Guest Lecture: Paul Springer

Paul Springer a senior software developer at NVIDIA will give a guest lecture in the class Parallel Computing. The lecture will take place on Thursday, January 11, 2024, from 12:00PM - 02:00PM. The location is HS 235 (Fürstengraben 1). Interested students outside of the class are cordially invited to join. Please write a brief email to alex.breuer@uni-jena.de or in Matrix if you would like to attend and are not part of the Parallel Computing class.

About the speaker: Dr. Paul Springer is a senior software developer at NVIDIA with a strong interest in low-level kernel development and their applications to quantum circuit simulations, computational physics and machine learning. Before joining NVIDIA in 2018, he received his Ph.D. in computer science from RWTH Aachen university where he focused on the development of high-performance tensor operations and dense linear algebra. Nowadays he is primarily tasked with the design of CUDA math libraries—most noticeably cuTENSOR.

AI Summer School 2023

Our lab co-organizes the AI Summer School 2023 which will take place from September 4-8 in Bad Kösen. The program is tailored to bachelor’s and master’s students with previous experience in artificial intelligence and programming. Accommodation and meals of all participants are covered. Additionally, travel support is available for selected participants.

Illustration of the AI Summer School 2023 by DALL-E.

The application process opens on April 1 and closes on May 15. Students at Friedrich Schiller University Jena and Technische Universität Ilmenau are invited to apply. A few spots are available for students enrolled at any other German university.

Summer Semester 2023

Winter is coming to an end and our lab already started preparing the summer semester. This year we will teach the two classes High Performance Computing (HPC) and Efficient Machine Learning (EML). HPC will be in the third instantiation while EML will be offered a second time. We are eager to keep the classes up to date by integrating latest research and technology.

In the case of the HPC class, the Neoverse V1 microarchitecture used in the Graviton3 server processors will be covered in detail. Over the duration of the summer semester, a special emphasis will be put on the newly introduced SVE Bfloat16 vector instructions and their use when writing fast matrix-matrix multiplication kernels.

EML will also receive major updates. First, we will integrate some of the latest features coming with PyTorch 2. Especially the new software ecosystem behind torch.compile is a key development when targeting efficient machine learning. Second, we will extend the class’s scope by also discussing inference on mobile devices. Obtaining high performance on mobile devices typically requires a technique called quantization. Currently, we plan to target the Snapdragon 8 Gen 2 system on chip which is used in latest flagship smartphones. Students will have access to Qualcomm Innovators Development Kits sponsored by Qualcomm.


All Posts