Three Quick, Practical Examples of OpenMP* Offload to GPUs

OpenMP* has been around since October 1997—an eternity for any software—and has long been the industry-wide parallel-programming model for high-performance computing.

It continues to evolve in lockstep with the ever-expanding hardware landscape: The API now supports GPUs and other accelerators.

In this session, Intel principal engineer Xinman Tian shares three examples of how to develop code that exploits GPU resources using the latest OpenMP features, including:

• An introduction to OpenMP and its GPU-offload support
• Examples of OpenMP code offloaded to GPUs, including products with X^e architecture
• How to take advantage of the Intel® Developer Cloud for oneAPI to run code samples on the latest Intel® oneAPI hardware and software

• Sign up for an Intel® Developer Cloud account—a free development sandbox with access to the latest Intel hardware and oneAPI software.
• Explore oneAPI, including developer opportunities and benefits.
• Subscribe to Code Together, an interview series that explores the challenges at the forefront of cross-architecture development. Each biweekly episode features industry VIPs who are blazing new trails through today’s data-centric world. Available wherever you get your podcasts.

Xinmin Tian

Intel senior principal engineer and compiler architect, Intel Corporation

Xinmin is responsible for driving compiler OpenMP, offloading, vectorization, and parallelization technologies into current and future Intel architecture. His focus is on programming languages for Intel® oneAPI toolkits for CPU and accelerators for Xe architecture, compilers, and application performance tuning. Xinmin holds 27 US patents, has authored over 60 technical papers, and coauthored three books that span his expertise. Xinmin holds a PhD from the University of San Francisco.