Hands-on ® Development & oneAPI WORKSHOP

May 26-27, 2020 Scandic Solli, Parkveien 68 Box 2458 Solli, 0202 Oslo

AGENDA DAY 1 - Technical Computing & Developer Tools - May 26

Timing Sessions

08:30 – 09:00 Registration & Light breakfast

Part 1: Coding for maximum performance using the new Intel® Parallel Studio XE 2020

A refresher on the Intel® Hardware Architecture for Software Developers and Architects 09:00 -09:45 This session will offer in-depth insights into the current and future Intel® hardware platforms tailored to the needs of software developers, software architects, HPC and AI experts. We will cover the latest Intel® processors and the future Intel® GPU architecture.

Developing code for Intel® architecture: how to achieve maximum performance using the new Intel® Parallel Studio XE 2020 09:45 – 10:30 Learn how Intel® Software Development Tools will help you to achieve optimal performance in your High Performance Computing, Artificial Intelligence ,and IoT projects. Includes a look at the new Intel® Parallel Studio XE 2020 tools which are designed to take advantage of the latest generation of Intel processors.

10:30 – 11:00 Coffee Break

How to optimize and maximize code performance Learn how to use some of the advanced features of Intel® VTune™ Amplifier profile your applications. See how you can use event-based and architectural analysis to fine-tune your code so that it is taking full 11:00 – 12:00 advantage of the latest processor features of the target CPU. Learn how to use Intel Advisor, a powerful tool for tracking down and solving vectorization problems. In this session we will demonstrate how the Intel Advisor vector analysis and associated Roofline Model can be used to identify and help fixing vectorization problems.

12:00 – 13:00 Lunch break

Part 2: Introducing Intel® oneAPI

Software Developers: what you need to know about the Intel OneAPI project Hear about the latest update on the “Intel OneAPI” project: a unified programming model to simplify application 13:00 – 13:30 development across diverse computing architectures. One API supports direct programming and API programming, and will deliver a unified language and libraries that offer full native code performance across a range of hardware, including CPUs, GPUs, FPGAs and AI accelerators.

Offload Advisor: How to decide which parts of the code need to be offloaded? Learn how to use the Offload Advisor, a tool that allows you to collect performance predictor data in addition to 13:30 – 14:15 the profiling capabilities of Intel® Advisor, and determine what code can be offloaded to a GPU, accelerating the performance of your CPU-based application.

14:15 – 14:45 Coffee break

Introduction to Data Parallel C++ (DPC++) Data Parallel C++ is the language of oneAPI targeting multiple architectures, including CPU and compute accelerators like GPUs and FPGAs. It provides features needed to define data parallelfunctions and to launch 14:45 – 16:30 them on different processing devices.

Learn DPC++ programming basics on a simple vector addition example and dive deeper into programming in DPC++, including best practices you can put to use today and the iso3DFD* demo.

16:30 – 18:30 Networking with drinks and snacks

Hands-on Intel® Software Development & oneAPI WORKSHOP

May 26-27, 2020 Scandic Solli, Parkveien 68 Box 2458 Solli, 0202 Oslo

AGENDA DAY 2 – Artificial Intelligence & Machine Learning – May 27

Timing Sessions

8:30 – 9:00 Registration & Light breakfast

Getting deeper into the Intel® AI Software Stack for Developers & Data Scientists 09:00 -09:30 Optimized Software for Deep Learning and Machine Learning. Stephen Blair-Chappell, Technical Director, Bayncore Labs

Faster Machine Learning and Deep Learning training with optimized Frameworks (part 1) See how the Intel optimized frameworks can be used for Deep Learning training on Intel CPU based 09:30 – 10:30 platforms. In this session, we show and discuss the advantages of running the frameworks on Intel architecture Jimmy Kromann, Senior Consultant, Bayncore Labs

10:30 – 11:00 Coffee Break Faster Machine Learning and Deep Learning training with optimized Frameworks (part 2) 11:00 – 12:30

12:30 – 13:30 Lunch break

Deep Learning Inference on Intel® with the OpenVINO™ Toolkit In this session, we will introduce the OpenVINO™ Toolkit. This toolkit provides flexibility and availability to the developer community to accelerate the development of 13:30 –15:00 and Deep Learning workloads. It enables high-performance computer vision and deep learning inference with easy heterogeneous execution across multiple types of Intel® platforms. During this session, we will show use cases of this toolkit in different segments such as industry, healthcare, and digital surveillance. Stephen Blair-Chappell, Technical Director, Bayncore Labs

15:00 - 15:30 Coffee break

15:30 - 16:15 Deep Learning Inference on Intel® with the OpenVINO™ Toolkit - Continued

16:15 – 16:30 Q&A

In partnership with: