Oneapi

oneAPI

Great Reads

5 Minutes to Your First oneAPI App on DevCloud

by Jeremy C. Ong

A quick demonstration of writing an application using DPC++ and oneAPI and deploying to Intel DevCloud

by Intel

In this article, we’ll discuss the Intel GZIP example design, implemented with oneAPI, and how it can help make FPGAs more accessible.

An Introduction to Accelerator and Parallel Programming

by Intel

This is the first in a series of articles where I will talk about parallel programming and various ways to enable it on modern accelerators.

ArrayFire Interoperability with oneAPI, Libraries, and OpenCL

by Stefan Yurkevitch

In this article, we’ll be exploring how to integrate the oneAPI Deep Neural Network (oneDNN) library and the SYCL-based Data Parallel C++ (DPC++) programming language into existing codebases.

Latest Articles

5 Minutes to Your First oneAPI App on DevCloud

by Jeremy C. Ong

A quick demonstration of writing an application using DPC++ and oneAPI and deploying to Intel DevCloud

Accelerating Compression with FPGAs

by Intel

In this article, we’ll discuss the Intel GZIP example design, implemented with oneAPI, and how it can help make FPGAs more accessible.

An Introduction to Accelerator and Parallel Programming

by Intel

This is the first in a series of articles where I will talk about parallel programming and various ways to enable it on modern accelerators.

ArrayFire Interoperability with oneAPI, Libraries, and OpenCL

by Stefan Yurkevitch

In this article, we’ll be exploring how to integrate the oneAPI Deep Neural Network (oneDNN) library and the SYCL-based Data Parallel C++ (DPC++) programming language into existing codebases.

All Articles

top

oneAPI

5 Minutes to Your First oneAPI App on DevCloud

by Jeremy C. Ong

A quick demonstration of writing an application using DPC++ and oneAPI and deploying to Intel DevCloud

Accelerating Compression with FPGAs

by Intel

In this article, we’ll discuss the Intel GZIP example design, implemented with oneAPI, and how it can help make FPGAs more accessible.

An Introduction to Accelerator and Parallel Programming

by Intel

This is the first in a series of articles where I will talk about parallel programming and various ways to enable it on modern accelerators.

ArrayFire Interoperability with oneAPI, Libraries, and OpenCL

by Stefan Yurkevitch

In this article, we’ll be exploring how to integrate the oneAPI Deep Neural Network (oneDNN) library and the SYCL-based Data Parallel C++ (DPC++) programming language into existing codebases.

Breaking Cross-Architecture Barriers with oneAPI: Libraries for Easy Heterogeneous Compute

by Robert Mueller-Albrecht

In this article we explore how using oneAPI the software-development paradigm changes and targeting and maintaining multiple execution environments for a given workload becomes more easily achievable

Comparing Programming models: SYCL and CUDA

by Dhruv__Patel

In this article we compare and contrast SYCL and CUDA, and discuss how the oneAPI compiler can work with SYCL.

Cross-Architecture Capabilities: Thinking With GPUs

by Roger Winter

In this article we look at how developers can take advantage of the cross-architecture of oneAPI to make use of GPU resources in their applications.

Cross-Architecture Compiling: Using SYCL Code with the Intel oneAPI Compiler

by Sergiu Oprea

This article is a hands-on look at using the Intel oneAPI DPC++/C++ Compiler for compiling SYCL code built for cross-architecture deployment.

Cultivating Parallel Standards: Diversity, Alignment, and Cross-Pollination

by Intel

The article emphasizes the importance of interoperability between various standards, such as Level Zero, SYCL, SPIR-V, OpenMP, ISO C++, and ISO Fortran, and explores the evolution and alignment of these standards over the last decade, while also considering how SYCL may influence the future of

Device Discovery with SYCL

by Henry A Gabb, John Pennycook

Learn about the Accelerators in Your System

Discover How oneAPI Is Revolutionizing Programming

by Intel

It's not just between one architecture today and another architecture today, but the architectures of today and tomorrow. oneAPI has the potential to become the industry norm for compiling code for all kinds of architectures.

