Effective High-Performance Computing & Data Analytics with GPUs
Applications for this program are now closed
The Swiss National Supercomputing Centre (ETH Zurich / CSCS) and Università della Svizzera italiana (USI) are pleased to announce that the annual Summer School will be held as an online course this year, from July 19 to 30, 2021.
The course will last two weeks (weekends excluded) and will be held between 9:00 and 15:30 (/16:30 on the last day) CEST (Central European Summer Time). In case of a large number of high-quality applications, in order to support students in their learning process with the resources that are available, we will have to divide the selected applicants in two separate groups (additional information is available under the section “Course Structure” below).
This summer school will focus on the effective exploitation of state-of-the-art hybrid High-Performance Computing (HPC) systems with a special focus on Data Analytics. The content of the course is tailored for intermediate graduate students (3rd year Bachelor's students, Master’s students, Ph.D students, and early stage Postdocs) interested in both learning parallel programming models, and having hands-on experience using HPC systems. Starting from an introductory explanation of the available systems at CSCS, the course will progress to more applied topics such as parallel programming on accelerators, code optimization, scientific libraries, and deep learning software frameworks.
The following topics will be covered:
- GPU architectures
- GPU programming (CUDA and OpenACC)
- Performance optimization and scientific libraries (Kokkos)
- Interactive supercomputing (JupyterLab)
- Python HPC libraries (Numpy/SciPy/Dask/Numba)
- Introduction to Machine Learning and GPU optimized frameworks (Rapids)
- Deep Learning on HPC platforms (TensorFlow)
Lectures will be held by ETH Zurich / CSCS, USI, UNIL and NVIDIA.
Extensive lab sessions will help to clarify and consolidate the theoretical material. The virtual training will be composed of lectures and interactive sessions for hands-on, as well as Q&A. We are aiming at limiting the lectures to 50% so as to have enough time for hands-on; however, the mileage may vary depending on the topic.
The course will last two weeks (weekends excluded) and will be held between 9:00 and 15:30 (/16:30 on the last day) CEST (Central European Summer Time). In case of a large number of high-quality applications, in order to support students in their learning process with the resources that are available, we will have to divide the selected applicants in two separate groups:
1- Group 1: the first group will follow the lectures live and participate live in the hands-on exercises. As they are following live, they will be able to ask for assistance from lecturers as needed. Group 1 students are expected to attend all the live classes on the program (every day - 9:00 - 15:30). This group will have the possibility to take an exam on the last day of the course and students are eligible to receive ECT credit points from Università della Svizzera italiana, provided that they pass the exam. In case of a large number of high-quality applications, priority to attend this program will be given to students in the same time-zone.
2- Group 2: the second group has the possibility to follow the lectures either via live streaming, or as recorded sessions; however, these students will have to wait until 16:00 CEST to ask their questions. Each day, we will reserve a one-hour slot (16:00-17:00 CEST) where lecturers will be available to answer questions coming from students of this group. We imagine that students living in a different time zone will benefit from this schedule. These students are also eligible to take the exam for earning the ECT credit points. The exam will be held on Friday, July 30, at 13:30 CEST (Central European Time).
Students will be able to earn ECTS credit points for this course (subject to online exam) from the Faculty of informatics at Università della Svizzera italiana (USI) in Lugano, Switzerland: https://search.usi.ch/courses/35262228/effective-high-performance-computing-data-analytics-summer-school
The examination method will be a quiz on the last day of the summer school program - Friday, July 30, at 13:30 CEST (Central European Summer Time). The quiz will be done on iCorsi and covers all objectives and content of the course. It will include closed-ended questions (which will then be assessed automatically by the system) and open-ended questions (which will be assessed by the lecturers and professors). Students will be notified about the result of the examination by Wednesday August 4, 2021.
Students who successfully pass the exam will receive a "confirmation of participation and exam certificate" for this course.
The target audience is intermediate graduate students, which includes 3rd year Bachelor's students, Master’s students, Ph.D students, and early stage Postdocs.
Applicants have to meet the following requirements:
- Good knowledge of C/C++ and basic knowledge of Python
- Basic understanding of MPI
- Familiarity with the UNIX/Linux OS and the basic programming environment tools (terminals, editors, compilers)
- Require HPC skills for their work or research
Only applicants who satisfy all requirements will be considered. Participants will work on their own laptop for practical sessions. Credentials for accessing the machines will be provided to selected students, who will have to confirm their consent to the policy of temporary use of the supercomputer resources and will be asked to provide a document that verifies their identity (the document will be deleted after identity verification).
We are currently processing the applications and we are no longer accepting new ones.
You will be notified about acceptance or rejection of your application by Monday, May 10, 2021.
Those candidates whose application successfully passes the selection process will receive further information regarding registration.
Students from USI and ETH Zurich who are enrolled or have passed the following courses:
will be automatically accepted for the summer school, but still need to confirm their interest in attending by applying by the application deadline. In addition, students from USI have to enroll on the USI teaching platform at USI by April 3, 2021.
Registration for this program is free-of-charge. Mentors and learning materials are offered by CSCS, USI, and NVIDIA.
Candidates whose application successfully passes the selection process will receive further information regarding registration.
Inquiries may be addressed to firstname.lastname@example.org.
The summer school is supported by: