These workshops will cover an overview of the Data Parallel C++ language and oneAPI tools that are created to benefit developers in solving real world problems on heterogenous platforms. This is a great opportunity to meet and collaborate with other developers, learn about oneAPI and DPC++, and code from home while using cutting-edge Intel hardware and software.
Register for all workshops
During this workshop, you will learn about the oneAPI programming model for heterogeneous computing. You will also learn the Data Parallel C++ (DPC++) language and familiarize yourself with Jupyter notebooks on Intel DevCloud.
1. We will go in-depth on SYCL fundamental classes and device selection to offload kernel workloads.
2. You will learn new Data Parallel C++ (DPC++) features such as Unified Shared Memory and subgroups.
3. The oneAPI DPC++ Library (oneDPL) will be introduced to simplify programming by using DPC++ Library algorithms.
DPC++ provides developers with the ability to write standard C++ code for heterogeneous systems, and accelerate execution using a range of different processors including CPUs, GPUs and FPGAs. In this session you will learn:
1. Best practices for using Intel® Data Parallel C++ Compatibility Tool, a one-time migration tool that migrates CUDA applications into standards-based Data Parallel C++ (DPC++) code.
2. How to use the oneAPI features that focus on performance optimization using analysis tools including Intel® VTune™
In this tutorial, you will learn to write and compile Data Parallel C++ (DPC++) code to target an Intel® FPGA. You will learn and practice the development flow to (1) emulate your code to ensure functionality, (2) optimize your code using reports, and (3) generate and profile the hardware bitstream created from your code.
Please choose the webinar(s) you would like to register for: