Tutorial: Application Development with SYCL

Abstract

Parallel programming with heterogeneous architectures has gained a reputation for being difficult, but is it really? Modern C++ has come a long way to making parallel programming easier, and the SYCL programming model means heterogeneous programming using C++ is now more accessible than ever. SYCL uses modern standard C++, and it’s a programming model that lets developers support a wide variety of devices (CPUs, GPUs, FPGAs, and more) from a single code base. Given the growing heterogeneity of processor roadmaps, moving to an open standard, platform-independent model (without vendor lock-in) is essential for modern software developers. There are multiple implementations of SYCL available including open source projects, and in this tutorial you will join instructors who are developing some of these alongside experienced developers from academic institutions implementing complex SYCL code bases. This tutorial will provide a way for developers to gain expertise with SYCL in a practical environment focused more on writing code than Powerpoint. Attendees will gain a background of how the designers of the SYCL standard have addressed heterogeneous programming in C++ through industry collaboration. SYCL has gained widespread support in recent years and is available on Exascale systems, desktops, embedded systems, FPGAs, and automotive platforms. Regardless of the particular constructs in the future - the material in this course will prove timeless. This course will start by teaching the fundamentals of heterogeneous parallelism using SYCL. It will also teach you how to make use of modern C++ and the SYCL programming model to build parallel algorithms for heterogeneous devices. Most of the programming focus will be on GPUs, but some time will be spent applying the techniques to simple FPGA examples. The course will teach you how to apply some common GPU optimizations.