DPC++ Part 1: An Introduction to the New Programming Model

We’re all familiar with C++. But DPC++?

Shorthand for Data Parallel C++, it’s the new direct programming language of oneAPI—an initiative led by Intel to unify and simplify application development across diverse computing architectures.

DPC++ is based on familiar (and industry-standard) C++, incorporates SYCL* specification 1.2.1 from the Khronos Group*, and includes language extensions developed using an open community process. Purposely designed as an open, cross-industry alternative to single-architecture, proprietary languages, DPC++ enables developers to more easily port their code across CPUs, GPUs, and FPGAs, and also tune performance for a specific accelerator.

Tune in for an overview of this new programming model with Michael Kinsner, software engineer at Intel and Khronos Group contributor.

• Get an introduction to the DPC++ programming model, including implementation and memory
• Get details on the fundamental building blocks of the DPC++ programming model, including default selection and queues, buffers, command group function objects, accessors, device kernels, and more
• Learn how to use the DPC++ compiler to build heterogeneous applications
• Explore extensions specific to Intel, such as unified shared memory and subgroups

Other Resources

• Download webinar slides
• Download the first four chapters of a new DPC++ book, written by an expert author team
• Learn more about the oneAPI Initiative
• Explore this initiative led by Intel, including the download of free software toolkits like the essential Intel® oneAPI Base Toolkit, which includes the Intel® oneAPI DPC++/C++ Compiler and libraries. Learn More
• Sign up for an Intel® Developer Cloud account—a free development sandbox with access to the latest Intel® hardware and oneAPI software. No downloads. No configuration steps. No installations.