and HPE Cray supercomputer) will be one of the first exascale systems in the US.

        Zuse Institute Berlin (ZIB) Ported easyWAVE Tsunami Simulation Application

        Learn how porting from CUDA* to oneAPI delivered performance on CPUs, GPUs, and FPGAs.

        Accelerate Google Cloud Platform* Service Workloads for HPC

        This service offers great performance for HPC workloads: 40% higher performance per core on Intel Xeon processors optimized by Intel® oneAPI Base & HPC Toolkits.

        CERN* Uses Intel® Deep Learning Boost & oneAPI to Juice Inference without Accuracy Loss

        CERN*, SURFsara*, and Intel are driving breakthrough performance on simulations used in scientific, engineering, and financial applications.

        Visualization & File System Use Cases Show Value of Large Memory Fat Nodes on Frontera

        Texas Advanced Computing Center (TACC) uses on the Frontera supercomputer showcase advanced visualization using rendering libraries and optimized memory from Intel.

        GROMACS Advances Open Source Drug Discovery with oneAPI

        GROMACS, a simulation application used to design new drugs, was optimized by oneAPI. CUDA code was migrated to SYCL to create cross-architecture code targeting Intel CPUs and multiple accelerators.

        More Resources

        The Parallel Universe Magazine

        Read Intel's quarterly magazine featuring the latest tools, tips, and training to expand your expertise.

        oneAPI Video Series

        Watch this collection of short videos to get started with oneAPI.

        Technical Articles & How-Tos

        Access a library of knowledge articles to improve software performance.

        Intel® Software on YouTube*

        Build your development skill set with this collection of videos.