Hands-on Intel® Software Developer Workshop for Technical Computing and Artificial Intelligence
Hands-on Developer Workshop for Parallel Programming and Deep Learning with Intel® Software
Two Days of deep-dive hands-on training sessions with Intel experts.
Following a series of technical workshops on Parallel Programming and Deep Learning with Intel® Software, we are now going to the next level with the first hands-on workshop where you’ll have the opportunity to try all the software and programming techniques by yourself on your own laptop, guided by the experts.
Please bring your own – Intel®-based – laptop*, we’ll provide all required software and technology. Detailed technical requirements will be sent to the registered attendees.
Date: 28. & 29. November 2018
Venue: Hammarby Kaj 10D, Internetstiftelsen i Sverige (IIS), 120 30 Stockholm
Day 1: Code Modernization for Intel Architecture
When it comes to improve application performance, one needs to re-architect and/or tuning existing code to expose enough vectorization and parallelism. In this workshop we will dive into the code modernization framework. This results in a systematic approach which needs to be followed to achieve the highest performance possible. With the help of examples, use cases and a better usage of the Intel® C/C++ compiler, we pinpoint you to possible inefficiencies both on sequential and vectorized code and we explain remedies, hints and strategies to be considered to ensure an application delivers great performance on today’s scalable hardware and upcoming future generations.
AGENDA DAY 1**
08:00-09:00 Registration with light breakfast
9:00-10:00 Introduction to Intel tools
This session will introduce intel tools and the different suites available for writing codes for single or multi-nodes computers as well as analyzing the performance.
10:00-10:30: Login to GCP
11:00-12:00: Compiler Based Optimization - nbody - part 1
This session will drive the user into many compilers based optimizations. Step by step, the attendee will be able to understand how to modify the code and the compiler arguments to achieve a great performance.
13:00-15:00 Compiler Based Optimization - nbody - part 2
This session will drive the user into many compiler based optimizations. Step by step, the attendee will be able to understand how to modify the code and the compiler argumuments to achieve a great performance.
15:30-16:30 OpenMP for Threading and Vectorization
Modern architectures offers many way to greatly speedup your applications. Parallelism is one of them. On a single node point of view, parallelization can be achieved by threading and vectorization. This presentation will explain how to create threaded and vectorized workload with OpenMP.
16:30-17:00 Memory Optimization (Cache Blocking) - iso3dfd
Moving data in an efficiçent way is a crictical point when it is about HPC. Many HPC applications tends to be memory bounded and it is alway a good practice to verify that memory accesses are hadware frendly and that we reuse as much data from the cache as it is possible.
17:00-18:00 Intel VTune optimization - iso3dfd
This session will drive the user from an unoptimized version of a wave propagation kernel to a much more optimized version. We will see on a real world example how to detect bottlenecks and how to optimize them.
18:00-19:00 Get-together Networking evening with drinks & food
Day 2 Performance Optimization, Artificial Intelligence and Machine Learning
The second day morning session will be about the analysis tool Intel® Advisor and how it gives software architects and developers they need to build well-threaded and vectorized code that exploits modern hardware capabilities. The sessions before lunch will focus on Artificial Intelligence and Deep Learning with TensorFlow. In the afternoon a business case with Machine Learning will discussed and finished with a deep-dive in OpenVINO.
AGENDA DAY 2**
08:00-09:00 Registration with light breakfast
09:00-10:00 Intel Advisor – nbody
Intel Advisor is a powerful tool for tracking down and solving vectorization problems. This presentation will introduce Intel Advisor and especially the survey and the trip count analyses. We will explain how to read Advisor's outputs to improve the vectorization.
10:00-10:30 Presentation AI
11:00-12:00 Deep Learning for image classification
In this session, we'll use TensorFlow with Keras in order to train a neural network for image classification.
13:00-15:00 Credit card fraud detection with Scikit-Learn & TensorFlow
Credit card fraud is an issue that retailers and many other businesses face. Machine Learning can be used to mitigate this problem. In this lab, we’ll use different supervised algorithm to detect fraud with a Kaggle dataset. We’ll use Logistic regression, neural networks, random forest and gradient boosting to predict frauds. We’ll also try unsupervised learning techniques such as K-Means clustering and see how they compare with supervised learning algorithms. We’ll show how Intel has optimised the underlying libraries (TensorFlow and Scikit-Learn) with the MKL and the DAAL and how much speed we get from those optimisations.
In this session, we'll present OpenVINO, a framework to develop multiplatform computer vision solutions. We'll explain how the Model Optimizer can be used to speedup your inference on various hardware.
16:30-17:00 Q&A Open discussion
During the workshop, we will provide to the attendee’s access to the Skylake processors and Intel® tools using VM instances offered by Google Cloud Platform. Attendees should be comfortable with either C/C++ or Fortran programming language and basic Linux command, like make and ssh. No previous experience in vectorization and parallelization is required and profiling tools, as well.
Date & Time:
Wednesday, November 28th
8.00 – 19.00
Thursday, November 29th
8.00 – 17.00
Location: Hammarby Kaj 10D , Internetstiftelsen i Sverige (IIS), 120 30 Stockholm
* Other names and brands may be claimed as the property of others.
** Agenda is subject to change
Preparation, configuration, and usage of your laptop computer during the workshop is at your own risk. Please note that Intel cannot take on any responsibility for your hardware.
|Event date||28. Nov 2018, 8:00|
|Event End Date||29. Nov 2018, 17:00|