2805 Bowers Ave, Santa Clara, CA 95051 | 408-730-2275
My Colfax  

Learn all about oneAPI from the experts

As the world’s data-centric workloads become more diverse, so do architectures that process that data. The Intel oneAPI project aims to deliver a unified standards-based programming model to simplify application development across diverse computing architectures spanning scalar, vector, matrix, and spatial (SVMS) deployed in CPU, GPU, AI, FPGA, and other accelerators.

While a unified development model can potentially be a game-changer, developers will still need to tune code for the hardware they target.

Get the skills you need to program in a heterogeneous world

In partnership with Intel, Colfax has been a leading provider of code modernization and optimization training (the HOW Series). We are excited to be leading the way with training for oneAPI and Data Parallel C++ (DPC++). The training includes access to Intel® DevCloud providing you with the hardware and software to try oneAPI/DPC++ easily (you can also download and use the tools on your own system).

Included in our experts for oneAPI and DPC++, is James Reinders (retired from Intel and also one of the co-authors on an upcoming book on DPC++) who has an impressive track record of teaching parallel programming and supercomputer-know-how. Together we are excited to bring advanced training on oneAPI and DPC++ on the web, cloud, classrooms, or on-premise to suit your needs.

Contact us for more information

Training Modules

The following training modules are available now.

Getting Started with oneAPI

  1. Programming in a heterogeneous world
  2. How oneAPI addresses our heterogeneous world
  3. Hello Doubler - simple DPC++ coding example
  4. What is SYCL?
  5. DevCloud - Try oneAPI easily
  6. oneAPI - Why and how
  7. What is Data Parallel C++?

Watch the video

Download Module 1 Slides

Introduction to DPC++

  1. DPC++, SYCL, C++, and a heterogeneous universe
  2. Anatomy of a DPC++ program
  3. Hello Doubler - DPC++
  4. Device selection in DPC++
  5. DPC++ - Standards-based cross-architecture language
  6. Why not an existing language?
  7. What is Data Parallel Computing?

Watch the video

Download Module 2 Slides

Fundamentals of DPC++

  1. DPC++ programs
  2. Execution model
  3. Where and how to get and use DPC++
  4. id, item, nd_item
  5. Lab exercise: stencil code
  6. Host/Accelerator model
  7. VTune for probing
  8. Heirarchical parallelism
  9. Launching kernels with dependencies

Watch the video

Download Module 3 Slides

Download Module 4 Slides

Future Training Modules

Future training modules (coming up in 2020) will dive into more detail on DPC++ and oneAPI, with topics including event handling, optimizing for CPU/GPU/FPGA, and oneAPI libraries.

Exclusive Advanced Preview of Upcoming Book

Intel Corporation’s partnership with the Apress Open Access program introduces a brand new title, Data Parallel C++: Mastering DPC++ for Programming of Heterogeneous Systems Using C++ and SYCL. This book is first-to-market on DPC++ and is an excellent complementary resource to the Colfax training. The full book will be available in mid-2020, and the authors from Intel have just released the first four chapters in advance for free download.

Download the first four chapters

Inquiry Form

* First Name
* Last Name
* Email
* Telephone
* Company Name
* Title
* Company Address
* Country
* State/Province
* City
* Zip/Postal Code
* I'm interested in

leave this field blank 

Intel, the Intel logo, are trademarks or registered trademarks of Intel Corporation in the U.S. and/or other countries.
* Other names and brands may be claimed as the property of others.