TU Berlin

Architektur eingebetteter SystemeArchitektur eingebetteter Systeme

AES Logo


zur Navigation

Willkommen bei AES


Das Fachgebiet Architektur Eingebetteter Systeme (AES) beschäftigt sich in Forschung und Lehre mit allen Bereichen der Rechnerarchitektur, von energieeffizienten Systemen bis hin zu massiv parallelen Hochleistungsrechnern. Dabei liegt der Schwerpunkt auf dem Entwurf und der Implementierung von hochperformanten eingebetteten Systemen, bei denen Anwendungsanforderungen mit neuartigen Architekturen optimal in Einklang gebracht werden sollen. Zusätzlich befassen wir uns mit der Verbesserung von Energieeffizienz, Programmierbarkeit, Vorhersagbarkeit und Fehlertoleranz moderner Prozessorarchitekturen.


AES paper accepted at ARCS 2022


[aes/dm,fbk] The paper "Effects of Approximate Computing on Workload Characteristics" has been accepted for publication at the ARCS 2022.

The paper studies how Approximate Computing fundamentally affects the core of workload characteristics and proposes a holistic approach of both traditional software optimizations and approximate computing techniques.

The ARCS conference has over 30 years of tradition reporting leading edge research in computer architecture and operating systems. This years' edition is taking place in Heilbronn, Germany on September 13-15.

AES paper accepted at Euro-Par 2021

Euro-Par Logo

[aes/dm,fbk] The paper "ALONA: Automatic Loop Nest Approximation with Reconstruction and Space Pruning" has been accepted as full paper at the International European Conference on Parallel and Distributed Computing.

This work is authored by Daniel Maier, Biagio Cosenza (University of Salerno) and Ben Juurlink and presents a novel approach for automatic loop nest approximation based on a polyhedral compilation.

Euro-Par is the prime European conference covering all aspects of parallel and distributed processing. The 27th edition of Euro-Par will take place from 30 August – 3 September 2021 as hybrid event in Lisbon, Portugal.

13.11.2020: Paper accepted at DATE'21


The paper "QSLC: Quantization-Based, Low-Error Selective Approximation for GPUs" by Sohan Lal, Jan Lucas, and Ben Juurlink has been accepted for publication at DATE 2021. The paper proposes a simple quantization-based selective approximation technique that has 5x lower error and 7.6x lower area than the state-of-the-art.

DATE is the top scientific event in Design, Automation, and Test of microelectronics and embedded systems for the academic and industrial research communities worldwide. The 2021 edition of the conference will take place from Februrary 01-05, 2021, in Grenoble, France.

More information can be found at www.date-conference.com

Noch mehr News finden Sie hier



Schnellnavigation zur Seite über Nummerneingabe