High Performance Computing Center North
This two days workshop is arranged together with PRACE, and will have instructors from Intel. The course focuses on programming and optimizing the Intel ® Xeon Phi™ Manycore Processor, codenamed "Knights Landing (KNL)" and how to best use it efficiently.
While code examples will be profiled on KNL processors, all methods can be applicable to other architectures as well, for instance Intel Broadwell. Therefore, also codes using CPU+GPU programming models can benefit from the present course by optimizing the code running on the chip - optimization which is in many cases overlooked.
The course is thus relevant to many different groups of people, including HPC users and researchers who want to get as much as possible possible out of their architecture. Also, the course is of interest for anyone who wants to increase their knowledge about vectorization and optimization, and learn more about how to apply it to their own codes.
Day 1 (KNL architecture, KNL configuration: memory and cluster modes, Intel® Software tools, exercises)
Participation is free. Please bring your own laptop if you wish to participate in the hands-on!
The hands-on will be done on HPC2N's systems, so you will need to have an account at HPC2N (or create one when added to the course project) in order to participate in that part.
Lunch and coffee/tea will be provided both days.
Prerequisites: The participants are expected to have a basic knowledge of programming.
Instructors: Mikko Byckling and Asma Farjallah from Intel.
Time and date: 24-25 April 2018. 1 day: 9:00-17:15, 2 day: 9:00-15:30.
Location: MIT-Huset. Day 1: room MC313, Day 2: room MC413 (Directions to MIT huset here).
Deadline for registration: 16 April 2018
Please register using this form. All fields marked with * are mandatory. Registration is closed! Contact firstname.lastname@example.org if you wish to participate.