oneAPI is a unified programming model to optimize performance for a wide range of data-centric workloads across scalar, vector, matrix and spatial architectures, deployed in CPU, GPU, AI, FPGA and other accelerators. It includes the programming language, Data Parallel C++ and libraries that, together, deliver parallel programming productivity, and cross-architecture application performance while providing an alternative to single architecture programming approaches.
Required Fields(*)
09:00am - Welcome and Check-in
09:30am - Introduction to the Intel oneAPI beta product
10:00am - Module 1: DPC++ fundamentals
10:45am - Break
11:00am - Module 2: Deeper dive (part 1) on DPC++, the programming model
11:45am - Module 3: Deeper dive (part 2) on DPC++, memory considerations per device, device flows
12:30pm - Lunch
1:30pm - Module 4 : Cover DPC++ interop with other libraries and performance analysis
2:15pm - Module 5 : Introduction to the parallel standard-libraries
3:00pm - Break
3:15pm - Module 6 : Programming FPGA with oneAPI
4:15pm - Module 7 : Further examination of task-parallel and data-parallel working in concert
5:00pm - Summary, Drinks and Feedback
6:00pm - Close
Level 39
One Canada Square, Canary Wharf
London, UK, E14 5AB