10 months ago
The Argonne Leadership Computing Facility
(ALCF) in partnership with Intel will host a hands-on learning series
that will explore the use of oneAPI and Data Parallel C++ (DPC++),
Intel's open-source implementation of SYCL, to demonstrate methods to
achieve performant, portable code across five different platforms
available on the Intel Devcloud.
The virtual series is scheduled Wednesdays from 1:00 - 3:00 p.m. US Central.
- Module 1: Jan. 12, 2022, 1:00-3:00 p.m.
- Module 2: Feb. 9, 2022, 1:00-3:00 p.m.
- Module 3: Mar. 9, 2022, 1:00-3:00 p.m.
- Module 4: Mar. 16, 2022, 1:00-3:00 p.m.
Module 1 Introduction to Performance, Portability, and Productivity for HPC In this session we will introduce you to Data Parallel C++ and the importance of performance, portability, and productivity for HPC development. We will set up a Jupyter Lab environment for training, which will allow hands-on compilation and execution of simple DPC++ code samples.
Module 2 Optimization Best Practices Using SYCL/DPC++ In this session we will present a DPC++ code walk-through of simple matrix multiplication example, and look at how we can optimize the code for performance using various features of DPC++. We will compare the execution times of various optimizations.
Module 3 Using Analysis Tools for Portable Offload to CPU or GPU In this session we will learn how to optimize the code for performance portability so that we get best performance regardless of whether the code is offloaded to GPU or CPU. We will look at Intel VTune and Intel Advisor Roofline analysis for various optimizations.
Bring your own code; staff will be on hand to assist.