Популярное

Музыка Кино и Анимация Автомобили Животные Спорт Путешествия Игры Юмор

Интересные видео

2025 Сериалы Трейлеры Новости Как сделать Видеоуроки Diy своими руками

Топ запросов

смотреть а4 schoolboy runaway турецкий сериал смотреть мультфильмы эдисон
dTub
Скачать

(Co-)designing a European CPU for HPC/AI

Автор: NHR@FAU

Загружено: 2024-11-29

Просмотров: 507

Описание:

NHR PerfLab Seminar talk on October 29, 2024

Speaker: Prof. Dr. Estela Suarez from SiPearl

Slides: https://hpc.fau.de/files/2024/11/2024...

Abstract:
Developing high-end processors for the HPC and AI markets is an extremely complex and high-risk endeavor, requiring both large economic investments and a wide range of complementary expertise. For the first time in more than two decades, this challenge is being tackled in Europe, with technological sovereignty as a key objective. SiPEARL’s Arm-based Rhea product line aims to deliver high application efficiency with CPUs characterized by a design balancing memory bandwidth and computing power. The development of Rhea started within the EPI project, a European funded research project with more than 30 partners, in which the Jülich Supercomputing Centre played a leading role in co-design activities.

In this talk, we will present the motivation behind and the path towards the first generation of HPC-oriented CPU designs in Europe, as well as our experience in co-design at processor level, based on gem5 simulations of the chip architecture. We will discuss examples of our gem5 studies, present the Rhea architecture, and share some of the experiences gathered in the interaction between modeling experts and chip designers.

Short bio:
Prof. Dr. Estela Suarez is Senior Principal Solution Architect at SiPearl. She took this role in September 2024, taking a sabbatical from her positions as Joint Lead of the department Novel System Architecture Design at the Jülich Supercomputing Centre, and Associate Professor for High Performance Computing at the University of Bonn. Her expertise is in HPC system architecture and codesign. As leader of the DEEP project series, she has driven the development of the Modular Supercomputing Architecture, including the implementation and validation of hardware, software, and applications. In addition, she has been leading the codesign efforts within the European Processor Initiative since 2018. She holds a Master’s degree in Astrophysics from the University Complutense of Madrid (Spain) and a PhD in Physics from the University of Geneva (Switzerland).

For a list of past and upcoming NHR PerfLab seminar events, see: https://hpc.fau.de/research/nhr-perfl...

(Co-)designing a European CPU for HPC/AI

Поделиться в:

Доступные форматы для скачивания:

Скачать видео mp4

  • Информация по загрузке:

Скачать аудио mp3

Похожие видео

Neuromorphic Computing from the Computer Science Perspective – Algorithms and Applications

Neuromorphic Computing from the Computer Science Perspective – Algorithms and Applications

The Genius of RISC-V Microprocessors - Erik Engheim - ACCU 2022

The Genius of RISC-V Microprocessors - Erik Engheim - ACCU 2022

Exploring Compilers for HPC

Exploring Compilers for HPC

Architecture All Access: Modern CPU Architecture 2 - Microarchitecture Deep Dive | Intel Technology

Architecture All Access: Modern CPU Architecture 2 - Microarchitecture Deep Dive | Intel Technology

Neuromorphic Computing: Object Tracking using Event-based vision

Neuromorphic Computing: Object Tracking using Event-based vision

Slinky: Slurm in Kubernetes, Performant AI and HPC Workload Management in Kubernetes - Tim Wickberg

Slinky: Slurm in Kubernetes, Performant AI and HPC Workload Management in Kubernetes - Tim Wickberg

Как крутят нейронки на периферийных устройствах / База по Edge Computing от инженера из Qualcomm

Как крутят нейронки на периферийных устройствах / База по Edge Computing от инженера из Qualcomm

These Computers Changed the World

These Computers Changed the World

Do we really need NPUs now?

Do we really need NPUs now?

Explaining RISC-V: An x86 & ARM Alternative

Explaining RISC-V: An x86 & ARM Alternative

Почему НЕЛЬЗЯ использовать бесплатный ВПН? Разбор специалистом по кибербезопасности

Почему НЕЛЬЗЯ использовать бесплатный ВПН? Разбор специалистом по кибербезопасности

Intel Supercomputing 2022 Keynote: Maximize Possibilities for High Performance Computing & AI

Intel Supercomputing 2022 Keynote: Maximize Possibilities for High Performance Computing & AI

UCIe™ (Universal Chiplet Interconnect Express™)

UCIe™ (Universal Chiplet Interconnect Express™)

Чем ОПАСЕН МАХ? Разбор приложения специалистом по кибер безопасности

Чем ОПАСЕН МАХ? Разбор приложения специалистом по кибер безопасности

Самая сложная модель из тех, что мы реально понимаем

Самая сложная модель из тех, что мы реально понимаем

Google’s Chip Designing AI

Google’s Chip Designing AI

Стратегии англосферы в условиях кризиса меняющегося миропорядка | Олег Яновский

Стратегии англосферы в условиях кризиса меняющегося миропорядка | Олег Яновский

AI Hardware: Training, Inference, Devices and Model Optimization

AI Hardware: Training, Inference, Devices and Model Optimization

2024 High Performance Computing Lecture 0 Prologue Part One 💻

2024 High Performance Computing Lecture 0 Prologue Part One 💻

Quantum computing with Schrödinger cat states

Quantum computing with Schrödinger cat states

© 2025 dtub. Все права защищены.



  • Контакты
  • О нас
  • Политика конфиденциальности



Контакты для правообладателей: [email protected]