Classify images using a pretrained SqueezeNet Open Neural Network Exchange (ONNX*) model with the ONNX Runtime accelerator and the OpenVINO™ toolkit execution provider.
High-performance, embedded machine vision controller. Offers powerful AI inference capability and rich I/O for industrial automation use cases, including 5 Gigabit ethernet ports.
This tutorial takes "heat equation" code written in standard C and C++, adds DPC++ constructs, and runs it on different parallel processing units.
Learn about the collaboration of Intel and OmniSci that helps data scientists to run large-scale analytical computations over enormous datasets.
OpenVINO™ 2021.4 Release
The process of migrating and compiling the C++ code to oneAPI DPC++ Compiler (for Data Parallel C++), running it on Windows*, and examines the relevance of oneAPI to customers in the healthcare space.
Discover how new Intel® Inspector features support analysis and debugging of code that is offloaded to GPUs.
This case study illustrates how to take DPC++ code and successfuly offload it to Gen9 and Gen11 architectures for optimal performance.
Get an introduction to mpitune_fast, an MPI tuning tool found in the Intel MPI Library. Article includes code walks and benchmarks.
Get tips and instructions for using Intel compiler optimization reports to write faster code that performs better.
The standards-based Intel® oneAPI Math Kernel Library open-source interface project lets developers to use optimized third-party libraries to deploy fast BLAS on CPUs and GPUs.
Analyze, tune, and optimize AI and HPC applications and solutions to unlock the power of the 3rd Generation Intel® Xeon® Scalable processors.