ess logo  
 
 
 
     
     
  Products  
     
 
 
     
 
 
     
  Events & Promos  
 
 
 
     
Intel® oneAPI New
 
 

Modern workload diversity necessitates the need for architectural diversity; no single architecture is best for every workload. XPUs, including CPUs, GPUs, FPGAs, and other accelerators, are required to extract high performance.

Intel® oneAPI products will deliver the tools needed to deploy applications and solutions across these architectures. Its set of complementary toolkits—a base kit and specialty add-ons—simplify programming and help developers improve efficiency and innovation. The core Intel® oneAPI DPC++ Compiler and libraries implement the oneAPI industry specifications available at oneapi.com.

Watch this conversation where Tech.Decoded’s Henry Gabb and Senior Principal Engineer Paul Petersen discuss how oneAPI delivers specific benefits to developers, including:

 
  • oneAPI analysis tools that give deep insight into hardware utilization, system-wide performance, and memory.
  • Modeling what code can be best offloaded to other accelerators … and optimizing its performance using awesome goodies available in Intel® Advisor.
  • Insight on opportunities of using single-source code so developers spend their time on performance and value—optimizing code, designing algorithms, and analyzing systems and modeling parameters—and less on overhead.
  • The future … where technologies don’t just find code problems, but also fix them.
 

Get started with oneAPI

 
 
oneAPI: Why Should You Care?   Keynote: An In-Depth Tech Talk about oneAPI
     
 
oneAPI: The Path to Streamlined Cross-Architecture Development   Breaking Boundaries with Data Parallel C++
     
 
Data Parallel C++: An Open Alternative for Cross-Architecture Development   oneAPI for All: a New Initiative for Industry-wide Innovation
     

OneAPI for cross-architecture performance

Highlights
Data Parallel C++ Language for Direct Programming CUDA* Source Code Migration
Data Parallel C++ (DPC++) is an open, standards-based evolution of ISO C++ that incorporates Khronos SYCL* and community extensions to simplify data parallel programming. DPC++ allows code reuse across hardware targets, and enables high productivity and performance across CPU, GPU, and FPGA architectures, while permitting accelerator-specific tuning. The DPC++ Compatibility Tool is a migration engine that transforms CUDA* code into a standards-based DPC++ code.

Intel® DPC++ Compatibility Tool
AI and Data Analytics, Powered by oneAPI Libraries for API-Based Programming
Designed for end-to-end machine learning and data science pipelines, these toolkits are comprised of optimized Python* libraries and high-performance, deep learning frameworks and tools based on oneAPI libraries.

“Powered by oneAPI” describes frameworks, middleware, and applications built using one or more of the oneAPI industry specification elements, the DPC++ language, and libraries listed on oneapi.com.
Powerful libraries—including deep learning, math, and video and media processing—are preoptimized for domain-specific functions and custom coded to accelerate compute-intense workloads.
 

Download OneAPI Specification

The oneAPI specification extends existing developer programming models to enable a diverse set of hardware through language, a set of library APIs, and a low level hardware interface to support cross-architecture programming. To promote compatibility and enable developer productivity and innovation, the oneAPI specification builds upon industry standards and provides an open, cross-platform developer stack.
 

Download Intel oneAPI Product Brief