Explore GPU Acceleration in the Intel® DevCloud

There are scant few “vision-type” applications that can’t reap additional benefits when accelerated for graphics processing units—whether discrete GPUs or integrated multi-component architectures.

This session focuses on how to do exactly that.

How? Using the optimized software tools found in the Intel® oneAPI Base Toolkit coupled with Data Parallel C++ (DPC++), a new language based on familiar C++ and SYCL.

Join software application engineers Anant Sinha and Alberto Villareal for a tour through the entire oneAPI workflow of GPU-focused acceleration, including:

  • Identifying the parts of your code that will benefit from acceleration (Hint: this uses Intel® Advisor’ Offload feature)
  • Creating accelerated software in DPC++
  • Exploring oneAPI accelerated libraries
  • A live demo showing how to optimize the final code result and run it in the Intel® DevCloud on the latest collection of Intel® Processor Graphics Architecture

Get the software

  • Download the Intel® oneAPI Base Toolkit—includes nearly 20 dev tools and libraries for creating cross-architecture applications, including all those showcased in this webinar.
  • Sign up for an Intel® DevCloud for oneAPI account—a free development sandbox with access to the latest Intel® hardware and oneAPI software.

Other resources

  • Learn more about the DPC++ language
  • Learn more about the Intel® oneAPI DPC++ Library
  • Learn about Intel® Advisor’s Offload feature (available as part of the Intel oneAPI Base Toolkit)
  • Subscribe to the POD—Code Together is an interview series that explores the challenges at the forefront of cross-architecture development. Each bi-weekly episode features industry VIPs who are blazing new trails through today’s data-centric world. Available wherever you get your podcasts.
Anant Sinha, Software Applications Engineer, Intel Corporation

Anant is a Software Application Engineer who works with developers, helping them optimize their deep learning and machine learning applications for Intel architectures. Prior to joining Intel in 2018, he spent nearly 10 years as a software product engineer and software developer for Esri, a global market leader in the GIS (geographical information system) framework. Anant holds a bachelor’s in computer science from BITS Pilani, Masters of Engineering in Computer Science from Cornell University and Masters of Science in Computer Science from University of California, Riverside.

Alberto Villareal, Software Applications Engineer, Intel Corporation

Alberto is a software engineer responsible for helping developers optimize their applications to take advantage of parallel architectures. He came to Intel in 2016 with 15 years’ experience in software optimization and algorithm development/analysis in the energy industry. Alberto holds two MSc degrees from the Colorado School of Mines: Mathematics &Computer Science and Geophysics.

Performance varies by use, configuration, and other factors. Learn more at www.Intel.com/PerformanceIndex.