Faster XGBoost, LightGBM, and CatBoost Inference on the CPU

by Intel

Accelerate Your XGBoost, LightGBM, and CatBoost Inference Workloads with Intel® oneAPI Data Analytics Library (oneDAL)

Getting Started with oneAPI on Intel® DevCloud Using Jupyter

by Dhruv__Patel

In this article we demonstrate how to set up Intel DevCloud and get started using oneAPI while demonstrating some of oneAPI’s unique capabilities.

Getting To Know LLVM

by Bridget Mwikali

This article provides an overview of LLVM and how it applies to oneAPI and its compiler.

Heterogeneous Programming with oneAPI

by Intel

This article introduces the beta release of the oneAPI product to facilitate heterogeneous programming.

How to Determine if You’re Getting the Most from Your Cross-Architecture Implementation

by Dhruv__Patel

In this article we look at how developers can use Intel® Advisor and Intel® VTune™ Profiler to efficiently offload to GPU and optimize their cross-architecture applications.

How to Move from CUDA Math Library Calls to oneMKL

by Robert Mueller-Albrecht

Using the Intel® oneAPI Math Kernel Library SYCL API

How To Optimize A Parallel Stable Sort Performance Using The Revolutionary Intel® oneAPI HPC Toolkit

by Arthur V. Ratz

In this article I will thoroughly discuss about the several aspects of using the revolutionary new Intel® oneAPI HPC Toolkit to deliver a modern code that implements a parallel “stable” sort

oneAPI – The Cross-Architecture, Multi-Vendor Path to Accelerated Computing

by Intel

In this article we explore why oneAPI is an alternative to proprietary programming models for accelerated computing.

oneMD: A Molecular Dynamics Simulator in Modern C++ and SYCL

by Allister Beharry

oneMD is a molecular dynamics simulator coded in C++ 17 designed to take advantage of hardware data parallelism across a diverse set of devices and architectures using Intel's oneAPI framework and SYCL -- the successor to the OpenCL standard for parallel processing

oneMKL: C++ API with SYCL Support for Data Fitting

by Intel

Intel® oneAPI Math Kernel Library (oneMKL) now includes adding support for C++ and GPUs, taking full advantage of the SYCL cross-platform abstraction layer.

Optimize Distributed AI Training Using Intel® oneAPI Toolkits

by Abhay_Rawat, Dr. Amarpal S Kapoor

This article focuses on tuning and scaling a deep-learning-based algorithm on a cluster of compute nodes.

Port a CUDA App to oneAPI and DPC++ in 5 Minutes

by Jeremy C. Ong

A quick 5-minute introduction to porting a CUDA app to Data Parallel C++ (DPC++)

Portable, Accelerated Image Processing with the oneAPI Image Processing Library

by Valentin Kubarev

In this article we discuss how to use SYCL and oneIPL to offload Gaussian image filtering to an accelerator.

Raytracing From CUDA to SYCL 2020 via DPC++

by Shao Voon Wong

How to convert a code from parallel C++ ray-tracing code to CUDA, then to SYCL 2020 via Intel® DPC++

Scale Your Pandas Workflow with Modin

by Vasilij Litvinov

This article introduces Intel Distribution of Modin, part of the Intel oneAPI AI Analytics Toolkit (AI Kit), which is now available from Anaconda’s “defaults” channel (and from conda-forge, too).

SYCL versus CUDA

by Dhruv__Patel

In this article we compare and contrast SYCL and CUDA, introduce oneAPI, and discuss how the oneAPI compiler can work with SYCL.

Use oneAPI to Make Your C++ Application GPU Aware

by Jeremy C. Ong

Accelerate a C++ article with GPU support using Intel's oneAPI

Using oneAPI to Convert CUDA to SYCL

by Sergiu Ovidiu Oprea

This article is a hands-on look at the process of converting CUDA to SYCL.

What Cross-Architecture Programming Means for IoT

by Ahmed Hashesh

This article examines how Intel provides standardized specifications that streamline this environment.

Why ISO C++ Is Not Enough for Heterogeneous Computing

by Intel

In this article we look at why C++ with SYCL is the best approach to accelerated computing, and why the C++ standard is a critically important foundation but insufficient for the needs of accelerated computing.

Zero in on Level Zero

by Robert Mueller-Albrecht

An Open, Backend Approach to Compute Anywhere