oneAPI and DPC++ Aurora Learning Paths Webinars
This new training series of webinars will help attendees advance the development of applications for Argonne’s upcoming Intel-HPE exascale supercomputer.
An increasingly diverse number of computing platforms – featuring multiple generations of CPUs, GPUs, and FPGAs – offer developers greater choice in their high-performance computing applications. However, without understanding the big picture as well as the nitty-gritties, these choices can increase the amount of time required to develop code that’s performant and portable across platforms.
To help developers learn how to reduce the time they spend coding, the Argonne Leadership Computing Facility (ALCF) partnered with Intel to produce this webinar series, Aurora Learning Paths: Performance, Portability, and Productivity
The series, led by Rakshith Krishnappa, Developer Evangelist and Software Engineer at Intel, explored the use of oneAPI and Data Parallel C++ (DPC++), Intel’s open source implementation of SYCL, to demonstrate methods that can deliver performant, portable code across five platforms available on the Intel Devcloud.
oneAPI is an open, unified and cross-architecture programming model for CPUs and accelerator architectures. Its standards-based model simplifies software development, enables legacy code integration, and delivers uncompromised performance for accelerated compute without proprietary lock-in. With oneAPI, developers can choose the best architecture for their solution without rewriting software for the next architecture and platform.
View Aurora Learning Paths Sessions
Module 1: Introduction to Performance, Portability, and Productivity for HPC
View Video and Slides
In this session, you’ll get introduced to Data Parallel C++ and the importance of performance, portability, and productivity for HPC development. You’ll also learn how to set up a Jupyter Lab environment for training, which allows hands-on compilation and execution of simple DPC++ code samples.
Module 2: Optimization Best Practices Using SYCL
View Video and Slides
In this session, Rakshith Krishnappa presents a DPC++ code walk-through of a simple matrix multiplication example, and explains how one can optimize the code for performance using various features of DPC++. We’ll also compare the execution times of various optimizations.
Module 3: Using Analysis Tools for Portable Offload to CPU or GPU
View Video and Slides
In this session, Rakshith Krishnappa covered how to optimize code for portability to gain the best performance regardless of whether the code is offloaded to GPU or CPU. You’ll also learn about Intel VTune and Intel Advisor Roofline analysis for various optimizations.
Module 4: Mini Hackathon
View Video and Slides
Learn from this mini hackathon session by watching how Rakshith Krishnappa, along with Intel code developers and ALCF staff experts, assisted the participants in this rare hands-on opportunity.
Get Involved and Review the oneAPI Specification
Learn about the latest oneAPI updates, industry initiative and news. Check out our videos and podcasts. Visit our GitHub repo – review the spec and give feedback or join the conversation happening now on our Discord channel. Then get inspired, network with peers and participate in oneAPI events.
Oak Ridge National Laboratory Establishes oneAPI Center for Excellence
Dr. Zheming Jin, a research scientist at Oak Ridge National Laboratory (ORNL), is leading ORNL’s effort to study how various approaches to parallel programming, including...
Porting NAMD to oneAPI DPC++
Intel’s Gamble on oneAPI and DPC++ for Parallel Processing and Heterogeneous Computing: An Interview with Intel’s James Reinders
