Programming heterogeneous environments with Intel oneAPI

Course/Event Essentials

Event/Course Start
Event/Course End
Event/Course Format
Mixed
Live (synchronous)

Venue Information

Country: Czech Republic
Venue Details: Click here

Training Content and Scope

Scientific Domain
Level of Instruction
Beginner
Intermediate
Sector of the Target Audience
Research and Academia
Industry
Public Sector
HPC Profile of Target Audience
Application Developers
Language of Instruction

Other Information

Supporting Project(s)
EuroCC/CASTIEL
Event/Course Description

Annotation

The NCC Czech Republic and Intel are inviting you to a three-day event dedicated to oneAPI. Join Intel and leading oneAPI professionals for this hands-on workshop. Learn how to accelerate your code while avoiding vendor lock-in using oneAPI on CPUs, GPUs/FPGAs.

At the end of this workshop, you will:

•    Understand the importance of using open standards in programming for Heterogeneous systems
•    Learn how to use oneAPI / SYCL / DPC++ to offload code to various accelerators including CPU and GPU
•    Be able to use the compatibility tool to help port CUDA code to SYCL/DPC++
•    Be able to profile code running on various accelerators and assess their performance/efficiency 
•    Know how to use the Intel DevCloud as a ready-to-use sandbox in developing your codes.

Level

beginner

Language

English

Prerequisites


Ideally, you should have some moderate experience in using Python, C++, and (optionally) CUDA.

Program

(For detailed agenda including times see Timetable.)

DAY 1 – THEME:  PROGRAMMING WITH ONEAPI

Morning 

Introduction to practical programming with oneAPI. Topics include:

  • Introduction to oneAPI and DevCloud infrastructure
  • Programming CPU/GPU using SYCL
  • Porting CUDA code to SYCL using the Compatibility Tool

Afternoon

  • Online Q&A with an oneAPI Center of Excellence (TBD)
  • Hands-on with Compatibility Tool 
  • Additional lab time / individual help (optional) 

DAY 2 – THEME:  PERFORMANCE LIBRARIES AND PROFILING

Morning

Performance, performance, performance

  • Libraries : oneDPL, oneTBB, oneMKL
  • Profiling and perf analysis with Vtune / Advisor

Afternoon

  • Online Q&A with oneAPI Center of Excellence (TBD)
  • Hands-on VTune
  • Additional lab time / individual help (optional) 

DAY 3

Bring your own code (for preselected participants)
Start offloading your code in a vendor-independent way here and now with the help of Intel experts

About the tutors

Stephen Blair-Chappell is an independent software consultant and is an Intel-certified oneAPI instructor.  He was formerly the Technical Director at Bayncore where he led a team of consultants providing HPC and AI training on Intel Architecture. For 18 years he was a Technical Consulting Engineer at Intel helping their strategic customers in software optimization and code modernization.   He is the author of the book "Parallel Programming with  Intel Parallel Studio XE". 

Georg Zitzlsberger is a research specialist for Machine and Deep Learning at IT4Innovations. He has for over three years been certified by NVIDIA as a University Ambassador of the NVIDIA Deep Learning Institute (DLI) program. This certification allows him to offer NVIDIA DLI courses to academic users of IT4Innovations' HPC services. In addition, in collaboration with Bayncore, he is a trainer for Intel HPC and AI workshops and conferences carried out across Europe. He has been contributing to these events, which are held for audiences from industry and academia, for five years.

Soner Steiner is an HPC, HPDA, and IA specialist at Vienna Scientific Cluster (VSC) and is involved in the EuroCC-Austria project (a European network for awareness creation, consultancy, and training in HPC). He has 5 years of teaching experience at the university level (University of Applied Science, Austria-Wiener Neustadt). At VSC he is involved in training and consultancy of academia and industry. Before his role at the VSC, he was involved for several years in computational material science. And he is freshly a certified Intel oneAPI instructor in DPC++ essentials, OpenMP offload basics, and ML using oneAPI.

Gennady Fedorov is an Intel Technical Consulting Engineer in the field of Intel(R) Performance ( Math Kernel Library(MKL), Performance Primitives (IPP), and Data Analytic Acceleration (DAAL)) Libraries. Gennady holds a Ph.D. in Nuclear Physics from the Russian National Research Nuclear University.

Dmitry Sivkov is an Intel Technical Consulting Engineer with more than 20 years of experience in Computer Sciences and HPC. He has a Ph.D. in Applied Math. Dmitry is enabling and supporting Intel Cluster Tools for 11+ years with a lot of projects with Data Centers, Clouds, and HPC clusters.

Acknowledgments       

This event is supported by Intel.

                                      

This event was supported by the EuroCC project. This project has received funding from the European High-Performance Computing Joint Undertaking (JU) under grant agreement No 951732. The JU receives support from the European Union’s Horizon 2020 research and innovation programme and Germany, Bulgaria, Austria, Croatia, Cyprus, the Czech Republic, Denmark, Estonia, Finland, Greece, Hungary, Ireland, Italy, Lithuania, Latvia, Poland, Portugal, Romania, Slovenia, Spain, Sweden, the United Kingdom, France, the Netherlands, Belgium, Luxembourg, Slovakia, Norway, Switzerland, Turkey, Republic of North Macedonia, Iceland, Montenegro. This project has received funding from the Ministry of Education, Youth and Sports of the Czech Republic (ID:MC2101).